Procedia Computer Science最新文献_第9页

Real-Time Object Recognition For Advanced Driver-Assistance Systems (ADAS) Using Deep Learning On Edge Devices

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2024.12.004

Santhosh Kumar Dhatrika , D. Ramesh Reddy , Nagaram Karan Reddy

引用次数: 0

Assessment of Driver Situation for Control Authority Transition from Conditionally Automated Vehicles using Chassis and Galvanic Skin Response Sensors

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.028

Daghan Dogan , Tankut Acarman

引用次数: 0

Design of a Scoring System for National Fitness Volunteer Services Under Deep Learning

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.025

Abhimeet Singh , Raghav Singla , Pulkit Sodhi , M. Thurai Pandian

{"title":"Design of a Scoring System for National Fitness Volunteer Services Under Deep Learning","authors":"Abhimeet Singh , Raghav Singla , Pulkit Sodhi , M. Thurai Pandian","doi":"10.1016/j.procs.2025.01.025","DOIUrl":"10.1016/j.procs.2025.01.025","url":null,"abstract":"<div><div>This work is developed to establish a comprehensive, scientific, and reasonable national fitness volunteer service scoring system under a long short-term memory (LSTM) recurrent neural network (RNN) algorithm. The LSTM RNN algorithm-based architecture of a three-layer information processing system for human motion recognition is proposed, which includes a data acquisition layer, a data calculation layer, and a data application layer. The LSTM RNN model is verified on the public dataset PAMAP2. Under the LSTM RNN-based information processing system for human motion recognition, the national fitness volunteer service scoring system is established by using the literature method, the survey method, the analytic hierarchy process (AHP) method, and the Delphi method. The candidate indicators are screened regarding the dimension of “service quality”, the indicators are screened by the Delphi method, and the judgment matrix weights and consistency of each included indicator are analyzed. It is found that the information processing system for human motion recognition based on the LSTM RNN algorithm can effectively identify different motion states, such as sitting, lying down, running, walking, and cycling. A national fitness volunteer service scoring system based on the quality of communal sports facilities, services, fitness environment, affiliated sports facilities, and mass fitness service personnel is established under the LSTM RNN-based human motion recognition information processing system. The system includes one number of(#) first-level indicator, five number of(#) second-level indicators, and thirty two number of (#) third-level indicators. In summary, the LSTM RNN-based human motion recognition information processing system can correctly mine the types of fitness exercises, and the established national fitness volunteer service scoring system provides a scientific reference for building a perfect national fitness service system.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 653-664"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376905","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-Driven Real-Time Visual Pollution Detection and Multi-Class Waste Classification in Urban and Textile Landscapes

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.012

Israt Jahan , Md. Faishal Ahmed Rudro , Warda Ruhin Parsub , Seaum Insaniat Swapnil , Ahmed Wasif Reza

{"title":"Deep Learning-Driven Real-Time Visual Pollution Detection and Multi-Class Waste Classification in Urban and Textile Landscapes","authors":"Israt Jahan , Md. Faishal Ahmed Rudro , Warda Ruhin Parsub , Seaum Insaniat Swapnil , Ahmed Wasif Reza","doi":"10.1016/j.procs.2025.01.012","DOIUrl":"10.1016/j.procs.2025.01.012","url":null,"abstract":"<div><div>The expanding issue of visual pollution in urban and textile environments has a negative influence on public health, aesthetics, and overall quality of life. Unmanaged garbage, crowded regions, and poorly maintained structures are some prevalent factors that reduce the aesthetic appeal of cities and industrial areas. The growing problem of visual pollution in urban and textile contexts is the subject of this study. As urbanization and industrial activity rise, sources of visual pollution including uncontrolled garbage, urban congestion, and badly kept industrial zones become increasingly noticeable. Various rubbish categories are classified by the waste sorting system in a publicly accessible dataset. This paper suggests a deep learning-based system for monitoring and identifying visual pollution in real time utilizing cutting-edge deep learning techniques, using developments in deep learning and real-time image identification. The objective of this research is to develop a predictive model for the automatic classification of thirty distinct waste object kinds using SSD (Single Shot Multibox Detector) technology. There are five pre-trained networks as backbone networks for feature extraction: ResNet-50, ResNet-18, MobileNetV3, and EfficientNetV5.When compared to the current conventional approaches, the applied model performs better for classification(ResNet-18) in terms of accuracy 96%, precision 96.3%, recall 95.83%, and F1-score 96.13% and for detection(SSD MobileNet V2) in terms of precision 98.7%, recall 98.5%, and mAP50 98%. The findings imply that the system can successfully increase the efficacy and precision of garbage sorting procedures in practical situations.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 529-538"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376951","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

Hybrid Profile based Multi-document Text Summarisation

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.047

Jean Louis K.E. Fendji , Dounia Donatien , Marcellin Atemkeng

{"title":"Hybrid Profile based Multi-document Text Summarisation","authors":"Jean Louis K.E. Fendji , Dounia Donatien , Marcellin Atemkeng","doi":"10.1016/j.procs.2025.01.047","DOIUrl":"10.1016/j.procs.2025.01.047","url":null,"abstract":"<div><div>The internet has become a crucial component of the daily routines, offering numerous resources and documents for a variety of tasks and information retrieval. However, the large volume of available information often leads to ”information saturation,” posing a challenge to efficient processing and extraction of relevant information. To mitigate this issue, extensive research has been conducted exploring a range of methods, including machine learning and deep learning techniques. A significant advancement in this field is automatic text summarisation, which employs Natural Language Processing (NLP). Despite their efficacy, traditional summarisation methods typically fall short as they fail to consider the unique needs and preferences of individual users. This study introduces a novel, hybrid and profile-based multi-document summarisation method that selects relevant documents according to user queries and preferences, as defined in a user profile. By leveraging NLP algorithms, the proposed system creates personalised summaries by initially extracting sentences from documents that closely match the user’s profile, followed by the generation of a concise abstract summary. The model, specifically developed for French, results in a success rate of 87.5%, and delivering semantically coherent summaries for up to three documents concurrently. This method enhances the user experience by providing succinct and customised information.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 862-872"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376768","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

Energy and Security-Aware Task Scheduling in Fog Computing: A Comparative Analysis of Scheduling Algorithms using IoT

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.002

Nikita Sehgal , Savina Bansal , RK Bansal

{"title":"Energy and Security-Aware Task Scheduling in Fog Computing: A Comparative Analysis of Scheduling Algorithms using IoT","authors":"Nikita Sehgal , Savina Bansal , RK Bansal","doi":"10.1016/j.procs.2025.01.002","DOIUrl":"10.1016/j.procs.2025.01.002","url":null,"abstract":"<div><div>Efficient task scheduling in fog-cloud computing environments is essential for optimizing critical parameters such as energy efficiency, security, and real-time performance. Existing scheduling algorithms like Pure Random (PR) and Earliest Deadline First Random (EDF_R) often lack in generalization as its focus is primarily on individual aspects such as task deadlines or random task assignments, leading to inefficiencies in load balancing, resource utilization, and security management. The Security Aware Scheduling (SAS) algorithm introduces a security-centric approach, prioritizing task assignment based on security requirements, thus ensuring tasks are allocated to nodes that meet or exceed their security needs. The Minimum Energy Security-Aware Scheduling (MESA) algorithm addresses the energy constraints by minimizing energy consumption during task scheduling while maintaining security compliance. Furthermore, the Minimum Response Time Security-Aware Scheduling (MRSA) algorithm aims to reduce response times by optimizing node selection based on both minimum response time and security requirements. Despite these advancements, there is a need for a more comprehensive solution that simultaneously addresses the challenges of energy efficiency, security, and real-time task execution. This research proposes the Optimal Energy-Security Aware Scheduling (OESAS) framework, which integrates these critical factors, providing an adaptive and efficient scheduling solution for heterogeneous fog-cloud systems.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 430-439"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377146","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 Smart Approach for Early Detection of DDoS Attacks: Artificial Neural Network and Random Forest Hybridization

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.008

Ishmam Ahmed Ongshu , Ahmed Wasif Reza , Md. Emad Uddin Aksir , Mohammed Tasiful Alam , Md. Mahfuzul Haq , Farhana Alam

{"title":"A Smart Approach for Early Detection of DDoS Attacks: Artificial Neural Network and Random Forest Hybridization","authors":"Ishmam Ahmed Ongshu , Ahmed Wasif Reza , Md. Emad Uddin Aksir , Mohammed Tasiful Alam , Md. Mahfuzul Haq , Farhana Alam","doi":"10.1016/j.procs.2025.01.008","DOIUrl":"10.1016/j.procs.2025.01.008","url":null,"abstract":"<div><div>Advances in networking technology have made Distributed Denial of Service (DDoS) attacks a real danger to today’s networks. Using logical reasoning, the network flow circumstances may be classified as an attack or a routine state to mimic DDoS detection. This research builds an Artificial Intelligence (AI) system using current improvements in Detection System (DS) and Artificial Neural Network (ANN) algorithms advances. It examines User Datagram Protocol (UDP) foods, ping foods, Transmission Control Protocol (TCP) foods, and land attacks to better understand attack behavior. The categorization model for DDoS attacks is constructed using machine learning approaches. Once trained and evaluated, the model can identify unlabeled benign or malicious network data. Experiments reveal that Decision Tree (DT), Random Forest (RF), Naïve Bayes, and ANN are more accurate in separating ordinary and attack traffic. The ANN is used to extract optimal features from Internet of Things (IoT) Intrusion Detection System (IDS) data. The DS Algorithm, a new RF optimizer, is employed for effective feature selection. Performance evaluation of the resulting model called Artificial Neural Network-Random Forest (ANN-RF), is done using the ”Application DDoS Layer Dataset”. RF was selected because it trains faster than DT. We have got 99.998% better accuracy than 99.930% which is the most efficient accuracy from previous work in this field. As per our results, the proposed work has detected smart accuracy and can detect it in real time while keeping the network connected at the same time. Furthermore, we do thorough empirical comparisons of various optimization techniques utilizing a variety of categorization performance metrics. The results confirmed that the proposed technique had a competitive performance across all datasets.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 490-499"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377152","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

Adaptive Anomaly Detection in Cardiovascular Time Series Through Deep Reinforcement and Active Learning

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2024.12.005

M. Briskilla , T. Dhiliphan Rajkumar Dr.

{"title":"Adaptive Anomaly Detection in Cardiovascular Time Series Through Deep Reinforcement and Active Learning","authors":"M. Briskilla , T. Dhiliphan Rajkumar Dr.","doi":"10.1016/j.procs.2024.12.005","DOIUrl":"10.1016/j.procs.2024.12.005","url":null,"abstract":"<div><div>In this research, a novel framework is proposed for detecting anomalies in time series and medical imaging data, leveraging Deep Reinforcement Learning (DRL) and Active Learning (AL) methodologies. This approach integrates DRL’s dynamic learning capabilities with AL’s efficiency in handling label scarcity, specifically for a cardiovascular disease dataset. This dataset encompasses various features, including demographic (age, gender), anthropometric (height, weight), clinical (blood pressure, cholesterol, glucose levels), and lifestyle factors (smoking, alcohol intake, physical activity), alongside the binary target variable indicating the presence of cardiovascular disease. The proposed framework employs RLAD (Reinforcement Learning for Anomaly Detection) to identify anomalies in the cardiovascular dataset. The RL component is designed to adaptively learn from the continuous action space, efficiently detecting outliers in the clinical and lifestyle features that could indicate potential cardiovascular anomalies. Concurrently, the AL component selectively queries the most informative data points to enhance the labeling process, addressing the challenge of limited labeled data. The results of the method show the efficacy of the proposed approach in accurately identifying anomalies, outperforming traditional methods through methods of precision, recall, and F1-score. This hybrid DRL-AL framework not only improves convergence rates but also adapts effectively to the evolving nature of cardiovascular health data. It highlights the potential of advanced machine learning techniques in enhancing the early identification and diagnosis of cardiovascular diseases, paving the way for improved patient outcomes and healthcare strategies.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 43-52"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376846","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 Hybrid Deep Learning Model with Consensus-Based Feature Selection for DDoS Attacks Detection in SDN

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2025.01.024

Amit V Kachavimath , Narayan D G

{"title":"A Hybrid Deep Learning Model with Consensus-Based Feature Selection for DDoS Attacks Detection in SDN","authors":"Amit V Kachavimath , Narayan D G","doi":"10.1016/j.procs.2025.01.024","DOIUrl":"10.1016/j.procs.2025.01.024","url":null,"abstract":"<div><div>Software-Defined Networking (SDN) increases network flexibility by decoupling network control from hardware. However, this also makes networks more vulnerable to Distributed Denial of Service (DDoS) attacks, that can severely disrupt operations. Existing detection methods typically focus on specific DDoS attacks, highlighting the necessity for more comprehensive detection strategies. Our proposed methodology presents a resilient technique for detecting DDoS attacks by employing a hybrid deep learning approach. Utilizing the InSDN dataset tailored for SDN environments, we employ an advanced feature selection process based on a consensus approach to identify the best eight features, enhancing detection accuracy and efficiency. Cross entropy is utilized at the control plane to detect anomalous activity by computing the entropy between source IP (Internet Protocol) and destination IP data to identify DDoS attacks. Our proposed model integrates Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) networks, achieving a detection accuracy of 99.9%. The CNN provides efficient spatial feature extraction, while LSTM captures temporal dependencies, enhancing the model’s capability to detect complex attack patterns. We also implement a comprehensive evaluation framework, including metrics such as model loss, model accuracy, and confusion matrix.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 643-652"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376904","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

Cycle-Consistent Generative Adversarial Network Based Approach for Denoising CT Scan Images

Procedia Computer Science Pub Date : 2025-01-01 DOI: 10.1016/j.procs.2024.12.037

Vidya Kuraning , Shantala Giraddi , Vishwanath P. Baligar

{"title":"Cycle-Consistent Generative Adversarial Network Based Approach for Denoising CT Scan Images","authors":"Vidya Kuraning , Shantala Giraddi , Vishwanath P. Baligar","doi":"10.1016/j.procs.2024.12.037","DOIUrl":"10.1016/j.procs.2024.12.037","url":null,"abstract":"<div><div>Computed Tomography (CT) plays a pivotal role in detecting and observing various medical conditions. Although low-dose CT scans are frequently chosen to minimize radiation exposure, the image quality is degraded and substantial noise is produced. Important details may be obscured by the added noise. It is challenging for conventional image denoising techniques to strike a compromise between minimizing noise and keeping image details. Hence, minimizing radiation exposure while maintaining image quality makes denoising low-dose CT images a critical challenge in medical imaging.</div><div>This study investigates the application of CycleGAN, a deep learning-based model, for this purpose. CycleGAN model makes use of a U-net based generator and PatchGAN based discriminator. A conventional UNet model and a Gaussian filter were compared with the CycleGAN model. Structural Similarity Index (SSIM) and peak signal-to-noise ratio (PSNR) measures were utilized to assess the models’ functioning in terms of quality of image and structural similarity. The CycleGAN model performed better than the UNet and Gaussian filters, according to the results, striking an improved harmony between detail preservation and noise reduction. The results indicate that CycleGAN is a promising low-dose CT image denoising technique that can be used to improve diagnostic accuracy while exposing users to as little radiation as possible.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"252 ","pages":"Pages 355-364"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376953","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