Recent Advances in Computer Science and Communications最新文献

{"title":"Motion Signal-Based Recognition of Human Activity from Video Stream Dataset Using Deep Learning Approach","authors":"Ram Kumar Yadav, A. Daniel, Vijay Bhaskar Semwal","doi":"10.2174/0126662558278156231231063935","DOIUrl":"https://doi.org/10.2174/0126662558278156231231063935","url":null,"abstract":"\u0000\u0000Human physical activity recognition is challenging in various research\u0000eras, such as healthcare, surveillance, senior monitoring, athletics, and rehabilitation. The use\u0000of various sensors has attracted outstanding research attention due to the implementation of\u0000machine learning and deep learning approaches.\u0000\u0000\u0000\u0000This paper proposes a unique deep learning framework based on motion signals to recognize\u0000human activity to handle these constraints and challenges through deep learning (e.g., Enhance\u0000CNN, LR, RF, DT, KNN, and SVM) approaches.\u0000\u0000\u0000\u0000This research article uses the BML (Biological Motion Library) dataset gathered from\u0000thirty volunteers with four various activities to analyze the performance metrics. It compares\u0000the evaluated results with existing results, which are found by machine learning and deep\u0000learning methods to identify human activity.\u0000\u0000\u0000\u0000This framework was successfully investigated with the help of laboratory metrics with\u0000convolutional neural networks (CNN) and achieved 89.0% accuracy compared to machine\u0000learning methods.\u0000\u0000\u0000\u0000The novel work of this research is to increase classification accuracy with a lower\u0000error rate and faster execution. Moreover, it introduces a novel approach to human activity\u0000recognition in the BML dataset using the CNN with Adam optimizer approach.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"46 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140493261","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":"Komodo Dragon Mlipir Algorithm-based CNN Model for Detection of\u0000Illegal Tree Cutting in Smart IoT Forest Area","authors":"Dr Rajanikanth Aluvalu, Tarunika Sharma, U. V., Arunadevi thirumalraju, K. M. Prasad, Swapna Mudrakola","doi":"10.2174/0126662558282932240119071339","DOIUrl":"https://doi.org/10.2174/0126662558282932240119071339","url":null,"abstract":"\u0000\u0000Trees and woods are vital to preventing climate change and protecting our planet. Sadly, they are constantly being destroyed due to human activities like deforestation, fires, etc.\u0000\u0000\u0000\u0000This research presents and examines an outline for using audio event categorisation to\u0000automatically detect unlawful tree-cutting activity in forests. To monitor large swaths of forest,\u0000the research team proposes using ultra-low-power, minor devices incorporating edgecomputing microcontrollers and long-range wireless communication. An efficient and accurate\u0000audio classification solution based on multi-layer perceptron (MLP) and modified convolutional neural networks (M-CNN) is projected and tailored for cutting. The Komodo Dragon Mlipir\u0000Algorithm (KDMA) is used to pick the best weight for the CNN.\u0000\u0000\u0000\u0000Compared to earlier efforts, the suggested system uses a computing technique to recognise deforestation-related hazards. Various preprocessing methods have been evaluated, with\u0000special attention paid to the trade-off between classification precision and computer resources,\u0000memory, and power use.\u0000\u0000\u0000\u0000Additionally, there have been long-range communication trials performed in natural settings. The experimental consequences demonstrate that the suggested method can notice\u0000and apprise tree-cutting occurrences through smart IoT for efficient and lucrative forest nursing.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"108 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140494038","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":"CNN-FastText Multi-Input (CFMI) Neural Networks for Social Media Clickbait Classification","authors":"Chirag Sharma, Gurneet Singh, Pratibha Singh Muttum, Shubham Mahajan","doi":"10.2174/0126662558283914231221065437","DOIUrl":"https://doi.org/10.2174/0126662558283914231221065437","url":null,"abstract":"\u0000\u0000User-generated video portals, such as YouTube, are facing the chal-lenge of Clickbait. These are used to lure viewers and gain traffic on specific content. The real content inside the video deviates from its title. and a thumbnail. The consequence of this is poor user experience on the platform.\u0000\u0000\u0000\u0000The method employs a self-developed convolutional model, combined with different other video metadata. The thumbnail of any video plays a vital role in gathering user attention; hence, it should also be addressed. Moreover, we believe that word embeddings can help in determining the words that can attract viewers.\u0000\u0000\u0000\u0000The existing identification techniques either use pre-trained models or are restricted to text only. Other video metadata is not considered. To tackle this situation of clickbait, we propose a CNN-Fast Text Multi-Input (CFMI) Neural Network. The method employs a self-developed convolutional model, combined with different other video metadata. The thumbnail of any video plays a vital role in gathering user attention; hence, it should also be addressed. With greater expressiveness, it depicts and captures the parallels between the title and thumb-nail and the video content.\u0000\u0000\u0000\u0000This research also compares the proposed system with the previous works on various parameters. With the usage of the proposed network, the platforms can easily analyze the videos during the uploading stage. In Industry 4.0, every data bit is crucial and must be preserved carefully.\u0000\u0000\u0000\u0000This research also compares the proposed system with the previous works on various parameters. With the usage of the proposed network, the platforms can easily analyze the vide-os during the uploading stage. The future belongs to Post Quantum Cryptography (PWC), we reviewed various encryption standards in this paper.\u0000\u0000\u0000\u0000In Industry 4.0, every data bit is crucial and must be preserved carefully. This in-dustry will surely benefit from the model as it will eliminate false and misleading videos from the platform.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140495748","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 DWT-ERT-based Fault Location for Distribution Network","authors":"Roshni Rahangdale, Archana Gupta","doi":"10.2174/0126662558269531231218052251","DOIUrl":"https://doi.org/10.2174/0126662558269531231218052251","url":null,"abstract":"\u0000\u0000A new DWT-ERT-based fault location method is suggested in the IEEE test feeder.\u0000\u0000\u0000\u0000A new DWT-ERT based fault location method is suggested in IEEE Test Feeder.\u0000\u0000\u0000\u0000The fault location approach in the distribution network has been proposed in this pa-per that utilizes the discrete wavelet transform (DWT) and ensemble regression tree (ERT).\u0000\u0000\u0000\u0000The fault location approach in the distribution network was proposed in this paper utilises the discrete wavelet transform (DWT) and ensemble regression tree (ERT).\u0000\u0000\u0000\u0000The fault location methodology has been validated by simulations conducted on an IEEE 13 bus node test feeder.\u0000\u0000\u0000\u0000The fault location methodology is validated by simulations conducted on an IEEE 13 bus node test feeder.\u0000\u0000\u0000\u0000The results show that the suggested solution has low compute burden and memory re-quirements, and is unaffected by system and fault situations.\u0000\u0000\u0000\u0000In this study, the fault location approach for the distribution system employing DWT and ERT has been proposed.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"348 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140495277","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":"Network Security and Cryptography: Threats, Obstacles and Solutions - A Bibliometric Analysis","authors":"Purushottam Singh, Sandip Dutta, Prashant Pranav","doi":"10.2174/0126662558280232231213053002","DOIUrl":"https://doi.org/10.2174/0126662558280232231213053002","url":null,"abstract":"\u0000\u0000In the wake of escalating cyber threats and the indispensability of robust\u0000network security mechanisms, it becomes crucial to understand the evolving landscape of\u0000cryptographic research. Recognizing the significant contributions and discerning emerging\u0000trends can guide future strategies and technological advancements. Our study endeavors to\u0000shed light on this through a bibliometric analysis of publications in the realms of Network Security\u0000and Cryptography.\u0000\u0000\u0000\u0000To chronicle and synthesize the progression of research methodologies from their inception\u0000to the present day, we undertook a comprehensive Bibliometric Analysis of Network\u0000Security and Cryptography. Our data set was culled from the Clarivate Analytics Web of Science\u0000Database, encompassing 3,897 papers, 603 sources, and 7,886 authors from across the\u0000globe.\u0000\u0000\u0000\u0000Our analysis revealed a marked upsurge in cryptographic research since 1992, with\u0000China standing out as a dominant contributor in terms of publications. Notably, while 'security'\u0000and 'cryptography' emerged as recurrent research themes, there's an observable downtrend in\u0000international collaborations. Our study also highlights pivotal topics shaping the network security\u0000domain, offering insights into the trajectories of research source growth, structural variabilities\u0000in research relevance, and prospective intellectual and collaborative avenues as guided by\u0000authorship patterns.\u0000\u0000\u0000\u0000Cryptographic research is on an upward trajectory, both in volume and significance.\u0000However, the tapering of international collaborations and an evident need to concentrate\u0000on emergent challenges, such as data privacy and innovative network attacks, emerge as notable\u0000insights. This bibliometric review serves as a compass, directing researchers and academicians\u0000towards areas warranting heightened attention, thereby informing the roadmap for future\u0000investigative pursuits.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"118 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140495515","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":"Research on Internet of Medical Things: Systematic Review, Research\u0000Trends and Challenges","authors":"Dinesh Anand, Avinash Kaur, Manpreet Singh","doi":"10.2174/0126662558248187231124052846","DOIUrl":"https://doi.org/10.2174/0126662558248187231124052846","url":null,"abstract":"\u0000\u0000Remote data exchange operations in healthcare are observed, consulted, monitored and treated by the Internet of Medical Things (IoMT). It is an extension of the\u0000Internet of Things (IoT).\u0000\u0000\u0000\u0000At the growing stage of IoT, IoMT is speedily drawing researchers’ interest due to its extensive use in healthcare systems. Smaller and lower-priced\u0000wireless devices with various communication protocols have led to the formation of IoMT.\u0000Healthcare data is exchanged through wireless communication with IoMT. The margining of\u0000IoMT and healthcare can yield multiple benefits in terms of: better quality of life, care services\u0000and developing solution/s at low cost. In this article, a systematic literature review has been\u0000conducted on IoMT.\u0000\u0000\u0000\u0000Authors have thoroughly investigated the different versions of\u0000healthcare 1.0, 2.0, 3.0 and 4.0 as proposed by the healthcare industry. Furthermore, the taxonomy of IoMT has been designed and compared with existing surveys.\u0000\u0000\u0000\u0000This survey\u0000is unique and stands different from the point of view of existing surveys. It supports the future\u0000of IoMT researchers to bring new insight to their researches.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"18 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140496559","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":"Maximizing Emotion Recognition Accuracy with Ensemble Techniques on\u0000EEG Signals","authors":"Sonu Kumar Jha, Dr Somaraju Suvvari, Mukesh Kumar","doi":"10.2174/0126662558279390240105064917","DOIUrl":"https://doi.org/10.2174/0126662558279390240105064917","url":null,"abstract":"\u0000\u0000Emotion is a strong feeling such as love, anger, fear, etc. Emotion can\u0000be recognized in two ways, i.e., External expression and Biomedical data-based. Nowadays,\u0000various research is occurring on emotion classification with biomedical data.\u0000\u0000\u0000\u0000One of the most current studies in the medical sector, gaming-based applications, education\u0000sector, and many other domains is EEG-based emotion identification. The existing research\u0000on emotion recognition was published using models like KNN, RF Ensemble, SVM, CNN, and\u0000LSTM on biomedical EEG data. In general, only a few works have been published on ensemble\u0000or concatenation models for emotion recognition on EEG data and achieved better results than\u0000individual ones or a few machine learning approaches. Various papers have observed that CNN\u0000works better than other approaches for extracting features from the dataset, and LSTM works\u0000better on the sequence data.\u0000\u0000\u0000\u0000Our research is based on emotion recognition using EEG data, a mixed-model deep\u0000learning methodology, and its comparison with a machine learning mixed-model methodology.\u0000In this study, we introduced a mixed model using CNN and LSTM that classifies emotions in\u0000valence and arousal on the DEAP dataset with 14 channels across 32 people.\u0000\u0000\u0000\u0000We then compared it to SVM, KNN, and RF Ensemble, and concatenated\u0000these models with it. First preprocessed the raw data, then checked emotion classification\u0000using SVM, KNN, RF Ensemble, CNN, and LSTM individually. After that with the mixed model\u0000of CNN-LSTM, and SVM-KNN-RF Ensemble results are compared. Proposed model results\u0000have better accuracy as 80.70% in valence than individual ones with CNN, LSTM, SVM, KNN,\u0000RF Ensemble and concatenated models of SVM, KNN and RF Ensemble.\u0000\u0000\u0000\u0000Overall, this paper concludes a powerful technique for processing a range of EEG\u0000data is the combination of CNNs and LSTMs. Ensemble approach results show better performance\u0000in the case of valence at 80.70% and 78.24% for arousal compared to previous research.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":" 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139617259","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":"Enhancing Image Captioning Using Deep Convolutional Generative Adversarial Networks","authors":"Tarun Jaiswal, Manju Pandey, Priyanka Tripathi","doi":"10.2174/0126662558282389231229063607","DOIUrl":"https://doi.org/10.2174/0126662558282389231229063607","url":null,"abstract":"\u0000\u0000Introduction: Image caption generation has long been a fundamental challenge in the\u0000area of computer vision (CV) and natural language processing (NLP). In this research, we present\u0000an innovative approach that harnesses the power of Deep Convolutional Generative Adversarial\u0000Networks (DCGAN) and adversarial training to revolutionize the generation of natural\u0000and contextually relevant image captions.\u0000\u0000\u0000\u0000Our method significantly improves the\u0000fluency, coherence, and contextual relevance of generated captions and showcases the effectiveness\u0000of RL reward-based fine-tuning. Through a comprehensive evaluation of COCO datasets,\u0000our model demonstrates superior performance over baseline and state-of-the-art methods.\u0000On the COCO dataset, our model outperforms current state-of-the-art (SOTA) models\u0000across all metrics, achieving BLEU-4 (0.327), METEOR (0.249), Rough (0.525) and CIDEr\u0000(1.155) scores.\u0000\u0000\u0000\u0000The integration of DCGAN and adversarial training opens new possibilities\u0000in image captioning, with applications spanning from automated content generation to enhanced\u0000accessibility solutions.\u0000\u0000\u0000\u0000This research paves the way for more intelligent\u0000and context-aware image understanding systems, promising exciting future exploration and innovation\u0000prospects.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"61 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140505276","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":"Diagnosis and Management System of Healthcare Resources for Pulmonary Cardio-vascular Diseases Based on Supervised Machine Learning","authors":"Mohamed Mbida","doi":"10.2174/0126662558290514240102050746","DOIUrl":"https://doi.org/10.2174/0126662558290514240102050746","url":null,"abstract":"\u0000\u0000The detection and management of diseases have always been\u0000critical and challenging tasks for healthcare professionals. This necessitates expensive\u0000human and material resources, resulting in prolonged treatment processes. In medicine,\u0000misdiagnosis and mismanagement can significantly contribute to mistreatment and resource\u0000loss. However, machine learning (ML) techniques have demonstrated the potential\u0000to surpass standard patient treatment procedures, aiding healthcare professionals in\u0000better disease management.\u0000\u0000\u0000\u0000Machine learning (RFR)\u0000\u0000\u0000\u0000In this project, the focus is on smart auscultation systems and resource management,\u0000employing Random Forest Regression (RFR). This system collects patients'\u0000physiological values (specifically, photoplethysmography techniques: PPG) as input and\u0000provides disease detection, treatment protocols, and staff assignments with greater precision.\u0000The aim is to enable early disease detection and shorten both staff and disease\u0000treatment durations.\u0000\u0000\u0000\u0000Additionally, this system allows for a general diagnosis of the patient's condition,\u0000swiftly transitioning to a specific one if the initial auscultation detects a suspicious disease.\u0000\u0000\u0000\u0000Compared to the conventional system, it offers quicker diagnoses and satisfactory\u0000real-time patient sorting.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":" 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139624590","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":"Supervised Rank Aggregation (SRA): A Novel Rank Aggregation\u0000Approach for Ensemble-based Feature Selection","authors":"Rahi Jain, Wei Xu","doi":"10.2174/0126662558277567231201063458","DOIUrl":"https://doi.org/10.2174/0126662558277567231201063458","url":null,"abstract":"\u0000\u0000Feature selection (FS) is critical for high dimensional data analysis.\u0000Ensemble based feature selection (EFS) is a commonly used approach to develop FS techniques. Rank aggregation (RA) is an essential step in EFS where results from multiple models\u0000are pooled to estimate feature importance. However, the literature primarily relies on static\u0000rule-based methods to perform this step which may not always provide an optimal feature set.\u0000The objective of this study is to improve the EFS performance using dynamic learning in RA\u0000step.\u0000\u0000\u0000\u0000This study proposes a novel Supervised Rank Aggregation (SRA) approach to allow\u0000RA step to dynamically learn and adapt the model aggregation rules to obtain feature importance.Method: This study proposes a novel Supervised Rank Aggregation (SRA) approach to allow\u0000RA step to dynamically learn and adapt the model aggregation rules to obtain feature importance.\u0000\u0000\u0000\u0000We evaluate the performance of the algorithm using simulation studies and implement\u0000it into real research studies, and compare its performance with various existing RA methods.\u0000The proposed SRA method provides better or at par performance in terms of feature selection\u0000and predictive performance of the model compared to existing methods.\u0000\u0000\u0000\u0000SRA method provides an alternative to the existing approaches of RA for EFS.\u0000While the current study is limited to the continuous cross-sectional outcome, other endpoints\u0000such as longitudinal, categorical, and time-to-event data could also be used.\u0000","PeriodicalId":36514,"journal":{"name":"Recent Advances in Computer Science and Communications","volume":"76 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139388266","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}