With the advent of ICT (Information and Communication Technologies) education sector is also experiencing change in teaching process. Different mode of delivery with the use of ICT and digital content has made concept of E-learning and Blended learning more acceptable. But all the available technologies are not used with full potential, sometimes even not introduced at all. Business Intelligence (BI) is one of them. Educational sector also has got vast amount of data scattered in different forms which can be reused to make more intelligent decisions. Various data mining techniques are available which can be used in order to get intelligent information from educational data. Furthermore with the increasing awareness of benefits due to use of Open Source technologies it has become possible for educational institutes to use various technologies with low cost or no cost. In this paper we have used Open Source software Knime for predicting student's results using Naïve Bayesian Learner and Naïve Bayesian predictor. We also have used Moodle logs data of student's activities as one of the attributes in order to predict results using Naïve Bayes theory.
{"title":"Development of predictive model in education system: using Naïve Bayes classifier","authors":"M. Sharma, Monali Mavani","doi":"10.1145/1980022.1980064","DOIUrl":"https://doi.org/10.1145/1980022.1980064","url":null,"abstract":"With the advent of ICT (Information and Communication Technologies) education sector is also experiencing change in teaching process. Different mode of delivery with the use of ICT and digital content has made concept of E-learning and Blended learning more acceptable. But all the available technologies are not used with full potential, sometimes even not introduced at all. Business Intelligence (BI) is one of them. Educational sector also has got vast amount of data scattered in different forms which can be reused to make more intelligent decisions. Various data mining techniques are available which can be used in order to get intelligent information from educational data. Furthermore with the increasing awareness of benefits due to use of Open Source technologies it has become possible for educational institutes to use various technologies with low cost or no cost. In this paper we have used Open Source software Knime for predicting student's results using Naïve Bayesian Learner and Naïve Bayesian predictor. We also have used Moodle logs data of student's activities as one of the attributes in order to predict results using Naïve Bayes theory.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121422288","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}
In most of the infrastructure networks, in which all terminals communicate through an access point (AP). In such scenarios, the AP can gather information about the state of the network, e. g., the path-losses among terminals. Cooperative ARQ techniques can be useful for selecting a best mode based upon some network performance criterion. It is propose that a DF-HARQ (Decode and forward hybrid ARQ) Protocol which enhances throughput of the system. Base station will select a cooperative mode based upon some network performance criterion, and feed back its decision on the appropriate control channels. Here cooperative diversity lives across the throughput performance of the network. The protocol model and performance analysis to evaluate the throughput of the network is demonstrated.
{"title":"Cooperative ARQ techniques for wireless networks","authors":"A. Kemkar, T. Sontakke","doi":"10.1145/1980022.1980210","DOIUrl":"https://doi.org/10.1145/1980022.1980210","url":null,"abstract":"In most of the infrastructure networks, in which all terminals communicate through an access point (AP). In such scenarios, the AP can gather information about the state of the network, e. g., the path-losses among terminals. Cooperative ARQ techniques can be useful for selecting a best mode based upon some network performance criterion. It is propose that a DF-HARQ (Decode and forward hybrid ARQ) Protocol which enhances throughput of the system. Base station will select a cooperative mode based upon some network performance criterion, and feed back its decision on the appropriate control channels. Here cooperative diversity lives across the throughput performance of the network. The protocol model and performance analysis to evaluate the throughput of the network is demonstrated.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114749922","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}
Signature identification and verification is considered among the most popular biometric methods in the area of personal authentication. The proposed method is based on offline verification of signature by two different algorithms. Before extracting different features from the signature, some preprocessing of the signature is done. In preprocessing, the signature is colour normalized and scaled into a standard format. The first algorithm is based on discrete cosine transform and it takes into consideration all the Discrete Cosine Transform (DCT) coefficients while finding match between test signature and signature stored in the database. The second algorithm is improved version of the first algorithm; it considers only significant DCT coefficients while matching. Both the algorithms use Euclidean distance classifier for comparing test signature with database. The algorithms have shown promising results while dealing with random forgeries and simple forgeries; also it gives good recognition rates.
{"title":"Offline signature verification based on discrete cosine transform","authors":"P. Mhatre, M. Maniroja","doi":"10.1145/1980022.1980033","DOIUrl":"https://doi.org/10.1145/1980022.1980033","url":null,"abstract":"Signature identification and verification is considered among the most popular biometric methods in the area of personal authentication. The proposed method is based on offline verification of signature by two different algorithms. Before extracting different features from the signature, some preprocessing of the signature is done. In preprocessing, the signature is colour normalized and scaled into a standard format. The first algorithm is based on discrete cosine transform and it takes into consideration all the Discrete Cosine Transform (DCT) coefficients while finding match between test signature and signature stored in the database. The second algorithm is improved version of the first algorithm; it considers only significant DCT coefficients while matching. Both the algorithms use Euclidean distance classifier for comparing test signature with database. The algorithms have shown promising results while dealing with random forgeries and simple forgeries; also it gives good recognition rates.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126440871","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}
This paper describes the reduction in torque ripple due to phase commutation of brushless dc motors. The torque ripple at low speeds is reduced by dual switching mode with 120° switching. In this paper an adaptive hysteresis current controller is proposed to eliminate harmonics and to compensate reactive power of VSI fed BLDC drive. An algorithm based on reference frame theory (d-q-0) is used to determine suitable current reference signals. The result of simulation study presented in the paper along with PI controller is found satisfactory to reduce the commutation torque ripple and to eliminate harmonics in the utility current. These results are compared with the conventional sensored BLDC motor drive which is controlled by outer speed loop using PI controller. The above studies have been carried out through detailed digital dynamic simulation using the MATLAB/Simulink.
{"title":"An adaptive current controller for reduction of commutation torque ripple in a sensorless BLDC drive","authors":"M. B. Basam, S. Ajitha","doi":"10.1145/1980022.1980283","DOIUrl":"https://doi.org/10.1145/1980022.1980283","url":null,"abstract":"This paper describes the reduction in torque ripple due to phase commutation of brushless dc motors. The torque ripple at low speeds is reduced by dual switching mode with 120° switching. In this paper an adaptive hysteresis current controller is proposed to eliminate harmonics and to compensate reactive power of VSI fed BLDC drive. An algorithm based on reference frame theory (d-q-0) is used to determine suitable current reference signals. The result of simulation study presented in the paper along with PI controller is found satisfactory to reduce the commutation torque ripple and to eliminate harmonics in the utility current. These results are compared with the conventional sensored BLDC motor drive which is controlled by outer speed loop using PI controller. The above studies have been carried out through detailed digital dynamic simulation using the MATLAB/Simulink.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128128005","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}
The basic aim of biometric identification system is to discriminate automatically between subjects in a reliable and dependable way, according to specific-target application. The randomness of iris pattern makes it one of the most reliable biometric traits. The personal identification approaches using mutialgorithmic are more promising now a day. In this paper a multialgoritmic approach for feature extraction using, a new block-sum method, which results in a compact and efficient feature vector, Haar transform and multiresolution feature extraction techniques is used. The experimental results show that this technique gives most promising results as compared to the existing approaches.
{"title":"A novel multialgoritmic approach for improving accuracy of iris recognition using Haar, multiresolution and new block sum method","authors":"U. Gawande, M. Zaveri, A. Kapur","doi":"10.1145/1980022.1980149","DOIUrl":"https://doi.org/10.1145/1980022.1980149","url":null,"abstract":"The basic aim of biometric identification system is to discriminate automatically between subjects in a reliable and dependable way, according to specific-target application. The randomness of iris pattern makes it one of the most reliable biometric traits. The personal identification approaches using mutialgorithmic are more promising now a day. In this paper a multialgoritmic approach for feature extraction using, a new block-sum method, which results in a compact and efficient feature vector, Haar transform and multiresolution feature extraction techniques is used. The experimental results show that this technique gives most promising results as compared to the existing approaches.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125601334","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}
Nanotechnology has given us the ground to play with the ultimate toy box of nature i. e. atoms and molecules. Everything is made from it and hence the possibilities to create new things appear limitless that holds great potential for improving our lives. The nanoscale materials have high surface to volume ratio, which dramatically changes its electrical, optical and magnetic properties as that of bulk material due to Quantum size effect. Recently this concept was playing important role in the development of electronic industry especially nano-devices.
{"title":"Quantum size effect in nanosize semiconductor materials","authors":"A. Vyavahare, Amit Patil, S. Hadapad","doi":"10.1145/1980022.1980396","DOIUrl":"https://doi.org/10.1145/1980022.1980396","url":null,"abstract":"Nanotechnology has given us the ground to play with the ultimate toy box of nature i. e. atoms and molecules. Everything is made from it and hence the possibilities to create new things appear limitless that holds great potential for improving our lives. The nanoscale materials have high surface to volume ratio, which dramatically changes its electrical, optical and magnetic properties as that of bulk material due to Quantum size effect. Recently this concept was playing important role in the development of electronic industry especially nano-devices.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121943763","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}
Skin detection plays an important role in a wide range of image processing applications ranging from Hand and face detection, tracking in gesture analysis. This work deals with skin color identification algorithm using color segmentation to detect human hands and face in color images. For color segmentation both Single Gaussian Model (SGM) and Gaussian Mixture Model (GMM) are used on different images. Experimental results on images presenting variations in lighting condition and background, and variation in age of the person, demonstrate the efficiency of described skin-segmentation algorithm. This work evolves and compares four GMM's with respect to the SGM.
{"title":"Body parts detection in gesture recognition using color information","authors":"S. M. Bopalkar, P. Talwai, Bhavesh Parmar","doi":"10.1145/1980022.1980054","DOIUrl":"https://doi.org/10.1145/1980022.1980054","url":null,"abstract":"Skin detection plays an important role in a wide range of image processing applications ranging from Hand and face detection, tracking in gesture analysis. This work deals with skin color identification algorithm using color segmentation to detect human hands and face in color images. For color segmentation both Single Gaussian Model (SGM) and Gaussian Mixture Model (GMM) are used on different images. Experimental results on images presenting variations in lighting condition and background, and variation in age of the person, demonstrate the efficiency of described skin-segmentation algorithm. This work evolves and compares four GMM's with respect to the SGM.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115786963","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}
Improvement in digital signal processing makes it better for high speed application. DSP applications such as multimedia and image processing are characterized by colossal amount of data accesses. Today cardinal issue of DSP application is to reduce impact of memory accesses on execution time. Memory Scheduling is important for DSP application to use memory bandwidth effectively. The paper recounts all memory scheduler for DSP application till today. The paper also, introduces dynamic memory access scheduling with refresh priority scheduling. H.264/AVC provides higher coding efficiency through added features and functionality, which impose additional computational complexity in encoder and decoder. The features of memory access patterns of H.264 encoder are analyzed. The overhead cycle of page activation has been reduced to improve bus efficiency which, further adheres to cut down latency of operations. Experiment results from running H.264 application and memory scheduler on Xilinx FPGA. Ultimately, paper compares reduction in execution time with all previous memory scheduler.
{"title":"FPGA implementation & comparison of current trends in memory scheduler for multimedia application","authors":"A. Kulkarni, A. Venkatesan","doi":"10.1145/1980022.1980288","DOIUrl":"https://doi.org/10.1145/1980022.1980288","url":null,"abstract":"Improvement in digital signal processing makes it better for high speed application. DSP applications such as multimedia and image processing are characterized by colossal amount of data accesses. Today cardinal issue of DSP application is to reduce impact of memory accesses on execution time. Memory Scheduling is important for DSP application to use memory bandwidth effectively. The paper recounts all memory scheduler for DSP application till today. The paper also, introduces dynamic memory access scheduling with refresh priority scheduling. H.264/AVC provides higher coding efficiency through added features and functionality, which impose additional computational complexity in encoder and decoder. The features of memory access patterns of H.264 encoder are analyzed. The overhead cycle of page activation has been reduced to improve bus efficiency which, further adheres to cut down latency of operations. Experiment results from running H.264 application and memory scheduler on Xilinx FPGA. Ultimately, paper compares reduction in execution time with all previous memory scheduler.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115834252","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}
Palmprints are one of the oldest biometric traits used by mankind. It is highly universal and moderate user co-operation is required in implemented system. Palmprints are rich in texture information which can be used classification purpose. Wavelets are very good in extracting localized texture information. In this paper a new and faster type of wavelets called kekre's wavelets are used for extracting feature vector from palmprints. Multilevel decomposition is performed and feature vectors are matched using Euclidian distance and Relative Energy Entropy. The results indicate that kekre's wavelets are viable option for extracting texture information from palmprints and provide good accuracy with faster performance.
{"title":"Palmprint recognition using Kekre's wavelet's energy entropy based feature vector","authors":"H. B. Kekre, V. Bharadi, V. Singh, A. Ambardekar","doi":"10.1145/1980022.1980031","DOIUrl":"https://doi.org/10.1145/1980022.1980031","url":null,"abstract":"Palmprints are one of the oldest biometric traits used by mankind. It is highly universal and moderate user co-operation is required in implemented system. Palmprints are rich in texture information which can be used classification purpose. Wavelets are very good in extracting localized texture information. In this paper a new and faster type of wavelets called kekre's wavelets are used for extracting feature vector from palmprints. Multilevel decomposition is performed and feature vectors are matched using Euclidian distance and Relative Energy Entropy. The results indicate that kekre's wavelets are viable option for extracting texture information from palmprints and provide good accuracy with faster performance.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115948919","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}
Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. Unsupervised learning (clustering) deals with which have not been pre classified in any way and so do not have a class attribute associated with them. The scope of applying clustering algorithm is to discover useful but unknown classes of items. Unsupervised learning is an approach of learning where instances are automatically placed into meaningful groups based on their similarity. This paper addresses fundamental concepts of unsupervised learning while it serveys recent clustering algorithm and their complexities.
{"title":"A survey on clustering in data mining","authors":"M. Dalal, N. Harale","doi":"10.1145/1980022.1980143","DOIUrl":"https://doi.org/10.1145/1980022.1980143","url":null,"abstract":"Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. Unsupervised learning (clustering) deals with which have not been pre classified in any way and so do not have a class attribute associated with them. The scope of applying clustering algorithm is to discover useful but unknown classes of items. Unsupervised learning is an approach of learning where instances are automatically placed into meaningful groups based on their similarity. This paper addresses fundamental concepts of unsupervised learning while it serveys recent clustering algorithm and their complexities.","PeriodicalId":197580,"journal":{"name":"International Conference & Workshop on Emerging Trends in Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132418789","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：