Pub Date : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00137
Rudrajit Choudhuri, Amit Paul
A Novel Coronavirus (Sars-Cov-2) struck the world in December, 2019. First Detected in Wuhan, China: this acute respiratory syndrome has spread all over the world at the present moment and has been officially declared as a global pandemic. A massive detrimental effect on global health and economy has been noticed. While researchers are continuously in search of vaccines - detection and proper diagnosis of the virus is as important to limit the spread of the virus. Chest X-Rays (CXRs) is one of the most common types of radiology examination and CXRs of the infected patients can serve as a crucial step in detection of the virus. Having a computer aided automatic diagnosis can minimize human interactions, errors, and workload and maximize efficiency. Various studies have shown that use of artificial intelligence in detection of Covid-19 patients through their CXRs is strongly optimistic. In this paper, a robust and efficient computer aided detection system has been proposed for multiclass image classification of diseases like Covid-19 and Pneumonia using the CXRs of patients. The algorithms have currently achieved desired results which can be further improved when more CXR images are available. The proposed method has outperformed current state of the art algorithms and has achieved 98.3% accuracy with a precision metric of 0.94, and can be used as a fast and reliable preliminary test for detection of the virus.
{"title":"Multi Class Image Classification for Detection Of Diseases Using Chest X Ray Images","authors":"Rudrajit Choudhuri, Amit Paul","doi":"10.1109/INDIACom51348.2021.00137","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00137","url":null,"abstract":"A Novel Coronavirus (Sars-Cov-2) struck the world in December, 2019. First Detected in Wuhan, China: this acute respiratory syndrome has spread all over the world at the present moment and has been officially declared as a global pandemic. A massive detrimental effect on global health and economy has been noticed. While researchers are continuously in search of vaccines - detection and proper diagnosis of the virus is as important to limit the spread of the virus. Chest X-Rays (CXRs) is one of the most common types of radiology examination and CXRs of the infected patients can serve as a crucial step in detection of the virus. Having a computer aided automatic diagnosis can minimize human interactions, errors, and workload and maximize efficiency. Various studies have shown that use of artificial intelligence in detection of Covid-19 patients through their CXRs is strongly optimistic. In this paper, a robust and efficient computer aided detection system has been proposed for multiclass image classification of diseases like Covid-19 and Pneumonia using the CXRs of patients. The algorithms have currently achieved desired results which can be further improved when more CXR images are available. The proposed method has outperformed current state of the art algorithms and has achieved 98.3% accuracy with a precision metric of 0.94, and can be used as a fast and reliable preliminary test for detection of the virus.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"365 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131764175","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00146
Sachin Aggarwal, A. Shal
Today we are living in a world where technology is dominating every sector. The need of automation is increasing day by day and the way of working of the whole world is moving towards the automation of different tasks, which can be done with expert knowledge without any need for human efforts. Due to this, the electricity demand is increasing, but this includes a lot of wastage of electricity that can be saved. The problem which we have identified here is wastage of electricity and to solve this problem we simply need a system which can be used for monitoring the usage of electricity. At first place, this problem looks very simple, and it seems it can be solved easily by some manual work done by a human but, this problem is very complex in reality as the consumer is not able to identify the exact point where electricity is being wasted or else it will be identified once electricity is already wasted which is of no use. These traditional systems are not efficient enough as they cannot identify a potential electricity wastage in advance, for example, if we charge mobile and we forget to turn it off then the charger will consume electricity for several hours and the wastage of electricity will be identified when we turn off charging. To solve these problems many models have been proposed by so many researchers that are BP Neural Network model, EPSO-BP neural network model and there are many more models that were used to solve this problem. The working and drawbacks of previously proposed models will be discussed further in the related work section of this paper. To solve this problem in this paper we have proposed a model that includes 3 sections. In the first section, we have created an IoT based device to measure and store the electricity usage of each appliance. In the second section, we have used the LSTM version of RNN which is very accurate and efficient to create a model that can work in real-time with very high accuracy. In the last section, this paper includes a web app as the frontend of this whole work done in previous sections.
{"title":"Automated Monitoring of Electricity Consumption Using LSTM-RNN and IoT","authors":"Sachin Aggarwal, A. Shal","doi":"10.1109/INDIACom51348.2021.00146","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00146","url":null,"abstract":"Today we are living in a world where technology is dominating every sector. The need of automation is increasing day by day and the way of working of the whole world is moving towards the automation of different tasks, which can be done with expert knowledge without any need for human efforts. Due to this, the electricity demand is increasing, but this includes a lot of wastage of electricity that can be saved. The problem which we have identified here is wastage of electricity and to solve this problem we simply need a system which can be used for monitoring the usage of electricity. At first place, this problem looks very simple, and it seems it can be solved easily by some manual work done by a human but, this problem is very complex in reality as the consumer is not able to identify the exact point where electricity is being wasted or else it will be identified once electricity is already wasted which is of no use. These traditional systems are not efficient enough as they cannot identify a potential electricity wastage in advance, for example, if we charge mobile and we forget to turn it off then the charger will consume electricity for several hours and the wastage of electricity will be identified when we turn off charging. To solve these problems many models have been proposed by so many researchers that are BP Neural Network model, EPSO-BP neural network model and there are many more models that were used to solve this problem. The working and drawbacks of previously proposed models will be discussed further in the related work section of this paper. To solve this problem in this paper we have proposed a model that includes 3 sections. In the first section, we have created an IoT based device to measure and store the electricity usage of each appliance. In the second section, we have used the LSTM version of RNN which is very accurate and efficient to create a model that can work in real-time with very high accuracy. In the last section, this paper includes a web app as the frontend of this whole work done in previous sections.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132281143","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00022
Farah Fayaz Qureshi, M. Wani
This paper presents a new clustering algorithm that is based on non-negative matrix factorization approach. The proposed algorithm is executed in two steps. The first step uses non-negative matrix factorization approach for dimensionality reduction to scale-back the computational burden and noise. The second step performs clustering by using the matrix with reduced dimensions obtained during the step 1.The algorithm is compared with two well-known clustering algorithms namely K-means algorithm and hierarchical clustering algorithm. IRIS dataset is used to compare the three algorithms. The algorithms are compared for the different initial values of parameters associated with clustering algorithms, and by presenting dataset with different order to clustering algorithms. The results indicate that the proposed algorithm produces good clusters while addressing some of the issues related to clustering.
{"title":"A New Clustering Algorithm Based on Non-Negative Matrix Factorization Approach","authors":"Farah Fayaz Qureshi, M. Wani","doi":"10.1109/INDIACom51348.2021.00022","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00022","url":null,"abstract":"This paper presents a new clustering algorithm that is based on non-negative matrix factorization approach. The proposed algorithm is executed in two steps. The first step uses non-negative matrix factorization approach for dimensionality reduction to scale-back the computational burden and noise. The second step performs clustering by using the matrix with reduced dimensions obtained during the step 1.The algorithm is compared with two well-known clustering algorithms namely K-means algorithm and hierarchical clustering algorithm. IRIS dataset is used to compare the three algorithms. The algorithms are compared for the different initial values of parameters associated with clustering algorithms, and by presenting dataset with different order to clustering algorithms. The results indicate that the proposed algorithm produces good clusters while addressing some of the issues related to clustering.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122250782","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00093
N. Jyoti, Sunny Behal
Distributed Denial of Service Attack (DDoS) is a dynamic challenge in the field of network security. These attacks ban legitimate users from utilizing network resources as per their requirements. Intrusion Detection Systems (IDSs) can detect attacks up to a specific limit so it should always be equipped with a new type of defence solutions to combat the latest attacks. In this paper, authors evaluate the performance of various ML classifiers such as BayesNet, Naive Bayes, J48 and Random Forest to detect DDoS attacks. In this methodology, KDDCup99 data set is used for training and testing purpose. Principal Component Analysis (PCA) method is utilized for feature selection, choosing the most optimal features from the data set. By selecting top-ranked 20 features through PCA method, 10 fold cross-validation is done to measure the system's robustness. WEKA machine learning workbench is used to classify various attack types and validate its performance.
{"title":"A Meta-evaluation of Machine Learning Techniques for Detection of DDoS Attacks","authors":"N. Jyoti, Sunny Behal","doi":"10.1109/INDIACom51348.2021.00093","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00093","url":null,"abstract":"Distributed Denial of Service Attack (DDoS) is a dynamic challenge in the field of network security. These attacks ban legitimate users from utilizing network resources as per their requirements. Intrusion Detection Systems (IDSs) can detect attacks up to a specific limit so it should always be equipped with a new type of defence solutions to combat the latest attacks. In this paper, authors evaluate the performance of various ML classifiers such as BayesNet, Naive Bayes, J48 and Random Forest to detect DDoS attacks. In this methodology, KDDCup99 data set is used for training and testing purpose. Principal Component Analysis (PCA) method is utilized for feature selection, choosing the most optimal features from the data set. By selecting top-ranked 20 features through PCA method, 10 fold cross-validation is done to measure the system's robustness. WEKA machine learning workbench is used to classify various attack types and validate its performance.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116473018","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00097
Vishal Gupta, H. Singh
Websites become a primary source of information for most Universities where users can communicate and share their relevant data. Web accessibility means the websites, technologies, and tools developed and designed for all users (abled/ disabled). This paper examines accessibility of 27 University websites belonging to Indian state of Punjab. The website examination is carried out by adapting two major evaluation tools: TAW and WAVE. These tools provide us the results of selected websites status on (Web Content Accessibility Guidelines) WCAG 2.1. The evaluation has also noticed that few recurrent errors are there which shall be eliminated by simply adding accessibility features elements. The overall results of analysis further demanded for improvement regarding the accessibility of these sites. The paper comes up with a list of errors that will benefit user groups having different disabilities when corrected, feature metrics elements, and useful suggestions for improving the accessibility of these websites, so that information provided by these sites shall reach their audience without any barrier.
{"title":"Web Content Accessibility Evaluation of Universities' Websites - A Case Study for Universities of Punjab State in India","authors":"Vishal Gupta, H. Singh","doi":"10.1109/INDIACom51348.2021.00097","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00097","url":null,"abstract":"Websites become a primary source of information for most Universities where users can communicate and share their relevant data. Web accessibility means the websites, technologies, and tools developed and designed for all users (abled/ disabled). This paper examines accessibility of 27 University websites belonging to Indian state of Punjab. The website examination is carried out by adapting two major evaluation tools: TAW and WAVE. These tools provide us the results of selected websites status on (Web Content Accessibility Guidelines) WCAG 2.1. The evaluation has also noticed that few recurrent errors are there which shall be eliminated by simply adding accessibility features elements. The overall results of analysis further demanded for improvement regarding the accessibility of these sites. The paper comes up with a list of errors that will benefit user groups having different disabilities when corrected, feature metrics elements, and useful suggestions for improving the accessibility of these websites, so that information provided by these sites shall reach their audience without any barrier.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116030910","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00117
Ronak Agrawal, D. Sharma
In today's world, fake news identification is a critical problem. Fake news may exist in form of text, images and videos also. There are several techniques exist for fake news detection including forgery detection techniques. This paper discussed the existing forgery techniques used for the fake video detection. In this study, we addressed the existing issues and challenges which make the forgery detection task cumbersome. We have discussed the use of deep neural network, convolutional neural network, biological signal and spatio-temporal neural network for fake video identification. A comparative study of existing techniques, used for forgery detection, is also provided. This exhaustive survey will help the other researchers to combat deep fake problem.
{"title":"A Survey on Video-Based Fake News Detection Techniques","authors":"Ronak Agrawal, D. Sharma","doi":"10.1109/INDIACom51348.2021.00117","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00117","url":null,"abstract":"In today's world, fake news identification is a critical problem. Fake news may exist in form of text, images and videos also. There are several techniques exist for fake news detection including forgery detection techniques. This paper discussed the existing forgery techniques used for the fake video detection. In this study, we addressed the existing issues and challenges which make the forgery detection task cumbersome. We have discussed the use of deep neural network, convolutional neural network, biological signal and spatio-temporal neural network for fake video identification. A comparative study of existing techniques, used for forgery detection, is also provided. This exhaustive survey will help the other researchers to combat deep fake problem.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116022601","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00032
C. Vanipriya, A. Tomar, Gaurav Gupta, Namita Gandotra, S. N. Sheshappa, K. ThammiReddy
The stock market prediction is considered to be the most exigent and challenging problem in the domain of finance and time series prediction. In this paper we present problems pertaining stock market prediction and the models of prediction. Further, we also probe into the effect of global events and their influence on the stock prices. It was found that by incorporating the event information in the prediction model, the prediction's accuracy will be escalated. The overall scope of this work is to provide the predictive power to the investor in the web environment so that he could take informed decision of whether he can invest in the company in question, and yield high profits, by considering the effect of the events occurred. We have established that there is a huge impact of negative news on the stock and also we proved that our method outperformed SVM and NBC techniques.
{"title":"Stock Market Prediction using Sequential Events","authors":"C. Vanipriya, A. Tomar, Gaurav Gupta, Namita Gandotra, S. N. Sheshappa, K. ThammiReddy","doi":"10.1109/INDIACom51348.2021.00032","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00032","url":null,"abstract":"The stock market prediction is considered to be the most exigent and challenging problem in the domain of finance and time series prediction. In this paper we present problems pertaining stock market prediction and the models of prediction. Further, we also probe into the effect of global events and their influence on the stock prices. It was found that by incorporating the event information in the prediction model, the prediction's accuracy will be escalated. The overall scope of this work is to provide the predictive power to the investor in the web environment so that he could take informed decision of whether he can invest in the company in question, and yield high profits, by considering the effect of the events occurred. We have established that there is a huge impact of negative news on the stock and also we proved that our method outperformed SVM and NBC techniques.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114759205","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00040
Z. Haq, Z. Jaffery
The classification of fruits into various classes is becoming inherent to the food processing industry. This paper presents a simulation analysis of effect of activation functions: ReLu, Softmax, sigmoid, and Softplus on the accuracy and latency of the CNN algorithm for classification of fruits: apple, banana and orange. The paper presents the comparative increase of accuracy of different activation functions over the ReLu activation function. The algorithm is trained and tested over a database created by downloading fruit images from the online sources. Also, this paper presents the effect of increasing the number of convolutional layers of the CNN algorithm on the Accuracy and latency of the model. The software used for simulation of the model is Python implemented using Jupyter Notebook over the Anaconda platform.
{"title":"Impact of Activation Functions and Number of Layers on the Classification of Fruits using CNN","authors":"Z. Haq, Z. Jaffery","doi":"10.1109/INDIACom51348.2021.00040","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00040","url":null,"abstract":"The classification of fruits into various classes is becoming inherent to the food processing industry. This paper presents a simulation analysis of effect of activation functions: ReLu, Softmax, sigmoid, and Softplus on the accuracy and latency of the CNN algorithm for classification of fruits: apple, banana and orange. The paper presents the comparative increase of accuracy of different activation functions over the ReLu activation function. The algorithm is trained and tested over a database created by downloading fruit images from the online sources. Also, this paper presents the effect of increasing the number of convolutional layers of the CNN algorithm on the Accuracy and latency of the model. The software used for simulation of the model is Python implemented using Jupyter Notebook over the Anaconda platform.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116559948","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00094
Anil Katiyar, Sunny Behal, Japinder Singh
It is a crucial part of any manufacturing process, either using manual inspection or using today's modern approaches, to detect the defects at the earlier stages to minimise the risks of failure at later stages. In the early days, manual inspection was prone to many errors, leading to a loss of resources and was very time-consuming. Among the other research areas, it is also an active field of research to achieve the perfect balance between high performance and accuracy in defect detection. ResNet, AlexNet, GoogLeNet, and VGGNet has shown remarkable improvement over old traditional designs in this regard. Image processing and deep learning-based object detection model adopted by Google Cloud Machine Learning Engine were widely used for defect detection and had shown somewhat satisfactory results. In this paper, we proposed a model which is successfully trained on the Google Cloud ML Engine. The results have shown that MobileNet-SSD can automatically detect surface defects more frequently, accurately, and precisely compared to conventional deep learning methods. We have used the pre-trained model of MobileNet V2, which is already trained on lakhs of images and is resource-efficient because it needs small memory setup and lower processing power of the CPU.
它是任何制造过程的关键部分，无论是使用人工检查还是使用今天的现代方法，在早期阶段检测缺陷，以尽量减少后期阶段失败的风险。在早期，人工检查容易出现许多错误，导致资源的损失，并且非常耗时。在其他研究领域中，如何在缺陷检测的高性能和准确性之间取得完美的平衡也是一个活跃的研究领域。ResNet, AlexNet, GoogLeNet和VGGNet在这方面比旧的传统设计有了显着的改进。谷歌云机器学习引擎采用的图像处理和基于深度学习的物体检测模型被广泛用于缺陷检测，并取得了令人满意的效果。在本文中，我们提出了一个模型，并成功地在Google Cloud ML Engine上进行了训练。结果表明，与传统的深度学习方法相比，MobileNet-SSD可以更频繁、更准确、更精确地自动检测表面缺陷。我们使用了MobileNet V2的预训练模型，它已经在成千上万的图像上进行了训练，并且资源高效，因为它需要较小的内存设置和较低的CPU处理能力。
{"title":"Automated Defect Detection in Physical Components using Machine Learning","authors":"Anil Katiyar, Sunny Behal, Japinder Singh","doi":"10.1109/INDIACom51348.2021.00094","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00094","url":null,"abstract":"It is a crucial part of any manufacturing process, either using manual inspection or using today's modern approaches, to detect the defects at the earlier stages to minimise the risks of failure at later stages. In the early days, manual inspection was prone to many errors, leading to a loss of resources and was very time-consuming. Among the other research areas, it is also an active field of research to achieve the perfect balance between high performance and accuracy in defect detection. ResNet, AlexNet, GoogLeNet, and VGGNet has shown remarkable improvement over old traditional designs in this regard. Image processing and deep learning-based object detection model adopted by Google Cloud Machine Learning Engine were widely used for defect detection and had shown somewhat satisfactory results. In this paper, we proposed a model which is successfully trained on the Google Cloud ML Engine. The results have shown that MobileNet-SSD can automatically detect surface defects more frequently, accurately, and precisely compared to conventional deep learning methods. We have used the pre-trained model of MobileNet V2, which is already trained on lakhs of images and is resource-efficient because it needs small memory setup and lower processing power of the CPU.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121233418","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00045
Praveen Kumar
The Emerging Technologies are disruptive so, an attempt has been made to study Big Data Analytics (BDA), which is placed under the emerging technology segment by various industry leaders. The research's main objective is to identify BDA's presence in several journal literature. The study considers BDA implementation from the earlier conceptualization to framework design, the utility of technology in various industrial verticals, and its core competencies. It gets accomplished by using the systematic literature review (SLR) of some of the digital repositories as a methodology with specific keywords. As concluded in the study, for over a decade or so, a wide presence has evident through journal articles published and indexed in JSTOR and Science Direct digital repositories. The areas of implementation dominated by Military and Defence studies involving Artificial Intelligence-driven machine learning. Biological science also has its place on the popularity list. Overall, the BDA technologies have an open-source framework, and hence its penetration and spread across the various industry have speeded up in the last decade. The role of both predictive and prescriptive analytics in core competencies of industrial verticals like Education, Medical trials, research, and development centers has also been seen.
{"title":"Big Data Analytics: An Emerging Technology","authors":"Praveen Kumar","doi":"10.1109/INDIACom51348.2021.00045","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00045","url":null,"abstract":"The Emerging Technologies are disruptive so, an attempt has been made to study Big Data Analytics (BDA), which is placed under the emerging technology segment by various industry leaders. The research's main objective is to identify BDA's presence in several journal literature. The study considers BDA implementation from the earlier conceptualization to framework design, the utility of technology in various industrial verticals, and its core competencies. It gets accomplished by using the systematic literature review (SLR) of some of the digital repositories as a methodology with specific keywords. As concluded in the study, for over a decade or so, a wide presence has evident through journal articles published and indexed in JSTOR and Science Direct digital repositories. The areas of implementation dominated by Military and Defence studies involving Artificial Intelligence-driven machine learning. Biological science also has its place on the popularity list. Overall, the BDA technologies have an open-source framework, and hence its penetration and spread across the various industry have speeded up in the last decade. The role of both predictive and prescriptive analytics in core competencies of industrial verticals like Education, Medical trials, research, and development centers has also been seen.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125367265","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：