检索结果-内蒙古大学图书馆

Automation and Computation (AUTOCOM), International Conference on

作者： Sankar Kumar Mridha Kanika Seth Srikrishna Baskar Rao Natya S Savita Neelesh Singh Department of Computer Science and Information Technology Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Engineering and Technology Aerospace Engineering JAIN (Deemed to be University) Bangalore Karnataka Department of Electronics and Communication Engineering Presidency University Bangalore Karnataka India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

The arena shifts closer to sustainable transportation, electric-powered vehicles (EVs) have emerged as a promising solution to reduce greenhouse gasoline emissions. However, the great adoption of EVs faces numerous challenges, such as confined riding ranges and lengthy charging instances. Battery electricity storage systems were diagnosed as a critical technology to address those barriers and free up the total capacity of EVs. BESS allows for the efficient garage and control of power in EVs, allowing quicker charging instances and extended driving variety. This gadget now not only benefits the vehicle proprietor but also offers grid flexibility and balance by helping smart charging and car-to-grid (V2G) capabilities. BESS additionally has the potential to reduce the strain on the present power grid by moving charging demand to off-peak hours. To completely leverage the benefits of BESS in EVs, sizable advancements are wanted in battery technology, including elevated energy density, quicker charging skills, and longer lifespan. Additionally, studies and development are required to optimize the integration of BESS with the vehicle and the grid. With speedy improvements in the development of BESS and expanded investments in EV infrastructure, the total potential of battery power garage structures in electric-powered motors can be unlocked. It may no longer be the best way to accelerate the transition toward sustainable transportation; however, it provides full-size financial and environmental blessings.

关键词： Vehicle-to-grid Electric potential Electricity Transportation Motors Power grids Protection Petroleum Strain Smart charging

来源：评论

学校读者我要写书评

暂无评论

Optimizing for the Shortest Path in Denoising Diffusion Model

arXiv

引用

arXiv 2025年

作者： Chen, Ping Zhang, Xingpeng Liu, Zhaoxiang Hu, Huan Liu, Xiang Wang, Kai Wang, Min Qian, Yanlin Lian, Shiguo Data Science & Artificial Intelligence Research Institute China Unicom China Unicom Data Intelligence China Unicom China DJI Technology Co. Ltd. China School of Computer Science and Software Engineering Southwest Petroleum University Chengdu China

In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error. By optimizing the initial residuals, we improve the efficiency of the reverse diffusion process and the quality of the generated samples. Extensive experiments on multiple standard benchmarks demonstrate that ShortDF significantly reduces diffusion time (or steps) while enhancing the visual fidelity of generated samples compared to prior arts. This work, we suppose, paves the way for interactive diffusion-based applications and establishes a foundation for rapid data generation. Code is available at https://***/UnicomAI/ShortDF. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Heterogeneous Long-term Causal Effect Estimation via Data Combination

arXiv

引用

arXiv 2025年

作者： Chen, Weilin Cai, Ruichu Wan, Junjie Yang, Zeqin Hernández-Lobato, José Miguel School of Computer Science Guangdong University of Technology Guangzhou510006 China Peng Cheng Laboratory Shenzhen China Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom

Long-term causal inference has drawn increasing attention in many scientific domains. Existing methods mainly focus on estimating average long-term causal effects by combining long-term observational data and short-term experimental data. However, it is still understudied how to robustly and effectively estimate heterogeneous long-term causal effects, significantly limiting practical applications. In this paper, we propose several two-stage style nonparametric estimators for heterogeneous long-term causal effect estimation, including propensity-based, regression-based, and multiple robust estimators. We conduct a comprehensive theoretical analysis of their asymptotic properties under mild assumptions, with the ultimate goal of building a better understanding of the conditions under which some estimators can be expected to perform better. Extensive experiments across several semi-synthetic and real-world datasets validate the theoretical results and demonstrate the effectiveness of the proposed estimators. Copyright © 2025, The Authors. All rights reserved.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Inter-patch spatio-temporal relation prediction for video anomaly detection

引用

Signal, Image and Video Processing 2025年第7期19卷 1-11页

作者： Shen, Hao Shi, Lu Zhang, Linna Xu, Wanru Cen, Yigang An, Gaoyun State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing China The School of Computer Science and Technology Beijing Jiaotong University Beijing China Visual Intellgence +X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University Beijing China School of Mechanical Engineering Guizhou University Guiyang China

Video anomaly detection (VAD), aiming to identify abnormalities within a specific context and timeframe, is crucial for intelligent video surveillance systems. While recent deep learning-based VAD models have shown promising results by generating high-resolution frames, they often lack competence in preserving detailed spatial and temporal coherence in video frames. To tackle this issue, we propose a self-supervised learning approach for VAD through an inter-patch relationship prediction task. Specifically, we introduce a two-branch vision transformer network designed to capture deep visual features of video frames, which can address spatial and temporal dimensions responsible for modeling appearance and motion patterns, respectively. The inter-patch relationship in each dimension is decoupled into inter-patch similarity and the order information of each patch. To mitigate memory consumption, we convert the order information prediction task into a multi-label learning problem, and the inter-patch similarity prediction task into a inter-patch distance matrix regression problem. Comprehensive experiments demonstrate the effectiveness of our method, surpassing pixel-generation-based methods by a significant margin across three public benchmarks. Additionally, our approach outperforms other self-supervised learning-based methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bilevel Learning for Low-Light Image Enhancement and Detection

Bilevel Learning for Low-Light Image Enhancement and Detecti...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Wang Bojian Song Xi Chen Yaxin Gao Weimin Lei School of Computer Science and Engineering Northeastern University Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China He University Shenyang China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Object detection in low-light scenes is a challenging but widely discussed topic in computer vision. A common approach in low-light object detection involves employing cascaded architectures to connect enhancement and detection networks. This strategy aims to bridge the gap between low-light and normal-light images in both the image and feature domains, enabling the effective application of existing object detection networks to low-light scenarios. However, the cascade architecture ignores the intrinsic connection between low-light image enhancement and object detection tasks. To address this problem, we use a bilevel learning architecture to bridge these two tasks. Specifically, we take the parameters of the enhancement network as the main optimization objective and the parameters of the object detection network as the learnable constraints. In addition, to improve the practicality, we propose a method based on implicit function theory to approximate the solution of the corresponding gradient. Numerous experiments have demonstrated that our method significantly improves enhancement quality and detection accuracy.

关键词： computer vision Accuracy Computational modeling Object detection computer architecture Speech enhancement Signal processing Feature extraction Image enhancement Optimization

来源：评论

学校读者我要写书评

暂无评论

Interplay between Bayesian Neural Networks and Deep Learning: A Survey

SSRN

引用

SSRN 2025年

作者： Chen, Yinsong Yu, Samson S. Li, Zhong Eshraghian, Jason K. Lim, Chee Peng School of Engineering Deakin University MelbourneVIC3216 Australia Faculty of Mathmatics and Computer Science FernUniversität Hagen58084 Germany Department of Electrical and Computer Engineering University of California Santa CruzCA95064 United States Department of Computing Technologies Swinburne University of Technology HawthornVIC3122 Australia

While deep learning models have seen significant success across various domains, their black-box learning nature and lack of interpretability affect their reliability in safety-critical applications like medical diagnostics and autonomous vehicles. In an attempt to address these limitations, Bayesian neural networks (BNNs) offer a promising alternative by incorporating uncertainty estimation into model predictions, enhancing transparency and decision-making. However, BNN development has primarily focused on efficient, high-fidelity approximate inference and guaranteed convergence in asymptotic settings. These are unsuitable for modern high-dimensional, multimodal, and non-asymptotic deep learning applications, undermining their theoretical advantages. To bridge this gap, this paper provides in-depth reviews on how approximate Bayesian inference leverages deep learning optimization to achieve high efficiency and fidelity in high-dimensional spaces and multimodal loss landscapes. It also reconciles Bayesian consistency with generalization objectives in non-asymptotic settings and investigates the generalization capabilities of BNNs. Additionally, this survey examines the often-overlooked expressiveness of BNNs, emphasizing how weight uncertainty and the absence of in-between uncertainty affect their performance. This survey aims to inspire BNN practitioners to adopt a deep learning perspective and offer valuable insights to propel further advancements in the field. © 2025, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

LSTM-based argument recommendation for non-API methods

引用

science China(Information sciences) 2020年第9期63卷 5-26页

作者： Guangjie LI Hui LIU Ge LI Sijie SHEN Hanlin TANG School of Computer Science and Technology Beijing Institute of Technology School of Electronics Engineering and Computer Science Peking University

Automatic code completion is one of the most useful features provided by advanced IDEs. Argument recommendation, as a special kind of code completion, is widely used as well. While existing approaches focus on argument recommendation for popular APIs, a large number of non-API invocations are requesting for accurate argument recommendation as well. To this end, we propose an LSTM-based approach to recommending non-API arguments instantly when method calls are typed in. With data collected from a large corpus of open-source applications, we train an LSTM neural network to recommend actual arguments based on identifiers of the invoked method, the corresponding formal parameter, and a list of syntactically correct candidate arguments. To feed these identifiers into the LSTM neural network, we convert them into fixed-length vectors by Paragraph Vector, an unsupervised neural network based learning algorithm. With the resulting LSTM neural network trained on sample applications, for a given call site we can predict which of the candidate arguments is more likely to be the correct one. We evaluate the proposed approach with tenfold validation on 85 open-source C applications. Results suggest that the proposed approach outperforms the state-of-the-art approaches in recommending non-API arguments. It improves the precision significantly from 71.46% to 83.37%.

关键词： argument recommendation LSTM deep learning non-API

来源：评论

学校读者我要写书评

暂无评论

Improved Quaternion Discriminant Analysis for Feature Extraction and Classification of Hyperspectral Image

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年

作者： Wang, Xinpeng Ling, Bingo Wing-Kuen Yu, Long Dai, Qingyun Liu, Shaopeng Zhao, Jiandong Kuang, Weichao Guangdong Polytechnic Normal University Faculty of Computer Science Guangzhou China Guangdong University of Technology School of Information Engineering Guangzhou China Sun Yat-sen University School of Geography and Planning Guangzhou510275 China Dongguan University of Technology Department of Electronic Engineering and Intellectualization Dongguan China

Real domain discriminant analysis (RDA) can not solve the crosstalk of strong correlation between adjacent spectral bands, and also causes spectral information loss of hyperspectral image (HSI). As a result, the effect of feature extraction is not ideal. Besides, in the case of small samples, using quaternion discriminant analysis (QDA) based on Cos-sin Decomposition, the matrix obtained by the first orthogonal trigonometric decomposition is not a diagonal matrix, that makes the projection axis not optimal. To solve these problems, firstly, a quaternion discriminant analysis method based on stable quaternion Cossin Decomposition (QDASG) is proposed to solve the small sample problem. Secondly, this paper theoretically analyzes that when the number of projection axes in QDASG is smaller than that in traditional DA methods, the discriminant formula can achieve optimal results, and verifies this conclusion through experiments. Then, according to the number of training samples, the implementation process of QDA is discussed in two cases. Finally, spatial filtering is used to extract spatial information, and the distance quotient formula between classes is proposed as the standard for selecting the the optimal number of stacking layers for the filter. Experimental results show that this method is effective compared with deep learning method and and other traditional machine learning methods, especially in the case of small samples. © 2008-2012 IEEE.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

AoI-Delay Tradeoff in Mobile Edge Caching: A Lyapunov Optimization-Based Method

引用

IEEE Internet of Things Journal 2025年

作者： Li, Ran Huang, Chuan Qin, Xiaoqi Fu, Zhanhong Yang, Lei Yang, Dong The Future Network of Intelligence Institute The Chinese University of HongKong Shenzhen518172 China The Department of Information Engineering The Chinese University of Hong Kong Hong Kong The School of Science and Engineering The Future Network of Intelligence Institute The Chinese University of HongKong Shenzhen518172 China The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China SF Technology Shenzhen518052 China The Department of Computer Science and Engineering University of Nevada RenoNV89557 United States The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China

Mobile edge caching (MEC) is a promising technique to improve the quality of service (QoS) for mobile users (MU) by bringing data to the network edge. However, optimizing the crucial QoS aspects of message freshness and service promptness, measured by age of information (AoI) and service delay, respectively, entails a tradeoff due to their competition for shared edge resources. This paper investigates this tradeoff by formulating their weighted sum minimization as a sequential decision-making problem, incorporating high-dimensional, discrete-valued, and linearly constrained design variables. First, to assess the feasibility of the considered problem, we characterize the corresponding achievable region by deriving its superset with the rate stability theorem and its subset with a novel stochastic policy, and develop a sufficient condition for the existence of solutions. Next, to efficiently solve this problem, we propose a mixed-order drift-plus-penalty algorithm by jointly considering the linear and quadratic Lyapunov drifts and then optimizing them with dynamic programming (DP). Finally, by leveraging the Lyapunov optimization technique, we demonstrate that the proposed algorithm achieves an O(1/V) versus O(V) tradeoff for the average AoI and average service delay. © 2014 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Seamless Graph Task Scheduling over Dynamic Vehicular Clouds: A Hybrid Methodology for Integrating Pilot and Instantaneous Decisions

引用

IEEE Transactions on Services Computing 2025年

作者： Guo, Bingshuo Liwang, Minghui Xia, Xiaoyu Li, Li Jiao, Zhenzhen Hosseinalipour, Seyyedali Wang, Xianbin Xiamen University School of Informatics Fujian China Rmit University School of Computing Technologies MelbourneVIC Australia Tongji University Department of Control Science and Engineering Shanghai China Beijing Teleinfo Technology Co. Ltd. Caict IF-Labs China University at Buffalo-SUNY Department of Electrical Engineering NY United States Western University Department of Electrical and Computer Engineering ON Canada

Vehicular clouds (VCs) play a crucial role in the Internet-of-Vehicles (IoV) ecosystem by securing essential computing resources for a wide range of tasks. This paPertackles the intricacies of resource provisioning in dynamic VCs for computation-intensive tasks, represented by undirected graphs for parallel processing over multiple vehicles. We model the dynamics of VCs by considering multiple factors, including varying communication quality among vehicles, fluctuating computing capabilities of vehicles, uncertain contact duration among vehicles, and dynamic data exchange costs between vehicles. Our primary goal is to obtain feasible assignments between task components and nearby vehicles, called templates, in a timely manner with minimized task completion time and data exchange overhead. To achieve this, we propose a hybrid graph task scheduling (P-HTS) methodology that combines offline and online decision-making modes. For the offline mode, we introduce an approach called risk-aware pilot isomorphic subgraph searching (RA-PilotISS), which predicts feasible solutions for task scheduling in advance based on historical information. Then, for the online mode, we propose time-efficient instantaneous isomorphic subgraph searching (TE-InstaISS), serving as a backup approach for quickly identifying new optimal scheduling template when the one identified by RA-PilotISS becomes invalid due to changing conditions. Through comprehensive experiments, we demonstrate the superiority of our proposed hybrid mechanism compared to state-of-the-art methods in terms of various evaluative metrics, e.g., time efficiency such as the delay caused by seeking for possible templates and task completion time, as well as cost function, upon considering different VC scales and graph task topologies. © 2025 IEEE.

关键词： Undirected graphs

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：