2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)最新文献

{"title":"Performance Analysis of Python-based Finite Volume Solver ANUGA on Modern Architectures","authors":"Nishant Agrawal, Abhishek Das, Girishchandra R. Yendargaye, T. M. Prabhu, Sandeep K. Joshi, V. V. Shenoi","doi":"10.1145/3474124.3474152","DOIUrl":"https://doi.org/10.1145/3474124.3474152","url":null,"abstract":"The performance analysis of ANUGA, a Python-based finite volume solver on the unstructured grid for shallow water model in two dimensions, on recent Intel and AMD processor-based HPC clusters, form the focus of the present study. The analysis uses three datasets with different resolutions of the underlying triangular mesh for discretizing the region of interest. The computational workload depends on the resolution of the grid, which impacts the computation time required for the simulation of the flow. The factors influencing the parallel performance: workload distribution across different processes, and the bulk of the data exchange (the communication overhead), are studied systematically. This paper is an account of the preliminary study to understand the impact of the memory hierarchy (due to the relative sizes of cache) available on different architecture on the performance of this application.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"55 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114112188","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}

{"title":"Performance Analysis and Evaluation of Routing Protocols for Mobile Adhoc Networks","authors":"G. Nigam","doi":"10.1145/3474124.3474182","DOIUrl":"https://doi.org/10.1145/3474124.3474182","url":null,"abstract":"MANET is a self-ruling assortment of dispersed mobile users. Every host that exists in MANET bear packets for other available hosts and work itself as a source and sink and thus works as a router as well. In MANET, every node action as a router and an end node which may either be a source or destination. Thus, it may happen that the breakdown of some node's operation can enormously crimp the shooting of the network and also influence the elemental opportunity of the network. The present paper compares and simulates significant attributes of one proactive protocol (DSDV) and three reactive protocols (AODV, DSR, TORA) on the criteria of various performance metrics viz. throughput, PDR, nodal delay, scalability, overhead, energy consumption etc. Our simulations demonstrate that proactive protocol (AODV) is best suitable for energy consumption and scalability. AODV has low PDR and steep routing overhead although good throughput and less nodal delay.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122107313","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}

{"title":"Detection of iOS Malware apps based on Significant Services Identification using Borda count","authors":"Neetu Sardana, Arpita Jadhav Bhatt","doi":"10.1145/3474124.3474136","DOIUrl":"https://doi.org/10.1145/3474124.3474136","url":null,"abstract":"In today's era, smartphones are used in daily lives because they are ubiquitous and provide internet connectivity everywhere. The primary reason for the increased usage of smartphones is their functional expandability by installing third-party apps, which span a wide range of categories including books, social networking, instant messaging, etc. Users are compelled to use these feature-rich apps. As a result, the menaces because of these apps, which are potentially risky for user's privacy, have increased. As the information on smartphones is perhaps, more personal than compared to data stored on desktops or computers because smartphones remain with individuals throughout the day and generate contextual data through sensors making it an easy target for intruders. Both Android and iOS follow a permission-based access control mechanism to protect the privacy of their users where an app has to specify the permissions it will use during its run-time. However, the users are unaware whether the app is breaching the user's privacy or sharing it with third-party apps. A lot of work for detecting malicious Android apps using feature selection techniques has been conducted because of the availability of a large permission set and labeled data set. However, minimal work has been conducted for the iOS platform because of the limited permission set, limited labeled data set, and closed-source platform. To combat this problem, in the paper we propose an approach to detect malicious iOS apps based on the app's category using static analysis of app permissions to identify the most significant permission. In this work, several feature ranking techniques such as Correlation, Gain ratio, Info gain, OneR, and ReliefF have been employed on a data set of 1150 iOS apps to identify the riskiest permission across 12 different app categories. To improve the permission selection process and improve the precision of classifiers, the Borda count method has been utilized. Our empirical analysis proves that the proposed approach effectively identifies the top 5 risky permissions within different categories.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128214260","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}

{"title":"A Novel Threshold Secret Sharing Scheme for CP-ABE: A secret sharing approach for CP-ABE","authors":"Shardha Porwal, S. Mittal","doi":"10.1145/3474124.3474137","DOIUrl":"https://doi.org/10.1145/3474124.3474137","url":null,"abstract":"Secret sharing is an integral part of CP-ABE implementation. Currently, Linear Secret Sharing Scheme (LSSS) and Lagrange interpolation are used in existing CP-ABE implementation. Implementation is complex and computational cost is high for generating the access tree structure using these schemes. In this paper, a novel construction of CP-ABE has been developed which implements counting based secret share generation and reconstruction method to generate access tree structure and reconstruct secret shares. The proposed development reduces the cost of access structure generation and reconstruction of secret and improves security by generating the large number of secret shares for small-sized secret. Hence, the new construction enhances the efficiency of encryption and decryption operations of CP-ABE.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129329237","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}

{"title":"AI Driven Identification of Fake News Propagation in Twitter Social Media with Geo-Spatial Analysis","authors":"Priyanshu Sehgal, Bhavika Bhutani, Neha Rastogi, Adwitiya Sinha, Megha Rathi","doi":"10.1145/3474124.3474189","DOIUrl":"https://doi.org/10.1145/3474124.3474189","url":null,"abstract":"With an explosion of online users over social media around the globe, we are no longer strangers to anything and anybody. With increased availability and exchange of information, the propagation of fake news and posts has also increased. Fake news refers to falsified versions of facts that get circulated among the general public to deliberately deceive people rapidly in the network. With the dawn of social networking, the dissemination of fake news has increased a lot due to share-ability, speed and lack of accountability. To address such problems on social media, we have presented an innovative geo-spatial detection mechanism for identifying fake news on Twitter. Our artificial intelligence based proposed strategy is implemented based on machine learning to improve accuracy for ensuring appropriate classification of news being posted on the social media platform so that online users may remain aware of getting duped by fake content.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124769696","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}

{"title":"Machine Unlearning: Its Need and Implementation Strategies","authors":"Aman Tahiliani, Vikas Hassija, V. Chamola, M. Guizani","doi":"10.1145/3474124.3474158","DOIUrl":"https://doi.org/10.1145/3474124.3474158","url":null,"abstract":"Generally when users share information about themselves on some online platforms, they knowingly or unknowingly allow this data to be used by the companies behind these companies for various purposes including selling this information to advertisers as well as using it to better enrich their predictive models. In the event of the user changing their minds on allowing such data about them to be able to be used by the companies, it becomes a strenuous task for the companies to get rid of the influence of this collected data, especially when it has been used to train their machine learning models. Recent legislations by governing bodies, like the European Union, grant people the right to choose where data about them may be used, including a right to have their data and its resulting influence be completely removed from a company’s databases and machine learning models. To be able to do this at scale new machine unlearning solutions need to be invented. In this paper, we look at some of these early models of machine unlearning strategies that have been proposed.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131148025","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}

{"title":"Medical Prescription and Report Analyzer","authors":"Bipin Kumar Rai, Shivani Sharma, Anjani Kumar, Akash Goyal","doi":"10.1145/3474124.3474165","DOIUrl":"https://doi.org/10.1145/3474124.3474165","url":null,"abstract":"More often than not, we find prescriptions are not properly written which are being handed over to patients and the diagnostic reports handed can't be monitored without the doctor's involvement due to lack of medical knowledge. This has resulted in putting the patient's safety at risk, and also sometimes there is an unavailability of doctors for the required time for monitoring of reports because of which there is also a danger to patients’ life. The objective of this Medical Prescription and Report Analyzer (MPRA) model is to help patients get an easy understanding of their report and prescribed medicine by addressing the important challenge of extraction of handwritten text data from images, analyzing it using test data then giving a much-refined output. Handwriting Character Recognition (HCR) technique, as well as Printer Character Recognition (PCR) technique, have been used to identify both handwritten as well as printed text in prescription and report, and techniques such as image processing to refine image to give an accurate output.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133198336","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}

{"title":"Parental Security Control: A tool for monitoring and securing children's online activities.","authors":"Milind Kumar, Vaibhav Dwivedi, Anubhav Sanyal, Parth Bhatt, Rupesh Koshariya","doi":"10.1145/3474124.3474196","DOIUrl":"https://doi.org/10.1145/3474124.3474196","url":null,"abstract":"The use of internet browsing through laptops, desktop systems, and mobile phones by kids has augmented manifold during this COVID-19 pandemic for online education. Since there is an inordinateness of objectionable content on the internet, the kids might get exposed to this content typically accidentally whereas sometimes intentionally. Therefore, it becomes vital to observe the web activities of kids by the parents. The lack of parental control, guidance & inability of parents to monitor their kids throughout the whole time frame motivated us to style and develop a parental control and management tool. Initially, we conducted a background study to understand the state-of-the-art tools currently available in the market and compare those tools in terms of functionality, accuracy, efficiency, usability, and security. We also studied the benchmark requirements set by the parents and the freedom of access expressed by the children. We have implemented a front-end solution and an Android App that follows the default criteria set by us. As the internet is a highly dynamic space, we have used a Machine Learning-based approach to classify the website dynamically to provide dynamicity to the tool. The very basic idea is to scrape a website's content once the user enters the URL and then apply an appropriate algorithm to classify the same, essentially converting the problem into a multi-class classification problem. The result indicates that our tool efficiently blocks inappropriate content and facilitates parents with features to control and monitor their children's online activity and help mitigate the risk of cyber threats for children of the current age.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123893938","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}

{"title":"Study on Blockchain Scalability Solutions","authors":"Shobha Tyagi, Madhumita Kathuria","doi":"10.1145/3474124.3474184","DOIUrl":"https://doi.org/10.1145/3474124.3474184","url":null,"abstract":"The adoption of blockchain and Distributed Ledger Technology is continuously increasing and offering solutions to various application areas. In the last few decades, much more developments in various features are seen to improve the performance, but still scalability is becoming the bottleneck for the performance enhancement. The scalability problem further leads to severe delays and high costs in a bitcoin network. Nowadays, the real-time transactions in cryptocurrencies need to be scaled up from seven transactions per second to thousands of transactions per second to handle real-life problems in the field of visa, healthcare, flights, etc. In this paper, a detailed study on the scalability issues, Proof of Work, and Practical Byzantine Fault Tolerant in blockchain was given. It also explored and analyzed the recent promising research areas in blockchain scalability such as net neutrality, sharding, side-chain, and off-chain scaling through blockchain distributed networks along with their effects.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114762784","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}

{"title":"Explainable AI for Deep Learning Based Disease Detection","authors":"S. Kinger, V. Kulkarni","doi":"10.1145/3474124.3474154","DOIUrl":"https://doi.org/10.1145/3474124.3474154","url":null,"abstract":"Deep learning in computer vision has shown remarkable success in the performance of detection systems for plant diseases. However, due to the complexity and deeply nested structure of these models, these are still considered as black-box and explanations are not intuitive for human users. Many researchers have developed deep neural architectures for plant disease detection but have not provided classification explanations. To be used in practical applications, our model needs to explain why the model classified a given image. Explainable Artificial Intelligence (XAI) provides algorithms that can generate human-understandable explanations of AI decisions. In this paper, we summarize recent developments in XAI techniques, develop a plant disease detection system, and most importantly an explainable AI method named Gradient-weighted Class Activation Mapping ++ (GradCAM++) is used to locate the disease and highlight the most important regions on the leaves contributing towards the classification.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117143364","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}