J. Raheja, Radhey Shyam, Jatin Gupta, Umesh Kumar, P. B. Prasad
This paper describes a robust technique to determine happy/sad/neutral facial gestures of humans by processing an image containing human face. It aims to do away with the cumbersome process of training the computer with images and thereby significantly reducing the processing time. In this technique human face is identified using skin color identification on various spaces like HSV and YCbCr. Segmented features of face like the lips are determined using unique face feature determination. Contour of lips formed for different human moods are analyzed to identify, facial gesture. Edge detection of lips, followed by morphological operation, gives lip structure. Pattern analysis of lips using the unique histogram algorithm and subsequent comparison with different facial gesture icons gives facial gesture of human being in an image. This technique when tested on a huge database of human images under varying lightning conditions gave acceptable accuracy rates and was found fast enough to be used in real time video-stream
{"title":"Facial Gesture Identification Using Lip Contours","authors":"J. Raheja, Radhey Shyam, Jatin Gupta, Umesh Kumar, P. B. Prasad","doi":"10.1109/ICMLC.2010.13","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.13","url":null,"abstract":"This paper describes a robust technique to determine happy/sad/neutral facial gestures of humans by processing an image containing human face. It aims to do away with the cumbersome process of training the computer with images and thereby significantly reducing the processing time. In this technique human face is identified using skin color identification on various spaces like HSV and YCbCr. Segmented features of face like the lips are determined using unique face feature determination. Contour of lips formed for different human moods are analyzed to identify, facial gesture. Edge detection of lips, followed by morphological operation, gives lip structure. Pattern analysis of lips using the unique histogram algorithm and subsequent comparison with different facial gesture icons gives facial gesture of human being in an image. This technique when tested on a huge database of human images under varying lightning conditions gave acceptable accuracy rates and was found fast enough to be used in real time video-stream","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130132357","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}
P. V. Rao, S. Madhusudana, Nachiketh S.S., K. Keerthi
This paper explores the application of artificial neural networks to image compression. An image compressing algorithm based on Back Propagation (BP) network is developed after image pre-processing. By implementing the proposed scheme the influence of different transfer functions and compression ratios within the scheme is investigated. It has been demonstrated through several experiments that peak-signal-to-noise ratio (PSNR) almost remains same for all compression ratios while mean square error (MSE) varies.
{"title":"Image Compression using Artificial Neural Networks","authors":"P. V. Rao, S. Madhusudana, Nachiketh S.S., K. Keerthi","doi":"10.1109/ICMLC.2010.33","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.33","url":null,"abstract":"This paper explores the application of artificial neural networks to image compression. An image compressing algorithm based on Back Propagation (BP) network is developed after image pre-processing. By implementing the proposed scheme the influence of different transfer functions and compression ratios within the scheme is investigated. It has been demonstrated through several experiments that peak-signal-to-noise ratio (PSNR) almost remains same for all compression ratios while mean square error (MSE) varies.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"134 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131004452","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. K, Vidya Yeri, Arjun A.V., Venugopal K.R., L. Patnaik
Wireless Sensor Networks(WSN) consists of sensor nodes that are networked and are deployed in unattended areas where security is very important. Security is considered as one of the vital issues in the area of sensor networks. This work proposes an efficient scheme that deals with the availability of a mobile node and introduces a session time within which the secured secret key remains valid. The analysis and simulation results showed that the performance of the proposed scheme is better than the existing scheme.
{"title":"Adaptive Mobility and Availability of a Mobile Node for Efficient Secret Key Distribution inWireless Sensor Networks","authors":"S. K, Vidya Yeri, Arjun A.V., Venugopal K.R., L. Patnaik","doi":"10.1109/ICMLC.2010.30","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.30","url":null,"abstract":"Wireless Sensor Networks(WSN) consists of sensor nodes that are networked and are deployed in unattended areas where security is very important. Security is considered as one of the vital issues in the area of sensor networks. This work proposes an efficient scheme that deals with the availability of a mobile node and introduces a session time within which the secured secret key remains valid. The analysis and simulation results showed that the performance of the proposed scheme is better than the existing scheme.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131557957","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 aims to establish a semantic model which is the most important and central component of our Vietnamese Language Query Processing (VLQP) framework. The VLQP framework is architecture of 2-tiers. This framework includes a restricted parser for analyzing Vietnamese query from users based on a class of the pre-defined syntactic rules and a transformer for transforming syntactic structure of query to its semantic representation. In this framework, the semantic model is an original feature we have addressed. This semantic model contributes to the syntax analysis and representation of Vietnamese query forms involving to application domain. We also propose transforming rules to transform syntactic structures to their semantic representation.
{"title":"A Semantic Model for Building the Vietnamese Language Query Processing Framework in e-Library Searching Application","authors":"Dang Tuan Nguyen, Tuan Ngoc Pham, Quoc Tan Phan","doi":"10.1109/ICMLC.2010.17","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.17","url":null,"abstract":"This paper aims to establish a semantic model which is the most important and central component of our Vietnamese Language Query Processing (VLQP) framework. The VLQP framework is architecture of 2-tiers. This framework includes a restricted parser for analyzing Vietnamese query from users based on a class of the pre-defined syntactic rules and a transformer for transforming syntactic structure of query to its semantic representation. In this framework, the semantic model is an original feature we have addressed. This semantic model contributes to the syntax analysis and representation of Vietnamese query forms involving to application domain. We also propose transforming rules to transform syntactic structures to their semantic representation.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128075053","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 proposes Modified Ant Miner algorithm for intrusion detection. Ant Miner and its descendant have produced good result on many classification problems. Data mining technique is still relatively unexplored area for intrusion detection. In this paper, modification has been suggested in basic ant miner algorithm to improve accuracy and training time of algorithm. The KDD Cup 99 intrusion data set is used to evaluate our proposed algorithm and the result obtained from this experiment is compared with that of Support Vector Machine. It has been found that our proposed algorithm is more effective in case of DOS, U2R, and R2L type of attacks.
提出了一种改进的蚂蚁挖掘算法用于入侵检测。蚁矿机及其后续算法在许多分类问题上都取得了很好的结果。数据挖掘技术在入侵检测中仍然是一个相对未开发的领域。本文对基本蚂蚁挖掘算法进行了改进，提高了算法的准确率和训练时间。利用KDD Cup 99入侵数据集对该算法进行了验证，并将实验结果与支持向量机的结果进行了比较。实验结果表明，本文提出的算法在DOS、U2R和R2L类型的攻击中更为有效。
{"title":"Modified Ant Miner for Intrusion Detection","authors":"Deven Agravat, Urmi Vaishnav, P. Swadas","doi":"10.1109/ICMLC.2010.52","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.52","url":null,"abstract":"This paper proposes Modified Ant Miner algorithm for intrusion detection. Ant Miner and its descendant have produced good result on many classification problems. Data mining technique is still relatively unexplored area for intrusion detection. In this paper, modification has been suggested in basic ant miner algorithm to improve accuracy and training time of algorithm. The KDD Cup 99 intrusion data set is used to evaluate our proposed algorithm and the result obtained from this experiment is compared with that of Support Vector Machine. It has been found that our proposed algorithm is more effective in case of DOS, U2R, and R2L type of attacks.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114057384","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 this paper we discuss various machine learning approaches used in mining of data. Further we distinguish between symbolic and sub-symbolic data mining methods. We also attempt to propose a hybrid method with the combination of Artificial Neural Network (ANN) and Cased Based Reasoning (CBR) in mining of data.
{"title":"Hybrid Machine Learning Approach in Data Mining","authors":"Jyothi Bellary, Bhargavi Peyakunta, Sekhar Konetigari","doi":"10.1109/ICMLC.2010.57","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.57","url":null,"abstract":"In this paper we discuss various machine learning approaches used in mining of data. Further we distinguish between symbolic and sub-symbolic data mining methods. We also attempt to propose a hybrid method with the combination of Artificial Neural Network (ANN) and Cased Based Reasoning (CBR) in mining of data.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115307709","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}
Precise and timely predicting the amount of gas emitted from the coal is of great importance for coal mine safety. A novel artificial network model based on fuzzy-rough set for gas emission forecasting of coal mine is proposed in this paper. Some practices prove that this model can perform better than the tradition neural network.
{"title":"The Study of the Gas Emission Prediction Model Based on Fuzzy-rough Set Neural Network","authors":"Jing Hong, Yi Zhao","doi":"10.1109/ICMLC.2010.16","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.16","url":null,"abstract":"Precise and timely predicting the amount of gas emitted from the coal is of great importance for coal mine safety. A novel artificial network model based on fuzzy-rough set for gas emission forecasting of coal mine is proposed in this paper. Some practices prove that this model can perform better than the tradition neural network.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125177428","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 group-oriented applications like conferencing, chat groups and interactive gaming myriad messages are sent from one or more sources to multiple users. Multicasting is the optimum technique for such group oriented applications with effective network resource utilization. But maintaining security is a critical issue in group oriented protocols with frequent membership changes. Confidentiality can be achieved through changing the key material, known as rekeying every time a new member joins the group or existing member leaves from the group. Many techniques have been proposed earlier for this purpose. In centralized approach, a single key server is responsible to generate and distribute keys. In decentralized approach, a hierarchy of key managers distributes the keys. In distributed key-agreement protocol, the group members collectively generate and distribute a group key. This paper uses combination of both de-centralized and key agreement approaches to prevent a single point of failures and to improve the reliability as well as the performance of the system. This paper proposes new a technique(SGKP-1), using hybrid key trees, has certain advantages like secure channel establishment for the distribution of the key material, reducing the storage requirements and burden at each member, minimization of time requirement to become a new member of a group. The computational complexity further reduced using both the combination of public and private key crypto systems.
{"title":"Secure Group Key Distribution Using Hybrid Cryptosystem","authors":"V. Kumari, D. Nagaraju, K. Soumya, K. Raju","doi":"10.1109/ICMLC.2010.41","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.41","url":null,"abstract":"In group-oriented applications like conferencing, chat groups and interactive gaming myriad messages are sent from one or more sources to multiple users. Multicasting is the optimum technique for such group oriented applications with effective network resource utilization. But maintaining security is a critical issue in group oriented protocols with frequent membership changes. Confidentiality can be achieved through changing the key material, known as rekeying every time a new member joins the group or existing member leaves from the group. Many techniques have been proposed earlier for this purpose. In centralized approach, a single key server is responsible to generate and distribute keys. In decentralized approach, a hierarchy of key managers distributes the keys. In distributed key-agreement protocol, the group members collectively generate and distribute a group key. This paper uses combination of both de-centralized and key agreement approaches to prevent a single point of failures and to improve the reliability as well as the performance of the system. This paper proposes new a technique(SGKP-1), using hybrid key trees, has certain advantages like secure channel establishment for the distribution of the key material, reducing the storage requirements and burden at each member, minimization of time requirement to become a new member of a group. The computational complexity further reduced using both the combination of public and private key crypto systems.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127279141","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 this paper, we modify the Split Bregman algorithm for color image restoration with the edge-preserving color image total variation model. The observed blurred images are assumed to be degraded by within channel and cross channel blurs. Our proposed algorithm is based on the Split Bregman process and simply requires Fast Fourier Transform in each iteration. Experimental comparisons using various types of blurs are reported, and the results show that, the proposed method significantly outperforms existing methods, such as the variable splitting alternative minimization algorithm and that adopted by MATLAB deblurring function, in terms of both objective signal to noise ratio and subjective vision quality. This demonstrates the efficiency of our proposed algorithms.
{"title":"Color Image Restoration Based on Split Bregman Iteration Algorithm","authors":"Yi Li-ya, Xiaolei Lu, Furong Wang","doi":"10.1109/ICMLC.2010.22","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.22","url":null,"abstract":"In this paper, we modify the Split Bregman algorithm for color image restoration with the edge-preserving color image total variation model. The observed blurred images are assumed to be degraded by within channel and cross channel blurs. Our proposed algorithm is based on the Split Bregman process and simply requires Fast Fourier Transform in each iteration. Experimental comparisons using various types of blurs are reported, and the results show that, the proposed method significantly outperforms existing methods, such as the variable splitting alternative minimization algorithm and that adopted by MATLAB deblurring function, in terms of both objective signal to noise ratio and subjective vision quality. This demonstrates the efficiency of our proposed algorithms.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125439309","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}
Traditionally, researchers compare the performance of new machine learning algorithms against those of locally executed simulations that serve as benchmarks. This process requires considerable time, computation resources, and expertise. In this paper, we present a method to quickly evaluate the performance feasibility of new algorithms – offering a preliminary study that either supports or opposes the need to conduct a full-scale traditional evaluation, and possibly saving valuable resources for researchers. The proposed method uses performance benchmarks obtained from results reported in the literature rather than local simulations. Furthermore, an alternate statistical technique is suggested for comparative performance analysis, since traditional statistical significance tests do not fit the problem well. We highlight the use of the proposed evaluation method in a study that compared a new algorithm against 47 other algorithms across 46 datasets.
{"title":"Fast Preliminary Evaluation of New Machine Learning Algorithms for Feasibility","authors":"Dustin Baumgartner, G. Serpen","doi":"10.1109/ICMLC.2010.31","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.31","url":null,"abstract":"Traditionally, researchers compare the performance of new machine learning algorithms against those of locally executed simulations that serve as benchmarks. This process requires considerable time, computation resources, and expertise. In this paper, we present a method to quickly evaluate the performance feasibility of new algorithms – offering a preliminary study that either supports or opposes the need to conduct a full-scale traditional evaluation, and possibly saving valuable resources for researchers. The proposed method uses performance benchmarks obtained from results reported in the literature rather than local simulations. Furthermore, an alternate statistical technique is suggested for comparative performance analysis, since traditional statistical significance tests do not fit the problem well. We highlight the use of the proposed evaluation method in a study that compared a new algorithm against 47 other algorithms across 46 datasets.","PeriodicalId":423912,"journal":{"name":"2010 Second International Conference on Machine Learning and Computing","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132585256","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：