检索结果-内蒙古大学图书馆

Photoplethysmography Bio-Signal Extraction for Classifying Diabetes Mellitus Diseases Using Pretrained Deep Learning Networks

引用

SN Computer Science 2025年第2期6卷 1-14页

作者： Tarmizi, Syaidatus Syahira Ahmad Suriani, Nor Surayahani Mohd, Mohd Norzali Bin Hj Bagchi, Susama Debnath, Sanjoy Kumar Shah, Syed Mehr Ali Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Johor Parit Raja Malaysia Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India College of Computing & Information Sciences University of Technology & Applied Sciences Musandem Oman

This study investigates the association between the presence of blood glucose and blood pressure variations to determine an individual’s health. It classified diabetes mellitus by using a publicly available PPG-BP dataset of 72 subjects. Increasing diabetes trends due to undiagnosed disease were overcome through continuous finger cuff-based blood pressure measurements via photoplethysmography to extract diabetes related features including the baseline anthropometrical characteristics and signal morphology. The variations in blood pressure obtained from single channel PPG are processed to extract signal information and the results which are the STFT transformed version of the signal as the input data to investigate the meaningful patterns of the original raw, filtered and their derivatives between healthy and diabetic individuals. This can be followed by the state of the art of pretrained deep learning networks such as DenseNet121, DenseNet169, EfficientNetB0, EfficientNetB1, InceptionResNetV2, ResNet50, ResNet101 and Xception which were discussed in the comparative analysis that can be effectively used for classification on the respective sets of signals. The result indicates that InceptionResNetV2 and Xception networks outperform the rest of the pretrained deep learning used in the study with the highest recorded accuracy, precision and recall values which making them the most effective networks for classification problems. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blood glucose Blood pressure Diabetes mellitus Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

“Cropmaster” - Real-Time Coordination of Multirobot Systems for Autonomous Crop Harvesting: Design and Implementation

“Cropmaster” - Real-Time Coordination of Multirobot System...

引用

Power Electronics, Computer Applications (ICPECA), IEEE International Conference on

作者： Isuranga Pramod Avishka Mallawa Arachchi Chemuthu Rashen Gayan Chinthaka Dinithi Pandithage Narmada Gamage Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331533694

ISBN: (纸本)9798331533700

The CropMaster is an autonomous rover system designed to enhance Scotch Bonnet production by improving disease management, crop sorting, autonomous navigation, and real-time environmental monitoring. Equipped with sensors to measure sunlight, humidity, pH, NPK content, and soil moisture, the rover securely transmits analyzed data to a web-based dashboard. LIDAR technology enables efficient autonomous navigation, allowing the rover to move around fields and avoid obstacles. The MQTT protocol facilitates communication between multiple rovers, preventing duplicate measurements and ensuring data is sent to the dashboard for comprehensive data collection across large areas. TensorFlow's machine learning models allow the rover to accurately assess crop health and detect early-stage diseases, followed by automated pesticide and fertilizer application through a spraying system. To maintain reliability, the rover's operations, including data transfer and task execution, are continuously monitored for Quality of Service (QoS). All collected data is stored in the cloud for long-term access. Built with a lightweight aluminum and plastic chassis and robotic arms, the rover is designed for adaptability and operational efficiency, aiming to improve crop management and increase yields across extensive agricultural fields.

关键词： Protocols Soil measurements Robot kinematics Crops Quality of service Real-time systems Autonomous robots Farming Diseases Sorting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Timeliness and Accuracy in Blood Transportation through Drone technology in Saudi Arabia’s Government Clinic

Enhancing Timeliness and Accuracy in Blood Transportation th...

引用

Learning and technology Conference (L&T)

作者： Meaad Alseraihi Amjaad Aljadani Samar Alsahafi Maryam Alzein Salma Elhag Faculty of Computing & Information Technology King Abdulaziz University Jeddah Saudi Arabia

ISBN: (数字)9798331532215

ISBN: (纸本)9798331532222

Timely blood sample transportation is crucial for healthcare, particularly in emergencies, in Saudi Arabia’s government clinics, the current process involves daily noon collections by SPL logistics representatives, causing delays in testing and limited availability for urgent cases. Through consultations with a healthcare professional, we identified Key inefficiencies include restricted collection times, absence of onsite laboratories, and lengthy transportation, often exceeding an hour. This study applied business process re-engineering (BPR) to address these issues by integrating drone technology, using the Business Process Model and Notation (BPMN) framework, the current process (AS-IS) was analyzed, and a future model (TO-BE) incorporating drones was developed, simulations using Bizagi revealed a significant reduction in average process time from 3 hours and 20 minutes to 1 hour and 19 minutes, the findings highlight the potential of drones to revolutionize healthcare logistics, reducing delays and improving patient outcomes, future research proposes a hybrid approach, integrating drones with traditional logistics systems for enhanced efficiency and scalability.

关键词： Analytical models Government Transportation Medical services Delays Business process re-engineering Blood Drones Logistics Testing

来源：评论

学校读者我要写书评

暂无评论

Stealth Eye: Behavioral Analysis for Fileless Malware Detection

Stealth Eye: Behavioral Analysis for Fileless Malware Detect...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： H.M.H.M Bandara K.M.N Ayeshani M.M.P.M Kumari D.M.S.T Wijerathna Kavinga Yapa Abeywardena Ayesha Wijesooriya Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331509934

ISBN: (纸本)9798331509941

Fileless malware is a significant cybersecurity threat as it is entirely present in system memory and evades traditional signature-based detection methods. This paper introduces STEALTH EYE, an endpoint behavioral analysis framework for detecting fileless malware, such as ransomware, spyware, trojans, and RedLine Stealer, in real time. The framework utilizes an endpoint agent that monitors system activity in real time and captures snapshots of behavior every 60 seconds for real- time threat analysis. These captures track memory injections, DLL loading and execution, file and handle operations, service activity, process and thread behavior, registry modifications, network communications, cryptographic function usage, keystroke logging, and clipboard access. The data that is collected is analyzed through supervised machine learning mechanisms to detect patterns that indicate fileless malware activity. In contrast to traditional post-infection forensic approaches, STEALTH EYE provides real-time monitoring, notification, and active response with enhanced cybersecurity resilience against the widespread fileless attacks.

关键词： Supervised learning Loading Machine learning Real-time systems Trojan horses Ransomware Spyware Computer security Monitoring Resilience

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Behavior-Driven Pipeline Generation

Context-Aware Behavior-Driven Pipeline Generation

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Pawara Gunathilaka Dinal Senadheera Shenan Perara Chamithu Gunawardana Samantha Thelijjagoda Jenny Krishara Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331509934

ISBN: (纸本)9798331509941

An efficient CI/CD process is crucial for modern software teams, but manual pipeline creation is error-prone and requires high DevOps expertise, slowing deployment speed and reducing productivity. This research introduces a context-aware, behavior-driven approach to fully automating CI/CD pipeline generation by analyzing GitHub user activity patterns. The proposed solution utilizes a historical analysis of repository events, developer contributions, and workload distribution to dynamically generate pipelines and assign reviewers to pull requests based on expertise. Unlike previous template-based and generative AI solutions that require manual intervention, our approach leverages pattern recognition and adaptive decision-making to continuously refine automation. This paper presents the methodology behind data collection, analysis, and pipeline generation, demonstrating its effectiveness in reducing human effort while improving software delivery efficiency. This research highlights how behavior-driven automation streamlines the complexity of CI/CD pipeline creation, enabling more adaptive and intelligent systems that effectively respond to the evolving needs of software development teams.

关键词： Automation DevOps Adaptive systems Reviews Pipelines Manuals Software Security Intelligent systems Testing

来源：评论

学校读者我要写书评

暂无评论

Child’s Age Range Prediction Using Sinhala Speech Recognition System

Child’s Age Range Prediction Using Sinhala Speech Recogniti...

引用

Advanced Research in computing (ICARC), International Conference on

作者： Ashimi Kathriarachchi Koliya Pulasinghe Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

This study predicts the age range of a child speaking Sinhala by analyzing voice characteristics and acoustic features. Identifying speech impairments in children aged 6 to 72 months is critical for early intervention, mainly when using a system that recognizes their native language. The developed system generates accurate insights to assist speech pathologists in diagnosing speech disorders. A Multilayer Perceptron neural network is proposed for age group prediction, leveraging Mel Frequency Cepstral Coefficients (MFCC) and pitch features to enhance recognition accuracy. The system demonstrated an overall accuracy rate of 77% in age range identification, providing a valuable tool for healthcare professionals to evaluate and monitor speech development in Sinhala-speaking children.

关键词： Pediatrics Accuracy Speech recognition Computer architecture Speech enhancement Data models Convolutional neural networks Mel frequency cepstral coefficient Usability Overfitting

来源：评论

学校读者我要写书评

暂无评论

Harnessing Deep Learning for Enhancing Brain Tumor Classification in a Sustainable Healthcare Environment

Harnessing Deep Learning for Enhancing Brain Tumor Classific...

引用

Learning and technology Conference (L&T)

作者： Adnan Salem Bajaber Mahmoud Ragab Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

ISBN: (数字)9798331532215

ISBN: (纸本)9798331532222

Brain tumor affect human health owing to their location. Early detection plays a pivotal role in improving treatment efficacy and patient outcomes. Computer-Aided detection systems, leveraging medical imaging techniques, have emerged as valuable tools for assisting clinicians in diagnosing cancer. Deep learning, particularly convolutional neural networks, has shown remarkable promise in medical image analysis, offering enhanced accuracy and efficiency. This study employed transfer learning and deep neural networks for the classification of brain tumors into its different classes. The pre-trained CNN models, used in the classification were EfficientNet, ResNet, DenseNet, and Xception and a series of image pre-processing and augmentation were carried out before feeding the images to the classification models to enhance classification performance. Four ensemble models were built after getting the results from the classification models, ICAVG for image classification average predictions, ICMAX for image classification maximum predictions, FCAVG for extracted features classification average predictions, and FCMAX for extracted features classification maximum predictions. The results from these four ensemble models were again combined into CAVG for the average results of both ICAVG and FCAVG, and CMAX for the maximum results from both ICMAX and FCMAX. The proposed model was tested on a brain tumor dataset of 3064 samples and the investigational validation of the proposed technique portrayed a superior accuracy value of 99.02% over existing models. Based on high predictive results this research work endeavors to contribute to the advancement of cancer diseases detection, facilitating early diagnosis and improving patient outcomes.

关键词： Deep learning Accuracy Computational modeling Transfer learning Predictive models Brain modeling Feature extraction Real-time systems Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Custody Evidence Management System for Healthcare Forensics

Blockchain-Based Custody Evidence Management System for Heal...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： R.D.D.L.K Jayasinghe M.W.K.L Sasanka D.A.S.M Athukorala M.A.D Sandeepani Anuradha Jayakody Amila Senarathna Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331509934

ISBN: (纸本)9798331509941

As digital evidence increasingly growing in significance in healthcare forensics, safeguarding sensitive medical data's confidentiality, integrity, and limited access remains to be an important issue. Existing forensic evidence management systems are subject to data breaches and illegal access since they frequently lack significant privacy-preserving measures. In order to overcome such challenges, this research suggests a Blockchain-Based Custody Evidence Management System for Healthcare Forensics, which combines blockchain technology, machine learning, and encryption methods to improve security, privacy, and accessibility. To ensure accurate and efficient gathering of information, machine learning algorithms are used to extract handwritten and printed text from medical photographs. AES encryption ensures safe storage, while Fully Homomorphic Encryption (FHE) is used for dynamic access level control to protect gathered evidence. Identity verification is made possible via a web-based authentication system that uses Zero-Knowledge Proofs (ZKP) to protect privacy by preventing the disclosure of personal data. By preventing unintended modifications, blockchain technology is used to preserve the custody chain's integrity. Furthermore, machine learning-driven PII detection and masking methods balance the requirement for forensic investigation with privacy compliance by controlling data accessibility according to access entitlements. Based on permitted access levels, the system makes it possible to share safe evidence with law enforcement agencies, such as courts, the police, and other forensic groups. Using blockchain to guarantee data immutability, cryptographic security to restrict access, and artificial intelligence (AI) to safeguard data, this approach enhances the privacy, security, and dependability of handling forensic evidence in medical investigations.

关键词： Data privacy Privacy Machine learning algorithms Law enforcement Forensics Medical services Machine learning Blockchains Homomorphic encryption Identification of persons

来源：评论

学校读者我要写书评

暂无评论

Personalized Book Recommendation Engine with Emotional Understanding and Contextual Relevance Based on Hybrid Filtering - A Novel Method Providing Recommendation Explanation

Personalized Book Recommendation Engine with Emotional Under...

引用

Software Engineering and Computer Science (CSECS), International Conference on

作者： Perera U. L. U.S. L H.M.Samadhi Chathuranga Thusithanjana Thilakarathna Faculty of Computing Sri Lanka Institute of Information and Technology Malabe Sri lanka

ISBN: (数字)9798331522216

ISBN: (纸本)9798331522223

This paper introduces a novel personalized book recommendation system that integrates emotional understanding and contextual relevance to enhance the accuracy and personalization of suggestions. The system employs a hybrid filtering method, combining content-based and collaborative filtering, to address the limitations of traditional recommendation systems. By incorporating Explainable AI (XAI), the system provides transparent justifications for each recommendation, enhancing user trust and engagement. Additionally, sentiment analysis and contextual factors, such as weather, time of day, and the user's emotional state, are considered to ensure that the recommended books align with the user's current circumstances. Our findings show that the integration of Explainable AI significantly improved user satisfaction and engagement. Testing with 100 participants resulted in a high level of satisfaction, with 55% reporting that they found the recommendations more trustworthy due to explanations. The system makes a significant contribution to improving emotional well-being by providing personalized recommendations.

关键词： Sentiment analysis Accuracy Filtering Explainable AI Collaborative filtering Recommender systems Testing Meteorology Videos Software engineering

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

Computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：