2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)最新文献

Security Considerations for a Real Time Landslide Monitoring System 滑坡实时监测系统的安全考虑

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524165

Karthik A, Sangeeth Kumar, Sethuraman N. Rao

{"title":"Security Considerations for a Real Time Landslide Monitoring System","authors":"Karthik A, Sangeeth Kumar, Sethuraman N. Rao","doi":"10.1109/ICCIC.2017.8524165","DOIUrl":"https://doi.org/10.1109/ICCIC.2017.8524165","url":null,"abstract":"The development of Wireless Sensor Network (WSN) used in various industrial applications and remote monitoring has been motivated from the military applications such as battlefield surveillance. The wireless sensor networks contains a group of sensors which monitor or sense several physical parameters like temperature, pressure, moisture content, etc., and pass the data through the network wirelessly to other sensors or to a remote location without being lost or being eavesdropped. WSNs for landslide monitoring are deployed by our research center in some areas of the Western Ghats and another location in the north eastern India which are prone to landslide due to heavy rainfall. The landslide research work includes various sensors for sensing and monitoring the parameters which may lead to landslide, which is one of the natural calamities that can cause several life losses. The sensor values at the landslide prone area are monitored in the data management center, which is situated several kilometers away from the sensors. The paper focus on the architecture of the landslide project, the security threats faced in real world applications, and how they can be resolved.","PeriodicalId":247149,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127499903","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: 1

Wet Face Recognition in Uncontrolled Scenario 非受控场景下的湿人脸识别

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524561

Krishna Dharavath, S. Chede

引用次数: 2

Security Challenges in the Integration of IoT with WSN for Smart Grid Applications 智能电网应用中物联网与WSN集成的安全挑战

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524233

A. Viswanathan, N. B. Sai Shibu, Sethuraman N. Rao, M. Ramesh

{"title":"Security Challenges in the Integration of IoT with WSN for Smart Grid Applications","authors":"A. Viswanathan, N. B. Sai Shibu, Sethuraman N. Rao, M. Ramesh","doi":"10.1109/ICCIC.2017.8524233","DOIUrl":"https://doi.org/10.1109/ICCIC.2017.8524233","url":null,"abstract":"Internet of Things (IoT) is an emerging technology paradigm that can be incorporated in various applications such as Smart Grid, Smart Home, and Communication Networks etc. Wireless Sensor Networks (WSN) are playing a key role in various applications such as landslide detection, waste management, water quality monitoring in rivers and lakes etc. One of the most data critical applications of WSN is Smart grids. The major problem in the existing power grid is the lack of reliability as one cannot predict power failure. The primary cause of power failure is the energy scarcity and the lack of awareness among the users of the energy availability and their usage limits. This result in increase in the energy consumption costs and projects the impression that electricity is unaffordable in the user's mind. Smart Grid offers promising solutions in transforming the existing power grids into a reliable and cost efficient grid by using WSN. This paper focuses on incorporating IoT into Smart Grid and then various security challenges faced therein. It also introduces a solar energy harvester for Smart City Framework, a community of buildings, each equipped with a solar energy harvesting system, which can share their energy according to the decision taken by the control station. There by, it proposes a cost-effective Smart Grid model using distributed renewable energy generators that helps meet the local power demands.","PeriodicalId":247149,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114425798","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: 11

Wideband High-Gain Circularly Polarized Planar Antenna Array for L Band Radar L波段雷达宽带高增益圆极化平面天线阵列

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524447

Sekhar M, E. Kusuma Kumari, A.N.V.Ravi Kumar

引用次数: 15

Effective Deep Learning Model to Predict Student Grade Point Averages 预测学生平均成绩的有效深度学习模型

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524317

Akhilesh P Patil, Karthik Ganesan, A. Kanavalli

{"title":"Effective Deep Learning Model to Predict Student Grade Point Averages","authors":"Akhilesh P Patil, Karthik Ganesan, A. Kanavalli","doi":"10.1109/ICCIC.2017.8524317","DOIUrl":"https://doi.org/10.1109/ICCIC.2017.8524317","url":null,"abstract":"The main objective of this paper is to provide an overview of the deep learning techniques that can be used to predict a student's performance as compared to other traditionally used machine learning techniques. In our research, we developed feed forward neural networks and recurrent neural networks for developing a model to effectively predict the student GPA. The recurrent neural networks gave greater accuracy as compared to feed forward neural networks, as they have memory and take into consideration the consistency of the student performance. The main contribution of the paper is that we have compared various recurrent neural architectures such as single hidden layer long short-term memory network, long short-term memory network with multiple hidden layers, and Bi-directional long short-term memory network with multiple hidden layers. We compared these techniques with root mean square error as the parameter of comparison and found Bi-directional long short-term memory network to have the least error of 8.2%. A comparison of results of the proposed technique versus other deep learning models and machine learning techniques has been provided in the section VIII and the visualization of the results has been provided in section IX. The novelty of the method proposed is that it has memory to differentiate tuples with different order of scores and learn to assign the weights of relationship between nodes by scanning the sequence in both directions compared to decision tree, SVM, feed forward neural network based algorithms which have been earlier used to solve this problem of predicting student score.","PeriodicalId":247149,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114317918","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: 21

Protection Scheme for Shunt Faults in Six-Phase Transmission System Based on Wavelet Transform and Support Vector Machine 基于小波变换和支持向量机的六相输电系统并联故障保护方案

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524340

S. Shukla, Ebha Koley, Subhojit Ghosh

{"title":"Protection Scheme for Shunt Faults in Six-Phase Transmission System Based on Wavelet Transform and Support Vector Machine","authors":"S. Shukla, Ebha Koley, Subhojit Ghosh","doi":"10.1109/ICCIC.2017.8524340","DOIUrl":"https://doi.org/10.1109/ICCIC.2017.8524340","url":null,"abstract":"The rising demand of electrical energy has put considerable stress on the existing network. In this regard, six-phase transmission system with the ability to transmit 73% more power has been proved to be a better alternative than the classical three phase transmission network and that too without any major modifications in the existing set-up. However, the protection protocol of six-phase transmission system is quite complex, due to the larger number of possible faults. In this context, this paper presents a protection scheme based on combined framework of discrete wavelet transform (DWT) and support vector machine (SVM). The approach aims at performing the tasks of detection and classification of shunt faults in six-phase transmission system. The use SVM is motivated by the fact that it has emerged as an efficient, powerful and fast machine learning tool for finding solution to the complex classification problems. The effectiveness of the proposed scheme have been examined for wide variation in fault parameters such as fault location, fault resistance and inception angle. The test results reveal the effectiveness of the proposed scheme in providing information regarding the system status and immunity to parameter perturbations.","PeriodicalId":247149,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125744761","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: 1

Design and Anti-Interference Ability Analysis of RFID Positioning System for Mine Locomotive 矿用机车RFID定位系统设计及抗干扰能力分析

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524442

Yu Lin, Li Meng, Cheng Jin, Liang Shuang

引用次数: 2

Rectangular Micro Strip Antenna Design Using Particle Swarm Optimiztion,Neural Networks and Genetic Algorithms 基于粒子群优化、神经网络和遗传算法的矩形微带天线设计

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8523827

Allemki Santhosh Kumar

引用次数: 1

Abnormalities in Mitral Valve of Heart Detection and Analysis Using Echocardiography Images 心脏二尖瓣异常的超声心动图检测与分析

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524172

A. Anbarasi, R. Subban

{"title":"Abnormalities in Mitral Valve of Heart Detection and Analysis Using Echocardiography Images","authors":"A. Anbarasi, R. Subban","doi":"10.1109/ICCIC.2017.8524172","DOIUrl":"https://doi.org/10.1109/ICCIC.2017.8524172","url":null,"abstract":"Mitral valve is the second most important chamber in the heart which often faces mitral valves stenosis, mitral valves regurgitation and mitral valve prolapsed. This leads to a sudden heart attack where the blood flow in the ventricles pushes back through the backward direction indicating sudden rise and fall in the function of heart. Thus it is threated to be a serious issue which needs to be treated at the earliest, by using an echocardiography method which uses the ultra sound waves bypassing through the muscles and creates an image of the heart muscles. The image captured is analysed with respect to the position of the mitral valve and the blood pressure directions in order to detect the occurrence of heart attack and track the direction of blood at the earlier stage. This paper presents a detailed survey on the different techniques available for the mitral valve stenosis, regurgitation and valve prolapse. Even though the methods like, computer assisted visual feedback, magnetic tracking system, robotically-actuated delivery sheath, parameterized real operations, probabilistic, hierarchical and discriminant, proximal flow convergence method, image acquisition and contour delineation, 3D planimetry technique, support vector machines, Saint Venant-Kirchhoff elasticity model, zero d models, remodelling phenotype, k means clustering 3D tee methods, boosting learning, optical flow algorithm and proximal flow convergence methods are used. Probabilistic hierarchical and discriminant framework and learning recognition model produces more than 90% accuracy. But optical flow algorithm and proximal flow convergence method produces 100% accuracy.","PeriodicalId":247149,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132228107","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: 0

Priority Based Dynamic Resource Allocation in MIMO Cognitive Radio Networks 基于优先级的MIMO认知无线网络动态资源分配

2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) Pub Date : 2017-12-01 DOI: 10.1109/ICCIC.2017.8524549

S. Tamilarasan, P. Kumar

{"title":"Priority Based Dynamic Resource Allocation in MIMO Cognitive Radio Networks","authors":"S. Tamilarasan, P. Kumar","doi":"10.1109/ICCIC.2017.8524549","DOIUrl":"https://doi.org/10.1109/ICCIC.2017.8524549","url":null,"abstract":"The cognitive radio (CR) technology is a developing innovation and offers prominent solution to serious scarcity of spectrum and radio resources in today's situation. Multi-Input and Multi-Output cognitive radio networks (MIMO-CRN) comprise primary users (PUs) and secondary users (SUs) to cooperatively relay the primary traffic. It is extremely complicated to assign channel allocation and resources distribution in heterogeneous networks. The channel selection of SUs should fulfill rate and delay constraints of respective SUs. To overcome this issue we can formulate an efficient dynamic resource allocation technique which should uses very reliable nodes for efficient data transmission. The resources are allocated dynamically after ensuring that the nodes fulfill the specified constraints. This proposed framework should leads to effective data transmission and offer significant network throughput performance by comparing with the existing DRA-CRN algorithm and the simulation results shows that 27% more efficient than existing DSA-CRN algorithm. Furthermore limits the interference at PUs and it should avoid collision.","PeriodicalId":247149,"journal":{"name":"2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134327131","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: 3