检索结果-内蒙古大学图书馆

Qualitative and Quantitative Model Checking Against Recurrent Neural Networks

Journal of computer science & technology 2024年第6期39卷 1292-1311页

作者： Zhen Liang Wan-Wei Liu Fu Song Bai Xue Wen-Jing Yang Ji Wang Zheng-Bin Pang Institute for Quantum Information&State Key Laboratory of High Performance Computing College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China School of Information Science and Technology ShanghaiTech UniversityShanghai 201210China Institute of Software Chinese Academy of SciencesBeijing 100190China

Recurrent neural networks (RNNs) have been heavily used in applications relying on sequence data such as time series and natural languages. As a matter of fact, their behaviors lack rigorous quality assurance due to the black-box nature of deep learning. It is an urgent and challenging task to formally reason about the behaviors of RNNs. To this end, we first present an extension of linear-time temporal logic to reason about properties with respect to RNNs, such as local robustness, reachability, and some temporal properties. Based on the proposed logic, we formalize the verification obligation as a Hoare-like triple, from both qualitative and quantitative perspectives. The former concerns whether all the outputs resulting from the inputs fulfilling the pre-condition satisfy the post-condition, whereas the latter is to compute the probability that the post-condition is satisfied on the premise that the inputs fulfill the pre-condition. To tackle these problems, we develop a systematic verification framework, mainly based on polyhedron propagation, dimension-preserving abstraction, and the Monte Carlo sampling. We also implement our algorithm with a prototype tool and conduct experiments to demonstrate its feasibility and efficiency.

关键词： recurrent neural network model checking temporal logic qualitative/quantitative verification

来源：评论

学校读者我要写书评

暂无评论

Automatic Positioning of Intelligent Mobile Robot Based on Improved Front-End Scanning Matching

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第1期10卷 559-572页

作者： Wang, Hong Wang, Yi-Gui Zhang, Jie Department of Computer and Software Engineering Shandong College of Electronic Technology Jinan250200 China School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China College of Agricultural Science and Technology Yana Royal Polytechnic University Chiang Mai50000 Thailand

Traditional autonomous navigation methods for mobile robots mainly rely on geometric feature-based LiDAR scan-matching algorithms, but in complex environments, this method is often affected due to the presence of moving objects, occlusions, and other interfering factors, resulting in a decrease in positioning accuracy. With the growing demand for robotics applications in logistics, security, exploration and other fields, the need for robust autonomous navigation and high-precision mapping in highly dynamic and complex environments is becoming more and more urgent. To solve this problem, an improved front-end scan matching algorithm based on Frequency Modulated Continuous Wave (FMCW) LiDAR is proposed in this paper. Firstly, by using the target Doppler velocity information provided by the FMCW LiDAR, we design a novel point cloud segmentation algorithm based on velocity clustering, which is able to effectively distinguish between stationary and moving objects, and avoid the dynamic interference affecting the position estimation. Secondly, we introduce the Gaussian Mixture Model Sampling Consistency (GMMSC) algorithm, which is more robust to reject the mis-matched pairs in the scanning matching process and improve the alignment accuracy. Finally, based on the residual high-quality matched pairs, we combine the classical ICP algorithm with the robust kernel function to further enhance the stability of the position estimation in the case of occlusion and local mismatch. The experimental results show that the proposed improved algorithm significantly improves the mapping capability of mobile robots in complex environments compared with the existing techniques. The average relative error of the improved front-end scanning matching algorithm is reduced by 40.6 % compared with the pre-improved one. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

LSRN-AED: lightweight super-resolution network based on asymmetric encoder–decoder

引用

Soft Computing 2024年第13-14期28卷 8513-8525页

作者： Huang, Shuying Li, Wei Yang, Yong Wan, Weiguo Lai, Houzeng School of Software Tiangong University Tianjin300387 China School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics Nanchang330032 China School of Computer Science and Technology Tiangong University Tianjin300387 China

Due to limited memory and computing resources, the application of deep neural networks on embedded and mobile devices is still a great challenge. To tackle this problem, this paper proposes a lightweight super-resolution network based on asymmetric encoder–decoder (LSRN-AED), which achieves better performance while reducing model parameters and computation. On the basis of rethinking the roles of encoder and decoder, an asymmetric encoder–decoder (AED) composed of complex encoders and simple decoders is designed to achieve feature extraction and reconstruction. Here, the decoder only adopts one inverted residual block, which can reduce the computational cost of the model and the redundancy of mapping features. For the encoder, inspired by the Transformer structure, an epiphany encoder is designed to realize the feature extraction and representation. In the encoder, a multi-way epiphany attention module (MEAM) is constructed, in which inverted residual blocks are used to replace traditional residual blocks to extract features and reduce model complexity. To realize the selection and enhancement of spatial features, an epiphany attention block (EAB) is designed by exploiting depth-wise convolutions which can learn the significant spatial information of the feature maps. Experimental results demonstrate that the proposed LSRN-AED can achieve better performance at lower parameter cost and outperform some existing state-of-the-art lightweight models. For example, compared to the advanced SMSR method, the proposed LSRN-AED has better evaluation metrics while reducing the number of parameters by 45%, 44%, and 44%, and FLOPs by 44%, 42%, and 41% on the × 2/3/4 SR tasks, respectively. The code will be published on GitHub after our paper is accepted for publication. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Dual modality prompt learning for visual question-grounded answering in robotic surgery

引用

Visual Computing for Industry,Biomedicine,and Art 2024年第1期7卷 316-328页

作者： Yue Zhang Wanshu Fan Peixi Peng Xin Yang Dongsheng Zhou Xiaopeng Wei National and Local Joint Engineering Laboratory of Computer Aided Design School of Software EngineeringDalian UniversityDalian 116622LiaoningChina School of Computer Science and Technology Dalian University of TechnologyDalian 116081LiaoningChina

With recent advancements in robotic surgery,notable strides have been made in visual question answering(VQA).Existing VQA systems typically generate textual answers to questions but fail to indicate the location of the relevant content within the *** limitation restricts the interpretative capacity of the VQA models and their abil-ity to explore specific image *** address this issue,this study proposes a grounded VQA model for robotic surgery,capable of localizing a specific region during answer *** inspiration from prompt learning in language models,a dual-modality prompt model was developed to enhance precise multimodal information ***,two complementary prompters were introduced to effectively integrate visual and textual prompts into the encoding process of the model.A visual complementary prompter merges visual prompt knowl-edge with visual information features to guide accurate *** textual complementary prompter aligns vis-ual information with textual prompt knowledge and textual information,guiding textual information towards a more accurate inference of the ***,a multiple iterative fusion strategy was adopted for comprehensive answer reasoning,to ensure high-quality generation of textual and grounded *** experimental results vali-date the effectiveness of the model,demonstrating its superiority over existing methods on the EndoVis-18 and End-oVis-17 datasets.

关键词： Prompt learning Visual prompt Textual prompt Grounding-answering Visual question answering

来源：评论

学校读者我要写书评

暂无评论

Dynamic Countdown Scheduling MAC Protocol in Underwater Acoustic Sensor Networks

引用

IEEE Sensors Journal 2025年第11期25卷 20797-20812页

作者： Feng, Libin Li, Zhe Mai, Haohao Chen, Yanxia Huang, Xiangdang Hainan University School of Computer Science and Technology Haikou570228 China Hainan University School of Software Engineering Haikou570228 China Hainan University School of Cyberspace Security Haikou570228 China Hainan University and the Innovation Platform for Academicians of Hainan Province School of Computer Science and Technology Haikou570228 China

Underwater acoustic sensor networks (UASNs) are highly sensitive to collisions due to the unique characteristics of underwater acoustic signal propagation. Thus, developing medium access control (MAC) protocols that can effectively avoid collisions has become particularly important. This paper proposes a dynamic countdown scheduling MAC protocol (DCS-MAC) to achieve collision-free transmission for UASNs. First, transmission schedules of nodes are integrated directly into data frames, eliminating the need for control frames, thereby reducing latency and energy consumption. Second, considering defined collision constraint, a dynamic countdown strategy is introduced where the transmission schedule of each node dynamically adjusts according to collected collision constraints, reducing the probability of data frame collisions. Then, interval trees are used to dynamically update collision constraints, maximizing the coverage of collision time periods and selecting the optimal transmission schedule. Finally, simulation results show that DCS-MAC excels in data frame delivery rate, network throughput, throughput fairness, and energy consumption. © 2001-2012 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering 31

Fine-tuning Large Language Models for Improving Factuality i...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Hu, Yinghao Gan, Leilei Xiao, Wenyi Kuang, Kun Wu, Fei School of Software Technology Zhejiang University China College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)9798891761964

Hallucination, or the generation of incorrect or fabricated information, remains a critical challenge in large language models (LLMs), particularly in high-stake domains such as legal question answering (QA). In order to mitigate the hallucination rate in legal QA, we first introduce a benchmark called LegalHalBench and three automatic metrics to evaluate the common hallucinations when LLMs answer legal questions. We then propose a hallucination mitigation method that integrates behavior cloning and a novel Hard Sample-aware Iterative Direct Preference Optimization (HIPO). We conduct extensive real-data experiments to validate the effectiveness of our approach. Our results demonstrate remarkable improvements in various metrics, including the newly proposed Non-Hallucinated Statute Rate, Statute Relevance Rate, Legal Claim Truthfulness, as well as traditional metrics such as METEOR, BERTScore, ROUGE-L, and win rates. Our benchmark and model are available at https://***/YinghaoHu/LegalHalBench. © 2025 Association for Computational Linguistics.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Triple Path Enhanced Neural Architecture Search for Multimodal Fake News Detection

Triple Path Enhanced Neural Architecture Search for Multimod...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xu, Bo Xie, Qiujie Zhou, Jiahui Zong, Linlin School of Computer Science and Technology Dalian University of Technology China School of Computer Science Fudan University China School of Software Dalian University of Technology China

ISBN: (纸本)9798350368741

Multimodal fake news detection has become one of the most crucial issues on social media platforms. Although existing methods have achieved advanced performance, two main challenges persist: (1) Under-performed multimodal news information fusion due to model architecture solidification, and (2) weak generalization ability on partial-modality contained fake news. To meet these challenges, we propose a novel and flexible triple path enhanced neural architecture search model MUSE. MUSE includes two dynamic paths for detecting partial-modality contained fake news and a static path for exploiting potential multimodal correlations. Experimental results show that MUSE achieves stable performance improvement over the baselines. © 2025 IEEE.

关键词： fake news detection neural architecture search

来源：评论

学校读者我要写书评

暂无评论

Toward actionable testing of deep learning models

引用

science China(Information sciences) 2023年第7期66卷 300-302页

作者： Yingfei XIONG Yongqiang TIAN Yepang LIU Shing-Chi CHEUNG Key Laboratory of High Confidence Software Technologies(Peking University) Ministry of Education School of Computer Science Peking University Department of Computer Science and Engineering The Hong Kong University of Science and Technology School of Computer Science University of Waterloo Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Department of Computer Science and Engineering Southern University of Science and Technology

Deep learning has become an important computational paradigm in our daily lives with a wide range of applications,from authentication using facial recognition to autonomous driving in smart vehicles. The quality of the deep learning models, i.e., neural architectures with parameters trained over a dataset, is crucial to our daily living and economy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ER-Net:Efficient Recalibration Network for Multi-ViewMulti-Person 3D Pose Estimation

引用

computer Modeling in Engineering & sciences 2023年第8期136卷 2093-2109页

作者： Mi Zhou Rui Liu Pengfei Yi Dongsheng Zhou National and Local Joint Engineering Laboratory of Computer Aided Design School of Software EngineeringDalian UniversityDalian116622China School of Computer Science and Technology Dalian University of TechnologyDalian116024China

Multi-view multi-person 3D human pose estimation is a hot topic in the field of human pose estimation due to its wide range of application *** the introduction of end-to-end direct regression methods,the field has entered a new stage of ***,the regression results of joints that are more heavily influenced by external factors are not accurate enough even for the optimal *** this paper,we propose an effective feature recalibration module based on the channel attention mechanism and a relative optimal calibration strategy,which is applied to themulti-viewmulti-person 3D human pose estimation task to achieve improved detection accuracy for joints that are more severely affected by external ***,it achieves relative optimal weight adjustment of joint feature information through the recalibration module and strategy,which enables the model to learn the dependencies between joints and the dependencies between people and their corresponding *** call this method as the Efficient Recalibration Network(ER-Net).Finally,experiments were conducted on two benchmark datasets for this task,Campus and Shelf,in which the PCP reached 97.3% and 98.3%,respectively.

关键词： Multi-view multi-person pose estimation attention mechanism computer vision

来源：评论

学校读者我要写书评

暂无评论

Weighted Attribute Based Conditional Proxy Re-Encryption in the Cloud

引用

computers, Materials & Continua 2025年第4期83卷 1399-1414页

作者： Xixi Yan Jing Zhang Pengyu Cheng Henan Key Laboratory of Network Cryptography Technology Network Information Security and Cryptography LaboratorySchool of SoftwareHenan Polytechnic UniversityJiaozuo454003China School of Computer Science and Technology Henan Polytechnic UniversityJiaozuo454000China

Conditional proxy re-encryption(CPRE)is an effective cryptographic primitive language that enhances the access control mechanism and makes the delegation of decryption permissions more granular,but most of the attribute-based conditional proxy re-encryption(AB-CPRE)schemes proposed so far do not take into account the importance of user attributes.A weighted attribute-based conditional proxy re-encryption(WAB-CPRE)scheme is thus designed to provide more precise decryption rights *** introducing the concept of weight attributes,the quantity of system attributes managed by the server is reduced *** the same time,a weighted tree structure is constructed to simplify the expression of access structure *** conditional proxy re-encryption,large amounts of data and complex computations are outsourced to cloud servers,so the data owner(DO)can revoke the user’s decryption rights directly with minimal *** scheme proposed achieves security against chosen plaintext attacks(CPA).Experimental simulation results demonstrated that the decryption time is within 6–9 ms,and it has a significant reduction in communication and computation cost on the user side with better functionality compared to other related schemes,which enables users to access cloud data on devices with limited resources.

关键词： Cloud service conditional proxy re-encryption user revocation weighted attribute

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：