{"title":"Comparison of Hidden Markov Models and Support Vector Machines for vehicle crash detection","authors":"Gautam B. Singh, Haiping Song","doi":"10.1109/ICM2CS.2010.5706709","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706709","url":null,"abstract":"In this paper, machine-learning techniques, such as Hidden Markov Models (HMMs) and Support Vector Machines (SVMs), are applied to discriminate vehicle crashes. Both HMMs and SVMs are optimal with respect to their individual objectives. However, the performances between these two models may be very different depending on how their respective assumptions match with reality. With the exception of some benchmark reports, there is little literature comparing these two promising pattern recognition approaches. In this paper, we compare these two models analytically and experimentally, using a third intermediary method of the Linear Discriminant Analysis (LDA) for detection of crash pulses.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126349264","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":"Optimization of media processor performance through sub word virtual register design","authors":"M. Chauhan","doi":"10.1109/ICM2CS.2010.5706724","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706724","url":null,"abstract":"Subword data is widely used in embedded applications, particularly related to media and network processing. The highest concentration of subword data length in embedded systems is in the 16-bit range. Since the conventional word size is 32-bit, on the average half of the registers remain unoccupied during the register allocation phase. Subword parallelism though less effective as compared to ILP (Instruction Level Parallelism), plays a defining role in latency reduction efforts. The latency issues are important to streaming media processing. In order to provide for the efficient use of registers, new primitive data types are proposed which enables packing of multiple subwords on a register. Since these new data types are operated on conventional instructions, there is very little increase in code size of a program. The work around creates a flexible packing algorithm which prevents the register to remain partially vacant. The use of gate logic to solve the subword packing in registers makes the algorithm efficient and fast. The technique further creates an opportunity to have a single programmable core for different application-specific media needs. In addition to this the use of simplified gate logic for the algorithm implementation makes the hardware implementation/mapping of the algorithm much easier and error free.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115512819","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":"The application of sixth order accurate parallel quarter sweep alternating group explicit algorithm for nonlinear boundary value problems with singularity","authors":"N. Jha","doi":"10.1109/ICM2CS.2010.5706722","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706722","url":null,"abstract":"The aim of this paper is to describe the formulation of quarter sweep alternating group explicit (QSAGE) iterative method using six order accurate finite difference approaches for solving nonlinear singular two point boundary value problems. The proposed QSAGE method shows the superiority over corresponding full sweep AGE and SOR method. The proposed method is applicable to problems both in Cartesian and polar coordinate and suitable for use on parallel computers. Computational results are provided to illustrate the proposed method.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126490136","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":"Applications of clustering algorithms and self organizing maps as data mining and business intelligence tools on real world data sets","authors":"Lavneet Singh, Savleen Singh, P. K. Dubey","doi":"10.1109/ICM2CS.2010.5706714","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706714","url":null,"abstract":"Partitioning a large set of objects into homogeneous clusters is a fundamental operation in data mining. The k-means algorithm is best suited for implementing this operation because of its efficiency in clustering large data sets. In this paper we present a comparative study on different clustering algorithms with respect to k - means clustering to work on large data sets. In this paper we present a comparison among some nonhierarchical and hierarchical clustering algorithms including SOM (Self-Organization Map) neural networks methods. Data were simulated considering correlated and uncorrelated variables, non overlapping and overlapping clusters with and without outliers. Tested with Telecommunication Users and Iris Flower data set, the comparative algorithms had demonstrated a very good classification performance. Experiments on a very large telecommunication data set set consisting of 1000 records and 32 categorical attributes & Iris Flower data set consisting of 150 samples show that the SOM clustering with respect to k means & hierarchical clustering algorithm is scalable in terms of both the number of clusters and the number of records.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123786009","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":"Context ontology driven relevant search using data mining techniques (CODT)","authors":"N. Pahal, P. Gulati, Poonam, P. Gupta","doi":"10.1109/ICM2CS.2010.5706715","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706715","url":null,"abstract":"The size of the publicly indexable World Wide Web (WWW) has probably surpassed 14.3 billion documents and as yet growth shows no sign of leveling off. Search engines encounter the problem of ambiguity in words; therefore, search engines use ontology to find pages with words that are syntactically different but semantically similar. The knowledge provided by ontology is extremely useful in defining the structure and scope for mining web content. Context-ontology is a shared vocabulary to share context information in a pervasive computing domain and include machine-interpretable definitions of basic concepts in the domain and relations among them. This paper proposes an architecture for relevant searching of web documents using data mining techniques such as clustering and association rules. These techniques together with context and ontology extract potentially useful documents from the database. Also, an algorithm has been devised which shows the working in sequence of steps. Finally, the results are compared with the prevailing approaches and with the help of an example it has been seen that CODT is better in context of relevancy.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124916451","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":"Distributed algorithm for optimized vertex coloring","authors":"S. Choudhary, G. Purohit","doi":"10.1109/ICM2CS.2010.5706720","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706720","url":null,"abstract":"Vertex coloring is a well probed problem in graph theory. The problem of graph coloring is known to be NP-complete problem. Such NP complete problems can easily be solved with the help of distributed computing and parallelism, since distributed algorithms are applicable in many real life applications. In this paper we are using distributed algorithm for solving vertex coloring problem. The main objective of this paper is to minimize the number of colors used for achieving the proper vertex coloring of the graph. We have performed an experimental study employing distributed algorithm. We have presented an experimental analysis of simple and elegant distributed algorithm for achieving optimized vertex coloring problem.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123444887","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":"Cluster based approach for centralized routing","authors":"Neha Sharma, Ritwick Chaudhry","doi":"10.1109/ICM2CS.2010.5706726","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706726","url":null,"abstract":"Routing in a network may involve a complex collection of functions that work more or less independently and yet support each other by exchanging services or information. The complexity arises due to maintaining coordination between all the nodes of the subnet, coping with link and node failures. Complexity of centralized routing control strategies may be reduced by partitioning a network into smaller subnetworks or clusters such that the routing functionality leads to efficient network performance. Hence, each cluster is having one network routing control center. Existing hierarchical and partitional clusters are based upon creating groups consisting of elements that are close to each other w.r.t. the distance or parameters considered in the application. But these algorithms are not adequate and appropriate. For designing and selecting an appropriate routing strategy for a network, a number of factors that influence the behavior of the strategy have to be considered such as traffic patterns, volumes, service requirements, feasibility and optimality of routes with respect to resource utilization etc. This paper presents an optimal approach for clustering a large network by first choosing appropriate nodes that can act as a Network Routing Control Centers.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115660135","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":"Web search result optimization by mining the search engine query logs","authors":"A. Sharma, N. Aggarwal, Neelam Duhan, R. Gupta","doi":"10.1109/ICM2CS.2010.5706716","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706716","url":null,"abstract":"Modern Information Retrieval Systems match the terms of a user query with available documents in their index and return a large number of Web pages generally in the form of a ranked list. It becomes almost impractical at the user end to examine every returned document, thus necessitating the need to look for some means of result optimization. In this paper, a novel result optimization technique based on learning from historical query logs is being proposed, which predicts users' information needs and reduces their navigation time within the result list. The method first performs query clustering in query logs based on a novel similarity function and then captures the sequential patterns of clicked web pages in each cluster using a sequential pattern mining algorithm. Finally, search result list is re-ranked by updating the existing PageRank values of pages using the discovered sequential patterns. The proposed work results in reduced search space as user intended pages tend to move upwards in the result list.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131498532","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":"Energy efficient routing for MANET","authors":"A. Kush, Sunil Taneja, D. Sharma","doi":"10.1109/ICM2CS.2010.5706729","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706729","url":null,"abstract":"A recent trend in ad hoc network routing is the reactive on-demand philosophy where routes are established only when required. Most of the protocols in this category, however, use single route and do not utilize multiple alternate paths. This paper proposes an analytical analysis of energy parameters, their usage and their evaluation in ad hoc networks. The scheme is incorporated with the AODV and DSR protocols and the performance has been studied through simulation.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124061301","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}
Supriya B. Harlapur, J. Mallapur, Ajayakumar Katageri, V. S. Patil
{"title":"Call admission control and congestion control for integrated packet networks","authors":"Supriya B. Harlapur, J. Mallapur, Ajayakumar Katageri, V. S. Patil","doi":"10.1109/ICM2CS.2010.5706727","DOIUrl":"https://doi.org/10.1109/ICM2CS.2010.5706727","url":null,"abstract":"Call admission and congestion control mechanisms are the integral parts of any Quality of Service (QoS) design for computer networks that support integrated traffic. In this paper, we propose an call admission control algorithm and a congestion control algorithm for cluster based networks, which are used in a various set of applications that require QoS guarantees. We mainly consider queue length as a main parameter to provide service to the client. Scheduler will keep the track of all the necessary information about the various servers i.e., server which is busy, in which server the queue length is less etc. As the clients arrive for service, scheduler will check out the queue length of the packets and status of the server, then accordingly route the clients request to the desired idle server, if the server is busy, packets will be queued up.","PeriodicalId":320437,"journal":{"name":"2010 International Conference on Methods and Models in Computer Science (ICM2CS-2010)","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124894565","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}