Pub Date : 2020-01-01DOI: 10.1109/confluence47617.2020.9058231
{"title":"[Confluence 2020 Front Matter]","authors":"","doi":"10.1109/confluence47617.2020.9058231","DOIUrl":"https://doi.org/10.1109/confluence47617.2020.9058231","url":null,"abstract":"","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122418637","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9057841
Vandana Bharti, Bhaskar Biswas, K. K. Shukla
Nature-inspired computations are commonly recognized optimization techniques that provide optimal solutions to a wide spectrum of computational problems. This paper presents a brief overview of current topics in the field of nature-inspired computation along with their most recent applications in deep learning to identify open challenges concerning the most relevant areas. In addition, we highlight some recent hybridization methods of nature-inspired computation used to optimize the hyper-parameters and architectures of a deep learning framework. Future research as well as prospective deep learning issues are also presented.
{"title":"Recent Trends in Nature Inspired Computation with Applications to Deep Learning","authors":"Vandana Bharti, Bhaskar Biswas, K. K. Shukla","doi":"10.1109/Confluence47617.2020.9057841","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9057841","url":null,"abstract":"Nature-inspired computations are commonly recognized optimization techniques that provide optimal solutions to a wide spectrum of computational problems. This paper presents a brief overview of current topics in the field of nature-inspired computation along with their most recent applications in deep learning to identify open challenges concerning the most relevant areas. In addition, we highlight some recent hybridization methods of nature-inspired computation used to optimize the hyper-parameters and architectures of a deep learning framework. Future research as well as prospective deep learning issues are also presented.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130746725","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9058283
Karanjot Singh, S. Bedi, P. Gaur
Travelling Salesman Problem (TSP) is a real-world Non-deterministic polynomial-time hard – combinatorial optimization problem. Given several points (cities) to be visited, the objective of the problem is to find the shortest possible route (called Hamiltonian Path) that visits each point exactly once and returns back to the starting point. Several exact, approximate and heuristic algorithms have been proposed to solve the TSP. The objective of this paper is to compare 10 such different algorithms on the basis of cost of the path found and time taken to find that solution in order to identify an algorithm which works most efficiently and thus, can be used in practical scenarios. Therefore, the comparative analysis has been made without time constraints as a preliminary test and then with a constraint of 1 second to determine the most efficient algorithm. This algorithm was then used at the core of the web-based tool (a practical use case) developed for release in public domain which helps users find an optimal round-trip route (i.e. Hamiltonian Path) among the points marked on the map. Google Maps API was used for providing map interface and obtaining real-time distance/duration data (matrix) in the web-application front end.
{"title":"Identification of the most efficient algorithm to find Hamiltonian Path in practical conditions","authors":"Karanjot Singh, S. Bedi, P. Gaur","doi":"10.1109/Confluence47617.2020.9058283","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9058283","url":null,"abstract":"Travelling Salesman Problem (TSP) is a real-world Non-deterministic polynomial-time hard – combinatorial optimization problem. Given several points (cities) to be visited, the objective of the problem is to find the shortest possible route (called Hamiltonian Path) that visits each point exactly once and returns back to the starting point. Several exact, approximate and heuristic algorithms have been proposed to solve the TSP. The objective of this paper is to compare 10 such different algorithms on the basis of cost of the path found and time taken to find that solution in order to identify an algorithm which works most efficiently and thus, can be used in practical scenarios. Therefore, the comparative analysis has been made without time constraints as a preliminary test and then with a constraint of 1 second to determine the most efficient algorithm. This algorithm was then used at the core of the web-based tool (a practical use case) developed for release in public domain which helps users find an optimal round-trip route (i.e. Hamiltonian Path) among the points marked on the map. Google Maps API was used for providing map interface and obtaining real-time distance/duration data (matrix) in the web-application front end.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113935441","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9057981
P. Kala, A. Agrawal, Rishi Sharma
Maintaining security and energy consumption of wireless sensor networks is a bit difficult due to non-availability of any central controller. They are also self-configuring in nature. Such types of networks are susceptible to several types of attacks. In this paper, we focus on one such attack called sink hole attack in which the malicious nodes spoof identification of base station and act like base station. The sensor nodes start transmitting data to malicious node instead of base station. This paper proposes a new technique to identify and eliminate such malicious nodes using identity verification to provide a secure environment for communication in the network. Proposed technique is implemented in NS2 and extensive simulations are performed to obtain the results. Results indicate the superiority of the proposed approach over existing approaches in terms of (packet loss, energy consumption, delay and throughput).
{"title":"A Novel Approach for Isolation of Sinkhole Attack in Wireless Sensor Networks","authors":"P. Kala, A. Agrawal, Rishi Sharma","doi":"10.1109/Confluence47617.2020.9057981","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9057981","url":null,"abstract":"Maintaining security and energy consumption of wireless sensor networks is a bit difficult due to non-availability of any central controller. They are also self-configuring in nature. Such types of networks are susceptible to several types of attacks. In this paper, we focus on one such attack called sink hole attack in which the malicious nodes spoof identification of base station and act like base station. The sensor nodes start transmitting data to malicious node instead of base station. This paper proposes a new technique to identify and eliminate such malicious nodes using identity verification to provide a secure environment for communication in the network. Proposed technique is implemented in NS2 and extensive simulations are performed to obtain the results. Results indicate the superiority of the proposed approach over existing approaches in terms of (packet loss, energy consumption, delay and throughput).","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114364843","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9058138
Ruchin Gupta, S. Singh
Code smell is a characteristic of the source code which indicates some serious problem in the code which might affect the quality of the source code. There exists a list of 22 code smells as defined by Martin Fowler. But all these code smells have not been worked upon. Temporary field code smell is one of them, which has not been considered for its detection and refactoring. In this paper, we have reconstructed a motivating example of object oriented JAVA code that indicates the impact of code smell and need to remove temporary field based on metrics and rules.We have proposed a method to detect temporary field code smell based on software metrics derived from data flow and control flow graphs. We also proposed the process of refactoring the code to improve the maintainability. Analysis of results has shown that NFM, NMN, NCF metrics can help to detect Temporary field code smell. Extract class is more appropriate refactoring technique than parameter passing to remove Temporary Field code smell.
{"title":"Using Software Metrics to detect Temporary Field code smell","authors":"Ruchin Gupta, S. Singh","doi":"10.1109/Confluence47617.2020.9058138","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9058138","url":null,"abstract":"Code smell is a characteristic of the source code which indicates some serious problem in the code which might affect the quality of the source code. There exists a list of 22 code smells as defined by Martin Fowler. But all these code smells have not been worked upon. Temporary field code smell is one of them, which has not been considered for its detection and refactoring. In this paper, we have reconstructed a motivating example of object oriented JAVA code that indicates the impact of code smell and need to remove temporary field based on metrics and rules.We have proposed a method to detect temporary field code smell based on software metrics derived from data flow and control flow graphs. We also proposed the process of refactoring the code to improve the maintainability. Analysis of results has shown that NFM, NMN, NCF metrics can help to detect Temporary field code smell. Extract class is more appropriate refactoring technique than parameter passing to remove Temporary Field code smell.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114786568","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}
The world is moving towards new and innovative approaches for making human life much more simpler and easier by automating every task that requires human effort. IoT has been proved to be a boon in this direction. IoT is currently being used in many sectors, automobile being one of them. Need of smart car is not new and various initiatives in research and development has been going on to implement IoT in automobile sector to provide a better vehicular service to consumers. A systematic literature review of IoT in the automobile sector is the major focus of the study. To undertake this review, various studies were taken into consideration. As a result we were able to classify the studies into various sub domains and also were able to identify the current trends and open issues.
{"title":"IoT in Automobile Sector: State of the Art","authors":"Aakarsh Shrivastava, Anshul Bhardwaj, Nitasha Hasteer","doi":"10.1109/Confluence47617.2020.9058202","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9058202","url":null,"abstract":"The world is moving towards new and innovative approaches for making human life much more simpler and easier by automating every task that requires human effort. IoT has been proved to be a boon in this direction. IoT is currently being used in many sectors, automobile being one of them. Need of smart car is not new and various initiatives in research and development has been going on to implement IoT in automobile sector to provide a better vehicular service to consumers. A systematic literature review of IoT in the automobile sector is the major focus of the study. To undertake this review, various studies were taken into consideration. As a result we were able to classify the studies into various sub domains and also were able to identify the current trends and open issues.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124038369","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9057851
Samidha Khatri, Aishwarya Arora, A. Agrawal
In today’s economic scenario, credit card use has become extremely commonplace. These cards allow the user to make payments of large sums of money without the need to carry large sums of cash. They have revolutionized the way of making cashless payments and made making any sort of payments convenient for the buyer. This electronic form of payment is extremely useful but comes with its own set of risks. With the increasing number of users, credit card frauds are also increasing at a similar pace. The credit card information of a particular individual can be collected illegally and can be used for fraudulent transactions. Some Machine Learning Algorithms can be applied to collect data to tackle this problem. This paper presents a comparison of some established supervised learning algorithms to differentiate between genuine and fraudulent transactions.
{"title":"Supervised Machine Learning Algorithms for Credit Card Fraud Detection: A Comparison","authors":"Samidha Khatri, Aishwarya Arora, A. Agrawal","doi":"10.1109/Confluence47617.2020.9057851","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9057851","url":null,"abstract":"In today’s economic scenario, credit card use has become extremely commonplace. These cards allow the user to make payments of large sums of money without the need to carry large sums of cash. They have revolutionized the way of making cashless payments and made making any sort of payments convenient for the buyer. This electronic form of payment is extremely useful but comes with its own set of risks. With the increasing number of users, credit card frauds are also increasing at a similar pace. The credit card information of a particular individual can be collected illegally and can be used for fraudulent transactions. Some Machine Learning Algorithms can be applied to collect data to tackle this problem. This paper presents a comparison of some established supervised learning algorithms to differentiate between genuine and fraudulent transactions.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122144183","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9058014
Lokesh Khurana, Arun Chauhan, Prabhishek Singh
In today’s world, face recognition has turned out to be one of the key aspects of Computer Vision. People are truly adept at perceiving faces and computer complex figures. Indeed, even an entry of time doesn’t influence this ability and along these lines, it would help become as hearty as people in face acknowledgment. Machine acknowledgment of human countenances from still or video pictures has pulled in a lot of consideration in the brain research, picture handling, design acknowledgment, neural science, computer security, and computer vision networks. Face recognition is presumably a standout amongst the most non-meddlesome and easy to use biometric validation techniques right now accessible; a screensaver furnished with face recognition innovation can naturally open the screen at whatever point the approved client approaches the machine. Tech organizations are utilizing these uncommon advances in their items nowadays in all respects now and again. The face is a significant piece of our identity and how individuals recognize us. Face recognition has been one of the fast-growing, exacting and very keen areas in real-time applications. It is seemingly an individual’s most extraordinary physical trademark. While people have had the intrinsic capacity to perceive and recognize various faces for many years, computers are a little difficult to perform so while it’s getting up to speed. Facial recognition programming is intended to pinpoint a face and measure its highlights or various components. Each face has a certain breakthrough, which makes up the distinctive facial highlights. These milestones are implied as nodal focuses. There are around 80 nodal focuses on a human face.
{"title":"Comparative Analysis of OpenCV Recognisers for Face Recognition","authors":"Lokesh Khurana, Arun Chauhan, Prabhishek Singh","doi":"10.1109/Confluence47617.2020.9058014","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9058014","url":null,"abstract":"In today’s world, face recognition has turned out to be one of the key aspects of Computer Vision. People are truly adept at perceiving faces and computer complex figures. Indeed, even an entry of time doesn’t influence this ability and along these lines, it would help become as hearty as people in face acknowledgment. Machine acknowledgment of human countenances from still or video pictures has pulled in a lot of consideration in the brain research, picture handling, design acknowledgment, neural science, computer security, and computer vision networks. Face recognition is presumably a standout amongst the most non-meddlesome and easy to use biometric validation techniques right now accessible; a screensaver furnished with face recognition innovation can naturally open the screen at whatever point the approved client approaches the machine. Tech organizations are utilizing these uncommon advances in their items nowadays in all respects now and again. The face is a significant piece of our identity and how individuals recognize us. Face recognition has been one of the fast-growing, exacting and very keen areas in real-time applications. It is seemingly an individual’s most extraordinary physical trademark. While people have had the intrinsic capacity to perceive and recognize various faces for many years, computers are a little difficult to perform so while it’s getting up to speed. Facial recognition programming is intended to pinpoint a face and measure its highlights or various components. Each face has a certain breakthrough, which makes up the distinctive facial highlights. These milestones are implied as nodal focuses. There are around 80 nodal focuses on a human face.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115478300","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9058196
Subhankar Ganguli, Sanjeev Thakur
Recommender system helps people in decision making by asking their preferences about various items and recommends other items that have not been rated yet and are similar to their taste. A traditional recommendation system aims at generating a set of recommendations based on inter-user similarity that will satisfy the target user. Positive preferences as well as negative preferences of the users are taken into account so as to find strongly related users. Weighted entropy is usedz as a similarity measure to determine the similar taste users. The target user is asked to fill in the ratings so as to identify the closely related users from the knowledge base and top N recommendations are produced accordingly. Results show a considerable amount of improvement in accuracy after using weighted entropy and opposite preferences as a similarity measure.
{"title":"Machine Learning Based Recommendation System","authors":"Subhankar Ganguli, Sanjeev Thakur","doi":"10.1109/Confluence47617.2020.9058196","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9058196","url":null,"abstract":"Recommender system helps people in decision making by asking their preferences about various items and recommends other items that have not been rated yet and are similar to their taste. A traditional recommendation system aims at generating a set of recommendations based on inter-user similarity that will satisfy the target user. Positive preferences as well as negative preferences of the users are taken into account so as to find strongly related users. Weighted entropy is usedz as a similarity measure to determine the similar taste users. The target user is asked to fill in the ratings so as to identify the closely related users from the knowledge base and top N recommendations are produced accordingly. Results show a considerable amount of improvement in accuracy after using weighted entropy and opposite preferences as a similarity measure.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127521145","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 : 2020-01-01DOI: 10.1109/Confluence47617.2020.9057961
Poorvika Singh Negi, A. Garg, Roshan Lal
With the rapid increase in the number of users, there is a rise in issues related to hardware failure, web hosting, space and memory allocation of data, which is directly or indirectly leading to the loss of data. With the objective of providing services that are reliable, fast and low in cost, we turn to cloud-computing practices. With a tremendous development in this technology, there is ever increasing chance of its security being compromised by malicious users. A way to divert malicious traffic away from systems is by using Honeypot. It is a colossal strategy that has shown signs of improvement in security of systems. Keeping in mind the various legal issues one may face while deploying Honeypot on third-party cloud vendor servers, the concept of Honeypot is implemented in a file-sharing application which is deployed on cloud server. This paper discusses the detection attacks in a cloud-based environment as well as the use of Honeypot for its security, thereby proposing a new technique to do the same.
{"title":"Intrusion Detection and Prevention using Honeypot Network for Cloud Security","authors":"Poorvika Singh Negi, A. Garg, Roshan Lal","doi":"10.1109/Confluence47617.2020.9057961","DOIUrl":"https://doi.org/10.1109/Confluence47617.2020.9057961","url":null,"abstract":"With the rapid increase in the number of users, there is a rise in issues related to hardware failure, web hosting, space and memory allocation of data, which is directly or indirectly leading to the loss of data. With the objective of providing services that are reliable, fast and low in cost, we turn to cloud-computing practices. With a tremendous development in this technology, there is ever increasing chance of its security being compromised by malicious users. A way to divert malicious traffic away from systems is by using Honeypot. It is a colossal strategy that has shown signs of improvement in security of systems. Keeping in mind the various legal issues one may face while deploying Honeypot on third-party cloud vendor servers, the concept of Honeypot is implemented in a file-sharing application which is deployed on cloud server. This paper discusses the detection attacks in a cloud-based environment as well as the use of Honeypot for its security, thereby proposing a new technique to do the same.","PeriodicalId":180005,"journal":{"name":"2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127898306","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：