检索结果-内蒙古大学图书馆

A novel hybrid deep learning framework for pedestrian detection based on thermal infrared and visible spectrum images

引用

Multimedia Tools and Applications 2025年 1-27页

作者： Defaoui, Mahassine Koutti, Lahcen El Ansari, Mohamed Lahmyed, Redouan Masmoudi, Lhoussaine LabSIV Department of Computer Science Faculty of Science Ibn Zohr University Agadir80000 Morocco Informatics and Applications Laboratory Faculty of Science My Ismail University Meknes Morocco Conception and Systems Laboratory Faculty of Sciences Mohamed V University Rabat Morocco

For many intelligent systems, designing accurate pedestrian detection approaches is a fundamental task. This paper describes a novel hybrid system to detect pedestrians using both visible and thermal infrared sensors. The proposed method is achieved in two primary stages. The first stage, hypotheses generation (HG), aims to extract the regions that represent suspected pedestrians from the image. It is performed using both thermal and visible images of the same scene. Here, an improved deep learning-based solution with a convolutional neural network named PedTherm-U-net is proposed. It segments the thermal images and maps the segmentation results into the corresponding visible image to extract the ROIs (candidate pedestrians). The second stage, hypotheses verification (HV), classifies the ROIs extracted from the first stage into pedestrians and non-pedestrians. In the HV step, a novel PedVis-ResNet framework to classify the extracted ROIs is introduced. It is a modified version of ResNet model dedicated to classify the visible pedestrian samples. The proposed method has been tested on the publicly accessible OSU Color-Thermal dataset, and the obtained results demonstrate the effectiveness of the proposed method when compared to the recent state of the art pedestrian detection approaches. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

BeGrading: large language models for enhanced feedback in programming education

引用

Neural Computing and Applications 2025年第2期37卷 1027-1040页

作者： Yousef, Mina Mohamed, Kareem Medhat, Walaa Mohamed, Ensaf Hussein Khoriba, Ghada Arafa, Tamer Center for Informatics Science School of Information Technology and Computer Science Nile University Giza Egypt Faculty of Computers and Artificial Intelligence Helwan University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Benha Egypt

In recent years, large language models (LLMs) have gained significant traction across various domains, including education. This paper explores the application of LLMs in grading programming assignments. By leveraging data collected from existing programming assignments and their corresponding grades, we aim to develop a robust LLM-based grading system. We also incorporate augmented data representing various grading scenarios to enhance the model’s performance and ensure comprehensive coverage across all grading levels. Our approach involves training the LLM on this combined dataset to enable accurate and consistent evaluation of programming assignments. The proposed model, BeGrading, aims to reduce the grading burden on educators and provide timely and objective feedback to students. Compared to the Codestral model, our proposed model demonstrates an absolute difference rate of 19%, equivalent to ±0.95 out of 5. This is acceptable for using a small, fine-tuned model with optimized data. Additionally, the Codestral model compared to the dataset optimized score shows a difference of 15% equivalent to a margin of ±0.75 out of 5. Preliminary results demonstrate the potential of LLMs to perform grading tasks with a high degree of reliability, opening avenues for further research and practical applications in automated education systems. © The Author(s) 2024.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Fog Computing-based Real-Time Emotion Recognition using Physiological Signals 27

Fog Computing-based Real-Time Emotion Recognition using Phys...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Erzurumluoglu, Omur Fatmanur Ozlem, Kadir Atalay, Asli Tuncay Atalay, Ozgur Ince, Gokhan Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey Faculty of Textile Technologies and Design Istanbul Technical University Istanbul Turkey

ISBN: (纸本)9791188428137

Emotion recognition based on physiological signals has become a crucial area of research in affective computing and human-computer interaction, with applications in smart homes, workplaces, educational institutions, healthcare, and entertainment. In this study, a real-time emotion recognition system utilizing fog computing architecture was developed by considering the challenges of latency, total response time, resource usage, and security in IoT environments. The random forest machine learning model was trained with time-based statistical features by using the DREAMER dataset. Even though the model achieved an accuracy of 84.21% with 104 features, to meet real-time performance requirements, the system was optimized to calculate 24 features, maintaining a commendable accuracy of 79.70%. Extensive experiments demonstrated the superior performance of fog computing compared to edge and cloud computing in terms of latency, queuing delay, jitter, and most importantly total response time. The results highlight the proposed system's ability to support multiple users simultaneously. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Graph Residual Noise Learner Network for Brain Connectivity Graph Prediction 6th

Graph Residual Noise Learner Network for Brain Connectivity...

引用

6th International Workshop on Graphs in Biomedical Image Analysis, GRAIL 2024

作者： Demirbilek, Oytun Peng, Tingying Bessadok, Alaa Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey Helmholtz AI Helmholtz Munich Neuherberg Germany

ISBN: (纸本)9783031832420

A morphological brain graph depicting a connectional fingerprint is of paramount importance for charting brain dysconnectivity patterns. Such data often has missing observations due to various reasons such as time-consuming and incomplete neuroimage processing pipelines. Thus, predicting a target brain graph from a source graph is crucial for better diagnosing neurological disorders with minimal data acquisition resources. Many brain graph generative models were proposed for promising results, yet they are mostly based on generative adversarial networks (GAN), which could suffer from mode collapse and require large training datasets. Recent developments in diffusion models address these problems by offering essential properties such as a stable training objective and easy scalability. However, applying a diffusion process to graph edges fails to maintain the topological symmetry of the brain connectivity matrices. To meet these challenges, we propose the Graph Residual Noise Learner Network (Grenol-Net), the first graph diffusion model for predicting a target graph from a source graph. Its two core contributions lie in (i) introducing a graph diffusion model that learns node-level noise for accurate denoising (ii) introducing a node-based diffusion function to better maintain the topological structure of brain graphs. Our Grenol-Net is composed of graph convolutional blocks, which first learn the source embeddings and second, a set of fully connected layers assisted with a positional encoding block that predicts the nodes with noise level t-1 in the target domain. We further design a batch normalization block that learns the target distribution at diffusion timestep t and operates an element-wise subtraction from the predicted nodes with noise level t-1. Our Grenol-Net outperformed existing methods on the morphological brain graph extracted from cortical measurements of the left and right hemispheres separately and on three distinct datasets from multiple cohorts. ©

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

End-to-end optimized ensemble model for Alzheimer’s disease detection 19

End-to-end optimized ensemble model for Alzheimer’s disease...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Hassan, Abdelrahman Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with an increasing prevalence among the elderly, making early and accurate diagnosis critical for effective intervention and management. This paper introduces an end-to-end machine learning pipeline optimized for detecting AD using multimodal data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The study proposes an ensemble model that integrates key modalities—demographics, cognitive scores, neuropsychological assessments, and MRI data—via early fusion to enhance AD detection. Various machine learning models, including Logistic Regression, Gradient Boosting, AdaBoost, XGBoost, Support Vector Machine, and Neural Networks, are compared, and feature selection is optimized through Recursive Feature Elimination, ANOVA F-value, and mutual information methods, with mutual information showing the most efficacy. With further hyperparameter tuning, the highest accuracy is achieved at 95.85%, with Gradient Boosting as the top-performing model. Additional experiments assess and evaluate individual modality contributions, underscoring the predictive value of cognitive scores and neuropsychological features. To enhance clinical interpretability, we incorporate model explainability using LIME and SHAP, which identify key features influencing model predictions across different AD stages. Explainable AI (XAI) is essential in healthcare for providing transparency and supporting clinician confidence by highlighting which biomarkers, such as MMSE, CDRSB, and PTAU, contribute most to diagnostic outcomes. This study demonstrates classical machine learning's potential in AD diagnostics, offering a pathway to cost-effective and clinically viable models for neurodegenerative disease management. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Smart Pharmacy Systems: Enhancing Drug Safety and Operational Efficiency 19

Leveraging Large Language Models for Smart Pharmacy Systems:...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Osheba, Abdelrahman Abou-El-Ela, Ahmed Adel, Osama Maaod, Youssef Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

Adverse drug reactions (ADRs) remain a crucial challenge in healthcare systems, highly contributing to patient mortality. We present an innovative smart pharmacy system that utilizes advanced large language models (LLMs) to enhance drug safety and pharmacy operational efficiency. Our system integrates real-time data from patient's prescriptions, medication databases, and electronic health records (EHR) to automate the detection of potential drug interactions, optimizing clinical decision-making and reducing ADR-related risks. The system's architecture is designed to easily manage prescription processing for patients, inventory management and control, and Pharmacist consultations through an intelligent chatbot interface. Key features include real-time tracking of medication expiration and inventory levels, an interaction checker API for identifying and mitigating risky drug combinations, and an LLM-powered chatbot for accurate data analysis and visualization. By combining advanced computational techniques with AI-driven insights, our smart pharmacy system not only improves medication safety but also eases pharmacy operations. This transformative approach holds the potential to significantly reduce ADR-related hospital admissions and enhance overall healthcare delivery. Our research underscores the vital role of AI and LLMs in modern pharmacy practice, offering an inclusive solution that integrates easily into existing healthcare infrastructures. The proposed smart pharmacy system can be plugged into hospital EHR systems to automatically track patient medications. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Smart real-time detection of risky roads using vehicles trajectories for intelligent transportation

引用

International Journal of Cognitive Computing in Engineering 2025年 6卷 370-379页

作者： Eldawy, Eman O. Abdalla, Mohammed Mokhtar, Hoda M.O. Hendawi, Abdeltawab AbdelAziz, Amr M. Minia Egypt Faculty of Computers and Information Minia University Egypt Faculty of Computers and Artificial Intelligence Beni-Suef University Egypt Egypt University of Informatics Egypt Department of Computer Science and Statistics University of Rhode Island United States

Indeed, risky roads have a negative impact on traffic by causing road injuries with fatalities, which can lead to negative emotional, social, and economic influences on humans, countries, and the world. Additionally, taxi and rideshare passengers prefer to move on familiar and safe roads. Therefore, to ensure the high quality of transportation services, it is required to follow secure roads to avoid poorly maintained roads, areas with high incidences of car accidents, neighborhoods with high crime rates, and places with a history of terrorist attacks or civil unrest. In this regard, discovering risky roads is a need. This paper introduces a real-time framework, named RiskyMove, that helps drivers and passengers to follow safe roads and avoid risky once that are not safe for travel. Mainly, the RiskyMove framework employs a probabilistic method based on a Minimum Adaptive Viterbi (MAV) algorithm to identify risky paths during the trip and alarm the drivers to take precautions. An experimental evaluation of the RiskyMove with a real dataset of the movement of cabs in San Francisco illustrates the effectiveness of the proposed framework. © 2025 The Authors

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuned Attribute Weighted Naïve Bayes with Modified Partial Instances Reduction for Gaming Disorder Classification

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2025年第1期6卷 67-80页

作者： Latubessy, Anastasya Wardoyo, Retantyo Musdholifah, Aina Kusrohmaniah, Sri Doctoral Program Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Informatics Engineering Faculty of Engineering Universitas Muria Kudus Indonesia Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Psychology Faculty of Psychology Universitas Gadjah Mada Yogyakarta55281 Indonesia

Fine Tuning Attribute Weighted Naïve Bayes (FTAWNB) is a reliable modified Naïve Bayes model. Even though it is able to provide high accuracy on ordinal data, this model is sensitive to outliers. To improve the performance of FTAWNB, this research modified the Partial Instances Reduction (PIR) technique to make the FTAWNB more adaptive to outliers. Nevertheless, in contrast to the original PIR technique, which substitutes missing values for data values deemed outliers, the PIR technique suggested in this study replaces data values deemed outliers using a Naïve Bayes weighting approach. The attribute values from the outlier data are replaced with the highest probability values for the attributes in the actual class. This PIR technique is referred to as modified PIR. The FTAWNB model with modified PIR has been evaluated using the Gaming Disorder dataset. Replacing the four attributes with the least amount of information resulted in accuracy gains of 99.74%, an increase of 1.53% over the FTAWNB model. The experimental result shows that adding the modified PIR technique to the FTAWNB model can handle the outlier in the data, proving it by increasing the performance in terms of accuracy, precision, and recall without pruning the dataset used. © 2025, Ital Publication. All rights reserved.

关键词： Attribute Weighted Classification Fine-Tune Gaming Disorder Instances Reduction Naïve Bayes

来源：评论

学校读者我要写书评

暂无评论

Early Parkinson's Disease Detection and Classification using Machine Learning and Neutrosophic Sets

引用

Neutrosophic Sets and Systems 2025年 82卷 873-886页

作者： Oudah, Hasan H. Metwaly, Ahmed A. Eassa, Mohamed Abdelhafeez, Ahmed Nagm, Ahmad M. Salama, Ahmed S. College of Arts Department of Journalism Ahl Al Bayt University Karbala Iraq Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Engineering and Electronics Cairo Higher Institute for Engineering Computer Science and Management New Cairo Egypt

Optimizing therapy and rehabilitation for Parkinson's disease (PD) requires early identification and precise evaluation of the illness's course. However, there is disagreement about the best way to use gait analysis to categorize the severity of motor symptoms and identify early-stage Parkinson's disease. The precision of machine learning (ML) models in identifying early and intermediate stages of Parkinson's disease was assessed in this study. Six ML models are used in this study for the prediction of PD. Different metrics are used to evaluate ML models such as accuracy, precision, recall, f1-score, and AUC score. Then we propose a multi-criteria decision-making methodology (MCDM) to evaluate the ML models and select the best one. Two MCDM methods are used such as CRITIC method to compute the criteria weights and the TOPSIS method to rank the alternatives. These methods are used under the bipolar neutrosophic sets (BNSs) to deal with uncertainty information. The results show the support vector machine is the best ML model for the prediction of PD. © 2025, University of New Mexico. All rights reserved.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Comparison of Classical and Deep Learning-Based Feature Representations for Age-Related Macular Degeneration 5th

Comparison of Classical and Deep Learning-Based Feature Re...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Sinichi, Parsa Bernabeu, Miguel O. Javidi, Malihe Department of Computer Engineering Faculty of Electronic and Computer Engineering Quchan University of Technology Quchan Iran Centre for Medical Informatics University of Edinburgh Edinburgh United Kingdom

ISBN: (纸本)9789819638628

Age-related Macular Degeneration (AMD) is a leading cause of visual impairment among the elderly worldwide. This study compares deep learning-based and classical feature extraction methods for AMD classification using colour fundus images, a cost-effective imaging modality. This comparative approach aims to evaluate the performance of advanced deep learning methods against traditional computer vision approaches in generating effective feature representation. To achieve this, we compared various classical feature extraction methods alongside deep learning-based approaches, specifically VGG16 pre-trained on ImageNet, RETFound and RETFound-Green, which are foundation models pre-trained on a significant number of retinal images. The results demonstrate that combinations of classical features still obtained notable performance and even outperformed the VGG16 model pre-trained on ImageNet. These results also highlight the need for deep learning models to be trained on domain-specific data to surpass classical approaches. In this regard, the pre-trained RETFound and RETFound-Green models yielded promising outcomes for AMD classification, and the highest performance was achieved using a fine-tuned RETFound model. Furthermore, the best proposed method was compared with the state-of-the-art methods. This approach achieved competitive results on the ADAM dataset, demonstrating its robustness and effectiveness in AMD classification while utilising a significantly simpler architecture. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive 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：