S. Poorna, C. Y. Jeevitha, S. Nair, S. Santhosh, G. Nair
{"title":"Emotion recognition using multi-parameter speech feature classification","authors":"S. Poorna, C. Y. Jeevitha, S. Nair, S. Santhosh, G. Nair","doi":"10.1109/CCOMS.2015.7562904","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562904","url":null,"abstract":"Speech emotion recognition is basically extraction and identification of emotion from a speech signal. Speech data, corresponding to various emotions as happiness, sadness and anger, was recorded from 30 subjects. A local database called Amritaemo was created with 300 samples of speech waveforms corresponding to each emotion. Based on the prosodic features: energy contour and pitch contour, and spectral features: cepstral coefficients, quefrency coefficients and formant frequencies, the speech data was classified into respective emotions. The supervised learning method was used for training and testing, and the two algorithms used were Hybrid Rule based K-mean clustering and multiclass Support Vector Machine (SVM) algorithms. The results of the study showed that, for optimized set of features, Hybrid-rule based K mean clustering gave better performance compared to Multi class SVM.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129964950","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":"Deep learning for gender recognition","authors":"Qili Deng, Yong Xu, Jinghua Wang, Kai Sun","doi":"10.1109/CCOMS.2015.7562902","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562902","url":null,"abstract":"The secondary sex characteristics in faces of people are quite different due to variations of age, sex hormone, race and dress-up style. It is a very challenging work to build a gender recognition model for all kinds of people. This paper proposes to train a gender recognition model based on the deep convolutional network on a complete dataset. Our newly built complete dataset contains as many common variations of face images as possible. Based on this complete dataset, we design a very deep convolutional network as our gender classifier. We achieve an accuracy of 98.67% on the most challenging public database, labelled faces in the wild (LFW) [1]· We collect 10000 images from Internet and build a new dataset - Chinese wild database. Our model achieves the accuracy of 97.51% This indicates our model is robust to racial variation. In the above two experiments, our model achieves the state-of-the-art performances in the wild.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"107 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130773979","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":"Implementation of message passing interface in MANETs in processing of big data","authors":"Vishal Sinha, T. Raj","doi":"10.1109/CCOMS.2015.7562883","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562883","url":null,"abstract":"For many years, data mining has been one of the most important tools in the field of research. The mere reason for the rapid growth in availability of raw data is due to cheap information-sensing devices that are readily available. Big data is a term used to define data sets that are comparatively very big and complex like user database of Facebook, and require a lot of resources to process. MANETs stands for Mobile Ad-hoc Networks and is a comparatively new technology and studies have been in progress to make it a more reliable technology. Message passing interface is a basic portable message-passing interface designed to function on several computers at once. It is regularly integrated where there is the need of high speed computing. This paper describes the use of Message Passing Interface which is in preference to MapReduce in Mobile Ad-Hoc Networks to process large and complex data. Here each node in the given network can use partially reserved CPU cycles and the other nodes in the network are used to carry out processing of data in an affordable manner using various architectures of distributed computing. This allows smaller organizations to gather refined information in a much easier way and that too without the need of huge amounts of server to do the same.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116736646","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":"A flexible FPGA-to-FPGA interconnect interface design and implementation","authors":"An Wu, Xi Jin, Shuaizhi Guo, Xueliang Du","doi":"10.1109/CCOMS.2015.7562851","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562851","url":null,"abstract":"In FPGA-based SoCs, interconnect bus such as PCIe and Ethernet has a separate physical layer and physical layer interface. The physical layer (PHY) consumes quite a few power consumption and area overhead. In this paper, we propose a flexible interconnect interface (Unified PHY Interface, UPI) based on FPGA and describe its design. More specifically, UPI can parse various packets automatically by adding an interface convertor between physical layer and upper layer. Thus, a flexible interconnect architecture can be realized by using UPI for each upper layer controller. We implemented UPI on two Xilinx Virtex-7 FPGAs with Synopsys PCIe and Serial RapidIO (SRIO) IP core to verify our design. Experimental results show that the resource utilization was reduced to 72. 8% of the original design.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116079294","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":"Network anomaly recognition based on cauchy particle swarm optimization algorithm-RBF neural network","authors":"Xi Zhen-yuan, Wang Chang-li, Chen He, Wu Jing","doi":"10.1109/CCOMS.2015.7562910","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562910","url":null,"abstract":"Network anomaly recognition based on Cauchy particle swarm optimization algorithm-RBF Neural Network is presented in this paper. We collect 300 samples of KDDCUP99 datasets to study the network anomaly recognition ability based on Cauchy particle swarm optimization algorithm-RBF neural network. We employ the particle swarm optimization algorithm-RBF neural network model, traditional RBF neural network model to compare with the Cauchy particle swarm optimization algorithm-RBF neural network model. The network anomaly recognition results of the Cauchy particle swarm optimization algorithm-RBF neural network model shows that only 2 samples are incorrectly classified. The testing results show that the network anomaly recognition ability of Cauchy particle swarm optimization algorithm-RBF neural network is better than that of the particle swarm optimization algorithm-RBF neural network model, traditional RBF neural network model.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124872911","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":"Two directional multiple colour fusion for face recognition","authors":"Mustafa M. Alrjebi, Wanquan Liu, Ling Li","doi":"10.1109/CCOMS.2015.7562895","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562895","url":null,"abstract":"Colour plays an important role in face recognition and different colour combinations can give different recognition performances. Currently, most of the existing colour component extraction approaches are based on holistic operations as well as only using three-colour components. Recently, a new approach called the Multiple Colour Fusion model (MCF) is proposed for face verification based on more than three colour components but still with holistic manipulations. In this paper, we will investigate the MCF approach for face recognition from a different perspective with local patch operations. First, with a given training-testing dataset, we can extract multiple important colours for all given local patches based on the MCF approach. In this case, the number of extracted colour components on different patches may be different. Secondly, with each prioritized colour component for each patch, we can consequently select different layers via greedy selection approach and then create a three dimensional colour map template. Finally, the resultant template is used for face recognition. With extensive experiments in AR face database, and Curtin face database, we have demonstrated that the proposed approach can improve recognition accuracy from 3.37% to 7.58% in comparison with the original MCF and other different state of the art colour extraction approaches.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129699244","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":"An algorithm for mining closed weighted sequential patterns with flexing time interval for medical time series data","authors":"K. Pazhanikumar, S. Arumugaperumal","doi":"10.1109/CCOMS.2015.7562847","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562847","url":null,"abstract":"In this paper, an algorithm for mining the nonredundant closed weighted sequential patterns with flexible time intervals for the medical time series data is proposed. Initially, the sequence weight for each sequence is calculated based on the time interval between the itemsets and subsequently the candidate sequences are generated with flexible time intervals. The next step is, computation of frequent sequential patterns with the aid of proposed support measure and subsequently the frequent sequential patterns are subjected to closure checking process which leads to filter the closed sequential patterns with flexible time intervals. Finally, the proposed methodology produces a necessary sequential patterns which is proved. The proposed methodology constructs closed sequential patterns which are 23.2% lesser than the sequential patterns.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121254711","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":"BM3D denoising based on minimum GCV score","authors":"Shanshan Shan, Yuehua Li, Shujin Zhu","doi":"10.1109/CCOMS.2015.7562892","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562892","url":null,"abstract":"Block-matching and 3D filtering(BM3D) is an effective denoising approach introduced by Dabov et al. which utilizes 3D transform collaborative filtering on small similar patches extracted from the image corrupted by additive white Gaussian noise. However, when it comes to blind filtering, the denoising performance will worsen rapidly. In this paper, an improved version of BM3D which applies the adaptive noise estimation method based on minimum generalized cross-validation (GCV) score is proposed. Firstly, the noise standard deviation is estimated by minimizing GCV score. According to the optimal smoothing parameter setting, curve fitting is then analyzed to build a formula to modify the estimated noise level. The modified smoothing parameter computed by the built formula is used in BM3D filtering, which induces BM3D algorithm to become adaptive to variant noise. Experiment results display that the proposed method outperforms the original BM3D algorithm in terms of the visual effect and the image quality.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128831770","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":"Quantum computer architectures: An idea whose time is not far away","authors":"R. Vignesh, P. G. Poonacha","doi":"10.1109/CCOMS.2015.7562843","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562843","url":null,"abstract":"Current day computers are increasingly getting limited in hardware due to deep sub-micron effects which may prevent finer gate widths. Parallel computing methods with a large number of cores can only give a linear speed up. Quantum computing is an attempt to unite Quantum mechanics and information science together to achieve next generation computation. Quantum computers have simultaneity and parallelism built inherently. Building a Quantum computer has some difficulties associated with it which involves criteria such as hardware architecture, coherence and fidelity. Quantum computing promises interesting possibilities. Many laboratories in the world are doing research on building Quantum computers which promise exponential speed up. In this article we have given a brief introduction to Quantum mechanics and examine Quantum computing possibilities using few architectures which are being investigated for Quantum computing. We compare three different architectures, namely, Trapped ion architecture, Quantum computing using superconducting Qubits and Quantum computing with Nitrogen Vacancy center in diamonds with various factors such as temperature requirements, coherence time of superposition states, fidelity, error correction, power dissipation and noise.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"11 14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125761210","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":"A novel algorithm for circle curve fitting based on the least square method by the points of the Newton's rings","authors":"Chunlong Fan, Chang Liu","doi":"10.1109/CCOMS.2015.7562911","DOIUrl":"https://doi.org/10.1109/CCOMS.2015.7562911","url":null,"abstract":"Circle curve fitting is always the one of the hot issues of the engineering technology field, circle curve fitting is good or bad depends not only on the fitting algorithm, also depends on the quality of the fitting data. Especially a certain number of disturbed observation points with errors are often used to fit a circle, which will impact the accuracy of least square fitting. This paper proposes an novel method, according to the data of Newton's rings special features. Using the software of Matlab automatically extract the points from the Newton's rings image, and making circular curve fitting by least square method. The algorithm can not only effectively extract data on the circle of the Newton's rings image with noise, even on incomplete Newton's rings image, and get the fitting result with higher accuracy.","PeriodicalId":149896,"journal":{"name":"2015 International Conference on Computers, Communications, and Systems (ICCCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117045318","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}