2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)最新文献

{"title":"Assessing the Effect of Imbalanced Learning on Cross-project Software Defect Prediction","authors":"Md. Fahimuzzman Sohan, Md. Ismail Jabiullah, Sheikh Shah Mohammad Motiur Rahman, S. Mahmud","doi":"10.1109/icccnt45670.2019.8944622","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944622","url":null,"abstract":"Software Defect Prediction (SDP) identifies the defect-prone modules from software source code, which helps to serve good quality software. Mostly previous cross-project SDP models were built based on single project data, where single project was used to prepare prediction models. However, this investigation represents an empirical study of SDP where multiple projects data have been used to prepare prediction models. In this study, multiple projects data have been used to prepare a balance and an imbalance datasets. After that this datasets have been used in different prediction models with eight different classifier algorithms. The trained models have been cross-checked by one balanced and imbalanced test datasets. Five evaluation metrics have been considered for evaluating the performance of the models. The experimental results show that there was no significant changes observed between balanced and imbalanced training models. Only AUC (Area Under the Curve) scores have increased significantly in terms of balanced training model with imbalanced test datasets. In the same training model with the balanced test, accuracy and AUC score have increased significantly. However, this study covers widely by creating the classification model from multiple projects' historical data. Further, it proves that if the sufficient number of non-defective and defective data are supplied in the prediction model, it can predict balanced and imbalanced both categories dataset alike. Here, recommendation will be to consider the imbalanced learning while building the prediction model for cross-projects.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126311278","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":"Machine Learning Applied to Kidney Disease Prediction: Comparison Study","authors":"AKM SHAHARIAR AZAD RABBY, Rezwana Mamata, Monira Akter Laboni, Ohidujjaman, Sheikh Abujar","doi":"10.1109/icccnt45670.2019.8944799","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944799","url":null,"abstract":"Machine learning has earned a remarkable position in healthcare sector because of its capability to enhance the disease prediction in healthcare sector. Artificial intelligence and Machine learning techniques are being used in healthcare sector. Nowadays, one of the world's crucial health related problem is kidney disease. It is increasing day by day because of not maintaining proper food habits, drinking less amount of water and lack of health consciousness. So we need some technique that will continuously monitor health condition effectively. Here, we have proposed an approach for real time kidney disease prediction, monitoring and application (KDPMA). Our aim is to find an optimized and efficient machine learning (ML) technique that can effectively recognize and predict the condition of chronic kidney disease. In this work, we used ten most popular machine learning technique to predict kidney disease. In this process, the data has been divided into two sections. In one section train dataset got trained and another section got evaluated by test dataset. The analysis results show that Decision Tree Classifier and Gaussian Naive Bayes achieved highest performance than the other classifiers, obtaining the accuracy score of 100% and 1 recall(Sensitivity) score. Now we are developing mobile application based on the best output results classifier technique to predict Kidney Disease from patient report.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126416773","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":"Obesity Related Disease Prediction from Healthcare Communities Using Machine Learning","authors":"N. C. Pereira, J. D'souza, Parth Rana, Supriya Solaskar","doi":"10.1109/icccnt45670.2019.8944798","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944798","url":null,"abstract":"In addition to the rapid growth of Machine Learning in biomedical and healthcare communities, the accurate analysis of medical data benefits early disease detection, patient care and community services. However, the analyses accuracy of a disease is reduced when the intake and the quality of medical data is unexplored and incomplete. Obesity happens to be a highly ignored yet a grave health issue that gives rise to a lot of potentially harmful cardiovascular diseases which if neglected could prove fatal. Many people overlook this condition not realizing that by taking small steps to improve their health they can keep many other diseases at bay. Moreover, the underlying problem that persists is not only identifying obesity as a physical medical problem but also speculating the different factors that give rise to it. The key to combatting this real-life problem and staying in the pink of health would be to thoroughly investigate and survey the many reasons as to why people get obese in the first place and eventually nip all the other probable deadly diseases in the bud because prevention is better than cure! This work aims to overcome the above-mentioned limitations by developing a state-of-the-art system that streamlines machine learning algorithms for the effective prediction of Obesity and its related diseases considering the population of India. The government indulgent regulation on food restriction provides easy accessibility to unhealthy, processed food. Also, India's growing career-oriented lifestyle gives rise to irregular biological patterns especially in younger generation who prefer indoor games rather than playing outside. The behavioral and socio-psychological factors such as sleep, stress, ethnicity in addition to hormonal disorders are influential in giving rise to obesity in today's era. There felt a need to develop a system that consider parameters affecting an individual physically, internally, mentally, psychologically and emotionally that contribute to the occurrence of Obesity and also suggest healthier alternatives to curb this problem. Some of the common diseases due to Obesity included in the system are Diabetes, Heart Attack, Hypertension, Osteoarthritis and Varicose Veins. The developed system will undeniably be beneficial for predicting obesity, its related diseases and for the future betterment of an individual.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126573622","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":"Constrained Markov Decision Processes for Intelligent Traffic","authors":"Tripty Singh","doi":"10.1109/icccnt45670.2019.8944574","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944574","url":null,"abstract":"Traffic congestion has become a serious problem as most of the roads are busy and has to suffer vehicular traffic at an increasing rate. Proficient Signaling Systems are indispensable for reducing traffic congestion at intersections. This work tries to design a model according to constraint markov decision process for a given reinforcement learning problem statement which prediction of traffic congestion at the intersection and lanes in a busy roads. A Green Light Simulator is used to simulate real time data set of the Bangalore Roads and Traffic. After that several TLC algorithms are run and efficiency is computed manually. In the third step policy is build using parameters that contain features like acceleration, velocity, no of vehicles plying on the road. Based on these parameters, the policy generated helps to predict congestion at the busy roads. The dataset includes traffic data from Bangalore Roads.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122173271","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":"Line Segmentation of Handwritten Kannada Documents","authors":"S. Swetha, P. Chinmayi, H. Mamatha","doi":"10.1109/icccnt45670.2019.8944517","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944517","url":null,"abstract":"Line Segmentation of handwritten documents is the process of detecting/segmenting lines from an image. It plays an important role in Optical Character Recognition (OCR) and Word Spotting. This paper focuses on the segmentation of handwritten Kannada documents. The importance of the research arises from the need for a paperless environment, making documents searchable and the difficulty in storing and preserving old books and documents. In this paper, we have proposed two novel algorithms for line segmentation of the handwritten Kannada documents - Vertical Strips Method and Connected Components Method. A dataset comprising of around 200 images was used to evaluate the algorithms. The dataset is divided into three categories based on the skew in the lines and the spacing between lines - Easy, Medium and Complex. The algorithm is evaluated based on these three categories and the results are compared for both the methods respectively.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"252 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121036240","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 Multi-Band Frequency Reconfigurable Antenna for Wireless Applications","authors":"R. Parashar, Yogesh Bhomia, Devendra Soni, R. Saraswat","doi":"10.1109/icccnt45670.2019.8944871","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944871","url":null,"abstract":"An octagonal shape introduced split ring resonator based multiband antenna with frequency reconfigurable in its operating band, characteristics is presented here. The antenna is printed on FR4 substrate with dimension of $44times 39times 1.6 mathbf{mm}^{3}$. The antenna consists SRR based octagonal ring as the radiation element with switchable reclined L-shaped slotted ground plane. Antenna achieve hexa bands for wireless standards upper WLAN (5.0/5.8 GHz), lower WiMAX (3.3 GHz), super extended C-band (6.6 GHz), middle X band (9.9 GHz – for space communication) and lower Ku band (15.9 GHz – for satellite communication systems operating band). Stable radiation patterns found with in operating bands with low cross polarization. The proposed design resonates in triple band mode as well as hexa band mode depending upon the switching state of PIN diode placed at reclined L-shaped slot in the ground plane. Experimental antenna shows close results with those obtained in simulation of the proposed antenna.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"44 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120985401","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 Blockchain Based Decentralized Authentication Framework for Resource Constrained IOT devices","authors":"Soumyashree S. Panda, Utkalika Satapathy, B. Mohanta, Debasish Jena, Debasis Gountia","doi":"10.1109/icccnt45670.2019.8944637","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944637","url":null,"abstract":"Internet of Things (IoT) is excessively influencing our day to day lives in many domains be it small smart device like a smart-watch or large industrial enterprises. Thus, a number of different IoT based applications are developed and deployed for these sectors. An IoT system enables devices to communicate among each other without human assistance/involvement. Therefore, verifying the authenticity of devices and ensuring integrity of the communicated messages should be given major importance in this type of autonomous systems. Apart from this, it is almost impractical to develop a centralized authentication scheme for a system whose size growing day by day. For this reason, a decentralized framework based on Blockchain technology that can efficiently manage such a large number of smart devices has been proposed in this paper. An authentication scheme using which devices as well as end users can prove their legitimacy to each other is also designed.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123858800","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":"MD-Tree: A search-optimized Index Structure for Flash Devices","authors":"V. Karthik, G. N. S. Prasanna","doi":"10.1109/icccnt45670.2019.8944765","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944765","url":null,"abstract":"Flash memory provides significant performance improvement over HDDs, but are confronted with some unique challenges like write endurance and write amplifications. Designing of indexing data structures for flash memory has been an area of interest. In this work, we explore a new perspective in implementing B-trees on flash. Previous works have predominantly focused on improving the insert performance which compromised search performance. We propose ways to improves search performance without compromising insert performance using a novel concept of an optimized metadata to speed up the search performance. New ideas to smartly exploit the incremental 1-to-0 update properties of flash in interesting ways to improve the endurance are explored. Our experiments revealed 60% search response time improvement over the best of the alternative schemes. The problems addressed are also relevant to emerging areas like Non-volatile Memory (NVM).","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122411220","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 Deep Learning Approach for Motion Segmentation Using An Optical Flow Technique","authors":"Pooja Ghaywate, Falguni Vyas, Sneha Telang, Supriya Mangale","doi":"10.1109/icccnt45670.2019.8944422","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944422","url":null,"abstract":"There is a severe need of a constant human surveillance of the real-time security footage. Computer Vision is a novel way to reduce human involvement for the said task. Motion segmentation is a crucial step in analyzing video data. The challenges present in motion segmentation, such as illumination changes, dynamic background, and camouflage negatively affect the performance of existing motion segmentation algorithms. In this paper a method of using Convolutional Neural network with optical flow is proposed to improve performance and segment required motion properly. The proposed method is compared with the Lucas-Kanade optical flow method in terms of F1 score. The dataset used is wallflower video dataset. This contains different challenges of motion segmentation viz., illumination changes, dynamic background and clutter.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"242 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131120330","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 Voice Signaling Protocol for Tactical Broadcast Voice Communication in Mobile Ad Hoc Network","authors":"N. Patel, Payal Saxena, Rajesh Singh, Satyendra Kumar","doi":"10.1109/icccnt45670.2019.8944860","DOIUrl":"https://doi.org/10.1109/icccnt45670.2019.8944860","url":null,"abstract":"Push-to-Talk (PTT) based broadcast voice communication is an essential requirement for tactical military radio communication. The uncoordinated and uncontrolled way of PTT based voice communication faces lots of signaling issues in MANET scenario. In this paper; a novel method of signaling for broadcast voice is proposed for multi-hop broadcast voice communication in tactical Mobile Ad-hoc Network (MANET) with Time Division Multiple Access (TDMA) as underlying MAC scheme. The proposed voice signaling protocol has been implemented and validated in real tactical environment.","PeriodicalId":438405,"journal":{"name":"2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131133072","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}