Pub Date : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032502
Naman Jain, Shreesha Yerragolla, Tanuja Guha, Mohana
The single object detection has been performed by using the concepts of convolution layers. A neural network consists of several different layers such as the input layer, at least one hidden layer, and an output layer. The dataset used for single object detection is the on-road vehicle dataset. This dataset consists of three classes of images which are Heavy, Auto and Light. The dataset consists of images of varying illuminations. The performance metrics has been calculated for the day dataset, evening dataset and night dataset. Multiple object detection has been performed using the You Only Look Once (YOLOv3) algorithm. This approach encompasses a single deep convolution neural network dividing the input into a cell grid and each cell predicts a boundary box and classifies object directly. The dataset used for multiple object detection is the KITTI dataset. It consists of 80 classes out of which five classes has been considered for this project which are: car, bus, truck, and motorcycle and train. Using the Multiple Object Detection concepts, tracking of vehicles was further implemented. The first frame of the video was taken and Multiple object detection was performed and in the further frames of the video the object was tracked using its centroid position. This has been developed using OpenCV and Python using YOLOv3 algorithm for the object detection phase.
利用卷积层的概念进行了单目标检测。神经网络由几个不同的层组成，如输入层、至少一个隐藏层和一个输出层。用于单目标检测的数据集是道路车辆数据集。该数据集由三类图像组成，分别是Heavy, Auto和Light。数据集由不同光照的图像组成。计算了白天数据集、晚上数据集和夜间数据集的性能指标。使用YOLOv3 (You Only Look Once)算法进行多目标检测。该方法包含一个深度卷积神经网络，将输入划分为一个单元格，每个单元格预测一个边界框并直接对对象进行分类。用于多目标检测的数据集是KITTI数据集。它由80个类别组成，其中五个类别已被考虑用于该项目:汽车，公共汽车，卡车，摩托车和火车。利用多目标检测的概念，进一步实现了车辆的跟踪。拍摄视频的第一帧并执行多目标检测，并在视频的其他帧中使用其质心位置跟踪目标。这是使用OpenCV和Python开发的，使用YOLOv3算法进行对象检测阶段。
{"title":"Performance Analysis of Object Detection and Tracking Algorithms for Traffic Surveillance Applications using Neural Networks","authors":"Naman Jain, Shreesha Yerragolla, Tanuja Guha, Mohana","doi":"10.1109/I-SMAC47947.2019.9032502","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032502","url":null,"abstract":"The single object detection has been performed by using the concepts of convolution layers. A neural network consists of several different layers such as the input layer, at least one hidden layer, and an output layer. The dataset used for single object detection is the on-road vehicle dataset. This dataset consists of three classes of images which are Heavy, Auto and Light. The dataset consists of images of varying illuminations. The performance metrics has been calculated for the day dataset, evening dataset and night dataset. Multiple object detection has been performed using the You Only Look Once (YOLOv3) algorithm. This approach encompasses a single deep convolution neural network dividing the input into a cell grid and each cell predicts a boundary box and classifies object directly. The dataset used for multiple object detection is the KITTI dataset. It consists of 80 classes out of which five classes has been considered for this project which are: car, bus, truck, and motorcycle and train. Using the Multiple Object Detection concepts, tracking of vehicles was further implemented. The first frame of the video was taken and Multiple object detection was performed and in the further frames of the video the object was tracked using its centroid position. This has been developed using OpenCV and Python using YOLOv3 algorithm for the object detection phase.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116469359","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032541
Soumyalatha Naveen, Manjunath R. Kounte
In recent years, the tremendous growth of interconnected devices results in a new technology called Internet of Things (IoT). Cloud computing assists the IoT applications to store the data and perform computation in order to control and manage the vast amount of data generated by these IoT devices. But the major challenge in Cloud computing is to meet requirements of many real-time applications of Internet of Things. Whereas, Edge is a computing architecture that helps to communicate, manage, store, and processes the data that quickly returns the response. This is made possible by moving these functionalities closer to the end users. Edge computing and cloud computing are independent as wells as mutually beneficial to many applications. This paper discusses the overview of IoT, communication technologies and protocols required for IoT, data transfer in IoT. Cloud services to store, process and to analyze the data generated from IoT devices are explored.
{"title":"Key Technologies and challenges in IoT Edge Computing","authors":"Soumyalatha Naveen, Manjunath R. Kounte","doi":"10.1109/I-SMAC47947.2019.9032541","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032541","url":null,"abstract":"In recent years, the tremendous growth of interconnected devices results in a new technology called Internet of Things (IoT). Cloud computing assists the IoT applications to store the data and perform computation in order to control and manage the vast amount of data generated by these IoT devices. But the major challenge in Cloud computing is to meet requirements of many real-time applications of Internet of Things. Whereas, Edge is a computing architecture that helps to communicate, manage, store, and processes the data that quickly returns the response. This is made possible by moving these functionalities closer to the end users. Edge computing and cloud computing are independent as wells as mutually beneficial to many applications. This paper discusses the overview of IoT, communication technologies and protocols required for IoT, data transfer in IoT. Cloud services to store, process and to analyze the data generated from IoT devices are explored.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129539603","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032673
Jyothika Subramanian, M. A., Sherin George, D. S, A. S
Fuel cells are emerging as a promising source of green energy that emit electrical energy with almost no pollutants. Fuel cell technology highlights a vital role in the evolution of alternative energy which can be applied for all future applications such as automobile, stationary power plants and to power up devices like mobiles and laptops. One of the most attractive fuel cell types is the polymer electrolytic membrane fuel cells (PEMFCs) due to its ability to operate at low temperature conditions, low corrosion, low weight and quick start-up, which widens its area of applications. There are many operating parameters of PEMFC such as temperature, pressure, flow rate, voltage etc. affecting the overall system efficiency in PEMFC. Controlling the operating parameters of PEMFC is important as it affects the performance, lifetime, working and the response times. In this project, we are focusing on optimization of PEM Fuel Cell. Among these different parameters two are considered to optimize: Flow rate and Pressure. For this optimization problem, different algorithms are compared in this project and the one that best optimizes PEMFC parameters is selected after simulation and analysis. Finally, genetic algorithm is implemented into which holds advantage and from this, selected algorithms are also included into GA. Since, GA is a powerful and dependable innovation to optimize fuel cell stack model. A review of recent research indicates that GAs and other computational intelligence techniques are likely to dominate PEMFC modeling efforts in the future. And the outcome is confirmed to be effective.
{"title":"Performance comparison of Honey Bee Mating Optimization algorithms for Fuel Cell operating parameters","authors":"Jyothika Subramanian, M. A., Sherin George, D. S, A. S","doi":"10.1109/I-SMAC47947.2019.9032673","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032673","url":null,"abstract":"Fuel cells are emerging as a promising source of green energy that emit electrical energy with almost no pollutants. Fuel cell technology highlights a vital role in the evolution of alternative energy which can be applied for all future applications such as automobile, stationary power plants and to power up devices like mobiles and laptops. One of the most attractive fuel cell types is the polymer electrolytic membrane fuel cells (PEMFCs) due to its ability to operate at low temperature conditions, low corrosion, low weight and quick start-up, which widens its area of applications. There are many operating parameters of PEMFC such as temperature, pressure, flow rate, voltage etc. affecting the overall system efficiency in PEMFC. Controlling the operating parameters of PEMFC is important as it affects the performance, lifetime, working and the response times. In this project, we are focusing on optimization of PEM Fuel Cell. Among these different parameters two are considered to optimize: Flow rate and Pressure. For this optimization problem, different algorithms are compared in this project and the one that best optimizes PEMFC parameters is selected after simulation and analysis. Finally, genetic algorithm is implemented into which holds advantage and from this, selected algorithms are also included into GA. Since, GA is a powerful and dependable innovation to optimize fuel cell stack model. A review of recent research indicates that GAs and other computational intelligence techniques are likely to dominate PEMFC modeling efforts in the future. And the outcome is confirmed to be effective.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130644995","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032426
R. N., M. Ajeeth, S. Akash, P. Muralikrishnan
The majority applications such as traffic light control, Elevator, Valet car parking system uses LED displays to show the numbers. Sequential counters are used in those applications in which it represents the numbers in four bit binary coded decimal (BCD) form. In byte oriented systems BCD is a decimal representation of a number directly coded in binary digit by digit. Applications of addition in BCD found in many applications which uses decimal data. This paper proposes an efficient implementation of Binary Coded Decimal Adder (BCDA) using parallel prefix addition which consumes very less power, operating with greater speed and also occupies less area. The proposed adder architecture is simulated using Xilinx 14.2 and power, area and delay results are carried out using cadence software. The proposed adder results in very less power consumption, operating with greater speed and also occupies less area.
{"title":"An Efficient Implementation of Decimal Adder Using Parallel Prefix Addition","authors":"R. N., M. Ajeeth, S. Akash, P. Muralikrishnan","doi":"10.1109/I-SMAC47947.2019.9032426","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032426","url":null,"abstract":"The majority applications such as traffic light control, Elevator, Valet car parking system uses LED displays to show the numbers. Sequential counters are used in those applications in which it represents the numbers in four bit binary coded decimal (BCD) form. In byte oriented systems BCD is a decimal representation of a number directly coded in binary digit by digit. Applications of addition in BCD found in many applications which uses decimal data. This paper proposes an efficient implementation of Binary Coded Decimal Adder (BCDA) using parallel prefix addition which consumes very less power, operating with greater speed and also occupies less area. The proposed adder architecture is simulated using Xilinx 14.2 and power, area and delay results are carried out using cadence software. The proposed adder results in very less power consumption, operating with greater speed and also occupies less area.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134216160","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032548
K. Vengatesan, Abhishek Kumar, V. Karuppuchamy, R. Shaktivel, A. Singhal
Face recognition and biometrics are based on a specific and unique person identification. This procedure is completely dependent on matching the image and other individual image for generating a recognizable proof. This is the one of the best approaches to perform the correlation by choosing facial attributes from the image and from a facial database. In facial recognition calculations ought to have the option to recognize the comparative looking people or ready to isolate the identical twins utilizing face recognition with precision classification. The extract attributes were classified utilizing SVM classifier. The input image of an individual is first identified to be twins or not founded on classification techniques. SVM could be used for both regression and classification challenges. It is commonly used in taxonomy problems. SVM is less computationally intensive and generalizable. Therefore, it would be extensively studied and rapidly developed in recent years.
{"title":"Face Recognition of Identical Twins Based On Support Vector Machine Classifier","authors":"K. Vengatesan, Abhishek Kumar, V. Karuppuchamy, R. Shaktivel, A. Singhal","doi":"10.1109/I-SMAC47947.2019.9032548","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032548","url":null,"abstract":"Face recognition and biometrics are based on a specific and unique person identification. This procedure is completely dependent on matching the image and other individual image for generating a recognizable proof. This is the one of the best approaches to perform the correlation by choosing facial attributes from the image and from a facial database. In facial recognition calculations ought to have the option to recognize the comparative looking people or ready to isolate the identical twins utilizing face recognition with precision classification. The extract attributes were classified utilizing SVM classifier. The input image of an individual is first identified to be twins or not founded on classification techniques. SVM could be used for both regression and classification challenges. It is commonly used in taxonomy problems. SVM is less computationally intensive and generalizable. Therefore, it would be extensively studied and rapidly developed in recent years.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132500214","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032466
G. Muneeswari, A. Puthussery
In the current internet technology, most of the transactions to banking system are effective through online transaction. Predominantly all these e-transactions are done through e-commerce web sites with the help of credit/debit cards, net banking and lot of other payable apps. So, every online transaction is prone to vulnerable attacks by the fraudulent websites and intruders in the network. As there are many security measures incorporated against security vulnerabilities, network thieves are smart enough to retrieve the passwords and break other security mechanisms. At present situation of digital world, we need to design a secured online transaction system for banking using multilevel encryption of blowfish and AES algorithms incorporated with dual OTP technique. The performance of the proposed methodology is analyzed with respect to number of bytes encrypted per unit time and we conclude that the multilevel encryption provides better security system with faster encryption standards than the ones that are currently in use.
{"title":"Multilevel Security and Dual OTP System for Online Transaction Against Attacks","authors":"G. Muneeswari, A. Puthussery","doi":"10.1109/I-SMAC47947.2019.9032466","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032466","url":null,"abstract":"In the current internet technology, most of the transactions to banking system are effective through online transaction. Predominantly all these e-transactions are done through e-commerce web sites with the help of credit/debit cards, net banking and lot of other payable apps. So, every online transaction is prone to vulnerable attacks by the fraudulent websites and intruders in the network. As there are many security measures incorporated against security vulnerabilities, network thieves are smart enough to retrieve the passwords and break other security mechanisms. At present situation of digital world, we need to design a secured online transaction system for banking using multilevel encryption of blowfish and AES algorithms incorporated with dual OTP technique. The performance of the proposed methodology is analyzed with respect to number of bytes encrypted per unit time and we conclude that the multilevel encryption provides better security system with faster encryption standards than the ones that are currently in use.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114916404","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032650
S. A. Selvi, Dr. T. Ananth kumar, R. Rajesh, M. Ajisha
One of the key requirements for inter active application is seamless connectivity. Existing wireless infrastructures is inadequate to support seamless connectivity. Recently Li-Fi networks are introduced to extend the RF connectivity to indoor regions. Light Fidelity (Li-Fi) Networks are becoming popular, due to their support of wide range of un-licensed bandwidth, which enables communication in radio Frequency (RF) sensitive environments, realizes energy-efficient data transmission, and has the potential to boost the capacity of wireless access network through spatial reuse. Due to the rapid development of Li-Fi Based systems they need to co-exist with existing wi-fi based RF systems until its fully evolved. Hence the concept of Wi-Li-Fi is very significant area of research. In this paper we have proposed novel hybrid communication scheme for Wi-Li-Fi environment with an hybrid environment experimental setup. In this scheme a novel M-frame and M-connect frame formats take care of the proper communication mechanism for the proposed model of Wi-Li-Fi environment. Experimental results have revealed that the proposed scheme outperforms the conventional methods for the crowded environments in terms of handover overhead and increase the average throughput. It is concluded that the proposed communication scheme can be able to improve the performance of future seamless interactive applications.
{"title":"An Efficient Communication Scheme for Wi-Li-Fi Network Framework","authors":"S. A. Selvi, Dr. T. Ananth kumar, R. Rajesh, M. Ajisha","doi":"10.1109/I-SMAC47947.2019.9032650","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032650","url":null,"abstract":"One of the key requirements for inter active application is seamless connectivity. Existing wireless infrastructures is inadequate to support seamless connectivity. Recently Li-Fi networks are introduced to extend the RF connectivity to indoor regions. Light Fidelity (Li-Fi) Networks are becoming popular, due to their support of wide range of un-licensed bandwidth, which enables communication in radio Frequency (RF) sensitive environments, realizes energy-efficient data transmission, and has the potential to boost the capacity of wireless access network through spatial reuse. Due to the rapid development of Li-Fi Based systems they need to co-exist with existing wi-fi based RF systems until its fully evolved. Hence the concept of Wi-Li-Fi is very significant area of research. In this paper we have proposed novel hybrid communication scheme for Wi-Li-Fi environment with an hybrid environment experimental setup. In this scheme a novel M-frame and M-connect frame formats take care of the proper communication mechanism for the proposed model of Wi-Li-Fi environment. Experimental results have revealed that the proposed scheme outperforms the conventional methods for the crowded environments in terms of handover overhead and increase the average throughput. It is concluded that the proposed communication scheme can be able to improve the performance of future seamless interactive applications.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116224525","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032457
B. Devi, Noorul Islam
This paper intends to design a novel FER model that includes four phases such as (i) Face Detection, (ii) Feature extraction, (iii) Dimension reduction, and (iv) Classification. Here, Viola Jones (VJ) method is deployed for face detection, which is the initial technique to offer better object detection at real-time. Subsequently, feature extraction is carried out by means of Local Binary Pattern (LBP), and Discrete Wavelet Transform (DWT). As the “curse of dimensionality” seems to be a major fact, the dimension reduction of features is done using Principal Component Analysis (PCA). Finally, the classification is carried out by means of Neural Network (NN) with the new training algorithm called Probability based-Bird Swarm Algorithm (P-BSA), by which the weights are optimized. The performance of the proposed algorithm is done by making the algorithmic analysis. More importantly, the positive integer ($U$) of the proposed algorithm is varied to certain values: 0.5, 1, 1.3, 1.5 and 1.8, respectively.
本文拟设计一种新的FER模型，该模型包括(i)人脸检测、(ii)特征提取、(iii)降维和(iv)分类四个阶段。在这里，Viola Jones (VJ)方法被用于人脸检测，这是提供更好的实时目标检测的初始技术。随后，利用局部二值模式(LBP)和离散小波变换(DWT)进行特征提取。由于“维数诅咒”似乎是一个主要的事实，因此使用主成分分析(PCA)来进行特征的降维。最后，利用神经网络(NN)进行分类，并提出了一种新的训练算法——基于概率的鸟群算法(P-BSA)，通过该算法优化权重。通过对算法的分析，验证了算法的性能。更重要的是，本文算法的正整数$U$被改变为一定的值:分别为0.5、1、1.3、1.5和1.8。
{"title":"Parametric Analysis on Enhanced Facial Emotion Recognition with Weight Optimized Neural Network","authors":"B. Devi, Noorul Islam","doi":"10.1109/I-SMAC47947.2019.9032457","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032457","url":null,"abstract":"This paper intends to design a novel FER model that includes four phases such as (i) Face Detection, (ii) Feature extraction, (iii) Dimension reduction, and (iv) Classification. Here, Viola Jones (VJ) method is deployed for face detection, which is the initial technique to offer better object detection at real-time. Subsequently, feature extraction is carried out by means of Local Binary Pattern (LBP), and Discrete Wavelet Transform (DWT). As the “curse of dimensionality” seems to be a major fact, the dimension reduction of features is done using Principal Component Analysis (PCA). Finally, the classification is carried out by means of Neural Network (NN) with the new training algorithm called Probability based-Bird Swarm Algorithm (P-BSA), by which the weights are optimized. The performance of the proposed algorithm is done by making the algorithmic analysis. More importantly, the positive integer ($U$) of the proposed algorithm is varied to certain values: 0.5, 1, 1.3, 1.5 and 1.8, respectively.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114808212","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032528
J. Omana, M. Moorthi
Diabetes mellitus is the deficiency that is widely spreading nowadays. Manually diagnosing a person with diabetes is more complicated. If diabetes is not treated early it may lead to severe complications. We focus on Electronic Medical Records (EMR) to find out the factors that represent a patient with the risk of developing diabetes. We apply Apriori, Éclat and OPUS association rule mining techniques to generate the risk factors that occur frequently will help greatly in predicting diabetes. These frequent risk factors of each technique are subject to Naïve Bayes with which the chances for developing diabetes mellitus is predicted and the efficiency of each is obtained with respect to Success probability. In evaluating and comparing the previous techniques, OPUS is found to be efficient in predicting the factors that have a high risk of developing diabetes mellitus.
{"title":"Naïve Bayes based Summarizing Ruleset in Prediction of Diabetes Mellitus using Magnum Opus","authors":"J. Omana, M. Moorthi","doi":"10.1109/I-SMAC47947.2019.9032528","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032528","url":null,"abstract":"Diabetes mellitus is the deficiency that is widely spreading nowadays. Manually diagnosing a person with diabetes is more complicated. If diabetes is not treated early it may lead to severe complications. We focus on Electronic Medical Records (EMR) to find out the factors that represent a patient with the risk of developing diabetes. We apply Apriori, Éclat and OPUS association rule mining techniques to generate the risk factors that occur frequently will help greatly in predicting diabetes. These frequent risk factors of each technique are subject to Naïve Bayes with which the chances for developing diabetes mellitus is predicted and the efficiency of each is obtained with respect to Success probability. In evaluating and comparing the previous techniques, OPUS is found to be efficient in predicting the factors that have a high risk of developing diabetes mellitus.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133912997","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 : 2019-12-01DOI: 10.1109/I-SMAC47947.2019.9032448
Ritu Singh, Smruti Rekha Pattanaik, A. Bhuyan, B. Panigrahi, Jyoti Shukla, S. Shukla
Transmission lines are high voltage lines which carry electricity from the power plant to the substation and it is further transmitted to different areas. Distribution lines of low voltage lines for residential and commercial use that bring power from substations to end users. Various types of switching and protecting devices and instruments are used during the transmission and distribution of electrical power. Day by day the demand for electric power is increasing, hence different types of Distributed Generator (DG) such as wind, tidal, solar, diesel generator, etc. are used to increase electrical power generation. The diesel generator is linked to the grid through long transmission networks in this work. Faults must be resolved as soon as possible with respect to customer satisfaction & service quality. The detection method ought to be correct and sharp in order to clarify the fault very soon. The methodology of artificial neural network is a quick-witted method used for classification of fault that can classify the fault. MATLAB and SIMULINK are used for system modeling in this work. The extracted voltage signal fed to the ANN as input which is accurately trained and tested.
{"title":"Classification of Faults in a Distributed Generator Connected Power System Using Artificial Neural Network","authors":"Ritu Singh, Smruti Rekha Pattanaik, A. Bhuyan, B. Panigrahi, Jyoti Shukla, S. Shukla","doi":"10.1109/I-SMAC47947.2019.9032448","DOIUrl":"https://doi.org/10.1109/I-SMAC47947.2019.9032448","url":null,"abstract":"Transmission lines are high voltage lines which carry electricity from the power plant to the substation and it is further transmitted to different areas. Distribution lines of low voltage lines for residential and commercial use that bring power from substations to end users. Various types of switching and protecting devices and instruments are used during the transmission and distribution of electrical power. Day by day the demand for electric power is increasing, hence different types of Distributed Generator (DG) such as wind, tidal, solar, diesel generator, etc. are used to increase electrical power generation. The diesel generator is linked to the grid through long transmission networks in this work. Faults must be resolved as soon as possible with respect to customer satisfaction & service quality. The detection method ought to be correct and sharp in order to clarify the fault very soon. The methodology of artificial neural network is a quick-witted method used for classification of fault that can classify the fault. MATLAB and SIMULINK are used for system modeling in this work. The extracted voltage signal fed to the ANN as input which is accurately trained and tested.","PeriodicalId":275791,"journal":{"name":"2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130545394","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：