International Journal of Wireless and Mobile Computing (48 papers in press)
Expected-mode augmentation method for group targets tracking using the random matrices
by Yun Wang, Guoping Hu, Hao Zhou
Abstract: In order to improve the estimation performance of interactive multiple models (IMM) tracking algorithm for group targets, a new EMA-VSIMM tracking algorithm is proposed in this paper. Firstly, by using the expected-mode augmentation (EMA) method, a more proper expected mode set has been chosen from the basic model set of group targets, which can make the selected tracking models match up to the unknown true mode availably. Secondly, in the filtering process of variable-structure interactive multiple model (VSIMM) approach, the fusion estimation of kinematic state and extension state have been implemented by using classical weighting method and scalar coefficients weighting method, respectively. We use the trace of the corresponding covariance matrix of extension state to calculate the weight coefficient. We calculate the prediction value of the extension state parameter by using a fuzzy reasoning approach to improve the estimation accuracy of the covariance matrix, which takes the elliptical area of extension and its change ratio as the input of the fuzzy controller. The performance of the proposed EMA-VSIMM algorithms is evaluated via simulation of a generic group targets manoeuvring tracking problem.
Keywords: interactive multiple models; expected-mode augmentation; group targets; maneuvering tracking.
Evaluation on multithreaded queue test data for multi-channel filter rod forming machine
by Jianhong Cao, Xu Kong, Qi Ji, Min Zhang
Abstract: This paper takes the real-time problems of cigarette industry multithreaded queue test data for multi-channel filter rod forming machine, under the existing evaluation system has not adapted the premise of the entire inspection business, through the information technology tools to assist in establishing business operational standards, and processes involved in the production and business management, based on dynamic statistics analysis the multi-threaded process for different queues to ensure the output results in real time. This method guarantees the DF10 double pole filter rod forming machine 1000 metres per minute production quality control, real-time visualisation of process quality, and fills the trade gap in this technically area.
Keywords: cigarette equipment; multithread; queue; testing data.
Numerical simulation on explosion overpressure features of methane-air premixed gas at different concentrations in utility tunnels
by Shangqun Xie, De-Ying Li, Le-Duan Chen, Rui Zhou
Abstract: According to the structural features of utility tunnels, the origin and development process of combustion and explosion of premixed natural gas with the volume fraction of 5%, 7%, 9%, 11%, 13% and 15% was simulated by fluid dynamics software ANSYS-Fluent. The results showed that the evolution rules of the overpressure and overtemperature produced by the flame front were basically the same within the critical concentration range of methane explosion. Local pressure and temperature jumps in the right of bottom edges were formed, appearing at the maximum overpressure, which was affected by the combustion front and pressure waves together with reflected wave pressure. The combustion process in utility tunnels can be divided into four stages: rapid growth of combustion, steady development of combustion, combustion jump, pressure and temperature oscillating retrenchment after burning. The simulated maximum overpressure is around 1.7 MPa and it is obtained under the conditions when the premixed gas concentration is 9% and 7%.
Keywords: numerical simulation; utility tunnels; explosion; overpressure.
An automatic detection model of pulmonary nodules based on deep belief network
by Zhiyong Zhang, Jialing Yang, Juanjuan Zhao
Abstract: The deep belief network (DBN) is a typical representative of deep learning, which has been widely used in speech recognition, image recognition and text information retrieval. Owing to a large number of CT images formed by the advanced spiral CT scanning technology, a pulmonary nodules detection model based on user-defined DBN with five layers (PndDBN-5) is proposed in this paper. The process of the method consists of three main stages: image preprocessing, training of PndDBN-5, testing of PndDBN-5. First, the segmentation of lung parenchyma is done. Segmented images are cut with minimum external rectangle and resized using the bilinear interpolation method. Then the model PndDBN-5 is built and trained with preprocessed training samples. Finally, testing PndDBN-5 with preprocessed testing samples is completed. The data used in this method are derived from The Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), which is the largest open lung nodule database in the world. The experimental results show that the correct rate of PndDBN-5 model for pulmonary nodule detection reached 97.5%, which is significantly higher than the traditional detection method.
Keywords: deep belief network; contrastive divergence; pulmonary nodules; detection.
Multi-threads computation for aggregation of time-series data
by Wang Jie, Lu Jingyi
Abstract: Applications involving time-series data have become popular with the rapid improvement of smart terminals and wireless networks. For example, in the case of mobile sensing, a sensing user will get a private input in each time period. And during the same period, the aggregator wants to calculate the aggregation statistics from the private inputs of sensing users. The privacy issue becomes much more challenging in the case of an untrusted aggregator. We are trying to increase the computation efficiency of the untrusted aggregator. Multi-cores architecture based CPU has been widely applied for not only personal computers but also servers. It has been an indispensible field in our everyday life. In this paper, we take advantages of multi-threads computation to a scalable basic aggregation protocol, and improve the computation efficiency of the trusted aggregator. We conduct some experiments to compare it with the basic protocol. The conducted experiments show the computation efficiency of our proposed protocol.
Keywords: cryptography; privacy; time-series data; multi-threads.
Low financial cost with ant colony optimisation in intelligent agriculture
by Xu Gaofeng
Abstract: With the development of wireless sensor networks, industrial automation and other computer and information related high technologies, a lot of practical IoT applications have greatly increased the productivity. Currently, more and more capital is being invested in IoT, especially intelligent agriculture as many countries begin to pay more attention to basic and intelligent agriculture. For large intelligent agriculture systems, it will cost a lot of time and energy (which further will cost investors' money) for the mobile sink to collect all the data of the sensing system with the help of cluster head node. In this paper, we try to solve this issue that minimizes the data collection path of the mobile sink, with the help of the ant colony optimisation algorithm. We implement the algorithm in Python and conduct two experiments that show that we can get the best path of the given example and show how the efficiency changes when the numbers of ants and loops increase. The better the optimal path becomes, the less financial cost we can achieve.
Keywords: financial cost; wireless sensor network; ant colony optimisation; intelligent agriculture.
A hybrid training method of convolution neural networks using adaptive cooperative particle swarm optimisation
by Genfu Xiao, Huan Liu, Weian Guo, Lei Wang
Abstract: In order to deal with the problem of easily falling into local minimum in convolution neural networks (CNN) training, a hybrid training algorithm based on heuristic algorithm is proposed. Firstly, an adaptive cooperative particle swarm optimisation (ACPSO) is proposed, which uses a learning automaton to adaptively divide the subpopulation of the cooperative particle swarm optimisation (CPSO) and lets the decision variables with strong coupling relationship enter the same subpopulation. The adaptive strategy improves the ability of the CPSO algorithm to solve the high dimensional problem. Then, the connection weights of CNN are considered as elements in particles, and the ACPSO algorithm is used to train the CNN. The output of the ACPSO algorithm is applied as the initial weight of the BP algorithm for the purpose of speeding up the training speed of the CNN. The experimental results show that the ACPSO-BP algorithm has achieved good results, and the recognition rate of the CNN is improved. Thus it has the potential to be applied to other deep learning fields.
Keywords: convolution neural networks; cooperative particle swarm optimization; learning automata; BP algorithm.
Research on robust reduction control method of steering-by-wire based on MBSE
by Huipeng Chen, Chen Yue, Guojin Chen, Chang Chen
Abstract: Based on the theory and method of MBSE, a model of a Steering-By-Wire (SBW) system with mechanical and electrical integration is established. Based on the model, a robust control strategy with H∞ mixed sensitivity is used, and a robust controller is designed. The high order robust controller is poor in real-time and has a high cost. Routh, Hankel norm and ISE index reduction method are used to reduce the controller. Through time domain and frequency domain analysis, the effects of various reduction methods on the controller are discussed. Simulation results show that the ISE index reduction method has better reduction effect and has good robust performance and robust stability.
Keywords: MBSE; steering-by-wire; sensitivity; robust control; model reduction.
Trajectory optimisation design of robot based on artificial intelligence algorithm
by Li Huang, Kai Zhang, Wei Hu, Chengcheng Li
Abstract: Artificial intelligence has attracted more and more attention and has been widely used in all walks of life, especially in the education industry, where it has gradually become the core. Aiming at the problem of robot trajectory planning in artificial intelligence, this paper applies the project teaching method to the course of artificial intelligence, regards trajectory planning as a project, analyses and studies it, and uses ant colony algorithm to find the optimal planning path. Through the teaching of the project, the students will understand the ant colony algorithm more deeply. The algorithm is programmed independently to achieve the final trajectory optimisation. Students become the main body of the classroom, give full play to the initiative and enthusiasm of the students, through the operation of the project to train the students' innovative ability and cooperation ability, and improve the overall quality of the college students.
Keywords: trajectory planning; project teaching method; artificial intelligence; ant colony algorithm.
Intelligent evaluation and computation of food packaging culture in Shanghai
by Zhen Wei, Wei Zhang, Chunhong Sun
Abstract: Presently, the priority for design in Shanghai is to quantitatively evaluate food packaging culture connotation with intelligence. This paper introduces analytic hierarchy process (AHP) to establish a Shanghai food packaging culture evaluation system and determine its index factors with ample computation. By selecting 50 sets of sample data, using artificial intelligence (AI) and back propagation (BP) neural network, the paper builds up Shanghai food packaging intelligent evaluation system, and provides a theoretical basis for the scientific computation on Shanghai food packaging culture connotation.
Keywords: Shanghai; food packaging; intelligence; evaluation; computation.
An efficient access control scheme based on CP-ABE with supporting attribute change in cloud storage systems
by Tao Ye, Yongquan Cai, Xu Zhao, Yongli Yang, Wei Wang, Yi Zhu
Abstract: The CP-ABE-based access control scheme, which can better realise the access control of many-to-multi-ciphertext shared in the cloud storage architecture, is still faced with the problems that the system cost is too large and the policy attribute revocation or restoration is not flexible. This paper proposes an efficient access control scheme based on CP-ABE with supporting attribute change in cloud storage system. The fine-grained access control can be achieved by re-encryption mechanism which takes the minimum shared re-encryption key for policy attribute set. Then the access structure tree is expanded by creating a corresponding virtual attribute for each leaf node attribute. The analysis results of the scheme indicate that not only are the efficiency and flexibility of the attribute change improved, but also the system cost is reduced.
Keywords: access control; policies attribute change; cloud storage; ciphertext-policy ABE.
Sliding mode control with PI-based saturation for nano-positioning
by Liu Yang, Donghao Xu
Abstract: This paper proposes a modified sliding mode controller design with proportion-integral (PI)-based saturation (PISSMC) for nano-positioning of piezoelectric actuators (PEAs). Based on the sliding mode theory, the controller can consider hysteresis as the uncertainty of the system, and the nonlinearities of hysteresis and model imperfection can be processed to achieve precise positioning and tracking control. The PI term of this controller can decrease the steady-state error of the system and alleviate the chattering of the discontinuous part of the SMC controller. Further, as the only measurable information is the position, a high-gain observer is adopted to estimate the states. The designed controller employs a linear PEA system as parameters estimation of the model to estimate the control gain and compensate for the process nonlinearity. The robust stability of the PISSMC is proved through a Lyapunov stability analysis. Experimental results demonstrate that compared with the traditional SMC, the proposed controller can accomplish better control performance, such as more accurate resolution, less steady-state error and slighter chattering.
Keywords: sliding mode control; piezoelectric actuators; hysteresis; nano-positioning; nonlinear system.
Detection of malicious domain names based on an improved hidden Markov model
by Tang Hengliang, Dong Chengang
Abstract: The ability to detect malicious domain names is critical for protection against internet security, data theft, and other dangers. Current methods for recognising malicious domain names have demonstrated poor detection accuracy in dealing with massive data. This paper proposes a novel malicious domain name detection method based on an improved Hidden Markov Model (HMM). First, by analysing various characteristics of good and evil domain names in DNS communication, we can use Spark fast extraction to distinguish their attributes; Then we can quickly classify unknown domain names accurately by using Baum-Welch algorithm and Viterbi algorithm in Hidden Markov Model (BVHMM) to achieve the effective detection of malicious domain names; Finally, to test our approach, we conducted a series of experiments, and the experimental results demonstrated that our model achieved good accuracy and recall rate compared with other detection models.
Keywords: malicious domain names; hidden Markov model; Baum-Welch algorithm; Viterbi algorithm; Spark.
Corrugated fractal monopole antenna with enhanced bandwidth for ultrawideband applications
by Rajeshkumar Venkatesan, Rajkumar Rengasamy
Abstract: A very compact coplanar waveguide (CPW) fed fractal monopole antenna with a modified ground plane is presented. The main objective is to obtain ultrawideband (UWB) characteristics from a simple microstrip monopole antenna. A wideband behaviour and good impedance matching are obtained by modifying the ground plane to semi-trapezoidal shape. Further, the self-similar fractal nature is introduced in the radiating element to enhance the bandwidth. The proposed antenna shows a wider impedance bandwidth from 3 GHz to 11.2 GHz for S11 ≤ 10 dB. A fractional bandwidth of about 115.5% (impedance bandwidth ratio 3.73:1) is achieved for the third fractal iteration. The total volume of the presented antenna is 18
Keywords: CPW; fractal antenna; self-similar; ultrawideband; wireless communication.
Mathematical modelling and analysis of hierarchical modulation in AWGN and Rayleigh channel.
by Kala K. Chandra, J. Jayakumari
Abstract: In digital video broadcasting, either multifrequency or single frequency network is used to transmit local and global broadcasting contents, respectively. Multifrequency network consumes large spectrum to transmit local information alone. Therefore an efficient technique is required to embed both local and global content in a single constellation. In this paper, hierarchical modulation or multilayered modulation is employed to satisfy this requirement in which the task is achieved by layered constellation. The base layer carries the high priority global contents and the low priority information by the enhancement layer. The performance of the system is highly determined by the detection rules and the coder chosen. The performance of hierarchical modulation system is analysed by framing decision rules for both high priority and low priority streams. In addition to derivation of probability of error of the system, the analysis of bit error rate of coded and uncoded system is done. Convolutional encoder with code rate 1/3, 1/2 and 2/3 is used in this paper.
Keywords: single frequency network; multifrequency network; QPSK; QAM hierarchical modulation; multilayer modulation; digital video broadcasting.
Application of Q-learning based on adaptive greedy considering negative rewards in football match system
by Xue Fei, Li Juntao, Yuan Ruiping, Liu Tao, Dong Tingting
Abstract: Aiming at the problem that the multi-robot task allocation method in a soccer system can easily fall into the problem of local optimal solution and real-time performance, a new multi-robot task allocation method is proposed. First, in order to improve the speed and efficiency of finding optimal actions and make better use of the disadvantages that traditional Q-learning cannot often propagate negative values, we propose a new way to propagate negative values, that is, Q-learning methods based on negative rewards. Next, in order to adapt to the dynamic external environment, an adaptive ε greedy method of which the mode of operation is judged by the ε value is proposed. This method is based on the classical ε-greedy. In the process of solving problems, ε can be adaptively changed as needed for a better balance of exploration and exploitation in reinforcement learning. Finally, we apply this method to the robot's football game system. It has been experimentally proven that dangerous actions can be avoided effectively by the Q-learning method which can spread negative rewards. The adaptive ε-greedy strategy can be used to adapt to the external environment better and faster so as to improve the speed of convergence.
Keywords: task assignment; Q-learning; negative reward; ε algorithm； adaptive technology.
Full-duplex relay selection analysis for decode and forward and amplify and forward relaying
by Fatima Ezzahra Airod, Houda Chafnaji, Ahmed Tamtaoui
Abstract: In this paper, we explore the cooperation over a modern wireless communication network, where we promote the communication between a pair of moving nodes, the source and the destination, to exchange information. We assume that fading constraints overrun this environment, so accordingly the direct link between the source and the destination nodes is not considered. Therefore, full-duplex (FD) relays cooperate with the source to send data packets to the destination. In this new generation of networks, the crucial issue for wireless devices is their limited battery capacity that impacts mainly, the network lifetime. Note that this constraint has as much as importance when devices forward data to other terminals. Thus, with the regard of keeping a good compromise between the power consumption and the system performance, this paper studies an optimal relay selection to select one best relay to forward data to the destination based on Decode-and-Forward (DF) and Amplify-and-Forward (AF) relaying techniques. We derive the DF and AF outage probability closed form expressions and the AF numerical approximation for the relay selection strategy. For verification, simulation results are presented. We also perform an analysis of asymptotic results in order to evaluate the impact of the power transmission on the system performances.
Keywords: full-duplex relay; relay selection; amplify-and-forward; decode-and-forward; Doppler effect; outage probability; power transmission.
A novel quantum-inspired binary wolf pack algorithm for difficult knapsack problem
by Yangjun Gao, Fengming Zhang, Yu Zhao, Chao Li
Abstract: 0-1 knapsack problem is a classical combinatorial optimization problem, which is often used to validate the search performance of binary intelligent algorithms. Although the traditional binary wolf pack algorithm (BWPA) can provide an effective solution to the general knapsack problem, it cannot achieve satisfied optimization results for the difficult knapsack problems such as the high-dimensional KP01 and often fall into the local optimum in some extreme cases. In order to improve the BWPAs applicability and searching ability in difficult knapsack problem which has not been well resolved, a novel Quantum-Inspired WPA (QWPA) which based on quantum encoding to enhance the performance of WPA for difficult knapsack problem is presented. In this paper, we have introduced the detailed quantitative design of the three important behaviours in presented QWPA and a modified form of quantum collapse which brings better diversity has been proposed. Moreover, a new diversity analysis mechanism is given to verify the diversity of the proposed algorithm compared to other quantum-inspired intelligent algorithms which including QIEA-PSA, QPSO, and QGA. Numerical simulation is obtained from both general and difficult benchmark instances of knapsack problem and the simulation results show that the QWPA has a more competitive performance than other Quantum-Inspired algorithms with the increasing of the size of knapsack problems
Keywords: binary wolf pack algorithm; quantum encoding; combinatorial optimization; diversity; difficult 0-1 knapsack problem.
A game theoretic approach to maximise payoff and customer retention for differentiated services in a heterogeneous network environment
by Pushpa Singh, Rajeev Agrawal
Abstract: Future networks are being devised with the vision of heterogeneity in which a mobile user/device will be able to connect seamlessly to multiple wireless networks (WLAN, cellular, WMAN, WPAN) and evolve simultaneously. Coexistence of the underlying network is the requirement of telecom industry, which leads to an open competition among the service providers. To survive in the market, telecom operators are investing more in retaining the valuable users rather than acquiring new users. This paper introduces the user agent to check the loyalty of user and application preference, and the network agent is used to rank the network as social, quality and normal network. The user can also set his preference as social trust, quality trust and normal trust. The game between the user agent and the network agent constructs a payoff matrix for loyal users and normal users. Results show seven equilibrium cases for loyal users where the user agent and network agent have equal payoff. In the case of normal users, there is only one case of equilibrium and for the other cases the network agent can maximise his payoff.
Keywords: heterogeneous network; QoS; loyalty; payoff; game theory; traffic class; service provider.
Reliable and energy-aware routing in mobile ad-hoc networks
by Sajal Sarkar
Abstract: In a Mobile Ad-hoc Network (MANET), energy-awareness is a crucial design issue as it consists of a group of mobile nodes. The mobile nodes with limited battery power act as router in MANET. Though establishment of an appropriate and efficient route is an important design aspect, a more challenging task is to establish and select a reliable and energy-efficient route between a source-destination pair. Thus, power failure of a mobile node constituent influences data routing, link failure and network lifetime. Therefore, to meet the above mentioned goal and overcome energy-aware routing design issues, in this paper routing protocols are proposed to construct a reliable and energy-aware route considering energy consumption and remaining energy of nodes. The remaining energy and the energy factor (the ratio of remaining energy and initial energy of a node) are used as important parameters for selection of a node in a route. Under the considered parameters, the proposed routing protocols ensure reliability and energy-awareness in the MANET and avoid link failure due to the node's low power in an established route. Simulation results show that the proposed routing protocols perform better than the similar kind of popular existing routing schemes in terms of energy consumption, throughput, delay and routing overhead in different network scenarios.
Keywords: MANET; routing protocol; energy consumption; energy-aware routing; reliability.
IPCA-SVM based real-time wrinkling detection approaches for strip steel production process
by Tong Zhao, Xiong Chen, Lirong Yang
Abstract: Strip steel wrinkling is one of the common problems in strip steel production line. The wrinkling phenomenon has a serious impact on the quality of the products, resulting in product waste, and even leading to the entire production line downtime. The key point to solve the problem is real-time detection for strip wrinkling while making an early warning. This paper proposes an IPCA-SVM based online wrinkling detection approach. IPCA is used to compress each frame image from industrial camera and extract effective features from frame images. The projection coefficients of each frame image on the principal components are the inputs to SVM model for classification. Experiment results show that the proposed method is valid for real-time wrinkling detection for strip steel production process.
Keywords: strip wrinkling; IPCA-SVM; real-time detection.
Constrained solution of CEC 2017 with monarch butterfly optimisation
by Hui Hu, Zhaoquan Cai, Song Hu, Yingxue Cai, Jia Chen, Sibo Huang
Abstract: Recently, inspired by the behaviour of monarch butterflies in North America, Wang et al. proposed a new kind of swarm intelligence algorithm, called Monarch Butterfly Optimisation (MBO). Since it was proposed, it has been widely studied and applied in various engineering fields. In this paper, we apply MBO algorithm to solve CEC 2017 competition on constrained real-parameter optimisation. Also, the performance of MBO on 21 constrained CEC 2017 real-parameter optimisation problems is compared with five other state-of-the-art evolutionary algorithms. The experimental results indicate that MBO algorithm performs much better than the other five evolutionary algorithms on most cases. It is strongly proven that MBO is a very promising algorithm for solving constrained engineering problems.
Keywords: monarch butterfly optimisation; migration operator; butterfly adjusting operator; constrained optimisation.
Novel localization algorithms in wireless sensor networks
by Abdelali Hadir, Khalid Zine-Dine, Mohamed Bakhouya, Jamal El Kafi
Abstract: Localisation precision is one of the predominant challenges in static and mobile wireless sensor networks. It is a critical issue to be tackled when developing applications that rely on this type of network. This paper presents three localisation techniques, named eDV-Hop1, eDV-Hop2, and eDV-Hop3, based on geometry principles. The performance of these techniques was evaluated using the network simulator (OMNeT++) and compared with the basic DV-Hop, iDV-Hop1, and iDV-Hop2. Results show that significant improvement is obtained in terms of energy consumption and localisation error according to several parameters, mainly the number of sensors, the number of anchor nodes, and the communication range of sensor nodes.
Keywords: wireless sensor networks; localisation techniques; simulations and performance evaluation.
Surface EMG electrode distribution for thumb motion classification based on wireless communication equipment
by Wanfen Xu, Gongfa Li, Zhaojie Ju, Honghai Liu
Abstract: The interaction between humans and computers has become more necessary and more specific, and the informatisation of human hands has made the human-machine interaction based on gesture recognition more and more extensive. The thumb, as the most important finger, plays a decisive role in decoding the gesture, especially in controlling of the smart phones and many other smart devices. As a result, this study aims to decode the different thumb gestures from sEMG signal and to improve the robustness of gesture recognition and decrease the influence of physiological conditions and the electrode displacement between different users. In this article, we use the Bluetooth wireless communication and focus on the relationship between the EMG signal and the electrode identifier number. We change the electrode's number into a new feature and combining the traditional features with the new features to verify the electrode's number has a correlation with the thumb gesture. Experiments show that after adding new features, the gesture recognition rate has increased.
Keywords: EMG; thumb; gesture recognition; wireless communication.
Survey on WiFi infrastructure attacks
by Rui Guo
Abstract: This article describes WiFi hacking techniques that attackers have used, and suggests various defensive measures. It also shows how easy it is to forge disassociation and deauthentication packets. Its less secure than wired connections because an intruder does not need a physical connection. It also explains man-in-the-middle attacks, Rogue AP, Race Conditions attacks, in wireless networks, and gives a list of selected open-source tools. The article includes several recommendations that will help to improve security in a wireless infrastructure.
Keywords: WiFi network; Rogue AP; Race Conditions; MITM.
A novel DV-hop method based on coupling algorithm used for wireless sensor network localisation
by Yechuang Wang, Penghong Wang, Jiangjiang Zhang, Xingjuan Cai, Wuchao Li, Yanyan Ma
Abstract: Wireless sensor network (WSN) localisation is an essential requirement in the increasing prevalence of WSN applications. As an important part of the Internet of Things (IOT) it has become a hot research area. Distance vector-hop algorithm (DV-Hop), an range-free algorithm, is widely deployed to solve the localisation problem in WSN. However, the results of the estimation precision are usually not satisfactory. In order to improve the WSN positioning accuracy, in this paper, we propose a new coupling algorithm based on bacterial foraging algorithm (BFA) and glowworm swarm optimisation (GSO) (BFO-GSO). The algorithm has good convergence speed, local search ability of BFO and global convergence of GSO. The optimisation performance is verified by CEC2013 benchmarks in those designs against the original algorithm. Furthermore, Wilcoxons rank-sum non-parametric statistical test and Friedman test were carried out to judge whether the results of the proposed algorithm differ from those of the other algorithms in a statistically significant way. The numerical results prove that it is able to significantly outperform others on majority of the benchmark functions. Finally, the proposed algorithm is also combined into the DV-Hop algorithm to improve the WSN positioning accuracy. Experimental results show that our improve algorithm achieves better performance when compared with others DV-Hop algorithms.
Keywords: WSN; localisation; DV-Hop; coupling algorithm; BFO algorithm; GSO; CEC2013.
Demand estimation of water resources based on algorithm comparison
by Junyan Wang, Jiangjiang Zhang, Xingjuan Cai, Yanyan Ma
Abstract: Water is the source of life and the correct assessment of water resources is an important prerequisite for the rational use of water resources. In this paper, water resources are evaluated and predicted by three different algorithms, including Bat Algorithm (BA), Particle Swarm Optimisation (PSO) and Pigeon-inspired Optimisation (PIO). Comparing the errors of water resources assessed for the three algorithms, we select an algorithm of the minimum error to predict the future water demand. In the experiments, firstly, the water data from 2003 to 2012 are used to find the optimal weights of the models. Then the weight factor is combined with the given model to gain the error between predicted value and the rest data (2013-2015). Finally, the simulation results show that PIO algorithm has a better performance than the BA and PSO algorithms.
Keywords: water resources; bat algorithm; particle swarm optimisation; pigeon-inspired optimisation.
Research on parameter search of the worst operating condition for explosion overpressure in utility tunnels based on genetic algorithm
by Shangqun Xie, De-Ying Li, Hui Lv, Rui Zhou
Abstract: In this paper, the 2D numerical simulation model for the gas pipe tank of utility tunnels is established. Aiming at optimising the maximum overpressure produced by an explosion in the gas pipe tank, in restricted conditions of vent position, premixed gas concentration in the tank and ignition position, a method of parameter optimisation of the worst operating condition for explosion overpressure in the gas pipe tank of utility tunnels is proposed by combining computational fluid mechanics and genetic algorithm. The results show that genetic algorithm is feasible in searching for the worst operating condition for explosion overpressure in the gas pipe tank of utility tunnels and can improve the searching efficiency significantly. Methane-air premixed gas under the two conditions being both pre- and post-optimised can form deflagration phenomenon. The deflagration wave is the direct factor of the overpressure formed at the boundary of the model. Both the pressure and temperature imposed by the deflagration wave acting on the model boundaries show an evident rise compared with those before optimisation. The maximum overpressure is increased by 15% and the maximum temperature is increased by 7%.
Keywords: genetic algorithm; utility tunnel; explosion overpressure; numerical simulation.
A novel method for user relationship measuring in social networks
by Jie Wang, Chonghuan Xu
Abstract: Recommender systems are widely used to provide users with appropriate items, and have emerged in response to the problem of information overload. The measuring method of user relationship in social networks is the core of personalised recommendation. To a certain extent, the measuring quality of users relationships determines the accuracy of recommendation results. In this paper, we propose a novel measuring method of user relationship that considers direct and indirect relationships among users. The experimental results on two famous microblog datasets shows that the presented algorithm is of high performance.
Keywords: online social networks; user relationship; direct relationship; indirect relationship.
Contact analysis and simulation of high performance round link chain
by Xiangjuan Bian, Youping Gong, Longbiao Gao
Abstract: High performance round link chains are applied in many fields, such as mining, metallurgy, hoisting, shipping, etc., and accidents can easily happen under bad and complicated working conditions. This paper studies the dynamic analysis of the round link chain transmission process. The kinematics analysis is carried out first, and then the dynamic analysis is carried out after the force analysis of each component. By establishing the mathematical equation of the structural model of the round link chain, the two static analysis models for the contact of the chain links are derived. Then, the collision process between the round link chains is simulated and analysed. Finally, the fatigue fracture mechanism of round link chain and the propagation law of fatigue crack are studied, and experiments verified that the round link chain satisfies the actual requirement in special needs such as mining.
Keywords: round link chain; kinetic analysis; fatigue analysis; numerical simulation.
A dynamic resource allocation scheme based on cognition in LTE system
by Junshe Wang, Yanfei Wang, Songhua Wang
Abstract: In this paper, we propose a dynamic spectrum allocation scheme based on cognition in LTE system. The new scheme is to address the poor communication service problem caused by co-channel interference between the cell-edge users in the LTE system. The scheme leverages the cognitive characteristic in the LTE system to enable the base station to dynamically obtain the idle resource status information of the adjacent cells and integrates the idle resource information of the target cell, and then employs the ant colony optimisation technique to allocate the resource blocks to users. Experimental results show that the proposed scheme allows the cell-edge users to dynamically use the idle resource blocks of adjacent cells, which enhances resource blocks usage and system throughput while ensuring fairness among users, which may improve the quality of user service at the cell-edge.
Keywords: LTE system; resource allocation; cell edge user; cognitive characteristic; ant colony optimisation.
Energy balanced adaptive clustering routing protocol for heterogeneous wireless sensor networks
by Hu Zhongdong, Wu Hualin, Wang Zhendong
Abstract: In wireless sensor networks (WSNs), the main problem is how to design an energy efficient routing protocol, but one of the bottlenecks is that the WSN's energy is limited. Owing to the current cluster routing protocols unconsidered node location and adopted single hop routing mechanism in routing communication in heterogeneous WSNs, a large number of cluster heads that are far away from the base station will consume a large amount of energy. In this paper, an energy balanced adaptive clustering routing protocol is proposed for heterogeneous WSNs, node location and the residual energy are considered to improve the cluster heads elected mechanism, which increases the probability to become cluster heads that the nodes are close to the base station and have high residual energy. In addition, the protocol uses an adaptive routing communication mechanism combining multi-hop with single-hop to balance the network energy consumption. Theoretical and simulation results show that compared with DEEC and SEP, the protocol can prolong the lifetime of the network and increase the network throughput.
Keywords: heterogeneous wireless sensor networks; energy consumption; adaptive; clustering protocol.
Efficient multi-vehicle navigation based on trajectory vector features considering non-uniform destination distribution for emergency evacuation
by Yang Cao, Zhiming Ding, Fujie Ren, Limin Guo
Abstract: In recent years, large-scale events have been held frequently, and more and more people are participating in these activities. When encountering an emergency, it is necessary to quickly evacuate the participating people. A reasonable traffic evacuation plan is an important part of the efficient evacuation. However, the uneven geographical distribution of a large number of vehicles and participants poses a challenge for efficient evacuation planning. An efficient emergency evacuation plan needs to minimise evacuation time and traffic congestion. Reasonable route selection and traffic flow assessment are key to the evacuation plan. In this paper, we propose an efficient multi-vehicle navigation method based on trajectory vector features considering non-uniform destination distribution for emergency evacuation. First, we employed the CrossRank algorithm to extract the real-time state vector of roads and then navigate the vehicles based on these state vectors. In addition, spatial diversity theory is introduced into our model for the non-uniform distribution of multi-vehicle evacuation. We conduct a series of multi-vehicle navigation simulation experiments on a real taxi trajectory dataset. The experimental results demonstrate that our approach is effective and efficient.
Keywords: multi-vehicles navigation; vector features; trajectory data; non-uniform
destination distribution; emergency evacuation.
A novel firefly algorithm for parameter estimation
by Gan Yu
Abstract: Firefly algorithm (FA) is a recently proposed optimisation technique, which has shown good optimisation performance. However, FA suffers from slow convergence and low accuracy of solutions. To improve this case, this paper presents a novel FA (NFA) by combining two strategies. First, a local search operator is constructed for better fireflies in the population. Second, a concept of opposition-based learning is used for improving the accuracy of the global best solution. The experiment consists of two parts: 1) seven classical benchmark functions are used to verify the optimisation ability of NFA; and 2) NFA is used for parameter estimation of frequency modulated sound synthesis. Simulation results show our NFA approach can achieve promising performance.
Keywords: firefly algorithm; local search; opposition; parameter estimation.
New blind equalisation for non-constant modulus signals using a segment cost function
by Wei Rao, Huijun Xu, Jianqiu Zhang
Abstract: It is well known that for constant modulus (i.e., magnitude) signals the famous constant modulus (CM) blind equalisation algorithm implemented in a fractionally spaced equaliser can present a zero steady-state mean square error (MSE), which means completely eliminating the distortions introduced in transmitting signals through channels. But for non-constant modulus signals it suffers a large steady-state MSE. In order to overcome this defect, a segment cost function according to the CM criterion is suggested. The distinctive feature of the segment cost function is that the equalised signals (of the non-constant modulus signals) are divided into three segments to form a n shape where the ideal signals have a constant modulus instead of non-constant. Then a new blind equalisation algorithm seeking to minimise this segment cost function by applying a stochastic gradient method is proposed. When employing the proposed algorithm to equalise the 4-PAM or 16-QAM non-constant modulus signals, just as using the CM blind equalisation algorithm to equalise the 4-QAM constant modulus signal, a zero steady-state MSE can be obtained, which is derived. Compared with the classical bind equalisation algorithms, such as CMA, MMA, MCMA, or CMA+SDD, the proposed algorithm yields improved performance, especially for higher SNR.
Keywords: adaptive equaliser; blind deconvolution; blind equalisation; constant modulus algorithm.
A novel estimation model for user relationship intensity in social network
by Huijian Xu, Wanqiong Tao, Feipeng Guo
Abstract: With the development of social networks, the relationship intensity of social network users has become an increasingly important topic. This paper proposes an approach based on Sina and Tencent microblog, which can be used to calculate the relationship intensity among users. It has considered the various relationship intensities in seven different fields, such as working, shopping, travelling, sports, entertainment and so on. However, most of the existing approaches only focus on the direct relationship intensity between different users in one activity field. They havent taken the indirect relationship intensity into consideration. Therefore, in this paper we propose a general relationship intensity that consists of both direct and indirect relationship intensity in the same activity field, even if there is only the indirect relationship between users. We conduct the experiment on Sina and Tencent microblog datasets, using the users profile and interaction activities information. The analysis results on real datasets show that our approach achieves performance superior to the existing methods.
Keywords: social network; relationship intensity; direct relationship; indirect relationship.
A multiple relay selection scheme Based on QPO in cognitive relay networks
by Gao Hongyuan, Su Yumeng, Zhang Shibo
Abstract: Cognitive relay networks, which can increase the channel gain of wireless transmission and strengthen the anti-fading ability of the channel, have recently been considered as an effective way to improve the throughput of a cognitive radio system. Therefore, determining the appropriate relay selection scheme is of vital importance to improve the quality of communication. In this paper, we study the difficulty of multiple relay selection (MRS) in cognitive relay networks (CRNs). Considering the scenario of spectrum sharing, we adopt simple power control strategy to limit the power of secondary sources and relays in order to satisfy the interference constraint. To get a better solution for the discrete MRS problem in CRNs, we propose a novel intelligent algorithm which is named as quantum-inspired physics optimisation (QPO) algorithm. For QPO, the law of gravity, Newton's second law, and quantum mechanism are combined effectively. We have designed three different quantum rotation angles. Based on the quantum mechanism, the convergence rate and the searching ability of the algorithm are improved. The good performance of the proposed scheme in MRS is demonstrated according to the simulation results.
Keywords: cognitive relay networks; multiple relay selection; quantum-inspired physics optimisation; intelligent algorithm.
An evolutionary model of urban comprehensive service function based on cooperative development
by Bo Wei, Hui Zheng, Gang Chen, Xianliang Zong, Fuying Zhang
Abstract: The level of urban comprehensive service function reflects the state of a city's sustained, coordinated and healthy development. It is the essence of a city's competitiveness. With continuous expansion of a citys scale, finding key driving forces to enhance urban comprehensive service function, and developing its subsystems and elements coordinately have become an important basis for government decision making, especially for making industrial development policies. An urban comprehensive service function mainly includes five subsystems: transportation, financial, trade and business, high-end manufacturing and social environment service. Interactions among these subsystems are generally nonlinear and constrained by external factors. In this study, firstly, theoretical analysis and expert consultation method are used to select state parameters which are representative, available and reliable. Through calculating correlation degree of these parameters by canonical correlation analysis, parameters with higher correlation coefficient are selected as the state parameters of urban comprehensive service function system. Then, by establishing a collaborative development model, we quantitatively describe the nonlinear interaction among the five subsystems, and obtain order parameters-main forces behind coordinated development of urban comprehensive service function. In this study, a northern China city, Tianjin, is selected to illustrate the mathematical model. The calculation results show that the decisive order parameters of urban comprehensive service function for Tianjin are: available tonnage of civil aviation, domestic and foreign currency deposits per capita, scale of social financing, gross import and export value of customs per capita, output value of high-tech industry, number of patent authorisation per capita and annual volume of urban garbage disposal. This result corresponds to the actual development of the city in recent years
Keywords: urban comprehensive service function; collaborative development model; self organisation; order parameter.
Computational intelligence based energy-efficient routing protocols with QoS assurance for wireless sensor networks: A survey
by Tarunpreet Kaur, Dilip Kumar
Abstract: Over the decades, wireless sensor networks (WSNs) have reached great heights and started to emerge into various applications, ranging from health care to multimedia transmission. In these application domains, energy efficiency and quality of service (QoS) assurance remains a challenging issue owing to dynamic network conditions and resource-constrained nature of sensor nodes. This challenging issue has received considerable research attention at the network layer, which requires efficient routing protocols to meet the application-specific requirements. Therefore, WSN researchers have turned to different Computational Intelligence (CI) techniques in an attempt to address various routing issues in WSN. This paper presents a systematic survey on CI techniques based routing protocols in WSN. Moreover, a comparative analysis of reviewed protocols with their strengths and limitations is also included in the survey. Finally, this paper discusses various potential directions that guide researchers to design efficient routing protocols by combining WSN with CI techniques
Keywords: quality-of-service; routing protocol; energy-efficiency; end-to-end delay; packet delivery ratio; computational intelligence.
A novel evaluation method of roundness error based on equilateral polygon search algorithm
by Feng-hua Xu, Shenghuai Wang, Jie Wang
Abstract: For the evaluation of roundness error, a novel roundness error evaluation method is introduced, which is based on the equilateral polygon search algorithm. The principle and the calculation steps of the evaluation method for roundness error are described in detail. The proposed method is that a series of certain length of equilateral polygons are set with the centre of the least squares circle of the measured roundness firstly, the radius values of all the measured points are calculated using every vertex of the equilateral polygon as the new centre secondly. Roundness error values according to minimum circumscribed circle method, maximum inscribed circle method, and minimum zone method according to relevant standards are obtained through comparison, judgement and reinvention of equilateral polygons. Simulation and experiment results indicate that the evaluation of roundness error can be satisfied by the evaluation method of roundness error based on equilateral polygon search algorithm.
Keywords: roundness error; roundness evaluation; equilateral polygon; search algorithm.
Filling missing values by local reconstruction for incomplete label distribution learning
by Xue-Qiang Zeng, Su-Fen Chen, Run Xiang
Abstract: Label Distribution Learning (LDL) deals with the problems when we care more about the relative importance of different labels in the description of an instance, where labels are associated with each instance to some degree. LDL has achieved great success in many applications, but most existing LDL methods cannot handle learning tasks with incomplete annotation information. In this paper, we propose a novel incomplete label distribution learning method based on local reconstruction (IncomLDL-LR). Both the feature matrix and label information are included in a unified Principal Component Analysis (PCA) model to describe the intrinsic structure of original data in the supervised low-dimensional space. Based on the reasonable assumption that the incomplete label of each instance can be linearly reconstructed from its neighbors labels, IncomLDL-LR gradually recovers the missing label values by the averaged column score of corresponding neighbors in the PCA space. The proposed algorithms are compared with state-of-the-art algorithms using five LDL evaluation metrics on 15 public datasets. Extensive experiments validate the effectiveness of our proposal.
Keywords: incomplete label distribution learning; local reconstruction; neighborhood information; label distribution learning; principal component analysis.
Congestion adaptive load balanced clustering scheme for prolonging network lifetime in mobile ad-hoc networks
by Naghma Khatoon, Mrs Amritanjali
Abstract: Clustering in a Mobile Ad-hoc Network (MANET) is the most effective technique to improve scalability and network lifetime. However, congestion and load balancing are still a major concern for optimising energy consumption and packet loss. Most of the existing routing protocols for MANET provide a solution for congestion control or load balancing among cluster heads separately. In this paper, a congestion adaptive load-balanced clustering scheme is proposed where we are emphasising not only on the problem of appropriate cluster head selection, but also on assigning mobile nodes to cluster heads efficiently, based on the congestion status of cluster heads. Thus, our proposed algorithm revolves around three benefits for load-balanced clustering with congestion control, i.e. the selection of most suitable nodes to serve as cluster heads, minimising the overall loads to cluster heads, and congestion control, which improve network lifetime with minimal overhead. The simulation results demonstrate the effectiveness of the proposed clustering algorithm compared with the existing algorithms in terms of average number of clusters formed, average end-to-end delay, packet delivery ratio, average number of re-clustering required and network lifetime.
Keywords: ad-hoc networks; clustering; load balancing; congestion status.
A heuristic channel allocation model with multi-lending in mobile computing network
by Sunil Kumar Singh, Deo Prakash Vidyarthi
Abstract: Radio channel allocation is broadly studied in the framework of cellular networks. Channels are scarce resources and must be used judiciously by the cells of the network. During the course of channel allocation, channels are normally lent/borrowed to the neighbour cells. Most of the available channel allocation techniques apply only single lending/borrowing. With the emergence of cognitive radio, it has become possible to use the channels opportunistically. Availing the channels are the services which are normally categorised into real-time and non-real-time services. Of these, real-time services are given more priority to serve over the non-real-time services. Further, among the new call and handoff services, the latter are given priority to serve. This paper proposes a novel heuristic approach for better channel usage for these services, blending the ideas of cognitive radio and multi-channel lending/borrowing. The performance study of the proposed model is done by simulation, which alludes to the effective channel usage in terms of blocked and dropped services.
Keywords: cognitive radio; channel allocation; cellular systems; single-channel lending; multi-channel lending; co-channel interference.
Research on the knowledge representation and retrieval for mechanical product design based on ontology
by Su Shaohui, Wang Yiting, Chen Chang, Li Pengfei, Zhang Dongyang, Chen Guojin
Abstract: Different subjects are applied in the design of mechanical products. For efficient sharing and reusing of knowledge in the diverse forms of information, this study presents the classification of mechanical design and the process of ontology construction. The knowledge of mechanical field can fully express the semantics and syntax of concept through the function of ontology. Furthermore, based on the representation of ontology knowledge, it establishes a knowledge retrieval model of mechanical product and proposes a corresponding retrieval algorithm, which implements much higher precision and recall in the mechanical field.
Keywords: knowledge representation; ontology; knowledge retrieval; retrieval algorithm.
A unified modelling method for cyber-physical systems based on Modelica
by Chang Chen, Han Cao, Shaohui Su, Huipeng Chen, Youping Gong, Guojin Chen
Abstract: A Cyber-Physical System (CPS) is a complex system consisting of discrete asynchronous clock systems and continuous synchronous time systems that are different in structure and mathematics basis. This research aims to establish a unified modelling method for CPS based on the Modelica semantic. According to framework of the existing semantic, the clock semantics are proposed to describe the clock system. The decomposition method is proposed to separate the clock system into several sub-blocks that have different clock frequency. The clock diffusing rules consisting of single clock diffusing, clock consistent rule and clock super-rule are presented to access the variables and expressions between each of the sub-blocks. Also, the semantic integration between time and clock sub-systems is researched. The proposed method suggests that the CPS model could be built in a unified framework and the clock system and time system could be linked automatically.
Keywords: Cyber-physical systems; unified modeling method; Modelica; continuous-discrete hybrid system.
Demand estimation of water resources via bat algorithm
by Xiangdong Pei, Youqiang Sun, Yeqing Ren
Abstract: In the process of urban water resources planning, the demand estimation of urban water consumption is one of the important basic contents. In this paper, a hybrid of a linear estimation model and an exponential estimation model is proposed to forecast the water consumption. The bionic intelligent algorithms are widely used in industrial engineering, so we use intelligent algorithms to solve the proposed model including Bat Algorithm (BA) and modified Bat Algorithm (FTBA). FTBA improves the global search capability, and the improvements increase the probability of solving the optimal value. In the simulation experiments, we use the data from Nanchang city during 2003 to 2015. The data from 2003 to 2012 are used to find the optimal weights, and the remaining data (2013-2015) are used to test the model. Simulation results show that the modified BA (FTBA) is superior to the standard algorithm and achieves higher accuracy in prediction.
Keywords: demand estimation; water resource; hybrid model; bat algorithm.
Development and application of model of configuration for order-engineered enterprise resource
by Chuchu Rao, Renwang Li
Abstract: The paper builds a model of enterprise resource optimisation configuration for the product which is engineering to order (ETO). Firstly, it decomposes the product into several parts in different custom depth at the design stage, then uses the different enterprise surplus resources to achieve the production for different kinds of parts and components production, based on the cost and time constraints. This model can help to reduce the cost of production and improve the competitiveness of the enterprise. Finally, the paper proves the superiority of the enterprise resources optimisation allocation model by an example of a customised special machine tool.
Keywords: order-engineered; resource optimisation; configuration model; cost.
Intelligent optimisation algorithm of rolling schedule for steel integrated production
by Le Yang, Guozhang Jiang, Xiaowu Chen, Gongfa Li
Abstract: The paper presents an improved algorithm-heuristic genetic algorithm which is different from the traditional algorithm. Combining this with the mode knowledge in the knowledge base, we develop an algorithm library that orients the steel production order. The algorithm, which has quick convergence speed and strong global search ability, avoids the defects of the premature convergence of traditional genetic algorithms. Firstly, we analyse the integrated steel production planning system structure, describe the rolling plan problem, give rolling planning model that considered maximum rolling miles, and give the detailed steps of the various specific rolling schedule algorithms, including the selection of clustering operator, construct initial solution, crossover operator and mutation operator and ranking operator. Then we gave the process of rolling planning algorithm. Finally, the algorithm is verified by simulation examples, and the optimal solution is obtained, which not only improves the efficiency of the calculation, but also increases the reliability of the data.
Keywords: optimal production plan; intelligent scheduling; scheduling algorithm; heuristic genetic algorithm.