检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of computer Vision (WACV)

作者： Mahdi Alehdaghi Pourya Shamsolmoali Rafael M. O. Cruz Eric Granger Dept. of Systems Engineering ETS LIVIA ILLS Montreal Canada Dept. of Computer Science University of York UK

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single intermediate bridging domain are often less effective, as this generated domain may not adequately capture sufficient common discriminant information. This paper introduces Bidirectional Multi-step Domain Generalization (BMDG), a novel approach for unifying feature representations across diverse modalities. BMDG creates multiple virtual intermediate domains by learning and aligning body part features extracted from both I and V modalities. In particular, our method aims to minimize the cross-modal gap in two steps. First, BMDG aligns modalities in the feature space by learning shared and modality-invariant body part prototypes from V and I images. Then, it generalizes the feature representation by applying bidirectional multi-step learning, which progressively refines feature representations in each step and incorporates more prototypes from both modalities. Based on these prototypes, multiple bridging steps enhance the feature representation. Experiments 1 1 Our code is available at: ***/BMDG conducted on V-I ReID datasets indicate that our BMDG approach can outperform state-of-the-art part-based and intermediate generation methods, and can be integrated into other part-based methods to enhance their V-I ReID performance.

关键词： Training computer vision Accuracy Codes Prototypes Feature extraction Identification of persons

来源：评论

学校读者我要写书评

暂无评论

A Web-Based Interface that Leverages Machine Learning to Assess an Individual’s Vulnerability to Brain Stroke

引用

IEEE Access 2025年 13卷 87950-87964页

作者： Bhandari, Divyansh Agarwal, Arnav Reena Roy, R. Priyatharshini, Rajaram Cristian, Rodriguez Rivero Vellore Institute of Technology School of Electronics Engineering Tamil Nadu Chennai India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Chennai India Cardiff Metropolitan University Cardiff School of Technologies Centre for Engineering Research in Intelligent Sensors and SystemsComputer Science Wales United Kingdom Cardiff Metropolitan University Academic Associate Cardiff School of Technologies Cardiff United Kingdom Universitat Politècnica de Catalunya Industrial and ICT Systems Engineering Dept. of Mining Spain

Cerebral stroke is a major global health issue, contributing to high mortality and long-term disability. Early identification of individuals at high risk of stroke can significantly improve preventive care outcomes. We present a web-based stroke risk assessment tool that uniquely combines an accessible user interface with robust machine learning modeling. The proposed platform leverages a novel combination of SMOTE oversampling and logistic regression to address class imbalance in patient health records, improving the detection of stroke risk factors over existing methods. We compare a range of algorithms – including traditional classifiers and deep learning models – and report comprehensive performance metrics (accuracy, precision, recall, F1-score, and AUC-ROC) for each. Our best model (logistic regression with SMOTE and standard scaling) achieves 93.2% accuracy with a substantially higher F1-score for the stroke-positive class than other models, indicating improved sensitivity to stroke cases. To bridge the gap between complex predictive models and end-users, we deploy this model in an intuitive web interface (built with Streamlit) that non-technical individuals and healthcare providers can easily use. This interface requires no specialized knowledge, preserves user privacy by avoiding any data storage, and provides clear explanations of results. By offering a practical and transparent tool for stroke risk screening, our work advances health informatics with an emphasis on accessibility, interpretability, and early intervention. Potential applications range from personal health self-assessment to integration in clinical workflows for preventive care, ultimately aiming to improve public health outcomes through early detection and intervention in stroke. © 2013 IEEE.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

Design and control of a High-Bandwidth Dual Active Bridge DC-DC Converter

Design and Control of a High-Bandwidth Dual Active Bridge DC...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Alper Uzum Syed Imam Hasan Yilmaz Sozer Kenneth A. Loparo Dept. of Electrical and Computer Engineering The University of Akron Akron OH USA Dept. of Electrical Computer and Systems Engineering Case Western Reserve University Cleveland OH USA

ISBN: (数字)9798331516116

ISBN: (纸本)9798331516123

For the stable operation of sensitive systems, achieving high-bandwidth control in power converters is critical, as the current and voltage ripple directly reflects the quality of the synthesized waveform. The selection of an appropriate DC-link capacitor, which significantly influences the system’s bandwidth, plays a pivotal role in ensuring performance. This paper explores the intricate relationship between input and output DC-link capacitance and its effect on the system bandwidth in Dual Active Bridge (DAB) converters, a topic that remains relatively unexplored despite numerous research on high-bandwidth control for other power converters. To address the challenges posed by the bulky DC-link capacitor typically required to manage ripple current, the proposed approach integrates a harmonic trap filter to effectively mitigate these limitations. Using state-space modeling and state-variable feedback control, the design and control strategy is validated on a 5 kW DAB converter, demonstrating its ability to enhance system bandwidth without compromising ripple performance.

关键词： Electric potential Capacitors Bridge circuits Bandwidth Harmonic analysis Power electronics Feedback control Voltage control Power harmonic filters System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Enhanced deep learning framework for real-time pain assessment using multi-modal fusion of facial features and video streams

引用

engineering Applications of Artificial Intelligence 2025年 154卷

作者： El-Ghaish, Hany Al-Basiouny, Mohamed Yousry Alshewimy, Mahmoud A.M. Tanta University Faculty of Engineering Computer and Control Engineering Dept. Tanta Egypt

This paper introduces an enhanced deep learning multimodal framework for real-time pain assessment that addresses the limitations of the single-mode approaches. Specifically, time-related disadvantages and its poor temporal analysis, noted in recent studies. The proposed framework fuses VGG16 (Visual Geometry Group 16-layer network), a pre-trained convolutional neural network (CNN), with a bidirectional long short-term memory network (Bi-LSTM) augmented with attention mechanisms. VGG16 has a proven ability to capture fine-grained spatial information in facial expressions to extract powerful spatial features, whereas the Bi-LSTM augmented with attention mechanisms because of its computational efficiency and concisely captures temporal features. Moreover, adaptive boosting has used seeking generalization across a broad base of settings and Gradient-weighted Class Activation Mapping (Grad-CAM) to provide comprehensible and interpretable visual explanations of the decision-making processes of the framework. Extensive evaluations were conducted on diverse popular benchmark datasets: BioVid, UNBC-McMaster, and MIntPAIN. Our framework achieves an AUC (the Area under the Receiver Operating Characteristic Curve) of 0.99 and 99% cross-validation accuracy, corresponding to a 12.5% improvement in accuracy and a 20% reduction in false positives relative to state-of-the-art convolutional neural network–long short-term memory (CNN–LSTM) models. Real-time deployment on an NVIDIA Jetson Nano yields 120 ms (ms) inference per frame with less than 1% accuracy loss, demonstrating its feasibility for edge-based telemedicine. Combined with explainability via Grad-CAM and privacy-preserving vision-only inputs, this framework offers an ethical, scalable solution for nonverbal pain detection. © 2025 Elsevier Ltd

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ML-Inspired Multiple Relay Selection in UAV-Enabled Untrusted Networks

ML-Inspired Multiple Relay Selection in UAV-Enabled Untruste...

引用

IEEE Conference on Wireless Communications and Networking

作者： Lefteris Tsipi Emmanouel T. Michailidis Konstantinos Maliatsos Demosthenes Vouyioukas Dept. of Information and Communication Systems Engineering University of the Aegean Samos Greece Dept. of Informatics and Computer Engineering University of West Attica Egaleo Greece Dept. of Digital Systems University of Piraeus Piraeus Greece

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

In this paper, multiple relay selection (MRS) schemes for untrusted unmanned aerial vehicle (UAV)-enabled networks are proposed. In this context, various machine learning (ML) models are employed to improve secrecy performance by optimally selecting multiple aerial relays from the available ones, all of which are regarded as untrusted. Notably, these ML models can cope with the quickly changing and random positioning of the aerial relays, effectively decoupling the intricate coupling relationship between the secrecy rate, channel coefficients, and inter-node distances. The results indicate that the ML-based MRS schemes obtain sufficient accuracy and better decoupling than a respective exhaustive searching (ES) approach, while also maintaining a lower computational complexity.

关键词： Couplings Accuracy Predictive models Autonomous aerial vehicles Security Ensemble learning Relays Computational complexity Context modeling

来源：评论

学校读者我要写书评

暂无评论

Forest Fire Prevention and Detection System

Forest Fire Prevention and Detection System

引用

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

作者： Lasitha Jayakody Chamathka Edirisinghe Tharush Senasinghe Shaminda Dissanayake Narmada Gamage Dinithi Pandithage Jaliya L. Wijayaraja Dept. of Computer Systems Engineering Sri Lanka Institute of Information Malabe Sri Lanka

ISBN: (数字)9798331533694

ISBN: (纸本)9798331533700

Forest fires pose significant threats to both the environment and human life, necessitating the development of advanced detection and prevention systems. In this study, we propose an integrated IoT (Internet of Things)-based system for early detection and management of forest fires. The system incorporates a range of sensors including heat, gas, and thermal imaging sensors, along with IoT technology for real-time monitoring and communication. Utilizing image processing techniques and (ML) Machine Learning algorithms, the system can accurately detect fires, predict their spreading patterns, and analyze environmental conditions. Key features include the deployment of disposable heat sensors for temperature monitoring, IoT sensors for gas detection and weather monitoring, and a centralized processing node for data analysis. Alerts are sent to nearby authorities and residents, while automated firefighting devices are activated to suppress fires until backup arrives. Experimental results demonstrate the effectiveness of the proposed system in early detection and prevention of forest fires.

关键词： Temperature sensors Technological innovation Wildfires Prevention and mitigation Forestry Sensor phenomena and characterization Sensor systems Real-time systems Gas detectors Resilience

来源：评论

学校读者我要写书评

暂无评论

Proposal for a Job Management Tool for Deep Learning in a Mixed Environment of Heterogeneous GPUs

Proposal for a Job Management Tool for Deep Learning in a Mi...

引用

Consumer Technology (ICCT-Pacific), International Conference on

作者： Nobuyuki Ishii Aoi Kondo Hiroaki Koga Dept. Control and Information Systems Engineering National Institute of Technology Kurume College Fukuoka Japan

ISBN: (数字)9798331504120

ISBN: (纸本)9798331504137

In recent years, the use of GPUs for computation has become commonplace in deep learning. It is not uncommon for deep learning labs to procure GPU servers for computation without standardising specifications such as GPU architecture and VRAM capacity, resulting in a heterogeneous GPU server environment. Container technology is also widely used as a method of isolating software execution environments. Among them, Docker is the de facto standard for container platforms. In this paper, we have developed a management system that can allocate deep learning training jobs to GPU servers (workers) using container technology to absorb differences in execution environments in heterogeneous GPU server environments. In experiments, we confirmed that the proposed system can estimate the completion time of training for each worker and can detect Out-Of-Memory (OOM) of GPUs in advance. We were able to confirm in advance the “inference time” and the “possibility of OOM”, which are difficult to predict when performing deep learning. We have succeeded in obtaining the “predicted value of learning time” and “possibility of OOM” that engineers need to know in advance, and have shown that the proposed system is effective in deep learning tests.

关键词： Deep learning Training Graphics processing units Containers Software Servers Resource management Proposals Standards Testing

来源：评论

学校读者我要写书评

暂无评论

Verification of the Effect of Label Modification on Neural Network Learning

Verification of the Effect of Label Modification on Neural N...

引用

Consumer Technology (ICCT-Pacific), International Conference on

作者： Tsubasa Oka Hiroaki Koga Dept. Control and Information Systems Engineering National Institute of Technology Kurume College Fukuoka Japan

ISBN: (数字)9798331504120

ISBN: (纸本)9798331504137

This study focuses on the problem of subjective labeling that arises in the application of machine learning with neural networks to the medical field. The first problem is that of subjectivity, which arises because the labeling of medical data relies on expert knowledge and the process can be subjective. The second problem is the reduced information content of labels caused by discrete and quantitative labeling. If the intermediate values between the discrete values also have evaluative meaning, the detailed information is lost due to the discrete numerical labeling. We focus on such instability in labels and propose an approach to label modification using values inferred during neural network training. Specifically, we consider labels that are discrete, quantitative numbers as continuous numbers, compare the inferred value with the label value at each step in the learning phase, and compare the label value with the inferred value at each step in the learning phase. The update method is to give the label a sign-responsive variation. The goal is to modify each label using the value inferred by the inference made during learning in this way. As an experiment, we conducted an experiment on label modification under pseudo-conditions to verify its effectiveness. The results showed that when the amount of label modification was controlled by a constant, the generalization performance and the nature of label modification differed depending on the constant. In particular, generalization performance was improved when the constant of the label modification amount was determined so that the label value was separated from the inferred value at each step.

关键词： Training Neural networks Machine learning Labeling

来源：评论

学校读者我要写书评

暂无评论

Enhancing Train Transportation in Sri Lanka: A Smart IOT based Multi-Subsystem Approach using MQTT

arXiv

引用

arXiv 2025年

作者： Balasingham, Dhanushka Samarathunga, Sadeesha Bandara, Anuththara Arachchige, Gayantha Godakanda Gamage, Narmada Wijayaraja, Jaliya L. Dept. of Computer Systems Engineering Sri Lanka Institute of Information Technology Sri Lanka

This research proposes a system as a solution for the challenges faced by Sri Lanka’s historic railway system, such as scheduling delays, overcrowding, manual ticketing, and management inefficiencies. It proposes a multi-subsystem approach, incorporating GPS tracking, RFID-based e-ticketing, seat reservation, and vision-based people counting. The GPS-based real-time train tracking system performs accurately within 24 meters, with the MQTT protocol showing twice the speed of the HTTP-based system. All subsystems use the MQTT protocol to enhance efficiency, reliability, and passenger experience. The study’s data and methodology demonstrate the effectiveness of these innovations in improving scheduling, passenger flow, and overall system performance, offering promising solutions for modernizing Sri Lanka’s railway infrastructure. © 2025, CC BY.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Predicting Lifespan of Ground-to-Air Multipath Components in mmWave UAV Channels

Predicting Lifespan of Ground-to-Air Multipath Components in...

引用

IEEE Conference on Wireless Communications and Networking

作者： Wahab Khawaja Rune H. Jacobsen Sajid Hussain Ismail Guvenc Dept. Electrical and Computer Engineering Aarhus University Aarhus Denmark Dept. Computer Systems Engineering Mirpur Univ. Science and Technology Mirpur AJK Pakistan Dept. Electrical and Computer Engineering North Carolina State University Raleigh NC USA

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

In mobile ground-to-air (GA) propagation channels, the birth and death of multipath components (MPCs) are frequently observed, and the wide-sense stationary uncorrelated scattering (WSSUS) assumption does not always hold. Several methods exist for tracking the birth and death of MPCs, however, to the best of knowledge of authors, there is no existing literature that addresses the prediction of the lifespan of the MPCs in non-WSSUS GA propagation channels. In this work, we consider the GA channel as non-WSSUS and individual MPCs across receiver positions are represented as time series based on the Euclidean distance between channel parameters of the MPCs. These time series representations, referred to as path bins, are analyzed using a semi-Markov chain model. The channel parameter variations and dependencies between path bins are used to predict the lifespan of path bins using weighted sum method, machine learning classifiers, and deep neural networks. For comparison, the birth and death of path bins are also modeled using a Poisson distribution and a Markov chain. Simulation results demonstrate that deep neural networks offer highly accurate predictions for the lifespan (including death) of MPC path bins in the considered GA propagation scenario.

关键词： Analytical models Simulation Time series analysis Scattering Artificial neural networks Machine learning Receivers Euclidean distance Autonomous aerial vehicles Millimeter wave communication

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：