iosr-JECE   National Conference on Wireless Communication, Microelectronics and Emerging Technologies (NC-WiCOMET2013)

Abstract: The main objective of this paper is to detect changes in the optical images of the same area acquired over different times based on Block Matching and Fuzzy Clustering algorithm. The proposed Fuzzy k means clustering is combined with block matching, is less time consuming and do not need any priori knowledge of distribution of changed and unchanged pixel . Inorder to reduce the iteration steps and computation time fuzzy clustering is performed prior to Block Matching. Noises caused by imaging effects or camera jitter can be reduced, and change detection [1] based on Block Matching and Fuzzy k means clustering algorithm becomes feasible. The change detection results obtained by Block Matching and Fuzzy k means clustering algorithm exhibits enhanced tolerance to noises and illumination changes.

Keywords: Block matching ,Change detection ,Clustering ,Fuzzy k means clustering.

[1]. Maoguo Gong, Member, IEEE, Zhiqiang Zhou, and Jingjing Ma,"Change Detection in Synthetic Aperture Radar Images based on
Image Fusion and Fuzzy Clustering" ,Ieee Transactions On Image Processing, Vol. 21, No. 4, April 2012.
[2]. Aroh Barjatya,"Block Matching Algorithms For Motion Estimation",Student Member, IEEE, DIP 6620 Spring 2004 Final Project Paper.
[3]. Susmita Ghosh, Niladri Shekhar Mishra, Ashish Ghosh, "Unsupervised Change Detection of Remotely Sensed Images using Fuzzy
Clustering ",2009 Seventh International Conference on Advances in Pattern Recognition.
[4]. Chih-Tang Chang1, Jim Z. C. Lai2 And Mu-Der Jeng1,"A Fuzzy K-means Clustering Algorithm Using Cluster Center Displacement" , Journal Of Information Science And Engineering 27, 995-1009, (2011).
[5]. R. J. Radke, S. Andra, O. Al-Kofahi, and B. Roysam, "Image change detection algorithms: A systematic survey," IEEE Trans. Image
Process., vol. 14, no. 3, pp. 294–307, Mar. 2005.
[6]. L. Bruzzone and D. F. Prieto, "An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images," IEEE Trans. Image Process., vol. 11, no. 4, pp. 452–466, Apr. 2002.
[7] M. Bosc, F. Heitz, J. P. Armspach, I. Namer, D. Gounot, and L. Rumbach,"Automatic change detection in multimodal serial MRI:
Application to multiple sclerosis lesion evolution," Neuroimage, vol. 20, no. 2, pp. 643–656, Oct. 2003.
[8] D. Rey, G. Subsol, H. Delingette, and N. Ayache, "Automatic detection and segmentation of evolving processes in 3-D medical images: Application to multiple sclerosis," Med. Image Anal., vol. 6, no. 2, pp.163–179, Jun. 2002.
[9] D. M. Tsai and S. C. Lai, "Independent component analysis-based background subtraction for indoor surveillance," IEEE Trans. Image Process., vol. 18, no. 1, pp. 158–167, Jan. 2009.
[10] S. S. Ho and H. Wechsler, "A martingale framework for detecting changes in data streams by testing exchangeability," IEEE
Trans.Pattern Anal. Mach. Intell., vol. 32, no. 12, pp. 2113–2127, Dec.2010.

Abstract: Technological developments in the medical industry have contributed to significant improvements in patient care. Non-aggressive monitoring of critical biological functions is an important need to provide appropriate care to patients and leads to their improved health. Supervision and analysis of ECG has long been used in clinical practice. The technological developments of ECG monitoring have made it more mobile and convenient, but this has resulted in decreased signal quality. In this paper, PCA is used along with an optimal filter developed using Bayesian framework to enhance the signal quality of ECG signal. This filter has the form of a Kalman Filter. Also, the method of PCA allows efficient estimation of QRS complexes from the noisy ECG data. The adaptive estimation of the process noise covariance is performed based on earlier parameter estimates and on newly arriving data. The measurement noise covariance is obtained by the spatial correlation between several simultaneously recorded ECG signals. The filter has been evaluated on TWA signals and Fetal ECG signals.

Keywords - Electrocardiogram, PCA, Kalman Filter, Noise Estimation.

Books:
[1] Rangaraj .M. Rangayyan,Biomedical Signal Analysis: A Case Study Approach(Wiley IEEE Press, December 2001)
Journal Papers:
[2] W. Chen, C. Sonntag, F. Boesten, S.BambangOetomo, and L. Feijs, A design of power supply for neonatal monitoring with wearable
sensors, Journal of Ambient Intelligence and Smart Environments,1(2), 2009,185–196.
[3] A. Gruetzmann, S. Hansen, and J. M¨uller, Novel dry electrodes for ECG monitoring, Physiol. Meas., 28(11),2007, 1375–1390.
[4] An Adaptive Kalman Filter for ECG Signal Enhancement RikVullings, Bert de Vries, and Jan W. M. Bergmans, IEEE Transactions On Biomedical Engineering, 58(4), 2011, 1094-1103.

Abstract: Biometrics refers to statistically analyzing biological characteristics of a person for authentication as well as identification and is of prime importance because of the eminent role security plays in different areas in day to day life. Application of such system includes terrorist determination, passport control, banking etc. All in all, biometrics is not a secure approach unless; suitable countermeasures are employed to make the enrolled data inaccessible to intruder. This work introduces a technique for providing biometric face data secure by using Grey level Extended Visual Cryptography (GEVCS), Principal Component Analysis (PCA) and Euclidian distance approach. The performance is analyzed using Peak Signal to Noise Ratio (PSNR). The results show that the reconstructed image as well as the share images is similar in appearance to the original target image and the host images respectively.

Key-Words: - Biometric database, Euclidian distance, GEVCS, PCA, PSNR

[1] G. I. Davida, Y. Frankel, and B. J. Matt, "On enabling secure applications through off-line biometric identification," in Proc.
IEEE Symp. Security and Privacy, 1998, pp. 148–157.
[2] N. Ratha, J. Connell, and R. Bolle, "Enhancing security and privacy in biometrics-based authentication systems," IBM Syst. J.,
vol. 40, no. 3, pp. 614–634, 2001.
[3] Y. Feng, P. Yuen, and A. Jain, "A hybrid approach for face template protection," in Proc. SPIE Conf. Biometric Technology for
Human Identification, Orlando, FL, 2008, vol. 6944.
[4] A. Jain and U. Uludag, "Hiding biometric data," IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 11, pp. 1494–1498, Nov.
2003.
[5] J. Dong and T. Tan, "Effects of watermarking on iris recognition performance," in Proc. 10th Int. Conf. Control, Automation,
Robotics and Vision,2008 (ICARCV 2008), 2008, pp. 1156-1161.
[6] N. Agrawal and M. Savvides, "Biometric data hiding: A 3 factor authentication approach to verify identity with a single image
using steganography, encryption and matching," in Proc. Computer Vision and Pattern Recognition Workshop, 2009, vol. 0, pp. 85–92.
[7] D. Bitouk, N. Kumar, S. Dhillon, P. Belhumeur, and S. K. Nayar, "Face swapping: Automatically replacing faces in
photographs," ACMTrans. Graph., vol. 27, no. 3, pp. 1–8, 2008.
[8] M. Naor and A. Shamir, "Visual cryptography," in Proc. EUROCRYPT, 1994, pp. 1–12.
[9] M. Nakajima and Y. Yamaguchi, "Extended visual cryptography for natural images," J. WSCG, vol. 10, no. 2, pp. 303–310,
2002.
[10] Arun Ross and Asem Othman, "Visual Cryptography For Biometric Privacy," in IEEE Transactions On Information Forensics
And Security, Vol. 6, No. 1, March 2011
[11] T. Cootes et al., "Active appearance models," IEEE Trans. PatternAnal. Mach. Intell., vol. 23, no. 6, pp. 681–685, Jun. 2001.
[12] G. Ateniese, C. Blundo, A. Santis, and D. Stinson, "Extended capabilities for visual cryptography," Theor. Comput. Sci., vol.
250, no. 1–2, pp. 143–161, 2001.
[13] Mamta Dhanda, "Face recognition using eigenvectors from Principal component analysis" in International Journal of Advanced
Engineering Research and Studies/ Vol. I/ Issue II/January-March, 2012/37-39
[14] Marijeta Slavković, Dubravka Jevtić, "Face Recognition Using Eigenface Approach", Serbian Journal Of Electrical
Engineering, Vol. 9, No. 1, February 2012, 121-130

Abstract: Personal Health Record Management system is a patient centric model which utilizes the myriad applications of cloud computing .It utilizes the RSA algorithm to encrypt the Health records and is stored in the cloud server. Here the health data of a patient is maintained by himself. These health records are very much different from the ordinary electronic medical records maintained by hospitals. During the last few years, there has been an increased number of applications that have "migrated to the cloud",and new cloud-based applications have become popular.

Keywords - PHRMS, PHR,cloud computing,RSA encryption,SAAS,HAAS,PAAS

1. Scalable and Secure Sharing of Personal Health Records in Cloud by Ming Li Member, IEEE, Shucheng Yu, Member, IEEE, Yao Zheng, Student Member, IEEE, Kui Ren, SeniorMember, IEEE, and Wenjing Lou, Senior Member, IEEE
2. M. Li, S. Yu, K. Ren, and W. Lou, "Securing personal health records in cloud computing: Patient-centric and fine-grained dataaccess control in multi-owner settings," in SecureComm'10, Sept.2010, pp. 89–106.
3. H. L¨ohr, A.-R. Sadeghi, and M. Winandy, "Securing the e-healthcloud," in Proceedings of the 1st ACM International Health InformaticsSymposium, ser. IHI '10, 2010, pp. 220–229.
4. M. Li, S. Yu, N. Cao, and W. Lou, "Authorized private keyword search over encrypted personal health records in cloud computing," in ICDCS '11, Jun. 2011.
5. "The health insurance portability andaccountability act." [Online]. Available:http://www.cms.hhs.gov/HIPAAGenInfo/01 Overview.asp
6. www.lifesensor.com
7. www.healthvault.com

Abstract: This paper aims at providing a brief overview of speaker verification system. Our aim is to implement text dependent speaker verification system that is insensitive to noise. In this paper, a novel family of windowing technique is used to compute Mel Frequency Cepstral Coefficient (MFCC) for automatic speaker recognition from speech. This method is based on fundamental property of discrete time Fourier transform (DTFT) related to differentiation in frequency domain. Classical windowing scheme such as hamming window is modified to obtain derivatives of discrete time Fourier transform coefficients. This paper, presents an effective approach to improve the accuracy of speaker recognition by combining the modified MFCC and spectral information (discrete wavelet coefficients).

Keywords:Differentiation in frequency, DWT, Mel frequency cepstral coefficients (MFCC), feature extraction, speaker verification

[1] Tomi Kinnunen, Haizhou Li, An Overview of Text-Independent Speaker Recognition: from Features to Supervectors, Speech
Communication ,52(1) ,2009

[2] Amin Fazel and Shantanu Chakrabartty,An Overview of Statistical Pattern Recognition Techniques for Speaker Verification - IEEE
Circuits and Systems Magazine , 11( 2), 2011,pp. 62-81.
[3]Atal, B., Effectiveness of Linear Prediction Characteristics of the Speech Wave for Automatic Speaker Identification and Verification,
Journal of Acoustical Society America, Vol. 55,1974, pp. 1304-1312.
[4] White, G. M. and Neely, R. B., peech Recognition Experiments with Linear Prediction, Bandpass Filtering, and Dynamic Programming, IEEE Trans. On Acoustics, Speech, Signal Processing, Vol. 24, 1976, pp. 183_188.
[5] Vergin, R., O'Shaughnessy, D. and Farhat, A.,Generalized Mel Frequency Cepstral Coefficients for Large-Vocabulary Speaker-
Independent Continuous-Speech Recognition,IEEE Trans. on Speech and Audio Processing, Vol. 7,1999, pp. 525_532 .
[6] B. C. Jong, wavelet Transform Approach For Adaptive Filtering With Application To Fuzzy Neural Network Based Speech Recognition, PhD Dissertation,Wayne State University, 2001.
[7] Z. Tufekci, Local Feature Extraction For Robust Speech Recognition in The Presence of Noise, PhD Dissertation, Clemson University, 2001.
[8]R. Sarikaya, Robust And Efficient Techniques For Speech Recognition in Noise, PhD Dissertation, Duke University, 2001.
[9]A. Oppenheim, S. Willsky, and S. Nawab, Signals And Systems(second edition ed. PHI Learning, 2009).
[10] Md Sahidullah,Goutam Saha, A Novel Windowing Technique for Efficient Computation of MFCC for Speaker Recognition Signal
Processing Letters, IEEE ,20(2),Feb 2013

Abstract: Wireless Mesh Network (WMN) is a communications network, which is of radio nodes organized in a mesh topology. Wireless mesh networks often consists of mesh clients, mesh routers and gateways. The range of router is greater than that of the client in the WMN and may cause link asymmetry, leading to degradation in network performances. Link asymmetry in WMN causes unidirectional Link problem, Heterogeneous Hidden Terminal problem and Heterogeneous Exposed Terminal Problem. Cross-layer design is the promising method to improve the efficiency of the network performance, which uses the multihop path to establish a reverse path between the client and the router. Different topology may be tested to check the effectiveness of cross-layer approach for improving the network performance

Keywords - Cross-layer design, WMN

[1] A Cross-Layer Approach Handling Link Asymmetry for Wireless Mesh Access Networks Yuefeng Huang, Xinyu Yang, Shuseng Yang, Wei Yu, and Xinwen Fu, Member, IEEE, IEEE Transactions on vehicular technology, vol. 60,no.3, march 2011
[2] I. F. Akyildiz and X. Wang, "A survey on wireless mesh networks," IEEE Commun. Mag., vol. 43, no. 9, pp. S23–S30, Sep. 2005.
[3] Viral. V. Kapadia, Sudarshan. N. Patel and Rutvij H. Jhaveri, "Comparative study of hidden node problem and solution using different techniques and protocols" , Journal of computing, volume 2, issue 3, march 2010, issn 2151-961765, https://sites.google.com/site/journalofcomputing/
[4] Y. Y. Su, S. F. Hwang, and C. R. Dow, "An efficient cluster-based routing algorithm in ad hoc networks with unidirectional links," J. Inf. Sci. Eng., vol. 24, no. 5, pp. 1409–1428, 2008.
[5] N. Poojary, S. V. Krishnamurthy, and S. Dao, "Medium access control in a network of ad hoc mobile nodes with heterogeneous power capabilities," in Proc. IEEE ICC, Helsinki, Finland, Jun. 2001, pp. 872–877.
[6] M. T. Thai, R. Tiwari, and D. Z. Du, "On construction of virtual backbone in wireless ad hoc networks with unidirectional links," IEEE Trans. Mobile Comput., vol. 7, no. 9, pp. 1098–1109, Sep. 2008.
[7] K. M. Mahesh and R. D. Samir, "Routing performance in the presence of unidirectional links in multihop wireless networks," in Proc. 3rd ACM Int. Symp. Mobile Ad Hoc Netw. Comput., Lausanne, Switzerland, Jun. 2002,pp. 12–23.
[8] Kyle Jamieson, Bret Hull, Allen Miu, Hari Balakrishnan, "Understanding the Real-World Performance of Carrier Sense", MIT Computer Science and Artificial Intelligence Laboratory, The Stata Center, 32 Vassar St., Cambridge, MA 02139,{jamieson, bwhull, aklmiu, hari}@csail.mit.edu
[9] Anucha U. Sylvester, Asagba O. Prince, Ogheneovo E. Edward," Carrier sensing mechanisms: the impact on throughput performance of IEEE 802.11 WLANs" Scholars March – 2012, Volume – 1, Issue – 1,Article #01,www.setscholars.org, Knowledge is Power,IJAR-CSIT, Research Paper,ISSN: 1839-8480, Corresponding author's e-mail: udlondy@yahoo.com
[10] An Chan and Soung Chang Liew, " Merit of PHY-MAC Cross-Layer Carrier Sensing: A MAC-Address-based Physical Carrier Sensing Scheme for Solving Hidden-Node and Exposed-Node Problems in Large-Scale Wi-Fi Networks", Department of Information Engineering, The Chinese University of Hong Kong, {achan5, soung}@ie.cuhk.edu.

Abstract:Traffic analysis using Discrete Wavelet Transform and Bayesian Regression is used to estimating the size of inhomogeneous traffic, composed of vehicles that travel in different directions without using explicit object segmentation or tracking is proposed .Using the dynamic texture motion model, here the traffic is segmented into components of homogeneous motion. From each segmented region, a set of holistic low-level features are extracted using 4-level discrete wavelet transform. Using the 4 level discrete wavelet transform, I calculate the energy of wavelet coefficients and a function that map features into estimates of the number of vehicle per segment is learned with Bayesian regression. Here two Bayesian regression models are examined. The first is a Gaussian Process Regression with a compound kernel, which accounts for both the global and local trends of the count mapping but is limited by the real-valued outputs that do not match the discrete counts. I addressed this limitation with a second model which is based on a Bayesian treatment of poisson regression that introduces a prior distribution on the linear weights of the model. Experimental results show that regression-based counts are accurate regardless of the traffic size. Velocity of each car can be calculated.

Keywords -Bayesian regression, Discrete Wavelet Transform, Gaussian processes, Poisson regression, Traffic analysis.