检索结果-内蒙古大学图书馆

Driver Drowsiness Detection Using Swin Transformer and Diffusion Models for Robust Image Denoising

IEEE Access 2025年 13卷 71880-71907页

作者： El-Nabi, Samy Abd Ibrahim, Ahmed F. El-Rabaie, El-Sayed M. Hassan, Osama F. Soliman, Naglaa F. Ramadan, Khalil F. El-Shafai, Walid Faculty of Computer Science and Engineering Department of Artificial Intelligence Engineering South Sinai 46511 Egypt Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt Suez Canal University Faculty of Computers and Informatics Information Systems Department Ismailia41522 Egypt Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Computer Science Department Riyadh11586 Saudi Arabia

With the rapid development of intelligent transportation systems and growing emphasis on driver safety, real-time detection of driver drowsiness has become a critical area of research. This study presents a robust and scalable driver drowsiness detection framework that integrates a Swin Transformer-based deep learning model with a diffusion model for image denoising. While conventional convolutional neural networks (CNNs) are effective in standard vision tasks, they often suffer performance degradation in real-world driving scenarios due to noise, poor lighting, motion blur, and adversarial attacks. To address these challenges, the proposed model focuses on eye-state detection, specifically, prolonged eye closure, as a primary indicator of driver disengagement and fatigue. Our system introduces a novel preprocessing stage using a denoising diffusion model built on a U-Net encoder-decoder architecture, effectively mitigating the impact of Gaussian noise and adversarial perturbations. Additionally, we incorporate adversarial training with Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks, demonstrating significant improvements in classification accuracy and resilience. Evaluations are conducted on two benchmark datasets, Eye-Blink and Closed Eyes in the Wild (CEW), under both clean and noisy conditions. Comparative experiments show that the proposed system outperforms several state-of-the-art models, including ViT, ResNet50V2, InceptionV3, MobileNet, DenseNet169, and VGG19, in terms of accuracy (up to 99.82%), PSNR (up to 41.61 dB), and SSIM (up to 0.984), while maintaining competitive inference times suitable for practical deployment. Moreover, a detailed sensitivity analysis of data augmentation strategies reveals that techniques such as rotation and horizontal flip substantially enhance the model’s generalization across variable visual inputs. The system also demonstrates improved robustness under real-world black-box scenarios and adver

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Estimation of cutting temperature using machine learning based on signal information received from power analyzer in vortex machining conditions

引用

Journal of Manufacturing Processes 2025年 137卷 100-112页

作者： Siyambaş, Yusuf Akdulum, Aslan Çakıroğlu, Ramazan Uzun, Gültekin Erzincan Binali Yıldırım University Vocational High School Department of Machinery and Metal Technologies Erzincan24002 Turkey Hacettepe University Başkent OSB Vocational School of Technical Sciences Department of Machinery and Metal Technologies Ankara06909 Turkey Gazi University Faculty of Technology Department of Energy Systems Engineering Ankara Ankara06500 Turkey Gazi University Faculty of Technology Department of Manufacturing Engineering Ankara06500 Turkey

Cutting temperature directly determines power consumption by influencing tool wear and workpiece quality. Especially for workpieces that cause high heat generation due to low thermal conductivity coefficients, such as Ti6Al4V, it is a challenge to control and determine the cooling method and cutting parameters accordingly. Pre-process modeling and estimation of the cutting temperature due to the cutting variables is necessary for effective process planning and machining efficiency. In this study, it is aimed to use various signal information received from the power analyzer as input features to effectively model and estimate by using the machine learning method the cutting temperature occurring in the turning using various cooling environments of Ti6Al4V workpieces. The features extracted from the four signal information were used both individually and by obtaining hybrid signal features where all the features are combined. While individual signals were used directly in establishing the models, hybrid signals were ranked using the feature ranking method according to six different importance levels. As a result of the study, it was determined that the cutting temperature could be predicted with high success by modeling it according to the features extracted from the signal information obtained from the power analyzer. © 2025 The Society of Manufacturing Engineers

关键词： Cutting temperature estimation Feature selection Feature sorting Power analyzer signal Ti6Al4V vortex cooling

来源：评论

学校读者我要写书评

暂无评论

Deep learning application in diagnosing breast cancer recurrence

引用

Multimedia Tools and Applications 2025年第13期84卷 12265-12297页

作者： Jam, Zeinab Albadvi, Amir Atashi, Alireza Department of Information Technology Engineering-Industrial and Systems Engineering Faculty Tarbiat Modares University Tehran Iran Medical Informatics Department Breast Cancer Research Center Motamed Cancer Institute ACECR Tehran Iran Department of Digital Health School of Medicine Tehran University of Medical Sciences Tehran Iran

Patients' lives can always be saved when diseases, especially special diseases, are detected early. The chances of a patient surviving can be increased by early detection. Breast cancer is one of the deadliest and common cancers. After recovering from breast cancer, patients are always worried about recurrence and return. The use of modern technology, however, can help predict disease recurrence at an early stage, allowing patients to receive treatment sooner. Significant strides have been achieved in deep learning, demonstrating strong performance in handling unstructured data challenges. However, when it comes to predicting tabular data, deep learning hasn't quite matched its success with unstructured data. Presently, ensemble models relying on gradient-boosted decision trees (GBDT) are frequently favored for tabular data prediction tasks. Typically, these GBDT-based models outshine deep learning approaches. Many novel deep learning techniques are emerging for handling tabular data. TabNet, for instance, mirrors decision tree feature selection within a neural network framework. AutoInt addresses high dimensionality by condensing data through embedding layers. Tab Transformer adapts the transformer model, generating text representations for categorical attributes. Despite their innovation, these methods remain less recognized compared to those for image and text data processing. In this study, 158 different characteristics of 5142 breast cancer patients from 1997 to 2019 were examined. We aim to evaluate deep learning techniques effectiveness in detecting breast cancer recurrence. Through examination of evaluation metrics, it becomes evident that deep learning approaches applied to tabular data surpass traditional machine learning algorithms, even when dealing with imbalanced datasets. Ultimately, the results derived from each algorithm analyzed and concluded with a review and comparison of the findings. © The Author(s), under exclusive licence to Springer Science+

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

PneuX-Net: An Enhanced Feature Extraction and Transformation Approach for Pneumonia Detection in X-Ray Images

引用

IEEE Access 2025年 13卷 84024-84037页

作者： Munir, Kashif Usama Tanveer, Muhammad Alyamani, Hasan J. Bermak, Amine Ur Rehman, Atiq Khwaja Fareed University of Engineering and Information Technology Institute of Information Technology Rahim Yar Khan 64200 Pakistan King Abdulaziz University Faculty of Computing and Information Technology in Rabigh Department of Information Systems Jeddah 21589 Saudi Arabia Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha Qatar

Pneumonia is a critical respiratory condition characterized by inflammation in the alveoli, leading to impaired gas exchange and severe respiratory distress. It poses a significant threat to high-risk populations, including neonates, geriatric patients, and immunocompromised individuals. Early and precise detection is crucial to optimizing treatment strategies and reducing morbidity and mortality rates. To address this problem, we propose PneuX-Net, an ensemble-based feature extraction framework that integrates multiple machine learning (ML) models Random Forest (RF), Gaussian Naïve Bayes (GNB) and K-Nearest Centroid (KNC). Random Forest (RF) builds multiple decision trees to identify complex, non-linear patterns within the feature space. Gaussian Naïve Bayes (GNB) utilizes a probabilistic framework based on Bayes’ theorem to manage uncertainty in feature distributions. K-Nearest Centroid (KNC) improves class distinction by clustering feature vectors according to their proximity to centroids. The ensemble methodology harnesses the complementary strengths of these models, improving feature representation and mitigating overfitting, a prevalent issue in white-box models. To validate the effectiveness of PneuX-Net, we conduct extensive experimentation using a 10-fold cross-validation approach. Our results demonstrate that the PneuX-Net+KNC model achieves a remarkable 99.91% accuracy, highlighting its robustness and reliability in pneumonia classification tasks. This ensemble-driven methodology underscores the potential of machine learning in augmenting clinical decision-making by providing an accurate and automated pneumonia detection framework. © 2013 IEEE.

关键词： healthcare AI machine learning medical diagnosis pneumonia detection PneuX-Net

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Anomaly Detection in Smart City Traffic: Performance Comparison and Insights 11

Machine Learning-Based Anomaly Detection in Smart City Traff...

引用

11th International Conference on Vehicle technology and Intelligent Transport systems, VEHITS 2025

作者： Bawaneh, Mohammad Simon, Vilmos Department of Networked Systems and Services Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3 BudapestH-1111 Hungary

ISBN: (纸本)9789897587450

In recent years, urban roads have suffered from substantial traffic congestion due to the rapidly increasing number of road users and vehicles. Some traffic congestion patterns on specific roadways, such as the recurring congestion during morning and evening rush hours, can be foreseen. However, unexpected events, such as incidents, may also cause traffic congestion. Monitoring traffic status poses vital importance for city traffic operators. They can leverage the monitoring system for resource allocation, traffic lights adjusting, and adapting the public transport schedules to alleviate traffic congestion. Machine learning-based methods for anomaly detection are valuable tools for monitoring traffic status and promptly detecting congestion on city roads. In this paper, we comprehensively study the performance of the common machine learning methods for anomaly detection in the traffic congestion detection use case. In addition, we provide methods usage insights based on the study findings by examining the accuracy, detection speed, and computation overhead of the methods to guide the researchers and city operators toward a suitable method based on their needs. Copyright © 2025 by SCITEPRESS - Science and technology Publications, Lda.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Numerical Investigation of the Effect of Storage Tank Orientation on the Melting of Phase Change Material in a Square-Shaped Tank 15

Numerical Investigation of the Effect of Storage Tank Orient...

引用

15th International Renewable Energy Congress, IREC 2025

作者： Chebli, Fatiha Mechighel, Farid Djebali, Ridha Energy Systems Technology Laboratory National Higher School of Technology and Engineering Annaba Algeria Faculty of Technology Badji Mokhtar - Annaba University Department of Mechanical Engineering PO. Box 12 Annaba23000 Algeria University of Jendouba UR: Modeling Optimization and Augmented Engineering Islaib Béja Tunisia

ISBN: (纸本)9798331516772

The storage capacity of surplus energy produced by renewable and conventional power plants makes latent heat storage units (LHSUs) using phase change materials (PCMs) relevant. The phase change processes are affected by the geometric shape of the PCM tank and the operating conditions to which it is subjected. This study explores the behavior of the melting process of paraffin (a PCM) in a square-shaped tank oriented in various orientations 0°, 30°, 60° and 90°. The results show that initially, the melting is dominated by thermal conduction, but as it progresses, natural convection takes over. Furthermore, the melting rate increases with the inclination angle. The total energy stored in a PCM during melting remains constant, although the time needed to store that energy can be considerably influenced by the orientation of the cavity. © 2025 IEEE.

关键词： Tanks (containers)

来源：评论

学校读者我要写书评

暂无评论

Agricultural consumer Internet of Things devices: Methods for optimizing data aggregation

引用

Alexandria engineering Journal 2025年 125卷 692-699页

作者： Mengash, Hanan Abdullah Mahgoub, Hany Alshuhail, Asma Darem, Abdulbasit A. Majdoubi, Jihen Yafoz, Ayman Alsini, Raed Alghushairy, Omar Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Engineering and Technology Unit Applied College Majmaah University Al Majmaah11952 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Department of Information Systems and Technology College of Computer Science and Engineering University of Jeddah Jeddah21589 Saudi Arabia

With the advent of state-of-the-art computer and digital technology, modern civilisation has been immensely facilitated and optimised. The Internet of Things (IoT) has grown in importance in recent years, allowing us to monitor our physical environments and broadening our horizons. The "practice, science, or art" of farming is defined as tending to land, growing crops with the use of different tools and techniques, and then selling the harvested food. If farmers optimise their operations with the help of a Wireless Sensor Network (WSN), they will be able to work much more efficiently and effectively. Data aggregation involves collecting information from multiple sensors. The data aggregation process is optimised by applying metaheuristic techniques. A Genetic Algorithm (GA) is a method for modelling evolution that uses mutation, crossover, and natural selection as its building blocks. The key benefit of the Artificial Bee Colony (ABC) approach is that it simultaneously considers local and global search, and it doesn't get trapped calculating its local minima. Naturalistic algorithms like ALO model their hunting behaviour after that of ant-lions and doodlebugs. It manages to find a happy medium between exploration and exploitation with just one operator. Experimental evidences show that the proposed metaheuristic technique, ABC-ALO, which combines the best elements of Artificial Bee Colony and Ant Lion Optimisation, is superior to existing metaheuristic approaches in terms of lifetime computation, or the number of alive nodes at different round counts. © 2025

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Physicochemical Properties and Cost-Benefit of Supplementing Signal Grass (Brachiaria decumbens) in Sasso Broilers Production

引用

BioResources 2025年第2期20卷 3176-3194页

作者： Seng, Kelly Wong Kai Zheng, Alvin Lim Teik Ong, Yee Lyn Lease, Jacqueline Andou, Yoshito Jesse, Faez Firdaus Abdullah Dunshea, Frank R. Chung, Eric Lim Teik Department of Agribusiness and Bioresource Economics Faculty of Agriculture Universiti Putra Malaysia UPM Selangor Serdang43400 Malaysia Department of Science and Technology Faculty of Humanities Management and Science Universiti Putra Malaysia Bintulu Campus Sarawak Bintulu97008 Malaysia Department of Animal Science Faculty of Agriculture Universiti Putra Malaysia UPM Selangor Serdang43400 Malaysia Department of Life Science and Systems Engineering Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology Fukuoka808-0196 Japan Department of Veterinary Clinical Studies Faculty of Veterinary Medicine Universiti Putra Malaysia UPM Selangor Serdang43400 Malaysia School of Agriculture Food and Ecosystem Faculty of Science The University of Melbourne ParkvilleVIC3010 Australia Faculty of Biological Science The University of Leeds LeedsLS2 9JT United Kingdom

There has been a growing interest in using natural alternatives to synthetic additives in animal feed. This study aimed to examine the physicochemical properties of signal grass (Brachiaria decumbens) and its cost-benefit application in broiler production. The characterization was performed using Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), thermogravimetric/derivative thermogravimetry (TG/DTG), and scanning electron microscopy (SEM). A feeding trial involving 216 Sasso broiler chicks was conducted to assess the economic value of including B. decumbens grass meal in their diets. The chicks were divided into six groups, with Treatments 1 and 2 serving as controls (without antibiotics and with oxytetracycline, respectively). Treatments 3 to 6 received diets supplemented with 1.25, 2.50, 3.75, and 5.00 g/kg of B. decumbens grass meal without antibiotics. Body weight and feed intake were monitored over eight weeks to determine growth performance and feed conversion ratio. Broilers in Treatment 6, which received 5.00 g/kg of the grass meal, showed significantly improved growth (p © 2025, North Carolina State University. All rights reserved.

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Classification Algorithms Using Big Data Analytics for Flight Delays Prediction 5th

Comparative Study of Classification Algorithms Using Big Dat...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Asiri, Mona Hassan AL-Malaise AL-Ghamdi, Abdullah S. Fayoumi, Ayman G. Ragab, Mahmoud Department of Information Systems Collage of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Information Systems Department School of Engineering Computing and Design Dar Al-Hekma University Jeddah34801 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Information Technology Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

ISBN: (纸本)9789819771776

Flight delays are the most pressing cause of concern in the airline sector because they can weaken and harm airlines, passengers, and airports. Flight delay prediction has become an essential step in decision-making processes within commercial aviation. Due to the developments of recent technologies, there are many prediction models for flight delays;however, more development of accurate prediction models is still needed. Machine learning, statistical models, and other techniques can be used to create quick and accurate flight delay prediction models. Furthermore, methods for feature selection can be developed to get rid of dimensionality issues. This study aimed to compare four classification algorithms using "big data analytics" to predict flight delays, a function that can improve the whole airline sector. The selected classification algorithms were the "Gaussian Naïve Bayes," "Gradient Boosted Tree" classifier, "Logistic Regression," and "Random Forest" classifier. Many assessment techniques were applied to each one of the suggested models to show the better performance of these models. The comparison used the resulting confusion matrix to summarize prediction results for the following classification problems: "F1 Score", "Accuracy," "Recall," "Precision," "Area Under ROC," and "Area Under PR." The assessment results showed the enhanced outcomes of the "Gradient Boosted Tree" Classifier with existing techniques, and all results of "Logistic Regression" and "Naïve Bayes" are equal. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

MuLAD: Multimodal Aggression Detection from Social Media Memes Exploiting Visual and Textual Features 27th

MuLAD: Multimodal Aggression Detection from Social Media Me...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Hasan, Md. Maruf Ahsan, Shawly Hoque, Mohammed Moshiul Dewan, M. Ali Akber Chittagong University of Engineering and Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada

ISBN: (纸本)9783031781186

Aggression detection from memes is challenging due to their region-specific interpretation and multimodal nature. Detecting or classifying aggressive memes is complicated in low-resource languages (including Bengali) because benchmark datasets and primary language processing software are needed. This paper proposes an innovative meme classification technique that harnesses deep learning (DL) approaches to leverage memes’ visual and textual features in Bengali. Various DL frameworks, such as VGG16, VGG19, ResNet50, CNN, BiLSTM, and BiLSTM+CNN, extract visual and textual features from memes. A novel corpus named the Bengali Meme Dataset (AMemD) is also introduced, comprising a substantial amount of multimodal data, including text and image components. Experimental results on AMemD demonstrate the effectiveness of the proposed approach. The CNN combined with VGG16 obtained the highest f1-score of 0.738 among all multimodal techniques tested. This pioneering research offers valuable insights into the complex task of aggression detection from memes in Bengali and provides a foundation for future studies in this area. The dataset is available at https://***/Maruf089/Multimodal-Aggression-Detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

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：