Procedia Computer Science最新文献_第5页

Integrating Human Motion Dynamics in CNN Architecture to Recognize Human Activity from Different Camera Angles

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.045

Kishan Kesari Gupta , Joo-Ho Lee , Parag Ravikant Kaveri , Prashant Awasthi

{"title":"Integrating Human Motion Dynamics in CNN Architecture to Recognize Human Activity from Different Camera Angles","authors":"Kishan Kesari Gupta , Joo-Ho Lee , Parag Ravikant Kaveri , Prashant Awasthi","doi":"10.1016/j.procs.2025.01.045","DOIUrl":"10.1016/j.procs.2025.01.045","url":null,"abstract":"<div><div>Human Activity Recognition (HAR) is a crucial component of computer vision, with applications in human-computer interaction and surveillance. As the need for HAR technology keeps increasing, so does the desire for solutions that can help people train by showcasing professional moves. For instance, new recruits can be successfully trained in particular fighting skills by observing the activities of seasoned soldiers. In order to increase the accuracy and dependability of HAR systems, this study investigates the incorporation of human motion dynamics into Convolutional Neural Network (CNN) architectures. This study enhances CNN’s ability to capture both spatial and temporal features by incorporating dynamic changes in human movement as additional inputs, which results in a more complex comprehension of human activity. A significant identification of complex human activity and frequent movement is made viable by the architecture’s proficiency in uniting motion data with classic graphic information. Experimentations operated on prominent datasets reveal that motion dynamics significantly enhance recognition exactness, mainly under challenging circumstances like occlusions, inconsistent viewpoints, and complicated actions. This study highlights how motion-informed CNN architectures can enhance HAR classification and open new avenues for multimodal action recognition research.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 841-850"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Efficient DDoS Attack Detection in SDN using Multi-Feature Selection and Ensemble Learning

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2024.12.026

Amit V Kachavimath , Narayan D G

{"title":"An Efficient DDoS Attack Detection in SDN using Multi-Feature Selection and Ensemble Learning","authors":"Amit V Kachavimath , Narayan D G","doi":"10.1016/j.procs.2024.12.026","DOIUrl":"10.1016/j.procs.2024.12.026","url":null,"abstract":"<div><div>Software-defined networking (SDN) has significantly enhanced network agility by decoupling network control from hardware devices. This architectural shift exposes SDN infrastructures to increased risks from Distributed Denial of Service (DDoS) attacks, which can severely disrupt network services and render them unavailable to legitimate users. Despite the existence of various techniques for detecting specific types of DDoS attacks, there remains a need for more comprehensive work capable of accurately identifying multiple attack categories. We have addressed the gap by proposing a robust DDoS attack detection method in the SDN. We utilize advanced machine learning (ML) algorithms to analyze the InSDN dataset, employing advanced feature extraction techniques to improve detection accuracy and efficiency. Three feature extraction methods, Se-lectKBest, ANOVA F-value scores, and feature importance scores from RandomForest Classifier, were used to select the best ten features from 81. This feature selection, combined with ensemble learning, achieved an accuracy of 99.9%. The Receiver Operating Characteristic (ROC) curve, confusion matrix, and K-fold cross-validation were used to evaluate the performance of the proposed model.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 241-250"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Secured Internet of Drone Model with Distributed Protocols

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.026

Janani V S , Adwitiya Mukhopadhyay

引用次数: 0

Lamport Blum Shub Signcryptive Extreme Learning Machine for Secure Transmission of Digital Images

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.033

V. Prabavathi (Ms.) , M. Sakthi Dr.

{"title":"Lamport Blum Shub Signcryptive Extreme Learning Machine for Secure Transmission of Digital Images","authors":"V. Prabavathi (Ms.) , M. Sakthi Dr.","doi":"10.1016/j.procs.2025.01.033","DOIUrl":"10.1016/j.procs.2025.01.033","url":null,"abstract":"<div><div>Image transmission refers to sending or transferring digital images from one location to another, typically over a network or communication channel across various domains, including telecommunications, multimedia messaging, surveillance systems, medical imaging, remote sensing, etc. However, with growing popularity of digital skills, ensuring safety and integrity of transmitted images has become a significant concern. For increasing security, Machine learning and cryptographic techniques have been discussed. Nevertheless, confidentiality during image transmission faces major challenges. Proposed Lamport Blum ShubSigncryptive Extreme Learning (LBSSEL) Method is introduced for secured image transmission with minimal time consumption. The Extreme Learning machine comprises different layers. Several natural images gathered as of dataset. The input layer receives these images for secure transmission. The proposed cryptographic method performs key generation, signcryption, as well as unsigncryption. Lamport One-Time Digital signature method applied in first hidden layer to generate key pairs. Signcryption carried out in second hidden layer which includes encryption and digital signature. For secured transmission, an encrypted image (i.e., cipher image) as well as signature broadcast to receiver to preserve input image. In third hidden layer, unsigncryption process carried out for receiving original image by authorized users through signature verification and decryption. Finally, confidentiality is improved during image transmission at the output layer. Simulation estimated with dissimilar factors. Outcomes of LBSSSEL model in terms of achieving maximum PSNR, confidentiality during transmission, with minimal time consumption when compared with existing approaches.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 728-737"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reduction of Mismatch Power Loss in a Partially Shaded Photovoltaic System Using the OTR

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.038

Shivangi Mittal , Amit Mittal , Dhiraj Nitnawre

引用次数: 0

Education Literacy Rate Forecasting Using Ensemble Models

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.011

Sheshang Degadwala , Jagdish Solanki Dr. , Maganbhai N Parmar Dr. , Dhairya Vyas

引用次数: 0

Genome Motif Discovery in Zika Virus: Computational Techniques and Validation Using Greedy Method

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2024.12.028

Pushpa Susant Mahapatro , Jatinderkumar R. Saini , Shraddha Vaidya

{"title":"Genome Motif Discovery in Zika Virus: Computational Techniques and Validation Using Greedy Method","authors":"Pushpa Susant Mahapatro , Jatinderkumar R. Saini , Shraddha Vaidya","doi":"10.1016/j.procs.2024.12.028","DOIUrl":"10.1016/j.procs.2024.12.028","url":null,"abstract":"<div><div>Identifying patterns in the genome sequences is an essential yet tricky task in Bioinformatics. It provides information about gene activity and gene functionality. In Deoxyribose Nucleic Acid (DNA) sequence analysis, computational approaches like Greedy motif search can be applied for motif identification. It finds recurring patterns called motifs by iteratively selecting the most promising sequence of a specified length from each DNA string. The selected string maximizes the scoring function and hence is selected. First, a set of initial motifs is selected for each set in the input string. Then, a subsequence that best aligns with the selected string is selected for the next iteration. The score is calculated and needs to be minimized. The validation of the obtained motif is also performed. This study focuses on applying the algorithm to identify patterns in the genome sequence of the Zika virus. In finding conserved patterns in the Zika virus genome sequence, the Greedy motif search is known for its efficiency and precision. The Greedy motif search results are compared with Gibbs sampler method of motif identification. This study adds knowledge of the viral genome and suggests new treatment development methods by confining these patterns.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 260-269"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning and Explainable AI Based Blast Wave Pressure Prediction in IoV Applications

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2024.12.029

Mahmood Hussain Mir , Judeson Antony , Sulaiman Syed Mohamed , Soumi Dhar , Pragya , Danish Fayaz

{"title":"Deep Learning and Explainable AI Based Blast Wave Pressure Prediction in IoV Applications","authors":"Mahmood Hussain Mir , Judeson Antony , Sulaiman Syed Mohamed , Soumi Dhar , Pragya , Danish Fayaz","doi":"10.1016/j.procs.2024.12.029","DOIUrl":"10.1016/j.procs.2024.12.029","url":null,"abstract":"<div><div>Predicting blast wave pressure is crucial for enhancing safety and response strategies in Internet of Vehicles (IoV) applications, particularly in the context of urban environments and high-risk areas. This paper presents a novel deep learning model designed for predicting blast frequencies in BLEVE (Boiling Liquid Expanding Vapor Explosion) scenarios. The article evaluates several activation functions, including ReLU, Mish, ELU, Silu, and Leaky ReLU, to determine their effectiveness in improving model accuracy. The results indicate that the Mish activation function achieves slightly lower Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores on the test dataset, with Train RMSE at 0.075 and Test RMSE at 0.099. The Silu activation function also demonstrates strong performance, yielding a Train RMSE of 0.074 and Test RMSE of 0.095, alongside high R<sup>2</sup> scores, indicating a good fit to the data. The paper further explores the interpretability of the model’s predictions using the LIME framework, revealing insights into how sensor positions and vapor heights influence blast frequency predictions. This research explores the potential of deep learning techniques in enhancing safety measures and predictive capabilities in hazardous scenarios, contributing valuable insights to the field of risk assessment and management in IoV applications.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 270-278"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optical Motion Detection Language Generator: A Survey

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2024.12.010

R. Vijaya Saraswathi , Mohanavamshi Devulapally , Sai Rakshita Narsingh , Harshitha Temberveni , Naga Nithin Katta

{"title":"Optical Motion Detection Language Generator: A Survey","authors":"R. Vijaya Saraswathi , Mohanavamshi Devulapally , Sai Rakshita Narsingh , Harshitha Temberveni , Naga Nithin Katta","doi":"10.1016/j.procs.2024.12.010","DOIUrl":"10.1016/j.procs.2024.12.010","url":null,"abstract":"<div><div>This is a comprehensive review of sign language detection and interpretation technologies, addressing the increasing need for effective communication solutions for individuals with speech disorders. The objective is to analyze existing literature, categorizing findings into key areas: sign language detection methodologies leveraging smartphones and advancements in machine and deep learning approaches. Methodologically, a systematic literature review (SLR) spanning from 2012 to July 2023 was conducted, focusing on publications that explore machine and deep learning techniques for sign language detection and interpretation via smartphones. The survey identifies gaps in current research, particularly in the generalizability of findings across different regional languages and the exclusion of less prevalent sign languages. It also highlights the need for enhanced accessibility solutions specific to diverse speech disorders. Future directions proposed include the development of more inclusive and accurate detection systems, potentially integrating advancements in machine learning and smartphone technology. Proactive measures in sign language detection and interpretation are emphasized as crucial for improving accessibility and communication for communities with specific speech needs.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 90-99"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing Railway Signaling and Platform Management with LoRaWAN, RFID and Automation Technologies

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.015

Samarth Sarvade , Vijaykumar Shirwal , Parth Kugaonkar , Kartik Mudgonda

{"title":"Optimizing Railway Signaling and Platform Management with LoRaWAN, RFID and Automation Technologies","authors":"Samarth Sarvade , Vijaykumar Shirwal , Parth Kugaonkar , Kartik Mudgonda","doi":"10.1016/j.procs.2025.01.015","DOIUrl":"10.1016/j.procs.2025.01.015","url":null,"abstract":"<div><div>The integration of advanced communication and automation technologies provides a transformative approach to enhancing railway signaling and platform management. This system utilizes real-time data exchange to optimize train positioning, platform allocation, and overall network operations. Leveraging long-range, low-power communication protocols such as LoRaWAN, the solution enables seamless and reliable coordination between trains and stations, reducing delays, enhancing safety, and improving the precision of platform management. Additionally, RFID technology is employed to enhance accuracy in monitoring train movements and platform occupancy, ensuring smoother and more efficient operations. The system architecture facilitates more effective resource management by automating key processes such as train scheduling and platform allocation, ultimately minimizing energy consumption and lowering operational costs. With improved communication accuracy, faster response times, and robust system reliability, the proposed solution addresses critical challenges faced by modern railway systems. This approach is designed to be scalable and adaptable to the evolving demands of large railway networks, including Indian Railways, providing a future-proof strategy for optimizing performance and sustainability. By modernizing traditional operations and improving efficiency, the system offers a comprehensive upgrade for both freight and passenger rail services, ensuring long-term operational resilience.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 557-566"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0