{"title":"Learning To Optimize VLSI Design Problems","authors":"Jayadeva, Sameena Shah, Suresh Chandra","doi":"10.1109/INDCON.2006.302857","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302857","url":null,"abstract":"We show applications of a new global optimization strategy that combines support vector machine (SVM) learning with simple local search. The use of SVM learning allows prediction of locations of the global optimum from knowledge of a few local minima. This is particularly valuable in VLSI design applications, where the search space is extremely large. The approach does not need the cost function or constraints to be provided in analytical form, thus allowing the optimizer to be linked with a circuit simulator that provides highly accurate information about circuit behavior. Experimental results show that the optimizer is highly effective in sizing transistors in analog CMOS circuits","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124581612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Learning To Optimize Constrained Problems","authors":"Senior Member, Sameena Shah, Suresh Chandra","doi":"10.1109/INDCON.2006.302858","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302858","url":null,"abstract":"This paper contains early work on how GOSAM, a learning based unconstrained optimization technique that we had proposed in previous work, can be extended to the constrained optimization domain. The algorithm, termed as a global optimizer using support vector regression based adaptive multistart (GOSAM), yielded highly encouraging results for unconstrained benchmark optimization problems","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116849423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Zayaraz, P. Thambidurai, Alain Abran, O. Ormandjieva, M. Talib, Maria Perez
{"title":"Quantitative Measurement of Software Architectural Qualities through COSMIC FFP","authors":"G. Zayaraz, P. Thambidurai, Alain Abran, O. Ormandjieva, M. Talib, Maria Perez","doi":"10.1109/INDCON.2006.302832","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302832","url":null,"abstract":"Quality measurement at the software architecture level leads to risk mitigation, cost reduction and quality assurance. Existing software architectural measurement techniques are qualitative in nature. However, quantification of quality measures facilitates the process of effective quality assurance. In this paper we propose a new quantitative measurement technique based on COSMIC full function points (CFFP) and ISO 9126 quality standards. Though CFFP methodology was basically designed to measure the functional size of software at the requirements level, attempt has been made to apply COSMIC FFP principles at the architectural level to measure the quality attributes based on ISO 9126 quality standards. The proposed measurement technique has been applied to the key word in context case study","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114244490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Novel Rate-Scalable Multimedia Service for E-Learning Videos using Content Based Wavelet Compression","authors":"A. Sood, D. Sarthi, A. Pande, A. Mittal","doi":"10.1109/INDCON.2006.302843","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302843","url":null,"abstract":"In this paper, we address the problem of delivery of multimedia services on bandwidth deficient wireless networks for E-learning. We propose a modified continuous rate-scalable wavelet based video compression technique for E-learning lecture videos. The algorithm eradicates spatial and temporal redundancies and exploits the virtues of content based classification for compression. Some of the distinguished features of our algorithm are its excellent subjective performance due to its adaptive behavior to the network conditions and excellent compression due to the classification of the objects in the E-learning lecture video. Also, the compression mechanism maintains high PSNR for prime objects present in the lecture video which further facilitates zooming operations. In this paper, we introduce a noble concept of even and odd frame distinction (EODist). A significant reduction in number of retransmissions of data packets has been observed after integrating EODist with conventional mechanism, which is also a potential advantage of our algorithm in bandwidth deficient wireless network environment. The algorithm exhibits high asymmetry between compressor and de-compressor. The compressor is designed to achieve optimum content based compression using content based wavelet transform and is computationally more complex whereas the decompressor is intentionally designed procedurally simple to support real time de-compression of the compressed data at the client side. The performance of our algorithm is analyzed and its advantages are justified with the help of experimental results","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125929625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stress Compensation for Improvement in Speaker Recognition","authors":"G. Raja, S. Dandapat","doi":"10.1109/INDCON.2006.302826","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302826","url":null,"abstract":"In this work, we propose three compensation techniques for reduction of stress or emotion effect and improvement in speaker recognition. The degradation of speaker recognition due to emotion has been analyzed on stressed speech database. First compensation technique is based on identification and removal of stressed vector from a set of feature vectors. Second compensation technique uses excitation suppression approach for feature vectors. Third compensation technique is enhancement technique which is based on combination of multiple features. Sinusoidal Amplitude features and Mel-frequency cepstral features with a vector quantization classifier are used for speaker recognition. Four emotions, anger, happy, neutral and question are used for evaluation. The average speaker identification rate of stressed speech except neutral emotion testing utterances with Neutral code book is 84.66%. All the three compensation techniques help improve the speaker identification rates. Third compensation technique produces the best result with an average speaker identification rate of 92.5 %","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127260229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Self-Healing for Self-Organizing Cluster Sensor Networks","authors":"R. Misra, C. Mandal","doi":"10.1109/INDCON.2006.302833","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302833","url":null,"abstract":"Self-healing approach enables sensor network configuration robust to node failures. Fault-tolerance of k-connected network can be achieved using threshold of critical transmission range and node density. A self-healing scheme for clusterhead failure in k-connected cluster sensor network is presented in this work. Clusterhead failure triggers re-clustering in existing clustering schemes for wireless sensor networks (WSN). Re-clustering being a global operation in sensor network, incurs high energy overhead in constrained battery powered WSN. An alternative framework for WSN is based on localized scheme, called 'clusterhead-clique', taken in this work for self-healing. The clusterhead-clique is nearest neighborhood of clusterhead within half transmission radius, results a localized scheme for clusterhead position transfer. The simulation of the protocol based on our approach self-healing achieves 35% energy-efficiency in reconfiguring clusterheads over the existing re-clustering scheme","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124185409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hexagonal Pixel Grid Modeling for Edge Detection and Design of Cellular Architecture for Binary Image Skeletonization","authors":"M. Senthinayaki, S. Veni, K. Narayanan Kutty","doi":"10.1109/INDCON.2006.302802","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302802","url":null,"abstract":"Digital images can be represented by rectangular pixel grid model. Yet an alternate model paradigm using a hexagonal pixel grid can be used to discretize and process images which are more suitable for computer vision modeling. The merits of using hexagonal lattice are superior symmetry, definite neighborhood and fewer samples are needed compared to a rectangular lattice. This paper elucidates the sub sampling procedure needed to obtain the hexagonally sampled image from the conventional rectangularly sampled image. Two image processing operations namely edge detection and image skeletonization were done on hexagonal lattice and also rectangular lattice for comparison. The algorithm used for the edge detection of sub sampled images is based on CLAP (cellular logic array processor) algorithm. Image Skeletonization was done using iterative thinning method which is better suited for VLSI Implementation. The paper further deals with the design and implementation of a cellular processor array (CPA) that executes binary image skeletonization on a hexagonal lattice. The implementation shows better results compared to the existing methods","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128238486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"FPGA Implementation of DSDV Based Router in Mobile Adhoc Network","authors":"M. Ramakrishnan, S. Shanmugavel","doi":"10.1109/INDCON.2006.302822","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302822","url":null,"abstract":"A mobile ad-hoc network is the cooperative engagement of a collection of mobile nodes without the intervention of any centralized access point. It is a temporarily formed infrastructure-less network using mobile nodes like laptops, personal digital assistants and cellular phones. The nodes in the network not only become source or destination but sometimes help other nodes to communicate with each other by behaving like a router. The routing is done using many protocols after taking into account the higher mobility rate involved in the network. The popular protocols are DSDV, DSR, AODV and TORA. These protocols can be implemented in software or in hardware. Hardware can achieve a faster call setup and quick reaction to dynamic topology changes. In the fixed wired network, routers are viewed as hardware devices that are optimized for routing packets at high speeds. Trading off cost, flexibility, ease of configuration and speed will be a challenge for router design. Towards this aim in this paper, the destination sequenced distance vector (DSDV) routing protocol is implemented in hardware using VHDL and the architecture is simulated. This paper proposes MANET router hardware architecture for implementing the DSDV protocol","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131660717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Janakiraman, Dr. V. Vasudevan, Dr. S. Radhakrishnan
{"title":"Agent based Intrusion Detection System: A Computational Biology Approach","authors":"S. Janakiraman, Dr. V. Vasudevan, Dr. S. Radhakrishnan","doi":"10.1109/INDCON.2006.302764","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302764","url":null,"abstract":"This paper is focused on network and agent based intrusion detection systems. This paper includes an overview of several IDS implementations. Many approaches based on hidden Markov models and various forms of finite state automata have been proposed to solve problem of detecting anomaly intrusion, a security attack in which an intruder assumes the identity of a legitimate user. It is proposed to give a general framework for IDS based on the application of techniques used in bioinformatics and agent technology. Our approach is focused on the application of techniques used in bioinformatics for a pair-wise sequence alignment and multiple sequence alignment to compare the monitored session with past user behavior. To achieve low false positive rate in this framework the intrusion can be detected by means of comparing the signature of the current user's session with already existing signatures of the potential intruder. The algorithms of computational biology such as approximation algorithm and Carillo-Lippman heuristic algorithm and sum-of-pairs scoring function are used to measure similarity between a sequence of commands produced by a potential intruder, the user signature and past intruder's signatures. Finally in this research work computational bioinformatics techniques and agent technology are used to offer security in host and network to yield a promising combination of intrusion detection rate and false positive rate","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"258263 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133216826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Novel Beard Removal Method based on Structural Similarity and Co-ordinate Transformations","authors":"N. Kaushik, A. Mittal","doi":"10.1109/INDCON.2006.302842","DOIUrl":"https://doi.org/10.1109/INDCON.2006.302842","url":null,"abstract":"Face reconstruction from available images of a human face is a vital step to achieve various objectives, such as study of human anatomy, intrusion detection, face recognition, content based retrieval, and law enforcement. This paper introduces a novel approach for removal of beard from bearded images using the concept of structural similarity and co-ordinate transformations. The proposed method utilizes the inherent characteristics of structural similarity in human faces which may be present in the form of similar eye-sockets, chin, lips, nose etc. The reconstruction is based on the observation that two humans having high similarity in some facial feature (such as eye sockets) are likely to have similarity in other features (say chin structure) as well. The technique works efficaciously on different type of faces, as it searches similar faces from database and achieves the desired goal of beard removal by accomplishing complicated task of chin reconstruction on the basis of structural mapping in two or more images","PeriodicalId":122715,"journal":{"name":"2006 Annual IEEE India Conference","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134561875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}