检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Guo, Yu Nie, Guigen Zou, Xiaowei Zhu, Dongliang Gao, Wenliang Liao, Mi GNSS Research Center Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China

HIGHLIGHTS·Optimized lane-change trajectories considering safety, comfort, and time efficiency.·Developed a model for identifying different lane changing styles to meet personalized driving preferences.·Comprehensive analysis uncovers significant energy consumption patterns in electric autonomous vehicles during lane-change maneuvers.·Conducted rigorous examination of energy consumption during lane changes, identifying consumption trends in aggressive, conservative, and normal driving styles.·Correlation analysis of key factors affecting energy consumption paves the way for customizing driving styles and powertrain design to reduce energy usage. © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

All Information is Necessary: Integrating Speech Positive and Negative Information by Contrastive Learning for Speech Enhancement

arXiv

引用

arXiv 2023年

作者： Xu, Xinmeng Tu, Weiping Han, Chang Yang, Yuhong National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Hubei Luojia Laboratory China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Monaural speech enhancement (SE) is an ill-posed problem due to the irreversible degradation process. Recent methods to achieve SE tasks rely solely on positive information, e.g., ground-truth speech and speech-relevant features. Different from the above, we observe that the negative information, such as original speech mixture and speech-irrelevant features, are valuable to guide the SE model training procedure. In this study, we propose a SE model that integrates both speech positive and negative information for improving SE performance by adopting contrastive learning, in which two innovations have consisted. (1) We design a collaboration module (CM), which contains two parts, contrastive attention for separating relevant and irrelevant features via contrastive learning and interactive attention for establishing the correlation between both speech features in a learnable and self-adaptive manner. (2) We propose a contrastive regularization (CR) built upon contrastive learning to ensure that the estimated speech is pulled closer to the clean speech and pushed far away from the noisy speech in the representation space by integrating self-supervised models. We term the proposed SE network with CM and CR as CMCR-Net. Experimental results demonstrate that our CMCR-Net achieves comparable and superior performance to recent approaches. © 2023, CC BY.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Effective Reinforcement Learning Based on Structural Information Principles

arXiv

引用

arXiv 2024年

作者： Zeng, Xianghua Peng, Hao Su, Dingli Li, Angsheng State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China School of Cyber Science and Technology Beihang University Beijing100191 China

Although Reinforcement Learning (RL) algorithms acquire sequential behavioral patterns through interactions with the environment, their effectiveness in noisy and high-dimensional scenarios typically relies on specific structural priors. In this paper, we propose a novel and general Structural Information principles-based framework for effective Decision-Making, namely SIDM, approached from an information-theoretic perspective. This paper presents a specific unsupervised partitioning method that forms vertex communities in the state and action spaces based on their feature similarities. An aggregation function, which utilizes structural entropy as the vertex weight, is devised within each community to obtain its embedding, thereby facilitating hierarchical state and action abstractions. By extracting abstract elements from historical trajectories, a directed, weighted, homogeneous transition graph is constructed. The minimization of this graph’s high-dimensional entropy leads to the generation of an optimal encoding tree. An innovative two-layer skill-based learning mechanism is introduced to compute the common path entropy of each state transition as its identified probability, thereby obviating the requirement for expert knowledge. Moreover, SIDM can be flexibly incorporated into various single-agent and multi-agent RL algorithms, enhancing their performance. Finally, extensive evaluations on challenging benchmarks demonstrate that, compared with SOTA baselines, our framework significantly and consistently improves the policy’s quality, stability, and efficiency up to 32.70%, 88.26%, and 64.86%, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Adaptive Random Testing based on the Modified Metric-memory Tree and Information Entropy 9

Adaptive Random Testing based on the Modified Metric-memory ...

引用

9th International Conference on Dependable Systems and Their Applications, DSA 2022

作者： Chen, Jinfu Chen, Haibo Wu, Yiming Mao, Chengying Cai, Saihua School of Computer Science and Communication Engineering Jiangsu University Zhenjiang212013 China Jiangsu University Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace Zhenjiang212013 China School of Software and IoT Engineering Jiangxi University of Finance and Economics Nanchang330013 China

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Adaptive Random Testing (ART) is a series of testing techniques proposed as an enhancement to random testing (RT). ART achieves better failure-detection than RT by distributing test cases more evenly throughout the input domain. However, the process of selecting test cases leads to significant computational costs and the increase of dimension leads to the decrease of effectiveness. In this paper, we propose a new ART approach to improve the efficiency and effectiveness of Fixed-size-Candidate-set ART (FSCS-ART) by applying a modified Metric-Memory tree and distance information entropy selection strategy, namely FSCS based on the modified MM-tree and information entropy (MMIE-FSCS). Simulations and empirical studies are conducted to examine the efficiency and effectiveness of the approach. The experimental results show that the approach reduces the computational cost of FSCS-ART and improves failure-detection effectiveness. © 2022 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

TUBENCH: BENCHMARKING LARGE VISION-LANGUAGE MODELS ON TRUSTWORTHINESS WITH UNANSWERABLE QUESTIONS

arXiv

引用

arXiv 2024年

作者： He, Xingwei Zhang, Qianru Jin, A-Long Yuan, Yuan Yiu, Siu-Ming The University of Hong Kong Hong Kong Xi’an Jiaotong-Liverpool University China School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Software Development Environment China Zhongguancun Laboratory China

Large Vision-Language Models (LVLMs) have achieved remarkable progress on visual perception and linguistic interpretation. Despite their impressive capabilities across various tasks, LVLMs still suffer from the issue of hallucination, which involves generating content that is incorrect or unfaithful to the visual or textual inputs. Traditional benchmarks, such as MME and POPE, evaluate hallucination in LVLMs within the scope of Visual Question Answering (VQA) using answerable questions. However, some questions are unanswerable due to insufficient information in the images, and the performance of LVLMs on such unanswerable questions remains underexplored. To bridge this research gap, we propose TUBench, a benchmark specifically designed to evaluate the reliability of LVLMs using unanswerable questions. TUBench comprises an extensive collection of high-quality, unanswerable questions that are meticulously crafted using ten distinct strategies. To thoroughly evaluate LVLMs, the unanswerable questions in TUBench are based on images from four diverse domains as visual contexts: screenshots of code snippets, natural images, geometry diagrams, and screenshots of statistical tables. These unanswerable questions are tailored to test LVLMs’ trustworthiness in code reasoning, commonsense reasoning, geometric reasoning, and mathematical reasoning related to tables, respectively. We conducted a comprehensive quantitative evaluation of 28 leading foundational models on TUBench, with Gemini-1.5-Pro, the top-performing model, achieving an average accuracy of 69.2%, and GPT-4o, the third-ranked model, reaching 66.7% average accuracy, in determining whether questions are answerable. Furthermore, our manual analysis of the model outputs reveals that: (1) Gemini-1.5-Pro provides both correct answers and explanations in only 41% of cases, and (2) hallucinations are the primary cause of error, accounting for 58.5% of the incorrect explanations generated by Gemini-1.5-Pro. These findings

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Precise Timing over Beyond 5G Networks for Intelligent Transport in the Smart City

Precise Timing over Beyond 5G Networks for Intelligent Trans...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Hongxing Li Guochu Shou Yaqiong Liu Yihong Hu State Key Laboratory of Networking and Switching Technology School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

The need for precise timing is increasing with the development of the smart city, and intelligent transport is a key application that often relies on the distribution of accurate timing. Existing time synchronization solutions cannot adequately meet the precise timing needs for practical applications in intelligent transportation. Global Navigation Satellite Systems (GNSS) signals, for instance, can be obstructed, weakened, or deflected in urban canyon environments. While certain sectors like telecommunications and smart grids have successfully adopted IEEE 1588 for high-precision time synchronization, its dependence on standalone networks and limited application within local area networks poses challenges when catering to the wide-ranging and mobile demands of intelligent transportation applications. This paper categorizes the time synchronization requirements of intelligent transport and proposes a time synchronization scheme over converged networks, which separates time transmission and precision compensation based on software-defined networking (SDN) principles, and makes it possible to provide precise timing for intelligent transport devices, including on-board units (OBUs) and roadside units (RSUs), over wired and wireless communication networks. Experimental results indicate that the proposed scheme achieves a relative time error of less than 1.2 microseconds over the converged networks.

关键词： Wireless communication Global navigation satellite system Accuracy Smart cities Transportation Telecommunications Smart grids Synchronization software defined networking Local area networks

来源：评论

学校读者我要写书评

暂无评论

MFN: Explainable DNA triple helixes Stabilized Design based on mCGR and flow network

MFN: Explainable DNA triple helixes Stabilized Design based ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaoru Wen Lijun Sun Lei Xie Yanfen Zheng Ben Cao Bin Wang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

DNA triple helix structure, as a highly specific gene targeting tool, enable gene regulation by precisely identifying and binding to target DNA sequences. However, the limits of design quality and efficiency affect their wide application in gene therapy. Therefore, in this paper, we propose an antiparallel DNA triple helixes design method-MFN based on matrix chaotic game representation (mCGR) and flow network. Leveraging the structural characteristics of DNA sequences, this method employs the mCGR algorithm to construct an initial matrix, generating a set of DNA sequences that conform to foundational constraints. Then, these sequences are mapped as stream network nodes to screen crosstalk structures by path search, and the whole process is observable and interpretable. Experimental results show that MFN significantly improves the design efficiency of triple helix structure and reduces crosstalk phenomenon. Wet experiments further verify the effectiveness of the method. In summary, MFN achieves an efficient and high-quality design of DNA triple helixes and provides a new idea for targeted gene therapy.

关键词： Scalability Design methodology DNA Crosstalk Genomics Games Reliability engineering Regulation Gene therapy Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Bilinear-Experts Network with Self-Adaptive Sampler for Long-Tailed Visual Recognition

SSRN

引用

SSRN 2024年

作者： Wang, Qin Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Long-tail distributed data hinders the practical application of state-of-the-art deep models in computer vision. Consequently, exclusive methodologies for handling the long-tailed problem are proposed, focusing on different hierarchies. For embedding hierarchy, existing works manually augment the diversity of tail-class features for specific datasets. However, prior knowledge about datasets is not always available for practical use, which brings unsatisfactory generalization ability in human fine-turned augmentation under such circumstances. To figure out this problem, we introduce a novel model named Bilinear-Experts Network (BENet) with Self-Adaptive Sampler (SAS). This model leverages model-driven perturbations to tail-class embeddings while preserving generalization capability on head classes through a designed bilinear experts system. The designed perturbations adaptively augment tail-class space and shift the class boundary away from the tail-class centers. Moreover, we surprisingly find that SAS automatically assigns more significant perturbations to specific tail classes rather than fewer-sample classes, which is against the common assumption that fewer-sample classes deserve greater attention. Also, experiments conducted across various long-tailed benchmarks validate the comparable efficacy of proposed BENet. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Dynamic personalized federated learning with adaptive differential privacy 23

Dynamic personalized federated learning with adaptive differ...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Xiyuan Yang Wenke Huang Mang Ye National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China

Personalized federated learning with differential privacy has been considered a feasible solution to address non-IID distribution of data and privacy leakage risks. However, current personalized federated learning methods suffer from inflexible personalization and convergence difficulties due to two main factors: 1) Firstly, we observe that the prevailing personalization methods mainly achieve this by personalizing a fixed portion of the model, which lacks flexibility. 2) Moreover, we further demonstrate that the default gradient calculation is sensitive to the widely-used clipping operations in differential privacy, resulting in difficulties in convergence. Considering that Fisher information values can serve as an effective measure for estimating the information content of parameters by reflecting the model sensitivity to parameters, we aim to leverage this property to address the aforementioned challenges. In this paper, we propose a novel federated learning method with Dynamic Fisher Personalization and Adaptive Constraint (FedDPA) to handle these challenges. Firstly, by using layer-wise Fisher information to measure the information content of local parameters, we retain local parameters with high Fisher values during the personalization process, which are considered informative, simultaneously prevent these parameters from noise perturbation. Secondly, we introduce an adaptive approach by applying differential constraint strategies to personalized parameters and shared parameters identified in the previous for better convergence. Our method boosts performance through flexible personalization while mitigating the slow convergence caused by clipping operations. Experimental results on CIFAR-10, FEMNIST and SVHN dataset demonstrate the effectiveness of our approach in achieving better performance and robustness against clipping, under personalized federated learning with differential privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Heterogeneous Federated Learning under Data Corruption

Robust Heterogeneous Federated Learning under Data Corruptio...

引用

International Conference on computer Vision (ICCV)

作者： Xiuwen Fang Mang Ye Xiyuan Yang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China

Model heterogeneous federated learning is a realistic and challenging problem. However, due to the limitations of data collection, storage, and transmission conditions, as well as the existence of free-rider participants, the clients may suffer from data corruption. This paper starts the first attempt to investigate the problem of data corruption in the model heterogeneous federated learning framework. We design a novel method named Augmented Heterogeneous Federated Learning (AugHFL), which consists of two stages: 1) In the local update stage, a corruption-robust data augmentation strategy is adopted to minimize the adverse effects of local corruption while enabling the models to learn rich local knowledge. 2) In the collaborative update stage, we design a robust re-weighted communication approach, which implements communication between heterogeneous models while mitigating corrupted knowledge transfer from others. Extensive experiments demonstrate the effectiveness of our method in coping with various corruption patterns in the model heterogeneous federated learning setting.

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：