检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Etezadi, Romina Abualhaija, Sallam Arora, Chetan Briand, Lionel School of Electrical Engineering & Computer Science University of Ottawa Canada SnT Centre for Security Reliability and Trust University of Luxembourg Luxembourg Faculty of Information Technology Monash University Melbourne Australia Lero Research Ireland centre for Software Research University of Limerick Ireland

New regulations are continuously introduced to ensure that software development complies with the ethical concerns and prioritizes public safety. A prerequisite for demonstrating compliance involves tracing software requirements to legal provisions. Requirements traceability is a fundamental task where requirements engineers are supposed to analyze technical requirements against target artifacts, often under limited time budget. Doing this analysis manually for complex systems with hundreds of requirements is infeasible. The legal dimension introduces additional challenges that only exacerbate manual effort. In this paper, we investigate two automated solutions based on large language models (LLMs) to predict trace links between requirements and legal provisions. The first solution, Kashιf, is a classifier that leverages sentence transformers and semantic similarity. The second solution prompts a recent generative LLM based on Rice, a prompt engineering framework. On a benchmark dataset, we empirically evaluate Kashιf and compare it against a baseline classifier from the literature. Kashιf can identify trace links with an average recall of ≈67%, outperforming the baseline with a substantial gain of 54 percentage points (pp) in recall. However, on unseen, more complex requirements documents traced to the European general data protection regulation (GDPR), Kashιf performs poorly, yielding an average recall of 15%. On the same documents, however, our Rice-based solution yields an average recall of 84%, with a remarkable gain of about 69 pp over Kashιf. Our results © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Segmented Merge: A New Primitive for Parallel Sparse Matrix Computations 17th

Segmented Merge: A New Primitive for Parallel Sparse Matrix...

引用

17th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2020

作者： Ji, Haonan Lu, Shibo Hou, Kaixi Wang, Hao Liu, Weifeng Vinter, Brian Super Scientific Software Laboratory Department of Computer Science and Technology China University of Petroleum-Beijing Beijing China Department of Computer Science Virginia Tech Blacksburg United States Department of Computer Science and Engineering The Ohio State University Columbus United States Faculty of Technical Sciences Aarhus University Aarhus Denmark

ISBN: (纸本)9783030794774

Segmented operations, such as segmented sum, segmented scan and segmented sort, are important building blocks for parallel irregular algorithms. We in this work propose a new parallel primitive called segmented merge. Its function is in parallel merging q sub-segments to p segments, both of nonuniform lengths. We implement the segmented merge primitive on GPUs and demonstrate its efficiency on parallel sparse matrix transposition (SpTRANS) and sparse matrix-matrix multiplication (SpGEMM) operations. © 2021, IFIP International Federation for Information Processing.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

DAM-Net: Global Flood Detection from SAR Imagery Using Differential Attention Metric-Based Vision Transformers

arXiv

引用

arXiv 2023年

作者： Saleh, Tamer Weng, Xingxing Holail, Shimaa Hao, Chen Xia, Gui-Song Wuhan University Wuhan430079 China National Engineering Research Center for Multi-media Software School of Computer Science Institute of Artificial Intelligence Wuhan University Wuhan430072 China Geomatics Engineering Department Faculty of Engineering at Shoubra Benha University Cairo1196 Egypt School of Computer Science Wuhan University Wuhan430072 China

The detection of flooded areas using high-resolution synthetic aperture radar (SAR) imagery is a critical task with applications in crisis and disaster management, as well as environmental resource planning. However, the complex nature of SAR images presents a challenge that often leads to an overestimation of the flood extent. To address this issue, we propose a novel differential attention metric-based network (DAM-Net) in this study. The DAM-Net comprises two key components: a weight-sharing Siamese backbone to obtain multi-scale change features of multi-temporal images and tokens containing high-level semantic information of water-body changes, and a temporal differential fusion (TDF) module that integrates semantic tokens and change features to generate flood maps with reduced speckle noise. Specifically, the backbone is split into multiple stages. In each stage, we design three modules, namely, temporal-wise feature extraction (TWFE), cross-temporal change attention (CTCA), and temporal-aware change enhancement (TACE), to effectively extract the change features. In TACE of the last stage, we introduce a class token to record high-level semantic information of water-body changes via the attention mechanism. Another challenge faced by data-driven deep learning algorithms is the limited availability of flood detection datasets. To overcome this, we have created the S1GFloods open-source dataset, a global-scale high-resolution Sentinel-1 SAR image pairs dataset covering 46 global flood events between 2015 and 2022. The experiments on the S1GFloods dataset using the proposed DAM-Net showed top results compared to state-of-the-art methods in terms of overall accuracy, F1-score, and IoU, which reached 97.8%, 96.5%, and 93.2%, respectively. Our dataset and code will be available online at https://***/Tamer-Saleh/S1GFlood-Detection. © 2023, CC BY.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Balls

arXiv

引用

arXiv 2025年

作者： Gao, Can Tan, Xiaofeng Zhou, Jie Ding, Weiping Pedrycz, Witold The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China The Faculty of Data Science City University of Macau Macau999078 China The Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland The Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia The Department of Computer Engineering Istinye University Istanbul Turkey

Outlier detection refers to the identification of anomalous samples that deviate significantly from the distribution of normal data and has been extensively studied and used in a variety of practical tasks. However, most unsupervised outlier detection methods are carefully designed to detect specified outliers, while real-world data may be entangled with different types of outliers. In this study, we propose a fuzzy rough sets-based multi-scale outlier detection method to identify various types of outliers. Specifically, a novel fuzzy rough sets-based method that integrates relative fuzzy granule density is first introduced to improve the capability of detecting local outliers. Then, a multi-scale view generation method based on granular-ball computing is proposed to collaboratively identify group outliers at different levels of granularity. Moreover, reliable outliers and inliers determined by the three-way decision are used to train a weighted support vector machine to further improve the performance of outlier detection. The proposed method innovatively transforms unsupervised outlier detection into a semi-supervised classification problem and for the first time explores the fuzzy rough sets-based outlier detection from the perspective of multi-scale granular balls, allowing for high adaptability to different types of outliers. Extensive experiments carried out on both artificial and UCI datasets demonstrate that the proposed outlier detection method significantly outperforms the state-of-the-art methods, improving the results by at least 8.48% in terms of the Area Under the ROC Curve (AUROC) index. The source codes are released at https://***/Xiaofeng-Tan/MGBOD. © 2025, CC BY.

关键词： Granulation

来源：评论

学校读者我要写书评

暂无评论

Improving WiFi Fingerprint Database With Irregular Distribution of Reference Points Using Interpolation Methods

Improving WiFi Fingerprint Database With Irregular Distribut...

引用

International Conference on Advanced Technologies for Communications, ATC

作者： Trung Vu-Thanh Jing He Ninh Duong-Bao Seon-Woo Lee Luong Nguyen Thi Khanh Nguyen-Huu College of Computer Science and Electronic Engineering Hunan University Changsha China Faculty of Mathematics and Informatics Dalat University Dalat Vietnam Division of Software Hallym University Chuncheon Korea Faculty of Information Technology Dalat University Dalat Vietnam Department of Electronics and Telecommunications Dalat University Dalat Vietnam

ISBN: (数字)9798350353983

ISBN: (纸本)9798350353990

Using WiFi Fingerprinting for indoor positioning is becoming increasingly popular due to its cost-effectiveness. However, to ensure the system can operate with high accuracy and stability, this technique requires a burden of data collection tasks from a dense distribution of reference points (RPs). To decrease the cost of data collection, as well as to improve the WiFi fingerprint database with irregular distribution of RPs, this study applies and compares different interpolation methods. Evaluating these methods in a public dataset including multiple sub-datasets with irregular distributions of RPs, the results highlight the Linear Barycentric interpolation (LB) as the most favorable method due to its low complexity and stable performance. The LB-based fingerprint database achieves an average interpolation error of less than 3 dBm compared to the original one. When applying the interpolated database to positioning tasks, it can help reduce acquisition costs by up to 50% while improving positioning accuracy by up to 11%. The study reveals the feasibility of interpolation in optimizing WiFi fingerprint data collection, especially in large and complex environments where regular distribution of RPs cannot be deployed.

关键词： Interpolation Costs Accuracy Databases Fingerprint recognition Data collection Reliability Computational complexity Wireless fidelity Floors

来源：评论

学校读者我要写书评

暂无评论

Design of a Lower Limb Exoskeleton Rehabilitation Robot System Based on Forward Dynamics Simulation

Design of a Lower Limb Exoskeleton Rehabilitation Robot Syst...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Yudong Fang Yuefei Wang Liucun Zhu Zhen Liu Lei Shi Muxin Du Jianchu Lin School of Mechanical and Marine Engineering Beibu Gulf University Qinzhou China Sentinel Institute of Science and Technology Beibu Gulf University Qinzhou China Nagasaki Institute of Applied Science Nagasaki Japan Guangzhou Shiyuan Electronic Technology Company Limited Guangzhou China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai'an China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

Lower limb exoskeleton rehabilitation robots can effectively improve the rehabilitation of stroke patients and can substantially reduce the workload of rehabilitation therapists and improve work efficiency. In this paper, we propose a method to investigate the influence of muscle groups on the hip joint during the gait cycle through kinetic modeling simulation. The method is validated using electromyographic signals (EMG). The patients are treated according to their gait characteristics. Simulation with OpenSim; optimisation by Scone controller; joint motion change curves were analysed by Matlab simulation to verify the correctness of the mathematical model, and the simulation showed excellent following effect. The feasibility of the theory is verified, and a new scheme is proposed for the treatment of stroke patients.

关键词： Limbs Exoskeletons Stroke (medical condition) Muscles Assistive robots Mathematical models Kinetic theory MATLAB Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Low Code Programming using Traditional vs Large Language Model Support

arXiv

引用

arXiv 2024年

作者： Liu, Yongkun Chen, Jiachi Bi, Tingting Grundy, John Wang, Yanlin Yu, Jianxing Chen, Ting Tang, Yutian Zheng, Zibin School of Software Engineering Sun Yat-sen University China The The University of Western Australia Australia The Faculty of Information Technology Monash University Australia The School of Artificial Intelligence Sun Yat-sen University China The School of Computer Science and Engineering University of Electronic Science and Technology of China China University of Glasgow United Kingdom

Low-code programming (LCP) refers to programming using models at higher levels of abstraction, resulting in less manual and more efficient programming, and reduced learning effort for amateur developers. Many LCP tools have rapidly evolved and have benefited from the concepts of visual programming languages (VPLs) and programming by demonstration (PBD). With huge increase in interest in using large language models (LLMs) in software engineering, LLM-based LCP has began to become increasingly important. However, the technical principles and application scenarios of traditional approaches to LCP and LLM-based LCP are significantly different. Understanding these key differences and characteristics in the application of the two approaches to LCP by users is crucial for LCP providers in improving existing and developing new LCP tools, and in better assisting users in choosing the appropriate LCP technology. We conducted an empirical study of both traditional LCP and LLM-based LCP. We analyzed developers’ discussions on Stack Overflow (SO) over the past three years and then explored the similarities and differences between traditional LCP and LLM-based LCP features and developer feedback. Our findings reveal that while traditional LCP and LLM-based LCP share common primary usage scenarios, they significantly differ in scope, limitations and usage throughout the software development lifecycle, particularly during the implementation phase. We also examine how LLMs impact and integrate with LCP, discussing the latest technological developments in LLM-based LCP, such as its integration with VPLs and the application of LLM Agents in software engineering. Copyright © 2024, The Authors. All rights reserved.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Sentiment-Based Neural Network Approach for Predicting the Severity of Bug Reports 5

Sentiment-Based Neural Network Approach for Predicting the S...

引用

5th International Conference on Intelligent Computing in Data sciences, ICDS 2021

作者： Baarah, Aladdin Aloqaily, Ahmad Zyod, Hala Mustafa, Nasser The Hashemite University Faculty of Prince Al-Hussein Bin Abdallah II for IT Department of Software Engineering P.O. Box 330127 Zarqa Jordan The Hashemite University Department of Software Engineering Zarqa Jordan Wenzhou-Kean University Department of Computer Science Wenzhou China

ISBN: (纸本)9781665442381

During the software maintenance process, bugs encountered by software users need to be solved according to their severity level to improve the quality of the software. Therefore, bug reports with high severity should have the highest priority to be fixed. A numerous number of bug reports are submitted daily through Bug Tracking Systems (BTS) such as Bugzilla. The bug triager examines the incoming bug reports manually and verifies whether the assigned severity level is correct or not. This manual process is time-consuming, requires much effort and is possibly error-prone. However, a limited number of research works have considered the sentiments of the bug reporters in predicting the severity of bug reports. This paper proposes two approaches based on sentiment analysis, the Lexicon-based and Multilayer Perceptron (MLP) neural network approaches. The sentiment analysis process determines and measures the sentiment words and their sentiment scores according to the popular sentiment lexicon called SentiWordNet. The proposed approaches are validated on the Eclipse open-source project, and the sentiment-based models performance is evaluated. According to the experimental results, the sentiment-based MLP outperforms the Lexicon-based approach (baseline approach). The F-measure has been improved significantly from 0.52 for the Lexicon-based approach to 0.81 when applying the MLP approach. © 2021 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Optimizing Results in Aerial Images through Post-Processing Techniques on YOLOv7 23

Optimizing Results in Aerial Images through Post-Processing ...

引用

12th International Symposium on Information and Communication Technology, SOICT 2023

作者： Vo, Nguyen D. Nguyen, Thu M. Nguyen, Triet H.M. Nguyen, Khang Multimedia Communications Laboratory University of Information Technology Vietnam National University Ho Chi Minh City Ho Chi Minh city Viet Nam Faculty of Computer Science University of Information Technology Vietnam National University Ho Chi Minh City Ho Chi Minh city Viet Nam Faculty of Software Engineering University of Information Technology Vietnam National University Ho Chi Minh City Ho Chi Minh city Viet Nam

ISBN: (纸本)9798400708916

Object detection in aerial images has garnered significant attention from the research community in recent years. The challenges posed by small objects, diverse orientations, and complex backgrounds have spurred extensive research efforts. In this paper, we focus on object detection in a YOLOv7-based framework, to address the issue of overlapping predicted regions, we introduce and apply the Soft-NMS (Non-Maximum Suppression) technique, a post-processing method known for its effectiveness in improving detection accuracy in such scenarios. Soft-NMS adjusts bounding box scores based on the extent of overlap, allowing for more accurate localization of objects in densely populated regions. Furthermore, we present comprehensive experimental results to validate the efficacy of our proposed approach. The analyses encompass a thorough evaluation on the UCAS Aerial Object Detection (UCAS AOD) dataset, comprising over 1500 aerial images captured from diverse perspectives. Our method has demonstrated an improvement in object detection performance, particularly in scenarios with closely positioned objects. The proposed framework showcases its ability to handle complex aerial scenes with higher precision and recall rates compared to conventional methods. © 2023 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Typical curve with G1 constraints for curve completion

引用

Visual Computing for Industry,Biomedicine,and Art 2021年第1期4卷 283-294页

作者： Chuan He Gang Zhao Aizeng Wang Fei Hou Zhanchuan Cai Shaolin Li School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China State Key Laboratory of Lunar and Planetary Sciences Macao University of Science and TechnologyMacao 999078China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of SciencesBeijing 100049China Faculty of Information Technology Macao University of Science and TechnologyMacao 999078China

This paper presents a novel algorithm for planar G1 interpolation using typical curves with monotonic *** G1 interpolation problem is converted into a system of nonlinear equations and sufficient conditions are provided to check whether there is a *** proposed algorithm was applied to a curve completion *** main advantages of the proposed method are its simple construction,compatibility with NURBS,and monotonic curvature.

关键词： Typical curves Monotonic curvature G1 interpolation Curve completion Euler spiral

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：