检索结果-内蒙古大学图书馆

Advanced human activity recognition on wearables with multi-scale sparse attention

Multimedia Tools and Applications 2025年 1-30页

作者： Muniasamy, Anandhavalli Asiri, Fatima College of Computer Science Department of Informatics and Computer Systems King Khalid University Abha Saudi Arabia College of Computer Science Informatics and Computer Systems Department King Khalid University Abha Saudi Arabia

Maintaining a regular daily activity routine is essential for overall health and well-being. Wearable sensors offer a convenient way to track daily activities, but accurately identifying a wide range of activities remains a challenge for existing methods. These methods relied heavily on feature selection approaches in CNNs, which were not only tedious but also struggled to accurately identify activities with similar patterns and, also fails to find the long-range dependencies. The introduction of transformers in CNNs addresses these limitations, enabling more efficient and precise recognition of activities even when patterns are similar. In this paper, a novel Human activity recognition model that combines CNN with a Residual Transformer Network (RTN) is proposed. This model incorporates two key improvements: a sparse attention technique applied at multiple scales to capture complex spatial patterns, and an adaptive fusion. Sparse attention allows the model to concentrate on the most critical parts of the spectrogram at different scales and directions. This approach aids the model in distinguishing between activities with similar overall patterns by capturing subtle differences. Additionally, it enhances the model’s ability to recognize long-range dependencies. An adaptive fusion technique is introduced to combine features from CNN and RTN, with a dynamic scoring function optimally weighting each feature stream. This ensures balanced contributions from spatial patterns and temporal dependencies for accurate activity classification. Experiments conducted on the HARTH, HU-HAR, and HuGaDB datasets demonstrate impressive results with higher accuracies of 94.82%, 98.94%, and 96.33%, respectively. These findings highlight the effectiveness of the proposed method for accurate activity detection and continuous health monitoring applications. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Integrating Bayesian and Convolution Neural Network for Uncertainty Estimation of Cataract from Fundus Images

引用

computer Modeling in Engineering & sciences 2025年第4期143卷 569-592页

作者： Anandhavalli Muniasamy Ashwag Alasmari Department of Informatics and Computer Systems College of Computer ScienceKing KhalidUniversityAbha61421Saudi Arabia Department of Computer Science King Khalid UniversityAbha61421Saudi Arabia

The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of ***,the mass disease that needs attention in this context is *** deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty ***,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the *** prepares convolutional neural network(CNN)and BCNN *** proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN *** study then trains them on a dataset of cataract images filtered from the ocular disease fundus images *** deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye *** compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.

关键词： Bayesian neural networks(BNNs) convolution neural networks(CNN) Bayesian convolution neural networks(BCNNs) predictive modeling precision medicine uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Different Methods to Estimate Stress-Strength Reliability Function for Modified Exponentiated Lomax Distribution

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2025年第2期6卷 99-106页

作者： Al-Rassam, Raya Salim Mohammed, Khalida Ahmed Rashed, Safwan Nathem Department of Statistics & Informatics College of Computer Science & Mathematics University of Mosul Iraq

When ensuring the reliability of device or the suitability of a material, it is necessary to take into consideration the stress cases in the operating environment. This means that the uncertainty about the reality environmental stress must be taken into as random. The stress-strength (S-S) model treated the stress and strength variables as random. In the simplest form of stress-strength model, y represents the stress put on the unit by the operating environment, and the strength of the unit represented by x. A unit is able to perform its required function if its stress imposed on it is less than the strength of the unit. In this paper, the stress-strength reliability estimation for the modified exponentiated Lomax distribution, which is generalization of the Lomax distribution, with an unknown shape parameter and a known scale parameters is studied using different methods. These methods include the maximum likelihood method, Bayesian estimation method under a quadratic loss function, and the least squares method for complete data. The estimators are compared based on Markov Chain Monte Carlo (MCMC) simulations using R-Studio, evaluated by the mean square error (MSE) criteria. The simulation results show that the maximum likelihood estimators are the best in two cases: the first is when the sample sizes are equal and the second is when the shape parameter of the strength variable is greater than the shape parameter of the stress variable. While least squares estimators are the beast if the strength sample size is smaller than the stress sample size. Finally when the strength sample size is greater than the stress sample size, then the best estimators differ between the maximum likelihood estimators and Bayesian estimators. Bayesian estimators become the best when the shape parameter of stress variable is larger than the shape parameter of the strength variable. © 2025 The Author(s).

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Biometric-Based Secure Encryption Key Generation Using Convolutional Neural Networks and Particle Swarm Optimization

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第16期49卷 213-234页

作者： Almola, Sahera A.S. Khudeyer, Raidah S. Younis, Hameed Abdulkareem Department of Computer Information Systems College of Computer Science and Information Technology University of Basrah Basrah Iraq

With the rapid expansion of computer networks and information technology, ensuring secure data transmission is increasingly vital—especially for image data, which often contains sensitive information. This research presents a biometric-based encryption system that uses fingerprint recognition and deep learning to generate strong, random encryption keys. Two convolutional neural networks (CNNs) are employed: one to verify identity based on a user’s ID and another to extract fingerprint features for key generation. These keys are optimized using Particle Swarm Optimization (PSO), enhancing their randomness and resistance to brute-force attacks. The system generates keys in real-time, eliminating the need for storage and minimizing the risk of theft or leakage. To further improve security, encryption keys are automatically updated after every ten messages, with different keys generated from multiple fingerprints of the same individual. Testing with the SOCOFing dataset (6,000 original and 49,270 synthetic images) achieved 99.75% identity verification and 99.83% classification accuracy. Performance metrics—entropy of 7.89, correlation factor of 0.00628, and zero repetition—demonstrate high robustness. This approach offers a secure, adaptive, and personalized encryption method ideal for sensitive domains like finance and healthcare. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Privacy-Aware Federated Learning Framework for IoT Security Using Chameleon Swarm Optimization and Self-Attentive Variational Autoencoder

引用

computer Modeling in Engineering & sciences 2025年第4期143卷 849-873页

作者： Saad Alahmari Abdulwhab Alkharashi Department of Computer Science Applied CollegeNorthern Border UniversityArar91431Saudi Arabia Department of Computer Science College of Computing and InformaticsSaudi Electronic UniversityRiyadh11673Saudi Arabia

The Internet of Things(IoT)is emerging as an innovative phenomenon concerned with the development of numerous vital *** the development of IoT devices,huge amounts of information,including users’private data,are *** systems face major security and data privacy challenges owing to their integral features such as scalability,resource constraints,and *** challenges are intensified by the fact that IoT technology frequently gathers and conveys complex data,creating an attractive opportunity for *** address these challenges,artificial intelligence(AI)techniques,such as machine learning(ML)and deep learning(DL),are utilized to build an intrusion detection system(IDS)that helps to secure IoT *** learning(FL)is a decentralized technique that can help to improve information privacy and performance by training the IDS on discrete linked *** delivers an effectual tool to defend user confidentiality,mainly in the field of IoT,where IoT devices often obtain privacy-sensitive personal *** study develops a Privacy-Enhanced Federated Learning for Intrusion Detection using the Chameleon Swarm Algorithm and Artificial Intelligence(PEFLID-CSAAI)*** main aim of the PEFLID-CSAAI method is to recognize the existence of attack behavior in IoT ***,the PEFLIDCSAAI technique involves data preprocessing using Z-score normalization to transformthe input data into a beneficial ***,the PEFLID-CSAAI method uses the Osprey Optimization Algorithm(OOA)for the feature selection(FS)*** the classification of intrusion detection attacks,the Self-Attentive Variational Autoencoder(SA-VAE)technique can be ***,the Chameleon Swarm Algorithm(CSA)is applied for the hyperparameter finetuning process that is involved in the SA-VAE model.A wide range of experiments were conducted to validate the execution of the PEFLID-CSAAI *** simulated outcomes demonstrated that the PEFLID-CSAAI

关键词： Federated learning internet of things artificial intelligence chameleon swarm algorithm intrusion detection system healthcare IoT devices

来源：评论

学校读者我要写书评

暂无评论

Autonomous vehicle surveillance through fuzzy C-means segmentation and DeepSORT on aerial images

引用

PeerJ computer science 2025年 11卷 1-23页

作者： Qureshi, Asifa Mehmood Alotaibi, Moneerah Alotaibi, Sultan Refa AlHammadi, Dina Abdulaziz Jamal, Muhammad Asif Jalal, Ahmad Lee, Bumshik Department of Computer Science Air University Islamabad Pakistan Department of Computer Science College of Science and Humanities Shaqra University Dawadmi Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia Information and Communication Engineering Chosun University Gwangju Korea Republic of Department of Computer Science and Engineering College of Informatics Korea University Seoul Korea Republic of

The high mobility of uncrewed aerial vehicles (UAVs) has led to their usage in various computer vision applications, notably in intelligent traffic surveillance, where it enhances productivity and simplifies the process. Yet, there are still several challenges that must be resolved to automate these systems. One significant challenge is the accurate extraction of vehicle foregrounds in complex traffic scenarios. As a result, this article proposes a novel vehicle detection and tracking system for autonomous vehicle surveillance, which employs Fuzzy C-mean clustering to segment the aerial images. After segmentation, we employed the YOLOv4 deep learning algorithm, which is efficient in detecting small-sized objects in vehicle detection. Furthermore, an ID assignment and recovery algorithm based on Speed-Up Robust Feature (SURF) is used for multi-vehicle tracking across image frames. Vehicles are determined by counting in each image to estimate the traffic density at different time intervals. Finally, these vehicles were tracked using DeepSORT, which combines the Kalman filter with deep learning to produce accurate results. Furthermore, to understand the traffic flow direction, the path trajectories of each tracked vehicle is projected. Our proposed model demonstrates a noteworthy vehicle detection and tracking rate during experimental validation, attaining precision scores of 0.82 and 0.80 over UAVDT and KIT-AIS datasets for vehicle detection. For vehicle tracking, the precision is 0.87 over the UAVDT dataset and 0.83 for the KIT-AIS dataset. © 2025 Qureshi et al.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Integration of data science with the intelligent IoT(IIoT): Current challenges and future perspectives

引用

Digital Communications and Networks 2025年第2期11卷 280-298页

作者： Inam Ullah Deepak Adhikari Xin Su Francesco Palmieri Celimuge Wu Chang Choi Department of Computer Engineering Gachon University University of Electronic Science and Technology of China College of Information Science and Engineering Hohai University Department of Computer Science University of Salerno Graduate School of Informatics and Engineering The University of Electro-Communications

The Intelligent Internet of Things(IIoT) involves real-world things that communicate or interact with each other through networking technologies by collecting data from these “things” and using intelligent approaches, such as Artificial Intelligence(AI) and machine learning, to make accurate decisions. Data science is the science of dealing with data and its relationships through intelligent approaches. Most state-of-the-art research focuses independently on either data science or IIoT, rather than exploring their integration. Therefore, to address the gap, this article provides a comprehensive survey on the advances and integration of data science with the Intelligent IoT(IIoT) system by classifying the existing IoT-based data science techniques and presenting a summary of various characteristics. The paper analyzes the data science or big data security and privacy features, including network architecture, data protection, and continuous monitoring of data, which face challenges in various IoT-based systems. Extensive insights into IoT data security, privacy, and challenges are visualized in the context of data science for IoT. In addition, this study reveals the current opportunities to enhance data science and IoT market development. The current gap and challenges faced in the integration of data science and IoT are comprehensively presented, followed by the future outlook and possible solutions.

关键词： Data science Internet of things (IoT) Big data Communication systems Networks Security Data science analytics

来源：评论

学校读者我要写书评

暂无评论

Hybrid TCN-transformer model for predicting sustainable food supply and ensuring resilience

引用

Alexandria Engineering Journal 2025年 127卷 380-391页

作者： Alrashdi, Ibrahim Abd El-Aziz, Rasha M. Taloba, Ahmed I. Farsi, Mohammed Department of Computer Science College of Computer and Information Sciences Jouf University Al-Jouf Sakaka73211 Saudi Arabia Department of Information Systems College of Computer Science and Engineering Taibah University Yanbu966144 Saudi Arabia

Major concerns occur in maintaining a sustainable food supply due to population expansion, supply chain interruptions, and climate-related changes. Traditional forecasting models, such as ARIMA, LSTM, and GRU, fail to deal with the dynamic fluctuations and long-range correlations. These methods often have reduced accuracy, high computational cost, and poor generalization when applied to shifting patterns in the food supply system. Based on the abovementioned limitations, this study proposes a Hybrid TCN-Transformer Model by combining the strength of Temporal Convolutional Networks (TCN) with Transformer Attention to provide accurate and efficient food supply prediction. Thus, the project's key objective is to develop a deep learning system that effectively handles massive quantities of temporal data while preserving dependence in short and long durations. The proposed method is novel since it integrates TCN's causal convolutions for extracting sequential patterns. It uses a Transformer Model's self-attention mechanism to capture the complex interactions across time steps. Hybrid design enables faster training, increased interpretability, and better prediction accuracy than current methods. Results from experiments have revealed that the suggested model surpasses the performance of the stand-alone TCN, ARIMA, LSTM, and GRU models in terms of accuracy of predictions, efficiency of computations, and adaptability. Findings thus far suggest deep learning-based predictive analytics has helped improve the food supply chain management by mitigating food wastage, making it environmentally resilient. © 2025 The Authors

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Remote Patient Healthcare Monitoring and Pose Recognition over Video Sensors

引用

Traitement du Signal 2025年第2期42卷 995-1005页

作者： Alabdullah, Bayan Tayyab, Muhammad Alhasson, Haifa F. Alshammari, Naif S. Jalal, Ahmad Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia Department of Computer Science Air University Islamabad44000 Pakistan Department of Information Technology College of Computer Qassim University Buraydah52571 Saudi Arabia Department of Computer Sciences College of Computer and Information Sciences Majmaah University Majmaah11952 Saudi Arabia Department of Computer Science and Engineering College of Informatics Korea University Seoul02841 Korea Republic of

Considering the fact of increasing population and as a result, the number of patients is constantly increasing the delivery of medical services must be prompt and of good quality. There is no question that any perfect healthcare system should track the given activities, behaviours, schedules, and even general health of the patients. The focus of this study is in utilizing ML and DL in tracing patients and diagnosing ailments. Mounted cameras from different orientations and placements are intended for health monitoring and event surveillance for possible medical issues in the future. Classical ML and more advanced DL methods are applied for analyzing physiological and behavioral patterns to identify health conditions and stress the importance of high accuracy and real-time performance for practical purposes. Initial outcomes show that patient outcomes are enhanced by getting timely medical advice while decreasing hospital-based burdens on staff. Two challenging datasets, ETRI-Activity3D and NTU-RGB-D, are pre-processed to remove unimportant data and reduce computational load. A strong multi-feature description system can extract gradient values, and the process is followed by feature matching and feature optimization. Then, in the last Maximum Entropy Markov Model (MEMM) classifier is used, achieving an accuracy of 97.2% for ETRI-Activity3D, and 98.3% for the NTU-RGB-D dataset. ©2025 The authors.

关键词： Remote patient monitoring

来源：评论

学校读者我要写书评

暂无评论

Deep neural network for emojis-based sentiment classification

引用

International Journal of Information Technology (Singapore) 2025年 1-8页

作者： Balaji, Prasanalakshmi Alsid, Linda Elzubir Gasm Sagar, Kalpna Prakasam, Shanmugapriya Department of Computer Science College of Computer Science King Khalid University Abha Saudi Arabia Department of Computer Science KIET Group of Institutions Delhi-NCR Ghaziabad India Department of Computer Science and Business Systems Rajalakshmi Engineering College Thandalam India

Sentiment classification using emojis on social media has become increasingly crucial in recent years. Social media commonly uses emojis to convey feelings, emotions, and moods. Hence, in this article, a Jellyfish Algorithm based on a Deep Convolution Neural Network (JA-DCNN) is developed for the sentiment classification of the emojis. Initially, the emoji images are collected from the open-source system. The proposed sentiment classification process uses a Jellyfish Algorithm (JA) optimized Deep Convolution Neural Network (DCNN). In DCNN, the hyperparameters are selected with the help of JA to improve accuracy and efficiency. The proposed method aims to improve the training features, maintain the resolution, reduce memory consumption, and improve the system’s accuracy. The proposed method decreases the computation cost and memory consumption, which empowers the system’s performance in emojis-based sentiment classification. The proposed method is implemented in MATLAB, and performance metrics of similarity and quality measurements evaluate performances. To validate the performance of the proposed methodology, it is compared with conventional methods such as MobilenetV2, ResNet18, and ResNet50, which have been proven to obtain better performance metrics. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Classification Deep convolution neural network Emojis Jellyfish algorithm Sentiment analysis

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

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

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：