International Journal of Computer Applications in Technology (85 papers in press)
Non-linear modified equation modeling in dynamical systems (Case Study research on Long Jump patterns)
by Farzad Sharifat
Improving Arabic Text Categorization using FA Words with K-Nearest Neighbor and Centroid-Based classification algorithms
by El-Sayed Atlam, M.E. Abd El-Monsef, O. El-Barbary
3D Scanning Machine and Additive Manufacturing: Concurrent Product and Process Development
by Ismet P. Ilyas
A novel dynamic integrated model for automated requirements in an engineering process
by Mohammed Lafi, Akram Abdel Qader
Abstract: This paper proposes a new dynamic and integrated model to manage the requirements collection process automatically. The result of this paper is to generate an automated requirement template that is compatible with the standard templates and enhances the process accuracy. The proposed model converts the gathered information from a selected requirement collection method into a table format. This table is analysed using the proposed algorithm to generate a normalised table and eliminate the inconsistent requirements. This normalised table is processed using the proposed algorithm to generate one of the standard requirement documentation templates automatically. The proposed model is tested using several requirements collection examples and shows a high accuracy comparing with some manual or automatic methods.
Keywords: software requirements; requirements elicitation; requirements process.
A unified method for services and user interfaces creation: application to persons with special needs
by Hajer Taktak, Faouzi Moussa
Abstract: This paper presents a method for the design and implementation of both services and user interfaces in ubiquitous environments. Communities of designers and developers think separately and generally do not converge. The proposed approach tackles context-awareness at two levels: code behind and user interface generation. Thus, it facilitates the work of designers and developers, limits incompatibility issues and supports dynamic generation of systems. After a deep analysis, we have noticed that both adaptive services and user interfaces design can follow the same creation process with respect to service validation, user and service task analysis and user requirements. The originality of our work comes from the fact that it supports content, service, behaviour and presentation adaptation. It exploits a model-driven approach to consume models and semi-automatically generate codes. We benefit from the pervasive services advantages to manage a complete application after the design phase. We present in this paper the different concepts leading to such a method, a state-of-the-art on existing approaches in the area of context-aware services and user interfaces, and a case study of a mobile application for patients in a retirement home to evaluate the usability of the proposed approach.
Keywords: context; adaptive system; service; MDA; ontology; user model; pervasive system; user interface.
The reference frame alternation strategy in image stabilisation based on error control
by Yang Gao, Xiao-qiang Yang, Yue Ma, Hong-jie Liang, Peng Pei
Abstract: Reasonable selection of reference frame plays a paramount role in the grey-scale projection algorithm. This paper demonstrates the error between vertical direction projection vector, which is calculated by the grey-scale projection algorithm, and angle of pitching, which is measured by an IMU sensor. Afterwards, the algorithm finds the vector and error are dependent. Controlling the vector less than a certain value can make the error stable and small. That is the method to alter the reference frame. Finally, there is an experiment designed to confirm the effect of this method. The result demonstrates that the availability field of view is expanded 2.5 times and the frames stay stable. This demonstrates that the method to alter the reference frame is effective.
Keywords: grey-scale projection algorithm; image electronic stabilization; reference frame; motion estimate.
Determinants of information disclosure intention in mobile commerce: an extended privacy calculus model
by Mutlaq Alotaibi
Abstract: This paper empirically examines a factor model for understanding information disclosure behaviour in the context of mobile commerce (M-commerce). The research model was derived from the privacy calculus model and tailored to fit the context at hand. Four factors were incorporated, namely: privacy awareness (PA), utilitarian benefit (UB), hedonic benefit (HB), and social norms (SN). The PA was theorised to predict privacy risks (PR), both the UB and HB were theorised to determine the perceived benefits (PB), and the SN was theorised to affect the intention to disclose information (IDI). The analysis used survey data gathered from 435 participants by means of an online questionnaire. Results indicated that the model exhibited adequate predictive ability and a considerable goodness of fit with empirical data. More importantly, the new variables were successfully integrated within the privacy calculus model. Furthermore, the addition of the SN seems to eliminate the negative effect of the privacy concerns on IDI.
Keywords: information disclosure; privacy calculus; mobile commerce; awareness; social norms.
Mutually authenticated key agreement protocol based on chaos theory in integration of the internet and MANET
by Atheeq Choudapur, M. Munir Ahmed Rabbani
Abstract: Integrated Internet MANET (IIM) is a heterogeneous network which is formed by the interconnection of the wired internet and the wireless mobile ad hoc network. It allows mobile nodes in MANETs to communicate with the fixed nodes in the internet through the gateway. IIM suffers from many security issues owing to the open wireless medium and lack of mutual authentication between nodes. Mutual authenticated key agreement technique is used to securely agree on a session key between communicating entities, and is also used for secure communication and to protect the data from malicious activities. In order to provide mutual authentication between mobile node and a fixed node in IIM, one must overcome two problems, i.e. key management and computational cost. The strength of any security algorithm depends on its key management technique with minimum overhead, as IIM is a resource-constrained network. We propose a method to provide mutual authentication between communicating entities using chaos theory. It overcomes the key management cost by avoiding modular exponentiation and scalar multiplications. Moreover, our proposed method mutually authenticated key agreement protocol provides a mechanism to securely agree the session key between source and destination. Through extensive simulation analysis, we conclude that the proposed method provides a better approach towards security and protection of data from malicious nodes with minimum overhead in IIM.
Keywords: integration; mutual authentication; chaotic maps; security; gateway; MANET;.
Ensemble-empirical-mode-decomposition based micro-Doppler signal separation and classification
by Chen Huajie, Lin Ping, Emrith Khemraj, Narayan Pritesh, Yao Yufeng
Abstract: The target echo signals obtained by Synthetic Aperture Radar (SAR) and Ground Moving Target Indicator (GMTI) platforms are mainly composed of two parts, the micro-Doppler signal and the target body part signal. The wheeled vehicle and the tracked vehicle are classified according to the different character of their micro-Doppler signal. In order to overcome the mode mixing problem in Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) is employed to decompose the original signal into a number of Intrinsic Mode Functions (IMF). The correlation analysis is then carried out to select IMFs which have a relatively high correlation with the micro-Doppler signal. Thereafter, four discriminative features are extracted and a Support Vector Machine (SVM) classifier is applied for classification. The experimental results show that the features extracted after EEMD decomposition are effective, with up 90% success rate for classification using one feature. In addition, these four features are complementary in different target velocity and azimuth angles.
Keywords: micro-Doppler; micro-motion; EEMD; IMF; wheeled/tracked vehicle; SAR/GMTI; signal separation; feature abstraction; vehicle classification; SVM.
A hybrid AHP-VIKOR methodology to evaluate the adoption of COTS database components based on usability
by Adnan Rawashdeh, Bassem Matalkah, Awni Hammouri
Abstract: Adopting commercial off-the-shelf (COTS) components in development projects of large systems provides benefits of software reuse; these include accelerated development, increased dependability, and reduced process risk. However, choosing the right component among multiple options is considered a hard process and may involve risk. Throughout the system development life cycle, many stakeholders contribute from their own perspectives and interests. For example, a business owner would primarily be concerned with meeting the requirements within the assigned cost and schedule. End users would want the product to be easy to use. Thus, usability is a user-focused quality attribute. Under such circumstances, there should be a mechanism that helps stakeholders to make decisions accordingly. Multiple-criteria decision-making (MCDM) or multiple-criteria decision analysis (MCDA) is a sub-discipline of operations research that explicitly evaluates multiple conflicting criteria in decision-making. In this research work, an application of decision-making methodology has been introduced. It employs two well-known MCDM techniques, namely Analytic Hierarchy Process (AHP) and Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR). The new model, as a hybrid approach from AHP and VIKOR, has been designed to facilitate the decision-making process, featuring the ability to analyse and select the best option from a number of COTS components. In this respect, the aim of using AHP is to analyse the structure of the database software selection problem and to obtain weights of the selected criteria. Then, the VIKOR technique is used to calculate the ratings of the COTS or database software components.
Keywords: COTS; VIKOR; AHP; usability; MCDM; normalising weight; reuse; component.
Simulation and visualisation approach for accidents in chemical plants
by Feng Ting-Fan, Tan Jing, Liu Jin, Deng Wensheng
Abstract: A new general approach to lay the foundation for building a more effective and real-time evacuation system for accidents in chemical plants is presented. In this work, we build the mathematical models and realise automatic grid generating based on the physical models stored in advance with several algorithms in jMonkeyEngine environment. Meanwhile, the results of the simulation data through finite difference method (FDM) are visualised coupling with the physical models. Taking fire as an example, including fire with single and multiple ignition sources, shows the feasibility of the presented approach. Furthermore, a coarse alarm and evacuation system from fire have been developed with a multiple SceneNode and roam system, which also includes the making and importing of the physical models. However, to improve the accuracy of the mathematical models, adaptability and refinement of the grids and universality of the evacuation system is the direction of efforts.
Keywords: simulation; chemical accidents; alarm and evacuation system; jMonkeyEngine.
Global asymptotically stability of neural networks with uncertain parameters and time-varying delay
by Yang Li, Jianhua Zhang, Xueli Wu
Abstract: This paper is concerned with the global asymptotically stability problem for a class of neural networks with uncertain parameters and time-varying delay. Using a new proposed inequality called free-matrix-based integral inequality, a new robust criterion is proposed, which is expressed by linear matrix inequalities, by means of linear matrix inequality technique to deal with the unknown parameters in the neutral systems. Examples are simulated to demonstrate the effectiveness and efficiency of the obtained criterion.
Keywords: neural networks stability; time-varying delay; uncertain parameters; Lyapunov-Krasovskii functional.
A novel multi-criteria self-organising migrating algorithm for engineering problems
by Bilel Najlawi, Nejlaoui Mohamed
Abstract: Solving engineering design and resources optimisation via multi-objective evolutionary algorithms has attracted much attention in the last few years. In this study, an improved Self-Organizing Migrating Algorithm (MOSOMA) is developed and investigated to solve multi-objective engineering design problems. The proposed MOSOMA algorithm uses a migration approach for the search of optima. In order to obtain a uniform distribution of Pareto optimal solutions, the crowding distance method is introduced. Pareto dominance is incorporated into the algorithm in order to allow this heuristic to handle problems with several objective functions. The performance of the MOSOMA algorithm is assessed by applying it on a set of multi- objective standard test functions and constrained engineering design problems. The results show that the proposed approach is competitive and effective compared with other algorithms contemplated in this work and it can also find the result with greater precision.
Keywords: multi-objective optimization; self-organising migrating algorithm; test problem; Pareto front.
Monitoring data-based automatic fault diagnosis for the brake pipe of high speed train
by Guo Xie, Minying Ye, Xinhong Hei, Fucai Qian
Abstract: As a key part of the railway system, the brake pipe is essential for the brake system, and its fault may cause serious consequences, and even threaten lives. The generally employed approach for fault diagnosis of the brake pipe is manual inspection during the parking time, which is time-consuming, laborious, and dependent on the experience of the inspectors. In view of these problems, an automatic fault diagnosis analysis for the brake pipe of high speed trains based on monitoring data is proposed in this paper. Based on the concept of big data, the characteristics of monitoring data are analysed, and the fault features are extracted, then the fault diagnosis rules are established. Specifically, the main steps are as follows. The first step is the data preprocessing, including correcting the singular zero points and populating the missing points. The second step aims to eliminate the noise and measurement errors. The third step includes the establishment of the fault diagnosis rules, data analysis and fault diagnosis. Lastly, the data from an actual train line is analysed, and the analysis results demonstrate the effectiveness and feasibility of the proposed method.
Keywords: high speed train; fault diagnosis; brake pipe pressure; data-based.
A recursive algorithm for open information extraction from Persian texts
by Mahmoud Rahat, Alireza Talebpour, Seyedamin Monemian
Abstract: Owing to the proliferation of textual data available in non-English languages, one of the current challenges of open information extraction (Open IE) is to adapt existing techniques to those languages. While several Open IE systems have been introduced for English, many other languages, such as Persian, lack such tools. Fundamental differences between English and Persian in syntax and the corresponding dependency representations make the process of adapting an Open IE system for Persian very challenging. To the best of our knowledge, this article is the first published paper about open information extraction for Persian. Many traditional Open IE systems apply a large set of lexical patterns, which is inefficient in out-of-domain text. We replace this large pattern set with a few syntactic rules upon dependency parse of a sentence that are specifically designed for Persian. Moreover, we investigated Open IE at document level, which helped our system to enhance the results. Our analysis on a parallel corpus reveals that the proposed system covers 85% of the area under the precision-yield curve of the best available systems for English. We also addressed some Persian-specific phenomena to enhance the results. The rules are designed to cover both inter-clause and intra-clause relations. Besides, the recursive nature of our algorithm enabled us to handle nested sentences.
Keywords: open information extraction; Persian text processing; dependency parsers; natural language processing.
Research on target recognition and path planning for EOD robot
by Wei Deng, Hui Zhang, Yibin Li, Feng Gao
Abstract: In order to improve the autonomy of the explosive ordnance disposal (EOD) robot, the paper makes a research on the target recognition and path planning algorithm based on laser range finder and Time of Flight (TOF) camera. The target position of the explosive is selected by the operator from the gray-scale image, then EOD robots use Kernelized Correlation Filters (KCF) tracking algorithm and distance constraint to realise the real-time explosives identification. In the case of the A* algorithm, it does not take the heading information of the robot into consideration, which may lead to the problem of heading shakes in the vicinity of the obstacle. In this paper, the heading constraint is introduced to improve the A* algorithm so as to eliminate the problem of heading shakes and improve the stability of the robot. The simulation and experiment results demonstrate the feasibility of the algorithm proposed in the paper.
Keywords: EOD robot; KCF algorithm; path planning; TOF camera.
Quran search engines: challenges and design requirements
by Yasser Alginahi
Abstract: The increased research work in the area of Islamic studies has introduced many new tracks of research. Thus, search engines/tools for the Holy Quran are very essential for researchers in order to locate particular verses of the Quran and their related concepts, meaning, location, etc. This study intends to gather as much information on available Quran search engines/tools in order to set up guidelines for the minimum requirements needed in designing Quran search engines. To achieve the goal of this study, the pros and cons of available engines are discussed. Owing to the difficulties encountered in collecting information on these Quran search tools and the unavailability of technical background for Quran-related search engines; in some cases the results may not be comparable. Finally, from the Quran search engines surveyed the challenges are identified in order to aid in the design of efficient Quran-related search tools.
Keywords: search engines; information retrieval; Quran.
Design of a switched hyperchaotic system and its application
by Rui Wang, Qisheng Xie, Yongtao Huang, Hui Sun, Yigang Sun
Abstract: This paper proposes an automatically switched hyperchaotic system between two hyperchaotic systems. Especially, one of the systems is designed by changing three equations of another system. Two linear-term parameters and one nonlinear term are changed for respective equations. The corresponding characteristics have been analysed in detail. There are two main contributions of this paper. One is that the new system automatically switches. Another is that the other hyperchaotic system is constructed by changing more parameters compared with the existing switched chaotic systems. In addition, the dynamic characteristics of the attractor of the new switched hyperchaotic system are analysed in detail by Matlab. Correspondingly, Multisim simulation results are also conducted and compared with circuit implementation results. They are consistent with each other to verify the existence of the attractor of the new switched hyperchaotic system. The system is also used for a secure communication implementation based on a chaotic masking method. The simulation for secure communication application is conducted and shows the success of this application.
Keywords: hyperchaotic systems; secure communication; switched systems; circuit implementations.
Implementing weighted entropy-distance based approach for the selection of software reliability growth models
by Aakash Gupta, Neeraj Gupta, Ramesh Kumar
Abstract: A computational quantitative model based on Weighted Euclidean Distance Based Approximation (WEBDA) has been developed to evaluate, select and rank the Software Reliability Growth Models (SRGMs) in ascending or descending order, based on their Euclidean distance value from the optimal SRGM. The SRGM with Rank 1 is considered the optimal selection for the software developers on the particular dataset under consideration. The main problem of SRGMs selection and ranking is deployed as a multi-criteria decision making (MCDM) problem, in which numerous inter-related attributes collectively termed as ranking criteria are identified to evaluate the available alternatives. In the present research, a dataset from Tandem Computer Software Failure has been used to show the utility of the developed model. Furthermore, the concept of methodology validation strengthens the present research by making a comparison of obtained results with those of existing MCDM approaches, such as analytical hierarchy processing (AHP) and technique for order of preference by similarity to ideal solution (TOPSIS).
Keywords: software reliability; ranking criteria; WEDBA; SRGM.
Earth pressure prediction in the chamber for earth pressure balanced shield machines
by Yi An, Xiaoli Zhou, Zhuohan Li, Cheng Shao
Abstract: Earth pressure balanced (EPB) shield machines are large and complex mechanical systems and have been widely applied to tunnel projects. The earth pressure in the chamber is very important for EPB shield machines to avoid ground settlement and guarantee safe construction during the tunnelling process. In order to improve the prediction accuracy of the earth in the chamber, we propose a new earth pressure prediction method in this paper. First, we analyse the main factors influencing the earth pressure in the chamber and determine the inputs and output of the prediction model. Then, we use the least squares support vector machine to establish the prediction model whose parameters are optimised by the particle swarm optimisation. The experimental results demonstrate that the proposed method has high prediction accuracy and is an effective way to predict the earth pressure in the chamber for EPB shield machines.
Keywords: earth pressure; shield machine; prediction model; support vector machine; particle swarm optimisation.
Model selection using historical pattern: case study of forecasting Indonesian research areas
by Indra Budi, Agus Widodo
Abstract: To guide the research directions among research institutes in Indonesia, a National Research Agenda is periodically formulated. The list of prospective research areas in this document is usually determined by the judgement of experts whose opinions could be subjective. Meanwhile, a more objective approach has been studied by several researchers to find the emerging research areas by tracking the frequency of scientific publications. This paper investigates the use of this bibliometric approach to identify and forecast the emerging research areas listed in the Indonesian National Research Agenda. Diverse forecast methods are employed and selected based on their performance on previous dataset. In this way, there is no need for training on the current dataset, which may reduce time to select the best method. The dataset is compiled from the Scopus search engine by querying the research area in question. To construct the historical database, we use the dataset from M1 competition and the testing dataset from NN3 competition as well as time series constructed from query on Scopus. Our experimental results indicate that our model selection may perform well compared with the individual predictor. In addition, the most emerging research topics based on the forecast results can be quantitatively identified.
Keywords: emerging research areas; forecast combination; time series characteristics; bibliometric; Indonesia.
Integrating IoT and cloud in a smart city context: the #SmartMe case study
by Dario Bruneo, Francesco Longo, Giovanni Merlino, Antonio Puliafito, Nidhi Kushwaha
Abstract: #SmartME is a crowdfounding project that aims at exploring the possible synergies between the cloud computing and the Internet of Things paradigms. The project's main aim is to morph Messina into a smart city. In this direction, the Stack4Things framework has been implemented, extending OpenStack towards the management of Internet of Things resources. This paper summarises the first two years of the #SmartME project and presents technical details about Stack4Things, with specific reference to the underlying technologies and to the web portals that are used for administration and semantically enabled data retrieval.
Keywords: smart city; Internet of Things; IaaS cloud; semantic web; machine learning.
Low power low voltage CMOS full adder cells based on energy efficient architecture
by Pankaj Kumar, Rajender Sharma
Abstract: This paper presents two low power full adder cells based on energy efficient internal logic approach and pass transistor logic. These two new designs successfully operate at low voltage with tremendous signal integrity and driving capability. These designs are tested on a common environment using 90-nm CMOS process technology at many supply voltages. The adder cells are compared with eight of the popularly known full adders based on power consumption, speed and power-delay-product (PDP) and area efficiency. Intensive simulation runs on cadence environment and spectra show that the proposed full adder cells outperform their counterparts, exhibiting 59.48% and 55.41% improvement in their PDP metrics.
Keywords: low power; high speed; low voltage; hybrid design; energy efficient; full adder.
LexiPal: Kinect-based application for dyslexia using multisensory approach and natural user interface
by Muhamad Risqi Utama Saputra, Syukron Abu Ishaq Alfarozi, Kuntoro Adi Nugroho
Abstract: Considered as an effective learning strategy for dyslexia, multisensory approach demands visual, auditory, and kinesthetic activity. While development of software application implementing multisensory approach has shown promising result, previous applications did not accurately resemble multisensory strategy because there is no kinesthetic implementation. This research proposes a Kinect-based application, termed LexiPal, which incorporates kinesthetic activity in multisensory implementation by using Natural User Interface (NUI). NUI provides more intuitive ways of interacting with the application by using body movement and gesture. LexiPal implements NUI by fusing several technologies, including Augmented/Mixed Reality (AR/MR), non-contact human-computer interaction, skeletal tracking, hand tracking, and gesture recognition. For evaluation purpose, LexiPal was tested to 40 dyslexic children and they considered LexiPal user interaction as easy to use and enjoyable, which attracted them to play the learning content again in the near future.
Keywords: Kinect; dyslexia; multisensory approach; natural user interface; body movement; gesture interaction; skeletal tracking; hand tracking; kinesthetic interaction; augmented reality; educational application.
Development of aircraft path planning scheme through automatic dependent surveillance broadcast
by Jianhua Zhang
Abstract: The intelligent flight task algorithm for aircraft is investigated to effectively determine and search the best flight routes amid complicated conditions, including the complicated topography and threats from other flights in the route airspace. The proposed method is composed of safety distance and path planning by a pulse-coupled neural network. The safety distance is regarded as a pre-processing procedure for searching for the safe path, and the pulse-coupled neural network is adopted to provide a smooth flight route for the aircraft. The global optimal flight route is acquired through wave propagation by the pulse-coupled neural network. The results of the simulation demonstrate the abilities of the proposed method to provide the best flight routes efficiently for aircraft.
Keywords: path planning; pulse-coupled neural networks; wave propagation.
An anomaly-based approach for detection of DDoS attacks in cloud environment
by Adnan Rawashdeh, Mouhammd Al-kasassbeh, Muna Al-hawawreh
Abstract: Cloud computing is one of the most important developments in information technology and the business environment in recent years and is likely to remain so for the foreseeable future. It draws significant attention from researchers owing to its widespread application and substantial benefits. Owing to its distributed nature, using virtualisation, multi-tenant and reliance on the internet to provide services, security poses a major obstacle for cloud computing. Insider Distributed Denial of Service (DDoS) attack is the biggest challenge for any cloud environment where the unavailability of services and connectivity issues in cloud can deactivate the service totally, which could result in immense business and financial losses for consumers. Hence, to protect the cloud environment, and in particular the virtual environment, from DDoS activities, we need more than the traditional defence mechanisms such as firewalls, which sniff the network packets at the boundary of the network to detect and prevent attacks from entering the network, but they cannot detect insider attacks. Intrusion detection system is an important key in the cloud infrastructure security. This work proposes an anomaly intrusion detection approach in the hypervisor layer to discourage the DDoS activities between virtual machines. The proposed approach is implemented by the evolutionary neural network, which integrates the particle swarm optimisation with neural network for detection and classification of the traffic that exchanges between virtual machines. The performance analysis and results showed that the proposed hypervisor intrusion detection approach based on the artificial neural network with particle swarm optimisation is well designed to detect and classify the DDoS attacks in cloud environment with minimum false alarms and high detection accuracy.
Keywords: distributed denial of service; DDoS; cloud computing; intrusion detection system; hypervisor; virtual machine monitor; attacks detection; neural networks.
FCM-LSSVM modelling for ethylene loss rate of distillation column with respect to operation conditions
by Shao Cheng, Dong Xiaoyun, Zhu Li
Abstract: Ethylene loss rate is an important evaluation index in ethylene distillation operation, which directly relates to the comprehensive energy efficiency level of ethylene production. Therefore, the accurate prediction of ethylene loss rate is helpful in optimising energy consumption of ethylene production in distillation column. It is observed that some working conditions, such as the composition of cracking gas, unit load and the refrigerant temperature, have a great influence on the ethylene loss rate. In this paper, the prediction of ethylene loss rate is thus concerned and a new method with FCM-LSSVM is proposed for modelling the ethylene loss rate of distillation column with respect to the operating conditions. The clustering method is employed to classify optimally the ethylene distillation operation database, and then the LSSVM is suggested to establish the ethylene loss rate prediction model with different working conditions. Finally, simulations and comparative analyses for the proposed method are carried out by using real distillation data, which demonstrates that the model set up under multi-conditions would be more effective owing to better predictive precision and generalisation ability.
Keywords: ethylene distillation column; operating condition; fuzzy C-means clustering; loss rate; LSSVM.
A survey of resource allocation in the mobile cloud computing environment
by Li Liu, Qi Fan, Dongmei Fu
Abstract: Mobile cloud computing (MCC) is the integration of mobile computing and cloud computing. It provides an opportunity for users to obtain cloud resources over the internet. Resource allocation is a complex problem owing to the presence of heterogeneous application workloads in MCC. In recent years, few studies have clearly analysed the research problem and surveyed resource allocation in the MCC environment. Hence, it is very important to provide a comprehensive review of resource allocation to complement existing literature for the MCC environment. In this paper, a survey is made of resource allocation in MCC, and the state-of-the-art of the resource allocation strategies is presented. The issues and the current approaches to solve this problem are discussed in detail. Opportunities and challenges in this field are also examined, and future research directions are presented.
Keywords: mobile cloud computing; resource allocation.
Towards development of cyber-physical systems based on integration of heterogeneous technologies
by SangSu Choi, Gyhun Kang
Abstract: Cyber-Physical System is (CPS) a concept expanded from embedded computing and is applied in various industries, such as aerospace, energy, transportation, and medical industry. Manufacturing industry is also improving its competitiveness through building CPS and is establishing environments for smart manufacturing. CPS in the manufacturing industry plays the role of controlling the entire process of product design, procurement, production, and logistics, as well as managing the comprehensive flow of information. CPS is a complex system that mandates flexible integration of various technologies. This paper introduces a CPS architecture based on heterogeneous systems and technologies, such as manufacturing execution system, product lifecycle management, process mining, discrete event simulation, and virtual reality and its applications. Future researches such as development of CPS based on cloud computing for SME users and development of standards for interoperability within CPS are also discussed.
Keywords: smart manufacturing system; system integration; interoperability; factory improvement; manufacturing system.
An improved AHP and BP neural network method for service quality evaluation of a city bus
by Ying Liu
Abstract: Aimed at the realistic problem that service quality of city buses is low in big cities, an improved AHP-BP neural network method is established based on quality survey data of real passengers, in order to evaluate the analysis of quality factors． Firstly, the weight of each expert is worked out based on the perspectives of interests related to improving the AHP, then the comprehensive weight of each index is determined by calculating the weighted average of the obtained index weight of each expert and the corresponding evaluation weight of expert. Secondly, the weight of the BP neural network is used to train and test the model based on the results of improved AHP， getting BP evaluation results with an acceptable error in order to promote the classifier system of service quality factors. Finally, an empirical research is carried for the example of service quality evaluation of a city bus in Shenyang city of China. The results show that the method fully reflects the views of the experts while avoiding the conflicts of interest among experts, and reduces the arbitrariness of subjective evaluation and the learning ability of BP neural network model, making results more accurate and reliable． This illustrates the high application value of the improved AHP-BP neural network method in the future evaluation of service quality of city buses.
Keywords: AHP improved; BP neural network; analysis of influencing factors; bus passengers' perceptions.
Ensemble effort estimation using selection and genetic algorithms
by Pichai Jodpimai, Peraphon Sophatsathit, Chidchanok Lursinsap
Abstract: Software effort estimation plays a vital role in software project management. Several
single estimation methods have been introduced vying to be the best estimation method. However, it is difficult to decide which method offers the best estimation result. This study proposes an ensemble effort estimation from several single estimation methods that yield different estimations but comparably high accuracy. The proposed technique employs a correlation-based feature selection algorithm to choose methods out of twelve methods derived from combinations of four transformation and three learning techniques. The ensemble then uses a genetic algorithm to build a mathematical function to compute one combined estimation from those selected method estimations. Experiments are set up based on six benchmark datasets to evaluate estimation performance. The resulting measure of error metrics shows that the proposed ensemble technique, deploying only necessary estimation methods, can yield more accurate estimation than the best method from the twelve methods.
Keywords: software project management; software effort estimation; estimation method; ensemble method; transformation technique; learning technique; correlation; feature selection; genetic algorithm; error metrics.
Study on seals of subsea production gate valves
by Xingping Xu, Sen Li, Ling Gong, Hai Wang, Yanzhe Wang
Abstract: A subsea oil production gate valve and its actuator are introduced. Seals for the valve seat and element are studied, and the seal principle is given. The seal of the valve cover is designed, which is composed of a Parker B3 seal ring, two Parker BD seal rings and a copper retainer ring superposed together. The seal of the balance bar is designed, which is similar to the seal of the valve cover, but without a retainer ring. The piston seal, consisting of a Parker B7 ring and a FR guide ring, end seals are designed. To validate all the seals designed, the finite element models are set up, and the stress, deformation and contacting pressure of the seals are analysed. Results show that the strength of the seal is enough and the seal is reliable.
Keywords: subsea production; gate valve; seal.
An agent-based inter-vehicle cooperative robust car-following model for longitudinal control under uncertainty
by Oussama Messaoudi, Ammar Lahlouhi
Abstract: Uncertainty is a common challenge facing system modelling and simulation in uncertain environments, where the outcome of control actions is unknown. In this paper, an agent-based robust car-following model is proposed to handle uncertainty in the longitudinal control system based on inter-vehicle cooperation, where an organisation of heterogeneous agents communicate and cooperate in a vehicular ad hoc network to provide reliable and collision-free control policies. We used agent-based modelling to model the inter-vehicle cooperative longitudinal control system while integrating human drivers in the multi-agent system to assume specific roles and cooperate with other agents to accomplish the task at hand. For behavioural analysis and comparison with other car-following models, microscopic agent-based simulations conducted using JADE and SUMO showed that the proposed model offers collision-free control of vehicle speed under different conditions including uncertainty. Also, we used the proposed model to investigate the effect of uncertainty on both vehicle's speed and its control actions.
Keywords: agent-based modelling; agent-based simulation; car-following model; longitudinal control; microscopic simulation; vehicular ad hoc network.
A consumer-based smart home and health monitoring system
by Kailas Patil, Meena Laad, Aakash Kamble, Shivani Laad
Abstract: The past few decades have seen a sharp increase in air pollution and its harmful effects on human health. Indoor air quality is a major determining factor of personal exposure to pollutants in todays scenario. A majority time is spent in indoor environments by a majority of people. Therefore monitoring indoor air quality has become an important issue. There are various reasons for poor quality of indoor air in which the oxygen level is below the healthy level, such as influx of polluted outdoor air, geological materials around the residential properties, household activities such as cooking, cleaning, and smoking, materials used in construction or painting the house, etc. With increasing pollution, respiratory diseases are on the rise and therefore there is a strong need to develop a smart home system which is capable to monitor environmental conditions for its users. This research study proposes a smart system that uses a renewable source of energy, monitors and controls the overall power consumption of the home, keeps a check on the environmental conditions by measuring the level of oxygen, and provides a provision for an alarm when the oxygen level falls below the safe limit. The proposed model is compact, cost-effective, energy-efficient and provides a smart home health system to the consumer and is especially useful for the old and physically challenged.
Keywords: health and safety; home automation; SCADA systems; smart homes; sensors; industrial automation.
Towards recent developments in the field of digital image forgery detection
by Tarun Kumar, Gourav Kumar
Abstract: Proliferation of powerful computers, innovative photo-editing software packages, and high resolution capturing devices leads to effortlessness in generating digital image falsification. Indeed, the security apprehension of digital images has ascended since a long period and diverse techniques for authenticating the integrity of digital images have been established. Conversely, significant exploration in this realm would not only be verifying the integrity of images but also correspondingly sensing the hints of tampering or falsification without necessitating additional prior information of the image content or any embedded watermarks. This paper reviews the recent developments in the field of digital image forgery detection. With the concept and methods, various applications of forgery detection are presented especially focusing on the use of soft computing for developing the techniques for forgery detection. The future of development and application of soft computing in digital image forgery detection is discussed.
Keywords: forgery detection; digital image processing; image watermarking; copy move forgery; image splicing; soft computing.
A new chaotic jerk system with two quadratic nonlinearities and its applications to electronic circuit implementation and image encryption
by Sundarapandian Vaidyanathan, Akif Akgul, Sezgin Kacar
Abstract: This work presents a new chaotic jerk system having two quadratic nonlinearities. Dynamical properties of the new jerk system are discovered through dissipativity, equilibrium point analysis, eigenvalues of the Jacobian matrices, bifurcation diagram, and Lyapunov exponents. The results also show that the new jerk system has interesting complex dynamics characteristics. Furthermore, random number generator (RNG), its NIST-800-22 tests, an image encryption application and its security analyses are realised with the new jerk system. The new chaotic jerk system can be useful in scientific fields such as physics, control, true and pseudo random number generator (TRNG,PRNG), artificial neural network, genetic algorithm, etc.
Keywords: chaos; jerk systems; chaotic systems; random number generator; chaos basedrnencryption; circuit implementation.
A new suitable feature selection and regression procedure for lithium ion battery prognostics
by Jaouher Ben Ali, Lofi Saidi
Abstract: The accurate prediction of lithium ion battery Remaining Useful Life (RUL) is indispensable for safe and lifetime-optimised operation. Thereby, the monitoring of this vital component is very necessary for planning repair work and minimising unexpected electricity outage. However, the study and the investigation of internal battery parameters show several value changes within the battery lifetime, and it is highly influenced by environmental and load conditions. Consequently, this paper presents a new prognostic method for online battery monitoring based on isometric feature mapping technique (ISOMAP) and incremental support vector regression (ISVR). ISOMAP is used to reduce some features extracted from lithium ion batteries, with different health states, in both modes of charge and discharge, and ISVR is used to regress online the selected feature. Experimental results show that the proposed methodology provides a new suitable trend parameter for battery prognostics.
Keywords: ISOMAP; ISVR; lithium ion battery; PHM; RUL.
API library-based identification and documentation of usage patterns
by Hamzeh Eyal Salman
Abstract: Application programming interfaces (APIs) are one of the most important sources for supporting source code reuse as each API provides a large set of pre-implemented functionalities that support programmers to achieve their daily work in different contexts. However, APIs provide a huge number of classes and methods that hinder programmers to understand and use APIs. Recently, numerous client-based approaches have been proposed for facilitating APIs usage through identifying frequent usage patterns. Although they represent significant efforts for helping to understand APIs, the client programs are not available for either newly released APIs libraries or APIs that are not widely used. In this article, a non-client-based approach for identification of frequent usage patterns and documentation is proposed. An experimental evaluation is conducted using four widely used APIs. For all the studied APIs, the obtained results show that the proposed approach is comparable with client-based approaches in terms of frequent usage patterns cohesion.
Keywords: reuse; frequent usage pattern; API; object-oriented; understanding; documentation.
A new hybrid strategy for data clustering using cuckoo search based on Mantegna Levy distribution, PSO and k-means
by Omid Tarkhaneh, Ayaz Isazadeh, Hossein Jabbari Khamenie
Abstract: Data clustering is one of the data mining techniques that is widely used in some applications, such as pattern recognition, machine learning, image processing, etc. Swarm intelligence-based algorithms are extensively used in data clustering in recent years. Cuckoo search (CS) is one of the recently proposed algorithm in the category of swarm intelligence-based techniques. In this paper, a new hybrid algorithm that uses CS, Particle Swarm Optimisation (PSO) and k-means is proposed (HCSPSO). The proposed algorithm employs PSO and k-means to produce new nests in standard CS to obtain better results. It also benefits the Mantegna Levy distribution to obtain higher convergence speed as well as local search. To eliminate the problem of the high number of functional evaluations in standard CS, a fraction of nests is assigned to every section of the algorithm. The proposed algorithm performance is evaluated by ten standard benchmark datasets. Evaluation results show that the proposed algorithm is an efficient method for data clustering and produces more optimised results in comparison with standard CS, PSO, elephant search algorithm, enhanced bat algorithm, bird flock gravitational search algorithm, improved cuckoo search and k-means.
Keywords: data mining; cuckoo search; Mantegna Levy distribution; swarm intelligence; particle swarm optimisation.
Reliability analysis of software with three types of error and imperfect debugging using Markov model
by Gireesh Kumar, Manju Kaushik, Rajesh Purohit
Abstract: In this analysis, we consider a Markovian software reliability model (SRM) with imperfect debugging (ID) wherein software may fail owing to three types of error called error generation (EG). For developing the governing differential equations of SRM with three types of error, an irreducible Markov process is used. Further, we have applied the Runge-Kutta (R-K) method under transient condition for obtaining reliability of concerned system in different configurations. Moreover, we suggest various software reliability indices such as reliability, failure frequency, mean time to failure (MTTF) and many more. By taking a numerical illustration, the sensitivity analysis is done to demonstrate the validity of analytical outcomes and to explore the effects of various parameters. Moreover, the analytical results are also compared with adaptive neuro-fuzzy inference system. Finally, conclusions are given.
Keywords: software reliability model; Markov model; imperfect debugging; errors; R-K method.
Analyses of parasitic capacitance effects and flicker noise of the DAC capacitor array for high resolution SAR ADCs
by Xicai Yue, Janice Kiely, Chris McLeod
Abstract: With the increasing number of bits, parasitic effects and flicker noise of switching transistors in the DAC capacitor array of the SAR ADC are getting relatively bigger when compared with the exponentially decreasing error budget. This paper analyses the effects of parasitic capacitances related to the top-plate and bottom-plate of unit capacitors on the accuracy and the noise performance of the DAC capacitor array, showing that thermal noise of the whole capacitor array decreases when parasitic capacitances are considered while in the meantime an unexpected gain error is introduced. Although the parasitic-capacitance-induced gain error is almost independent of the number of bits, parasitic effects should be minimised for high resolution SAR ADCs since the dynamic range of the high resolution ADC is severely reduced owing to the gain error. The post-layout parasitic capacitance extraction of a 10-bit poly-poly DAC capacitor array shows that the value difference between the top-plate and bottom-plate related parasitic capacitances is large, so that the parasitic-capacitance-induced gain error can be decreased by 152 times when top-plates of unit capacitors are connected together as the output node of the capacitor array. The switching transistors flicker noise calculation for a 10-bit SAR ADC shows that flicker noise can be safely ignored for 10-bit 1MSPS SAR, while the calculation for an 18-bit 1MSPS SAR ADC shows that flicker noise should be considered for the higher resolution SAR ADCs.
Keywords: successive approximation register ADC; DAC capacitor array; parasitic capacitance; thermal noise; flicker noise.
Hardware-in-the-loop simulation for the testing of smart control in grid-connected solar power generation systems
by Mohammad Hassan Khooban, Moslem Dehghani
Abstract: Those systems that convert sunlight to electricity directly are photovoltaic (PV) systems. PV(s) are solar energy supply systems. The power of a solar photovoltaic panel is strongly related to climate conditions. Because of that, a grid-connected system needs a good response for variations in the solar radiation and temperature. A smart technique which has a fine rejection of disturbances is the time-varying control. This work shows the application of the control based general type-II fuzzy for the grid-connected solar power generation system. In this study, general type-2 fuzzy logic sets (GT2FLS) and the Modified Backtracking Search Algorithm (MBSA) techniques for adaptive tuning of the most popular existing proportional-integral (PI) controller is integrated in order to tackle these uncertainties. The fast and robust response of the control allows a better use of the photovoltaic array energy to increase the efficiency of the system and guarantee stability for all the operational range. The achieved results are compared with a conventional PI controller and an Optimal Fuzzy PI (OFPI) controller, which are the most recent researches to evaluate the proficiency of the proposed controller. Finally, the extensive studies and hardware-in-the-loop simulations are presented to make obvious the successfulness and effectiveness of proposed controller.
Keywords: adaptive PI control; general type II fuzzy logic; grid-connected solar power generation system; modified backtracking search algorithm.
Novel approach for shape-based similarity search enabled by 3D PDF
by Frank Neumann, Michel Atten
Abstract: During product development, shape-based similarity search helps the engineering teams to discover parts and assemblies already existing in their companys component databases that match the ones required for the new product. Therefore, similarity search constitutes an important means to keep the overall number of components designed, managed and maintained by a company at the lowest possible level. This helps to reduce the efforts for engineering design, manufacturing planning, managing the master data, and consequently lowers the product costs. In this paper, we present a new approach for shape-based similarity search using 3D PDF as the unique neutral format for determining various types of shape descriptor. We find that this method significantly reduces the implementation efforts for analysing 3D geometries originating from various CAD systems. In addition, it permits to tackle novel use cases for shape-based similarity search owing to the versatile characteristics of the 3D PDF format.
Keywords: shape-based search; shape-based similarity search; 3D shape matching; 3D shape similarity; 3D shape retrieval; 3D shape descriptors; product data management; PDM; PLM; 3D PDF; PRC.
A framework for visualising road design prior to construction using driving simulation technologies
by Dahai Guo, Casey Baer, Xuedong Yan
Abstract: This paper proposes a framework where road designs can be visualised in a virtual reality environment prior to any physical construction. A software algorithm for generating computer graphics models automatically, enables this framework to be effective. Key road design parameters such as the number of lanes, shoulder length, speed limits, turn angles, etc., must first be identified and then a computer program is developed to build computer graphics models based on these parameters. The generated computer graphics will include triangle meshes, textures, and height maps which can be rendered within a virtual reality environment. When used in conjunction with driving simulation technologies, the program also enables road designers to drive on their road being designed. Any implementation of this framework will be the most effective if it is incorporated with an existing road design process. Additionally, a case study is presented in order to demonstrate an implementation of the proposed framework.
Keywords: visualisation; graphics modelling; driving simulation.
A metamodel-driven definition and implementation of ONDAR: a home automation ontology
by Achraf Lyazidi, Salma Mouline
Abstract: Smart homes are houses equipped by computational technology to assist inhabitants in several situations. To design these complex systems, we need to take into account the inhabitant's experiences and needs. A modelling language supporting the semantic aspect allows modelling close to end-user needs. Usually, such a language is based on the concept of ontology. However, research including ontologies to design smart homes is still limited. Also, in the ontology engineering, a field which studies the methods and methodologies for building ontologies, no standard methodology exists to design and implement ontologies. In this paper, we study several approaches for home automation design, then we present our ontology for home automation after we define a smart home and a home automation system functionalities and behaviour. We also conduct a brief state of the art about approaches for implementing ontologies, then we present our implementation process.
Keywords: ontology; home automation; smart home; ontology implementation; ontology engineering.
A deep learning approach to software evolution
by Shang Zheng, Hongji Yang
Abstract: Software evolution techniques should be made as important as software development techniques. One possible way to help with the situation is to learn from software development, and also to learn from software evolution techniques. The breakout of Machine Learning and Deep Learning (ML&DL) is becoming the big buzzwords in technology and should be studied for being made available for servicing software evolution. Open source projects provide an open defect repository to which users and developers can report bugs. It is a challenge to document bug reports to the appropriate developers. In this paper, we apply deep learning approaches and a topic model to learn the features of defect reports and then make recommendations. Compared with the traditional machine learning approaches, the proposed approach based on deep learning can perform better in accuracy and assign defect reports to developers more effectively and correctly along with the dataset increasing.
Keywords: software evolution; deep learning; machine learning.
Development and optimisation of image segmentation algorithm on an embedded DSP platform
by Boucif Beddad, Kaddour Hachemi, Sundarapandian Vaidyanathan
Abstract: In this work, a very efficient segmentation algorithm based on the analysis of vertical and horizontal histogram using edge detection method is developed in order to detect the licence plate from a colour vehicle image. VM3224K2 Daughter kit is used to capture the input image that is to be converted into YUV format and feed it to C6713 development kit. The licence plate localisation algorithm is implemented using MATLAB software and verified for its functionality. First, the in-built functions of MATLAB are replaced by user-defined functions in Simulink Model then translated into CCS project written in C using an integrated development environment provided by Texas Instruments; also, it is compiled and debugged using Code Composer Studio (CCS), downloaded onto TMS320C6713 DSP-Platform. Finally, VM3224 Daughter kit is embedded with DSK6713 kit to display the output image. The proposed algorithm has achieved an accuracy of around 100% and works for both front and rear digital images.
Keywords: image processing; VM3224K2 Daughter kit; segmentation; Code Composer Studio; TMS320C6713 DSK; edge detection.
Collaborative and ubiquitous mobile learning system prototype
by Mohammad Alnabhan, Ahmad Abu-Al-Aish, Sultan Al-Masaeed
Abstract: Mobile learning applications use the advantages of mobile technologies to increase learning opportunities, mainly on an anytime anywhere basis. The advancement of mobile technology has facilitated the development of numerous applications to improve students learning experience and performance. Successful implementation of m-learning is highly dependent on learning context and environment awareness. This work presents a multiphase exploration of early phases responsible for defining and validating the m-learning context, and later phases based on context validation results achieved from the previous phases, involving the development and evaluation of a new m-learning context prototype. This new prototype proved to provide context-aware and ubiquitous learning services, fulfilling several diverse user interaction levels and requirements.
Keywords: mobile learning; m-learning; m-learning system; e-learning; context factors; ubiquity learning.
Multi-objective evaluation of wind power acceptable capacity based on statistical characterisation
by Shuangxin Wang, Yinan Zhao, Meng Li
Abstract: The contribution of wind power to the availability of generating capacity becomes more important with increasing wind penetration. This paper presents a multi-objective evaluation of the acceptable capacity of wind power. A partitioning method that can adaptively divide the forecast power range into various regions according to its historical data is firstly proposed. Then, the multi-objective optimisation model of the power system integrated with wind is constructed, with the objectives of minimum generating cost, minimum pollutant emission and maximum wind power acceptable capacity. By amending the NDX (normal distribution crossover) operator into the binary crossover operator of NSGA2, the improved NSGA2 (named INSGA2) is tested by a benchmark for typical high-dimensional functions, and the simulation results confirmed the feasibility of the developed algorithm. Finally, a case study of IEEE 118 bus system is carried out to verify that the approach is beneficial to deal with the problems of evaluation on stochastic wind acceptance.
Keywords: wind power forecasting; multi-objective optimization; Pareto solutions; wind power acceptable capacity; statistical characterisation.
A framework for combining software patterns with the semantic web for unstructured data analysis
by Hossam Hakeem
Abstract: Unstructured data is heterogeneous and variable in nature and comes in many formats, including text document (Word documents, e.g., can be converted to text), image, audio and video. Unstructured data is growing faster than structured data. It will account for 90% of all data created in the near future. Unstructured data analytics can reveal important interrelationships that were previously difficult or impossible to determine and is currently seeking to gain richer, deeper, and more accurate insights into the business and social life for gaining competitive advantage and serving society better. To realise the full potential of unstructured data analysis, new approaches need to be developed. This paper proposes an approach to combining software patterns with the semantic web for constructing a data analysis framework for unstructured data.
Keywords: patterns; unstructured data; semantic web; data analysis.
Modeling and Simulation of the Ship Rapids-Ascending Ability in Lancang River
by Zhizhou Zhao, Sichen Tong, Feng Zhu, Guangxiang Xu
Abstract: Ship sailing resistance is an important indicator to judge the navigation capacity of a waterway. In this paper the empirical formula of Zwaan Kopf is modified according to the ship model test results in Lancang River channel, and the test find out that the navigation capacity of the channel can be represented by a critical compositive flow energy indicator ΔE=1.20. In order to validate the reliability of experimental results, this paper established a two-dimensional numerical model to simulate the water flow and ship sailing process in the channel. The relationship of flow energy indicator and the sailing velocity is being studied by simulating a typical 500t ship sailing in the channel of Lancang river, and the results show that: the value of critical flow energy indicator ΔE in the channel of Lancang river by simulation fits well with the tests, so the simulation method proposed in this paper is reasonable and feasible, and the critical flow energy indicator simulated by this method has important reference value in engineering
Keywords: Waterway Regulation; Rapids-Ascending ability; Sailing Resistance; Numerical simulation
Study on creep characteristics of geogrid based on modelling and experimental method
by Xia Li, Dinglong Shan, Feng Zhu, Ying Geng
Abstract: The creep characteristics of geogrid have significant influence on the analysis of the retaining wall's mechanical behaviour and deformation characteristics. This paper used digital speckle pattern interferometry to observe the model test of a retaining wall with embedded geogrid, and analysed the stress and strain distribution of soil behind the retaining wall according to the observation data. The mechanical model of stress distribution of geogrid is established in this paper, and the creep model of geogrid is also established to simulate the time-related behaviour of geogrid. In order to prove the rationality and reliability of the model proposed in this paper, the PFC2D software platform is employed to verify the numerical model of the reinforced retaining wall, and the creep model of geogrid is included in the PFC2D software. The calculation results show that the displacement of the retaining wall can be significantly reduced because of the anchoring effect of the geogrid. The time-dependent displacement of the retaining wall can approximately meet the logarithmic relationship. Therefore, the creep model of geogrid proposed in this paper is effective and reliable, and the method proposed in this paper can provide valuable reference information for similar engineering practice.
Keywords: geogrid; creep characteristics; digital speckle measurement system; particle element; numerical simulation.
EEG signals classification based on autoregressive and inherently quantum recurrent neural network
by Saleem Taha, Zahraa Taha
Abstract: This paper shows a novel hybrid approach in view of autoregressive (AR) model and Quantum Recurrent Neural Network (QRNN) for classification of two classes of electroencephalography (EEG) signals. The QRNN-AR has been shown to be capable to capture and quantify the uncertainty inherent in EEG signals, because it uses fuzzy decision boundaries to partition the feature space. Two diverse elements extraction techniques were used to extract the features from EEG signals; AR coefficients are processed with Levenion Durbin Algorithm and mean square error. AR provides a better frequency resolution and good spectrum of short EEG segments. The QRNN trained by the back-propagation algorithm is compared with Quantum Neural Network (QNN) and Quantum Wavelet Neural Network (QWNN). The average accuracy of the proposed QRNN model is 88.28452% at 6 seconds. The accuracy to time ratio value is 14.714086, which shows the superiority of the proposed model. Experimental results demonstrate that the QRNN-AR gives the highest overall accuracy and short processing time. In addition, the structure of the proposed method is more reliable.
Keywords: biomedical signal processing; electroencephalography; feature extraction; quantum computing; recurrent neural networks.
A real world online signature verification system based on correlation algorithm
by Charles Chen, Kuo-Kun Tseng, Xiaofeng Zhang
Abstract: Handwriting signature is a means of biometric identification and authentication, which is used to verify or authenticate a 'signer' and the document signed. An US law (the electronic signatures (E-Sign) in Global and National Commerce Act) and the United Nations Commission on International Trade Law Model Law on Electronic Commerce already grant electronic signatures legal validity equivalent to traditional hand-written counterparts. The intention of those laws is to cut costs while providing more stringent security, especially in the emerging e-commerce arena. In this paper, we (i) describe fundamentals and the current status of electronic signatures in detail; (ii) propose an online handwriting signature verification algorithm by using four online elements as the verification features: they are X axle, Y axle, pressure and velocity (time). A correlation algorithm is used to test and verify signatures; (iii) develop a real world application system with the online electronic signature.
Keywords: digital signature; online signature; signature verification.
Novel security issues and mitigation measures in cloud computing: Indian perspective
by Sudhakar Godi, Kurra Rajasekhar
Abstract: In the recent times, the demand and need for cloud computing is increasing owing to its wide range of applications, especially applications such as email, social networking apps, map storages, data sharing apps, etc., beside many useful applications. It has its own limitations such as cloud migration, storage space, efficient data mining, security and more. Data security is one of the major constraints of the cloud, especially in private and hybrid clouds. In this paper, a survey on the recent usage of the cloud computing technology in India is presented. Related security issues regarding the public, private and community clouds concerned are also depicted. This survey has been been conducted in both online and offline modes. It comprises opinion from 108 respondents out of 153 requests. A majority of participants reveal that they use cloud technology in their daily life applications, and approximately 73% are concerned about the security issues, especially private cloud storage and biometric security. Mitigation measures for all variants of the cloud technology have also been presented. A novel statistical survey report for 2016 is presented regarding security needs and improvements by considering various parameters. In addition, a list of cloud security attacks is also discussed.
Keywords: cloud computing; security; private cloud; real-time survey; security attacks; biometric.
Job-shop schedule modelling and parents-crossover evolutionary optimisation for integration of production schedules
by Jianxin Zhang, Jinxiang Chen, Haoyu Zhang
Abstract: An improved parents crossover evolutionary algorithm（IPCEA）is presented to deal with a class of job-shop scheduling optimisation problems. The considered integrated production process is firstly described as a job-shop model. Based on the model, the active schedules encoding and decoding approaches for production scheduling processes are proposed respectively. In order to avoid illegal chromosomes and preserve the good characteristics of the parent generation, an IPCEA is provided. Compared with the existing results, the proposed method can obtain better convergences and optimum solutions. The simulation results are given to show the effectiveness of our approaches.
Keywords: integrated production; SM-CC-HR; job-shop; IPPX-EA; ASD decode.
A novel reconfigurable control method for an aircraft with potential actuator failures
by Xinli Xu, Zhen Jiang, Huosheng Hu
Abstract: This paper presents a novel reconfigurable control method for an aircraft with potential actuator failures. A Variable Structure Model Reference Adaptive Control (VS-MRAC) scheme is deployed to counteract the adverse effects when the actuator failure occurs. Combined with exponential reaching law, the convergence rate is improved and the chattering is reduced. This approach ensures that the reference input value can be tracked rapidly and accurately. The safety and stability of the aircraft is much improved during the event of actuator failures. Finally, the simulation results are given to show the effectiveness and performance of the developed method.
Keywords: VS-MRAC; exponential reaching law; convergence rate; reconfigurable control; actuator failure; aircraft safety and stability.
Evaluation of various feature sets and feature selection towards automatic recognition of bird species
by Arti V. Bang, Priti P. Rege
Abstract: It is necessary to develop efficient methods for monitoring and recognising bird species that will help in evaluating the biodiversity of a region. In this paper we present techniques for automatic recognition of bird species based on audio recordings of their sounds. In this work, various audio features like descriptive features, wavelet packet decomposition-based features and perceptual features like Mel-frequency cepstral coefficients, perceptual linear prediction, and human factor cepstral coefficients are evaluated. Combination of these feature sets has also been evaluated. Classification of ten bird species is carried out using Gaussian Mixture Modelling (GMM) and Support Vector Machines (SVMs). When a number of features are extracted, the feature vector may contain redundancy. Redundant features may either degrade the performance of the system or add no value to the system. For feature subset selection, this work implements a technique based on singular value decomposition and QR decomposition using column pivoting.
Keywords: bird species; Mel-frequency cepstral coefficients; human factor cepstral coefficients; perceptual linear prediction; wavelet packet transform; Gaussian mixture modelling; support vector machines; singular value decomposition; QRcp factorisation.
Online identification of agent-based multi-model system and its application to the control valve circuit
by Xiaopeng Zhao, Guotian Yang, He Liu
Abstract: An agent-based online multi-model system is proposed in this paper, and the identification method of the model is described in detail. In the agent-based system, each agent can execute the task alone or collaborate with other agents to accomplish a fixed goal. The agent is structured by some cluster centres that can be obtained through the fuzzy subtractive clustering method. The behaviour of the agent can be described by a dynamic equation whose parameters can be identified online by the weighted recursive least squares method. In addition, an initial setting method is used to adjust the local model parameters when new data come to the system. The implementation of the mentioned system to the control valve in cooling water circuit is studied, and the simulation results illustrate the proposed strategy can obtain satisfactory performance.
Keywords: online identification; multi-model; agent; fuzzy clustering; non-linear system.
Evaluating impact on CMPs' power for design inaccuracy diagnosis
by Baisakhi Das, Biplab K. Sikdar
Abstract: In CMPs (Chip Multi-Processors), with thousand of processors, the issue of power dissipation has emerged as a matter of serious concern. Out of several factors responsible for huge power drainage the branch prediction unit of a processor contributes almost 10% of the overall power dissipation. This work aims to analyse the impact of inaccurate/faulty design on the branch predictors' power dissipation while realising speculative execution. The issue has been addressed through introduction of probable faults in a predictor that lead to mis-speculation. The prediction mechanism in CMPs also plays a role in dead-block identification, that is to avoid unutilised power consumption in a system as well as to overcome the poor cache efficiency. The performance loss of a system due to design inaccuracies/faults in dead-block prediction is also evaluated. The detail analysis reveals that the design inaccuracies of a predictor can cause a huge power loss, even up to 95%. The additional power loss in a processor can effectively be sensed to enable diagnosis of the faulty module (design inaccuracies) of predictor as well as to frame guidelines for operating mode of a CMP's cache system.
Keywords: CMPs; branch predictor; dead block prediction; speculative execution.
Modelling and simulation of sensor fault-tolerant networked control system with uncertainties
by Yanpeng Wu, Ying Wu
Abstract: This paper investigates the problem of fault-tolerant control against sensor failures for a class of uncertain networked control system with random time delays. A novel fault-tolerant control scheme against sensor faults with consideration of both time delays and norm-bounded uncertainties is proposed to stabilise the target fault system. A complete fault model of sensors is developed with the objective to represent the type and degree of sensor faults in an integrated parameterised way in plant model. By employing multiple parameter-dependent Lyapunov-Krasovskii functions, sufficient conditions of system stabilisation and robust fault mode dependent controllers are derived. The simulation results show the effectiveness of the proposed method.
Keywords: sensor failure; fault-tolerant control; uncertainties; time delay; LMIs; linear matrix inequalities.
Biometric authentication of physical characteristics recognition using artificial neural network with PSO algorithm
by Lazarus Nisha Evangelin, Alfred Lenin Fred
Abstract: Biometric authentication is the verification and identification of a person uniquely based on physical characteristics such as fingerprint, palm print and knuckle print. Biometric authentication is used in computer science as a form of identification and access control. For authentication four different modules are operated, including pre-processing, feature extraction, fusion and recognition modules, which are performed in our proposed work. In pre-processing module various techniques are used to improve the image quality and render the image suitable for additional processing; then for each character different feature extraction techniques are attained. After feature extraction of three authentications the fusion technique as feature level fusion is used for minimising features. This fusion technique is mainly used for reducing time compression when recognition of the images. Then, using the optimised Artificial Neural Network (ANN) with Particle Swarm Optimisation (PSO) algorithm, the images are classified as recognition and non-recognition. Finally while providing the test images the recognised images are identified for security purpose.
Keywords: biometric authentication; feature extraction; feature level fusion; ANN; artificial neural network; PSO; particle swarm optimisation.
Test case prioritisation during web application testing
by Munish Khanna, Naresh Chauhan, Dilip Kumar Sharma, Abhishek Toofani
Abstract: Owing to frequent alterations in the existing web applications, performing regression testing becomes necessary for the identification and rectification of the newly generated unwanted faults. Owing to various resource constraints, test case prioritisation is one of the strategies followed, rather than running test cases blindly. This paper proposes a novel approach towards prioritisation of test cases during regression testing of web application (dynamic website) using Bayesian network. Initially, a Bayesian network is formed using various parameters which affect the success of a test case as well as promote testing of more crucial sections of the web application. Thereafter, the conditional probability table and probabilistic inference algorithms are applied to evaluate the success probability and ultimately priority (importance) of a test case. Execution of the test cases takes place on the basis of their respective priority. The performance of proposed technique is compared with existing work, 2-opt inspired heuristic algorithm and genetic algorithm.
Keywords: test case prioritisation; Bayesian belief network; regression testing; web application testing.
Special Issue on: CAL'2016 Software Architecture for Emerging Systems
An emerging multi-paradigm for representing mobile applications architectures using heterogeneous conceptual bricks
by Afrah Djeddar, Hakim Bendjenna, Abdelkrim Amirat, Philippe Roose, Lawrence Chung
Abstract: The mobile applications have enjoyed explosive growth these last years. Taking advantage from these existing softwares, the constituent software bricks to compose such mobile applications can take different implementation forms and manipulate heterogeneous data by dint of users' requirements or its execution context. However, the mobile software developer confronts a difficulty to compose already existing software entities because of their heterogeneity. An emerging need is then to have a new modelling space to support the development of heterogeneous mobile applications. In view of this fact, this paper discusses the proposal of a multi-paradigm for representing mobile applications based on heterogeneous conceptual bricks, including their architectural conception and the specification of the necessary adaptation mediators. The proposed paradigm aims to deal with the heterogeneity presented by the constituent conceptual bricks and the execution environment of the final product. A conceptual description of a mobile application called ShopReview is presented to show the usability of the proposed paradigm.
Keywords: multi-paradigm; architectural description; heterogeneity; mobile applications; conceptual bricks; adaptation mediators.
A template for formalizing reliable Acme-based software architecture
by Rida Mezghache, Fadila Atil
Abstract: Acme/Armani is a declarative language based on first order predicate logic. Acme supports the component and connector paradigm with types, as well as invariants and architectural styles. It also supports constraints. Our main goal in this work is to provide Acme with a new architectural style that fully supports component based architectures. To this end, we propose first a formalized model based on Acme architectural elements to have no gap between the initial design and Acme semantics. Based on this model, we create an architectural style, then we present architecture constraints. while outlining how they are specified and interpreted. We will firstly express these constraints in the first order predicate logic, and then we will translate them in the Acme/Armani formalism, to ensure syntactic and composition conformance, which makes the configuration as reliable and consistent as design.
Keywords: component-based architectures; reliability; integrity constraints; software architecture; architecture description language; component; connector; configuration; Acme; Armani.
A contractual approach for the verification of UML2.0 software architectures
by Taoufik Sakka Rouis, Mohamed Tahar Bhiri, Mourad Kmimech, Faouzi Moussa
Abstract: The functional and qualitative properties are conventionally considered after software is completed. Currently, researchers consider treating those properties as soon as the architectural design phase. In this paper, the modelling and verification of the syntactic, behavioural and qualitative properties in UML2.0 software architectures were examined. To achieve this, an UML profile extending the UML2.0 component model by a set of qualitative concepts is proposed. The new profile, called CUMLQoS, was able to model the UML2.0 software architectures equipped with qualitative properties. Our verification approach suggested using the Acme/Armani ADL as a checking machine of syntactic and qualitative properties of UML2.0 software architectures deriving from our CUMLQoS profile. The choice of this ADL is justified by its ability of formal verification of different types of property related to software architectures. As a second step of our verification approach, UML2.0, Port State Machine (PoSM), Wright and CSP were combined to check the behavioural consistency of UML2.0 software architecture. To achieve this, a set of systematic rules was proposed allowing the translation of UML2.0 source model to the Wright target model. Using Wr2fdr tool, the Wright specification can automatically be translated to a CSP specification acceptable by the FDR2 model-checker.
Keywords: software architecture; verification; contract; UML2.0; PoSM; model-checker; FDR2.
Architectural method to design and control dynamic composite web Services
by Manel Amel Djenouhat, Faiza Belala, Kamel Barkaoui
Abstract: Nowadays, web services constitute the core technology of IT infrastructure that has emerged in response to a fundamental shift in the way enterprises conduct their business. A componentised model has emerged as the natural architecture for web services-based applications. Using Mop-ECATNets formalism (Meta Open Extended Concurrent Algebraic Term Nets) a sort of high-level Petri net, we show, in this paper, how we can ensure the formal specification of dynamic web services and control their interactions as well as their dynamic composition. Furthermore, in order to formally verify and execute web services-based system specifications, we implement Mop-ECATNet model in Maude system using a Model Driven Architecture (MDA) based approach.
Keywords: service-oriented architecture; dynamic web service composition; meta-open ECATNets; MDA; Maude.
MC-Sim: a mobile cloud simulation toolkit based on CloudSim
by Manel Gherari, Abdelkrim Amirat, Ridda Laouar, Mourad Oussalah
Abstract: Mobile Cloud Computing (MCC) has gained a significant attention these past years. MCC consists of migrating mobile applications from the constrained mobile devices to the cloud. This task is highly complicated and demanding, therefore several novel methods, tools, and approaches have been introduced to tackle this complexity. At this point, we argue that a simulation of the deployment mechanisms for accessing cloud services and testing mobile cloud applications in the cloud environment is a mandatory phase prior to real deployment in a real environment. A simulation will offer the developer a controllable and cost-free environment to test and evaluate applications performance according to different predefined scenarios. We can state that MCC lacks tools of simulation of its aspects; to fill this gap we propose Mobile Cloud Simulation (MC-Sim) toolkits based on CloudSim.
Keywords: CloudSim; mobile cloud computing; cloud simulation; mobile cloud simulation; mobile cloud computing modelling.
Improved linear local tangent space alignment and its application to pattern recognition
by Liqing Fang, Yan Lv, Leilei Ma, Ziyuan Qi, Yulong Zhao
Abstract: Considering the drawbacks of the linear local tangent space alignment, a Semi-Supervised Neighbourhood Adaptive Linear Local Tangent Space Alignment (SSNA-LLTSA) is proposed. The distance metric combining the Cosine similarity and the Euclidean distance is used in the algorithm instead of the Euclidean distance, and the algorithm realises the semi-supervised learning and neighbourhood adaptive adjustment by integrating some of the known category information and the method of Parzen window density estimation into the dimensionality reduction process. The simulation experiment of UCI standard data sets and the pattern recognition example of hydraulic pump show that the redefined distance metric has better performance than the Euclidean distance, and SSNA-LLTSA can overcome the defect that LLTSA is unsupervised. Meanwhile, the capability of neighbourhood adaptive adjustment makes the algorithm find the low-dimensional manifold of the data sets more effectively, which can further improve the accuracy of pattern recognition.
Keywords: pattern recognition; dimensionality reduction; semi-supervised learning; neighbourhood adaptive; LLTSA.
Modelling, specifying and verifying self-adaptive systems instantiating MAPE patterns
by Marwa Hachicha, Riadh Ben Halima, Ahmed Hadj Kacem
Abstract: Self-adaptive systems are able to modify their behaviour and/or structure to deal with their continuously changing environment and internal dynamics. MAPE control loops, based on the four steps of monitoring, analysis, planning, and execution, have been identified as crucial elements in realising self-adaptation of software systems. Adaptive systems are generally more difficult to design, specify and verify owing to their high complexity. Ensuring the correctness of the system's adaptation logic is very crucial. This correctness depends also on the time associated with events. In this paper, we propose a refinement approach that aimsfirst to model step-by-step self-adaptive systems that instantiate MAPE patterns for decentralised control in self-adaptive systems. Second, these models are then automatically translated into Event-B specifications that can be proved using the Rodin theorem prover. This formal specification provides a way to verify several relevant properties for self-adaptive systems. We distinguish between three classes of properties: adaptation, system and temporal properties. Adaptation properties are related to adaptation and any self-adaptive system should satisfy them. System properties are specific to the system to be analy ed. Temporal constraints are used to check that all the temporal deadlines are met. We illustrate our approach by modelling and verifying the forest fire detection system that exhibits a self-adaptive behaviour.
Keywords: self-adaptive systems; MAPE patterns; Event-B method; modelling; formal verification; structural; behavioural; refinement.
Special Issue on: ICMIC2015 Modelling, Computing, and Information Fusion
Analysis on sustainable development of manufacturing industry in Hebei Province based on synergetic degree
by Huizhen Kong, Zhi Gao, Shuyang Gao
Abstract: Manufacturing industry plays an important role in an economy and has become the chief wealth-producing sector of an economy. The sustainable development of manufacturing industry requires achieving synergy between the growth of manufacturing industry and environmental protection through innovation of science and technology. The paper tries to use synergetics theory to analyse the issue related to sustainable development of manufacturing industry. It firstly makes a brief introduction about synergetics and synergetic degree model. Next, it determines the subsystems of a sustainable development manufacturing industry system and selects the order parameters of each subsystem. Then, it makes an empirical analysis based on the data obtained from the websites of Hebei Provincial Statistic Bureau and National Bureau of Statistics of People Republic of China. In the end, it analyses the order degree of each subsystem and the synergetic degree of the sustainable development manufacturing industry system, and puts forwards relative suggestions for improving the sustainable development of manufacturing industry based on the analysis. The findings not only provide us the measures for improving the synergetic degree within a sustainable development manufacturing industry system, but also point out the ways for promoting the sustainable development of manufacturing industry through increasing the efficiency of economy, enhancing the utilisation efficiency of natural resources, and reinforcing innovation of science and technology.
Keywords: sustainable development; manufacturing industry; synergetic degree; order degree; synergetics.
Research of intelligent professional search engine based on agent
by Guoxia Yang, Xia Yang, Wei Hao
Abstract: Owing to the increasing growth of network information, users cannot quickly query. Especially for professional information, the query time needed is longer. In order to improve the precision of the professional search engine, after analysing the meta search engine technology, combining the rtf algorithm and the PageRank algorithm, an improved fusion algorithm of search results based on PageRank is proposed, which can query according to the synonym and the relevant word. The algorithm was applied to the search engine for coal geology, and the experimental results showed it can fuse the independent search engine results together in some degree, and increase the precision and the recall ratio of professional engine.
Keywords: meta-search; professional search; results fusion; improved PageRank algorithm; coal geology.
Analysis on seismic dynamic response and liquefaction area of tailings dam
by Chundi Si, Baolin Xiong, Wei Wang
Abstract: Taking a tailings dam in Hebei as the research object, the dynamic response of the dam under action of flood and earthquake is simulated by using a finite element software, and the seismic dynamic responses of the dam with respect to acceleration, stress, displacement, liquefaction area and stability are analysed. The results show that the vertical acceleration increases with the height of the dam, and the horizontal acceleration gradually increases from outside to inside. A larger horizontal and vertical displacement occurs at the 3/4 height of tailings dam. After considering the relative density of the tailings dam and drainage condition, all three kinds of seismic wave cause a small range of liquefaction area. The stability of the tailings dam is calculated with the Sweden Arc Method, showing that the dynamic stability safety factor is 1.257 when considering drainage, which is larger than code value, indicating the tailings dam is stable in the case of earthquake.
Keywords: tailings dam; seismic dynamic response; finite element method; liquefaction area; dynamic stability.
Mechanical acoustic fault diagnosis based on improved semi-blind extraction method
by Nan Pan, Yajun Sun
Abstract: According to statistics, about 30% of mechanical faults are caused by rolling bearing. Two or more combined failures may exist in the rolling bearing when the equipment is running. Many acoustic analyses just show an underdetermined situation because the number of microphones is less than the number of fault sources. In order to deal with these kinds of monitoring problem, a mechanical failure diagnosis method based on reference signal frequency domain semi-blind extraction is proposed. In this method, a dynamic particle swarm algorithm is used to construct improved multi-scale morphological filters, which are applicable to mechanical failure, in order to weaken the background noises; thus a reference signal unit semi-blind extraction algorithm is applied to do complex components blind separation band by band, coupled with J-divergence of complex independent components employed as distance measure to resolve the permutation. Finally, the estimated signal could be extracted and analysed by an envelope spectrum method. Compared with the time-domain blind deconvolution algorithm based on fuzzy clustering, it has several advantages such as being more effective and more accurate. Results from rolling bearing acoustic diagnosis experiment validate the feasibility and effectiveness of proposed method.
Keywords: frequency-domain blind deconvolution; mechanical acoustical diagnosis; J-divergence; reference signal; semi-blind extraction.
Application of EEMD and neural network in stress prediction of anchor bolt
by Hui Xing, Xiaoyun Sun, MingMing Wang, Haiqing Zheng, Jianpeng Bian
Abstract: An estimation method for free bolt stress is described. Acoustic stress wave signals of free bolts were collected under different tensile forces and analysed in the time and frequency domains after mutual correlation. The variations of wave propagation time, fundamental and secondary frequency of signals spectrum are studied. The signals are decomposed into intrinsic mode functions (IMFs) by Ensemble Empirical Mode Decomposition (EEMD). The normalised ratios of energy and correlation coefficients of IMFs are also discussed. Propagation time, fundamental and secondary frequency of signals spectrum, energy ratios and correlation coefficients of IMFs are influenced by applied tensile force. Thus they are selected as the components of eigenvector for inputs of neural network. Back-propagation neural network (BPNN) and genetic algorithm (GA) optimised BPNN are used for tensile force prediction. Eleven sets of data were used to test the stress prediction effect of BPNN after training. The results indicate that the BPNN optimised by GA can achieve small errors for stress prediction.
Keywords: back-propagation neural network; genetic algorithm; acoustic stress wave; ensemble empirical mode decomposition; stress prediction; bearing capacity detection.
Non-destructive test method of rock bolt based on D-S evidence and spectral kurtosis
by Xiaoyun Sun, Haiqing Zheng, Zhiyuan Wang, Jianpeng Bian, Hui Xing, Mingming Wang
Abstract: The length of the rock bolt is an important factor to evaluate the quality of an anchor. According to the fact that the calculated value of anchor length is far different from the actual situation owing to a lot of noise, a de-noising method based on Empirical Mode Decomposition (EMD) and Spectral Kurtosis (SK) is proposed in this paper, to filter noise and to improve the accuracy of calculating anchor length. The fundamental idea is that calculating SK for each component after EMD, the larger SK values are used to reconstruct the signal to improve the signal to noise ratio. The analysis results demonstrate that the method can improve the SK of the reconstructed signal and decrease the error of anchor length. In addition, D-S evidence is introduced to realise high precision computation for anchor length by data fusion of wavelet threshold de-noising and spectral kurtosis filter.
Keywords: spectral kurtosis; anchor; EMD decomposition; wavelet de-noising; D-S data fusion.
Application of control quality evaluation technology in complex industrial process
by Yongwei Li, Yuman Li, Hongfei Wang, Mingxing Chen
Abstract: In a class of time-varying, large delay, non-Gaussian and nonlinear characteristics of complex industrial processes, when the control loop after operation for a period of time, its control quality indicators often gradually deviate from the original design value or even show serious deterioration. The causes of this phenomenon include the changes in operating conditions, disturbances and equipment and instrument failure and other factors. In view of the above problems, it is very important to control the quality of the control loop in the complex industry process and find out why the control quality become poor. The synthetic ammonia decarbonisation is a complex industrial process that contains the characteristics of time varying large delay nonlinearity and non-Gaussian. The crystal size in the complex industrial process of the synthetic ammonia decarbonisation is chosen as the research object, and the control loop is evaluated by the method of control quality evaluation based on the minimum variance. The reasons for the variation of control quality are estimated and predicted by the method of particle filter. The simulation results show that the control quality evaluation method based on the minimum variance and the particle filter method are effective and feasible in order to estimate and predict the quality becoming poor of the control system. The control quality evaluation technique provides a feasible way for the effective control of a kind of complex industrial process.
Keywords: synthetic ammonia decarbonisation; quality evaluation; minimum variance; particle filter.
Study on licence plate location algorithm in complex weather
by Yan Wang
Abstract: An adaptive licence plate location algorithm is proposed to improve the locating accuracy of licence plates in the case of images collected in conditions of complex weather or insufficient light. The algorithm judges the different weather images by colour features and sharpness. The wavelet coefficients are used to adjust the contrast of images. At last, we fuse the vertical protection and template matching algorithms to locate the licence plate. Experiments show the algorithm can locate licence plates in varies weather conditions, such as sunny, rainy, foggy and evening. The average rate of licence plate location can reach 93.4%.
Keywords: colour feature; wavelet coefficients; vertical protection; template matching.
An improved image denoising method based on Contourlet transform and Neighshrink algorithm
by Liu Jian, Li Tong, Wei Song Bo, Xu Ke, Chang Ling
Abstract: Denoising is important in the use of images for non-destructive detection, in order to effectively remove image noise and preserve the good image detail. In this paper, a new improved image denoising method is proposed based on Contourlet and Neighshrink. Firstly, the image of the Contourlet coefficients is obtained by the Contourlet transform. Then, the Contourlet coefficients are contracted by the neighborhood shrinkage method. In order to prevent the threshold from changing over parameters of the decomposition scale, the shrinkage factor is improved. The Contourlet coefficients are processed by the improved threshold and the shrinkage factor. Lastly, the image is denoised by the inverse Contourlet transform. The universal threshold is improved by means of the new method, which combined with neighborhood window coefficient of local parameter and the new convergence factor, is constructed. It means more coefficients have been corrected instead of missing or 'killed in the process of denoising'. Taking elevator fault detection as a practical application example in the simulation study, the images of the elevator machine and the wire rope are denoised after graying. The detection images of the traction motor and wire rope are analysed and compared with other denoising methods, such as the median filter, the wavelet transform and the Contourlet transform denoising algorithms. The simulation experiments show that the improved algorithm can better protect the image details of the elevator machine and the wire rope, avoiding the Gibbs phenomenon.
Keywords: image denoising; Contourlet; NeighShrink; neighbouring coefficients; traction machine; steel wire rope.
Special Issue on: Advances in Computer Graphics and Imaging
Research on the Design of Visual Interface in Information Visualization
by Guangtao Ma, Tao Liu, Yang Zhou, Jun Li
Special Issue on: ICMIC2015 Modelling, Computing, and Information Fusion
Research on face recognition based on DRNLGBP
by Zhenzhou Wang, Xing Xing Xu, Li Li, Wei Liu
Abstract: For facial recognition of those wearing glasses, this paper first proposes a DRNLGBP algorithm based on DIMPCA and non-uniform local Gabor binary pattern method combined with random sampling. The algorithm firstly extracts and supplements the contour by the DIMPCA, and then it adopts the local Gabor binary pattern to represent the facial image, by which characteristic information of multi-scale and multi-direction can be extracted and can make the recognition less sensitive to illumination and robust to noise. The paper also brings up the non-uniform region division strategy, which can ensure sufficient image spatial information acquisition while treating the content information differently at the same time with weakening interference to adjustment from glasses. The method DRNLGBP makes full use of characteristics of random subspace method and binary pattern method, complementing each others deficiencies while optimising each advantages to maximise the effect of recognition. The experimental result shows that this method is more effective for facial recognition rate improvement for those wearing glasses than traditional methods, significantly making the influence of surrounding light degree to a less sensitive extent.
Keywords: non-uniform local binary; DRNLGBP algorithmic; stochastic subspace identification memory controller.
Research on the image segmentation of icing line based on Nsct and 2-D Ostu
by Lin Qi, Jing Wang, Can Dong Li, Wei Liu
Abstract: In allusion to increased noise and blurring of icing line images, this paper proposes a segmentation method based on NSCT and 2-D OSTU, using NSCT to implement de-noising processing of image, introduces combined threshold methods of improved genetic algorithm and 2-D algorithm OSTU for image segmentation, and describes the specific algorithm. The results show that this method can effectively realise the de-noising processing of icing images, making accurate extraction of the target, and reducing the search time, which is convenient for real time applications.
Keywords: NSCT; 2-D OSTU; image segmentation; icing line; improved genetic algorithm.
Construction of logistics level evaluation system and application on Wuhan city circle
by Yanling Xu, Miao Zhang, Jingli Zhang
Abstract: With the development of the global economy, the logistics industry is increasingly playing a greater role in economic development. In this paper, based on entropy method and factor analysis, an evaluation system is built from the aspects of politics, economy, society, transportation and resident consumption level to estimate the logistics levels of the cities in Wuhan city circle. The conclusion illustrates the nine cities in Wuhan city circle have very different logistics levels and can be ranked from the highest to lowest as follows in terms of their logistics level: Wuhan, Huanggang, Xiaogan, Huangshi, Xianning, Ezhou, Tianmen, Xiantao, Qianjiang.
Keywords: index system; logistics level; entropy weight; factor analysis; evaluation.
Special Issue on: Machine Vision and Computational Intelligence in Recent Industrial Practice
Robust Skin Segmentation using Color Space Switching
by Ankit Chaudhary, Ankur Gupta
Special Issue on: Xxxx
A Query Driven Method of Mapping from Global Ontology to Local Ontology in Ontology-based Data Integration
by Haifei Zhang