臺灣博碩士論文加值系統

本論文主要在探討無線感測網路(WSNs)中使用人工智慧之群聚演算法於目標的定位與追蹤，設計一套可使用在戶外的定位與追蹤的救援系統，希望藉由群聚演算法讓無線感測網路中目標的定位與追蹤可以達到快速、高且辨識精確的效能。在無線感測網路技術應用中，目標定位及追蹤一直是被探討的問題之一，其方法有接收信號角度法(Angle of Arrival, AOA)、到達時間法(Time of Arrival, TOA)與到達時間差定位法(Time Difference of Arrival, TDOA)等，但在實際應用上三種方法其設備相當昂貴，所以許多目標定位及追蹤相關研究常使用接收訊號強度(Received Signal Strength Indicator, RSSI)作為估測目標點與參考節點距離的依據，RSSI之優點在於設備取得容易、運算複雜度較低，因此我們將使用RSSI作為估測目標點與演算法個體(行動節點)距離的依據，然而在無線訊號從發射端發送出時，因訊號接觸到各種障礙物後的反射、散射和其他物理特性，使得接收端接收到的訊號會有相當大的誤差値，因此本論文提出混合式群聚演算法，利用個體(行動節點)移動的特性，進行戶外空間之目標定位及追蹤，如此便可減少誤差與因節點佈置不當對目標定位及追蹤造成的影響，也可以減少搜尋時間、人力與成本並增加定位或追蹤的成功率。
本論文使用粒子群最佳化演算法(Particle Swarm Optimization, PSO)往最佳解群聚之特性與倒傳遞類神經網路演算法(Back Propagation Neural Network, BPNN)監督式學習之特性，搭配RSSI通道模型作為目標函式來做室外空間目標定位及追蹤之模擬分析，並比較單一群聚演算法與混合式群聚演算法於目標定位與追蹤之效能優劣。本研究中演算法個體(行動節點)為接收端，目標點為發射端，將接收端與發射端之距離透過RSSI通道模型得到初始之RSSI値來模擬實際環境之狀況，再利用演算法模擬生物覓食之習性，演算法個體會向食物源(RSSI値)最大的方向移動，透過個體多次移動後估測出目標點所在位置，如此藉由數個演算法個體(行動節點)互相溝通與資料交流來降低因RSSI值之波動所造成的誤差，但這也衍生出另一問題，要使目標位置估測及追蹤的精準度提升，勢必要增加演算法個體的使用數量，如此才能保證有足夠的資料能夠分析及比較，因此要在不影響目標定位及追蹤之精準度上減少演算法個體使用的數量也是本研究所探討的問題之一。另外，本論文也針對提升目標定位及追蹤的效率，提出區域分割方法(Region Segmentation Method, RSM)、倒傳遞類神經網路演算法(Back Propagation Neural Network, BPNN)、動態個體選擇方法(Dynamic Individual Selection, DIS)，而模擬結果顯示，在不影響目標定位及追蹤之精準度下，所提出之方法能大幅減少演算法個體使用數量與誤差值，且可提升定位及追蹤之速度。

This paper mainly discusses the positioning and tracking of the target algorithm based on the swarm algorithm of artificial intelligence in wireless sensor networks (WSNs), and designs a rescue system that can be used for outdoor positioning and tracking. The positioning and tracking of targets in wireless sensing networks can achieve fast, high performance and accuracy. In the application of wireless sensor network technology, target location and tracking has been one of the problems to be discussed. The methods include Angle of Arrival (AOA), Time of Arrival (TOA) and arrival Time Difference of Arrival (TDOA), etc. In the practical application of these methods, its equipment is very expensive; therefore, many related researches of target positioning and tracking often use the Receive Signal Strength Indicator (RSSI) method. The advantage of the RSSI is that the device is easy to obtain and the computational complexity is low. Therefore, we will use RSSI as the basis for estimating the distance between the target point and the algorithm individual (Mobile Node). However, when the wireless signal is sent from the transmitter to receiver, the reflection, scattering, and other physical characteristics of the various barriers would cause the received RSSI value have a substantial error. Therefore, we propose Hybrid Swarm Algorithm (HSA) to slove the problem. Using the property of mobile individuals (Mobile Node) to locate and track objects in the outdoor space. In the case, it can reduce the influence of improper placement of the individuals on the target location and tracking, and can also reduce the cost of search time, work force and cost, and increase the success rate of positioning or tracking.
In this thesis, we used the characteristics of Particle Swarm Optimization (PSO) and Back Propagation Neural Network (BPNN), which used the individual''s ability of communication between individuals and supervised learning for target localization and tracking. In addition, we use the RSSI value as objective function to implement target positioning and tracking and compare the performance of single Swarm Optimization algorithm with that of Hybrid Swarm Algorithm. In this thesis, we set algorithm individuals (Mobile Node) as receiver and target point as transmitter. We use distance between receiver and transmitter to produce the RSSI value of channel model for initial to simulate real world conditions. Using the algorithm to simulate the habit of bio foraging. Individual of algorithm will move to the direction of the largest food source (RSSI value). We estimate the location of the target point by the moving individual. We could reduce the estimation error that caused by RSSI variation via the information sharing mechanism. On the other hand, we have to use more individuals to track the target positioning and tracking. A study to improve the accuracy of target positioning and tracking with less amount of individuals is addressed. To enhance the efficiency of positioning and tracking, the Regional Segmentation Method (RSM), Back Propagation Neural Network (BPNN) and Dynamic Individual Selection (DIS) are proposed in this paper. Simulations show that these methods can be significantly shorten the target positioning and tracking time, and have good precision performance.

摘要...i
Abstract...iii
誌謝...v
目錄...vi
表目錄...viii
圖目錄...xii
第一章 緒論...1
1.1 研究背景...1
1.2 研究動機及目的...2
1.3 論文架構...3
第二章 文獻回顧...4
2.1 RSSI通道模型介紹...4
2.2 粒子群最佳化演算法介紹...7
2.2.1 粒子群最佳化演算法概述...7
2.2.2 粒子群最佳化演算法行為...7
2.2.3 粒子群最佳化演算法改進...11
2.3 倒傳遞類神經網路演算法介紹...11
2.3.1 類神經網路演算法概述...11
2.3.2 類神經網路演算法架構...14
2.3.3 倒傳遞類神經網路演算法運作流程...15
2.4 混合式群聚演算法...18
2.4.1 混合式群聚演算法概述...18
2.4.2 混合式群聚演算法架構與流程...18
第三章 系統架構...20
3.1 粒子群最佳化演算法之目標定位方法...20
3.1.1 自適應速度權重方法...21
3.2 混合式群聚演算法之目標定位方法...22
3.3 區域分割方法...24
3.4 隨機點目標定位...26
3.5 目標追蹤方法...29
3.5.1 目標追蹤方法網路定義...30
3.5.2 演算法個體移動限制...31
3.5.3 粒子群最佳化演算法之目標追蹤方法...33
3.5.4 混合式群聚演算法之目標追蹤方法...35
3.5.5 動態個體選擇方法...37
第四章 模擬實驗與結果...38
4.1 模擬環境與設定...38
4.2 目標定位模擬分析...39
4.2.1 高斯隨機變數標準差於目標定位之影響...39
4.2.2 BPNN目標定位參數最佳化模擬分析...40
4.2.3 HSA目標定位模擬分析...47
4.2.4 PSO目標定位及HSA目標定位效能分析...59
4.3 目標追蹤模擬分析...69
4.3.1 BPNN目標追蹤參數最佳化模擬分析...69
4.3.2 HSA目標追蹤模擬分析...76
4.3.3 PSO目標追蹤與HSA目標追蹤效能分析...100
第五章結論與未來展望...120
參考文獻...121
Extended Abstract...125
簡歷(CV)...130

[1]鄭軍、張寶賢，無線傳感器網路技術，機械工業出版社，2012。
[2]曾煜棋、林政寬、林致宇、潘孟鋐，無線網路通訊協定、感測網路射頻技術與應用服務，碁?資訊股份有限公司，2011。
[3]A. Aziz, I. Joe, and Y. Choi, “A Localization Algorithm for Disaster Situation Using Flying Sensor Nodes”, 2014 International Conference on Information Science & Applications (ICISA), pp. 1-4, 2014.
[4]Q. Yang, Z. Wang, and Y. Yue, “Summarize the technology of the things of Internet”, 2012 2nd International Conference on Consumer Electronics, Communications and Networks (CECNet), pp. 1357-1360, 2012.
[5]M. Collotta, and G. Pau, “A Novel Energy Management Approach for Smart Homes Using Bluetooth Low Energy”, IEEE Journal on Selected Areas in Communications, vol. 33, pp. 2988-2996, 2015.
[6]M. Bagheri, and S. H. Movahed, “The Effect of the Internet of Things (IoT) on Education Business Model”, 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp. 435-441, 2016.
[7]M. A. Al-Taee, W. Al-Nuaimy, Z. J. Muhsin, and A. Al-Ataby, “Robot Assistant in Management of Diabetes in Children Based on the Internet of Things”, IEEE Internet of Things Journal, vol. 4, pp. 437-445, 2017.
[8]F. Hu, D. Xie, and S. Shen, “On the Application of the Internet of Things in the Field of Medical and Health Care”, 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, pp. 2053-2058, 2013.
[9]E. Xu, Z. Ding, and S. Dasgupta, “Target Tracking and Mobile Sensor Navigation in Wireless Sensor Networks”, IEEE Transactions on Mobile Computing, vol. 12, no. 1, pp. 177-186, 13 Dec. 2013.
[10]H. La, T. Nguyen, C. Hguyen, and H. N. Nguyen, “Optimal Flocking Control for a Mobile Sensor Network Based a Moving Target Tracking”, Proc. of IEEE International Conference on System, Man, and Cybernetics, San Antonio, pp. 4801-4806, 11-14 Oct. 2009.
[11]M. Laaraiedh, L. Yu, S. Avrillon, and B. Uguen, “Comparison of Hybrid Localizaiton Schemes using RSSI, TOA, and TDOA”, Proc. of IEEE Wireless Conference 2011-Substainalbe Wireless Technologies (European Wireless) 11th Europeanm, Vianna, Austria, pp. 1-5, 27-29 April 2011.
[12]L. Cheng, C. Wu, and Yun-Zhou Zhang, “Indoor Robot Localization Based on Wireless Sensor Networks”, IEEE Transactions on Computer Electronics, vol. 57, no. 3, pp. 1099-1104, August 2011.
[13]吳伯彥，2014，”模糊邏輯技術在XBee無線感測網路之RSSI定位演算法”，國立虎尾科技大學電機工程研究所碩士論文，頁 1~96。
[14]李紹瑋，2015，”雙層棋盤架構Zigbee網路應用於任意室內面積定位法之研究”，國立虎尾科技大學電機工程研究所碩士論文，頁 1~40。
[15]Z. Liu, and Z. Liu, “Node Self-Localization Algorithm for Wireless Sensor Networks Based on Modified Particle Swarm Optimization”, Proc. of the 27th Chinese Control and Decision Conference, Qingdao, pp. 5968-5971, 23-25 May 2015.
[16]C. Xu, and J. Chen, “Three-dimentional Sensor Node Localization based on AFSA-LSSVM”, International Jounal of Control & Automation, vol.7, no. 8, pp. 399-406, 2014.
[17]J. Godoy, A. Lanbert, and J. Villagra, “Development of an Particle Swarm Algorithm for Vehicle Localization”, Proc. of IEEE Intelligent Vehicles Symposium, Alcala de Henares, pp. 1114-1119, 3-7 June 2012.
[18]S. K. Gharghan, R. Nordin, M. Ismail, and J. A. Ali, “Accurate Wireless Sensor Localization Technique Based on Hybrid PSO-ANN Algorithm for Indoor and Outdoor Track Cycling”, IEEE Sensor Journal, vol. 16, no.2, pp. 529 -541, 29 September 2015.
[19]L. Ming-jie, and Z. Jin-guo, “The application and development of Internet of Things with its solutions of restrictive factors”, 2011 International Conference on Mechatronic Science, Electric Engineering and Computer (MEC), pp. 282-285, 2011.
[20]Y. Kang, and Z. Zhongyi, “Summarize on Internet of Things and exploration into technical system framework”, 2012 IEEE Symposium on Robotics and Applications (ISRA), pp. 653-656, 2012.
[21]Y. Gadallah, M. Tager, and E. Elalamy, “A framework for cooperative intranet of Things wireless sensor network applications”, 2015 IEEE 11th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), pp. 147-154, 2015.
[22]S. Agarwal, R. R. Murphy, and J. A. Adams, “Characteristics of Indoor Disaster Environments for Small UASs”, 2014 IEEE International Symposium on Safety, Security, and Rescue Robotics, pp. 1-6, 2014.
[23]S. Kumar, V. Reddy, P. Prakash, and A. P, “Fast Response Search and Rescue Robot, Assisted Low Power WSN Net for Navigation and Detection”, India Educators'' Conference (TIIEC), 2013 Texas Instruments, pp. 12-17, 2013.
[24]S. Gu, Y. Yue, C. Maple, and C. Wu, “Fuzzy logic based localisation in Wireless Sensor Networks for disaster environments”, 18th International Conference on Automation and Computing (ICAC), pp. 1-5, 2012.
[25]K. Liao, J. He, S. Zhou, and E. Li, “Optimization for cooperative spectrum sensing with energy detection in disaster environment”, 2015 Asia-Pacific Microwave Conference (APMC), vol.1, pp. 1-3, 2015.
[26]B. Soni, and A. Sowmya, “Victim Detection and Localisation in an Urban Disaster Site”, 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 2142-2147, 2013.
[27]J. Kim, J. J. Jang, and I.Y. Jung, “Near Real-Time Tracking of IoT Device Users”, 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 1085-1088, 2016.
[28]李志鵬、江弘志、林垂彩，WCDMA基頻訊號處理與系統設計實務，滄海書局，2007。
[29]Z. Fang, Z. Zhao, D. Geng, Y. Xuan, L. Du, and X. Cui, “RSSI Variability Characterization and Calibration Method in Wireless Sensor Network”, Proc. of IEEE International Conference on Information and Automation, Harbin, pp. 1532-1537, 20-23 June 2010.
[30]J. Xiong, Q. Qin, and K. Zheng, “A Distant Measurement Wireless Localization Correction Algorithm Based on RSSI”, Proc. of Seventh International Symposium on Computation Intelligence and Design, Hangzhou, pp. 176-278, 13-14 Dec. 2014.
[31]P. Barsocchi, S. Lenzi, S. Chessa, and G. Giunta, “A Novel Approach to Indoor RSSI Localization by Automatic Calibration of the Wireless Propagtion Model”, Proc. of IEEE 69th Vehicular Technology Conference, Barcelona, pp.1-5, 26-29 April 2009.
[32]J. Kennedy, R. Eberhart, “Particle Swarm Optimization”, Proc of IEEE International Conference on Nerual Networks, Perth, WA, vol.4 pp. 1942-1948, 27 Nov. ,1 Dec 1995.
[33]J. Kennedy, R. Eberhart, “A New Optimizer Using Particle Swarm Theory”, Proc. of Sixth Inernational Symposium on Micro Machine and Human Science, Nagoya, pp. 39-43, 4-6 Oct. 1995.
[34]F. Zhang, J. Cao, and Z. Xu, “An Imprved Particle Swarm Optimization Particle Filtering Algorithm”, Proc. of IEEE International Conference on Communications, Circuit and System, Chengdu, pp. 173-177, 15-17 Nov. 2013.
[35]D. Yan, J. Wang, L. Lui, and B. Wang, “Sensor Scheduling Target Tracking-oriented Based on Particle Swarm Optimization”, Proc. of 30th Chinese Control Conference, Yantai, pp. 5050-5053, 22-24 July 2011.
[36]K. Selvaraj, and S. Balaji, “Controlled Mobility Sensor Networks for Target Tracking Using Particle Swarm Optimization”, Proc. of International Conference on Current Trends in Engineering and Technology, Coimbatore, pp. 388-391, 3 July 2013.
[37]D. A. Prasetya, and T. Yasuno, “Cooperative Control of Multiple Mobile Robot Using Particle Swarm Optimization for Tracking Two Passive Target”, Proc. SICE Annual Conference, Akita, pp.1751-1754, 20-23 Aug. 2012.
[38]何怡偉、高一統、黃冠勳，2014， ”整合粒子群體演算法與單體法求解多目標問題之研究”，大同大學資訊工程碩士班碩士論文，頁 1~87。
[39]林建誌，2016，”基於群聚演算法之無線感測網路目標定位與追蹤”，國立虎尾科技大學電機工程研究所碩士論文，頁 1~104。
[40]S. He, N. B. H. Hamam, and Y. Bouslimani, “Fuzzy Clustering with Improved Artificial Fish Swarm Algorithm”, Proc. of International Joint Conference on Computatuinal Sciences and Optimization, Sanya, Hainan, pp.317-321, 24-26 April 2009.
[41]Rumelhart, D. E, H. G. E, and W. R. J, “Learning representations by back-propagating errors”, Nature, pp. 533-536, October 1986.
[42]許翔智，2016，”在ZigBee室內定位系統中以倒傳遞類神經網路提升區域定位準確性之研究”，國立虎尾科技大學電機工程研究所碩士論文，頁 1~46。
[43]Y. E. Hamzaoui, and J. A. H. Perez, “Application of Artificial Neural Networks to Predict the Selling Price in the Real Estate Valuation Process”, 2011 10th Mexican International Conference on Artificial Intelligence, pp.175-181, 2011.
[44]L. Xiaobin, “RBF Neural Network Optimized by Particle Swarm Optimization for Forecasting Urban Traffic Flow”, 2009 Third International Symposium on Intelligent Information Technology Application, pp. 124-127, 2009.
[45]D. Srinivasan, F. C. Yong, and A. C. Liew, “Electricity Price Forecasting Using Evolved Neural Networks”, 2007 International Conference on Intelligent Systems Applications to Power Systems, pp. 1-7, 2007.
[46]M. Sahin, H. I. Bulbul, and I. Colak, “Position Control of a DC Motor Used in Solar Panels with Artificial Neural Network”, 2012 11th International Conference on Machine Learning and Applications, pp. 487-492, 2012.
[47]W. Zhang, Z. Liu, and X. Zhou, “Wavelet neural network adaptive learning algorithm and its ship control application”, 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR), pp. 353-357, 2011.
[48]H. F. HSAhem, “Adaptive technique for human face detection using HSV color space and neural networks”, 2009 National Radio Science Conference, pp. 1-7, 2009.
[49]Z. Lin, and J. Z. Chen, “Classification of the normal and abnormal electrogastrogram using back-propagation neural networks”, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1091-1092, 1994.
[50]R. Dey, V. Bajpai, G. Gandhi, and B. Dey, “Application of Artificial Neural Network (ANN) technique for Diagnosing Diabetes Mellitus”, 2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems, pp. 1-4, 2008.
[51]李文慶，2014，“在OFDM系統中以改良式倒傳遞類神經網路進行通道估測之研究”，國立虎尾科技大學電機工程研究所碩士論文，頁 1-126。
[52]S. Razavi, and B. A. Tolson, “A New Formulation for Feedforward Neural Networks”, IEEE Transactions on Neural Networks, pp. 1588-1598, 2011.
[53]張斐章、張麗秋，類神經網路導論原理與應用，滄海書局，2010。
[54]葉怡成，類神經網路模式應用與實作，儒林圖書有限公司，1993。
[55]王進德、蕭大全，類神經網路與模糊控制理論入門，全華科技圖書股份有限公司，2003。
[56]R. C. Eberhart, and Y. Shi, “Tracking and Optimizing Dynamic Systems with Particle Swarms”, Proceedings of the 2001 Congress on Evolutionary Computation, pp.94-100, vol.1, 2001.