International Journal of Embedded Systems
These articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.
Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.
Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.
Register for our alerting service, which notifies you by email when new issues are published online.
International Journal of Embedded Systems (61 papers in press)
Abstract: Automated test data generation tools produce test data that can achieve high coverage faster than test data generated manually by a tester. However, the test data generated by automated tools has been shown to not help developers find more bugs. The main reason is that it is difficult for human testers to understand and evaluate the test data. In this paper, an approach is introduced to automatically generate readable test data, which has been implemented in a tool called CTS. CTS can mine constant information from projects under testing and obtain heuristic information by aggregating and rating related constants. CTS adds heuristic information to the automatic test data generation process to generate test data that is quick and easy for a human to comprehend and check. Empirical experiments show that the proposed approach can improve the efficiency of test data generation and generate test data that is more convenient for a human oracle.
Keywords: test data generation; readable test data; constraint-based testing; symbolic execution.
Research on electric vehicle charging scheduling algorithms based on a 'fractional knapsack'
by Zhenzhou Wang, Xinyuan Li, Pingping Yu, Ning Cao, Russell Higgs
Abstract: The large-scale disorderly charging of electric vehicles creates challenges for the security of power systems, especially power distribution systems. To avoid peak power consumption during the day and improve the use rate of the power grid at night, a charging scheduling algorithm for electric vehicles based on a 'fractional knapsack' is proposed. Considering the constraints of the users' charging demand and charging system capacity, a charging model based on a fractional knapsack is established to optimise the peak-valley load difference and reduce load fluctuation and charging cost, which is the objective function. To verify the effectiveness of the proposed algorithm, the Monte Carlo method is used to simulate the charging demand of electric vehicles, and the disorderly charging and orderly charging scheduling are simulated and compared under a time-sharing tariff mode. The results show that the proposed scheduling algorithm improves the peak-valley difference of the power grid, reduces fluctuation in the power grid load, and improves the use rate of the power grid.
Keywords: fractional knapsack; electric vehicle; charging scheduling; peak-valley load difference.
Enhanced parallel CFAR architecture with sharing resources using FPGA
by Sadok Msadaa, Youness Lahbib, Ridha Djemal, Abdelkader Mami
Abstract: The real time CFAR processor needs a very high computational performance. To meet the real-time requirements, this paper presents an implementation of a new hardware parallel design using ACOSD-CFAR detector. The aim of this work is to increase the architecture throughput and decrease the power consumption while maintaining a high resolution target detection. Our proposed implementation exploits the properties of the ACOSD-CFAR detector to enhance it with a parallel architecture, including some sharing resources. Compared with conventional implementation of CFAR, the proposed architecture increases the throughput from 2576 Mbit/s to 4736 Mbit/s by 184% and reduces the power consumption by 15%. The design is implemented on a Zync 7000 FPGA board, which is considered as a common validation platform.
Keywords: CFAR; VHDL; radar; parallel; FPGA; ACOSD; radar detector; radar implantation; enhanced; radar architecture; sharing resource.
Using improved RFM model to classify consumers in big data environment
by Guang Sun, Xiaofeng Xie, Jiayibei Zeng, Wangdong Jiang, Yuxuan Huang, Meisi Lin
Abstract: Big data makes the marketing focus of enterprises change from products to consumers, so customer relationship management (CRM) becomes a central issue for business operation. Because customer classification is the key question for CRM, this paper starts with RFM model, combines analysis of K-means clustering, and studies the method for distinguishing between valueless customers and high-value customers. Based on this method, specific management strategies are proposed to help enterprises find core consumers. Also, quantitative analysis of the validity of the cluster is done by using the elbow method. Results of the experiment show that establishing RFM index and using K-means clustering can start from the structure of dataset of consumers of enterprises and finally compare the difference among customer classification by using the clustered scatter plot to provide an effective way of classifying consumers.
Keywords: RFM model; customer segmentation; big data; cluster analysis.
Efficiency and safety assessment of suburban highway access management
by KeJun Long, Nuo Xu, Ling-yun Xiang, Xi Duan
Abstract: Congestion and traffic accidents often take place at the entrances and exits of highway. However, reasonable access management and design can greatly mitigate congestion and accident. This paper discusses the field of suburban highway access management by introducing three typical suburban highways access management models, including the two-way stop-controlled intersection, simplified Restricted Crossing U-Turn (RCUT), and interchange with right-in right-out. To ensure better efficiency and safety, the simulations were conducted in VISSIM and SSAM (Surrogate Safety Assessment Model) software. The travel time, delay, and throughput are used as the efficiency indexes, and the traffic conflicts are used as safety indexes to quantify the access management performance. The results show that the total delay at an interchange with right-in right-out decreased by 40.5%, and the conflict decreased by 50.0% than a two-way stop-controlled intersection design, as well as the total delay decreased by 30.7% and the conflict decreased by 67.4% than a simplified RCUT design.
Keywords: access management; traffic simulation; surrogate safety assessment model.
Energy-aware automatic tuning on many-core platform via adaptive evolution
by Chen Liu, Zhiliu Yang, Yijun Jiang
Abstract: Even though attaining high performance has been the users pursuit traditionally, in thernmany-core era the emphasis has shifted towards controlling the power and energy consumption so as to maintain a satisfying performance while consuming an acceptable amount of energy. This applies to both high performance and mobile computing platforms. To achieve this goal,We propose evolution algorithm based automatic tuning as one feasible solution for energy-aware computing on many-core microprocessors. In this paper, we presented several auto-tuning approaches employing Differential Evolution (DE) algorithms and Genetic Algorithm (GA). Our target is to approach the optimal setting of different power islands on a many-core platform as fast as possible when running multiple programs. Comparing with brutal-force approaches, our solution has the advantage of fast converging speed without the need to traverse the entire search space, and runtime tuning without a priori knowledge of the software workload. Our experimental results show that, AdaptivernDifferential Evolution algorithm is able to achieve reduced energy consumption as well as better energy delay product (EDP) than other representative algorithms that we examined. Based on the results we obtained, we believe adaptive evolution based auto-tuning approach is an effective method towards energy-efficient computing on many-core platforms.
Keywords: differential evolution algorithm; genetic algorithm; energy-aware computing; dynamic voltage and frequency scaling; many-core processors.
A review of regional distributed energy system planning and design
by Junjie Wang
Abstract: With the development of urbanisation in China, regional distributed energy plays a vital role in modern urban power systems, which can reduce emissions, reduce power consumption, and increase the safety and reliability of power grids. This paper focuses on three main aspects of regional distributed energy system planning and design: load forecasting, system optimisation and system evaluation. It summarises the types and research methods of each aspect and proposes the future development direction. Finally, the research framework of system planning and design is proposed.
Keywords: regional distributed energy system; load forecasting; system optimisation; system evaluation.
Real-time anomaly detection in gas sensor streaming data
by Haibo Wu, Shiliang Shi
Abstract: In order to improve the timeliness and accuracy of coal mine gas disaster risk assessments, it is important to detect anomalies in the gas sensor streaming data in real-time. In this paper, the support vector regression (SVR) algorithm combined with the normal statistical distribution technique is used to establish a real-time anomaly detection model for gas sensor streaming data. The model uses SVR to fit the nonlinear mapping relationship between the multi-dimensional monitoring data of the coal mine working face and the gas sensor streaming data to predict the gas sensor value. For the distance between the predicted and the measured gas sensor values, the normal distribution method is used to determine gas sensor anomalies in real-time. Furthermore, this paper presents a prototype system for the real-time anomaly detection in gas sensor streaming data that is built using the memory-based distributed stream processing framework Spark Streaming. Experiments show that the real-time anomaly detection system combined with the SVR algorithm and the normal statistical distribution can periodically update the anomaly detection model and determine anomalies in the sensor streaming data in real-time. For a window size of 9, an update cycle of 1 and an anomaly threshold of 0.95, the anomaly detection model is better than the boxplot, the statistical analysis and the clustering algorithm regarding the prediction precision and accuracy. Moreover, the presented approach improves the detection efficiency.
Keywords: gas sensor; anomaly detection; streaming data; SVR; Spark Streaming.
Research on fuzzy clustering method for working status of mineral flotation process
by Yanpeng Wu, Xiaoqi Peng, Nur Mohammad, Hengfu Yang
Abstract: A fuzzy clustering method based on FCM algorithm for the working status of the mineral flotation process is proposed to help workers control the mineral flotation process better. The working status of the mineral floatation process can be determined by judging dosing records, in terms of copper sulphate, lead nitrate, xanthate, 2# oil, black medicine, etc., or by observing the visual features of the foam layer including the average grayscale, R-means, G-means, B-means, the average bubble size, the skewness of bubble size, the standard deviation of bubble size and bubble stability. Nearly 6000 continuous dosing data were collected from an automatic dosing system installed in a gold mine flotation workshop and normalised to the range of [0, 1]. Those dosing data were first pre-classified into steady condition and unsteady condition according to the degree of change in neighbouring data and then clustered respectively. Ninety-six categories of steady condition and 24 categories of unsteady condition were obtained by an FCM program using Euclidean distance. Similarity coefficient analysis on mean, standard deviation, and variation coefficient indicate that the dosing clusters in steady condition are more trustworthy to dosing operators than those in unsteady condition. Meanwhile, FCM algorithm is suitable for dosing data clustering with high consistency.
Keywords: FCM; fuzzy clustering; dosing records; visual characteristic; mineral flotation.
Matrix completion based prediction analysis of carbon emissions
by Wei Huang, Danqing Wei, Cheng Wang, Chongze Lin
Abstract: China's carbon emissions data at this stage are mainly concentrated at the provincial and national levels. As a major area for the implementation of carbon emission reduction measures, cities have not had a complete carbon inventory for a long time owing to the lack of basic data. In order to solve this problem, this paper constructs a set of prefecture-level CO2 emission forecasting methods to study the carbon emissions of 11 urban areas in Zhejiang Province. The two-dimensional matrix is formed by one-to-one correspondence between city and time. Through the analysis of the historical data of carbon emissions, the intrinsic relationship is found, and the missing data is predicted by the method of matrix completion. Experiments show that compared with Zhejiang's actual carbon emissions statistics data, the difference is found to be within 1%, and can achieve 69.3% higher than the latest method.
Keywords: carbon emissions; carbon inventory; matrix completion.
LEG-PER - LiDAR-enhanced GNSS positioning error reduction
by Walter Balzano, Fabio Vitale
Abstract: Internet of Things is a promising research area, with many applications in smart home devices but also in vehicular communication and self-driving vehicles. Using this technology, vehicles are able to establish P2P connections in order to share information, improving road security and reliability against accidents due to road and traffic conditions. IoT and vehicle technologies are strongly dependent on positioning, which in outdoor environments is normally determined using satellite systems like GPS and GLONASS. However, the precision is not very reliable due to multipath issues and when the sky visibility is limited, like in urban canyons. In this paper we present LEG-PER - LiDAR-Enhanced GNSS Positioning Error Reduction, a new methodology that improves the accuracy of satellite-based systems using a combination of V2V and an elastic graph generated by the vehicles in the area using LiDAR-determined distances.
Keywords: vehicle-2-vehicle; LiDAR; global navigation satellite system.
Turtle-shell data embedding method with high image fidelity
by Guo-Hua Qiu, Chin-Feng Lee, Chin-Chen Chang
Abstract: In this paper, a modified version of the turtle-shell data-hiding (TDH) scheme is proposed, aiming at improving the quality of stego-image. TDH scheme was first proposed by Chang et al. in 2014. In comparison to other schemes at that time, the scheme exhibited a superior visual quality in the premise of ensuring high embedding capacity (EC). However, in the TDH scheme proposed by Chang et al., the rules to seek for the search space of the hiding message suffer the drawback of omitting the better alternative pixel pair. The scheme proposed in this paper modifies the embedding rule by allowing the selection of a proper region other than the search space proposed by Chang et al., so as to better hide data and minimise the image distortion. According to the experimental results with the same EC, the visual quality of the stego-image in the proposed method is 0.41 dB higher than that of stego-image in Chang et al.s method.
Keywords: data hiding; steganography; turtle-shell; visual quality; embedding capacity.
Scalable and efficient routing protocol for internet of things by clustering cache and diverse paths
by Zhiqiang Ruan, Haibo Luo
Abstract: This paper proposes SENR, a Scalable and Efficient Named-based Routing protocol for the Internet of Things (IoT). Unlike traditional IoT data collection mechanisms, SENR is a consumer-driven data retrieval scheme, which is motivated by the different architecture designs in Named Data Networking (NDN). SENR explores semantic notification and opportunistic caching strategy to enhance the data retrieval efficiency for smart systems. It includes three aspects: 1) for data and Interest aggregation, SENR performs data aggregation according to the hierarchy of namespace, and stores data over in-network storage node; in the data retrieval process, it marks each route notification at the edge nodes, and allows the Interest with the same name prefix to choose the same edge routing node towards to the storage node, which improves the cache hit ratio and reduces the network traffic; 2) for adjustable path selection, SENR adopts link-state routing protocols to collect network topology and compute the shortest path to the content source nodes, moreover, it uses distance-vector routing protocols to select multiple alternative paths to cope with node failures; 3) for partial information updates, SENR employs partial routing update to explicit support of dynamic paths and caching capabilities, so that each node simply informs its neighbours by the available routing updates, and allows the neighbours to fetch such part of updates. Simulation results demonstrate that SENR can significantly reduce the content retrieval delay and routing overheads.
Keywords: IoT; semantic query; opportunistic caching; future network.
MOGATS: a multi-objective genetic algorithm-based task scheduling for heterogeneous embedded systems
by Mohaddeseh Nikseresht, Mohsen Raji
Abstract: Multi-objective optimisation is an unavoidable requirement in different steps of embedded systems design, including task mapping and scheduling. In this paper, a new Multi-Objective Genetic Algorithm-based Task mapping and Scheduling (abbreviated as MOGATS) is presented for heterogeneous embedded system design. In MOGATS, the architecture of the hardware platform and the set of tasks in the form of a task graph are assumed to be given as the inputs. The task mapping and scheduling problem is modelled as a genetic algorithm-based optimisation approach in which the execution time, energy consumption, and reliability of the scheduling are considered as the objectives of the optimisation method. In MOGATS, we are interested in finding the Pareto frontier of the solutions (scheduled tasks) in order to help the designer to pick out the best outcome according to different design considerations. The experimental results on real application task graphs show that MOGATS provides a better solution than the greedy algorithm if it is applied as a single-objective task scheduling method. Moreover, the superiority of MOGATS in comparison with the state-of-the-art single- and multi-objective task scheduling algorithms is shown in terms of standard performances factors, such as scheduling length ratio and speed-up parameters.
Keywords: heterogenous embedded systems; task scheduling; multi-objective optimisation; genetic algorithm.
Research on teaching practice of app inventor course with embedded in computational thinking
by Hexiao Huang, Leilei Chen, Siwei Jin, Ying Wang, Hongzhi Hu
Abstract: At present, the concept of computational thinking is spreading in education around the world. From the point of view of current research and application in China, the research on the cultivation of computational thinking in K-12 education is still in the early stage. Based on the graphic programming design course of app inventor in primary and secondary schools, this study embeds computing thinking into teaching objectives and contents, constructs the teaching model of app inventor course with embedded computing thinking, and discusses how to cultivate students' computing thinking ability in teaching practice. The method provided in this paper is helpful to analyse the changes of students' computational thinking during the teaching process, and it can effectively identify teaching effects.
Keywords: computational thinking; app inventor; abstract thinking; teaching practice.
Anonymous chaotic based identity authentication protocol in IoT
by Jing Long, Xin Su
Abstract: With the rapid development of the Internet-of-Things (IoT), the credible identity authentications among the connected devices are widely examined by researchers and institutes. Traditional identity authentication protocols have issues in terms of security, complexity and authentication efficiency. To address these problems, this work introduces a chaotic mapping technique into identity authentication. Besides, anonymity and interactivity are also considered to realise a highly efficient and secure IoT device authentication. Firstly, Kent chaotic mapping technique is used to generate the chaotic sequence as the authentication key. After that, the interactive authentication among the server, reader and tag is performed. The authentication information is encrypted in the transmitted channel. The identity information is anonymous in the proposed protocol. Finally, the security, complexity and efficiency are analysed and discussed. The comparison results show that the proposed protocol is superior to other protocols.
Keywords: IoT; identity authentication; chaotic mapping; anonymity.
Analysis and compensation of inner lever arm effect in strapdown inertial navigation system
by Qi Wang, Changsong Yang, Shaoen Wu
Abstract: The inner lever arm effect is analysed under the ideal condition that the three sensitive axes of the accelerometers equipped in inertial measurement unit are perpendicular to each other and intersect at one point. The virtual normal acceleration integral and the virtual tangential acceleration integral cannot be completely cancelled, and the velocity drift rate of the inner lever arm effect is independent of the angular vibration centre. It is directly proportional to the length of the inner arm and directly proportional to the square of the vibration frequency. The method to compensate the effect of inner lever arm is presented in this paper to convert the measured acceleration at the sensitive point of accelerometer into the intersection point of their sensitive axes. The analysis and compensation process of the internal lever-arm effect will be more complicated in the case where the sensitive axes of the IMU accelerometer are not perpendicular to each other or do not intersect at one point. Inner lever arm cannot be avoided in the IMU of the redundant configuration of the multi-accelerometer. Simulation experiments were carried out and the results show that the method of compensating the inner lever arm is effective and greatly decreases the error of lever arm.
Keywords: inner lever arm effect; inertial measurement unit; compensation; simulation experiments.
Service component recommendation based on LSTM
by Xiao Yang, Hong Xu, Hongping Shu, Yaqiang Wang, Kui Liu
Abstract: Service component selection is a core problem in software development process. With an enormous number of components available, it is often difficult for the developer to select the most appropriate one, as he or she might not be aware of all the possible business scenes ahead of time. Taking these challenges into consideration, we propose a deep learning based system that automatically recommends service components based on component selection history during the software development process. We employ a sequential model with two long-short-term memory (LSTM) layers and two fully connected layers, using SoftMax as an activation function, to predict the next service component. The model was trained, validated and tested on a dataset with more than 120,000 examples from a real-world software company. The proposed network outperforms the baseline methods in terms of the evaluation criteria. In addition, the model results were deployed in a real-world software tool and yielded positive feedback.
Keywords: service component; recommendation system; long-short-term memory network.
Improved NSGA-II for the minimum constraint removal problem
by Bo Xu, Feng Zhou, Yonghui Xu, Xu Haoran, Kewen Xu
Abstract: This paper focuses on the minimum constraint removal (MCR) problem. Based on a preliminary study, this paper proposes a comprehensive multi-objective evaluation model to derive a feasible solution to MCR path planning that, from the robots individual perspective, is driven by the costs and benefits, and takes into account factors such as the minimum constraint set, the route length, and the cost. The feasible solution to the MCR path is evaluated using this model. A typical multi-objective algorithm NSGA-II is applied to the MCR problem. The algorithm test results show that compared with single objective algorithm planning, the NSGA-II-based path planning algorithm can find a shorter path that traverses fewer obstacle areas and can thus perform the MCR path planning more effectively.
Keywords: minimum constraint removal; minimum constraint set; path planning; multi-objective optimisation; robot.
Information hiding mechanism based on QR code and information sharing algorithm
by Xiaohui Cheng, Tong Niu
Abstract: With the rapid development of internet technology, information security is receiving more and more attention. In order to solve the problems of information leakage and information tampering during the transmission of information, an information hiding mechanism based on the QR code is proposed. This mechanism uses the error correction mechanism of the QR code to hide secret information, and then splits and transmits it through a secret sharing algorithm. Experiments show that the proposed information hiding mechanism can effectively hide secret information, and has strong security and robustness. The proposed information hiding mechanism has the characteristics of high flexibility and anti-theft, and can be applied to the actual information transmission process.
Keywords: QR code; information security; secret sharing; information hiding.
Design and implementation of a cloud encryption transmission scheme supporting integrity verification
by Zengyu Cai, Zuodong Wu, Jianwei Zhang
Abstract: In the cloud storage environment, the integrity of private data is one of the most concerned issues for users, which has become the focus of cloud storage research. For this kind of problem, the existing schemes usually sacrifice the communication efficiency of users for higher security, which often causes a lot of computing overhead. Therefore, the purpose of this paper is to achieve the coexistence of safety and efficiency, and adopts the ideas of Chinese commercial encryption algorithms SM2 and SM3, proposes a cloud encryption transmission scheme that supports integrity verification, and gives a security analysis under the assumption of discrete logarithm problem on elliptic curve and Diffie-Hellman problem. Finally, the actual test and comparative experiment results show that our scheme can not only realise the cloud data transmission encryption and cloud storage integrity verification functions at the same time without affecting the performance of the cloud server. Moreover, it can effectively resist all kinds of common attacks, reduce the storage and computing burden of cloud users, and has certain guiding significance for the research of user privacy protection in the cloud environment.
Keywords: cloud storage; Chinese commercial encryption algorithms; SM2; SM3; discrete logarithm; Diffie-Hellman; elliptic curve; cloud data transmission encryption; integrity verification; privacy protection;.
A combination classification method based on Ripper and Adaboost
by Min Wang, Zuo Chen, Zhiqiang Zhang, Sangzhi Zhu, Shenggang Yang
Abstract: With the growing demand for data analysis, machine learning technology has been widely used in many applications, such as mass data summarising rules, predicting behaviours and dividing characteristics. The Ripper algorithm presents better pruning and stopping criteria than the traditional decision tree algorithm (C4.5), while its error rate is less than or equal to C4.5 by O (nlog2n) time complexity. As a result of that, Ripper can maintain high efficiency even on the massive dataset which contains lots of noise. Adaboost is one of the iterative algorithms, which combines a group of weak classifiers together to set up a strong classifier. In order to improve the accuracy of Ripper classification algorithm and reduce the computational complexity, this paper proposes a Ripper-Adaboost combined classification method (Ripper-ADB). The experiment result shows Ripper-ADB could improve the classifier and get higher classification accuracy than decision tree and SVM.
Keywords: Ripper; feature selection; Adaboost; NSL-KDD; C4.5.
A movie recommendation model combining time information and probability matrix factorisation
by Huali Pan, Jingbo Wang, Zhijun Zhang
Abstract: A deep analysis and discussion of matrix factorisation technologies are given in this paper taking into account the defects of traditional collaborative filtering recommendation algorithms. In addition, we provide an analysis of the effects of feature vector dimensions on the recommendation quality and efficiency of a probability matrix factorisation (PMF) algorithm. A PMF algorithm will lead to inaccurate recommendations if it does not consider possible dynamic changes in a users interest over time. Accordingly, a TPMF model, a PMF algorithm integrated with time information, is proposed in this article. Its feasibility and effectiveness are empirically verified using movie recommendation datasets, and higher prediction accuracy is confirmed compared with existing recommendation algorithms.
Keywords: collaborative filtering; matrix factorization; movie dataset; personalised recommendation; time information.
Quantum image filtering and its reversible logic circuit design
by Gaofeng Luo, SheXiang Jiang, Liang Zong
Abstract: Quantum information processing can overcome the limitations of classical computation. Consequently, image filtering using quantum computation has become a research hotspot. Here, a quantum algorithm is presented on the basis of the classical image filtering principle to detect and cancel the noise of an image. To this end, a quantum algorithm that completes the image filtering task is proposed and implemented. The novel enhanced quantum representation of digital images is introduced. Then, four basic modules, namely, Position-Shifting, Parallel-CNOT, Parallel-Swap, and Compare the Max, are demonstrated. Two composite modules that can be used to realise the reversible logic circuit of the proposed quantum algorithm are designed on the basis of these basic modules. Simulation-based experimental results show the feasibility and the capabilities of the proposed quantum image filtering scheme. In addition, our proposal has outperformed its classical counterpart and other existing quantum image filtering schemes supported by detailed theoretical analysis of the computational complexity. Thus, it can potentially be used for highly efficient image filtering in a quantum computer age.
Keywords: quantum computing; reversible logic circuit; image filtering.
A TAO-based adaptive middleware for pervasive computing
by Yanhui Guo, Zhenmei Yu, Fuli Qu, Hui Liu
Abstract: Over the past years, a considerable amount of effort has been devoted, both in industry and in academia, towards the development of innovative applications for the Internet of Things(IoT). An important challenge of IoT application is to adapt to the dynamical environments, which can be modified at runtime considering the emergence of other requirements. To address this issue, pervasive computing can provide us with a good solution. Aiming at the environments that are open, dynamic and heterogeneous, we propose an adaptive middleware named PAmiddleware. PAmiddleware is service-oriented, context-aware, and supported by QoS. The architecture of PAmiddleware is based on TAO, which is a standards-based, CORBA middleware framework. Meanwhile, we present a model for context awareness to allow the adaptation and to give a modelling method of context description for context resource. We also propose an adaptive strategy that uses a genetic algorithm for optimisation. The proposed model can well meet the needs of pervasive computing, and provide more convenient service.
Keywords: pervasive computing; middleware; components; context awareness; adaptive.
Designing a high-speed light emitting diode driver circuit for visible light communications
by Wu Long, Xu Xiaojun, Feng Juqiang, Huang Kaifeng
Abstract: LEDs are an essential component in visible light communication systems and need to be modulated for data transmission at the same time of lighting. The modulation speed of LEDs is limited by the remaining carriers that remain in the depletion capacitance when the LEDs turn off. This paper designs a high-speed LED driver that can remove remaining carriers, which shortens the falling time of modulation pulse, namely improves the modulation speed. The driver is fabricated using three discrete FETs and some resistors and capacitors on a board. One FET is used to control the lighting and extinguishing of a LED and the other two FETs are used to remove remaining carriers. The performance of the driver is demonstrated by driving a blue LED and a near ultraviolet LED. In experiments, the FETs on the board are triggered by a square-wave signal with the frequency of 1 MHz and the optical signals emitted from the LEDs are detected by a photoelectric detector. The experimental results show that this design decreased the falling time from 66 down to 32 ns for the blue LED as well as from 40 down to 26 ns for the near ultraviolet LED, which demonstrates the improvement of the LED modulation speed.
Keywords: LED; driver; visible light communication; modulation speed.
Modular transformation of embedded systems from firm-cores to soft-cores.
by Ehsan Ali, Wanchalerm Pora
Abstract: Although there are many 8-bit IP processor cores available, only a few, such as Xilinx PicoBlaze and Lattice Mico8 firm-cores are reliable enough to be used in commercial products. One of the drawbacks is that their codes are confined to vendor-specific primitives. It is inefficient to implement a PicoBlaze processor on non-Xilinx FPGA devices. In this paper, we propose a systematic approach that transforms primitive-level designs (firm-cores) to vendor independent designs (soft-cores), while modularising them during the process. This makes modification and implementation of designs on any FPGA devices possible. To demonstrate the idea, our soft-core version of PicoBlaze is implemented on a Lattice iCE40LP1k FPGA device and is shown to be fully compatible with the original PicoBlaze macro. Rigorous verification mechanisms have been employed to ensure the validity of the porting process; therefore, the quality of transformation matches the industry expectation.
Keywords: embedded systems; FPGA; microprocessors; soft-core; firm-core; transformation; HDL; Xilinx PicoBlaze; Lattice Mico8.
FSVA-Data: a flexible solution for the visualisation and analysis of basin-scale water quality monitoring data
by Jianlong Xu, Yuhui Li, Kun Wang, Lianghong Xiao, Wei Liang
Abstract: Basin-scale water quality monitoring is an important part of water environment governance. However, owing to the multiple attributes, frequencies, methods, and data volume of water quality monitoring data, the efficient access, visualisation, and analysis of monitoring data is an important research topic in monitoring work. This paper proposes a flexible data visualisation and analysis solution, FSVA-Data. In this solution, various microservices-based methods are used for integrated data discovery, processing, and analysis. To monitor data series that only change gently, we propose a data-adaptive method for data scalability and a customisable chart visualisation system. Our solution is not only used for water quality monitoring in Lianjiang River, but also has great application prospects in improving the effectiveness of monitoring data systems and accelerating scientific insights in other agricultural and ecological fields.
Keywords: visualisation; water quality monitoring; microservices.
An analysis of power consumption and performance in runtime hardware reconfiguration
by Denis Loubach
Abstract: It will be more difficult to continue with Moores law scaling in the next few years without exploring new heterogeneous architectures with application-customised hardware. The expressive employment of customised accelerators, or runtime reconfigurable designs, will be required to deliver power- and performance-efficient systems. In view of recent technology advances, runtime partial reconfiguration has emerged supported by FPGA-based devices. Still, power consumption and performance are among the top concerns when devising new reconfigurable embedded systems. This paper addresses power and performance analysis of the partial reconfiguration process supported by runtime reconfigurable hardware. We introduce a heterogeneous system-on-chip FPGA-based runtime partial reconfigurable platform design along with an experimental and theoretical power consumption and performance models, which are specific to the partial reconfiguration process. The proposed design was implemented, and both experimental and theoretical power consumption and performance analyses were performed, thus providing a formal tool to the decision-making process between power consumption and performance applicable to the runtime reconfiguration phase. Results show an average accuracy of 89.76% for the power consumption model and 94.82% for the performance model.
Keywords: reconfigurable computing; embedded systems; power consumption; performance; heterogeneous systems; FPGA.
Study of online learning resource recommendation based on improved BP neural network
by Yonghui Dai, Jing Xu
Abstract: Personalised recommendation has gradually become an effective way to solve the problem of information overload in the era of big data. Therefore, in order to improve the efficiency of online learning, this paper discusses the design of an online learning resource recommendation algorithm based on improved BP neural network, and the results show that it has high value for popularisation and application. Based on the transmission network, the improved BP neural network of momentum factor can achieve more sufficient data mining. After training learning resources and user data, it can match the real score and the predicted score, so as to ensure the accuracy of personalised recommendation. The main contribution of this paper is to propose a recommendation algorithm for online learning resources through improved BP neural network algorithm, and the feasibility of the algorithm is verified. The research method of this paper provides a reference for the research of personalised recommendation algorithm of online resources.
Keywords: online learning resource; improved BP neural network; personalised recommendation algorithm; momentum factor.
A novel adjustable reversible data-hiding method for AMBTC-compressed codes using Hamming distance
by Ting-Ting Xia, Juan Lin, Chin-Chen Chang, Tzu-Chuen Lu
Abstract: In this paper, we propose a novel adjustable reversible data-hiding method for AMBTC-compressed codes using Hamming distance. First, the original image is compressed by AMBTC technique to obtain two quantisation levels and a bitmap of each block. Next, the scheme converts the bitmap of each block into the decimal number and calculates the frequency of the decimal number to find the maximum frequency of the decimal number as the peak bitmap. In our scheme, if the block is equal to the peak bitmap, then the block is embeddable. The scheme generates a candidate list to collect a different kind of bitmap in which the Hamming distance between the block and the peak bitmap is less than a pre-defined threshold. The length of the secret message is computed from the total number of bitmaps in the candidate list. The scheme converts the secret message to form an indicated index and uses the corresponding indicated bitmap in the candidate list to replace the original bitmap. Experimentally, the proposed scheme has a high image quality, and the information hiding capacity can be adjusted by the threshold.
Keywords: reversible data hiding; Hamming distance; AMBTC; bitmap characteristics; peak bitmap; compression domain; information security.
An integrated approach for prediction of radial overcut in electro-discharge machining using fuzzy graph recurrent neural network
by Amrut Ranjan Jena, Raja Das, Debi Prasanna Acharjya
Abstract: The manufacturing of goods relies on its design methodology and the process parameters. The parameters used in the manufacturing process play an important role to build a quality product. Initially, heuristic techniques are used for parameter selection. Much research has been conducted to predict the radial overcut using neural networks. Besides, the fuzzy neural network gains more popularity owing to the presence of fuzziness in the machining process. In this paper, fuzzy graph recurrent neural network architecture is used for modelling and predicting the radial overcut in electro-discharge machining. The proposed model is analysed over the information system obtained from VIT, Vellore, India. Moreover, it is also compared with the fuzzy graph neural network and traditional neural network, and found to be better in terms of accuracy.
Keywords: recurrent neural network; fuzzy graph; mean square error; radial overcut; electro-discharge machining.
Predicting missing data for data integrity based on the linear regression model
by Kai Gao, Chin-Chen Chang, Yanjun Liu
Abstract: Multiple linear regression is an important data analysis technique. Based on this technique, we propose a new method for predicting missing data items and detecting possible errors in the data. The proposed method has a key feature that it can be used to predict not only just one missing item, but also two or more missing items within a certain tolerance. At the same time, we perform a few experiments to prove the feasibility of our proposed method. The results of our experiments show that our method can indeed predict one or more missing items within an acceptable range and find the error of the original data.
Keywords: multiple linear regression; missing data; data integrity; predict.
Flexible heuristic-based prioritised latency-sensitive IoT application execution scheme in the 5G era
by Mahfuzulhoq Chowdhury
Abstract: With the rise of advanced internet technologies and smart machines, several emerging internet of things (IoT) applications have been deployed that offer significant benefits to humans. Owing to the limitations of size and resources, providing a high quality of service for many latency-sensitive IoT applications is increasingly critical for many smartphones/mobile devices. Mobile cloud computing technology can minimise the latency of IoT application execution by providing the necessary computation workload processing and data-caching facility to resource-limited smart devices. However, to ensure low latency for heavyweight IoT application processing is particularly challenging in the mobile cloud computing environment owing to the varying IoT-based application requirements, dynamically changing resources of the cloud devices or machines, network resources, mobility, varying input and output data size value of caching and computing applications, and communication overhead. To make satisfactory application execution decisions, in this paper we first investigate different challenges, requirements, and latency-sensitive applications of emerging IoT. Next, we present a flexible heuristic-based prioritised resource assignment strategy for IoT application execution considering four-level cloud mobile device cooperation in the 5G era. Numerical results are presented to evaluate the total elapsed time, battery power usage, and task requirement satisfaction ratio performance of our proposed heuristic-based prioritised latency-sensitive IoT application execution scheme. Evaluation results confirm the suitability and efficiency of the proposed scheme.
Keywords: caching; computing; edge cloud; internet of things; low latency; mobile cloud computing; priority awareness; 5G technologies.
A power-saving scrolling scheme for browsers on mobile OLED systems
by Hao-Chun Chang, Yu-Chieh Yang, Liang-Yan Yu, Yao-Hua Ho, Chun-Han Lin
Abstract: Mobile applications play an indispensable part in modern daily life, and reducing their power consumption has a great impact on user experience. For many, web browsers are a critical mobile application, and thus their power consumption plays an important role in the service lifetime of mobile systems. This paper studies ways of reducing the power consumption of OLED displays on mobile systems when users use scrolling operations in browsers without reducing the quality of the user experience. The limited displaying time caused by user operations is the first time considered in power-saving design. The proposed power-saving scrolling scheme links the visual appeal of web pages and the power models of OLED displays. To efficiently judge the visual appeal of displayed content in web pages, a content-based analysis is presented. According to the analysis results, power-saving transformation programs are dynamically generated by two proposed algorithms. Next, a scrolling monitor is designed to activate the transformation during scrolling operations. To provide a better user experience, two mechanisms are also proposed to smooth the transformation process and to improve analysis efficiency. Finally, four real-world web pages are used to evaluate the performance of the proposed power-saving scheme on a commercial smartphone. The results of the comprehensive experiments show that the proposed scheme can achieve device and OLED power savings in the ranges 9-16% and 16-30%, respectively.
Keywords: OLED displays; browser services; energy conservation; scrolling operations; mobile systems.
A sparse system identification algorithm based on fractional order LMS
by Yun Tan, Jiaohua Qin, Xuyu Xiang, Wentao Ma
Abstract: In this paper, a zero-attracting fractional order least mean squares (ZA-FLMS) algorithm is proposed for adaptive sparse system identification. l1-norm of the filter coefficients is considered and zero-attracting correction is introduced into the updating equation. The extension of the algorithm is also proposed for distributed local sensors of information-centric IoT. The convergence speed and MSE performance are investigated in the simulations, which show effective improvement for sparse system identification compared with traditional LMS, zero-attracting LMS and fractional order LMS, especially with lower sparsity and smaller fractional order. But the decrement of fractional order and step size will lead to slower convergence speed, while the bigger fractional order and step size will lead to bigger variation of MSE. Therefore, optimised ZA-FLMS is further introduced, which uses l0-norm in the initial stage of the algorithm and shows improvement of convergence speed for smaller fractional order.
Keywords: fractional order; sparse system identification; least mean square; LMS; zero-attracting.
A genetic algorithm-based tasks scheduling in multicore processors considering energy consumption
by Hassun Vakilian Zand, Mohsen Raji, Hossein Pedram, Hossein Heidari SharifAbadi
Abstract: Energy consumption has been always an important issue in multicore processors which are getting more and more popular in embedded systems. In this paper, we propose an energy-aware task scheduling approach taking advantages of heuristic algorithms based on genetic algorithm. The proposed approach includes both static and dynamic scheduling schemes. The task scheduling is modelled as a genetic algorithm problem which is mainly used when the tasks are ready before run-time; i.e., static task scheduling. The tasks which arrive after beginning task execution are dynamically scheduled using a proposed heuristic algorithm in combination with the genetic algorithm. The experimental results show that the proposed algorithm achieves more energy efficiency in both static and dynamic task scheduling for multicore processors as compared with similar energy-aware scheduling methods.
Keywords: multicore processor; task scheduling; energy consumption; genetic algorithm; evolutionary algorithm; embedded system; heuristic algorithm.
A new software-defined network architecture to solve energy balance problems in wireless sensor networks
by Yinxiang Qu, Yifei Wei, Mei Song, Dan Liu, Xiaojun Wang
Abstract: Wireless sensor networks (WSNs) are an important part of the internet of things. In WSNs, the sensor battery is limited, and the entire network has a data aggregation node called Sink. When the sensor transmits data to the Sink in a multi-hop manner, the sensors around the Sink also help other sensors to forward the data to the Sink. This causes those sensors to die faster than other sensors. This problem is called energy hole problem. Previous solutions such as sensor uneven distribution schemes and clustering schemes are not only difficult to implement, but also increase the design cost of the system. In particular, traditional WSNs cannot be updated once deployed. In order to solve the above problem, we propose a method of combining SDN and WSNs. The simulation results show that the proposed method has good performance in terms of the number of surviving sensors, network capacity and residual energy.
Keywords: soft-defined network; SDN; wireless sensor networks; WSNs; energy hole.
Localisation algorithm based on weighted semi-definite programming
by Jianfeng Lu, Xuanyuan Yang
Abstract: In order to improve the performance of reduced complexity positive semi-definite programming (RCSDP) algorithm based on time difference of arrival (TDOA), a weighted positive semi-definite programming (WSDP) scheme is proposed in this paper. Based on the squared distance differences between the target node to one anchor node and to the other anchor node, the location of the target node is described as the optimal solution of a non-convex optimisation problem. The semi-definite relaxation technique is used to transform the original non-convex problem into a weighted convex problem, which takes the measurement noise into consideration, and then the estimated location of the target node is obtained. The simulation results show that the localisation performance of WSDP algorithm is better than that of RCSDP algorithm, regardless of whether the target node is located inside or outside the area surrounded by anchor nodes.
Keywords: localisation; semi-definite programming; time difference of arrival; TDOA; weight factor.
An improved method for indoor positioning based on ZigBee technique
by Jiaqi Zhen, Boshen Liu, Yanwei Wang, Yong Liu
Abstract: With the popular use of smart mobile terminals, it is possible to locate the mobile terminals. The traditional indoor positioning methods often bring about large errors under the circumstance of interference. In this paper, an improved K-nearest neighbourhood method based on ZigBee wireless sensor network is proposed, it selects K nearest database vectors from the minimum distance, and calculate the average of these coordinates as the final location result. The accuracy of indoor positioning is effectively improved, meanwhile, there is no significant increase of the computing time. The effectiveness of the method has been verified in the end.
Keywords: indoor positioning; ZigBee; K-nearest neighbourhood method; wireless communication; internet of things; wireless sensor network; received signal strength; mesh network; ad-hoc network; database; embedded systems.
DOA estimation of wideband sources by sparse recovery based on uniform circle array
by Jiaqi Zhen, Yanwei Wang, Yong Liu
Abstract: The conventional direction of arrival (DOA) estimation by compressed sensing is based on wideband focusing and sparse recovery in discrete domain. The former needs high signal to noise ratio (SNR), and the latter requires the space division, or their performance will degrade seriously. Therefore, a new algorithm of wideband DOA calculation in frequency domain based on uniform circle array (UCA) is proposed, the optimisation problems are respectively disposed at each frequency, then the sparse support set is acquired by the corresponding semidefinite programming, after that DOA is calculated through fusing the data of every frequency, simultaneously the original sources can also be reconstructed. This algorithm averts the grid partition in discrete domain, and it also performs well in condition of small samples and low SNR.
Keywords: direction of arrival; wideband sources; sparse recovery; uniform circle array; array signal processing; semidefinite programming; linear frequency modulation; support set; signal parameter estimation; embedded systems.
Improved Faster R-CNN identification method for containers
by Ning Chen, Xiaohu Ding, Hongyi Zhang
Abstract: In a complex port environment, the fast and effective automatic visual recognition of containers is an important part of the intelligent operation and management of ports. Due to the large amount of container image data of complex scale and shape, the traditional target detection and recognition algorithm is limited by the illumination, weather and scenes of the port, it has created challenges and difficulties in port container recognition and identification. This paper proposes a deep learning method for container target recognition detection based on the Faster R-CNN framework, the deep separable network structure is introduced into the VGG network, and the DS-VGG network is designed to improve the accuracy while reducing the network parameters to improve the recognition speed, by introducing the adversarial spatial transformer network (ASTN) to the Faster R-CNN network training to enhance the diversity of data features and improve recognition performance. In order to enhance the convolution feature extraction of container targets, a strategy training network that enhances sample target foreground features, multi-scale training learning and data amplification are used. Finally, the performance test and comparison test of the improved model proposed in this paper are carried out. The test results show that the target recognition speed is 50 frames/s on the container test set, the average accuracy rate is 97.7% and the recall rate is 94.45%. Compared with Faster R-CNN, the recognition performance is significantly improved in complex scenes such as fog, rain and night.
Keywords: container; port intelligence; deep learning; target recognition; Faster R-CNN network; adversarial spatial transformer network; ASTN.
Design of network intrusion detection system based on parallel DPC clustering algorithm
by Jing Wang, Dezhi Han
Abstract: With the advent of the era of big data, network intrusion detection systems based on K-means algorithm cannot meet the detection efficiency and detection speed requirements in big data environment. The DPC algorithm can be applied to high-dimensional network traffic and large-scale data application environments, but there are problems of large calculated amount and limited serial processing capability. Aiming at the problems of DPC algorithm, the DPC algorithm is adjusted firstly to improve the clustering accuracy of the algorithm. Then, the DPC algorithm a parallelised on the Spark platform, so that the processing ability and running speed of the DPC algorithm is greatly improved by running in parallel in the memory of multiple virtual machines. The experimental results show that the network intrusion detection system based on parallel DPC clustering algorithm has higher detection rate and lower false rate. The parallelisation clustering efficiency is much higher than the single-computer clustering efficiency.
Keywords: DPC; clustering; network intrusion detection; Spark; parallel.
Based on the GF1 and GF4 radiation calibration analysis
by Shao Wen, Tao Zui, Xie Yong, John J. Qu, Huan Hai, Tian Chuan Yang
Abstract: In order to test the in-orbit radiation characteristics of GF-1 and GF-4, and obtain accurate radiometric calibration coefficients, this paper proposes a MODIS and LandSat 8 cross-calibration method based on Dunhuang radiation correction field and a method for comparing the radiance error of GF-1 and GF-4 satellite images based on uniform regions. First, this article introduces the cross-calibration principle and the overview of the uniform target sample area, and compares the band matching and spectral response of the four remote sensors. Then, cross-calibration based on the scenes of the same area at the same time of GF-1, GF-4, MODIS, and LandSat 8 on 28 July 2017. The results show that the calibration coefficient error obtained by this method is within 6%. The error of the calibration coefficient obtained by cross-calibration with LandSat 8 satellite is smaller, which satisfies the basic remote sensing quantitative demand. The GF-1 satellite has high calibration accuracy and is suitable for cross-calibration research of China's independent satellite remote sensors. It is of great significance for the establishment of China's in-orbit calibration system.
Keywords: cross calibration; Dunhuang radiation correction field; GF-1; MODIS; GF-4; LandSat 8; visible light; near infrared.
Comparative analysis on detection performance with ground-based microwave radiometer and radiosonde
by Lina Wang, Chaoyao Shen, Sheng Yuan, Yongjun Ren, Yong Wang, Jinyue Xia
Abstract: Ground-based microwave radiometer is a new type of automatic atmospheric detection device with high precision and multi-channel. In order to investigate the reliability of detection data, this article compares and analyses the meteorological elements retrieved from microwave radiometer (MWR) and observational data from radiosonde. The results show that temperature profile and water vapour density profile from MWR have better positive correlation with those from radiosonde. The temperature retrieved from MWR is lower than that from radiosonde in non-precipitation condition, but higher in precipitation condition. The bias may be related to sampling methods, MWR retrieval methods, precipitation and so on.
Keywords: comparative analysis; microwave radiometer; radiosonde; temperature; water vapour density; correlation.
Research on urban transport network topology vulnerability identification under rainfall conditions
by Weiwei Liu, Yang Tang, Fei Yang, Yi Dou, Jin Wang
Abstract: Under the impact of global climate change, meteorological disasters, such as rainstorms, have occurred frequently during recent years and have led to several severe disruptions of transport network in urban areas. In order to minimise the risk of potential losses of life and properties, this paper presents a method to identify topology vulnerability of road networks for a range of rainfall scenarios. Meanwhile, a review is presented regarding the theories and methods of vulnerability analysis. The paper defines the concept of vulnerability of road network considering the intensity of rainfall. It establishes a comprehensive assessment index of 'importance of nodes and edges' by combining the 'betweenness and traffic flow' to find out the source of road network fragility considering the intensity of rainfall. Afterwards, the assessment index 'mincuts frequency vector' is introduced into the assessment of topology vulnerability. This paper provided the scientific basis for disaster control and reduction of the urban road network.
Keywords: urban traffic; topology vulnerability; road network; rainfall; mincuts frequency vector.
Applying analytical and empirical schedulability analysis techniques to a real spacecraft flight software
by Nunzio Cecere, Massimo Tipaldi, Davide De Pasquale
Abstract: Software schedulability analysis is a crucial aspect for real-time software system verification. This paper presents a combined approach of analytical and empirical techniques for measuring task execution times and verifying the timing constraints of flight software (FSW) applications in real space projects. The proposed methodology is based on the following two main steps. Firstly, we perform an analytical verification via the response time analysis (RTA) in order to show that all the hard deadlines defined for time-critical SW tasks are met. In particular, the worst-case execution times (WCETs) of such SW tasks are measured via static code analysis. Secondly, we analyse the activities that are executed in the context of less time-critical tasks via a more empirical argumentation. The CPU load for the whole running FSW is measured in significant and time-consuming operational scenarios with the aim of proving that the CPU load requirements are fulfilled. Such approach has been applied to an industrial-sized spacecraft FSW and points out the importance of focusing on this topic in the early phases of the FSW development.
Keywords: SW schedulability analysis; spacecraft flight software; response time analysis; RTA; worst-case execution time; WCET; spacecraft operations.
Zero-error channel capacity of quantum 5-symbol obfuscation model
by Wenbin Yu, Zijia Xiong, Yang Liu, Shanshan Rong, Siyao Wang, Yinsong Xu, Alex X. Liu
Abstract: The existing noise channel coding methods need to be optimised in terms of channel capacity and algorithm complexity. Based on the characteristics of the quantum 5-symbol confusion-channel model and the theory of matrices, a coding method is proposed which combines the 5-symbol confusion channel with the quantum-superposition-state coding. This coding method uses two isomorphism steps to obtain the zero-error code words, which are the isomorphism between quantum superposition states and vectors and the isomorphism between channels and matrices. The theoretical derivation proves that the channel capacity is able to increase by employing quantum zero-error coding other than its classical counterpart.
Keywords: quantum coding; zero-error channel; channel capacity.
Urban waterlogging monitoring and early warning based on video images
by Fengchang Xue, Juan Tian, Xiaoyi Song, Yan Yan
Abstract: Urban flood disaster causes serious loss to urban residents. Timely access to urban waterlogging conditions has great significance for disaster prevention and disaster relief. Owing to the time resolution limitation of data, the traditional monitoring of urban flood disasters using remote sensing imagery cannot realise real-time automatic monitoring and continuous monitoring of key disaster areas. This paper selects road monitoring video, uses image difference operation and support vector machine (SVM) algorithm to identify the waterlogging area, and uses the region growing method to extract the waterlogging area range. The research results show that this method can be used for continuous monitoring and early warning of urban waterlogging in real time.
Keywords: waterlogging monitoring; road monitoring video; support vector machine; SVM; region growing method.
Enterprise internationalisation performance evaluation model based on artificial neural network
by Guojun Yang, Xiaohu Zhou, Zhiyao Liang
Abstract: The internationalisation performance of enterprises has been affected by many factors. Designing scientific and effective evaluation index system and conducting comprehensive evaluation are important means to help international enterprises to evaluate their internationalisation performance reasonably. This paper comprehensively reviews the research findings of factors influencing internationalisation performance and indexes at home and abroad, focusing on two quantifiable factors of financial performance and structural proportion, and constructs a hierarchy of internationalisation performance evaluation index system. Secondly, artificial neural network (ANN) is used for adaptive training to obtain the optimised connection weights. Finally, the data of some enterprises' internationalisation performance indexes are collected for empirical research to illustrate the rationality and effectiveness of the method.
Keywords: artificial neural network; ANN; internationalisation performance; index system; evaluation; enterprise internationalisation; financial performance; structural proportion.
Attacking the Niederreiter-type cryptosystem based on rank metric
by Chungen Xu, Yingying Zhang, Lin Mei, Lei Xu, Cong Zuo
Abstract: This paper deals with the Niederreiter cryptosystem based on Gabidulin codes which were solidly broken by Overbeck within polynomial time. In this paper, we first review the conditions under Overbeck's attack applications and then adjust corresponding parameters to target a high-security level. Since the permutation matrix and the scrambling matrix are used in Gabidulin codes, then the Frobenius matrices have too much structure to be hidden. By analysing the rank of the system matrix, we can find that choosing the matrix such that the dimension of the kernel of the public parity-check matrix greater than one will achieve a good result. In addition, we also show that bounding the rank of the distortion matrix is to enhance the security of the system. Finally, we give the security analysis of the modified Niederreiter type cryptosystem and demonstrate that it can resist structural and decoding attacks.
Keywords: public key; syndrome decoding; Gabidulin code; rank metric; Niederreiter.
Rainfall runoff prediction via a hybrid model of neighbourhood rough set with LSTM
by Xiaoli Li, Guomei Song, Shuailing Zhou, Yujia Yan, Zhenlong Du
Abstract: Accurate rainfall runoff prediction is crucial for flood forecasting and water resources management, and it remains a challenging issue in hydrological information processing. The most challenging problem is that the hydrological information has a strong locality and nonlinearity, which leads to poor prediction accuracy. Neighbourhood rough sets has strong capability on data classification and reduction, which can reduce those redundant rainfall runoff data. Long short-term memory (LSTM) network is a special recurrent neural network (RNN) that is an excellent variant of RNN, it is good at handling the time series data. In the paper, a hybrid model of neighbourhood rough sets with LSTM is proposed, which is used for the rainfall runoff prediction. The experimental results show that the presented model could improve the training speed of LSTM and achieve much higher prediction accuracy than the conventional rainfall runoff prediction methods.
Keywords: neighbourhood rough sets; attribute reduction; rainfall and runoff prediction; long short-term memory network.
Revocable ciphertext-policy attribute-based encryption in data outsourcing systems from lattices
by Xixi Yan, Chaochao Yang, Qichao Zhang, Jinxia Yu
Abstract: Attribute-based encryption mechanism is widely used in outsourcing systems because of its characteristics of 'one-to-many' communication. However, users' attributes often change dynamically. In order to solve the problem of attribute revocation in the attribute-based encryption scheme in the outsourcing systems, a revocable ciphertext policy attribute-based encryption in data outsourcing systems from lattices is proposed. The scheme uses the LWE problem to construct the encryption and decryption algorithm, which can resist the quantum attack. Tree-access structure is adopted to realise flexible fine-grained access strategy. In addition, with the help of the data outsourcing management server, the attribute key and ciphertext are updated to achieve immediate attribute revocation. The scheme is proved to be secure under the selective attribute and selective plaintext attacks. The comparative analysis shows that the scheme has a significant improvement in performance, and it supports immediate attribute revocation, which is more suitable for the dynamic change of users in the outsourcing systems, such as social network platforms.
Keywords: lattices; attribute-based encryption; attribute revocation; data outsourcing system.
A decision tree algorithm for forest fire prediction based on wireless sensor networks
by Demin Gao, Jie Xin, Fuquan Zhang
Abstract: Forest fire poses a significant threat not only to the natural environment and ecological systems but also to the safety of human life and property. Combined with new technologies, a decision tree algorithm is proposed for forest fire prediction, in which wireless sensor networks technology is utilised to transmit data and predict the ignition of the forest. There are four meteorological parameters as part of training data, containing temperature, relative humidity, wind speed, and daily precipitation, while the other part is prediction results of Forest Weather Index system. The decision tree generated by our system could classify these parameters from the most significant to the least significant so that it can better foretell fire occurrence. The analysis of prediction results shows that our system is effective.
Keywords: decision tree algorithm; forest fire prediction; wireless sensor networks; WSNs.
Low power transistor level synthesis of finite state machines using a novel dual gating technique
by Abhishek Nag, Subhajit Das, Sambhu Nath Pradhan
Abstract: In this work, an efficient technique of clock and power gating is concurrently introduced in finite state machines (FSM) with a view to minimising the overall power dissipation. The proposed power gating concept works on the principle of shutting down the power supply to the FSM during periods of inactivity. The extraction of the inactivity criteria is based on the occurrence of self-loops within the FSM or an unchanged FSM output between successive clock pulses. Clock gating, on the other hand, disables the clock signal to the sequential blocks of the FSM during this inactive/idle periods. The idea of implementing the gating in both the state logic as well as output logic is introduced in this work. The proposed approach has been introduced in three benchmark FSM circuits, simulated and synthesised in Cadence digital design tool. The results indicate a maximum of 73% total power savings (dynamic and static) with an average penalty of 27% area (approx.).
Keywords: clock gating; power gating; finite state machine; FSM; self-loops.
A combinational convolutional neural network of double subnets for food-ingredient recognition
by Lili Pan, Cong Li, Yan Zhou, Rongyu Chen, Bing Xiong
Abstract: Deep convolutional neural networks (DCNNs) have become the dominant machine learning for visual object recognition. They have been widely used in food image recognition and have achieved excellent performance. However, not only are the food-ingredient datasets not easy to obtain, but also the scale is not big enough to learn a deep learning model. For small-scale datasets, this paper proposes a novel DCNN architecture, which constructs an up-to-date combinational convolutional neural network of double subnets (CBDNet) for automatic classification of food ingredients using feature fusion. The feature fusion is a component which aggregates subnets for more abundant and precise deep feature extraction. In order to improve classification accuracy, some useful strategies are adopted, including batch normalisation (BN) operation and hyperparameters setting. Finally, experimental results show that the CBDNet integrating double subnets, feature fusion and BN operation extracts better image features and effectively improves the performance of food-ingredient recognition.
Keywords: food-ingredient recognition; deep feature; deep learning; deep convolutional neural network; DCNN.
Time-aware parallel collaborative filtering movie recommendation based on Spark
by Jing Zhang, Dan Yang
Abstract: Most of the traditional collaborative filtering (CF) recommendation models mainly consider the users' ratings on items, often ignore the time context information of users. However this information is non-trivial to improve the effectiveness of recommender system. A time-aware parallel CF movie recommendation based on Spark is proposed in this paper. The CF algorithm based on matrix factorisation can associate users' interests with items through implicit features and solve the sparse matrix problem. The time-aware CF algorithm considers the dynamic features associated with the items and users, which improves the recommendation accuracy by introducing discrete time parameter into the matrix factorisation model. To solve the problem of the slow processing speed of high volume data, distributed computing based on Spark is used to achieve the parallelisation of the algorithm. The experimental results on real dataset MovieLens show that the proposed method performs significantly better than traditional CF recommendation, which can alleviate the problem of data sparsity and significantly improve the processing speed and recommendation accuracy.
Keywords: time-aware; collaborative filtering recommendation algorithm; matrix factorisation; Spark.
Factor analysis and evaluation of China's higher education development in big data era
by Hangjun Zhou, Xingxing Zhou, Jing Liu, KeZhuo Chen
Abstract: Big data has become an indispensable part of higher education development now, and most of the related data in higher education of China can be applied to evaluation and analysis. However, currently there is a lack of research on the development of higher education using the latest China Statistical Yearbook data. In this paper, based on the latest data, by using SPSS to analyse and evaluate the development of higher education, the new issues can be discovered and initial reliability recommendations can be proposed. Therefore, we will have more profound and unique insights and applications in the practice of the big data era, and will further provide evidence and clues to better support and develop China's higher education.
Keywords: higher education; data analysis; SPSS; big data.
A software-based calibration approach to increase the robustness of embedded systems
by Md. Al Maruf, Akramul Azim
Abstract: Embedded systems often interact with dynamic environments requiring not only to meet deadlines but also to achieve a certain level of accuracy. Since the inaccuracy of a task output produces a similar adverse effect like timing violation, we propose a software-based calibration approach to increase the robustness of embedded systems by monitoring and comparing system component's output accuracy with a calibration standard to take actions for addressing any inaccuracy. The calibration standard is derived from a representative component's output with known high accuracy. As an example, we analyse the accuracy of a component that performs dynamic voltage and frequency scaling (DVFS) and explains the associated timing effects in terms of task schedulability. We also perform experiments on LITMUSRT kernel to demonstrate the need and applicability of our calibration approach in the domain of embedded systems.
Keywords: real-time embedded systems; task scheduling; task accuracy; software-based calibration; DVFS algorithm; LITMUSRT; monitoring framework; quality of service; QoS; accuracy-based schedulability; calibration standards.
Effect of the crowdfunding description on investment decisions from the perspective of prosocial behaviour
by Yonghui Dai, Tao Wang, Ziyi Wang, Bo Xu
Abstract: Alleviating poverty is a global challenge and requires extensive mobilisation of the participation from every social force. A feasible way for alleviating poverty is the crowdfunding through the internet, which could receive financial aid from a number of people all over the world for some reasonable projects released online officially. This work argues that prosocial behaviour can increase the possibilities of achieving projects' fundraising goals. Based on the prosocial behaviour theory, this work analyses the prosocial factors from the poverty alleviation projects' textual data published on an international crowdfunding platform, Kiva, and establish the logit model to test and verify the feasibility of these factors. The results show that the fundraiser identity and fundraising project orientation in the crowdfunding description both play critical roles in the financial funding process.
Keywords: poverty alleviation; crowdfunding; prosocial behaviour; investment decisions.
Special Issue on: Advances in Intelligence, Security, Privacy and Trust Technologies for the Social Internet of Things
by Yong-fang Qi, Liang-song Li, You-hua Peng
Abstract: This manuscript presents a method to solve the conformable fractional differential systems. In the first place, some results about conformable fractional are introduced. Secondly, the method used to get the general solutions of conformable fractional equations is developed. Finally, some examples of application of the method are presented.
Keywords: conformable fractional; differential system; general solution.