检索结果-内蒙古大学图书馆

Sparse Channel Reconstruction: A Generative Adversarial Network-Based Approach

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Zhang, Yuxin He, Ruisi Yang, Mi Wang, Chenlong Qiu, Zhicheng Lu, Yang Ai, Bo Beijing Jiaotong University School of Electronics and Information Engineering Beijing100044 China Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation The Frontiers Science Center for Smart High-speed Railway System Beijing100044 China Beijing Jiaotong University School of Computer and Information Technology Beijing100044 China

Wireless channels typically exhibit a sparse structure, with sparsity regarded as an inherent characteristics. A deeper understanding and accurate representation of channel sparsity contribute to a more comprehensive revelation of channel features and structure, thereby enhancing the performance of communication systems. However, current research on channel sparsity remains limited to the measurement, and traditional channel models have not sufficiently incorporated this critical characteristic. In this paper, considering channel deep sparse characteristics, a generative adversarial network (GAN)-based channel sparsity-tunable framework is proposed to reconstruct channel samples with various levels of sparsity. Specifically, continuous sparsity factors and a sparsity measurement module are introduced to manipulate and predict the sparsity of the reconstructed channel in the framework design. Channel power and delay are employed for model training to better consider the channel behavior of sparsity. Furthermore, the mutual information between input sparsity factors and reconstructed channels is enhanced to ensure that the sparsity factor has an actual impact on the level of reconstructed channel sparsity, thereby enabling the flexible and continuous reconstruction of channels with varying levels of sparsity. Simulation results prove that the proposed framework can effectively and accurately reconstruct channels with different levels of sparsity by changing sparsity factor, as well as providing good performance in measuring the sparsity of wireless channel. Finally, sparse manipulation performance is further validated using channel capacity simulation. © 2024 IEEE.

关键词： Signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Traffic Light Control system Based on Reinforcement Learning and Adaptive Timing 1

引用

2nd International Conference on Neural Computing for Advanced Applications, NCAA 2021

作者： Wu, Pengchun Song, Bin Chen, Xinhai Liu, Bingyi School of Computer Science and Technology Wuhan University of Technology Wuhan China Chongqing Engineering Research Center of Research and Testing for Automated Driving System and Intelligent Connected Vehicle Chongqing China

ISBN: (数字)9789811651885

ISBN: (纸本)9789811651878

Intelligent traffic light control is a key approach to improve the efficiency of transportation system. However, existing intelligent traffic light control methods usually only adjust phase with fixed duration or just adjust duration in a fixed phase circle. In actual scenarios with complicated and dynamic traffic flow, these methods cannot give the optimal phase and duration corresponding to the current situation because of their restricted traffic control mode, which limits the potential to further improve the efficiency of traffic transportation. For this sake, we propose a novel traffic light control system that achieves completely dynamic control. The system is able to efficiently adjust both phase and duration via deep reinforcement learning and adaptive timing. Among them, the reinforcement learning model is specially used for phase decision and the adaptive timing algorithm used for duration decision is designed for effective utilization of green time in each phase. We test our system in different traffic flows and explore the relationship between optimal duration and traffic flow. We also verify the superb performance of our traffic light control system in a whole-day traffic scene. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection 39

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Dist...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dai, Tao Lin, Yang Guo, Hang Wang, Jinbao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen City Key Laboratory of Embedded System Design Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)157735897X

Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of the spatial or channel domain from the teacher model to the student model, it allows for a more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains and find there exists a strong correlation between them, i.e. the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, we introduce channel-wise spatial feature distillation and global channel attention distillation, using information from both domains to improve the accuracy of the student network. Experiments demonstrate that our DCSF-KD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and based on RetinaNet and FCOS with ResNet-50 on MS COCO, our DCSF-KD can achieve 41.9% and 44.1% mAP, respectively. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Graph Sampling based Fairness-aware Recommendation over Sensitive Attribute Removal

Graph Sampling based Fairness-aware Recommendation over Sens...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Shenghao Liu Guoyang Wu Xianjun Deng Hongwei Lu Bang Wang Laurence Yang James J. Park Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea

Discrimination against different user groups has received growing attention in the recommendation field. To address this problem, existing works typically remove sensitive attributes that may cause discrimination through adversary learning to achieve fair recommendations. However, these approaches leverage all available interactions for learning user representations and overlook the fact that different interactions have varying relevance to users’ sensitive attributes. Ignoring this issue may weaken the effectiveness of adversary learning in removing sensitive attributes. To tackle this challenge, we propose a novel model called GS-FairRec, which distinguishes between user interactions to achieve better removal of sensitive attributes. The model consists of three modules: graph sampling-based representation learning, pseudo-user representation learning, and adversarial learning. Firstly, the graph sampling-based representation learning module removes some irrelevant neighbors from a user-item bipartite graph and employs a graph convolutional network (GCN) to learn user/item representations. Next, items that are relevant to a user’s sensitive information but do not match their preferences are defined as the user’s pseudo-interest items, which are leveraged to learn the pseudo-user representation. In the adversarial learning module, the user’s two kinds of representations are fused for adversarial learning to remove sensitive information. Additionally, we design a new metric to measure the model’s ability to remove sensitive attributes based on how a generated recommendation list discloses the user’s sensitive attributes. Finally, we conduct experiments on two real-world datasets, and our results demonstrate the superiority of our proposed model in fairness tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPL: Empirical Prototype Learning for Deep Face Recognition

arXiv

引用

arXiv 2024年

作者： Fan, Weijia Wen, Jiajun Jia, Xi Shen, Linlin Zhou, Jiancan Li, Qiufu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Computer Vision Institute Shenzhen University Shenzhen518060 China School of Computer Science University of Birmingham Birmingham United Kingdom Aqara Lumi United Technology Coopration Shenzhen China

Prototype learning is widely used in face recognition, which takes the row vectors of coefficient matrix in the last linear layer of the feature extraction model as the prototypes for each class. When the prototypes are updated using the facial sample feature gradients in the model training, they are prone to being pulled away from the class center by the hard samples, resulting in decreased overall model performance. In this paper, we explicitly define prototypes as the expectations of sample features in each class and design the empirical prototypes using the existing samples in the dataset. We then devise a strategy to adaptively update these empirical prototypes during the model training based on the similarity between the sample features and the empirical prototypes. Furthermore, we propose an empirical prototype learning (EPL) method, which utilizes an adaptive margin parameter with respect to sample features. EPL assigns larger margins to the normal samples and smaller margins to the hard samples, allowing the learned empirical prototypes to better reflect the class center dominated by the normal samples and finally pull the hard samples towards the empirical prototypes through the learning. The extensive experiments on MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace demonstrate the effectiveness of EPL. Our code is available at https://***/WakingHours-GitHub/EPL. © 2024, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Estimating Complexity for Perception-based ADAS in Unstructured Road Environments

Estimating Complexity for Perception-based ADAS in Unstructu...

引用

IEEE Symposium on Intelligent Vehicle

作者： Imane Taourarti Ayesha Choudhary Vivek Kumar Paswan Aditya Kumar Arunkumar Ramaswamy Javier Ibanez-Guzman Bruno Monsuez Adriana Tapus Autonomous Systems and Robotics Lab/U2IS Computer Science and System Engineering (U2IS) ENSTA Paris Institut Polytechnique de Paris France Research Department Renault Group France School of Computer and Systems Sciences Jawaharlal Nehru University New Delhi India

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Advanced Driver Assistance systems (ADAS) are rapidly becoming a standard feature in modern road vehicles, enhancing safety and driver comfort. As ADAS adoption expands across diverse geographical and cultural regions, the performance of camera-based perception systems may vary significantly due to environmental and expected social behaviour of the different actors. This paper explores the referred factors and evaluates the traffic environment complexity for vehicles with different levels of automation. In particular, we propose a novel modeling and quantitative assessment approach for environment complexity. Specifically, we compare a perception model trained on United States dataset with a dataset from India, a nation characterized by unique traffic patterns, signage conventions, and cultural norms to assess its performance variation, and to lay the basis for proposing influencing factors of traffic environment complexity. We establish a scheme of referential and additional static factors and based on an expert evaluation, environment complexity is established. The effectiveness of the proposed approach is testified by naturalistic driving data. These findings pave the way for future research in intelligent driving and emphasize the importance of addressing cultural nuances as vehicle automation levels increase.

关键词： Measurement Automation Roads Road vehicles Globalization Complexity theory Safety

来源：评论

学校读者我要写书评

暂无评论

Multimodal Joint Prediction of Traffic Spatial-Temporal Data with Graph Sparse Attention Mechanism and Bidirectional Temporal Convolutional Network

SSRN

引用

SSRN 2024年

作者： Zhang, Dongran Yan, Jiangnan Polat, Kemal Alhudhaif, Adi Li, Jun Guangdong Provincial Key Laboratory of Intelligent Transportation System School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518107 China Department of Electrical and Electronics Engineering Faculty of Engineering Bolu Abant Izzet Baysal University Bolu Turkey Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj11942 Saudi Arabia

Traffic flow prediction plays a crucial role in the management and operation of urban transportation systems. While extensive research has been conducted on predictions for individual transportation modes, there is relatively limited research on joint prediction across different transportation modes. Furthermore, existing multimodal traffic joint modeling methods often lack flexibility in spatial-temporal feature extraction. To address these issues, we propose a method called Graph Sparse Attention Mechanism with Bidirectional Temporal Convolutional Network (GSABT) for multimodal traffic spatial-temporal joint prediction. First, we use a multimodal graph multiplied by self-attention weights to capture spatial local features, and then employ the Top-U sparse attention mechanism to obtain spa-tial global features. Second, we utilize a bidirectional temporal convolutional network to enhance the temporal feature correlation between the output and input data, and extract inter-modal and intra-modal temporal features through the share-unique module. Finally, we have designed a multimodal joint prediction framework that can be flexibly extended to both spatial and temporal dimensions. Extensive experiments conducted on three real datasets indicate that the proposed model consistently achieves state-of-the-art predictive performance. © 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

Scavenger: Better Space-Time Trade-Offs for Key-Value Separated LSM-trees

Scavenger: Better Space-Time Trade-Offs for Key-Value Separa...

引用

International Conference on Data engineering

作者： Jianshun Zhang Fang Wang Sheng Qiu Yi Wang Jiaxin Ou Junxun Huang Baoquan Li Peng Fang Dan Feng Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology China Shenzhen Huazhong University of Science and Technology Research Institute Bytefrance Inc.

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Key- Value Stores (KVS) implemented with log- structured merge-tree (LSM-tree) have gained widespread ac-ceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction process. While KV-separated LSM-trees successfully tackle this issue, they also bring about substantial space am-plification problems, a concern that cannot be overlooked in cost-sensitive scenarios. Garbage collection (GC) holds significant promise for space amplification reduction, yet existing GC strategies often fall short in optimization performance, lacking thorough consideration of workload characteristics. Additionally, current KV-separated LSM-trees also ignore the adverse effect of the space amplification in the index LSM-tree. In this paper, we systematically analyze the sources of space amplification of KV- separated LSM-trees and introduce Scavenger, which achieves a better trade-off between performance and space amplification. Scavenger initially proposes an I/O-efficient garbage collection scheme to reduce I/O overhead and incorporates a space-aware compaction strategy based on compensated size to minimize the space amplification of index LSM-trees. Extensive experiments show that Scavenger significantly improves write performance and achieves lower space amplification than other KV-separated LSM-trees (including BlobDB, Titan, and TerarkDB).

关键词： Data engineering Compaction Indexes Optimization

来源：评论

学校读者我要写书评

暂无评论

Multimodal Joint Prediction of Traffic Spatial-Temporal Data with Graph Sparse Attention Mechanism and Bidirectional Temporal Convolutional Network

arXiv

引用

arXiv 2024年

Traffic flow prediction plays a crucial role in the management and operation of urban transportation systems. While extensive research has been conducted on predictions for individual transportation modes, there is relatively limited research on joint prediction across different transportation modes. Furthermore, existing multimodal traffic joint modeling methods often lack flexibility in spatial-temporal feature extraction. To address these issues, we propose a method called Graph Sparse Attention Mechanism with Bidirectional Temporal Convolutional Network (GSABT) for multimodal traffic spatial-temporal joint prediction. First, we use a multimodal graph multiplied by self-attention weights to capture spatial local features, and then employ the Top-U sparse attention mechanism to obtain spatial global features. Second, we utilize a bidirectional temporal convolutional network to enhance the temporal feature correlation between the output and input data, and extract inter-modal and intra-modal temporal features through the share-unique module. Finally, we have designed a multimodal joint prediction framework that can be flexibly extended to both spatial and temporal dimensions. Extensive experiments conducted on three real datasets indicate that the proposed model consistently achieves state-of-the-art predictive performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Epl: Empirical Prototype Learning for Deep Face Recognition

SSRN

引用

SSRN 2024年

Prototype learning is widely used in face recognition, which takes the row vectors of coefficient matrix in the last linear layer of the feature extraction model as the prototypes for each class. When the prototypes are updated using the facial sample feature gradients in the model training, they are prone to being pulled away from the class center by the hard samples, resulting in decreased overall model performance. this paper, we explicitly define prototypes as the expectations of sample features in each class and design the empirical prototypes using the existing samples in the dataset. We then devise a strategy to adaptively update these empirical prototypes during the model training based on the similarity between the sample features and the empirical prototypes. Furthermore, we propose an empirical prototype learning (EPL) method, which utilizes an adaptive margin parameter with respect to sample features. EPL assigns larger margins to the normal samples and smaller margins to the hard samples, allowing the learned empirical prototypes to better reflect the class center dominated by the normal samples and finally pull the hard samples towards the empirical prototypes through the learning. extensive experiments on MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace demonstrate the effectiveness of EPL. Our code is available at https://***/WakingHours-GitHub/EPL. © 2024, The Authors. All rights reserved.

关键词： Face recognition

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：