模糊逻辑信号强度识别算法的设计与验证
|
摘要
随着各种无线设备的日益普及,无线定位技术得到较多的应用,无线局域网因其广泛的覆盖范围成为了室内定位的更好选择。目前大部分无线局域网的定位技术都是基于到达时间、到达时间差和到达方向等,但这些信息需要发射机与接收机之间的准确同步,实现难度大,基于接收信号强度RSS的解决方案利用待测点感应的来自接入点AP的信号强度,且不需要专门设备支持,减少了额外的系统负担。
无线环境的复杂性和不同无线客户端之间的物理性能和软件差异,导致了信号强度特性在不同无线客户端之间存在非常大的差异。本文采取位置指纹方法解决了如上问题。方法在离线阶段,通过采集初始参考点处接收到的各个AP的信号强度值,并经过信号室内传播特性分析及信号预处理过程建立Radio Map,并以此训练算法,在线阶段以信号覆盖图为基础,在待测点进行空间信号的实时采样,然后通过算法匹配得出对采样数据的位置预测结果。
本文所设计模糊逻辑信号强度识别算法在结构辨识方面采用了减法聚类法,通过定义数据点的密度函数,将一个模糊空间内具有最大密度的数据点选为聚类中心,从而将一个模糊集划分为若干的模糊子集。然后通过神经网络BP算法调节IF-THEN规则的前、后件参数,从而达到系统误差最小的目的。信号强度均值具有较好的位置依赖性,在此基础上,本文选取了单复杂性和双复杂性两个实验环境,在测试环境1中,多数参考点的信号强度直方分布图呈现双峰特性,极大的影响了均值的位置依赖性,也是造成定位算法泛化能力下降的主要原因,通过微波暗室及网卡互干扰性实验发现,双峰现象的产生与网卡和AP的连接状态有关。为更加详细的分析系统性能,算法以自由空间的传播模型为基础进行了理想情况下仿真了系统性能。文章最后将本算法在两个测试环境内x轴和y轴的仿真定位结果与NN方法得到的结果相比较,仿真结果表明该算法在室内办公环境有较好的定位精度。
With an increasing popularity of a variety of wireless devices, the perceived demand of location-based information is gradually rising up in recent years, which made the wireless location technology be widely used. At present, most of the WLAN positioning technologies are based on Time of Arrival, Time Difference of Arrival and Direction of Arrival etc, which requires synchronization between the transmitter and receiver, and is difficult to achieve in many applications. Another choice of WLAN positioning is based on Receiving Signal Strength (RSS) which is a better choice of indoor positioning for its broad coverage.
The non-line-of-sight transmission of wireless network signal and the difference between physical properties and software of client lead to the large difference of RSS characters. The Fingerprint method the paper adopts is a good solution for the problems above, which selects RSS as the location character. During the off-line phase, the system establishes Radio Map through the analysis of indoor signal propagation and pre-processing part, then enters the off-line fuzzy logic positioning algorithm training one, reselects the initial reference points on the condition of over fitting or over matching. During the on-line phase, this method makes the real-time space signal sampling at the checking points on the basis of Radio map, inputs pre-processing sampling data in fuzzy logic positioning algorithm for searching and matching period, finally achieves the predicted point coordinates.
This paper adopts the clustering method for the structure identification. After defining and amending the density of each point, the clustering method selects the data with the highest density as the cluster center, then take the iterative process constantly until identify all the effective cluster centers,so as to divide the fuzzy set into sub sets. This paper adopts the BP algorithm of the neural network model to optimize the parameters for the objective of minimum systematic error. The mean of RSS has good location dependence, in two experimental environments, this paper selects the mean of AP as the features of location and the algorithm input. The RSS straight distribution shows bimodal distribution characteristics which greatly influences the location dependence and is the main reason for the decline of generalization ability. The further experiment shows the connection status of APs and network card has great influence on bimodal distribution, which is proved in the reference experiment of the network card. In the second environment, the result shows an improvement with a large upgrade. For a more detailed analysis of system performance, the algorithm makes an ideal based on simulation free space propagation model. Finally, this paper states the simulation of the algorithm and a comparation of NN algorithm, which shows the fuzzy logic algorithm a good system performance based on signal strength.
无线环境的复杂性和不同无线客户端之间的物理性能和软件差异,导致了信号强度特性在不同无线客户端之间存在非常大的差异。本文采取位置指纹方法解决了如上问题。方法在离线阶段,通过采集初始参考点处接收到的各个AP的信号强度值,并经过信号室内传播特性分析及信号预处理过程建立Radio Map,并以此训练算法,在线阶段以信号覆盖图为基础,在待测点进行空间信号的实时采样,然后通过算法匹配得出对采样数据的位置预测结果。
本文所设计模糊逻辑信号强度识别算法在结构辨识方面采用了减法聚类法,通过定义数据点的密度函数,将一个模糊空间内具有最大密度的数据点选为聚类中心,从而将一个模糊集划分为若干的模糊子集。然后通过神经网络BP算法调节IF-THEN规则的前、后件参数,从而达到系统误差最小的目的。信号强度均值具有较好的位置依赖性,在此基础上,本文选取了单复杂性和双复杂性两个实验环境,在测试环境1中,多数参考点的信号强度直方分布图呈现双峰特性,极大的影响了均值的位置依赖性,也是造成定位算法泛化能力下降的主要原因,通过微波暗室及网卡互干扰性实验发现,双峰现象的产生与网卡和AP的连接状态有关。为更加详细的分析系统性能,算法以自由空间的传播模型为基础进行了理想情况下仿真了系统性能。文章最后将本算法在两个测试环境内x轴和y轴的仿真定位结果与NN方法得到的结果相比较,仿真结果表明该算法在室内办公环境有较好的定位精度。
With an increasing popularity of a variety of wireless devices, the perceived demand of location-based information is gradually rising up in recent years, which made the wireless location technology be widely used. At present, most of the WLAN positioning technologies are based on Time of Arrival, Time Difference of Arrival and Direction of Arrival etc, which requires synchronization between the transmitter and receiver, and is difficult to achieve in many applications. Another choice of WLAN positioning is based on Receiving Signal Strength (RSS) which is a better choice of indoor positioning for its broad coverage.
The non-line-of-sight transmission of wireless network signal and the difference between physical properties and software of client lead to the large difference of RSS characters. The Fingerprint method the paper adopts is a good solution for the problems above, which selects RSS as the location character. During the off-line phase, the system establishes Radio Map through the analysis of indoor signal propagation and pre-processing part, then enters the off-line fuzzy logic positioning algorithm training one, reselects the initial reference points on the condition of over fitting or over matching. During the on-line phase, this method makes the real-time space signal sampling at the checking points on the basis of Radio map, inputs pre-processing sampling data in fuzzy logic positioning algorithm for searching and matching period, finally achieves the predicted point coordinates.
This paper adopts the clustering method for the structure identification. After defining and amending the density of each point, the clustering method selects the data with the highest density as the cluster center, then take the iterative process constantly until identify all the effective cluster centers,so as to divide the fuzzy set into sub sets. This paper adopts the BP algorithm of the neural network model to optimize the parameters for the objective of minimum systematic error. The mean of RSS has good location dependence, in two experimental environments, this paper selects the mean of AP as the features of location and the algorithm input. The RSS straight distribution shows bimodal distribution characteristics which greatly influences the location dependence and is the main reason for the decline of generalization ability. The further experiment shows the connection status of APs and network card has great influence on bimodal distribution, which is proved in the reference experiment of the network card. In the second environment, the result shows an improvement with a large upgrade. For a more detailed analysis of system performance, the algorithm makes an ideal based on simulation free space propagation model. Finally, this paper states the simulation of the algorithm and a comparation of NN algorithm, which shows the fuzzy logic algorithm a good system performance based on signal strength.
引文
1. S. Tekinay, E. Chao, and R. Richton. Performance Benchmarking for Wireless Location Systems. IEEE Communications Magazine. 1998, 36(4): 72-76.
2. P. Prasithsangaree, P. Krishnamurthy and P. Chrysanthis. On Indoor Position Location with Wireless LANs. The 13th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications. 2002: 720-724.
3.袁正午.移动通信系统终端射线跟踪定位理论与方法.电子工业出版社, 2007: 32-41.
4. Nissanka B. Priyantha, Anit Chakraborty and PHari Balakrishnan. The Cricket Location-Support System. International Conference on Mobile Computing and Networking 2000. 2000: 32-43.
5. T. Liu, P. Bahl, I. Chlamtac. A Hierarchical Position-Prediction Algorithm for Efficient Management of Resources in Cellular Networks. Proceedings of the IEEE GLOBECOM’97. 1997: 982-986.
6. C. Ma, R. Klukas, G. Lachapelle. An Enhanced Two Step Least Squared Approach for TDOA/AOA Wireless Location. IEEE International Conference on Communication 2003. 2003: 987-991.
7. Cong Li, Zhuang Weihua. Hybrid TDOA/AOA Mobile User Location for Wideband CDMA Cellular Systems. IEEE Transactions on Wireless Communications. 2002, 1(3): 439-447.
8. P. Bahl, V. N. Padmanabhan. Radar: An In-building RF-Based User Location and Tracking System. Proceedings of IEEE INFOCOM 2000. 2000: 775-784.
9. R. Battiti, M. Brunato, A. Villani. Statistical Learning Theory for Location Fingerprinting in Wireless LANs. Technical Report DIT-02-0086, University di Trento. 2002.
10. Zhou Junyang, W. M. C. Yeung and J. K. Y. Ng. Enhancing Indoor Positioning Accuracy by Utilizing Signals from Both the Mobile Phone Network and the Wireless Local Area Network. The 22nd International Conference on Advanced Information Networking and Applications 2008. 2008: 138-145.
11.郎昕培,许可,赵明.基于无线局域网的位置定位技术研究和发展.计算机科学. 2006(l33): 21-24.
12. L. A. Zadeh. Fuzzy Sets. Information Contro1, 1965, 8(3): 338-353.
13. E. H. Mamdani. Applications of Fuzzy Algorithms for Simple Dynamic Plant. Proceedings of IEE, 1974, 121(12): 1585-1588.
14. P. J. King, E. H. Mamdani. The Application of Fuzzy Control System to a Industrial Processes. Automat. 1977, 13(3): 235-242.
15. M. M. Gupta, G. N. Saridis, and B. R. Gaines Fuzzy Logic Automata and Decision Processes. Amsterdam: NorthHolland Publishing Company, 1977: 285-320.
16. Tomohiro Takagi, Michio Sugeno. Fuzzy Identification of Systems and Its Applications to Modeling and Control. IEEE Transactions on Systems, Man, and Cybernetics. 1985, 15(1): 116-132.
17. Hong Hui, Jian-Hua Li. Fingerprint Matching Using ANFIS. IEEE International Conference on Systems, Man and Cybernetics 2003. 2003: 217-222.
18. Wu Bing-Fei, Jen Cheng-Lung and Chang Kuei-Chung. Neural Fuzzy Based Indoor Localization by Kalman Filtering with Propagation Channel Modeling. IEEE International Conference on Systems, Man and Cybernetics 2007. 2007: 812-817.
19.闻新,周露. MATLAB模糊逻辑工具箱的分析与应用.科学出版社, 2001: 51-68.
20.吴小莉. MATLAB辅助模糊系统设计.西安电子科技大学出版社, 2002: 78-89.
21.伍士虔,徐军.动态模糊逻辑神经网络设计与应用.清华大学出版社, 2008:
102-119.
22. A. K. M. Mahtab Hossain, Van Hien Nguyen, et al. Indoor Localization Using Multiple Wireless Technologies. IEEE Internatonal Conference on Mobile Ad Hoc and Sensor Systems 2007. 2007: 1-8.
23. Chen Jiansheng, Moon Yiu-Sang. The Statistical Modelling of Fingerprint Minutiae Distribution with Implications for Fingerprint Individuality Studies. IEEE Conference on Computer Vision and Pattern Recognition 2008. 2008: 1-7.
24. Wang Hui-hui, Zhai Chuan-run, et al. The Research and Geometric Analysis of Indoor Positioning Using Multiple Pseudolites Signals. Congress on Image and Signal Processing 2008. 2008: 203-207.
25. H. K. Lam, Z. Hou, et al. A Systematic Topological Method for Fingerprint Singular Point Detection. The 10th International Conference on Control, Automation, Robotics and Vision 2008. 2008: 967-972.
26. B. A. Bushong. Fuzzy Clustering of Baseball Statistics. Fuzzy Information Processing Society Annual Meeting of the North American. 2007: 66-68.
27. J. Casillas, O. Cordon, M. J. De1 Jesus, et al. Genetic Feature Selection in a Fuzzy Rule-Based Classification System Learning Process for High-Dimensional Problems. Information Science. 2001, (136): 135-157.
28. H. Ishibuchi, T. Nakashima and T. Murata. Three-Objective Genetics-Based Machine Learning for Linguistic Rule Extraction. Information Sciences. 2001, 136(14): 109-133.
29. S. Abe, R. Thawonmas. A Fuzzy Classifier with Ellipsoidal Regions. IEEE Transactions on Fuzzy Systems. 1997, (5): 358-368.
30. Chen Yixin, J. Z. Wang. Support Vector Learning for Fuzzy Rule-Based Classification Systems. IEEE Transactions on Fuzzy Systems. 2003, 11(6): 716-728.
31. Song Chi-Hwa, Jeong Jin-Ku, et al. A Mean Field Annealing Algorithm for Fuzzy Clustering. Fourth International Conference on Fuzzy Systems and Knowledge Discovery. 2007: 193-197.
32. Yu Jian, Yang Miin-Shen. A Generalized Fuzzy Clustering Regularization Model with Optimality Tests and Model Complexity Analysis. IEEE Transactions on Fuzzy Systems. 2007, 15(5): 904-915.
33. Hou Yanfeng, J. M. Zurada, et al. Identification of Key Variables Using Fuzzy Average with Fuzzy Cluster Distribution. IEEE Transactions on Fuzzy Systems. 2007, 15(4): 673-685.
34. K. Derr, M. Manic. Wireless Based Object Tracking Based on Neural Networks. The 3rd IEEE Conference on Industrial Electronics and Applications. 2008: 308-313.
35. Lo Kuen-Rong, Chang Chung-Ju and C. B. Shung. A Neural Fuzzy Resource Manager for Hierarchical Cellular Systems Supporting Multimedia Services. IEEE Transactions on Vehicular Technology. 2003, 52(5): 1196-1206.
36. F. Evennou, F. Marx and E. Novakov. Map-Aided Indoor Mobile Positioning System Using Particle Filter. IEEE Wireless Communications and Networking Conference 2005. 2005: 2490-2494.
37. E. C. L. Chan, G. Baciu and S. C. Mak. Wireless Tracking Analysis in Location Fingerprinting. IEEE International Conference on Wireless and Mobile Computing Networking and Communications 2008. 2008: 214-220.
38. M. Llombart, M. Ciurana and F. Barcelo-Arroyo. On the Scalability of a Novel WLAN Positioning System Based on Time of Arrival Measurements. The 5th Workshop on Positioning, Navigation and Communication 2008. 2008: 15-21.
39. A. Teuber, B. Eissfeller and T. Pany. A Two-Stage Fuzzy Logic Approach for Wireless LAN Indoor Positioning. IEEE/ION Position, Location, And Navigation Symposium 2006. 2006: 730-738.
40. S. K. Modi, S. J. Elliott, et al. Impact of Age Groups on Fingerprint Recognition Performance. IEEE Workshop on Automatic Identification Advanced Technologies 2007. 2007: 19-23.
41. A. Kushki, K. N. Plataniotis, et al. Radio Map Fusion for Indoor Positioning in Wireless Local Area Networks. The 8th International Conference on Information Fusion. 2005: 8-16.
42. Wang Yuan, Yao Lixiu and Zhou Fuqiang. A Real Time Fingerprint Recognition System Based on Novel Fingerprint Matching Strategy. 8th International Conference on Electronic Measurement and Instruments 2007. 2007: 81-85.
43. Zhao Yongxiang, Zhou Huaibei, et al. Implementation of Indoor Positioning System Based on Location Fingerprinting in Wireless Networks. International Conference on Wireless Communications, Networking and Mobile Computing 2008. 2008: 1-4.
44. M. Stella, M. Russo and D. Begusic. Location Determination in Indoor Environment Based on RSS Fingerprinting and Artificial Neural Network. The 9th International Conference on Telecommunications 2007. 2007: 301-306.
45. Wang Hongpeng, Jia Fei. A Hybrid Modeling for WLAN Positioning System. International Conference on Wireless Communications, Networking and Mobile Computing 2007. 2007: 2152-2155.
2. P. Prasithsangaree, P. Krishnamurthy and P. Chrysanthis. On Indoor Position Location with Wireless LANs. The 13th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications. 2002: 720-724.
3.袁正午.移动通信系统终端射线跟踪定位理论与方法.电子工业出版社, 2007: 32-41.
4. Nissanka B. Priyantha, Anit Chakraborty and PHari Balakrishnan. The Cricket Location-Support System. International Conference on Mobile Computing and Networking 2000. 2000: 32-43.
5. T. Liu, P. Bahl, I. Chlamtac. A Hierarchical Position-Prediction Algorithm for Efficient Management of Resources in Cellular Networks. Proceedings of the IEEE GLOBECOM’97. 1997: 982-986.
6. C. Ma, R. Klukas, G. Lachapelle. An Enhanced Two Step Least Squared Approach for TDOA/AOA Wireless Location. IEEE International Conference on Communication 2003. 2003: 987-991.
7. Cong Li, Zhuang Weihua. Hybrid TDOA/AOA Mobile User Location for Wideband CDMA Cellular Systems. IEEE Transactions on Wireless Communications. 2002, 1(3): 439-447.
8. P. Bahl, V. N. Padmanabhan. Radar: An In-building RF-Based User Location and Tracking System. Proceedings of IEEE INFOCOM 2000. 2000: 775-784.
9. R. Battiti, M. Brunato, A. Villani. Statistical Learning Theory for Location Fingerprinting in Wireless LANs. Technical Report DIT-02-0086, University di Trento. 2002.
10. Zhou Junyang, W. M. C. Yeung and J. K. Y. Ng. Enhancing Indoor Positioning Accuracy by Utilizing Signals from Both the Mobile Phone Network and the Wireless Local Area Network. The 22nd International Conference on Advanced Information Networking and Applications 2008. 2008: 138-145.
11.郎昕培,许可,赵明.基于无线局域网的位置定位技术研究和发展.计算机科学. 2006(l33): 21-24.
12. L. A. Zadeh. Fuzzy Sets. Information Contro1, 1965, 8(3): 338-353.
13. E. H. Mamdani. Applications of Fuzzy Algorithms for Simple Dynamic Plant. Proceedings of IEE, 1974, 121(12): 1585-1588.
14. P. J. King, E. H. Mamdani. The Application of Fuzzy Control System to a Industrial Processes. Automat. 1977, 13(3): 235-242.
15. M. M. Gupta, G. N. Saridis, and B. R. Gaines Fuzzy Logic Automata and Decision Processes. Amsterdam: NorthHolland Publishing Company, 1977: 285-320.
16. Tomohiro Takagi, Michio Sugeno. Fuzzy Identification of Systems and Its Applications to Modeling and Control. IEEE Transactions on Systems, Man, and Cybernetics. 1985, 15(1): 116-132.
17. Hong Hui, Jian-Hua Li. Fingerprint Matching Using ANFIS. IEEE International Conference on Systems, Man and Cybernetics 2003. 2003: 217-222.
18. Wu Bing-Fei, Jen Cheng-Lung and Chang Kuei-Chung. Neural Fuzzy Based Indoor Localization by Kalman Filtering with Propagation Channel Modeling. IEEE International Conference on Systems, Man and Cybernetics 2007. 2007: 812-817.
19.闻新,周露. MATLAB模糊逻辑工具箱的分析与应用.科学出版社, 2001: 51-68.
20.吴小莉. MATLAB辅助模糊系统设计.西安电子科技大学出版社, 2002: 78-89.
21.伍士虔,徐军.动态模糊逻辑神经网络设计与应用.清华大学出版社, 2008:
102-119.
22. A. K. M. Mahtab Hossain, Van Hien Nguyen, et al. Indoor Localization Using Multiple Wireless Technologies. IEEE Internatonal Conference on Mobile Ad Hoc and Sensor Systems 2007. 2007: 1-8.
23. Chen Jiansheng, Moon Yiu-Sang. The Statistical Modelling of Fingerprint Minutiae Distribution with Implications for Fingerprint Individuality Studies. IEEE Conference on Computer Vision and Pattern Recognition 2008. 2008: 1-7.
24. Wang Hui-hui, Zhai Chuan-run, et al. The Research and Geometric Analysis of Indoor Positioning Using Multiple Pseudolites Signals. Congress on Image and Signal Processing 2008. 2008: 203-207.
25. H. K. Lam, Z. Hou, et al. A Systematic Topological Method for Fingerprint Singular Point Detection. The 10th International Conference on Control, Automation, Robotics and Vision 2008. 2008: 967-972.
26. B. A. Bushong. Fuzzy Clustering of Baseball Statistics. Fuzzy Information Processing Society Annual Meeting of the North American. 2007: 66-68.
27. J. Casillas, O. Cordon, M. J. De1 Jesus, et al. Genetic Feature Selection in a Fuzzy Rule-Based Classification System Learning Process for High-Dimensional Problems. Information Science. 2001, (136): 135-157.
28. H. Ishibuchi, T. Nakashima and T. Murata. Three-Objective Genetics-Based Machine Learning for Linguistic Rule Extraction. Information Sciences. 2001, 136(14): 109-133.
29. S. Abe, R. Thawonmas. A Fuzzy Classifier with Ellipsoidal Regions. IEEE Transactions on Fuzzy Systems. 1997, (5): 358-368.
30. Chen Yixin, J. Z. Wang. Support Vector Learning for Fuzzy Rule-Based Classification Systems. IEEE Transactions on Fuzzy Systems. 2003, 11(6): 716-728.
31. Song Chi-Hwa, Jeong Jin-Ku, et al. A Mean Field Annealing Algorithm for Fuzzy Clustering. Fourth International Conference on Fuzzy Systems and Knowledge Discovery. 2007: 193-197.
32. Yu Jian, Yang Miin-Shen. A Generalized Fuzzy Clustering Regularization Model with Optimality Tests and Model Complexity Analysis. IEEE Transactions on Fuzzy Systems. 2007, 15(5): 904-915.
33. Hou Yanfeng, J. M. Zurada, et al. Identification of Key Variables Using Fuzzy Average with Fuzzy Cluster Distribution. IEEE Transactions on Fuzzy Systems. 2007, 15(4): 673-685.
34. K. Derr, M. Manic. Wireless Based Object Tracking Based on Neural Networks. The 3rd IEEE Conference on Industrial Electronics and Applications. 2008: 308-313.
35. Lo Kuen-Rong, Chang Chung-Ju and C. B. Shung. A Neural Fuzzy Resource Manager for Hierarchical Cellular Systems Supporting Multimedia Services. IEEE Transactions on Vehicular Technology. 2003, 52(5): 1196-1206.
36. F. Evennou, F. Marx and E. Novakov. Map-Aided Indoor Mobile Positioning System Using Particle Filter. IEEE Wireless Communications and Networking Conference 2005. 2005: 2490-2494.
37. E. C. L. Chan, G. Baciu and S. C. Mak. Wireless Tracking Analysis in Location Fingerprinting. IEEE International Conference on Wireless and Mobile Computing Networking and Communications 2008. 2008: 214-220.
38. M. Llombart, M. Ciurana and F. Barcelo-Arroyo. On the Scalability of a Novel WLAN Positioning System Based on Time of Arrival Measurements. The 5th Workshop on Positioning, Navigation and Communication 2008. 2008: 15-21.
39. A. Teuber, B. Eissfeller and T. Pany. A Two-Stage Fuzzy Logic Approach for Wireless LAN Indoor Positioning. IEEE/ION Position, Location, And Navigation Symposium 2006. 2006: 730-738.
40. S. K. Modi, S. J. Elliott, et al. Impact of Age Groups on Fingerprint Recognition Performance. IEEE Workshop on Automatic Identification Advanced Technologies 2007. 2007: 19-23.
41. A. Kushki, K. N. Plataniotis, et al. Radio Map Fusion for Indoor Positioning in Wireless Local Area Networks. The 8th International Conference on Information Fusion. 2005: 8-16.
42. Wang Yuan, Yao Lixiu and Zhou Fuqiang. A Real Time Fingerprint Recognition System Based on Novel Fingerprint Matching Strategy. 8th International Conference on Electronic Measurement and Instruments 2007. 2007: 81-85.
43. Zhao Yongxiang, Zhou Huaibei, et al. Implementation of Indoor Positioning System Based on Location Fingerprinting in Wireless Networks. International Conference on Wireless Communications, Networking and Mobile Computing 2008. 2008: 1-4.
44. M. Stella, M. Russo and D. Begusic. Location Determination in Indoor Environment Based on RSS Fingerprinting and Artificial Neural Network. The 9th International Conference on Telecommunications 2007. 2007: 301-306.
45. Wang Hongpeng, Jia Fei. A Hybrid Modeling for WLAN Positioning System. International Conference on Wireless Communications, Networking and Mobile Computing 2007. 2007: 2152-2155.