mesh无线网络节点系统平台的设计开发
摘要
无线Mesh网络(WMN,Wireless Mesh Network,有称无线网状网或无线网格网)这个名词出现的时间并不是太长,大约在20世纪90年代中期以后,而真正引起人们关注只是在近两年。WMN的出现并不是偶然,与很多新技术出现的背景一样,WMN的出现是应用需求直接推动的结果。本文就一下几个方面给出了研究成果:
在无线mesh网络中,业务是在网关处聚合以及投递,网关以有线的形式连接主干网。合理有效地放置网关能有效地对无线mesh网络管理。本文针对在多业务多信道无线mesh网络进行网关放置,旨在保证簇内Qos的前提下选取最小数目的网关节点。通过在蚁群优化迭代算法前完成对待选簇内Qos的保证,而后在多项式时间内反复计算最小闭覆盖集合。本文给出了详尽的理论分析以及仿真。
本文提出了一种新的可以尽最大可能地分离混叠的信号(观测信号数≥源信号数)算法,唯一的先决条件就是混叠矩阵A必须是行满秩。通过把恢复信号代价函数的协方差与恢复信号的协方差之比作为特征值,使求解一个广义特征值问题,因此算法具有非常快的收敛速度。而且算法针对病态混叠信号的分离表现出非常好的鲁棒性。
本文提出了一种基于mesh网络基础架构的不同表情的人脸识别及其重建系统。由于无线网络传输容量的限制,本文提出了将不同表情的投影到由ICA算法提取的基空间组成的一组系数向量,通过在服务器端进行余弦测度进行辨识以及表情重构。本文首先提出了针对不同表情的ICA辨识算法框架,而后根据PCA在正面人脸图像上摘除眼镜上细节表现力不够强,采用ICA重建不戴眼镜的与其表情最接近的人脸,提取了人脸图像中被眼镜遮挡的区域,通过一个迭代的误差补偿的方法,合成了对应输入图像的无眼镜人脸图像。该方法能有效地从输入图像中“摘除”眼镜,合成的图像看起来非常自然,不存在原来眼镜的痕迹。合成了无眼镜人脸图像之后,识别率相对于合成前提高了近70%。
Wireless mesh network is not existed for a long time; this techque attracts people's attention mostly in the mid 20 century. The appearance of wireless mesh network is not accidental but develops by direct requirement of clients, just like other new techs. The main contributions are listed as follows:
1. In a wireless mesh network (WMN), the traffic is aggregated and forwarded towards the gateways. Strategically placing and connecting the gateways to the wired backbone is critical to the management and efficient operation of a WMN. In this paper, we address the problem of gateways placement in multi-task and multi-channel wireless mesh networks, consisting in placing a minimum number of gateways such that quality-of-service (QoS) requirements are satisfied. We propose a polynomial time near-optimal algorithm which recursively computes maximal users Dominating Sets (DS), while consistently preserving QoS requirements before iterations. We evaluate the performance of our algorithm using both analysis and simulation.
2. Up to date, most blind source separation algorithms need sufficient pre-condition, that is, the number of observed signals should be more or at least equivalent to the number of source signals. This paper develop a new algorithm which can try its best to separate the mixed signals under the condition of below, the only needed condition is mixed matrix should be row full rank. Further we transform to solve a generalized eigenvector which corresponding eigenvalue is the ratio of the covariance of a part sum of observed signals and the covariance of observed signals, the convergence speed is very fast. The algorithm shows its efficiency for signals separation with ill-mixed signals. The computer simulation shows its outstanding performance on blind source separation approach.
3. This paper develops a new framework which used to different emotion recognition and reconstruction base on wireless mesh networks architecture. Because of constrained capacity of wireless transmission, we propose a solution which projects the different emotional vectors to base space which generate by ICA algorithm; we make the face recognition happen through projection. This paper firstly develops a framework to recognize different emotion base on ICA (Independent Component Analysis) algorithm. Because PCA (Principle Component Analysis) is lack of detailed description in removing eyeglasses from frontal facial image, so we develop a new framework to reconstruct the different emotion with eyeglasses on frontal facial image, and then synthesizes a natural looking eyeglasses facial image by recursive error compensation. The synthesized images have no trace of the eyeglasses or the reflection and shade caused by the eyeglasses. Test results show that the method can effectively synthesize eyeglasses. The recognition rate increases up to 70%.
在无线mesh网络中,业务是在网关处聚合以及投递,网关以有线的形式连接主干网。合理有效地放置网关能有效地对无线mesh网络管理。本文针对在多业务多信道无线mesh网络进行网关放置,旨在保证簇内Qos的前提下选取最小数目的网关节点。通过在蚁群优化迭代算法前完成对待选簇内Qos的保证,而后在多项式时间内反复计算最小闭覆盖集合。本文给出了详尽的理论分析以及仿真。
本文提出了一种新的可以尽最大可能地分离混叠的信号(观测信号数≥源信号数)算法,唯一的先决条件就是混叠矩阵A必须是行满秩。通过把恢复信号代价函数的协方差与恢复信号的协方差之比作为特征值,使求解一个广义特征值问题,因此算法具有非常快的收敛速度。而且算法针对病态混叠信号的分离表现出非常好的鲁棒性。
本文提出了一种基于mesh网络基础架构的不同表情的人脸识别及其重建系统。由于无线网络传输容量的限制,本文提出了将不同表情的投影到由ICA算法提取的基空间组成的一组系数向量,通过在服务器端进行余弦测度进行辨识以及表情重构。本文首先提出了针对不同表情的ICA辨识算法框架,而后根据PCA在正面人脸图像上摘除眼镜上细节表现力不够强,采用ICA重建不戴眼镜的与其表情最接近的人脸,提取了人脸图像中被眼镜遮挡的区域,通过一个迭代的误差补偿的方法,合成了对应输入图像的无眼镜人脸图像。该方法能有效地从输入图像中“摘除”眼镜,合成的图像看起来非常自然,不存在原来眼镜的痕迹。合成了无眼镜人脸图像之后,识别率相对于合成前提高了近70%。
Wireless mesh network is not existed for a long time; this techque attracts people's attention mostly in the mid 20 century. The appearance of wireless mesh network is not accidental but develops by direct requirement of clients, just like other new techs. The main contributions are listed as follows:
1. In a wireless mesh network (WMN), the traffic is aggregated and forwarded towards the gateways. Strategically placing and connecting the gateways to the wired backbone is critical to the management and efficient operation of a WMN. In this paper, we address the problem of gateways placement in multi-task and multi-channel wireless mesh networks, consisting in placing a minimum number of gateways such that quality-of-service (QoS) requirements are satisfied. We propose a polynomial time near-optimal algorithm which recursively computes maximal users Dominating Sets (DS), while consistently preserving QoS requirements before iterations. We evaluate the performance of our algorithm using both analysis and simulation.
2. Up to date, most blind source separation algorithms need sufficient pre-condition, that is, the number of observed signals should be more or at least equivalent to the number of source signals. This paper develop a new algorithm which can try its best to separate the mixed signals under the condition of below, the only needed condition is mixed matrix should be row full rank. Further we transform to solve a generalized eigenvector which corresponding eigenvalue is the ratio of the covariance of a part sum of observed signals and the covariance of observed signals, the convergence speed is very fast. The algorithm shows its efficiency for signals separation with ill-mixed signals. The computer simulation shows its outstanding performance on blind source separation approach.
3. This paper develops a new framework which used to different emotion recognition and reconstruction base on wireless mesh networks architecture. Because of constrained capacity of wireless transmission, we propose a solution which projects the different emotional vectors to base space which generate by ICA algorithm; we make the face recognition happen through projection. This paper firstly develops a framework to recognize different emotion base on ICA (Independent Component Analysis) algorithm. Because PCA (Principle Component Analysis) is lack of detailed description in removing eyeglasses from frontal facial image, so we develop a new framework to reconstruct the different emotion with eyeglasses on frontal facial image, and then synthesizes a natural looking eyeglasses facial image by recursive error compensation. The synthesized images have no trace of the eyeglasses or the reflection and shade caused by the eyeglasses. Test results show that the method can effectively synthesize eyeglasses. The recognition rate increases up to 70%.
引文
1.Nortel.[Online].Available:http://www.nortel.com
2.苗长云 有限用户多信道共用系统理论分析及应用研究博士学位论文2005
3.MIAO Changyun Principle of Line Configuration and Monte-Carlo Simulation for Shared Multi-Channel System Transactions of Tianjin University Vol.11 No.3 Jun.2005pp162-166
4.D.Shmoys,"Approximation algorithms for facility location problems," in Proc.APPROX,Sep.2000.v,pp.27-32.
5.Kuehn and M.J.Hamburger,"A heuristic program for locating warehouses," Manage.Sci.,pp.9:643-666,1963.
6.S.Arora,P.Raghavan,and S.Rao,"Approximation schemes for euclidean k-medians and related problems," in Proc.ACM Syrup.Theory Comput.,1998,pp.106-113.
7.J.Li,C.Blake,D.De Couto,H.Imm,and L.Morris,"Capacity of ad hoc wireless networks," in Proc.Int.Conf.Mobile Comput.Netw.,2001.
8.P.Hsiao,A.Hwang,H.Kung,and D.Vlah,"Load balancing routing for wireless access networks," in Proc.IEEE INFOCOM,1999.
9.J.Wong,R.Jafari,and M.potkonjak,"Gateway placement for latency and energy efficient data aggregation," in Proc.IEEE Int.Conf.Local Comput.Netw.,2004,pp.490-497.
10.R.Chandra,L.Qiu,K.Jain,and M.Mahdian,"Optimizing the placement of integration points in multi-hop wireless networks," in Proc.IEEE ICNP,2004.
11.Antis,R.Prakash,T.Vuong,and D.Huynh,"Max-min d-elusterformation in wireless ad hoc networks," in Proc.IEEE INFOCOM,2000,pp.32-41.
12.Girolami M.Self-organising Neural Networks:Independent Component Analysis and Blind Source Separation[M]London:Springer Verlag 1999
13.Haykin S.Unsupervised Adaptive Filtering,Vol Ⅰ:Blind Source Separation[M].New York:Wiley,2000.
14.Hyvarinen A,Karhunen J,Oja E.Independent Component Analysis[M].New York:Wiley,2001.
15.Tong L,Liu RW,Soon VC,et al.Indeterminacy and Identifiability of Blind Identification[J].IEEE Trans on Circuits and Systems 1991,38(5):499-509
16.Comon P.Independent Component Analysis,a New Concept[J].Signal Processing,1994,36(3):2872314.
17.张洪渊,贾鹏,史习智.确定盲分离中未知信号源个数的奇异值分解法[J].上海交通大学学报,2001,35(8):1155-1158.
18.姚志湘等 针对FastICA计算终点判断的算法改进 计算机工程与应用2006.26 46-49
19.J utten C,Herault J1 Independent component analysis versus principal component analysis [A]I In:Processing of European Signal Processing Conference,Grenoble,France,1988643-646
20.Comon P1 Independent component analysis,a new concept[J]Signal Processing,1994,36(3):287-314
21.张洪渊.信号源盲分离的理论与实验研究[D].上海:上海交通大学,2000,12:87-103.
22.J V Stone.Blind source separation using temporal predictability[J].Neural Computation,2001,13(7):1559-1574.
23.J.Weinmiller,H.Woesner and A.Wolisz,"Analysis and Improving the IEEE 802.11-MAC protocol for wireless LANs",MAS-COTS'96,San Jose,USA 1996,12(4):200-205
24.随机过程及应用 电子科技大学应用数学学院 陈良均等 高等教育出版社2003pp145-151
25.Ad Hoc移动无线网络 国防工业出版社王金龙等2003
26.下一代无线因特网技术:无线mesh网络人民邮电出版社方旭明等2006
27.IEEE Computer Society.802.11:Wireless LAN Medium Access Control(MAC) and Physical Layer(PHY) Specifications.June 1997
28.J.H.Chert and Y.D.Chen,"AMNP:Ad Hoc Multichannel Negotiation Protocol for Multihop Mobile Wireless Networks," IEEE International Conference on Communication (ICC),pp.3607-3612,Jun.2004.
29.S.L.Wu,C.Y.Lin,Y.C.Tseng,and J.P.Sheu,"A New Multi-Channel MAC Protocol with On-Demand Channel Assignment for Multi-Hop Mobile Ad Hoc Networks," International Symposium on Parallel Architectures,Algorithms and Networks(I-SPAN),December 2000.
30.W.C.Hung,K.Law,and A.Leon-Garcia,"A Dynamic Multi-Channel MAC for Ad Hoc LAN," 21st Biennial Symposium on Communications,Apr.2002.
31.N.Jain,S.R.Das,and A.Nasipuri,"A multichannd CSMA MAC protocol with receiver-based channel selection for multihop wireless networks," Computer Communications and Networks,pp.15-17,Oct.2001.
32.C.Y.Chang,H.C.Sun,and C.C.Hsieh,"MCDA:an efficient multichannel MAC protocol for 802.11 wireless LAN with directional antenna",19th International Conference on Advanced Information Networking and Applications(AINA),pp.64-67,Mar.2005.
33.H.Koubaa,"Fairness-Enhanced Multiple Control Channels MAC for Ad Hoe Networks,"IEEE 61st Vehicular Technology Conference(VTC),pp.1504-1508,Jun 2005.
34.Y.Yorozu,M.Hirano,K.Oka,and Y.Tagawa,"Electron spectroscopy studies on magneto-optical media and plastic substrate interfaces(Translation Journals style)," IEEE Transl.J.Magn.Jpn.,vol.2,
35.J.Chen,S.T.Sheu,and C.A.Yang,"A new multi-channel access protocol for IEEE 802.11ad hoc wireless LANs," Personal,Indoor and Mobile Radio Communications,IEEE,pp.7-10,Sept.2003.
36.Nakjung Choi,Yongho Seok and Yanghee Cho,"Multi-Channel MAC protocol for Mobile Ad hoc Networks",IEEE,pp.1379-1382,2003
37.Draft Supplement to STANDARD FOR Telecommunications and Information Exchange Between Systems-LAN/MAN Speci_c Requirements-Part 11:Wireless Medium Access Control(MAC) and Physical Layer(PHY) Speci_cations:Medium Access Control(MAC)Enhancements for Quality of Service(QoS).IEEE Std 802.11e/D3.0,May 2002
38.S Corson,J Macker1 Mobile ad hoe networking(MANET):Routing protocol performance issues and evaluation considerations[S]1 RFC2501,1999
39.Joseph P Macker,M Scott Corsonl Mobile ad hoe networking and the IETF[J]1 ACM SIGMOBIL E Mobile Computing and Communications Review,2002,6(2):1-2
40.G Maldinl RIP Version 2[S]1 RFC 2453,1998
41.J Moy1 OSPF Version 2[S]1 RFC 2178,1997
42.Charles Perkings,Pravin Bhagwatl High dynamic destination2 sequenced distance2vector routing(DSDV) for mobile computer[C]1 ACM SIGCOMM'94,London,U K,1994
43.T W Chen,M Gerlal Global state routing:A new routing scheme for ad hoc wireless networks[C]1 The IEEE Int'l Conf on Communications(ICC),Atlanta,Georgia,USA,1998
44.David B Johnson,David A Maltz,et all The dynamic source routing protocol for mobile ad hoc networks[S]1 Draff2ietf2 manet2dsr2051txt12,2001
45.Charles E Perkins,Elizabeth M Royer,et all Ad hoe on2 demand distance vector(AODV)routing[S]1 RFC 3561,2003
46.David B Johnson,David A Maltz,Yih2Chun Hul The dynamic source routing protocol for mobile ad hoc networks(DSR),Draft2ietf2manet2dsr210[S]1 IETF MANET Working Group INTERNET2DRAFT,2004
47.Stephen Mueller,Rose P Tsang,Dipak Ghosall Multi2path routing in mobile ad hoc networks:Issues and Challenges[C]1 Confon MASCOTS,Orlando,Florida,USA,2003
48.M Marina,S Das1 Performance of route caching strategies in dynamic source routing[C]1Int'l Workshop on Wireless Networks and Mobile Computing(WNMC'01),Phoenix,Arizona,USA,2001
49.Y Hu,D Johnsonl Caching strategies in on2demand routing protocols for wireless ad hoc networks[C]1 ACM MOBICOM' 00,Boston,Massachusetts,USA,2000
50.(张禄林,李承恕1 MANET路由选择协议的比较分析研究[J]1电子学报,2000,28(11):88-92)
51.Wen Yingyou,Zhao Jianli,Zhao Linliang,et all A study of the relationship between performance of topology2based MANET routing protocol and network coverage density [J]1 Journal of Computer Research and Development,2005,42(4):684-689(in Chinese)
52.Phillips P,Grother P,Micheals R,et al FRVT 2002:Evaluation Report[OL]2003.http://www.frvt.org/FRVT2002/documents.html.
53.WU Chenyu,Liu Ce,Shum Heung-Yueng,et al.Automatic eyeglasses removal from face images[J]IEEE Trans on Pattern Analysis and Machine Intelligence 2004 26(30):322-336
54.JIANG X,Binkert M,Achemann B,et al Towards detection of glasses in facial images[A]International Conference on Pattern Recognition[C].Los A lamitos,CA IEEE Computer Soc,1998,1071-1073
55.WU H,Yoshikaw a g,Shioyama T,et al Glasses frame detection with 3d hough transform [A]international conference on pattern recognition[C]Los Alamitos CA:IEEE Computer Soc 2002 346-349
56.Saito Y,Kenmochi Y,Kotani K,Estimation of eyeglasses facial images using principle component analysis[A]International Conference on Image Proeessing[C]Piscataway NJ IEEE 1999 4 197-201
57.Su Guangda,Zhang Guiping,Ding Rong,et al MMP-PCA face recognition method[J]Electronics Letters,2002,38(5):1654-1666
58.Jian Yang,David Zhang,Jing Yu Yang;Constructing PCA Baseline Algorithms to Reevaluate ICA-Based Face-Recognition Performance IEEE Trans on Systems,Man,and Cybernetics-Part B:Cybernetics,vol 37 No 4.August 2007
59.Keun-Chang Kwak,Witold Pedrycz;Face Recognition Using an Enhanced Independent Component Analysis Approach IEEE Trans on Neural Networks vol.18,No.2,March 2007.
60.S.Bannour and R.M.Azimi-Sadjadi,"Principal component extractionusing reeursive least squares learning," IEEE Trans.Neural Netw.,vol.6,no.2,pp.457-469,Mar.1995
61.丁佩律等.基于独立分量分析的人脸自动识别方法研究成果.红外与毫米波学报,20-5,361-364,2001
2.苗长云 有限用户多信道共用系统理论分析及应用研究博士学位论文2005
3.MIAO Changyun Principle of Line Configuration and Monte-Carlo Simulation for Shared Multi-Channel System Transactions of Tianjin University Vol.11 No.3 Jun.2005pp162-166
4.D.Shmoys,"Approximation algorithms for facility location problems," in Proc.APPROX,Sep.2000.v,pp.27-32.
5.Kuehn and M.J.Hamburger,"A heuristic program for locating warehouses," Manage.Sci.,pp.9:643-666,1963.
6.S.Arora,P.Raghavan,and S.Rao,"Approximation schemes for euclidean k-medians and related problems," in Proc.ACM Syrup.Theory Comput.,1998,pp.106-113.
7.J.Li,C.Blake,D.De Couto,H.Imm,and L.Morris,"Capacity of ad hoc wireless networks," in Proc.Int.Conf.Mobile Comput.Netw.,2001.
8.P.Hsiao,A.Hwang,H.Kung,and D.Vlah,"Load balancing routing for wireless access networks," in Proc.IEEE INFOCOM,1999.
9.J.Wong,R.Jafari,and M.potkonjak,"Gateway placement for latency and energy efficient data aggregation," in Proc.IEEE Int.Conf.Local Comput.Netw.,2004,pp.490-497.
10.R.Chandra,L.Qiu,K.Jain,and M.Mahdian,"Optimizing the placement of integration points in multi-hop wireless networks," in Proc.IEEE ICNP,2004.
11.Antis,R.Prakash,T.Vuong,and D.Huynh,"Max-min d-elusterformation in wireless ad hoc networks," in Proc.IEEE INFOCOM,2000,pp.32-41.
12.Girolami M.Self-organising Neural Networks:Independent Component Analysis and Blind Source Separation[M]London:Springer Verlag 1999
13.Haykin S.Unsupervised Adaptive Filtering,Vol Ⅰ:Blind Source Separation[M].New York:Wiley,2000.
14.Hyvarinen A,Karhunen J,Oja E.Independent Component Analysis[M].New York:Wiley,2001.
15.Tong L,Liu RW,Soon VC,et al.Indeterminacy and Identifiability of Blind Identification[J].IEEE Trans on Circuits and Systems 1991,38(5):499-509
16.Comon P.Independent Component Analysis,a New Concept[J].Signal Processing,1994,36(3):2872314.
17.张洪渊,贾鹏,史习智.确定盲分离中未知信号源个数的奇异值分解法[J].上海交通大学学报,2001,35(8):1155-1158.
18.姚志湘等 针对FastICA计算终点判断的算法改进 计算机工程与应用2006.26 46-49
19.J utten C,Herault J1 Independent component analysis versus principal component analysis [A]I In:Processing of European Signal Processing Conference,Grenoble,France,1988643-646
20.Comon P1 Independent component analysis,a new concept[J]Signal Processing,1994,36(3):287-314
21.张洪渊.信号源盲分离的理论与实验研究[D].上海:上海交通大学,2000,12:87-103.
22.J V Stone.Blind source separation using temporal predictability[J].Neural Computation,2001,13(7):1559-1574.
23.J.Weinmiller,H.Woesner and A.Wolisz,"Analysis and Improving the IEEE 802.11-MAC protocol for wireless LANs",MAS-COTS'96,San Jose,USA 1996,12(4):200-205
24.随机过程及应用 电子科技大学应用数学学院 陈良均等 高等教育出版社2003pp145-151
25.Ad Hoc移动无线网络 国防工业出版社王金龙等2003
26.下一代无线因特网技术:无线mesh网络人民邮电出版社方旭明等2006
27.IEEE Computer Society.802.11:Wireless LAN Medium Access Control(MAC) and Physical Layer(PHY) Specifications.June 1997
28.J.H.Chert and Y.D.Chen,"AMNP:Ad Hoc Multichannel Negotiation Protocol for Multihop Mobile Wireless Networks," IEEE International Conference on Communication (ICC),pp.3607-3612,Jun.2004.
29.S.L.Wu,C.Y.Lin,Y.C.Tseng,and J.P.Sheu,"A New Multi-Channel MAC Protocol with On-Demand Channel Assignment for Multi-Hop Mobile Ad Hoc Networks," International Symposium on Parallel Architectures,Algorithms and Networks(I-SPAN),December 2000.
30.W.C.Hung,K.Law,and A.Leon-Garcia,"A Dynamic Multi-Channel MAC for Ad Hoc LAN," 21st Biennial Symposium on Communications,Apr.2002.
31.N.Jain,S.R.Das,and A.Nasipuri,"A multichannd CSMA MAC protocol with receiver-based channel selection for multihop wireless networks," Computer Communications and Networks,pp.15-17,Oct.2001.
32.C.Y.Chang,H.C.Sun,and C.C.Hsieh,"MCDA:an efficient multichannel MAC protocol for 802.11 wireless LAN with directional antenna",19th International Conference on Advanced Information Networking and Applications(AINA),pp.64-67,Mar.2005.
33.H.Koubaa,"Fairness-Enhanced Multiple Control Channels MAC for Ad Hoe Networks,"IEEE 61st Vehicular Technology Conference(VTC),pp.1504-1508,Jun 2005.
34.Y.Yorozu,M.Hirano,K.Oka,and Y.Tagawa,"Electron spectroscopy studies on magneto-optical media and plastic substrate interfaces(Translation Journals style)," IEEE Transl.J.Magn.Jpn.,vol.2,
35.J.Chen,S.T.Sheu,and C.A.Yang,"A new multi-channel access protocol for IEEE 802.11ad hoc wireless LANs," Personal,Indoor and Mobile Radio Communications,IEEE,pp.7-10,Sept.2003.
36.Nakjung Choi,Yongho Seok and Yanghee Cho,"Multi-Channel MAC protocol for Mobile Ad hoc Networks",IEEE,pp.1379-1382,2003
37.Draft Supplement to STANDARD FOR Telecommunications and Information Exchange Between Systems-LAN/MAN Speci_c Requirements-Part 11:Wireless Medium Access Control(MAC) and Physical Layer(PHY) Speci_cations:Medium Access Control(MAC)Enhancements for Quality of Service(QoS).IEEE Std 802.11e/D3.0,May 2002
38.S Corson,J Macker1 Mobile ad hoe networking(MANET):Routing protocol performance issues and evaluation considerations[S]1 RFC2501,1999
39.Joseph P Macker,M Scott Corsonl Mobile ad hoe networking and the IETF[J]1 ACM SIGMOBIL E Mobile Computing and Communications Review,2002,6(2):1-2
40.G Maldinl RIP Version 2[S]1 RFC 2453,1998
41.J Moy1 OSPF Version 2[S]1 RFC 2178,1997
42.Charles Perkings,Pravin Bhagwatl High dynamic destination2 sequenced distance2vector routing(DSDV) for mobile computer[C]1 ACM SIGCOMM'94,London,U K,1994
43.T W Chen,M Gerlal Global state routing:A new routing scheme for ad hoc wireless networks[C]1 The IEEE Int'l Conf on Communications(ICC),Atlanta,Georgia,USA,1998
44.David B Johnson,David A Maltz,et all The dynamic source routing protocol for mobile ad hoc networks[S]1 Draff2ietf2 manet2dsr2051txt12,2001
45.Charles E Perkins,Elizabeth M Royer,et all Ad hoe on2 demand distance vector(AODV)routing[S]1 RFC 3561,2003
46.David B Johnson,David A Maltz,Yih2Chun Hul The dynamic source routing protocol for mobile ad hoc networks(DSR),Draft2ietf2manet2dsr210[S]1 IETF MANET Working Group INTERNET2DRAFT,2004
47.Stephen Mueller,Rose P Tsang,Dipak Ghosall Multi2path routing in mobile ad hoc networks:Issues and Challenges[C]1 Confon MASCOTS,Orlando,Florida,USA,2003
48.M Marina,S Das1 Performance of route caching strategies in dynamic source routing[C]1Int'l Workshop on Wireless Networks and Mobile Computing(WNMC'01),Phoenix,Arizona,USA,2001
49.Y Hu,D Johnsonl Caching strategies in on2demand routing protocols for wireless ad hoc networks[C]1 ACM MOBICOM' 00,Boston,Massachusetts,USA,2000
50.(张禄林,李承恕1 MANET路由选择协议的比较分析研究[J]1电子学报,2000,28(11):88-92)
51.Wen Yingyou,Zhao Jianli,Zhao Linliang,et all A study of the relationship between performance of topology2based MANET routing protocol and network coverage density [J]1 Journal of Computer Research and Development,2005,42(4):684-689(in Chinese)
52.Phillips P,Grother P,Micheals R,et al FRVT 2002:Evaluation Report[OL]2003.http://www.frvt.org/FRVT2002/documents.html.
53.WU Chenyu,Liu Ce,Shum Heung-Yueng,et al.Automatic eyeglasses removal from face images[J]IEEE Trans on Pattern Analysis and Machine Intelligence 2004 26(30):322-336
54.JIANG X,Binkert M,Achemann B,et al Towards detection of glasses in facial images[A]International Conference on Pattern Recognition[C].Los A lamitos,CA IEEE Computer Soc,1998,1071-1073
55.WU H,Yoshikaw a g,Shioyama T,et al Glasses frame detection with 3d hough transform [A]international conference on pattern recognition[C]Los Alamitos CA:IEEE Computer Soc 2002 346-349
56.Saito Y,Kenmochi Y,Kotani K,Estimation of eyeglasses facial images using principle component analysis[A]International Conference on Image Proeessing[C]Piscataway NJ IEEE 1999 4 197-201
57.Su Guangda,Zhang Guiping,Ding Rong,et al MMP-PCA face recognition method[J]Electronics Letters,2002,38(5):1654-1666
58.Jian Yang,David Zhang,Jing Yu Yang;Constructing PCA Baseline Algorithms to Reevaluate ICA-Based Face-Recognition Performance IEEE Trans on Systems,Man,and Cybernetics-Part B:Cybernetics,vol 37 No 4.August 2007
59.Keun-Chang Kwak,Witold Pedrycz;Face Recognition Using an Enhanced Independent Component Analysis Approach IEEE Trans on Neural Networks vol.18,No.2,March 2007.
60.S.Bannour and R.M.Azimi-Sadjadi,"Principal component extractionusing reeursive least squares learning," IEEE Trans.Neural Netw.,vol.6,no.2,pp.457-469,Mar.1995
61.丁佩律等.基于独立分量分析的人脸自动识别方法研究成果.红外与毫米波学报,20-5,361-364,2001