International Journal of Wireless and Mobile Computing http://www.inderscience.com/browse/index.php?journalID=46&year=2011&vol=5&issue=1 Inderscience Publishers Ltd en-uk International Journal of Wireless and Mobile Computing 1741-1084 1741-1092 © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijwmc_scoverijwmc.jpg http://www.inderscience.com/browse/index.php?journalID=46&year=2011&vol=5&issue=1 http://www.inderscience.com/link.php?id=44112 In next generation wireless networks mobile users will be able to roam between heterogeneous networks, using terminals with multiple access interfaces. An important issue in such a heterogeneous environment is the provisioning of seamless mobility to users across heterogeneous access networks, according to the Always Best Connected and Served (ABC&S) model. Various vertical handover decision strategies have been proposed in the literature recently to answer ABC&S requirements, using advanced tools. In this paper we introduce a handover decision scheme that deploys fuzzy logic to address the uncertainty that is innate in some decision parameters. Furthermore, we elaborate on how the networks collect and adjust their resources that are broadcasted to the mobile terminals; we also explain how the mobile terminals rank the available offers by the networks. A handover is performed only if a network’s offer is considered more satisfactory than current status. Finally, a discussion is made through numerical paradigm and simulations, highlighting the proposed scheme’s effectiveness. Fuzzy-based handover decision with multi-attribute auctions in heterogeneous network environments
Dimitris E. Charilas; Athanasios D. Panagopoulos
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 1 - 11
In next generation wireless networks mobile users will be able to roam between heterogeneous networks, using terminals with multiple access interfaces. An important issue in such a heterogeneous environment is the provisioning of seamless mobility to users across heterogeneous access networks, according to the Always Best Connected and Served (ABC&S) model. Various vertical handover decision strategies have been proposed in the literature recently to answer ABC&S requirements, using advanced tools. In this paper we introduce a handover decision scheme that deploys fuzzy logic to address the uncertainty that is innate in some decision parameters. Furthermore, we elaborate on how the networks collect and adjust their resources that are broadcasted to the mobile terminals; we also explain how the mobile terminals rank the available offers by the networks. A handover is performed only if a network’s offer is considered more satisfactory than current status. Finally, a discussion is made through numerical paradigm and simulations, highlighting the proposed scheme’s effectiveness.

]]> 10.1504/IJWMC.2011.044112 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 1 - 11 Dimitris E. Charilas; Athanasios D. Panagopoulos National Technical University of Athens, School of Electrical & Computer Engineering, Mobile Radio Communications Laboratory, Iroon Polytechniou 9, Zografou 15780, Athens, Greece ' National Technical University of Athens, School of Electrical & Computer Engineering, Mobile Radio Communications Laboratory, Iroon Polytechniou 9, Zografou 15780, Athens, Greece 4G networks QoS quality of service game theory multi-attribute auctions fuzzy logic fuzzy inference systems multi-attribute decision making fuzzy TOPSIS heterogeneous environments wireless networks seamless mobility mobile communications handover decisions uncertainty. 2011-12-09T23:20:50-05:00 5 1 1 11 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44108 Reliability is an important parameter to measure the function of a wireless sensor network (WSN). In this paper, we consider a multi-state reliability model and message time delay problems in WSNs. The message time delay between target nodes and the sink node is an important factor to measure the reliability of WSNs. By defining the expected time delay for the message transmission, we further consider the multi-state reliability as the probability that there is at least one message which can be received by the sink node within the time period ?. Furthermore, an integer programming method is used to compute the multi-state reliability. Finally, examples are used to show the effectiveness of the proposed method. Multi-state reliability and message time delay in wireless sensor networks
Tao Shen; Fang-Ming Shao
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 12 - 17
Reliability is an important parameter to measure the function of a wireless sensor network (WSN). In this paper, we consider a multi-state reliability model and message time delay problems in WSNs. The message time delay between target nodes and the sink node is an important factor to measure the reliability of WSNs. By defining the expected time delay for the message transmission, we further consider the multi-state reliability as the probability that there is at least one message which can be received by the sink node within the time period ?. Furthermore, an integer programming method is used to compute the multi-state reliability. Finally, examples are used to show the effectiveness of the proposed method.

]]> 10.1504/IJWMC.2011.044108 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 12 - 17 Tao Shen; Fang-Ming Shao School of Science, East China University of Science and Technology, Shanghai 200237, China ' School of Science, East China University of Science and Technology, Shanghai 200237, China WSNs wireless sensor networks message time delay reliability wireless networks. 2011-12-09T23:20:50-05:00 5 1 12 17 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44116 In this paper, some improvements on Ant Colony Optimisation (ACO) are presented and we use the improved algorithm to solve the multicast routing problem. The improvements are given as follows: A novel optimised implementing approach is designed to reduce the processing costs (the bandwidth, delay, mincost) involved with routing of ants in the conventional ACO. Based on the model of network routing, the set of candidates is limited to the nearest c points in order to reduce the counting of other points. And we also use the flags on the blocked points in order to prevent selecting these points. Simulations show that the speed of convergence of the improved algorithm can be enhanced greatly compared with the traditional algorithm. An improved ant colony optimisation and its application on multicast routing problem
Zhang Yi; Liu Yan-chun
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 18 - 23
In this paper, some improvements on Ant Colony Optimisation (ACO) are presented and we use the improved algorithm to solve the multicast routing problem. The improvements are given as follows: A novel optimised implementing approach is designed to reduce the processing costs (the bandwidth, delay, mincost) involved with routing of ants in the conventional ACO. Based on the model of network routing, the set of candidates is limited to the nearest c points in order to reduce the counting of other points. And we also use the flags on the blocked points in order to prevent selecting these points. Simulations show that the speed of convergence of the improved algorithm can be enhanced greatly compared with the traditional algorithm.

]]> 10.1504/IJWMC.2011.044116 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 18 - 23 Zhang Yi; Liu Yan-chun Department of Computer Science, Jilin Business and Technology College, Changchun 130062, China; Military Simulation Technology Institute, Air Force Aviation University, Changchun 130022, China ' Military Simulation Technology Institute, Air Force Aviation University, Changchun 130022, China ant colony optimisation ACO multicast routing QoS constraints quality of service self-adaptive simulation. 2011-12-09T23:20:50-05:00 5 1 18 23 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44103 This paper proposes a simple combining technique with arbitrary modulations for a cooperative relay scheme based on a detect-and-forward relay protocol. Here we present maximum likelihood criterion detection at the destination which considers individual symbol error rate to facilitate the detection in noisy relay networks. In particular, our proposed algorithm is flexible to signals with different modulation formats as detection is done on a symbol-by-symbol basis. If different modulations are used at the source and the relays, we propose that lower modulation constellation is used at the source. By computer simulations, the results show that significant packet error rate performance can be achieved by the proposed scheme and we compare it against cooperative-maximum ratio combining and selection combining. Maximum likelihood detection with arbitrary modulations in cooperative relay channels
Azlan Abd Aziz; Yasunori Iwanami
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 24 - 31
This paper proposes a simple combining technique with arbitrary modulations for a cooperative relay scheme based on a detect-and-forward relay protocol. Here we present maximum likelihood criterion detection at the destination which considers individual symbol error rate to facilitate the detection in noisy relay networks. In particular, our proposed algorithm is flexible to signals with different modulation formats as detection is done on a symbol-by-symbol basis. If different modulations are used at the source and the relays, we propose that lower modulation constellation is used at the source. By computer simulations, the results show that significant packet error rate performance can be achieved by the proposed scheme and we compare it against cooperative-maximum ratio combining and selection combining.

]]> 10.1504/IJWMC.2011.044103 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 24 - 31 Azlan Abd Aziz; Yasunori Iwanami Department of Computer Science and Engineering, Graduate School of Engineering, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya 466-8555, Japan ' Department of Computer Science and Engineering, Graduate School of Engineering, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya 466-8555, Japan cooperative relay channels detect-and-forward relay protocol maximum-likelihood criterion detection arbitrary modulation. 2011-12-09T23:20:50-05:00 5 1 24 31 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44117 This paper investigates an analytical model of a channel allocation algorithm with a finite population of users in mobile cellular networks. The recursive formulas are derived for the new call blocking and handoff dropping probabilities of the Finite Population Fractional Guard Channel policies. The Fractional Guard Channel policy reserves a non-integral number of guard channels for handoff calls by rejecting new calls that depend on the current channel occupancy. The effect of users’ mobility on the maximum system capacity is achieved when the Finite Population Uniform Fractional Guard Channel (FPUFGC) policy is evaluated. It is shown that FPUFGC policy performs better than Finite Population Guard Channel policy under the low handoff/new traffic ratio. An optimal parameter of FPUFGC minimises the blocking probability subject to the constraint on the dropping probability. Numerical results show that the proposed policy gives an improved system performance, compared to the most commonly used handover algorithms. Performance analysis of finite population fractional guard channel policies in mobile cellular networks
Veena Goswami; Prasanta Kumar Swain
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 32 - 42
This paper investigates an analytical model of a channel allocation algorithm with a finite population of users in mobile cellular networks. The recursive formulas are derived for the new call blocking and handoff dropping probabilities of the Finite Population Fractional Guard Channel policies. The Fractional Guard Channel policy reserves a non-integral number of guard channels for handoff calls by rejecting new calls that depend on the current channel occupancy. The effect of users’ mobility on the maximum system capacity is achieved when the Finite Population Uniform Fractional Guard Channel (FPUFGC) policy is evaluated. It is shown that FPUFGC policy performs better than Finite Population Guard Channel policy under the low handoff/new traffic ratio. An optimal parameter of FPUFGC minimises the blocking probability subject to the constraint on the dropping probability. Numerical results show that the proposed policy gives an improved system performance, compared to the most commonly used handover algorithms.

]]> 10.1504/IJWMC.2011.044117 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 32 - 42 Veena Goswami; Prasanta Kumar Swain School of Computer Application, KIIT University, Bhubaneswar-751024, India ' School of Computer Application, KIIT University, Bhubaneswar-751024, India finite population channel reservation CAC call admission control fractional guard channel policy QOS quality of service channel allocation modelling mobile cellular networks mobile networks handoff calls user mobility. 2011-12-09T23:20:50-05:00 5 1 32 42 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44109 The optimal coverage problem plays an important role in wireless sensor networks. In this paper a new swarm intelligent technique, Social Emotional Optimisation Algorithm (SEOA), is used to solve the problem based on the probability measuring model. In SEOA, each individual represents a virtual person, and selects the behaviour according to the corresponding emotion index in each iteration. Simulation results showed that the effective coverage has reached 99.98%. Optimal coverage configuration with social emotional optimisation algorithm in wireless sensor networks
Zhihua Cui; Xingjuan Cai
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 43 - 47
The optimal coverage problem plays an important role in wireless sensor networks. In this paper a new swarm intelligent technique, Social Emotional Optimisation Algorithm (SEOA), is used to solve the problem based on the probability measuring model. In SEOA, each individual represents a virtual person, and selects the behaviour according to the corresponding emotion index in each iteration. Simulation results showed that the effective coverage has reached 99.98%.

]]> 10.1504/IJWMC.2011.044109 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 43 - 47 Zhihua Cui; Xingjuan Cai Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, Shanxi 030024, China; State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210093, China ' Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, Shanxi 030024, China social emotional optimisation optimal coverage wireless sensor networks WSNs wireless networks swarm intelligence emotion index simulation. 2011-12-09T23:20:50-05:00 5 1 43 47 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44106 A new version of the stream cipher Grain-128 is proposed. The new version, Grain-128a, is strengthened against all known attacks and observations on the original Grain-128, and has built-in support for optional authentication. The changes are modest, keeping the basic structure of Grain-128. This gives a high confidence in Grain-128a and allows for easy updating of existing implementations. Grain-128a: a new version of Grain-128 with optional authentication
Martin Ågren; Martin Hell; Thomas Johansson; Willi Meier
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 48 - 59
A new version of the stream cipher Grain-128 is proposed. The new version, Grain-128a, is strengthened against all known attacks and observations on the original Grain-128, and has built-in support for optional authentication. The changes are modest, keeping the basic structure of Grain-128. This gives a high confidence in Grain-128a and allows for easy updating of existing implementations.

]]> 10.1504/IJWMC.2011.044106 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 48 - 59 Martin Ågren; Martin Hell; Thomas Johansson; Willi Meier Department of Electrical and Information Technology, Lund University, P.O. Box 118, SE-221 00 Lund, Sweden ' Department of Electrical and Information Technology, Lund University, P.O. Box 118, SE-221 00 Lund, Sweden ' Department of Electrical and Information Technology, Lund University, P.O. Box 118, SE-221 00 Lund, Sweden ' FHNW Hochschule für Technik, Klosterzelgstr, CH-5210 Windisch, Switzerland Grain-128a Grain-128 stream cipher cryptographic primitive hardware attractive lightweight message authentication MAC medium access control security cryptography. 2011-12-09T23:20:50-05:00 5 1 48 59 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44107 This paper applies Dempster Shafer evidence theory to probe the synthetic evaluation issues, gets the Evidential Synthetic Evaluation (ESE) model and then uses ESE model to solve the performance evaluation problem of RMB PE funds. First, an index system to measure the performance of RMB PE funds has been built. The index weighting has been determined using Analytical Hierarchy Process (AHP) method. And then ESE model has been discussed and developed in the paper. For the examined six RMB PE funds, we invite three experts to give the evaluation scores and then using the ESE model to get the comprehensive score for each fund. Based on the comprehensive scores, a sort of six funds has been made. The model developed in this paper has the characteristics such as evidence collection way is more suitable for the human habit, the evidence received from different way can be combined and therefore the evaluation process can be extended if necessary. Finally, the model can deal with the incomplete and uncertain information. Using evidential synthetic evaluation model to evaluate the performance of RMB PE funds
Xinsheng Duan
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 60 - 69
This paper applies Dempster Shafer evidence theory to probe the synthetic evaluation issues, gets the Evidential Synthetic Evaluation (ESE) model and then uses ESE model to solve the performance evaluation problem of RMB PE funds. First, an index system to measure the performance of RMB PE funds has been built. The index weighting has been determined using Analytical Hierarchy Process (AHP) method. And then ESE model has been discussed and developed in the paper. For the examined six RMB PE funds, we invite three experts to give the evaluation scores and then using the ESE model to get the comprehensive score for each fund. Based on the comprehensive scores, a sort of six funds has been made. The model developed in this paper has the characteristics such as evidence collection way is more suitable for the human habit, the evidence received from different way can be combined and therefore the evaluation process can be extended if necessary. Finally, the model can deal with the incomplete and uncertain information.

]]> 10.1504/IJWMC.2011.044107 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 60 - 69 Xinsheng Duan School of Accounting, Capital University of Economics and Business, Beijing, 100070 China ESE evidential synthetic evaluation RMB PE funds MATLAB evidence theory performance evaluation analytical hierarchy process AHP incomplete information uncertain information private equity renminbi. 2011-12-09T23:20:50-05:00 5 1 60 69 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44110 Cloud computing is still in its infancy in spite of recently gained significant momentum. To allocate virtual machine resources in cloud data centre and taking both cloud preference and fairness into account are some of the major challenges. In this paper, a novel virtual machine scheduling algorithm by a clustering mechanism for maximising cloud computing system utility is put forward with a brief survey of virtual machine scheduling suitable for large-scale distributed virtual computing environments. It includes (a) modelling a general virtual machine scheduling model for clouds; (b) evaluating cloud preference of user and realising pre-classification virtual machines resources by a clustering mechanism in cloud data centre. The clustering mechanism is applied to meeting performance and fairness requirements of users and (c) designing the virtual machine scheduling algorithm in a cloud. Theoretical as well as experimental results conclusively demonstrate that the scheduling algorithm has high potential as it takes both preference and fairness into account, and maximises cloud computing system utility by the clustering mechanism in cloud computing environments. Modelling, evaluating and designing virtual machine scheduling by a clustering mechanism in cloud computing environments
Dawei Sun; Guiran Chang; Qiang Guo; Xingwei Wang
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 70 - 76
Cloud computing is still in its infancy in spite of recently gained significant momentum. To allocate virtual machine resources in cloud data centre and taking both cloud preference and fairness into account are some of the major challenges. In this paper, a novel virtual machine scheduling algorithm by a clustering mechanism for maximising cloud computing system utility is put forward with a brief survey of virtual machine scheduling suitable for large-scale distributed virtual computing environments. It includes (a) modelling a general virtual machine scheduling model for clouds; (b) evaluating cloud preference of user and realising pre-classification virtual machines resources by a clustering mechanism in cloud data centre. The clustering mechanism is applied to meeting performance and fairness requirements of users and (c) designing the virtual machine scheduling algorithm in a cloud. Theoretical as well as experimental results conclusively demonstrate that the scheduling algorithm has high potential as it takes both preference and fairness into account, and maximises cloud computing system utility by the clustering mechanism in cloud computing environments.

]]> 10.1504/IJWMC.2011.044110 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 70 - 76 Dawei Sun; Guiran Chang; Qiang Guo; Xingwei Wang School of Information Science and Engineering, Northeastern University, Shenyang 110004, China ' School of Information Science and Engineering, Northeastern University, Shenyang 110004, China ' School of Information Science and Engineering, Northeastern University, Shenyang 110004, China ' School of Information Science and Engineering, Northeastern University, Shenyang 110004, China virtual machines resource scheduling clustering mechanisms cloud computing virtual machine scheduling modelling. 2011-12-09T23:20:50-05:00 5 1 70 76 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44115 The present study reports the field strength measurements of some GSM transmitters in the 900 MHz band located in the urban and suburban regions of Delhi in India. The measured signal levels converted into path loss values have been compared with the losses predicted from models such as Hata, Lee and COST 231 Walfisch and Ikegami. The prediction errors and standard deviations of the prediction errors have been deduced. Based on these results, Lee prediction method has been tuned and new model parameters have been derived. The model comparison is done in terms of statistical parameters such as root mean square error, coefficient of determination and average hit rate error. Evaluation of cellular prediction models using 900 MHz outdoor measurements and tuning of Lee model over Indian urban and suburban regions
M.V.S.N. Prasad; K. Ratnamala; P.K. Dalela; Chandra Shekhar Misra
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 77 - 87
The present study reports the field strength measurements of some GSM transmitters in the 900 MHz band located in the urban and suburban regions of Delhi in India. The measured signal levels converted into path loss values have been compared with the losses predicted from models such as Hata, Lee and COST 231 Walfisch and Ikegami. The prediction errors and standard deviations of the prediction errors have been deduced. Based on these results, Lee prediction method has been tuned and new model parameters have been derived. The model comparison is done in terms of statistical parameters such as root mean square error, coefficient of determination and average hit rate error.

]]> 10.1504/IJWMC.2011.044115 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 77 - 87 M.V.S.N. Prasad; K. Ratnamala; P.K. Dalela; Chandra Shekhar Misra National Physical Laboratory, Dr. K.S. Krishnan Marg, New Delhi, India ' National Geophysical Research Institute, Uppal Road, Hyderabad 500606, Andhra Pradesh, India ' Centre for Development of Telematics (C-DOT), Chattarpur, Mehrauli, New Delhi, India ' AIRCOM International Pvt Ltd., M.G. Road, Gurgaon 122001, Haryana, India 900 MHz measurements path loss modelling Lee model tuning cellular prediction models outdoor measurements India urban areas suburban areas field strength measurements GSM transmitters. 2011-12-09T23:20:50-05:00 5 1 77 87 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44111 Clustering analysis is primarily concerned with the classification of data points into different clusters. Estimation of distribution algorithms (EDAs) uses machine learning techniques to solve optimisation problems by trying to learn the locations of the more promising regions of the search space. In EDAs a population may be approximated with a probability distribution, and new candidate solutions can be obtained by sampling from this distribution, instead of combining and modifying existing solutions in a stochastic way. Unsupervised clustering learning algorithm based on estimation of distribution (EDA-USL) is designed to solve the analysis of dataset without labels. EDA-USL randomly selects a few data as individuals to construct initial population. The probability distribution of population is computed to estimate the distribution of dataset. The optimal individuals in population are selected by the designed fitness function. Then the new individuals that combine with the optimal ones to form the next generation are selected according to the classification patterns of the optimal individuals. EDA-USL is validated on the benchmark datasets and analysed. The experimental results show that EDA-USL has high stability and performs well in classification accuracy. EDA-USL: unsupervised clustering algorithm based on estimation of distribution algorithm
Jiancong Fan; Yongquan Liang; Qiang Xu; Ruisheng Jia; Zhihua Cui
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 88 - 97
Clustering analysis is primarily concerned with the classification of data points into different clusters. Estimation of distribution algorithms (EDAs) uses machine learning techniques to solve optimisation problems by trying to learn the locations of the more promising regions of the search space. In EDAs a population may be approximated with a probability distribution, and new candidate solutions can be obtained by sampling from this distribution, instead of combining and modifying existing solutions in a stochastic way. Unsupervised clustering learning algorithm based on estimation of distribution (EDA-USL) is designed to solve the analysis of dataset without labels. EDA-USL randomly selects a few data as individuals to construct initial population. The probability distribution of population is computed to estimate the distribution of dataset. The optimal individuals in population are selected by the designed fitness function. Then the new individuals that combine with the optimal ones to form the next generation are selected according to the classification patterns of the optimal individuals. EDA-USL is validated on the benchmark datasets and analysed. The experimental results show that EDA-USL has high stability and performs well in classification accuracy.

]]> 10.1504/IJWMC.2011.044111 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 88 - 97 Jiancong Fan; Yongquan Liang; Qiang Xu; Ruisheng Jia; Zhihua Cui College of Information Science and Engineering, Shandong University of Science and Technology, Qingdao City, China ' College of Information Science and Engineering, Shandong University of Science and Technology, Qingdao City, China ' College of Information Science and Engineering, Shandong University of Science and Technology, Qingdao City, China ' College of Information Science and Engineering, Shandong University of Science and Technology, Qingdao City, China ' Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, Taiyuan City, China estimation of distribution evolutionary computation unsupervised learning clustering analysis machine learning optimisation stability classification accuracy. 2011-12-09T23:20:50-05:00 5 1 88 97 2011-12-09T23:20:50-05:00 http://www.inderscience.com/link.php?id=44102 Group Search Optimiser (GSO) is a new swarm intelligence optimiser algorithm inspired by animal social behaviours. In this paper, we proposed two variants of GSO to improve its search capability, and applied them to solving non-linear equations. Producers in the GSO are like the eyes of animals, which determine the ‘food’ position and the movement direction of scroungers. However, due to the random sample mechanism, the computational efficiency is poor. To improve its search efficiency, a new GSO based on quadratic interpolation method (QIGSO) is proposed, in which the estimated position with quadratic interpolation theory is used to replace the random point in each iteration to increase the speed of convergence. Furthermore, the steepest gradient descent method is also incorporated into QIGSO (QIGSO_SDO) to improve the local search capability. Numerical simulation and a special problem about radar detection are used to test the proposed two variants. Hybrid group search optimiser with quadratic interpolation method and its application
Jian Yao; Zhihua Cui; Zhanhong Wei; Ying Tan
International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 98 - 106
Group Search Optimiser (GSO) is a new swarm intelligence optimiser algorithm inspired by animal social behaviours. In this paper, we proposed two variants of GSO to improve its search capability, and applied them to solving non-linear equations. Producers in the GSO are like the eyes of animals, which determine the ‘food’ position and the movement direction of scroungers. However, due to the random sample mechanism, the computational efficiency is poor. To improve its search efficiency, a new GSO based on quadratic interpolation method (QIGSO) is proposed, in which the estimated position with quadratic interpolation theory is used to replace the random point in each iteration to increase the speed of convergence. Furthermore, the steepest gradient descent method is also incorporated into QIGSO (QIGSO_SDO) to improve the local search capability. Numerical simulation and a special problem about radar detection are used to test the proposed two variants.

]]> 10.1504/IJWMC.2011.044102 International Journal of Wireless and Mobile Computing, Vol. 5, No. 1 (2011) pp. 98 - 106 Jian Yao; Zhihua Cui; Zhanhong Wei; Ying Tan Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, No.66, Waliu Road, Wanbailin District, Taiyuan, Shanxi 030024, China ' Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, No.66, Waliu Road, Wanbailin District, Taiyuan, Shanxi 030024, China ' Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, No.66, Waliu Road, Wanbailin District, Taiyuan, Shanxi 030024, China ' Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, No.66, Waliu Road, Wanbailin District, Taiyuan, Shanxi 030024, China GSO group search optimiser quadratic interpolation steepest gradient descent nonlinear equations swarm intelligence optimisation search capability radar detection. 2011-12-09T23:20:50-05:00 5 1 98 106 2011-12-09T23:20:50-05:00