检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Alehdaghi, Mahdi Shamsolmoali, Pourya Cruz, Rafael M. O. Granger, Eric Livia Ills Dept. of Systems Engineering Ets Montreal Canada University of York Dept. of Computer Science United Kingdom

ISBN: (纸本)9798331510831

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. Experiments11Our 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. © 2025 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Advances in Deep Learning for Tuberculosis Detection in Chest X-Rays: A Review of Diagnostic Accuracy 3

Advances in Deep Learning for Tuberculosis Detection in Ches...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Jayakumar, K. Muthupandi, G. Dhayanidhi, R. Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of Technology Tamilnadu Chennai600069 India

ISBN: (纸本)9798331527549

Tuberculosis (TB) is one of the leading causes of deaths globally, mainly in low- and middle-income countries. Early and accurate detection is crucial for effective treatment and disease control. In this paper, models like CNNs-VGG16, ResNet, and DenseNet, to name a few, are taken into an exhaustive study. Optimization techniques, including transfer learning and ensemble methods, which can increase accuracy in the challenging diverse clinical settings, will be presented. Equitable healthcare outcome is achieved in terms of future research directions which include representative datasets and interpretability of the model. © 2025 IEEE.

关键词： Disease control

来源：评论

学校读者我要写书评

暂无评论

Smart ANPR: A Checkpoint-Based Toll and Parking Management System Using Hybrid OCR and Blockchain 3

Smart ANPR: A Checkpoint-Based Toll and Parking Management S...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Samarth, M.N. Gopisetti, Sampriti Chaitra, M. Bnm Institute of Technology Affiliated to Vtu Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331515911

Automated Number Plate Recognition is one of the most important applications of computer vision, employed in the enforcement of traffic law, vehicular management, security, and even at toll collection. This paper proposed an advanced system for ANPR that can move away from the traditional booth and establish a checkpoint. The strategically located cameras with checkpointing will automatically capture the plates of passing vehicles, permitting road tax and parking fees to be deducted without making contact. A hybrid approach that combines the capabilities of OpenCV, Tesseract OCR, and deep-learningbased OCR models helps tackle such challenges as stable images from live video feeds and highly accurate text recognition. To this end, since the system integrates high-resolution frame stabilization using OpenCV to ensure crystal clear captures, it further employs the use of YOLOv8 to boost the precision of real-time detection. The blockchain technology is further implemented to ensure that transactions are tamper proof, therefore ensuring secure and transparent billing systems. This makes the ANPR solution deployable on edge devices, which opens real-time processing capabilities for high-speed and high-volume environments, thereby offering a scalable and efficient approach for intelligent transportation and smart city applications. © 2025 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Smart Oral Health Monitor 3

Smart Oral Health Monitor

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Kamkar, Spandana Anilkumar Sanjay, Srushti Vaishnavi, P.S. Karthik, S. Bnm Institute of Technology Affiliated to Vtu Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331515911

Oral health is vital to overall well-being but is often overlooked due to inefficient monitoring tools and delayed diagnosis. This project presents a smart handheld device featuring a miniaturized camera for detecting oral issues like plaque, cavities, teeth discoloration and gum diseases in real-time. Using image processing and deep learning algorithms, the device provides precise feedback and actionable insights. Paired with a mobile application offering detailed analysis and recommendations, it empowers users to adopt proactive oral hygiene practices to prevent teeth disorder. © 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

Real-Time Traffic Management System Using YOLOv8 and CNN: A Deep Learning Approach with IoT Integration 1

Real-Time Traffic Management System Using YOLOv8 and CNN: A ...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Saklani, Sumit Manchanda, Mahesh Sharma, Raman Singh, Devendra Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to be University Dept. of Computer Application Dehradun India

ISBN: (纸本)9798331518578

Traffic management also plays a crucial role in urban planning and development, with pressing challenges related to congestion, safety, and environmental impact. In this study, we proposed a real time traffic control system using YOLOv8 and CNNs combined with Internet of Things (IoT) technologies. As a high-performing object detection model, YOLOv8 is able to accurately and rapidly detect vehicles, pedestrians, and other traffic objects. When combined with CNN based data analytics, the proposed system can successfully monitor traffic flow, discover irregularities, and control the signals dynamically. Creating a cohesive framework for intelligent decision-making IoT integration ensures real-time data acquisition from sensors, cameras and edge devices. IoT framework for a smart urban environment the proposed architecture provides the versatility through scalability, low latency, and adjustment to several urban perspective scenarios. The combination leads to greatly enhanced traffic flow efficiency, accident prevention and environmental impact reduction as experimental results show. With data till October 2023, this study resolves a gap between the developing field of deep learning and the Internet of Things (IoT), that creates to be utilized to connect to advanced town environments. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

LiDAR-Based Elderly Fall Detection System for Indoor Environments Using Neural Network Algorithms 4

LiDAR-Based Elderly Fall Detection System for Indoor Environ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Vignesh, Puthucode Ganesh Nithin Kumar, S. Senthil Kumar, T. Jeyakumar, G. Amrita School of Computing Dept. of Computer Science and Engineering Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798331523923

Fall detection systems are critical in elderly care and healthcare monitoring, but traditional camera-based solutions raise significant privacy concerns. This research presents a novel approach utilizing LiDAR (Light Detection and Ranging) sensors for fall detection in indoor environments, addressing privacy issues while maintaining high accuracy. We introduce LiFall, a new dataset captured using a Velodyne VLP 16 Puck LiDAR sensor, comprising 12 scenes and over 500 frames simulating various fall scenarios (including back falls, bed falls, and walking falls), contributing to the scarcity of LiDAR-based fall detection datasets. Our methodology employs two advanced deep learning architectures: Annularly Convolutional Neural Networks (ACNN) and Dynamic Graph Convolutional Neural Networks (DGCNN). Evaluating these models on both the ModelNet40 dataset and our custom LiFall dataset, results show DGCNN outperforms ACNN, achieving an accuracy of 84% on the ModelNet40 dataset with a 70:30 train-test split. On the LiFall dataset, despite challenges with dataset imbalance and achieving lower detection accuracy even after data augmentation, our approach demonstrates the potential of LiDAR-based fall detection systems. Compared to other fall detection methods, our LiDAR-based system offers significant advantages beyond privacy preservation, such as robust performance in low-light conditions and the ability to capture detailed 3D spatial information. While our current implementation is limited to laboratory settings, future work will focus on real-world deployments and further addressing dataset imbalance issues to enhance overall system performance. This research contributes to the field by providing a privacy-preserving, high-performance alternative to camera-based fall detection systems, paving the way for more acceptable monitoring solutions in sensitive indoor environments. © 2025 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity for Industrial IoT: A Review on Vulnerabilities and Attacks 8

Cybersecurity for Industrial IoT: A Review on Vulnerabilitie...

引用

8th International Conference on Electronics, Materials engineering and Nano-Technology, IEMENTech 2025

作者： Kumari, Reetu Kumar, Sunil Amandeep Dutta, Kamlesh Kumari, Aparna Guru Jambheshwar University of Science and Technology Dept. of Computer Science & Engineering Haryana Hisar India Guru Jambheshwar University of Science and Technology Dept. of AI & Data Science Haryana Hisar India National Institute of Technology Hamirpur Dept. of Computer Science & Engineering Himachal Pardesh India Institute of Technology Nirma University Dept. of Computer Science & Engineering Gujarat Ahmedabad India

ISBN: (纸本)9798331520762

Internet has evolved from a network of connecting people to a network of connecting things, leading to a more complex and sophisticated network of Industrial Things, known as Industrial IoT (IIoT) today. This evolution has revolutionized the traditional Industrial system into real-time smarter systems that enhanced overall efficiency and productivity. Despite its benefits, the interconnected nature of IIoT, expanded the attack surface, exposing the systems to new crucial and complex cybersecurity threats. Several real time attacks on various industries as mentioned in this paper and the increasing cybersecurity cost over the years, clearly states the need of robust security solutions. To deeply understand the cybersecurity aspect, we provided a comprehensive study of attacks and vulnerabilities in this paper. In this paper, we did a indept. study of various IIoT related severe attacks and aspects related to these attacks, like vulnerabilities, impacts, potential solutions etc. We also provided future research directions to help the research community, to work upon and develop more robust and efficient cybersecurity solutions. © 2025 IEEE.

关键词： attacks cybersecurity etc IIoT Industrial IoT IoT vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

A New Three-phase Multi-mode AC/DC LLC Converter with Output-controlled Active Rectifier (with V2G and G2V functions) For Fast DC Charging Application 14

A New Three-phase Multi-mode AC/DC LLC Converter with Output...

引用

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Xia, Xiaoyi Lam, John York University Dept. of Electrical Engineering and Computer Science Toronto Canada

ISBN: (纸本)9798331516116

This paper proposes a new three-phase multi-mode AC/DC LLC resonant converter with an output-controlled active rectifier for electric vehicle (EV) fast DC charging applications. In the proposed approach, two low-frequency bidirectional switches at the primary side in each phase of the converter allow vehicle-to-grid (V2G, i.e. DC/AC mode) and grid-to-vehicle (G2V, i.e. AC/DC mode) modes. When the proposed converter operates in AC/DC mode, each phase consists of an integrated bridgeless boost power factor corrector and an LLC resonant converter at the primary side. Output voltage regulation is managed by switches on the high frequency transformer's secondary side output rectifier in each phase, with soft-switching operation achieved in all the switches. When the proposed three-phase converter operates in DC/AC mode, each phase consists of a half-bridge DC/DC resonant converter cascaded with a half-bridge grid-side inverter. The operation of the proposed converter is explained in this paper. Results from a 20kW, 480VLLrms/350Vdc, 130kHz design, and a hardware test on a 130kHz, 250V-output proof-of-concept prototype are presented to validate the functionality of the proposed converter. © 2025 IEEE.

关键词： Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

LeXNet++: Layer-wise eXplainable ResUNet++ framework for segmentation of colorectal polyp cancer images

引用

Neural Computing and Applications 2025年第1期37卷 213-229页

作者： Das, Surajit Khan, Soumya Suvra Sengupta, Diganta Debashis, De Dept. of Information Technology Meghnad Saha Institute of Technology Behind Urbana Complex Near Ruby General Hospital Anandapur Rd Uchhepota Kolkata700150 India Dept. of Computer Science & Engineering Meghnad Saha Institute of Technology Behind Urbana Complex Near Ruby General Hospital Anandapur Rd Uchhepota Kolkata700150 India Dept. of Computer Science & Engineering Heritage Institute of Technology Chowbaga Road West Bengal Anandapur Kolkata700107 India Dept. of Computer Science & Engineering Maulana Abul Kalam Azad University of Technology West Bengal NH-12 Simhat Haringhata West Bengal Nadia741249 India

Colorectal polyps are benign lesions that develop in the colon and can progress to cancer if left untreated. Clinical observations from medical images are often preferred over computational results due to the lack of trust in the machine learning models, thereby posing serious challenge for the explainability of the results. In order to computationally diagnose colorectal polyps from cancerous images and explain the results, we propose a Layer-wise eXplainable ResUNet++ (LeXNet++) framework for segmentation of the cancerous images, followed by layer-wise explanation of the results. We utilize a publicly accessible dataset that contains of 612 raw images with a resolution of 256×256×3 and an additional 612 clinically annotated and labeled images with a resolution of 256×256×1, which includes the infected region. The LeXNet++ framework comprises of three components—encoder, decoder and the bridge. The encoder and the decoder components each comprise of four layers. Each of the four layers in the encoder and the decoder comprises of 14 and 11 internal sub-layers, respectively. Among the sub-layers of the encoder and the decoder, there are three 3×3 convolutional layers with an additional 3×3 convolution-transpose layer in the decoder. The output of each of the sub-layers has been explained through heatmap generation after each iteration which have been further explained. The encoder and the decoder are connected by the bridge which comprises of three sub-layers. The results obtained from these three sub-layers have also been explained to inculcate trust in the findings. In this study, we have used three models to segment the images, namely UNet, ResUNet, and proposed LeXNet++. LeXNet++ exhibited the best result among the three models in terms of performance;hence, only LeXNet++ was explained layer-wise. Apart from explanation of the results fetched in this study, the performance of the proposed explainable model has been observed to be 2% greater than the existing poly

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A glimpse ahead: Forecasting 5.5-s human vigilance for enhanced safety in Industry 5.0

引用

Biocybernetics and Biomedical engineering 2025年第2期45卷 258-268页

作者： Cinquetti, Ettore Siviero, Ilaria Babiloni, Fabio Menegaz, Gloria Storti, Silvia F. Dept. of Computer Science University of Verona Verona Italy Dept. of Engineering for Innovation Medicine University of Verona Verona Italy Dept. of Molecular Medicine Sapienza University of Rome Rome Italy

In the context of Industry 5.0 and human-robot interaction, ensuring the safety of operators by avoiding human errors is crucial. Monitoring vigilance decrement is an essential aspect of this effort, aimed at mitigating safety risks and enhancing productivity. A potentially promising solution to this challenge is using a passive brain-computer interface (BCI) based on electroencephalography (EEG) recordings. However, its application in industrial settings has yet to be explored in-dept.. This study uses EEG data to introduce a novel experimental protocol and analysis pipeline to predict vigilance degradation in an industrial research laboratory. The dataset was gathered from ten healthy volunteers who observed a robotic arm for 23 min. The EEG power spectrum over time was computed using the continuous wavelet transform (CWT). After confirming growth in power for the α band using a linear regression model, we forecast its trend using four models. As a conventional approach, we used the vector autoregressive (VAR) model, serving as a reference for comparison with three deep learning architectures: a temporal convolutional network (TCN), a gated recurrent unit (GRU) and an encoder-decoder (ED)-GRU. The proposed ED-GRU model outperformed the others showing accurate forecasts (mean absolute error = 0.048, R² = 0.726) up to 5.5 s. The findings suggest that monitoring vigilance degradation in Industry 5.0 is a feasible strategy to prevent human accidents and reduced performance during repetitive tasks. © 2025 Nalecz Institute of Biocybernetics and Biomedical engineering of the Polish Academy of sciences

关键词： Brain-computer interface Deep-learning Electroencephalography Forecasting Industry 5.0. Vigilance

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：