发布求助
文献互助 智能选刊 最新文献

2018 IEEE Punecon最新文献

筛选
英文 中文
Machine Learning Techniques to Predict Autism Spectrum Disorder 预测自闭症谱系障碍的机器学习技术
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745405
Bhawana Tyagi, Rahul Mishra, Neha Bajpai
{"title":"Machine Learning Techniques to Predict Autism Spectrum Disorder","authors":"Bhawana Tyagi, Rahul Mishra, Neha Bajpai","doi":"10.1109/PUNECON.2018.8745405","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745405","url":null,"abstract":"Autism Spectrum Disorder (ASD) is a serious developmental abnormality that seriously affects the behavior and communication of an individual. It limits the use of communicative, social and cognitive skills as well as abilities of the affected personality whereas its symptoms may vary from person to person. Artificial Intelligence’s branch i.e Machine learning is applied to diagnose ASD problem as a classification task in which prediction models were built based on chronological dataset, and then used those patterns to predict that the person is suffering from ASD or not. So it can be used for decision making under ambiguity. Here in this paper we have applied machine learning techniques and validate their performance on a Autism Spectrum Disorder dataset. In our result, we have shown comparison of the performance of different algorithms to diagnose ASD.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127050852","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: 13
Embedded Control System for Flash Lamp Pumped Solid-State Nd:Glass LASER Power Supply 闪光灯泵浦固态钕玻璃激光电源的嵌入式控制系统
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745373
Oishi Chowdhury, Yogesh Sahu, Subhash Maskawade, M. Ansari, Priti Shahane
{"title":"Embedded Control System for Flash Lamp Pumped Solid-State Nd:Glass LASER Power Supply","authors":"Oishi Chowdhury, Yogesh Sahu, Subhash Maskawade, M. Ansari, Priti Shahane","doi":"10.1109/PUNECON.2018.8745373","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745373","url":null,"abstract":"High-power solid state Nd:glass lasers find applications in diverse fields of industry and technology[1]. These lasers are pumped by flash lamps of different sizes. Flash lamps are intense source of wideband light ranging from infrared to ultraviolet. Nd: glass absorption band lies within the emission band of Xenon flash lamps[2]. This paper reports the development of a closed loop standalone embedded control system and the Graphical User Interface (GUI) for flash lamp power supply. The GUI is developed using the Processing software, which is an open-source Java-based software. The microcontroller-based control system continuously monitors and controls the charging process of the energy storage capacitor banks. After the user defined energy is stored on the capacitor banks, the control system generates trigger signals to couple the stored energy to flash lamp load and thereby convert the electrical energy into intense light pulse for pumping of the laser medium. The control system is tested for ruggedness and reliable operation under high EMI generated by switching of several power electronics devices and electromechanical relays. The Graphical User Interface allows a user to interact with the system through visual indicators and buttons. It also displays the time domain characteristics of Flash Lamp current, which is measured with the help of a current transformer. The control system design, product cycle and test results are discussed in this paper.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127711378","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
Cyber Intelligence Assessment- an approach through Entropy 网络情报评估——一种通过熵的方法
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745379
Prasenjit Sen
{"title":"Cyber Intelligence Assessment- an approach through Entropy","authors":"Prasenjit Sen","doi":"10.1109/PUNECON.2018.8745379","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745379","url":null,"abstract":"The conventional methods of defence against cyber attacks are classified principally under signature verification and pattern recognition. The weaknesses inherent in them enables the hackers to penetrate the cyber security. Hence Cyber threat intelligence has become a fundamental component of any advanced cyber security program. Other than the advance warning of incidences received from shared sources, the cyber intelligence is basically derived from the vast information generated from the in house systems, like SIEM data for anomaly and deviation. Assuming a probability distribution of the anomalies arriving in the SIEM system attempt in this paper is taking Shanon’s Entropy as a measure for the uncertainty for a typical data set. As in machine learning a model probability distribution of the alerts in the SIEM may be taken as ‘training data’ and the corresponding Entropy value as reference. Now for any sample of an actual Alerts is likely to have a different probability distribution. A Cross Entropy of this new distribution against the reference model will give the divergence value. This paper proposes to take this divergence as an index for assessment of the cyber intelligence.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116837435","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
Review on Video Refereeing using Computer Vision in Football 计算机视觉在足球视频裁判中的应用综述
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745418
Arik Badami, Mazen Kazi, Sajal Bansal, Krishna Samdani
{"title":"Review on Video Refereeing using Computer Vision in Football","authors":"Arik Badami, Mazen Kazi, Sajal Bansal, Krishna Samdani","doi":"10.1109/PUNECON.2018.8745418","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745418","url":null,"abstract":"Football is, without a doubt, one of the biggest and most popular sports in the world with an estimated fanbase of 3.5 million individuals. England’s \"Premier League\" has 20 teams and each of these teams earn roughly 40 million a year just through tv broadcast sales. Add to that jersey sales, tickets and sponsorship money, one slowly begins to understand just how popular this sport is. However, it is not immune to controversy and one of the biggest problem plaguing the sport is the referral system which is inconsistent and prone to mistakes. This paper presents a system to perform the job of refereeing in the sport of football by taking an input of the live video file and using computer vision and image processing to understand what is happening. Computer Vision is the science aiming at automating the process of information extraction, analysis and understanding information from a sequence of images. It works at providing the capability of vision to a computer. The system makes decisions such as goal, foul or offside. It then conveys this message to the on field official. It does so by tracking the players and the ball and analyzing their position at every instant.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130555111","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
Divide and Conquer Framework with Feature Partitioning Concepts 分而治之的框架与特征划分概念
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745391
Vijayakumar Kadappa, A. Negi
{"title":"Divide and Conquer Framework with Feature Partitioning Concepts","authors":"Vijayakumar Kadappa, A. Negi","doi":"10.1109/PUNECON.2018.8745391","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745391","url":null,"abstract":"Divide-and-Conquer (DC) approach is a classical well-adopted paradigm for designing algorithms. In current big data scenarios, processing of voluminous and variety of data is required. One of the characteristics is, large-dimensional data that needs to be analyzed; for example, high resolution images used in social media are used for sentiment analysis. Our research is oriented towards discovering approaches where stage-by-stage processing is done to bring out most salient features from high-dimensional data. However, we observe that data block processing, in most of the conventional approaches, does not scale well for higher dimensionality. Instead, we think of making blocks along the feature set and we propose a divideand-conquer based feature extraction framework based on feature set partitioning. We demonstrate the effectiveness of the proposed framework using various feature set partitioning based PCA approaches.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130858822","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
Performance of Artificial Neural Network in Nowcasting Summer Monsoon Rainfall: A case Study 人工神经网络在临近预报夏季风降水中的应用研究
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745413
Shilpa Hudnurkar, Neela Rayavarapu
{"title":"Performance of Artificial Neural Network in Nowcasting Summer Monsoon Rainfall: A case Study","authors":"Shilpa Hudnurkar, Neela Rayavarapu","doi":"10.1109/PUNECON.2018.8745413","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745413","url":null,"abstract":"Rainfall prediction has always remained challenging for meteorologists and forecasters due to the complex physics involved. Prediction is important as excess or deficient rainfall has adverse effects on the agriculture sector which in turn drives other economic sectors. Advances in technology have made it possible to have a web of weather stations from where data can be collected frequently in the form of numbers, images, graphs etc. With such availability of data, artificial intelligence has always been a choice of researchers for solving this complex problem. Artificial Neural Network (ANN), a data-driven approach is used here to predict the daily summer monsoon rainfall over Shivajinagar region (18.5308N, 73.8475E). Feed Forward Neural Network is employed for the rainfall prediction. Weather parameters are used as inputs. Number of inputs, number of nodes and number of layers are varied and each model is tested for unseen data. It was found that selection of inputs is important in the case of multivariate time series forecasting using ANN. Increasing the number of layers does not always help to increase accuracy. Performance of all the trained networks is tested for the daily summer monsoon rainfall of the year 2008. The predicted rainfall successfully followed an increase and decrease in the observed rainfall with the Mean Absolute Error of 4.6. A new paradigm for comparing the network performance is used here which is maximum and minimum rainfall prediction capability. It is found that a single hidden layer network with all-weather parameters as inputs has the ability to predict rainfall.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116114194","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
Cifar-10 Classification using Deep Convolutional Neural Network 基于深度卷积神经网络的Cifar-10分类
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745428
R. Doon, Tarun Kumar Rawat, S. Gautam
{"title":"Cifar-10 Classification using Deep Convolutional Neural Network","authors":"R. Doon, Tarun Kumar Rawat, S. Gautam","doi":"10.1109/PUNECON.2018.8745428","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745428","url":null,"abstract":"Deep learning models such as convolution neural networks have been successful in image classification and object detection tasks. Cifar-10 dataset is used in this paper to benchmark our deep learning model. Various function optimization methods such as Adam, RMS along with various regularization techniques are used to get good accuracy on image classification task.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115025443","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: 28
Proposed System Based on EEG and VSL to Detect Drowsiness and Curb Accidents 提出了一种基于EEG和VSL的睡意检测和事故控制系统
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745383
Anuja Kulkarni, Chirag Ghube, Chinmayi Bankar, Aditya Bhide, Dr. Mangesh Bedekar
{"title":"Proposed System Based on EEG and VSL to Detect Drowsiness and Curb Accidents","authors":"Anuja Kulkarni, Chirag Ghube, Chinmayi Bankar, Aditya Bhide, Dr. Mangesh Bedekar","doi":"10.1109/PUNECON.2018.8745383","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745383","url":null,"abstract":"Drowsiness is one of the most prevalent causes of car accidents, especially after drunk driving. There have been many studies to detect drowsiness while driving using different approaches. We propose a system which would efficiently detect drowsiness by integrating the real-time EEG method of detection and our concept of individual-level Hypothesized Variable Speed Limit (HVSL). By studying the power spectral density obtained from the driver’s EEG and the overall duration of the persistence of the alpha waves, it can be determined whether the driver is going into a state of drowsiness or not. In response to elongated time periods of persisting alpha waves, an alarm will be put off to alert the driver. The HVSL module would recommend an appropriate speed depending on environmental conditions as well as drowsy level, thus monitoring the vehicle speed. Hence, drowsiness detection can be combined with HVSL system to mitigate the chances of potential accidents.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115158851","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
Building Real-time knowledge in Social Media on Focus Point: An Apache Spark Streaming Implementation 在焦点上建立社交媒体的实时知识:一个Apache Spark流实现
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745394
Sonam Sharma
{"title":"Building Real-time knowledge in Social Media on Focus Point: An Apache Spark Streaming Implementation","authors":"Sonam Sharma","doi":"10.1109/PUNECON.2018.8745394","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745394","url":null,"abstract":"Be it an individual, or a community or an organization, Social media has given rise to trends and interests which can be triggered for various reasons. Analyzing social media with this freely available interesting public information could yield interested results. Focus Point means the current trend and interest on twitter which can help us in analyzing multiple factors e.g. sensitivity of the ongoing trend, its spread, people getting affected, its effect on business and soon. Traditionally available approaches help us in analyzing batch data and finding interests and trends on it. Now with the advancements in the field of technology helps us in analyzing large amount of online data within seconds. Here we will be exploring twitter streams API in combination with latest technologies like Apache Spark Streaming. In this paper, we will propose our methodology of analyzing and exploring tweets in real-time with the extent of converting information we are getting from twitter to knowledge.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124216751","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
PSO_based Congestion free Critical data transmission in health monitoring system 健康监测系统中关键数据的无拥塞传输
2018 IEEE Punecon Pub Date : 2018-11-01 DOI: 10.1109/PUNECON.2018.8745433
M. Shelke, Akshay Malhotra, P. Mahalle
{"title":"PSO_based Congestion free Critical data transmission in health monitoring system","authors":"M. Shelke, Akshay Malhotra, P. Mahalle","doi":"10.1109/PUNECON.2018.8745433","DOIUrl":"https://doi.org/10.1109/PUNECON.2018.8745433","url":null,"abstract":"Growth of any country is directly proportional to the health of the society. Society health can be categorized into three classes i.e. economic, physical and emotional health. Good physical and emotional health leads to economic growth of country and hence, its overall growth. Hence IOT has considered health industry as one of the main applications. WSN has become an integral part of Internet of Things (IOT). Networked sensors either worn on the body or embedded in our living environment monitor and collect rich health information. Intelligent use of health information can facilitate suitable treatment to the patient and reduce human intervention. Information remains of importance only if it reaches in time to the destination. Congestion can be a severe challenge in Wireless Sensor Networks (WSN) as it increases transmission delay, reduces throughput and sensor lifetime. Hence we propose Particle Swarm Optimization (PSO) based routing protocol aided with efficient scheduling to prevent loss of high priority data and to provide congestion free data flow. The performance of the proposed algorithm is simulated in Network Simulator (NS2) software and the efficiency is verified. The simulation results are compared with that of an existing approach.","PeriodicalId":166677,"journal":{"name":"2018 IEEE Punecon","volume":"70-72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131793469","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信