Recent Advances in Computer Science and Communications最新文献

{"title":"Flood Mapping and Damage Analysis Using Multispectral Sentinel-2 Satellite Imagery and Machine Learning Techniques","authors":"Rashmi Saini, Shivam Rawat, Suraj Singh, Prabhakar Semwal","doi":"10.2174/0126662558309143240529104953","DOIUrl":"https://doi.org/10.2174/0126662558309143240529104953","url":null,"abstract":"\u0000\u0000Floods are among the deadliest natural calamities, devastating ecosystems and human lives worldwide. In India, Bihar is a state grappling with economic hardships\u0000and faces severe agricultural devastation due to recurring floods, destroying crops and natural\u0000resources, which significantly impacts local farmers. This research addresses the critical need\u0000to deeply understand the flood dynamics of selected study areas.\u0000\u0000\u0000\u0000This research presents a case study that focuses on leveraging Remote Sensing tools\u0000and Machine Learning techniques for comprehensive flood mapping and damage analysis in\u0000Gopalganj District, Bihar, India, using remote sensing data. More specifically, this research\u0000presents three major objectives: (i) Flood damage mapping and change analysis before and after the flood using the Sentinel-2 satellite dataset, (ii) Evaluation of the impact of integrating\u0000spectral indices on the accuracy of classification, (iii) Identification of most robust predictor\u0000spectral indices for the classification.\u0000\u0000\u0000\u0000The Sentinel-2 satellite dataset encompasses 13 bands with resolutions of 10m, 20m,\u0000and 60m. Here, four spectral bands (NIR, Red, Green, and Blue) with the finest resolution of\u000010m have been selected for this study. These bands are integrated with four spectral indices,\u0000namely Normalized Difference Water Index (NDWI), MNDWI (Modified NDWI), Normalized\u0000Difference Vegetation Index (NDVI), and Soil Adjusted Vegetation Index (SAVI). Two ML\u0000classifiers, namely Support Vector Machine (SVM) and Random Forest (RF) have been employed for pixel-based supervised classification.\u0000\u0000\u0000\u0000Results have shown that RF outperformed and worked well in extracting water bodies\u0000and flood-damaged areas effectively. The results demonstrated that RF obtained (Overall Accuracy (OA)= 89.54% and kappa value (ka) = 0.872) and SVM reported (OA= 87.69%, ka=\u00000.849) for pre-crisis data, whereas, for post-crisis, RF reported (OA=91.54%, ka = 0.897),\u0000SVM reported (OA= 89.77%, ka= 0.875).\u0000\u0000\u0000\u0000It was reported that the integration of spectral indices improved the OA by\u0000+3.41% and +2.86% using RF and SVM, respectively. The results of this study demonstrated\u0000that the waterbody area increased from 12.72 to 88.23 km2,\u0000as shown by the RF classifier. The\u0000variable importance computation results indicated that MNDWI is the most important predictor\u0000variable, followed by NDWI. This study recommends the use of these two predictor variables\u0000for flood mapping.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":" 42","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141833376","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":"Efficacy of Keystroke Dynamics-Based User Authentication in the Face of Language Complexity","authors":"Sandip Dutta, Utpal Roy, Soumen Roy","doi":"10.2174/0126662558309578240705101526","DOIUrl":"https://doi.org/10.2174/0126662558309578240705101526","url":null,"abstract":"\u0000\u0000This study investigates the impact of language complexity on Keystroke\u0000Dynamics (KD) and its implications for accurate KD-based user authentication system\u0000performance in smartphones.\u0000\u0000\u0000\u0000This research meticulously analyzes keystroke patterns using 160 volunteers, including\u0000both frequently typed and infrequently typed texts. Our analysis of 12 anomaly detection\u0000algorithms reveals that a simple text-based KD system consistently outperforms its complex\u0000counterpart with superior Equal Error Rates (EERs).\u0000\u0000\u0000\u0000As a result, the Scaled Manhattan anomaly detector achieves an EER of 2.48% for\u0000simple text and an improvement over 2.98% for complex text. The incorporation of soft biometrics\u0000further enhances algorithmic performance, emphasizing strategies to build resilience\u0000into KD-based user authentication systems.\u0000\u0000\u0000\u0000Throughout this study, the importance of text complexity is emphasized, and innovative\u0000pathways are introduced to strengthen KD-based user authentication paradigms.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"55 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141653423","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":"Innovation in Knowledge Economy: A Case Study of 3D Printing's Rise in\u0000Global Markets and India","authors":"Aman Semalty, R. Agrawal","doi":"10.2174/0126662558304420240705114015","DOIUrl":"https://doi.org/10.2174/0126662558304420240705114015","url":null,"abstract":"\u0000\u00003D printing is a rapidly growing technology with features of enhanced\u0000customizability, reduced errors, zero material waste, reduced costs, and quick turnaround\u0000times. In this work, the data were collected from the Derwent Innovation and Web of Science\u0000databases for patent and publication search, respectively.\u0000\u0000\u0000\u0000The results were critically\u0000analysed and correlated with the global and Indian market growth. USA (with 5 out of the top\u0000ten patent contributing companies), China, Germany, France, and Taiwan were determined to\u0000be the top countries with the maximum number of patents on 3D printing technology. Both patents and publications exhibited consistent growth until 2011. From 2012 onwards, the rate of\u0000patent filings began to surpass that of academic publications, indicating a shift in the dynamics.\u0000\u0000\u0000\u0000This trend has continued over the years, leading to a notable difference between the\u0000number of patents (19,322) and publications (10,571) in the year 2022. India has been found to\u0000rank 8th in 3D printing innovation and research, globally.\u0000\u0000\u0000\u0000In this study, the global\u0000and Indian market growth has been observed and the opportunities and challenges for the Indian market have been critically studied.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"73 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141658372","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":"Cognitive Inherent SLR Enabled Survey for Software Defect Prediction","authors":"Anurag Mishra, Ashish Sharma","doi":"10.2174/0126662558243958231207094823","DOIUrl":"https://doi.org/10.2174/0126662558243958231207094823","url":null,"abstract":"\u0000\u0000Any software is created to help automate manual processes most of the\u0000time. It is expected from the developed software that it should perform the tasks it is supposed to do.\u0000\u0000\u0000\u0000More formally, it should work in a deterministic manner. Further, it should be capable of\u0000knowing if any provided input is not in the required format. Correctness of the software is inherent\u0000virtue that it should possess. Any remaining bug during the development phase would hamper the\u0000application's correctness and impact the software's quality assurance. Software defect prediction is\u0000the research area that helps the developer to know bug-prone areas of the developed software.\u0000\u0000\u0000\u0000Datasets are used using data mining, machine learning, and deep learning techniques to\u0000achieve study. A systematic literature survey is presented for the selected studies of software defect\u0000prediction.\u0000\u0000\u0000\u0000Using a grading mechanism, we calculated each study's grade based on its compliance\u0000with the research validation question. After every level, we have selected 54 studies to include in\u0000this study.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"18 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141710879","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":"An Era of Communication Technology Using Machine Learning\u0000Techniques in Medical Imaging","authors":"Vikash Yadav","doi":"10.2174/266625581705240522173248","DOIUrl":"https://doi.org/10.2174/266625581705240522173248","url":null,"abstract":"<jats:sec>\u0000<jats:title/>\u0000<jats:p/>\u0000</jats:sec>","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"58 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141711294","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 Artificial Intelligence in Internet-of-Medical Things","authors":"Y. Djenouri, Mohammad Kamrul Hasan, Rutvij H. Jhaveri","doi":"10.2174/266625581704240522171142","DOIUrl":"https://doi.org/10.2174/266625581704240522171142","url":null,"abstract":"<jats:sec>\u0000<jats:title/>\u0000<jats:p/>\u0000</jats:sec>","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"1 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141234124","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":"Schema Extraction in NoSQL Databases: A Systematic Literature Review","authors":"Saad Belefqih, A. Zellou, Mouna Berquedich","doi":"10.2174/0126662558273437231204061106","DOIUrl":"https://doi.org/10.2174/0126662558273437231204061106","url":null,"abstract":"\u0000\u0000Nowadays, NoSQL databases have taken on an increasingly important\u0000role in the storage of massive data within companies. Due to a common property called\u0000schema-less, NoSQL databases offer great flexibility, particularly for the storage of data in different\u0000formats. However, despite their success in data storage, schema-less databases are a major\u0000obstacle in areas requiring precise knowledge of this schema, especially in the field of data\u0000integration.\u0000\u0000\u0000\u0000This study presents a Systematic Literature Review (SLR) to explore, evaluate, and\u0000discuss relevant existing research and endeavors using novel schema extraction approaches.\u0000Furthermore, we conducted this study using a well-defined methodology to examine and study\u0000the problem of schema extraction from NoSQL databases.\u0000\u0000\u0000\u0000Our research results highlight and emphasize the scheme extraction approaches and\u0000provide knowledge to researchers and practitioners by proposing schema extraction approaches\u0000and their limitations, which contributes to inventing new, more efficient approaches.\u0000\u0000\u0000\u0000In our future work, inspired by the recent advances in quantum computing and the\u0000emergence of post-quantum cryptography (PQC), we aim to propose a schema extraction approach\u0000that blends cutting-edge technologies with a strong focus on database security.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"391 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140454208","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":"Energy and Performance Centric Resource Allocation Framework in\u0000Virtual Machine Consolidation Using Reinforcement Learning Approach","authors":"Madala Guru Brahmam, Vijay Anand R","doi":"10.2174/0126662558289911240206071447","DOIUrl":"https://doi.org/10.2174/0126662558289911240206071447","url":null,"abstract":"\u0000\u0000Virtual machines are used to reduce cloud platform application performance, management\u0000costs, and access irregularities. Virtual machines are frequently vulnerable to delays,\u0000overburdening workloads, and other obstacles while consolidating and migrating servers. To\u0000significantly disperse loads among virtual machines, dynamic consolidation techniques are implemented\u0000to control energy dissipation, monitor overloading, and address underloading problems.\u0000\u0000\u0000\u0000The process of consolidation involves more calculations and resources in order\u0000to transfer services between virtual machines, provided that Service Level Agreements are observed.\u0000\u0000\u0000\u0000The suggested approach promotes the use of cutting-edge architecture to combine\u0000virtual machines, and, therefore, strike a balance between performance and energy requirements.\u0000The main design considerations for the suggested Dynamic Weightage algorithm,\u0000which includes the clustering approach in relation to reinforcement learning approaches, are\u0000overall resource needs and Performance to Power Ratio (PPR). A cluster of ideal virtual machines\u0000is created, and resources are distributed according to performance and energy requirements.\u0000Virtual machine resource requests are converted into a matching relationship factor,\u0000which represents the individual hosts while taking PPR into account. The overall workload associated\u0000with virtual machine consolidation is also provided by these estimations. It is noted\u0000that there is little energy trade-off and that performance is maintained at a nominal level across\u0000the cluster. The architecture is put into practice throughout offline platforms, which are dispersed\u0000ecosystems that allow for increased system performance and scaling.\u0000\u0000\u0000\u0000The CloudSim simulator is used to validate the system using datasets that are obtained\u0000from PlanetLab. According to the data, energy saving has produced yields of up to 47% and\u0000promising quality of service attributes.\u0000\u0000\u0000\u0000The validation of the system is performed using the CloudSim simulator with datasets\u0000from PlanetLab. The results indicate significant energy conservation, up to 47%, along\u0000with promising quality of service parameters. The proposed architecture is compared with other\u0000state-of-the-art algorithms for distributed architectures and heterogeneous environments,\u0000showcasing its efficiency. The conclusion emphasizes the prioritization of VM consolidation\u0000and energy efficiency in the proposed architecture, which has been tested on a Proliant G7-\u0000based data center using a variety of hosts. Notably, the CloudSim Toolkit is highlighted as outperforming\u0000OpenStack-based techniques in simulation results.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"12 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139963043","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 Comprehensive Study of Deep Learning Techniques to Predict\u0000Dissimilar Diseases in Diabetes Mellitus Using IoT","authors":"Ramesh Balaraju, Kuruva Lakshmanna","doi":"10.2174/0126662558291849240118104616","DOIUrl":"https://doi.org/10.2174/0126662558291849240118104616","url":null,"abstract":"\u0000\u0000India has evaluated 77 million people with diabetes, which makes it the second most\u0000elaborated disease in the world. Diabetes is a chronic syndrome that occurs with increased sugar\u0000levels in the blood cells. Once diabetes is diagnosed and untreated by physicians, it may affect\u0000the internal organs slowly, so there is a necessity for early prediction. Popular Machine\u0000Learning (ML) techniques existed for the early prediction of diabetes mellitus. A significant\u0000perspective is to be considered in total management by machine learning algorithms, but it is\u0000not a good enough model to predict DMT2. Therefore, Deep learning (DL) models are utilized\u0000to produce enhanced prediction accuracy. The ML methods are evaluated and analyzed distinctly\u0000on the inconspicuous test information. DL is a subpart of ML with many data sets recurrently\u0000used to train the system. IoT was another emerging technology-based Healthcare Monitoring\u0000System (HMS) built to support the vision of patients and doctors in the healthcare domain.\u0000This paper aims to survey ML and DL techniques relevant to Dissimilar Disease prediction\u0000in Diabetes Mellitus. Finally, by doing a study on it, deep learning methods performed\u0000well in predicting the dissimilar diseases related to diabetes and also other disease predictions\u0000using m-IoT devices. This study will contribute to future deep-learning ideas that will assist in\u0000detecting diabetic-related illnesses with greater accuracy.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"151 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140481315","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":"Cross-Attention Based Text-Image Transformer for Visual Question\u0000Answering","authors":"Mahdi Rezapour","doi":"10.2174/0126662558291150240102111855","DOIUrl":"https://doi.org/10.2174/0126662558291150240102111855","url":null,"abstract":"\u0000\u0000Visual question answering (VQA) is a challenging task that requires\u0000multimodal reasoning and knowledge. The objective of VQA is to answer natural language\u0000questions based on corresponding present information in a given image. The challenge of VQA\u0000is to extract visual and textual features and pass them into a common space. However, the\u0000method faces the challenge of object detection being present in an image and finding the relationship between objects.\u0000\u0000\u0000\u0000In this study, we explored different methods of feature fusion for VQA, using pretrained models to encode the text and image features and then applying different attention\u0000mechanisms to fuse them. We evaluated our methods on the DAQUAR dataset.\u0000\u0000\u0000\u0000We used three metrics to measure the performance of our methods: WUPS, Acc, and\u0000F1. We found that concatenating raw text and image features performs slightly better than selfattention for VQA. We also found that using text as query and image as key and value performs worse than other methods of cross-attention or self-attention for VQA because it might\u0000not capture the bidirectional interactions between the text and image modalities\u0000\u0000\u0000\u0000In this paper, we presented a comparative study of different feature fusion methods for VQA, using pre-trained models to encode the text and image features and then applying\u0000different attention mechanisms to fuse them. We showed that concatenating raw text and image\u0000features is a simple but effective method for VQA while using text as query and image as key\u0000and value is a suboptimal method for VQA. We also discussed the limitations and future directions of our work.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"53 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140483218","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}