Image search techniques were not generally basedon visual features but on the textual annotation of images. Images were firstly annotated with text and then searched usinga text-based approach from traditional database management systems which is time consuming and difficult to manage. To overcome this problem, CBIR (Content Based Image Retrieval) is introduced which is becoming the hottest research area these days due to vast range of real time applications suchas Crime Prevention, Photograph Archives, Medical Diagnosis, Geographical Information and Remote Sensing System etc. The CBIR system consist of various phases to extract and matchthe features and search the images from the large scale image databases on the basis of visual contents such as Color, Shape andTexture according to the user's interest. As Semantic Gap is themost important and challenging issue. In this paper, Relevance Feedback is used to deal with this issue which based on Support Vector machine has been extensively used in the CBIR system to bridge the semantic gap between low level features and high level human perception features. The learning techniques are predominently used for the classification of images in lablelled and unlabelled datasets. In our proposed work we have to work on KNN, SVM and Bayes Classifier to classify the images. The implementation of our proposed work is done in OpenCv and experiments conducted on the Corel Dataset having 10,000 images. After attempting the experiments on various images wehave to calculate the Precision and Recall which represent in theform of graphs. After analyzing the results we have concludedthat our method is effective to reduce the semantic gap.
图像搜索技术一般不是基于图像的视觉特征，而是基于图像的文本注释。传统的数据库管理系统首先对图像进行文字标注，然后使用基于文本的方法进行检索，费时且管理困难。为了解决这一问题，基于内容的图像检索技术(Content Based Image Retrieval，简称CBIR)应运而生，由于其在犯罪预防、照片档案、医学诊断、地理信息和遥感系统等方面的广泛实时应用，成为当前研究的热点。CBIR系统由多个阶段组成，根据用户的兴趣，以颜色、形状、纹理等视觉内容为基础，从大型图像数据库中提取和匹配特征，并对图像进行搜索。由于语义差距是最重要和最具挑战性的问题。本文采用基于支持向量机的关联反馈方法来解决这一问题，支持向量机已广泛应用于CBIR系统中，以弥合低级特征与高级人类感知特征之间的语义差距。学习技术主要用于标记和未标记数据集中的图像分类。在我们提出的工作中，我们必须使用KNN, SVM和贝叶斯分类器来对图像进行分类。我们提出的工作的实现是在OpenCv中完成的，并在具有10,000张图像的Corel数据集上进行了实验。在对各种图像进行实验后，我们必须计算以图形形式表示的精度和召回率。通过对实验结果的分析，表明该方法能够有效地减少语义缺口。
{"title":"Relevance Feedback Based CBIR System Using SVM and Bayes Classifier","authors":"N. Kaur, Sonika Jindal, Bhavneet Kaur","doi":"10.1109/CICT.2016.50","DOIUrl":"https://doi.org/10.1109/CICT.2016.50","url":null,"abstract":"Image search techniques were not generally basedon visual features but on the textual annotation of images. Images were firstly annotated with text and then searched usinga text-based approach from traditional database management systems which is time consuming and difficult to manage. To overcome this problem, CBIR (Content Based Image Retrieval) is introduced which is becoming the hottest research area these days due to vast range of real time applications suchas Crime Prevention, Photograph Archives, Medical Diagnosis, Geographical Information and Remote Sensing System etc. The CBIR system consist of various phases to extract and matchthe features and search the images from the large scale image databases on the basis of visual contents such as Color, Shape andTexture according to the user's interest. As Semantic Gap is themost important and challenging issue. In this paper, Relevance Feedback is used to deal with this issue which based on Support Vector machine has been extensively used in the CBIR system to bridge the semantic gap between low level features and high level human perception features. The learning techniques are predominently used for the classification of images in lablelled and unlabelled datasets. In our proposed work we have to work on KNN, SVM and Bayes Classifier to classify the images. The implementation of our proposed work is done in OpenCv and experiments conducted on the Corel Dataset having 10,000 images. After attempting the experiments on various images wehave to calculate the Precision and Recall which represent in theform of graphs. After analyzing the results we have concludedthat our method is effective to reduce the semantic gap.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133463338","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}
Machine Learning is the field of computer science that learns from data by studying algorithms and their constructions. In machine learning, predictions can be made by using certain algorithms for specific inputs. In this paper important classification and clustering algorithms are discussed which can be further applied to BE (Information Technology). Third Semester to evaluate student's performance. The performance of students of Digital Electronics of University Institute of Engineering and Technology (UIET), Panjab University (PU) is calculated by applying Hierarchical Clustering Algorithm. Unsupervised Learning Algorithms like K-Means and Hierarchical clustering are discussed and for supervised learning, Naive Bayes and Logistic Regression are discussed. Further the comparisons between the two supervised algorithms and the two unsupervised algorithms are made.
{"title":"Application of Hierarchical Clustering Algorithm to Evaluate Students Performance of an Institute","authors":"Shiwani Rana, R. Garg","doi":"10.1109/CICT.2016.143","DOIUrl":"https://doi.org/10.1109/CICT.2016.143","url":null,"abstract":"Machine Learning is the field of computer science that learns from data by studying algorithms and their constructions. In machine learning, predictions can be made by using certain algorithms for specific inputs. In this paper important classification and clustering algorithms are discussed which can be further applied to BE (Information Technology). Third Semester to evaluate student's performance. The performance of students of Digital Electronics of University Institute of Engineering and Technology (UIET), Panjab University (PU) is calculated by applying Hierarchical Clustering Algorithm. Unsupervised Learning Algorithms like K-Means and Hierarchical clustering are discussed and for supervised learning, Naive Bayes and Logistic Regression are discussed. Further the comparisons between the two supervised algorithms and the two unsupervised algorithms are made.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132707053","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}
Classification is a challenging phenomenon. Text classification uses terms as features which can be grouped to vote for belongingness of a class. This paper explores the performance of Support Vector Machine (SVM) on variation of text features. Empirical results support the findings. The reported result shows significant degradation in SVM classifier as we reduce features from 100 to 50 and then to 25. Short text messages (tweets) are used as a data set and balanced binary classes are used with 841 tweets each. We have used radial basis function as a kernel parameter. TP Rate, FP Rate, Precision, Recall, F Measure are used as a measure of performance evaluator. Confusion matrix is used for quick review of classifier and 10 fold cross validation is used for estimation of prediction model.
{"title":"Feature Based Performance Evaluation of Support Vector Machine on Binary Classification","authors":"Shivani Sharma, S. Srivastava","doi":"10.1109/CICT.2016.41","DOIUrl":"https://doi.org/10.1109/CICT.2016.41","url":null,"abstract":"Classification is a challenging phenomenon. Text classification uses terms as features which can be grouped to vote for belongingness of a class. This paper explores the performance of Support Vector Machine (SVM) on variation of text features. Empirical results support the findings. The reported result shows significant degradation in SVM classifier as we reduce features from 100 to 50 and then to 25. Short text messages (tweets) are used as a data set and balanced binary classes are used with 841 tweets each. We have used radial basis function as a kernel parameter. TP Rate, FP Rate, Precision, Recall, F Measure are used as a measure of performance evaluator. Confusion matrix is used for quick review of classifier and 10 fold cross validation is used for estimation of prediction model.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115024391","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}
Ayush Aroliya, S. Gautam, Aakash Kumar, V. Shrivastava
Apart from all superfluous renewable sources, the wind power is the renewable resource which is gifted one. The major complications in these types of systems are to store the power to accomplish the necessity of load when the power due to wind is unattainable. This paper incapacitates the problematic of energy storage system in wind power generation system (WPGS). To accomplish this requirement, an energy system with the application of dc-dc bidirectional converter is suggested. The analysis of this projected system for WPGS has done on the MatLab/Simulink software. In this a bidirectional isolated dc-dc converter associated with a lithium ion battery of 12V. A variable wind speed has used for the analysis of application of bidirectional converter for energy storage system for WPGS.
{"title":"Analysis of Energy Storage System for Wind Power Generation with Application of Bidirectional Converter","authors":"Ayush Aroliya, S. Gautam, Aakash Kumar, V. Shrivastava","doi":"10.1109/CICT.2016.89","DOIUrl":"https://doi.org/10.1109/CICT.2016.89","url":null,"abstract":"Apart from all superfluous renewable sources, the wind power is the renewable resource which is gifted one. The major complications in these types of systems are to store the power to accomplish the necessity of load when the power due to wind is unattainable. This paper incapacitates the problematic of energy storage system in wind power generation system (WPGS). To accomplish this requirement, an energy system with the application of dc-dc bidirectional converter is suggested. The analysis of this projected system for WPGS has done on the MatLab/Simulink software. In this a bidirectional isolated dc-dc converter associated with a lithium ion battery of 12V. A variable wind speed has used for the analysis of application of bidirectional converter for energy storage system for WPGS.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117123464","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}
Due to the advancement of mobile technologies and portable devices, new research issue in education is evolved from desktop computers to handheld devices, that is, the development of educational assessment with personalized learning system support. In this paper, an integration of student modeling system with dynamic assessment strategy and context recommendations is proposed. This combination addressed some challenging issues from the perspective of cognitive learning to reflect the fundamental needs for effective mobile student learning process through the dynamic assessment. In the presented system, the assessment tests are designed according to the instructor's specification for the selection of questions, the scoring procedure and the evaluation technique. Furthermore, the knowledge estimation model with the guessing parameter is presented. The initial system User interface is implemented with Android Platform for 3rd Generation Mobile emulator which provides a rich set of User Interfaces (UI), gestures and 2-D and 3-D graphic.
{"title":"Improving Educational Assessment in Mobile Environment","authors":"S. Banno, Yanyan Yang","doi":"10.1109/CICT.2016.123","DOIUrl":"https://doi.org/10.1109/CICT.2016.123","url":null,"abstract":"Due to the advancement of mobile technologies and portable devices, new research issue in education is evolved from desktop computers to handheld devices, that is, the development of educational assessment with personalized learning system support. In this paper, an integration of student modeling system with dynamic assessment strategy and context recommendations is proposed. This combination addressed some challenging issues from the perspective of cognitive learning to reflect the fundamental needs for effective mobile student learning process through the dynamic assessment. In the presented system, the assessment tests are designed according to the instructor's specification for the selection of questions, the scoring procedure and the evaluation technique. Furthermore, the knowledge estimation model with the guessing parameter is presented. The initial system User interface is implemented with Android Platform for 3rd Generation Mobile emulator which provides a rich set of User Interfaces (UI), gestures and 2-D and 3-D graphic.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129903790","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}
Machine Translation may be defined as the task of transformation of source text from one language to another. In the following paper, we have discussed the improvement in quality of Machine Translation (MT) using Source text Rewriting. We have performed English to Hindi translation on our MT system and also translation of rewritten English text to Hindi and then compared their performances and evaluated MT system based on 11 features sets as well as using automatic evaluation metrics such as BLEU, METEOR and F-Measure. We found that the performance of MT improved by using Text Rewriting approach.
{"title":"Improving Quality of Machine Translation Using Text Rewriting","authors":"Deepti Chopra, Nisheeth Joshi, Iti Mathur","doi":"10.1109/CICT.2016.14","DOIUrl":"https://doi.org/10.1109/CICT.2016.14","url":null,"abstract":"Machine Translation may be defined as the task of transformation of source text from one language to another. In the following paper, we have discussed the improvement in quality of Machine Translation (MT) using Source text Rewriting. We have performed English to Hindi translation on our MT system and also translation of rewritten English text to Hindi and then compared their performances and evaluated MT system based on 11 features sets as well as using automatic evaluation metrics such as BLEU, METEOR and F-Measure. We found that the performance of MT improved by using Text Rewriting approach.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131250713","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}
Sliding Mode Control (SMC) technique has been used in an extensive manner in many practical applications especially in motion control systems. This paper investigates non-linear discrete time systems accommodating input delay. Firstly, input delay is removed by introducing a smith predictor that converts the original discrete system into delayed free version of the system and makes it solvable. Then, for an effective control "reaching law method" is used to design control law and construction of sliding surface for the delayed free system. The Chebyshev Neural Networks (CNNs) are used to approximate the unknown non-linearity. Simulation shows the robustness of the control scheme.
{"title":"Predictor Based Unknown Non-linear Discrete Time Delayed System Using Sliding Mode Control","authors":"Parmendra Singh, V. Goyal, V. Deolia, T. Sharma","doi":"10.1109/CICT.2016.113","DOIUrl":"https://doi.org/10.1109/CICT.2016.113","url":null,"abstract":"Sliding Mode Control (SMC) technique has been used in an extensive manner in many practical applications especially in motion control systems. This paper investigates non-linear discrete time systems accommodating input delay. Firstly, input delay is removed by introducing a smith predictor that converts the original discrete system into delayed free version of the system and makes it solvable. Then, for an effective control \"reaching law method\" is used to design control law and construction of sliding surface for the delayed free system. The Chebyshev Neural Networks (CNNs) are used to approximate the unknown non-linearity. Simulation shows the robustness of the control scheme.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125517605","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 study proposes a scheme of data transmission over an illicit network. We use image hiding and data compression technique with Diffie-Hellman cryptosystem to intensify the security of data to be transmitted over an insecure channel. Fuzzy error correction code is used to check precision and carriage of error free message.
{"title":"Secure Data Transmission over Illicit Network","authors":"Shubhi Gupta, M. Shrimali","doi":"10.1109/CICT.2016.65","DOIUrl":"https://doi.org/10.1109/CICT.2016.65","url":null,"abstract":"This study proposes a scheme of data transmission over an illicit network. We use image hiding and data compression technique with Diffie-Hellman cryptosystem to intensify the security of data to be transmitted over an insecure channel. Fuzzy error correction code is used to check precision and carriage of error free message.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121602614","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}
Big Data is the buzzword in the industry and academia alike. The reasons for this are not difficult to comprehend - we are living in an electronic age surrounded by exponentially increasing volume and heterogeneity of data. Study of Big Data is a huge opportunity to understand more from data - previously unseen patterns & analysis which was not possible earlier. However, just like any other technology Big Data is akin to a double edged sword, along with the opportunities and benefits it comes with its own set of problems. In this paper we strive to weigh the benefits and the banes of the technology. We start with a brief introduction to Big Data followed by an overview of related work done by the author(s) before moving on to area of focus of the paper and ending with concluding remarks and references.
{"title":"Big Data: A Boon or Bane - The Big Question","authors":"Smita Bajaj, R. Johari","doi":"10.1109/CICT.2016.29","DOIUrl":"https://doi.org/10.1109/CICT.2016.29","url":null,"abstract":"Big Data is the buzzword in the industry and academia alike. The reasons for this are not difficult to comprehend - we are living in an electronic age surrounded by exponentially increasing volume and heterogeneity of data. Study of Big Data is a huge opportunity to understand more from data - previously unseen patterns & analysis which was not possible earlier. However, just like any other technology Big Data is akin to a double edged sword, along with the opportunities and benefits it comes with its own set of problems. In this paper we strive to weigh the benefits and the banes of the technology. We start with a brief introduction to Big Data followed by an overview of related work done by the author(s) before moving on to area of focus of the paper and ending with concluding remarks and references.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116718588","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}
Prachi Dutta, Uzval Sai Gopinadha Varma Dontiboyina
Bicycles are considered to be one of the most ecofriendly and sustainable modes of transportation. Cyclists who have moved to a new city may get lost trying to remember the route they carefully planned at home. In this paper, we introduce a personalized GPS guidance bicycle: NaviRide, that will help the cyclists in selecting a cycling track from a number of pre-defined latitude/longitude waypoints. It has a built-in anti-theft tracking system, calorie counter and collision detection and SOS broadcast system. Our smart bicycle design will help the cyclists reach their cycling goals without any interruptions, promoting healthy and environment friendly human development.
{"title":"NaviRide: Smart Bicycle Computer with GPS Waypoint Indicators","authors":"Prachi Dutta, Uzval Sai Gopinadha Varma Dontiboyina","doi":"10.1109/CICT.2016.100","DOIUrl":"https://doi.org/10.1109/CICT.2016.100","url":null,"abstract":"Bicycles are considered to be one of the most ecofriendly and sustainable modes of transportation. Cyclists who have moved to a new city may get lost trying to remember the route they carefully planned at home. In this paper, we introduce a personalized GPS guidance bicycle: NaviRide, that will help the cyclists in selecting a cycling track from a number of pre-defined latitude/longitude waypoints. It has a built-in anti-theft tracking system, calorie counter and collision detection and SOS broadcast system. Our smart bicycle design will help the cyclists reach their cycling goals without any interruptions, promoting healthy and environment friendly human development.","PeriodicalId":118509,"journal":{"name":"2016 Second International Conference on Computational Intelligence & Communication Technology (CICT)","volume":"2 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113997208","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：