Pub Date : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00038
Bhuvnesh Khantwal, Reeta Verma
Radio Frequency (RF) energy has turned out to be a modernistic and essentially a green source of energy for the applications requiring low input power. It contributes to a more efficient utilization of RF radiations which would otherwise be lost in the environment. This energy from RF radiations is practically free and ubiquitous and hence it has gained a lot of attention in recent times. This paper focuses at different components of a RF harvesting system, providing a basic idea to achieve efficient power conversion of ambient RF energy to usable DC form. Apart from a clear and understandable summary of the design topologies in RF harvesting, this study reveals some of the critical design considerations, some important design problems and works done to counter them. Through this paper we bring out the current status of the field, new technologies, and developments in system designs. The study indicates that the availability of a number of design options in each system block and a number of conditions to be fulfilled by the harvesting system may become overwhelming to handle. We highlight the major causes of inefficient power conversion and how can they possibly be removed. Research gaps have been identified. Hence, this study sets a reference for the further research in the design of different system blocks for RF energy harvesting systems.
{"title":"A Meta-evaluation of Components of RF Energy Harvesting System","authors":"Bhuvnesh Khantwal, Reeta Verma","doi":"10.1109/INDIACom51348.2021.00038","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00038","url":null,"abstract":"Radio Frequency (RF) energy has turned out to be a modernistic and essentially a green source of energy for the applications requiring low input power. It contributes to a more efficient utilization of RF radiations which would otherwise be lost in the environment. This energy from RF radiations is practically free and ubiquitous and hence it has gained a lot of attention in recent times. This paper focuses at different components of a RF harvesting system, providing a basic idea to achieve efficient power conversion of ambient RF energy to usable DC form. Apart from a clear and understandable summary of the design topologies in RF harvesting, this study reveals some of the critical design considerations, some important design problems and works done to counter them. Through this paper we bring out the current status of the field, new technologies, and developments in system designs. The study indicates that the availability of a number of design options in each system block and a number of conditions to be fulfilled by the harvesting system may become overwhelming to handle. We highlight the major causes of inefficient power conversion and how can they possibly be removed. Research gaps have been identified. Hence, this study sets a reference for the further research in the design of different system blocks for RF energy harvesting systems.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"24 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":"115974998","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/INDIACom51348.2021.00155
Monir Yahya Ali Salmony, Arman Rasool Faridi
Sentiment Analysis (SA), which is also known as Opinion Mining, is a hot-fastest growing research area, making it challenging to follow all its activities. It intends to study peoples' thoughts, feelings, and attitudes about topics, events, issues, entities, individuals, and attributes in social media (e.g., social networking sites, forums, blogs, etc.) expressed by either text comments or tweets. Twitter is one of the world's largest online microblogging platforms that allows its users to freely post texts called tweets. It offers a wealth of information, therefore utilizing SA to analyze this information into positive or negative will assist organizations' and customers' decision-making that will have a significant impact on daily life. SA draws the attention of scientific research in the Natural Language Processing community due to the text structure challenges that may contain negation. Negation is a widespread linguistic structure that changes the text meaning to the opposite and affects text polarity. Therefore, it needs to be considered in sentiment analysis systems. In this paper, supervised machine learning models have been used as a baseline to categorize the sentiment of a Twitter dataset using (Bag of Words) and (Term Frequency Inverse Document Frequency) feature representation methods. Then we applied negation scope identification methods to find negated tokens and investigate how embedding these tokens can raise SA classifiers' accuracy. The results of the sentiment classification task show an improvement once considering these tokens.
情感分析(SA)，也被称为意见挖掘，是一个发展最快的热门研究领域，这使得跟踪其所有活动具有挑战性。它旨在研究人们对社交媒体(如社交网站、论坛、博客等)中的话题、事件、问题、实体、个人和属性的想法、感受和态度，这些想法、感受和态度可以通过文本评论或tweet来表达。Twitter是世界上最大的在线微博平台之一，它允许用户自由发布被称为tweet的文本。它提供了丰富的信息，因此利用情景分析将这些信息分析为积极或消极将有助于组织和客户的决策，这将对日常生活产生重大影响。由于可能包含否定的文本结构挑战，SA引起了自然语言处理界的科学研究的关注。否定是一种广泛存在的语言结构，它使语篇意义向相反的方向转变，影响语篇极性。因此，在情感分析系统中需要考虑它。在本文中，使用监督机器学习模型作为基线，使用(Bag of Words)和(Term Frequency Inverse Document Frequency)特征表示方法对Twitter数据集的情感进行分类。然后，我们应用否定范围识别方法来寻找否定令牌，并研究如何嵌入这些令牌来提高SA分类器的准确率。考虑到这些标记，情感分类任务的结果显示出改进。
{"title":"An Enhanced Twitter Sentiment Analysis Model using Negation Scope Identification Methods","authors":"Monir Yahya Ali Salmony, Arman Rasool Faridi","doi":"10.1109/INDIACom51348.2021.00155","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00155","url":null,"abstract":"Sentiment Analysis (SA), which is also known as Opinion Mining, is a hot-fastest growing research area, making it challenging to follow all its activities. It intends to study peoples' thoughts, feelings, and attitudes about topics, events, issues, entities, individuals, and attributes in social media (e.g., social networking sites, forums, blogs, etc.) expressed by either text comments or tweets. Twitter is one of the world's largest online microblogging platforms that allows its users to freely post texts called tweets. It offers a wealth of information, therefore utilizing SA to analyze this information into positive or negative will assist organizations' and customers' decision-making that will have a significant impact on daily life. SA draws the attention of scientific research in the Natural Language Processing community due to the text structure challenges that may contain negation. Negation is a widespread linguistic structure that changes the text meaning to the opposite and affects text polarity. Therefore, it needs to be considered in sentiment analysis systems. In this paper, supervised machine learning models have been used as a baseline to categorize the sentiment of a Twitter dataset using (Bag of Words) and (Term Frequency Inverse Document Frequency) feature representation methods. Then we applied negation scope identification methods to find negated tokens and investigate how embedding these tokens can raise SA classifiers' accuracy. The results of the sentiment classification task show an improvement once considering these tokens.","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":"132043515","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/INDIACom51348.2021.00124
Lakshya Agarwal, Manan Mukim, Harish Sharma, Amit Bhandari, A. Mishra
It is difficult for teachers to deal with student attendance during classes, whether online or offline since they do it by hand as they use their teaching time. To solve this problem, the smart and insightful attendance management system can be used. Authentication leads to the biggest impediment. The current structure uses biometric authentication, such as voice analysis and signature verification. The study suggested a system of attendance tracking built on facial recognition that can strengthen traditional biometric authentication. The architecture is a relationship between computers and humans and addresses a robust method of authentication. To identify a face, the system uses HOG and SVM and uses an existing database for labeling attendance. The experimental results show the device can automatically identify the faces recorded by the camera accurately and we can detect the face more precisely and efficiently with the use of the SVM classifier.
{"title":"Face Recognition Based Smart and Robust Attendance Monitoring using Deep CNN","authors":"Lakshya Agarwal, Manan Mukim, Harish Sharma, Amit Bhandari, A. Mishra","doi":"10.1109/INDIACom51348.2021.00124","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00124","url":null,"abstract":"It is difficult for teachers to deal with student attendance during classes, whether online or offline since they do it by hand as they use their teaching time. To solve this problem, the smart and insightful attendance management system can be used. Authentication leads to the biggest impediment. The current structure uses biometric authentication, such as voice analysis and signature verification. The study suggested a system of attendance tracking built on facial recognition that can strengthen traditional biometric authentication. The architecture is a relationship between computers and humans and addresses a robust method of authentication. To identify a face, the system uses HOG and SVM and uses an existing database for labeling attendance. The experimental results show the device can automatically identify the faces recorded by the camera accurately and we can detect the face more precisely and efficiently with the use of the SVM classifier.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"56 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":"132313349","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/INDIACom51348.2021.00132
K. Vinutha, H. K. Yogisha
The number of graduates that are produced from the higher education organizations are exponentially increasing which in turn creates the need for early prediction of employability of the students. As the world is moving towards digital adoption, acquisition of skills and enhancement of knowledge plays a vital role, but it is still practised and acquired in a traditional way. The intent is to address this issue by predicting the status of student's employability by considering various factors such as academic score and skill set the student needs to possess as defined by the companies in general using machine learning algorithms. The proposed work used various machine learning algorithms like Support vector machine, Naïve Bayes, Random forest, Bayesian classifier, Artificial neural network, Logistic regression, Gradient boosting and Xgboost for the first phase where the employability of the student was predicted along with the areas in which the student has to improve in order to be eligible for employability. For the final phase, random forest algorithm was used as it predicted the highest accuracy when compared to other algorithms and it predicted the List of companies that a student is eligible for, List of eligible students under a particular role, List of students eligible for a particular company, Generation of report about student's eligibility, Generation of report about percentage of eligibility under each role. This research would be helpful for all kinds of organizations such as government, private and corporations as well as educational organizations.
{"title":"Prediction of Employability of Engineering Graduates using Machine Learning Techniques","authors":"K. Vinutha, H. K. Yogisha","doi":"10.1109/INDIACom51348.2021.00132","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00132","url":null,"abstract":"The number of graduates that are produced from the higher education organizations are exponentially increasing which in turn creates the need for early prediction of employability of the students. As the world is moving towards digital adoption, acquisition of skills and enhancement of knowledge plays a vital role, but it is still practised and acquired in a traditional way. The intent is to address this issue by predicting the status of student's employability by considering various factors such as academic score and skill set the student needs to possess as defined by the companies in general using machine learning algorithms. The proposed work used various machine learning algorithms like Support vector machine, Naïve Bayes, Random forest, Bayesian classifier, Artificial neural network, Logistic regression, Gradient boosting and Xgboost for the first phase where the employability of the student was predicted along with the areas in which the student has to improve in order to be eligible for employability. For the final phase, random forest algorithm was used as it predicted the highest accuracy when compared to other algorithms and it predicted the List of companies that a student is eligible for, List of eligible students under a particular role, List of students eligible for a particular company, Generation of report about student's eligibility, Generation of report about percentage of eligibility under each role. This research would be helpful for all kinds of organizations such as government, private and corporations as well as educational organizations.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"6 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":"131761373","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/INDIACom51348.2021.00014
Sajad Ahmad Kawa, M. ArifWani
One of the prime issues in Convolutional Neural Networks (CNN) is the design of the architecture, which is mainly human crafted, requiring significant time and resources, including expert knowledge, as the number of design choices for CNN is quite large given the number of choices in the parameters of the CNN. In this paper, we analyze the different neural architecture search (NAS) approaches that have been used in recent times, and their issues, and propose a novel method of performing neural architecture search. Our proposed model uses a simplified search space, with a randomized search strategy. We utilize a cell-based architecture search method, with a cell having multiple CNN operations, along with the multiple link options within the operation nodes of a cell. The proposed model is then tested on the MNIST dataset, with significant comparable performance with state of art architecture for MNIST.
{"title":"Randomized Search on a Grid of CNN Networks with Simplified Search Space","authors":"Sajad Ahmad Kawa, M. ArifWani","doi":"10.1109/INDIACom51348.2021.00014","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00014","url":null,"abstract":"One of the prime issues in Convolutional Neural Networks (CNN) is the design of the architecture, which is mainly human crafted, requiring significant time and resources, including expert knowledge, as the number of design choices for CNN is quite large given the number of choices in the parameters of the CNN. In this paper, we analyze the different neural architecture search (NAS) approaches that have been used in recent times, and their issues, and propose a novel method of performing neural architecture search. Our proposed model uses a simplified search space, with a randomized search strategy. We utilize a cell-based architecture search method, with a cell having multiple CNN operations, along with the multiple link options within the operation nodes of a cell. The proposed model is then tested on the MNIST dataset, with significant comparable performance with state of art architecture for MNIST.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"172 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":"117323533","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/INDIACom51348.2021.00058
Charushila Patil, Anita Chaware
Traditionally, for monitoring one's health condition, one has to visit the hospitals and it is very hectic work and uncomfortable for every one especially for the patients and their relatives. For life style disease like hypertension and Blood Pressure, one need to daily monitor their health. Hence, monitoring patients remotely is the need of Era, where there is the huge use of ICT in every sector of life. With the use of information and communication technology, the health care systems have produced timely and reliable systems not only in the hospitals, but can be used now in the homes, and even in the workplace of the patients, which in turn is proving to be cost-effective.The main objective of this paper is to build a wireless heart monitoring system, for monitoring patients at any location, any time. This paper has proposed a model for monitoring heart patients using Internet of Things (IoT), which would help them to keep track of their record in real time. In this system, Sensors are used to continuously monitor the patient's pulse rate and resonance frequency. This real-time monitoring of a patient's heart would reduce the chances of heart attack and will save many lives. The data collected from this systems can be used further for the analysis purpose. This paper shows that many short coming of traditional system can be overcome by using such remote ICT based healthcare system.
{"title":"Heart (Pulse Rate) Monitoring using Pulse Rate Sensor, Piezo Electric Sensor and NodeMCU","authors":"Charushila Patil, Anita Chaware","doi":"10.1109/INDIACom51348.2021.00058","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00058","url":null,"abstract":"Traditionally, for monitoring one's health condition, one has to visit the hospitals and it is very hectic work and uncomfortable for every one especially for the patients and their relatives. For life style disease like hypertension and Blood Pressure, one need to daily monitor their health. Hence, monitoring patients remotely is the need of Era, where there is the huge use of ICT in every sector of life. With the use of information and communication technology, the health care systems have produced timely and reliable systems not only in the hospitals, but can be used now in the homes, and even in the workplace of the patients, which in turn is proving to be cost-effective.The main objective of this paper is to build a wireless heart monitoring system, for monitoring patients at any location, any time. This paper has proposed a model for monitoring heart patients using Internet of Things (IoT), which would help them to keep track of their record in real time. In this system, Sensors are used to continuously monitor the patient's pulse rate and resonance frequency. This real-time monitoring of a patient's heart would reduce the chances of heart attack and will save many lives. The data collected from this systems can be used further for the analysis purpose. This paper shows that many short coming of traditional system can be overcome by using such remote ICT based healthcare system.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"36 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":"133185730","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/INDIACom51348.2021.00106
Iqbal Hasan, S. Rizvi, S. Jain, Sakshi Huria
Semantic modeling of domain knowledge for natural language question-answering based on conversational assistants nowadays has gained popularity with the development of chatbots and voice assistants. Chatbots based on artificial intelligence and interactive technologies are helping organizations and governments to interact and accomplish tasks such as question answering, instant messaging, and promoting any ideas or services. As various government services are provided to fellow citizens through manual interaction or through electronic means. This causes a huge burden of works on various government departments and many queries of the citizens remain unresolved. Nowadays, intelligent chatbots can mimic humans and help users who are not acquainted with technologies to avail answers to their domain-specific queries. However, providing answers with domain-specific capabilities still remain a challenge. In this paper, we present the design of a conversational assistant for answering user queries and administrative support. It is developed using Google Dialogflow and trained on a domain-specific semantic model with intelligent abilities to answer user queries and process service requests. On analysis, we observed that the developed chatbot performs with approx. 95% accuracy in responding to the queries. The chatbot has been deployed in NIC for assistance to user queries regarding e-District services.
{"title":"The AI enabled Chatbot Framework for Intelligent Citizen-Government Interaction for Delivery of Services","authors":"Iqbal Hasan, S. Rizvi, S. Jain, Sakshi Huria","doi":"10.1109/INDIACom51348.2021.00106","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00106","url":null,"abstract":"Semantic modeling of domain knowledge for natural language question-answering based on conversational assistants nowadays has gained popularity with the development of chatbots and voice assistants. Chatbots based on artificial intelligence and interactive technologies are helping organizations and governments to interact and accomplish tasks such as question answering, instant messaging, and promoting any ideas or services. As various government services are provided to fellow citizens through manual interaction or through electronic means. This causes a huge burden of works on various government departments and many queries of the citizens remain unresolved. Nowadays, intelligent chatbots can mimic humans and help users who are not acquainted with technologies to avail answers to their domain-specific queries. However, providing answers with domain-specific capabilities still remain a challenge. In this paper, we present the design of a conversational assistant for answering user queries and administrative support. It is developed using Google Dialogflow and trained on a domain-specific semantic model with intelligent abilities to answer user queries and process service requests. On analysis, we observed that the developed chatbot performs with approx. 95% accuracy in responding to the queries. The chatbot has been deployed in NIC for assistance to user queries regarding e-District services.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"23 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":"114517578","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/INDIACom51348.2021.00002
Praveen Sankarasubramanian, E. Ganesh
Liquid metals are commonly used in chemical industries and nuclear reactors. Since liquid metals may be hazardous, they should be handled very carefully. Careless handling might cause an adverse effect and even disasters. Corrosion and pressure can deteriorate the structure that handles the liquid metals. Leakage of liquid metals can result in ecological disasters and can lead to a humanitarian crisis. Early warning systems, detection of the accident, and prompt steps taken after the incident are the three important phases of monitoring. Continuous monitoring and timely detection of risk reduce the impact caused by the leakage of liquid metal. At present, industries have sensors-based detection. This paper proposes an enhanced version of the existing system. Here, continuous monitoring uses sensors, the Internet of things (IoT), and an artificial intelligence-based system. In this paper, the conventional system is integrated with AI to identify indoor and open-air fire situations. This paper discusses different data collected and investigated data from the videos, sensors, other monitoring systems. And the false-positive results are reduced by using the proposed methodology.
{"title":"Artificial Intelligence-Based Detection System for Hazardous Liquid Metal Fire","authors":"Praveen Sankarasubramanian, E. Ganesh","doi":"10.1109/INDIACom51348.2021.00002","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00002","url":null,"abstract":"Liquid metals are commonly used in chemical industries and nuclear reactors. Since liquid metals may be hazardous, they should be handled very carefully. Careless handling might cause an adverse effect and even disasters. Corrosion and pressure can deteriorate the structure that handles the liquid metals. Leakage of liquid metals can result in ecological disasters and can lead to a humanitarian crisis. Early warning systems, detection of the accident, and prompt steps taken after the incident are the three important phases of monitoring. Continuous monitoring and timely detection of risk reduce the impact caused by the leakage of liquid metal. At present, industries have sensors-based detection. This paper proposes an enhanced version of the existing system. Here, continuous monitoring uses sensors, the Internet of things (IoT), and an artificial intelligence-based system. In this paper, the conventional system is integrated with AI to identify indoor and open-air fire situations. This paper discusses different data collected and investigated data from the videos, sensors, other monitoring systems. And the false-positive results are reduced by using the proposed methodology.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"86 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":"116238188","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/INDIACom51348.2021.00007
Mahmoud Al Ahmad, S. Patra, Suman Bhattacharya, S. Rout, S. Mohanty, Subham Choudhury, Rabindra Kumar Barik
Nowadays, fog assisted cloud is a dominant field of computing where data centers are engaged in providing services to various applications having distinct resource needs and priorities. Congestion in the network causes performance degradation in the applications. Some mission-critical applications need to data transfer even during the congestion period. In Software Defined Networks (SDN) clouds, there is a possibility of reconfiguration of the network flows dynamically to avoid such congestions for critical applications. In this paper, a priority-based virtual machine (VM) placement algorithm is proposed which takes care of the hosts and the network configuration. It tries to place the VMs of high-priority applications closely connected to hosts for reducing the network congestion caused by the other applications. The needed bandwidth for the critical applications is also managed by implementing a priority queue on each network device taken care of by SDN controller. The experiment shows that in multi-tenant applications, the proposed combined approach solves the purpose of high priority applications by allocating sufficient resources and meeting the Quality of Service (QoS) requirements.
{"title":"Priority Based VM Allocation and Bandwidth Management in SDN and Fog Environment","authors":"Mahmoud Al Ahmad, S. Patra, Suman Bhattacharya, S. Rout, S. Mohanty, Subham Choudhury, Rabindra Kumar Barik","doi":"10.1109/INDIACom51348.2021.00007","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00007","url":null,"abstract":"Nowadays, fog assisted cloud is a dominant field of computing where data centers are engaged in providing services to various applications having distinct resource needs and priorities. Congestion in the network causes performance degradation in the applications. Some mission-critical applications need to data transfer even during the congestion period. In Software Defined Networks (SDN) clouds, there is a possibility of reconfiguration of the network flows dynamically to avoid such congestions for critical applications. In this paper, a priority-based virtual machine (VM) placement algorithm is proposed which takes care of the hosts and the network configuration. It tries to place the VMs of high-priority applications closely connected to hosts for reducing the network congestion caused by the other applications. The needed bandwidth for the critical applications is also managed by implementing a priority queue on each network device taken care of by SDN controller. The experiment shows that in multi-tenant applications, the proposed combined approach solves the purpose of high priority applications by allocating sufficient resources and meeting the Quality of Service (QoS) requirements.","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":"123975722","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/INDIACom51348.2021.00143
Kirti Lakra, A. Chug
Software Maintainability is an indispensable characteristic to determine software quality. It can be described as the ease with which necessary changes such as fault correction, performance improvement, addition, or deletion of one or more attributes, etc., can be incorporated. A major purpose of software maintainability is to enable the software to adapt to the changing environment. Machine Learning (ML) algorithms are widely used for Software Maintainability Prediction (SMP). Hence, in the current study, QUES and UIMS, i.e., the two object-oriented datasets are used for SMP. In this study, an attempt has been made to improve the prediction results of five (ML) algorithms, viz., General Regression Neural Network (GRNN), Regularized Greedy Forest (RGF), Gradient Boosting Algorithm (GBA), Multivariate Linear Regression (MLR), and K-Nearest Neighbor (k-NN) on using three different feature selection methods, including the Pearson's Correlation (Filter Method), Backward Elimination (Wrapper Method), and Lasso Regularization (Embedded Method). Feature selection is a procedure to select a set of independent variables that contribute most to the predicted output, hence eliminating the irrelevant features in the data that may reduce the accuracy of an algorithm. The performance of all the models is evaluated using three accuracy measures, i.e., R-Squared, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The results portray an improvement in the prediction accuracies after employing feature selection techniques. It is observed that for the QUES dataset, R-Squared value on an average improves by 157.89%. Also, MAE and RMSE values enhance by 19.59% and 24.90%, respectively, depicting an overall decrease in the error. Similarly, for UIMS dataset, R-Squared value on an average increase by 126.08%, representing an improvement in the accuracy. Further, MAE and RMSE values also improve for the UIMS dataset, by 12.44% and 8.16%, respectively.
{"title":"Development of Efficient and Optimal Models for Software Maintainability Prediction using Feature Selection Techniques","authors":"Kirti Lakra, A. Chug","doi":"10.1109/INDIACom51348.2021.00143","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00143","url":null,"abstract":"Software Maintainability is an indispensable characteristic to determine software quality. It can be described as the ease with which necessary changes such as fault correction, performance improvement, addition, or deletion of one or more attributes, etc., can be incorporated. A major purpose of software maintainability is to enable the software to adapt to the changing environment. Machine Learning (ML) algorithms are widely used for Software Maintainability Prediction (SMP). Hence, in the current study, QUES and UIMS, i.e., the two object-oriented datasets are used for SMP. In this study, an attempt has been made to improve the prediction results of five (ML) algorithms, viz., General Regression Neural Network (GRNN), Regularized Greedy Forest (RGF), Gradient Boosting Algorithm (GBA), Multivariate Linear Regression (MLR), and K-Nearest Neighbor (k-NN) on using three different feature selection methods, including the Pearson's Correlation (Filter Method), Backward Elimination (Wrapper Method), and Lasso Regularization (Embedded Method). Feature selection is a procedure to select a set of independent variables that contribute most to the predicted output, hence eliminating the irrelevant features in the data that may reduce the accuracy of an algorithm. The performance of all the models is evaluated using three accuracy measures, i.e., R-Squared, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The results portray an improvement in the prediction accuracies after employing feature selection techniques. It is observed that for the QUES dataset, R-Squared value on an average improves by 157.89%. Also, MAE and RMSE values enhance by 19.59% and 24.90%, respectively, depicting an overall decrease in the error. Similarly, for UIMS dataset, R-Squared value on an average increase by 126.08%, representing an improvement in the accuracy. Further, MAE and RMSE values also improve for the UIMS dataset, by 12.44% and 8.16%, respectively.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"87 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":"126181523","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：