iosr-JEEE   International Conference on Advances in Engineering & Technology – 2014 (ICAET-2014)

Abstract: we propose in this paper a technology that can perform remote control and monitoring of electrical appliances on the Internet. To do this, an intelligent power socket (IPS) module that is able to control and monitoring the power of electricity is realized in this research. The IPS modules are placed in conjunction with the electrical appliances that are to be controlled from a far-end place . In addition, an embedded system based home gateway that can be connected with the Internet is set up in which the electrical appliances are located. Moreover, the acquired power consumption information or the status of the appliances is stored in a database server in the Cloud. With the proposed structure, authorized users or system managers can log into the web server which is connected with the database, monitoring the power status and take actions on the appliances remotely. The control command from the far-end place, i.e., from the web server on the Internet, is first sent to the home gateway and then transmitted to the IPS modules through the Zigbee wireless communication protocol so that the remote control of appliances can be achieved. The proposed architecture has been shown to be very convenient and useful for remote control and monitoring of electrical appliances, and hence can facilitate the life of human beings Keywords: Cloud Computing, Power management, Embedded systems.

[1] Jinsoo Han, Haeryong Lee, and Kwang-Roh Park, "Remote-Controllable and Energy-Saving Room Architecture Based on ZigBee
Communication," IEEE Trans on Consumer Electronics, vol.55, no.1, pp.264-268, Feb 2009.
[2] Ki Chool Yang and Sun Young Kim, "Automatically standby power cutoff plug socket," U.S. patent, no.US20080231121A1, Sep. 2008
[3] Sungjin Park, Eun Ju Lee, Jae Hong Ryu, Seong-Soon Joo, and Hyung Seok Kim, "Distributed Borrowing Addressing Scheme
for ZigBee/IEEE 802.15.4 Wireless Sensor Networks," ETRI Journal, vol.31, no.5, pp525-533, Oct. 2009.
[4] Masahiro Inoue, Toshiyasu Higuma, Yoshiaki Ito, Noriyuki Kushiro, and Hitoshi Kubota, "Network Architecture for Home Energy
Management System," IEEE Trans on Consumer Electronics, Vol. 49, No. 3, pp. 606-613, Aug. 2003.
[5] Eric Williams, Scott Matthews, Michael Breton, and Todd Brady, "Use of a Computer-Based System to Measure and Manage Energy
Consumption in the Home," Proceedings of the 2006 IEEE International Symposium on Electronics and the Environment, pp.167-172,
2006.

Abstract: Public Transport Corporations in any country rely on reliable and accurate broadcast information to transit users to achieve better service quality. Forecasting of vehicle travel and arrival time prediction has become one of the many challenging tasks due to the fact that vehicle operation variables and parameters are highly conjectural. This paper provides a case study on forecasting of travel time prediction for Jaipur-Delhi route, RSRTC India which gives results very rich non-linear dynamics using a focused time lagged recurrent (FTLR) neural network (NN).This is an optimal NN model and a highly non-linear complex dynamical system for the travel time prediction which is not currently available. This paper compares the performance of MLP NN and the proposed FTLRNN models and a standard static back propagation algorithm with momentum term has been applied for both the NN configurations. It is investigated that the estimated dynamic NN model comprising of a gamma memory (GM) filter followed by a MLP NN clearly outperforms the static MLP NN in correlation coefficients, NMSE and regression characteristics on the cross-validation (CV) as well as testing datasets. In addition, the outputs of the proposed FTLRNN model reasonably follow the desired outputs of the forecasting of travel time prediction for the testing and CV exemplars. This also means that most of the information about the rich non-linear dynamics of the system has been extracted satisfactorily from the training dataset and that the proposed model approximates the given system with realistic accuracy. In the result, it shows that the proposed FTLRNN model has a remarkable system prediction capability.

Keywords: Focused time lagged recurrent NN, Gamma memory, Non-linear system, Multi-layer perceptron NN, Back propagation algorithm, Rajasthan State Road Transport Corporation(RSRTC) and Intelligent Public Transport System (IPTS).

[1] H¨useyinAkcan, VassilKriakovHerv´eBr¨onnimann and Alex Delis, "GPSFree Node Localization in Mobile Wireless Sensor Networks" MobiDE‟06, June, USA.

[2] Jamal N. Al-Karaki and Ahmed E. Kamal, "Routing Techniques in Wireless Sensor Networks: A Survey" Iowa State University, Ames.

[3] Mehdi Vojdani and Mehdi Dehghan, "Localization in Anchor less Wireless sensor Network", IPCSIT vol.2 (2011).

[4] Clark Kerr Campus, "Conference on Transportation in Developing Countries" April 1998, Uni. Of California, Berkeley

Abstract: As per the development of electronic world it is quite impossible to secure the personal information. Considering the shortcoming of the unimodal biometrics authentication the proper selection of modality plays important role for authentication. Hence it is essential to develop safe and authentic recognition system to protect the privacy about the person. This paper proposes a recent authentication system using finger vein. The vein pattern present beneath the skin of finger is distinctive and stable. It can be used for personal authentication that provides high security and reliability because of its positive characteristics over the others biometrics modalities. This paper explores the IR based finger vein capturing device and different algorithm for feature extraction of finger vein used for authentication. The paper highlighted the finger-vein framework, its recognition performance parameter i.e. false acceptance rate (FAR) and false rejection rate (FRR). The characteristics of finger vein authentication shows that it is more secure than the other correlated modalities.

Keywords -Biometrics modality, finger vein, authentication, FAR, FRR

[1] L. Hong, Y. Wan, A. Jain, Fingerprint image enhancement: algorithm and performance evaluation, IEEE Transactions on Pattern Analysis and Machine Intelligence 20 (8) (1998) 777–789. [2]L. Hong and A. K. Jain,Integrating Faces and Fingerprints for Personal Identification, IEEE Trans. on Pattern Analysis and Machine Intel, vol. 20, no. 12, pp. 1295-1307, Dec 1998. [3] Naoto Miura, Akio Nagasaka, Takafumi Miyatake, Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification, Machine Vision and Applications 2004. [4]Bhupinder Singh, Neha Kapur, Puneet Kaur, Speech Recognition with Hidden Markov Model: A Review, International Journal of Advanced Research in Computer Science and Software Engineering Volume 2, Issue 3, March 2012. [5] Shang-Hung Lin, An Introduction to face recognition Technology, Informing science special issue on multimedia informingTechnologies-part2, vol.3 no.1 2000. [6]Duque Vehils, Jose Miguel, Final Thesis Design and Implementation of a Finger Vein Identification System, Institute of Technology,Cambridge, MA, 1978.2011.

Abstract: A new classification algorithm is proposed for soya bean crop diseases detection. In order to develop an algorithm, 10 different diseases have been considered for which, Trinocular Axio Lab microscope of 100X magnification range with Digital Camera is used. With a view to extract features from diseased and normal images, after image processing and localization of region-of interest, an algorithm is developed which proposes two-dimensional discrete Walsh- Hadamard Transform domain coefficients in addition to Average, Standard Deviation, Entropy, Contrast, Correlation, Energy, Homogeneity and shape descriptor. The suitability of classifiers based on Multilayer Perceptron (MLP) Neural Network and Modular Neural Network (MNN) is explored with the optimization of their respective parameters in view of reduction in time as well as space complexity. A separate Cross-Validation dataset is used for proper evaluation of proposed classification algorithm with respect to important performance measures, such as MSE and classification accuracy. The Average Classification Accuracy of Modular Neural Network comprising of two hidden layers and four parallel MLP neural networks organized in a typical topology is found to be superior (98%) amongst all classifier. Finally, optimal algorithm has been developed on the basis of the best classification performance. The algorithm suggested could be easily modified to classify more than 10 diseases. The algorithm will provide an effective alternative to traditional method of soya crop diseases accurate detection for E-Agriculture.

Keywords-Algorithm, Classification, Neural Network, Soya bean diseases, Walsh-Hadamard Transform

[1] R.M.Haralick, K. Shanmugam, J.Din "Texture features for image classification ", IEEE Trans. Syst. Man Cybern. Vol. SMC-3, pp.610-621, 1973.

[2] Duda, R. O., and Hart, P. E., (1973). "Pattern Classification and Scene Analysis," New York: John Wiley Nilsson, N. J., (1965).

Abstract: A wireless bio-medicalr sensor Network was designed to detect a human heartbeat and respiration signals without direct skin contact. In order to design a wireless bio-medical sensor quantitatively, the signal to-noise ratio (SNR) in the baseband output of a sensor should be calculated. Therefore, we analyzed the SNR of the wireless bio- medical sensor, considering the signal power attenuation in a human body and all kinds of noise sources. Especially, we measured a residual phase noise of a typical free-running oscillator and used its value for the SNR analysis. Based on these analysis and the measurement results, a compact, low-cost 2.4 GHz direct conversion bio-medical sensor was designed and implemented in a printed circuit board. The demonstrated sensor consists of two printed antennas, a voltage-controlled oscillator, an I/Q demodulator, and analog circuits. The heartbeat and respiration signals acquired from the I/Q channel of the sensor are applied to the digital signal processing circuit using MATLAB. ECG (electrocardiogram), and reference respiration signals are measured simultaneously to evaluate the performance of the sensor. With an output power of 0dBm and a free running oscillator without a phase locked loop circuits, a detection range of 50 cm was measured. Measurement results show that the heart rate and respiration accuracy was very high.

Keywords - Biomedical Monitoring, SNR, Wireless Sensor Network,ECG ,Doppler Theory.

[1]. Lubecke, V. M., O. Boric-Lubecke, A. Host-Madsen, and A. E. Fathy, "Through-the-Wall radar life detection and monitoring," IEEE MTT-S Int. Microwave Symposium Digest,769–772, May 2007. [2]. Droitcour, A., "Non-contact measurement of heart and respiration rates with a single-chip microwave doppler radar," Ph.D. Thesis, Stanford University, June 2006. [3]. Gao T, Greenspan D, Welsh M, Juang RR & Alm A (2005) Vital Signs Monitoring and Patient Tracking Over a Wireless Network. Proceedings of the 2005 IEEE Engineering in Medicine and Biology, Shanghai, China: 102–105. [4]. Milenkovic A, Otto C & Jovanov E (2006) Wireless Sensor Networks for Personal Health Monitoring: Issues and an Implementation, Computer Communications 29(13– 14): 2521–2533. [5]. Bedcos C, Harris M, Bover R, Schmidt R & Perez-Villacastin J (2007) Decision Support System for the Practical Implementation of the Chronic Heart Failure Guidelines: The MyHeart Approach. Computers in Cardiology 34: 57–60.

Abstract: PCG (phonocardiogram) segmentation plays very important role in heart sound analysis. PCG signal is a weak biological signal with the strong noise. The PCG segmentation of heart sound is generally used to determine the human heart condition. The biomedical signal recordings are so complex and non-stationary that they are also affected by different kinds of noise making their interpretation quite difficult. Different segmentation techniques are discussed in this paper and a survey is reported. PCG segmentation using discrete wavelet transform (DWT) in conjunction with Shannon entropy provides a useful tool for phonocardiogram segmentation. The entropy of the details coefficients is calculated at each level and threshold to detect heart sound signal. This paper presents an analysis of various PCG segmentation techniques and suggested performance measures.

Keywords: PCG signal, Wavelet, Entropy, Segmentation, Recurrence time statistics etc..

[1] Abhishek Misal and Sinha G.R. Denoising of PCG signal by using wavelet transforms Advances in Computational Research 4(1) 2012 46-49.
[2] AF Quiceno, E Delgado , M Vallverd, AM Matijasevic and G Castellanos-Domnguez, Effective Phonocardiogram Segmentation Using Nonlinear Dynamic Analysis and High-Frequency Decomposition Computers in Cardiology 35 2008 161-164.
[3] Cota Navin Gupta, Ramaswamy Palaniappan and Sundaram Swaminathan, Classification of Homomorphic Segmented honocardiogram Signals Using Grow and Learn Network IEEE Engineering in Medicine and Biology 27th Annual Conference Shanghai, China, 2005 4251-4254.
[4] Chissanuthat Bunluechokchai and Weerasak Ussawawongaraya, A Wavelet-based Factor for Classification of Heart Sounds with Mitral Regurgitation International Journal Of Applied Biomedical Engineering 2(1) 2009 44-48.
[5] Nayad Kouras, Daoud Boutana and Messaoud Benidir Wavelet based segmentation and time-frequency characterization of some abnormal heart sound signals 24th International Conference on Microelectronics (ICM) 2012.

Abstract: Autocorrelation is a measure of how similar a signal is to itself. It is often used in signal processing for analyzing functions or series of values, such as time domain signals. In this paper a scheme for finding out the autocorrelation of a sound signal is proposed. The main aim of this scheme is to find out the frequency of a complex signal like a speech signal using relatively easily available tools like Computer, MATLAB, Mike etc. The scheme presents a design of an interesting experiment for the Digital Signal Processing Laboratory.

Keywords: DSP, Autocorrelation, cross correlation, convolution.

[1] Digital Signal Processing Lab Manual. Books: [2] Alan V. Oppenheim and Ronald W. Schafer "Discrete-Time Signal Processing", 3rd Edition, Pearson, 2009.

[3] John G. Proakis and Dimitris G. Manolakis. "Digital Signal Processing. Principles, Algorithms, and Applications",4th Edition, Pearson, 2007.

Abstract: Face recognition(FR) is challenging issue due to variations in illumination, aging, expressions, pose, fading etc. The bottleneck problem in face recognition is due to differences in pose, we will try to minimize this using Bias-variance tradeoff.In this paper bias variance method is used to solve face recognition problems.This method is based on analysis of confidence interval.The variance projection function is developed and employed to locate landmark on human face which are then used to guide the detection of position of different points on face.In Bias variance method smoothing interval of each image is calculated,then estimated value of each interval is calculated to determine confidence interval,variance is defined for each pixel, after that filtering is done for smoothing of image. Smoothing factor and variance are the main feature vectors for face extraction.

Keyword-Bias-Variance, Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), Face recognition (FR)

[1]MessaoudBengherab/, Lamia Mezai1, Farid Harizi1, Mohamed.Cherie!2, Abderrazak Guessoum3 "Face Recognition Based on 2DPCA, DIAPCA and DIA2DPCA in DCT Domain",2008 5th International Multi- Conference on Systems, Signals and Devices [2] Randa Atta and Mohammad Ghanbari ,"Low-Memory requirement band efficient face recognition system based on DCT pyramid",IEEE transaction on Consumer Electronics,Vol 56,No.3,August 2010. [3]H. K. Ekenel and B. Sankur, "Mult-resolution face recognition," Imageand Vision Computing, vol. 23, pp. 469–477, 2005. [4] C. Garcia, G. Zikos, and G. Tziritas, "Wavelet packet analysis for facerecognition," Image and Vision Computing, vol. 18, no. 4, pp. 289– 297,2000. [5] M.sujaritha,S.Annadurai,"Face recognition using wavelet transform and locally discriminating projection.",INtrnational conference on computational Intelligence and multimedia Application 2007. [6]L. Shen and L. Bai, "A review on Gabor wavelets for face recognition,"Pattern Analysis and Applications, vol.9, no. 2, pp. 273-292,2006. [7]Bansal.A,Mehta.K,Arora.S," Face recognition using PCA and LDA Algorithm", Advanced Computing & Communication Technologies (ACCt) 2012 secondINternationalConfereence on Jan 2012. [8] Ahmed ShabaanSamra,Salah El Taweel Gad Allah,Raheb Mahmoud Ibrahim," Face Recognition using Wavelet Transform.FastForoer Transform and Discrete Cosine Transform."

Abstract: Receiver diversity is used to combat the adverse effect of fading. However in general, it is not possible to install multiple antennas at the receiver. Therefore, it is important to exploit diversity at the transmitter also. To do this, MISO (Multiple Input Single Output) and MIMO (Multiple Input Multiple Output) systems are considered in Transmit Beam forming (TB) technique and Space Time Block Coding (STBC) technique. In TB technique, CSI is available at both transmitter and receiver. Based on CSI at transmitter, maximum Eigen mode transmission is used to maximize the received SNR (Signal to Noise Ratio). It provides diversity gain along with antenna array gain also. Apart from it, it reduces delay spread by eliminating the echoes created by distant objects. By focusing power in one direction, it improves interference from other users. In STBC techniques, CSI is required only at the receiver not at transmitter. It provides full diversity gain. However, it is not possible to exploit antenna array gain. There is a loss of code rate for multiple antennas. However, Alamouti has proposed a transmission scheme with two transmit antennas, using which diversity gain of order two can be achieved without losing data rate.

Keywords: CSI, MISO, MIMO, STBC, TB, Transmit-Receive Diversity.

[1] K.S. Gomadam and Syed Ali Jafar, "Modulation and detection for simple receivers in rapidly time varying channels", IEEE transactions on communications vol. 55, March 2009, pp 529-539. [2] Y.N. Trivedi and A.K. Chaturvedi,"Detection in time-varying wireless channels using partial channel state information", International Conference on Communications 2010, IIT Guwahati. [3] T. Eng, N. Kong and L.B. Milstien,"Comparison of Diversity Combining Techniques for Rayleigh-Fading Channels", IEEE Trans. Communications, vol. 44, No. 9, pp. 1117-1129, September 2011. [4] V. Tarokh, N. Seshadri and A.R. Calderbank, "Space time codes for high data rate wireless communications: Performance criterion and code construction," IEEE Trans. Information theory, vol. 44, pp. 744-765, March 2012. [5] S.M Alamouti, "A simple transmit diversity technique for wireless communication," IEEE J. Selected Areas Communications, vol. 16, pp. 1451-1458, October 2012. [6] A.J. Grant, "Performance Analysis of Transmit Beam forming," IEEE Trans. Communications, vol. 51, No. 4, pp. 694-703, April 2013. [7] A. Vielmon, Ye li, J.R. Barry, "Performance of Alamouti transmit diversity over time varying Rayleigh fading channels," IEEE Trans. On wireless comm., vol. 3, pp. 1369-1373, May 2013. [8] J.K. Cavers, "Single user and multiuser adaptive maximal ratio transmission for Rayleigh channels," IEEE Trans. Vehicular Technology, vol. 49, No. 6, pp. 2043-2050, July 2013.

Abstract: Retrieval of video from large digital video storage is challenging task. Video segmentation is first step in the process of efficient video indexing and retrieval. Video shot boundaries needs to be clearly detected which will help in key frame extraction and then video retrieval. The shot transitions are of two types i.e. Abrupt Transition & Gradual Transition. In Gradual Transition, there are three types- fade in / fade out, dissolve and wipe. The detection of cuts are somewhat easier task, however the gradual transition detection is challenging task. Also discriminating gradual transition effect from camera motion and object motion is still an open problem. In our topic we are going to compare various metrics and techniques which are generally used for shot boundary detection. In our future work, Dual tree complex wavelet transform will be used for feature extraction and the classification of various gradual transitions will be done by some learning algorithm. The performance metrics such as recall and precision will be calculated for validation of our algorithm. Keywords: Dual tree complex wavelet transform, Precision, Recall, Shot boundary detection, Traditional metrics.

[1] Ba TuTruongt, Chitra Dorai, Svetha Venkatesht, "Improved fade and dissolve detection for reliable video .0369*69 segmentation,"0-7803-G297-7/00/2000 IEEE. [2] Liang Bai, Song-Yang Lao, Hai-Tao Liu, Jiang Bu , "Video Shot Boundary Detection Using Petri-Net,"1-4244-2096-4/08 ©2008 IEEE. [3] Yin Wang1, Xiangming Wen1, Xinqi Lin1,2, Peizhou He1, Wei Zheng1, "A Novel Video Shot Segmentation Based on Textural Features", 978-0-7695-3744-3/09 © 2009 IEEE DOI 10.1109/IAS.2009.232 [4] Xiang Fu, Jie-xian Zeng, "An Effective Video Shot Boundary Detection Method Based on the Local Color Features of Interest Points", 978-0-7695-3643-9/09 $25.00 © 2009 IEEE DOI 10.1109/ISECS.2009.140 [5] Jun Li, Youdong Ding, Yunyu Shi, Wei Li, "Efficient Shot Boundary Detection Based on Scale Invariant Features," 978-0-7695-3883-9/09 © 2009 IEEE DOI 10.1109/ICIG.2009.99 [6] Abdelati Malek Amel, Ben Abdelali Abdessalem and Mtibaa Abdellatif , "Video shot boundary detection using motion activity descriptor", Journal of Telecommunications, Volume 2, Issue 1, April 2010 [7] W.A.C. Fernando, C.N. Canagarajah, D. R. Bull, "FADE-IN AND FADE-OUT DETECTION IN VIDEO SEQUENCES USING HISTOGRAMS" ISCAS 2000 - IEEE International Symposium on Circuits and Systems, May 28-31, 2000, Geneva, Switzerland [8] Zhang xiaona_Qi guoqing_Wang Qiang_Zhang Tao, "An Improved Approach of Scene Change Detection in Archived Films", 978-1-4244-5900-1/10/$26.00 ©2010 IEEE [9] Costas Cotsaces, Marios A. Gavrielides, and Ioannis Pitas Costas Cotsaces, Marios A. Gavrielides, and Ioannis Pitas, "A Survey of Recent Work in Video Shot Boundary Detection", Department of Informatics, University of Thessaloniki, Thessaloniki 54124, Greece. [10] Krishna K. Warhade, Shabbier N. Merchant and U.B.Desai, "Performance Evaluation of Shot Boundary Detection Metrics in the Presence of Object and Camera Motion", IETE Journal of Researcch, Vol 57,Issue 5, sep-oct 2011.

Abstract: Day by Day the number of vehicles are increasing on the road. There has been drastic increase in sale of four wheelers and two wheelers since last five years and still the sale of the four wheelers are increasing every year. The increase in number of four wheelers has created many problems and one such major problem is parking space of these vehicles. Due to increase in large numbers of these vehicles, parking has become an headache for users of these vehicles. Many large buildings such as residential complex, malls, shopping market, government offices provides parking to the people coming to these buildings. Moreover the cars comes in different sizes some are big in size and some are smaller in size. If a small car comes to the parking area the space occupied by this car will be small. But since the space occupied by it will be small, the rest of the space near it will be wasted . Moreover the people coming to parking area to park the car face difficulties in finding the space to park the vehicles. So by means of this paper, a concept for space modeling has been brought into the picture. According to the size of the car coming for parking the space will be adjusted so that the wastage of extra space will be avoided. A system is developed for simulation in matlab which will guide the people by providing them with the information where the parking space is available by the means of displaying devices. In this way the concept of improved car parking can also be achieved.

Keywords: space modeling, matlab

[1] Seong-eun Yoo, Poh Kit Chong, Taehong Kim,― PGS: Parking Guidance System based on Wireless Sensor Network", 978-1-4244-1653-0/08/$25.00 ©2008 IEEE [2] Satish Reve and Sonal Choudhary ―Management of Car Parking System Using Wireless Sensor Network‖IJETAE Website: www.ijetae.com (ISSN 2250-2459, Volume 2, Issue 7, July 2012) [3] Mingkai Chen, Tianhai Chang, ‖ A Parking Guidance and Information System based on Wireless Sensor Network‖ 978-1-61284-4577-0270-9/11/$26.00 ©2011 IEEE [4] Mingkai Chen, Chao Hu, Tianhai Chang ―The Research on Optimal Parking Space Choice Model in Parking Lots," 978-1-61284-840-2/11/$26.00 ©2011 IEEE [5] Y. Khaled et al., ―An Intelligent Car Park Management System based on Wireless Sensor Networks,‖ IEEE VTC '09, 2009. [6] Rakesh Kumar, Naveen K Chilamkurti and Ben Soh, ―A Comparative Study of Different Sensors for Smart car park Management‖ 2007 International Conference on Intelligent Pervasive Computing [7] BI Yan-Zhong SUN Li-Min, ZHU Hong-Song1 YAN Ting-Xin LUO Zheng-Jun ―A Parking Management System Based on Wireless Sensor Network‖ Vol. 32, No. 6 ACTA AUTOMATICA SINICA November, 2006," IEEE Commun. Surveys & Tutorials, vol. 10, no. 2, 2008.

Abstract: Face recognition presents a challenging problem in the field of image analysis and computer vision. In the presented work we have proposed a novel approach for face recognition using Scale-invariant feature transform. We have the standard ORL (Olivetti Research Laboratories) Database. It contains 20 subject having 10 different orientation and expression. The database is divided into two parts, training and testing database. The SIFT features are generated for every training image and the features called key points is calculated, then k nearest neighbor's classifier is used for the matching scheme for test data . The recognition results demonstrate its robust performance under different expression conditions, Pose variation, illumination changes and partial occlusion. The Equal error rate can be calculated by FAR and FRR and the recognition rate show the robustness of the proposed method.

Keywords : Scale invariant feature transform k nearest neighbors, Equal error rate and Recognition rate

1] X. He, S. Yan, Y. Hu, P. Niyogi, and H. Zhang. Face recognition using Laplacian faces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(3):328–340, 2005. [2] B. Moghaddam and M. H. Yang, "Learning Gender with Support Faces," IEEE Transactions on Pattern Analysis& Machine Intelligence,Vol.24, pp.707-711, 2002. [3]Y. Shinohara and N. Otsu, "Facial Expression Recognition Using Fisher Weight Maps," in Sixth IEEE International Conference on Automatic Face and Gesture Recognition, Vol.100, 2004, pp.499-504. [4] Istanbul, Turkey. J. Wang and H. Yang, 2008, "Face Detection Based On Template Matching And 2DPCA Algorithm", Proc. 2008 Congress on Image and Signal Processing, pp.575-579, Hainan, China. [5] Han Yanbin, Yin Jianqin, Li Jinping, "Human Face Feature Extraction and Recognition Base on SIFT", 2008 International Symposium on Computer Science and Computational Technology. [6] Padraig Cunningham and Sarah Jane De lany,"k -Nearest Neighbor‟s Classifier‟‟, Technical Report UCD-CSI-2007-4 March 27, 2007. [7] Lichun Zhang, Junwei Chen, Yue Lu, and Patrick Wang, " Face Recognition Using Scale Invariant Feature Transform and Support Vector Machine‟‟, Department of Computer Science & Technology East China Normal University, College of Computer and Information Science, Northeastern University Boston, MA 02115, USA.

Abstract: The main objective of this proposal is to automate control and communication systems of the train using PIC18F4550 controller. This method will overcome the difficulties faced by the existing methods such as detecting cracks at rails, monitoring distance between rails, compartments monitoring, fire and smoke monitoring in compartments, and controlling of motors, transformers etc; by automatic operations. One of the major accidents in the railway networks occur due to track side faults. To avoid this we are going to design the automated engine model. The automation techniques are based on two nodes, Track side node and Station side node. The proposed scheme has been modeled for Automation Engines in the Indian railway networks alone. This proposed system will speed up all the operations received data and it will be quickly processed by Multi-channel sensors with help of PIC18F4550 in order to monitor the Temperature, Smoke and to reduce human errors to get the fast response.

Key Words: PIC18F4550 Microcontroller, Wireless Sensor Nodes (WSN), Train Automation (TA), and Electric Locomotive Engine (ELE).

[1] Phillip A. Laplante, Frederick C. Woolsey, "IEEE 1473: An Open-Source Communications Protocol for Railway Vehicles," IT Professional, vol. 5, no. 6, pp: 12-16, Nov. /Dec.2003,DOI:10.1109/ MITP. 2003.1254963 [2] Naderi, H. Mirabadi, A. "Railway Track Condition Monitoring using FBG and FPI Fiber Optic Sensors", The Institution of Engineering and Technology International Conference On Railway Condition Monitoring 29-30; Nov. 2006, pp: 198– 203. Books: [3] PIC MICROCONRTOLLER And Embedded Systems: Using Assembly and C for PIC18 by Muhammad Ali Mazidi, Rolin D. McKinlay, Danny Causey . [4] PIC Microcontroller Project Book For PIC Basic and PIC Basic Pro Compliers by JOHN IOVINE. [5] The PIC Microcontroller Your Personal Introductory Course by JOHN MORTON Web-Sites:-
[6] http://www.electrochemsolutions.com/df/TS1.pdf
[7] http://www.railway-technology.com