Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862730
K. Yazhini, D. Loganathan
Acquisition of knowledge and actionable insights from complex, high-dimensional and nonhomogeneous healthcare data still remains a major difficulty in the evolving health care applications. Different data types have been emerged in the advanced healthcare research area such as maintaining patient's records, imaging, sensors data and content that are not simple, nonhomogeneous, badly annotated and normally not structured well. Conventional data mining and machine learning methods has been executing feature engineering to attain efficient and highly robust features from the data, and then constructs a model to predict or cluster data. Several difficulties exist in the situation of complex information and insufficient domain information. The recent advancements in the Deep Learning (DL) models offer novel and efficient end to end frameworks for health care data. In this study, we attempt to survey the recently presented DL models in the advanced medicinal filed in various aspects.
{"title":"A State of Art Approaches on Deep Learning Models in Healthcare: An Application Perspective","authors":"K. Yazhini, D. Loganathan","doi":"10.1109/ICOEI.2019.8862730","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862730","url":null,"abstract":"Acquisition of knowledge and actionable insights from complex, high-dimensional and nonhomogeneous healthcare data still remains a major difficulty in the evolving health care applications. Different data types have been emerged in the advanced healthcare research area such as maintaining patient's records, imaging, sensors data and content that are not simple, nonhomogeneous, badly annotated and normally not structured well. Conventional data mining and machine learning methods has been executing feature engineering to attain efficient and highly robust features from the data, and then constructs a model to predict or cluster data. Several difficulties exist in the situation of complex information and insufficient domain information. The recent advancements in the Deep Learning (DL) models offer novel and efficient end to end frameworks for health care data. In this study, we attempt to survey the recently presented DL models in the advanced medicinal filed in various aspects.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"252 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129788231","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862609
R. Srujana, Y. Mohana Roopa, M. Datta Sai Krishna Mohan
Process scheduling is an important and necessary task of a Multiprogramming operating system where the process manager handles the selection and removal of processes based on a strategy. One such strategy is the Round Robin algorithm. where each process is given a time quantum for its execution. Our algorithm is a combined product of the shortest job first (SJF) algorithm and Round Robin (RR) algorithm. It retains the advantage provided by these algorithms that may have an impact on the overall performance of the CPU and hence, is used to overcome the drawbacks in the RR algorithm by developing the strategies in use. Also, a detailed analysis is performed to compare the proposed algorithm and the existing algorithm in terms of performance and output.
{"title":"Sorted Round Robin Algorithm","authors":"R. Srujana, Y. Mohana Roopa, M. Datta Sai Krishna Mohan","doi":"10.1109/ICOEI.2019.8862609","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862609","url":null,"abstract":"Process scheduling is an important and necessary task of a Multiprogramming operating system where the process manager handles the selection and removal of processes based on a strategy. One such strategy is the Round Robin algorithm. where each process is given a time quantum for its execution. Our algorithm is a combined product of the shortest job first (SJF) algorithm and Round Robin (RR) algorithm. It retains the advantage provided by these algorithms that may have an impact on the overall performance of the CPU and hence, is used to overcome the drawbacks in the RR algorithm by developing the strategies in use. Also, a detailed analysis is performed to compare the proposed algorithm and the existing algorithm in terms of performance and output.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128541374","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862624
S. Bai, D. Latha
Face recognition is one of the important applications in the field of security and surveillance. Even though many methodologies are existing for feature extraction and classification, we are in need of dynamic features and classifiers to overcome the emerging challenges in the field of FRS. On analyzing the work of various researchers, PCA feature extractor is found to be more dynamic than other existing techniques. In this paper, the unique performance of PCA with novel methodologies are overviewed and its merits are highlighted.
{"title":"Impacts of PCA on Face Recognition System","authors":"S. Bai, D. Latha","doi":"10.1109/ICOEI.2019.8862624","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862624","url":null,"abstract":"Face recognition is one of the important applications in the field of security and surveillance. Even though many methodologies are existing for feature extraction and classification, we are in need of dynamic features and classifiers to overcome the emerging challenges in the field of FRS. On analyzing the work of various researchers, PCA feature extractor is found to be more dynamic than other existing techniques. In this paper, the unique performance of PCA with novel methodologies are overviewed and its merits are highlighted.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128211531","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862781
Sarjak Chawda, Aditi Patil, Abhishek Singh, Ashwini M. Save
Clickbait refers to sensational headlines that often exaggerate facts, usually to entice readers to click on them. Many researchers have proposed different techniques involving various Machine Learning algorithms such as Support Vector Machine (SVM), Decision Tree, Random Forest, and Deep Learning techniques such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN). Although there have been previous attempts by many researchers on detection of Clickbait titles, very few have taken into consideration the context of the title. Context plays a vital role in capturing the semantics of the text. Misclassification of Clickbait titles can be avoided using context. The Recurrent Convolutional Neural Network (RCNN) considers the context for text classification. In this system, clickbait classification is done using RCNN model, and later enhanced with LSTM and Gated Recurrent Unit (GRU) to capture long term dependencies and provide better accuracy than the previous state-of-the-art techniques.
{"title":"A Novel Approach for Clickbait Detection","authors":"Sarjak Chawda, Aditi Patil, Abhishek Singh, Ashwini M. Save","doi":"10.1109/ICOEI.2019.8862781","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862781","url":null,"abstract":"Clickbait refers to sensational headlines that often exaggerate facts, usually to entice readers to click on them. Many researchers have proposed different techniques involving various Machine Learning algorithms such as Support Vector Machine (SVM), Decision Tree, Random Forest, and Deep Learning techniques such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN). Although there have been previous attempts by many researchers on detection of Clickbait titles, very few have taken into consideration the context of the title. Context plays a vital role in capturing the semantics of the text. Misclassification of Clickbait titles can be avoided using context. The Recurrent Convolutional Neural Network (RCNN) considers the context for text classification. In this system, clickbait classification is done using RCNN model, and later enhanced with LSTM and Gated Recurrent Unit (GRU) to capture long term dependencies and provide better accuracy than the previous state-of-the-art techniques.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127229145","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862525
P.Jeya Bright, G. Vishnuvarthanan
In today's technology, especially in Lossy Compression image reconstruction which is identical to the original image transmitted is highly unattainable, protection of digital data between buyer and seller especially from intruders and hackers which requires encryption and also to save space and increase speedy transmission which requires image compression has arisen as an important factor of research. This paper proposes a most efficient way of encrypting, compressing and recovering the original image at the receiver side with high PSNR value. The input image is encrypted by using the pseudo random number and compressed using Block Truncation Coding(BTC). The images are transmitted more securely using pseudo random number, which acts as a secret key and it is shared between sender and receiver. The original gray level pixel value is compressed using Block Truncation Coding(BTC). The encrypted image is obtained by adding compressed BTC pixel value with pseudo random number value and then transmitted. At the receiver side, the decryption process is done to recover the compressed pixel value and original image is reconstructed using BTC.
{"title":"Development Of A Scalable Coding For The Encryption Of Images Using Block Truncation Code","authors":"P.Jeya Bright, G. Vishnuvarthanan","doi":"10.1109/ICOEI.2019.8862525","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862525","url":null,"abstract":"In today's technology, especially in Lossy Compression image reconstruction which is identical to the original image transmitted is highly unattainable, protection of digital data between buyer and seller especially from intruders and hackers which requires encryption and also to save space and increase speedy transmission which requires image compression has arisen as an important factor of research. This paper proposes a most efficient way of encrypting, compressing and recovering the original image at the receiver side with high PSNR value. The input image is encrypted by using the pseudo random number and compressed using Block Truncation Coding(BTC). The images are transmitted more securely using pseudo random number, which acts as a secret key and it is shared between sender and receiver. The original gray level pixel value is compressed using Block Truncation Coding(BTC). The encrypted image is obtained by adding compressed BTC pixel value with pseudo random number value and then transmitted. At the receiver side, the decryption process is done to recover the compressed pixel value and original image is reconstructed using BTC.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127255401","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862516
S. Teja, L. Sujihelen
A robot is an automatic machine which perform based on the human behavior with flexible set of movements. This robotic application is always helpful in the field of medicine, rehabilitation, industries and even for rescues operations. Hence designing an improved automatic machine for firefighting is quite challenging. In this paper we have proposed to design and develop a firefighting robot using direction control model. This direction control model has three stages are Obstacle identification, Temperature Spark, and Gas sensors detection-based models. This DC model have improved the control and performs effectively by removing the obstacle on the way to alternative position utilizing a robotic arm to make the path clear.
{"title":"Design and Advancement of Firefighting Robot using Direction Control Model","authors":"S. Teja, L. Sujihelen","doi":"10.1109/ICOEI.2019.8862516","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862516","url":null,"abstract":"A robot is an automatic machine which perform based on the human behavior with flexible set of movements. This robotic application is always helpful in the field of medicine, rehabilitation, industries and even for rescues operations. Hence designing an improved automatic machine for firefighting is quite challenging. In this paper we have proposed to design and develop a firefighting robot using direction control model. This direction control model has three stages are Obstacle identification, Temperature Spark, and Gas sensors detection-based models. This DC model have improved the control and performs effectively by removing the obstacle on the way to alternative position utilizing a robotic arm to make the path clear.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123081627","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862628
Veenal Lalwani, Soheb Munir
FFT is normally utilized in computerized flag preparing algorithms. 4G correspondence and different remote framework based correspondence are directly hotly debated issues of innovative work in the remote correspondence and organizing field. FFT is a calculation that speeds up the count of DFT. In the main stage, low multifaceted nature Radix-2 Multi-way Delay Commutator (R2MDC) FFT recurrence change method is created through Exceptionally Large Scale Integration System structure condition. Low power utilization, less zone and rapid are the VLSI primary parameters. Customary R2MDC FFT structure has more equipment multifaceted nature because of its escalated computational components. Two strategies are utilized to plan radix-2 FFT calculation. In firest strategy is plan radix-2 FFT with the help of reversible Peres gate and TR gate. Second method is design radix-2 FFT with the help of reversible DKG Gate. The all structure are usage vertex-4 gadget family Xilinx programming and looked at past calculation.
{"title":"Area Efficient VLSI Architecture for Reversible Radix-2 FFT Algorithm using Folding Technique and Reversible Gate","authors":"Veenal Lalwani, Soheb Munir","doi":"10.1109/ICOEI.2019.8862628","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862628","url":null,"abstract":"FFT is normally utilized in computerized flag preparing algorithms. 4G correspondence and different remote framework based correspondence are directly hotly debated issues of innovative work in the remote correspondence and organizing field. FFT is a calculation that speeds up the count of DFT. In the main stage, low multifaceted nature Radix-2 Multi-way Delay Commutator (R2MDC) FFT recurrence change method is created through Exceptionally Large Scale Integration System structure condition. Low power utilization, less zone and rapid are the VLSI primary parameters. Customary R2MDC FFT structure has more equipment multifaceted nature because of its escalated computational components. Two strategies are utilized to plan radix-2 FFT calculation. In firest strategy is plan radix-2 FFT with the help of reversible Peres gate and TR gate. Second method is design radix-2 FFT with the help of reversible DKG Gate. The all structure are usage vertex-4 gadget family Xilinx programming and looked at past calculation.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114140740","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862537
Raju A. Nadaf, Vasudha M. Bonal
The present generation devices are built with smart capabilities. The intelligence is embedded in them to act wise in deployed environment. Mirrors are basically used in home for the purpose of grooming up or getting ready for the day. The same mirrors can be made to behave Smart to provide Security and Vigilance in deployed environment. Smart mirror is a system that not only works as a normal mirror but also provides Security against intrusion inside the home. The proposed system is designed using Raspberry Pi, Camera, Raspberry Pi compatible touch screen and microphone as hardware components and Python for programming. The proposed system can accept 3 modes of input commands namely Voice, Touch and Mobile commands. The Smart mirror can be used as a security system against the Intrusion in home. The Yolo Technique with OpenCV for object detection is used for detection of Intrusion of Human. The Yolo (You Only Look Once) is a Machine Learning concept for the detection of objects. The Yolo is an optimized technique as it looks image only once as compared to other image processing techniques, hence work faster. The Video is converted to frames and the frames are given as input to the Raspberry Pi. The Python programming is used along-with the Yolo technique with OpenCV to detect objects. As soon as the intrusion is confirmed, the administrator of the Smart Mirror will be sent an alert E-mail along-with the photo of an intruder and the details are stored in the storage device. The voice and Touch screen commands can be used whenever an administrator/owner is in front of the mirror. The mobile based controls can be used when the administrator/owner of the mirror is away from the mirror. The basic theme of the proposed model is that, to make use of household devices for providing security.
这一代设备具有智能功能。智能嵌入其中，以便在部署环境中明智地行动。镜子在家里基本上是用来梳妆打扮或为一天做准备的。同样的镜像可以使行为智能，以提供部署环境中的安全性和警惕性。智能镜子是一种不仅具有普通镜子的功能，还可以防止家庭内部入侵的安全系统。本系统采用树莓派、摄像头、兼容树莓派的触摸屏和麦克风作为硬件部件，使用Python编程。该系统可接受语音、触摸和移动三种输入命令模式。智能镜子可以作为家庭防盗系统。利用Yolo技术和OpenCV进行对象检测，实现了对人类入侵行为的检测。Yolo (You Only Look Once)是一个用于检测物体的机器学习概念。Yolo是一种优化的技术，因为与其他图像处理技术相比，它只看一次图像，因此工作速度更快。视频被转换成帧，帧作为输入给树莓派。Python编程与Yolo技术以及OpenCV一起用于检测对象。一旦确认入侵，智能镜像的管理员就会收到一封警告电子邮件以及入侵者的照片，详细信息将存储在存储设备中。只要管理员/所有者在镜子前，就可以使用语音和触摸屏命令。当镜像的管理员/所有者离开镜像时，可以使用基于移动设备的控件。所建议的模式的基本主题是，利用家用设备提供安全。
{"title":"Smart Mirror using Raspberry Pi as a Security and Vigilance System","authors":"Raju A. Nadaf, Vasudha M. Bonal","doi":"10.1109/ICOEI.2019.8862537","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862537","url":null,"abstract":"The present generation devices are built with smart capabilities. The intelligence is embedded in them to act wise in deployed environment. Mirrors are basically used in home for the purpose of grooming up or getting ready for the day. The same mirrors can be made to behave Smart to provide Security and Vigilance in deployed environment. Smart mirror is a system that not only works as a normal mirror but also provides Security against intrusion inside the home. The proposed system is designed using Raspberry Pi, Camera, Raspberry Pi compatible touch screen and microphone as hardware components and Python for programming. The proposed system can accept 3 modes of input commands namely Voice, Touch and Mobile commands. The Smart mirror can be used as a security system against the Intrusion in home. The Yolo Technique with OpenCV for object detection is used for detection of Intrusion of Human. The Yolo (You Only Look Once) is a Machine Learning concept for the detection of objects. The Yolo is an optimized technique as it looks image only once as compared to other image processing techniques, hence work faster. The Video is converted to frames and the frames are given as input to the Raspberry Pi. The Python programming is used along-with the Yolo technique with OpenCV to detect objects. As soon as the intrusion is confirmed, the administrator of the Smart Mirror will be sent an alert E-mail along-with the photo of an intruder and the details are stored in the storage device. The voice and Touch screen commands can be used whenever an administrator/owner is in front of the mirror. The mobile based controls can be used when the administrator/owner of the mirror is away from the mirror. The basic theme of the proposed model is that, to make use of household devices for providing security.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114230375","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862614
S. Sajikumar, A. Anilkumar
A continuous wavelet transform (CWT) based object tracking algoithm is proposed. Spatio-temporal motion-tuned wavelet is used to extract motion parameters like velocity, orientation, position and scale. CWT is used to define three energy densities which are used as estimators. Sequential optimization of parameters are done in a frame-by-frame manner which allows the algorithm to track moving objects. The problem of setting initial scale parameter is improved by a new functional relation between radius of the target and velocity using a third degree polynomial constructed from 2D-Chebyshev polynomials. Experimental results show that the new functional relation gives reasonable initial scale parameter without any analysis of huge amount of previous data and the revised algorithm tracks the object in a better way.
{"title":"An Object Tracking Algorithm Based on Motion-Tuned Continuous Wavelet Transform","authors":"S. Sajikumar, A. Anilkumar","doi":"10.1109/ICOEI.2019.8862614","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862614","url":null,"abstract":"A continuous wavelet transform (CWT) based object tracking algoithm is proposed. Spatio-temporal motion-tuned wavelet is used to extract motion parameters like velocity, orientation, position and scale. CWT is used to define three energy densities which are used as estimators. Sequential optimization of parameters are done in a frame-by-frame manner which allows the algorithm to track moving objects. The problem of setting initial scale parameter is improved by a new functional relation between radius of the target and velocity using a third degree polynomial constructed from 2D-Chebyshev polynomials. Experimental results show that the new functional relation gives reasonable initial scale parameter without any analysis of huge amount of previous data and the revised algorithm tracks the object in a better way.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121048184","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}
Pub Date : 2019-04-01DOI: 10.1109/ICOEI.2019.8862602
Yogesh S Lonkar, Abhinav Bhagat, Sd Aasif Sd Manjur
At starting of the Internet of Things (IoT), it is passing around a world, in which diverse kinds of different objects are there connected to the Internet. It contains the use of smart phones, sensors, cameras, and other devices to make over the actions of people and things into data and link it to the Internet. With its capability to model the real world in digital form and accomplish scrutiny and replication in cyberspace, the IoT is able to reveal new value at an unparalleled rate and deliver it as response to the real world. This is set to convey main changes that will lengthen to the structure of industry in addition to the infrastructure of society itself. Therefore although the occurrence of the IoT contributes rise to new value, it besides means the occurrence of new threats. The proposed work covenant with disaster management as well as prevention to manufacturing industry using IoT. System first investigates the threat scenario during general execution of work, and finds the critical situations. The system processes learning approach for identifying such critical situations and execute the output appliances. System utilized multiple input along with output sensor for experiment. The Q-Learning approach has used for updating the policy which can provide the best result with high accuracy.
{"title":"Smart Disaster Management and Prevention using Reinforcement Learning in IoT Environment","authors":"Yogesh S Lonkar, Abhinav Bhagat, Sd Aasif Sd Manjur","doi":"10.1109/ICOEI.2019.8862602","DOIUrl":"https://doi.org/10.1109/ICOEI.2019.8862602","url":null,"abstract":"At starting of the Internet of Things (IoT), it is passing around a world, in which diverse kinds of different objects are there connected to the Internet. It contains the use of smart phones, sensors, cameras, and other devices to make over the actions of people and things into data and link it to the Internet. With its capability to model the real world in digital form and accomplish scrutiny and replication in cyberspace, the IoT is able to reveal new value at an unparalleled rate and deliver it as response to the real world. This is set to convey main changes that will lengthen to the structure of industry in addition to the infrastructure of society itself. Therefore although the occurrence of the IoT contributes rise to new value, it besides means the occurrence of new threats. The proposed work covenant with disaster management as well as prevention to manufacturing industry using IoT. System first investigates the threat scenario during general execution of work, and finds the critical situations. The system processes learning approach for identifying such critical situations and execute the output appliances. System utilized multiple input along with output sensor for experiment. The Q-Learning approach has used for updating the policy which can provide the best result with high accuracy.","PeriodicalId":212501,"journal":{"name":"2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133630294","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：