检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Huayu Lu, Cheng Ying, Chengyang Su, Hang Zhu, Jun Department of Computer Science & Technology Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China Pazhou Lab Guangzhou510330 China

In offline reinforcement learning, weighted regression is a common method to ensure the learned policy stays close to the behavior policy and to prevent selecting out-of-sample actions. In this work, we show that due to the limited distributional expressivity of policy models, previous methods might still select unseen actions during training, which deviates from their initial motivation. To address this problem, we adopt a generative approach by decoupling the learned policy into two parts: an expressive generative behavior model and an action evaluation model. The key insight is that such decoupling avoids learning an explicitly parameterized policy model with a closed-form expression. Directly learning the behavior policy allows us to leverage existing advances in generative modeling, such as diffusion-based methods, to model diverse behaviors. As for action evaluation, we combine our method with an in-sample planning technique to further avoid selecting out-of-sample actions and increase computational efficiency. Experimental results on D4RL datasets show that our proposed method achieves competitive or superior performance compared with state-of-the-art offline RL methods, especially in complex tasks such as AntMaze. We also empirically demonstrate that our method can successfully learn from a heterogeneous dataset containing multiple distinctive but similarly successful strategies, whereas previous unimodal policies fail. The source code is provided at https://***/ChenDRAG/SfBC. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Wireless Federated Learning: A Secrecy Oriented Design via Sequential Artificial Jamming

引用

IEEE Transactions on Vehicular technology 2023年第5期72卷 6412-6427页

作者： Wang, Tianshun Huang, Ning Wu, Yuan Quek, Tony Q. S. University of Macau State Key Laboratory of Internet of Things for Smart City 999078 China University of Macau Department of Computer and Information Science 999078 China University of Macau State Key Lab of Internet of Things for Smart City The Department of Computer and Information Science 999078 China Zhuhai UM Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Tainan701 Taiwan

Wireless federated learning (FL) is envisioned as a promising paradigm of distributed learning in wireless networks without disclosing users' data privacy. However, radio channel leads to a potential risk of eavesdropping attack when sending the trained model data in wireless networks. To address this eavesdropping attack, in this work, we propose an energy-efficient wireless FL by using artificial jamming. Specifically, the group of wireless devices (WDs) adopt the time division multiple access (TDMA) approach to send their locally trained models to the FL server for model aggregation subject to the eavesdropping attack of a malicious node. When one of the WDs sends its local model, all the other WDs send the artificial jamming signals to interfere with the eavesdropper, which helps increase the secrecy throughput of the targeted WD for uploading its local model. Different from many existing studies using stochastic gradient descent (SGD), we adopt the stochastic average gradient (SAG) method in the local training to improve the convergence of FL and derive the corresponding lower bound of the FL convergence rate via SAG. Furthermore, we formulate an optimization problem that aims at minimizing the energy consumption of the WDs by jointly optimizing different WDs' local training time, their uploading transmission time in TDMA and the transmit-powers for providing artificial jamming, as well as the FL configurations of the local/global iterations. We also propose an efficient algorithm for solving this non-convex optimization problem. Numerical results are illustrated to validate the advantages of our design of wireless FL and the corresponding algorithms. In particular, the results demonstrate that our secrecy oriented energy-efficient FL can significantly outperform the other heuristic FL schemes. © 1967-2012 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Automated Maternal Fetal Ultrasound Image Identification Using a Hybrid Vision Transformer Model 27th

Automated Maternal Fetal Ultrasound Image Identification Usi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Krishna, Thunakala Bala Poreddy, Ajay Kumar Reddy Sindhu, Kolla Gnapika Kokil, Priyanka Lab Department of Electronics and Communication Engineering Indian Institute of Information Technology Design and Manufacturing Kancheepuram Chennai600127 India Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Tamil Nadu Chennai India

ISBN: (纸本)9783031781940

Ultrasound (US) technology has revolutionized prenatal care by offering noninvasive, real-time visualization of maternal-fetal anatomy. The accurate classification of maternal-fetal US planes is a critical segment of effective prenatal diagnosis. However, the inherent inter-class variance among different fetal US images presents a significant hurdle, making fetal anatomy detection a laborious and time-consuming task, even for experienced sonographers. This paper proposes a novel approach using a Hybrid Vision Transformer (H-ViT) for automated fetal anatomical plane classification to address these challenges. The proposed method utilizes hierarchical features extracted from DenseNet-121, which are then inputted into the vision transformer to analyze complex spatial relationships and patterns within fetal US images. By incorporating both global and local features, the proposed method enhances feature discriminability, thus alleviating low inter-class variance. The effectiveness of the H-ViT is evaluated using the largest publicly available maternal-fetal US image dataset. The experimental results rigorously demonstrate the superiority of our approach, achieving an accuracy of 96.60% compared to other state-of-the-art techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

VTSIM: Attention-Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation

VTSIM: Attention-Based Recurrent Neural Network for Intersec...

引用

作者： Liu, Jingyao Mao, Tianlu Wang, Zhaoqi Beijing Key Lab of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of Computer Science University of Chinese Academy of Sciences Beijing China

Simulating vehicle trajectories at intersections is one of the challenging tasks in traffic simulation. Existing methods are often ineffective due to the complexity and diversity of lane topologies at intersections, as well as the numerous interactions affecting vehicle motion. To address this issue, we propose a deep learning based vehicle trajectory simulation method. First, we employ a vectorized representation to uniformly extract features from traffic elements such as pedestrians, vehicles, and lanes. By fusing all factors that influence vehicle motion, this representation makes our method suitable for a variety of intersections. Second, we propose a deep learning model, which has an attention network to dynamically extract features from the surrounding environment of the vehicles. To address the issue of vehicles continuously entering and exiting the simulation scene, we employ an asynchronous recurrent neural network for the extraction of temporal features. Comparative evaluations against existing rule-based and deep learning-based methods demonstrate our model's superior simulation accuracy. Furthermore, experimental validation on public datasets demonstrates that our model can simulate vehicle trajectories among the urban intersections with different topologies including those not present in the training dataset. © 2024 John Wiley & Sons Ltd.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Probabilistic Constellation Shaping and Precoding for Multi-user VLC Systems

Joint Design of Probabilistic Constellation Shaping and Prec...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Nguyen, Thang K. Pham, Thanh V. Le, Hoang D. Nguyen, Chuyen T. Pham, Anh T. The University of Aizu Computer Communications Lab. Japan Shizuoka University Department of Mathematical and Systems Engineering Japan Hanoi University of Science & Technology School of Electrical and Electronic Engineering Viet Nam

ISBN: (纸本)9798350351255

This paper proposes a joint design of probabilistic constellation shaping (PCS) and precoding to enhance the sum-rate performance of multi-user visible light communications (VLC) broadcast channels subject to signal amplitude constraint. In the proposed design, the transmission probabilities of bipolar M-pulse amplitude modulation (M-PAM) symbols for each user and the transmit precoding matrix are jointly optimized to improve the sum-rate performance. The joint design problem is shown to be a complex non-convex problem due to the non-convexity of the objective function. To tackle the problem, the firefly algorithm (FA), a nature-inspired heuristic optimization approach, is employed to solve a local optima to the original non-convex optimization problem. The FA-based approach, however, suffers from high computational complexity. Therefore, we propose a low-complexity design based on zero-forcing (ZF) precoding, which is solved using an alternating optimization (AO) approach. Simulation results reveal that the proposed joint design with PCS significantly improves the sum-rate performance compared to the conventional design with uniform signaling. Some insights into the optimal symbol distributions of the two joint design approaches are also provided. © 2024 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Lossless DNA Sequence Compression: Exploring Spatial and Sequential Redundancies of DNA Sequence with 2-D CNN Autoencoder

Lossless DNA Sequence Compression: Exploring Spatial and Seq...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Sheena K. S. Madhu S. Nair Department of Computer Science Artificial Intelligence & Computer Vision Lab Cochin University of Science and Technology Kochi Kerala India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

The volume of genomic data being generated is growing due to the technological breakthroughs in genome sequencing and the economic affordability of sequencing. Consequently, the need for compression techniques that are specifically designed for genomic data is rising. Deep learning provides robust methods for reducing the data size and unlocking the full potential of genomic information. The proposed method minimizes storage requirements by applying a 2-D convolutional neural network autoencoder, which learns spatial and sequential redundancies in the sequence to compress the data losslessly. In contrast to conventional compression methods, which handle data as a one-dimensional sequence, the proposed approach uses the spatial structure of the data to produce more compact representations. We evaluated the proposed method with various compression approaches, including state-of-the-art DNA sequence compression algorithms, on two homo sapiens genomes. Experimental results indicate that the proposed method can compress the genomic data effectively, with an improvement of 31.3% compression over the best existing method.

关键词： Deep learning Sequential analysis Biological system modeling Redundancy Genomics DNA Data models

来源：评论

学校读者我要写书评

暂无评论

Anomaly Based Camera Prioritization in Large Scale Surveillance Networks

引用

computers, Materials & Continua 2022年第2期70卷 2171-2190页

作者： Altaf Hussain Khan Muhammad Hayat Ullah Amin Ullah Ali Shariq Imran Mi Young Lee Seungmin Rho Muhammad Sajjad Department of Software Sejong University143-747SeoulKorea Digital Image Processing Lab Islamia College Peshawar25000Pakistan Color Lab Department of Computer ScienceNorwegian University of Science and Technology(NTNU)2815GjovikNorway CORIS Institute Oregon State University97331OregonUSA

Digital surveillance systems are ubiquitous and continuously generate massive amounts of data,and manual monitoring is required in order to recognise human activities in public *** surveillance systems that can automatically identify normal and abnormal activities are highly desirable,as these would allow for efficient monitoring by selecting only those camera feeds in which abnormal activities are *** paper proposes an energy-efficient camera prioritisation framework that intelligently adjusts the priority of cameras in a vast surveillance network using feedback from the activity recognition *** proposed system addresses the limitations of existing manual monitoring surveillance systems using a three-step *** the first step,the salient frames are selected from the online video stream using a frame differencing method.A lightweight 3D convolutional neural network(3DCNN)architecture is applied to extract spatio-temporal features from the salient frames in the second ***,the probabilities predicted by the 3DCNN network and the metadata of the cameras are processed using a linear threshold gate sigmoid mechanism to control the priority of the *** proposed system performs well compared to state-of-theart violent activity recognition methods in terms of efficient camera prioritisation in large-scale surveillance *** experiments and an evaluation of activity recognition and camera prioritisation showed that our approach achieved an accuracy of 98%with an F1-score of 0.97 on the Hockey Fight dataset,and an accuracy of 99%with an F1-score of 0.98 on the Violent Crowd dataset.

关键词： Camera prioritisation surveillance networks convolutional neural network computer vision deep learning resource-constrained device violent activity recognition

来源：评论

学校读者我要写书评

暂无评论

Dual Encoder-Decoder U-Net Architecture for Polyp Segmentation in Colonoscopy Images with Shuffle Attention and Conditional Random Fields

Dual Encoder-Decoder U-Net Architecture for Polyp Segmentati...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Lijin P. Santhosh Kumar G. Madhu S. Nair Department of Computer Science Artificial Intelligence & Computer Vision Lab Cochin University of Science and Technology Kochi Kerala India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

Colonoscopy plays a pivotal role in detecting and diagnosing colorectal diseases, with polyp segmentation being a critical step for accurate diagnosis. In this study, we propose a novel approach for polyp segmentation in colonoscopy images, leveraging the Shuffle attention mechanism within the proposed architecture. Our method is rigorously evaluated across three diverse colonoscopy datasets, demonstrating promising results with an mean dice score of 0.93. Furthermore, to enhance segmentation accuracy, we employ a Conditional Random Field (CRF) post-processing method to refine the segmentation results. Through extensive experimentation and analysis, we showcase the effectiveness of our approach in achieving highly accurate polyp segmentation, thereby contributing to improved diagnostic outcomes in colorectal healthcare. Our method holds significant potential for enhancing computer-aided detection systems in clinical practice, facilitating early detection and treatment of colorectal abnormalities.

关键词： Measurement Image segmentation Accuracy Computational modeling Colonoscopy computer architecture Medical services

来源：评论

学校读者我要写书评

暂无评论

Disentangled latent factors for muti-cause treatment effect estimation 6

Disentangled latent factors for muti-cause treatment effect ...

引用

2024 6th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2024

作者： Zhao, Zhuoyue Wang, Haotian Xu, Liyang Wang, Qian Tang, Yuhua Department of Intelligent Data Science National University of Defense Technology Changsha410073 China Intelligent Game and Decision Lab. Academy of Military Science Beijing100071 China Institute for Quantum Information State Key Laboratory of High-Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China

Existing methods estimate treatment effects from observational data and assume that covariates are all confounders. However, observed covariates may not directly represent confounding variables that influence both treatment and outcome. They always include variables that only affect the treatment or the outcome. In addition, for multi-dimensional binary treatments, disentangled methods are mainly designed for binary variables and ignore the impact of multi-cause treatment variables on the inference of latent factors. To address these two issues, based on variable decomposition and proxy inference, we propose the Disentangled Latent Factors for Multi-cause Treatment Estimation (DEMTE) algorithm. It utilizes an identifiable autoencoder to infer and disentangle latent factors based on the joint distribution of variables in observational data. DEMTE evaluates the treatment effect on the disentangled factors. Synthetic experiments and semi-synthetic experiments demonstrate the effectiveness of the inference and disentanglement techniques and our method achieves more accurate treatment effect estimation. © 2024 Institute of Physics Publishing. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation 41

MorphGrower: A Synchronized Layer-by-layer Growing Approach ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Nianzu Zeng, Kaipeng Lu, Haotian Wu, Yexin Yuan, Zexin Chen, Danni Jiang, Shengdian Wu, Jiaxiang Wang, Yimin Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University China Guangdong Institute of Intelligence Science and Technology China SEU-ALLEN Joint Center Institute for Brain and Intelligence Southeast University China XVERSE Technology China

Neuronal morphology is essential for studying brain functioning and understanding neurodegenerative disorders. As acquiring real-world morphology data is expensive, computational approaches for morphology generation have been studied. Traditional methods heavily rely on expert-set rules and parameter tuning, making it difficult to generalize across different types of morphologies. Recently, MorphVAE was introduced as the sole learning-based method, but its generated morphologies lack plausibility, i.e., they do not appear realistic enough and most of the generated samples are topologically invalid. To fill this gap, this paper proposes MorphGrower, which mimicks the neuron natural growth mechanism for generation. Specifically, MorphGrower generates morphologies layer by layer, with each subsequent layer conditioned on the previously generated structure. During each layer generation, MorphGrower utilizes a pair of sibling branches as the basic generation block and generates branch pairs synchronously. This approach ensures topological validity and allows for fine-grained generation, thereby enhancing the realism of the final generated morphologies. Results on four real-world datasets demonstrate that MorphGrower outperforms MorphVAE by a notable margin. Importantly, the electrophysiological response simulation demonstrates the plausibility of our generated samples from a neuroscience perspective. Our code is available at https://***/Thinklab-SJTU/MorphGrower. Copyright 2024 by the author(s)

关键词： Neurons

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：