2016 Ninth International Conference on Contemporary Computing (IC3)最新文献_第4页

MetaFusion: An efficient metasearch engine using genetic algorithm MetaFusion:使用遗传算法的高效元搜索引擎

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880228

D. Gupta, Devika Singh

引用次数: 2

Automated segmentation of colon gland using histology images 利用组织学图像自动分割结肠腺体

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880223

Anamika Banwari, Namita Sengar, M. Dutta, C. Travieso-González

引用次数: 9

A hybrid approach for optimizing transparency, robustness and capacity of an audio watermarking algorithm 一种优化音频水印算法透明性、鲁棒性和容量的混合方法

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880237

A. Kaur, M. Dutta

{"title":"A hybrid approach for optimizing transparency, robustness and capacity of an audio watermarking algorithm","authors":"A. Kaur, M. Dutta","doi":"10.1109/IC3.2016.7880237","DOIUrl":"https://doi.org/10.1109/IC3.2016.7880237","url":null,"abstract":"In the field of digital audio watermarking, the issue of optimizing imperceptibility, robustness and payload is still a big challenge. In this paper, the problem of optimizing the design parameters has been addressed by presenting a secure, robust and imperceptible blind audio watermarking algorithm with large payload. The proposed algorithm is designed using the singular values of SVD in detailed coefficients of wavelet domain. Reference to the existing literature, embedding watermark in the singular values of SVD gives a robust algorithm and embedding in wavelet coefficients provide good transparency. The embedding quantization function is designed in such a way that it introduces minimal changes in the signal while embedding and provide opportunity to hide more watermarking data. The features of both the domains have been properly utilized to achieve robustness and imperceptibility at an acceptable level. The experimental results validate that proposed hybrid technique is robust to various signal processing attacks with good perceptual transparency at high payload. The efficiency of the proposed algorithm has been proved by simulation results. The comparison of the proposed algorithm with the existing algorithms show that proposed algorithm has good performance giving good imperceptibility and robustness at 1562.5 bps.","PeriodicalId":294210,"journal":{"name":"2016 Ninth International Conference on Contemporary Computing (IC3)","volume":"333 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134545633","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}

引用次数: 2

New approach toward data hiding using XOR for image steganography 利用异或技术实现图像隐写数据隐藏的新方法

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880204

Kamaldeep Joshi, Rajkumar Yadav

引用次数: 21

Community detection using meta-heuristic approach: Bat algorithm variants 使用元启发式方法的社区检测:Bat算法变体

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880209

Jigyasha Sharma, B. Annappa

{"title":"Community detection using meta-heuristic approach: Bat algorithm variants","authors":"Jigyasha Sharma, B. Annappa","doi":"10.1109/IC3.2016.7880209","DOIUrl":"https://doi.org/10.1109/IC3.2016.7880209","url":null,"abstract":"In the present world, it is hard to overlook — the omnipresence of ‘network’. Be it the study of internet structure, mobile network, protein interactions or social networks, they all religiously emphasizes on network and graph studies. Social network analysis is an emerging field including community detection as its key task. A community in a network, depicts group of nodes in which density of links is high. To find the community structure modularity metric of social network has been used in different optimization approaches like greedy optimization, simulated annealing, extremal optimization, particle swarm optimization and genetic approach. In this paper we have not only introduced modularity metrics but also hamiltonian function (potts model) amalgamated with meta-heuristic optimization approaches of Bat algorithm and Novel Bat algorithm. By utilizing objective functions (modularity and hamiltonian) with modified discrete version of Bat and Novel Bat algorithm we have devised four new variants for community detection. The results obtained across four variants are compared with traditional approaches like Girvan and Newman, fast greedy modularity optimization, Reichardt and Bornholdt, Ronhovde and Nussinov, and spectral clustering. After analyzing the results, we have dwelled upon a promising outcome supporting the modified variants.","PeriodicalId":294210,"journal":{"name":"2016 Ninth International Conference on Contemporary Computing (IC3)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128586890","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}

引用次数: 5

Deterministic learning machine for face recognition with multi-model feature extraction 基于多模型特征提取的人脸识别确定性学习机

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880264

V. P. Vishwakarma

{"title":"Deterministic learning machine for face recognition with multi-model feature extraction","authors":"V. P. Vishwakarma","doi":"10.1109/IC3.2016.7880264","DOIUrl":"https://doi.org/10.1109/IC3.2016.7880264","url":null,"abstract":"In this paper, a new fast learning algorithm named deterministic learning machine (DLM) for the training of single-hidden layer feed-forward neural network (SLFN) subject to face recognition problem is proposed to solve the problem of high dimensional pattern recognition. The existing training algorithms for SLFN are either gradient based iterative learning algorithms or non-iterative algorithms such as extreme learning machine (ELM). The iterative learning algorithms suffer from slow learning, under-fitting, over-fitting whereas in ELM input weights are randomly chosen consequently the classification using ELM is non-deterministic. The proposed DLM is a non-iterative algorithm in which input weights are derived from input space without finding any parameter experimentally and output weights are calculated as an exact solution of linear system. This makes very fast learning and deterministic classification. The feature extraction is performed in a multi-model way by integrating the face image pixels intensity and local entropy of the image. The resulting face recognition system is highly robust against ample facial variations including illumination, pose, expression and occlusion. The proposed DLM with multi-model feature extraction is evaluated on AT&T and Yale face databases. The experimental results clearly reveal the superiority of the proposed approach.","PeriodicalId":294210,"journal":{"name":"2016 Ninth International Conference on Contemporary Computing (IC3)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129323154","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}

引用次数: 15

Parameter estimation of a space radiator using differential evolution algorithm 基于差分进化算法的空间辐射器参数估计

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880200

R. Das

{"title":"Parameter estimation of a space radiator using differential evolution algorithm","authors":"R. Das","doi":"10.1109/IC3.2016.7880200","DOIUrl":"https://doi.org/10.1109/IC3.2016.7880200","url":null,"abstract":"In this article, different combinations of geometrical dimensions of a rectangular space radiator have been estimated using an inverse method. The solution procedure is based on the real-coded differential evolution (DE) optimization algorithm. Electronic equipments and aircraft power plants such as gas turbines need to be consistently cooled for safe operation and due to absence of air medium in space, the heat transfer occurs mainly by surface radiation. The required rate of heat to be dissipated is directly dependent upon the prevailing temperature distribution. Therefore, in this work, the estimation of parameters has been done for satisfying a predefined and simulated surface temperature profile on a space radiator. The temperature distribution used in the present inverse simulation study has been calculated and updated using the fourth order Runge-Kutta method and DE algorithm, respectively. Results have been validated against the existing literature. The present work reveals many possible combinations of the space radiator to attain a given temperature distribution. This offers the opportunity and flexibility to select a space radiator to achieve the required heat transfer rate for cooling various electronic equipments and power generating units typically for space applications.","PeriodicalId":294210,"journal":{"name":"2016 Ninth International Conference on Contemporary Computing (IC3)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121862636","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}

引用次数: 2

Review ranking method for spam recognition 垃圾邮件识别的评审排名方法

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880240

Gunjan Ansari, Tanvir Ahmad, M. Doja

引用次数: 2

RF energy harvesting based D2D communication in downlink cellular network with repulsion point process modeling 基于斥力点过程建模的下行蜂窝网络射频能量采集D2D通信

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880241

Veerpal Kaur, S. Thangjam

引用次数: 5

Logger4u: Predicting debugging statements in the source code Logger4u:预测源代码中的调试语句

2016 Ninth International Conference on Contemporary Computing (IC3) Pub Date : 2016-08-01 DOI: 10.1109/IC3.2016.7880255

Srishti Saini, Neetu Sardana, Sangeeta Lal

{"title":"Logger4u: Predicting debugging statements in the source code","authors":"Srishti Saini, Neetu Sardana, Sangeeta Lal","doi":"10.1109/IC3.2016.7880255","DOIUrl":"https://doi.org/10.1109/IC3.2016.7880255","url":null,"abstract":"Software logging is an essential programming practice that saves important runtime information that can be used later by software developers for troubleshooting, debugging and monitoring the software. Even though software logging has numerous benefits this practice is underutilized because of lack of any formal guiding principles to developers for making strategic and efficient logging decisions. Logging should be optimized because too much logging can cause performance overheads; sparse logging can leave out vital information that might give clues to developers about the real issues. In absence of any formal guidelines developers rely solely on their domain knowledge and experience while making logging decisions. In order to lessen this effort of making decisions we have proposed a machine learning based framework, Logger4u for if-block logging prediction. We extract and use 28 distinctive static features from the source code helpful in making well informed logging decisions. We use Support Vector Machine (two variants, 1 linear and 1 RBF kernel based) models, Multilayer Perceptron with back propagation model and Random forest model in our work. Our approach gives encouraging results for if-block logging task. The accuracy achieved by the Linear SVM, MLP, Random Forest and kernel SVM are 73.05%, 74.62%, 79.84% and 81.22% respectively","PeriodicalId":294210,"journal":{"name":"2016 Ninth International Conference on Contemporary Computing (IC3)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121857973","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}

引用次数: 2