检索结果-内蒙古大学图书馆

Toward AI-Powered Edge intelligence for Object Detection in Self-Driving Cars: Enhancing IoV Efficiency and Safety

IEEE Internet of Things Journal 2025年第11期12卷 16990-16997页

作者： Ahmed, Imran Ahmad, Misbah Siddiqi, Muftooh Ur Rehman Chehri, Abdellah Jeon, Gwangill Anglia Ruskin University School of Computing and Information Science CambridgeCB1 1PT United Kingdom University of the West of England Centre for Machine Vision Bristol Robotics Laboratory BristolBS16 1QY United Kingdom Hartpury University Department of Animal and Agriculture GloucesterGL19 3BE United Kingdom Aston University College of Engineering and Physical Sciences BirminghamB4 7ET United Kingdom Royal Military College of Canada Department of Mathematics and Computer Science KingstonONK7K 7B4 Canada Incheon National University Department of Embedded Systems Engineering Incheon22012 Korea Republic of

In the rapidly advancing field of intelligent transportation systems, integrating artificial intelligence (AI) with edge computing presents a promising way to enhance the safety and efficiency of the Internet of Vehicles (IoV). This study explores and presents a deep learning-based object detection model within an edge computing framework which aims to facilitate real time object detection in self driving cars. Using an urban traffic scenarios-based dataset, our research shows the ability of the model to accurately detect and classify various objects important for autonomous driving. The YOLOv8 model is used in this work due to its optimal balance between accuracy and computational efficiency. This model has also demonstrated its worth by achieving good performance results, including an average precision of 0.79, a recall of 0.62, and an F1-score of 0.69. The results are demonstrated by a detailed confusion matrix, highlighting the model’s effectiveness in complex driving environments and underscoring its reliability for in-vehicle deployment. By implementing AI directly on edge devices within vehicles, our approach might be helpful in significantly reducing latency, boosting decision-making speed, and enhancing data privacy by minimising dependence on cloud processing. The findings not only support the model’s capabilities but also illustrate the practical benefits of edge intelligence in autonomous vehicles. These benefits, such as faster decision making and improved data privacy, contribute effectively to the IoV infrastructure. This study marks a substantial step toward recognizing the possibility of AI-enhanced edge computing in driving the next generation of autonomous vehicle technology. © 2014 IEEE.

关键词： Artificial intelligence (AI) autonomous vehicles deep leaning edge computing Internet of Vehicles (IoV)

来源：评论

学校读者我要写书评

暂无评论

VisioPhysioENet: Multimodal Engagement Detection using Visual and Physiological Signals

arXiv

引用

arXiv 2024年

作者： Singh, Alakhsimar Verma, Nischay Goyal, Kanav Singh, Amritpal Kumar, Puneet Li, Xiaobai Computer Science and Engineering Department National Institute of Technology Jalandhar India Center for Machine Vision and Signal Analysis University of Oulu Finland The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China

This paper presents VisioPhysioENet, a novel multimodal system that leverages visual and physiological signals to detect learner engagement. It employs a two-level approach for extracting both visual and physiological features. For visual feature extraction, Dlib is used to detect facial landmarks, while OpenCV provides additional estimations. The face_recognition library, built on Dlib, is used to identify the facial region of interest specifically for physiological signal extraction. Physiological signals are then extracted using the plane-orthogonal-to-skin method to assess cardiovascular activity. These features are integrated using advanced machine learning classifiers, enhancing the detection of various levels of engagement. We thoroughly tested VisioPhysioENet on the DAiSEE dataset. It achieved an accuracy of 63.09%. This shows it can better identify different levels of engagement compared to many existing methods. It performed 8.6% better than the only other model that uses both physiological and visual features. Copyright © 2024, The Authors. All rights reserved.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions

arXiv

引用

arXiv 2024年

作者： Yan, Sheng Liu, Mengyuan Wang, Yong Liu, Yang Chen, Chen Liu, Hong School of Artificial Intelligence Chongqing University of Technology Chongqing401120 China Key Laboratory of Machine Perception Shenzhen Graduate School Peking University Shenzhen518055 China College of Computer Science Sichuan University Chengdu610065 China Center for Research in Computer Vision University of Central Florida FL32826 United States

In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query. Considering that 3D human motions are captured using specialized motion capture devices, motions with only a few joints lack complex scene information like objects and lighting. Due to this character, motion data has low contextual richness and semantic ambiguity between frames, which limits the accuracy of predictions made by current video localization frameworks extended to TSLM to only a rough level. To refine this, we devise two novel label-prior-assisted training schemes: one embed prior knowledge of foreground and background to highlight the localization chances of target moments, and the other forces the originally rough predictions to overlap with the more accurate predictions obtained from the flipped start/end prior label sequences during recovery training. We show that injecting label-prior knowledge into the model is crucial for improving performance at high IoU. In our constructed TSLM benchmark, our model termed MLP achieves a recall of 44.13 at IoU@0.7 on the BABEL dataset and 71.17 on HumanML3D (Restore), outperforming prior works. Finally, we showcase the potential of our approach in corpus-level moment retrieval. Our source code is openly accessible at https://***/eanson023/mlp. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Robust 3D Face Alignment with Multi-Path Neural Architecture Search

arXiv

引用

arXiv 2024年

作者： Jiang, Zhichao Wang, Hongsong Teng, Xi Li, Baopu Baidu Beijing China Department of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China Computer Vision Technology Institution Baidu Beijing China Baidu Research Baidu Sunnyvale United States

3D face alignment is a very challenging and fundamental problem in computer vision. Existing deep learning-based methods manually design different networks to regress either parameters of a 3D face model or 3D positions of face vertices. However, designing such networks relies on expert knowledge, and these methods often struggle to produce consistent results across various face poses. To address this limitation, we employ Neural Architecture Search (NAS) to automatically discover the optimal architecture for 3D face alignment. We propose a novel Multi-path One-shot Neural Architecture Search (MONAS) framework that leverages multi-scale features and contextual information to enhance face alignment across various poses. The MONAS comprises two key algorithms: Multi-path Networks Unbiased Sampling Based Training and Simulated Annealing based Multi-path One-shot Search. Experimental results on three popular benchmarks demonstrate the superior performance of the MONAS for both sparse alignment and dense alignment. © 2024, CC BY.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Quantum Gradient Class Activation Map for Model Interpretability

Quantum Gradient Class Activation Map for Model Interpretabi...

引用

IEEE Workshop on Signal Processing Systems (SIPS)

作者： Hsin-Yi Lin Huan-Hsin Tseng Samuel Yen-Chi Chen Shinjae Yoo Department of Mathematics and Computer Science Seton Hall University South Orange NJ USA Artificial Intelligence & Machine Learning Department Brookhaven National Laboratory Upton NY USA Wells Fargo New York NY USA

ISBN: (数字)9798350373752

ISBN: (纸本)9798350373769

Quantum machine learning (QML) has recently made significant advancements in various topics. Despite the successes, the safety and interpretability of QML applications have not been thoroughly investigated. This work proposes using Variational Quantum Circuits (VQCs) for activation mapping to enhance model transparency, introducing the Quantum Gradient Class Activation Map (QGrad-CAM). This hybrid quantum-classical computing framework leverages both quantum and classical strengths and gives access to the derivation of an explicit formula of feature map importance. Experimental results demonstrate significant, fine-grained, class-discriminative visual explanations generated across both image and speech datasets.

关键词： Location awareness Visualization Quantum advantage Computational modeling Conferences machine learning Signal processing Safety Quantum circuit Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Perivascular spaces relate to the course and cognition of Huntington’s disease

引用

Translational Neurodegeneration 2023年第1期12卷 546-549页

作者： Xiao-Yan Li Juan-Juan Xie Jin-Hong Wang Yu-Feng Bao Yi Dong Bin Gao Ting Shen Pei-Yu Huang Hao-Chao Ying Han Xu Anna Wang Roe Hsin-Yi Lai Zhi-Ying Wu Department of Medical Genetics and Center for Rare Diseases Department of Neurology in Second Affiliated HospitalKey Laboratory of Medical Neurobiology of Zhejiang ProvinceZhejiang University School of MedicineHangzhouChina Interdisciplinary Institute of Neuroscience and Technology College of Biomedical Engineering and Instrument ScienceKey Laboratory for Biomedical Engineering of Ministry of EducationZhejiang UniversityHangzhouChina College of Computer Science and Technology Zhejiang UniversityHangzhouChina Department of Radiology Second Affiliated HospitalZhejiang University School of MedicineHangzhouChina School of Public Health Zhejiang UniversityHangzhouChina MOE Frontier Science Center for Brain Research and Brain-Machine Integration School of Brain Science and Brain MedicineZhejiang UniversityHangzhouChina CAS Center for Excellence in Brain Science and Intelligence Technology ShanghaiChina

Huntington’s disease(HD)is an autosomal dominant neurodegenerative disease that is caused by a cytosine-adenine-guanine(CAG)expansion in the first exon of the huntingtin(HTT)gene,which codes for the hun-tingtin *** typically manifests with a triad of symptoms,including motor disorders,cognitive impair-ment and psychiatric disturbances[1].HD primar-ily affects the basal ganglia(BG),especially the caudate and putamen,after which it extends to more widespread gray and white matter[2].Perivascular spaces(PVSs)are fluid-filled extensions of the subarachnoid spaces that enclose cerebral blood vessels and extend from the cer-ebral cortex through the brain *** physi-ological role of PVSs is the drainage of brain interstitial fluid into perivascular pathways for the elimination of waste products through the glymphatic drainage *** increasing number of studies have demonstrated that enlarged PVSs indicate glymphatic dysfunction and are associated with many neurological diseases,such as Alzheimer’s disease,Parkinson’s disease and small vessel disease[3].With the advantage of strong field strengths,7.0 T images show superior resolution and signal-to-noise ratios than 3.0 T,which facilitate the visualization of *** automated segmentation methods could accurately identify PVS in a short time with no inter-rater *** the current study,we used U-shaped networks(U-net),a class of deep learning methods,to explore the PVS distribution in HD and *** date,PVS distribution in HD is still *** two studies have investigated PVSs in HD,and both dem-onstrated increased visible PVS burden in manifest HD compared to controls[4,5].However,whether PVS bur-den increases in premanifest HD(pre-HD)individuals remains unknown,and the relationship of PVS with cog-nitive decline has never been studied.

关键词： Huntington filled elimination

来源：评论

学校读者我要写书评

暂无评论

Clustering Interval and Triangular Granular Data: Modeling, Execution, and Assessment

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第6期36卷 10000-10014页

作者： Yiming Tang Wenbin Wu Witold Pedrycz Jianwei Gao Xianghui Hu Zhaohong Deng Rui Chen Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Hefei China Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada School of Computer and Information Hefei University of Technology Hefei China Faculty of Automatic Control Electronics and Computer Science Silesian University of Tecghnology Gliwice Poland Research Center of Performance and Productivity Analysis Istinye University Istanbul TÃrkiye School of Computer Science and Engineering Southeast University Nanjing China School of Artificial Intelligence and Computer Jiangnan University Wuxi Jiangsu China

In current granular clustering algorithms, numeric representatives were selected by users or an ordinary strategy, which seemed simple; meanwhile, weight settings for granular data could not adequately express their structural characteristics. Aiming at these problems, in this study, a new scheme called a granular weighted kernel fuzzy clustering (GWKFC) algorithm is put forward. We propose the representative selection and granularity generation (RSGG) algorithm enlightened by the density peak clustering (DPC) algorithm. We build interval and triangular granular data on the strength of numeric representatives obtained by RSGG under the principle of justifiable granularity (PJG), in which we establish some combinations of functions and boundary constraints and prove their properties. Furthermore, we present a novel distance formula via the kernel function for granular data and design new weights to affect the coverage and specificity of granular data. In addition, based upon these factors, we come up with the GWKFC algorithm of granular clustering, and its performance with different granularity is assessed. To sum up, a macro framework involving granular modeling, granular clustering, and assessment has been set up. Lastly, the GWKFC algorithm and ten other granular clustering algorithms are compared by experiments on some artificial and UCI datasets together with datasets with large data or those of high dimensionality. It is found that the GWKFC algorithm can provide better granular clustering results by contrast with other algorithms. The originality is embodied as follows. First, we improve the previous density radius and present the RSGG algorithm to acquire numeric representatives. Second, we propose a new strategy to determine granular data boundaries and further obtain novel weights enlightened by the idea of volume. Lastly, we employ the kernel function to calculate the distance between granular data, which has a stronger spatial division ability than the pr

关键词： Clustering algorithms Data models Computational modeling Numerical models Kernel Phase change materials Granular computing Uncertainty Fuzzy sets Noise

来源：评论

学校读者我要写书评

暂无评论

Dual encoding feature filtering generalized attention UNET for retinal vessel segmentation

引用

四川大学学报(自然科学版) 2025年第1期62卷 79-95页

作者： ISLAM Md Tauhidul WU Da-Wen TANG Qing-Qing ZHAO Kai-Yang YIN Teng LI Yan-Fei SHANG Wen-Yi LIU Jing-Yu ZHANG Hai-Xian Machine Intelligence Laboratory College of Computer ScienceSichuan UniversityChengdu 610064China Department of Ophthalmology West China HospitalSichuan UniversityChengdu 610041China West China School of Medicine Sichuan UniversityChengdu 610041China

Retinal blood vessel segmentation is crucial for diagnosing ocular and cardiovascular *** the introduction of U-Net in 2015 by Olaf Ronneberger significantly advanced this field,yet issues like limited training data,imbalance data distribution,and inadequate feature extraction persist,hindering both the segmentation performance and optimal model *** these critical issues,the DEFFA-Unet is proposed featuring an additional encoder to process domain-invariant pre-processed inputs,thereby improving both richer feature encoding and enhanced model generalization.A feature filtering fusion module is developed to ensure the precise feature filtering and robust hybrid feature *** response to the task-specific need for higher precision where false positives are very costly,traditional skip connections are replaced with the attention-guided feature reconstructing fusion ***,innovative data augmentation and balancing methods are proposed to counter data scarcity and distribution imbalance,further boosting the robustness and generalization of the *** a comprehensive suite of evaluation metrics,extensive validations on four benchmark datasets(DRIVE,CHASEDB1,STARE,and HRF)and an SLO dataset(IOSTAR),demonstrate the proposed method’s superiority over both baseline and state-of-the-art *** the proposed method significantly outperforms the compared methods in cross-validation model generalization.

关键词： Vessel segmentation Data balancing Data augmentation Dual encoder Attention Mechanism Model generalization

来源：评论

学校读者我要写书评

暂无评论

FedDA: Faster Framework of Local Adaptive Gradient Methods via Restarted Dual Averaging

arXiv

引用

arXiv 2023年

作者： Li, Junyi Huang, Feihu Huang, Heng Department of Electrical and Computer Engineering University of Pittsburgh Pittsburgh United States College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Federated learning (FL) is an emerging learning paradigm to tackle massively distributed data. In Federated Learning, a set of clients jointly perform a machine learning task under the coordination of a server. The FedAvg algorithm is one of the most widely used methods to solve Federated Learning problems. In FedAvg, the learning rate is a constant rather than changing adaptively. The adaptive gradient methods show superior performance over the constant learning rate schedule;however, there is still no general framework to incorporate adaptive gradient methods into the federated setting. In this paper, we propose FedDA, a novel framework for local adaptive gradient methods. The framework adopts a restarted dual averaging technique and is flexible with various gradient estimation methods and adaptive learning rate formulations. In particular, we analyze FedDA-MVR, an instantiation of our framework, and show that it achieves gradient complexity Õ(∊−1.5) and communication complexity Õ(∊−1) for finding a stationary point ∊. This matches the best known rate for first-order FL algorithms and FedDA-MVR is the first adaptive FL algorithm that achieves this rate. We also perform extensive numerical experiments to verify the efficacy of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

LC2R-ViT: Long-Range Cross-Residual vision Transformer for Medical Image Classification

LC2R-ViT: Long-Range Cross-Residual Vision Transformer for M...

引用

Complex Systems and Intelligent science (CSIS-IAC), International Annual Conference on

作者： Zhenwei Zhang Lei Zhang Lituan Wang Ke Zhong Haiying Huang Machine Intelligence Laboratory College of Computer Science Sichuan University Chengdu China Information Management Department West China Second University Hospital Sichuan University Chengdu China

With the development of Convolutional Neural Network (CNN) as well as the rise of vision Transformer (ViT), approaches based on these two series are widely used in various visual tasks. However, the performance of CNN-based approaches and transformer-based approaches can be very different for different datasets. In this work, we firstly investigate the applicability of CNN-based and transformer-based approaches for different datasets. Furthermore, in order to integrate advantages of CNN and transformer, a novel network named LC2R-ViT is designed to introduce the ability of extracting local but detailed features of CNN into the vision Transformer through a long-range cross-residual mechanism. To evaluate the effectiveness of the proposed LC2R-ViT, MedMNIST dataset that with the diversity among the tasks, the data scales and the modalities is employed. The comparative experiments have conducted and the experimental results have shown that the proposed LC2R-ViT can outperform CNN and vision Transformer on the most subsets of MedMNIST dataset. That means the proposed LC2R-ViT can improve the generalization of transformer-based approaches by introducing the CNN.

关键词：

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：