检索结果-内蒙古大学图书馆

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Weike Tang Dingming Wu Tsz Nam Chan Kezhong Lu College of Computer Science & Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798400712456

Spatial tensors have been extensively used in a wide range of applications, including remote sensing, geospatial information systems, conservation planning, and urban planning. We study the problem of Spatially Compact Dense (SCD) block mining in a spatial tensor, which targets for discovering dense blocks that cover small spatial regions. However, most of existing dense block mining (DBM) algorithms cannot solve the SCD-block mining problem since they only focus on maximizing the density of candidate blocks, so that the discovered blocks are spatially loose, i.e., covering large spatial regions. Therefore, we first formulate the problem of mining top-k Spatially Compact Dense blocks (SCD-blocks) in spatial tensors, which ranks SCD-blocks based on a new scoring function that takes both the density value and the spatial coverage into account. Then, we adopt a filter-refinement framework that first generates candidate SCD-blocks with good scores in the filtering phase and then uses the traditional DBM algorithm to further maximize the density values of the candidates in the refinement phase. Due to the NP-hardness of the problem, we develop two types of solutions in the filtering phase, namely the top-down solution and the bottom-up solution, which can find good candidate SCD-blocks by approximately solving the new scoring function. The evaluations on four real datasets verify that compared with the dense blocks returned by existing DBM algorithms, the proposed solutions are able to find SCD-blocks with comparable density values and significantly smaller spatial coverage.

关键词： dense block

来源：评论

学校读者我要写书评

暂无评论

Light-YOLOv8-Flame: A Lightweight High-Performance Flame Detection Algorithm

arXiv

引用

arXiv 2025年

作者： Lan, Jiawei Tao, Ye Wang, Zhibiao Yu, Haoyang Cui, Wenhua School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Fire detection algorithms, particularly those based on computer vision, encounter significant challenges such as high computational costs and delayed response times, which hinder their application in real-time systems. To address these limitations, this paper introduces Light-YOLOv8-Flame, a lightweight flame detection algorithm specifically designed for fast and efficient real-time deployment. The proposed model enhances the YOLOv8 architecture through the substitution of the original C2f module with the FasterNet Block module. This new block combines Partial Convolution (PConv) and Convolution (Conv) layers, reducing both computational complexity and model size. A dataset comprising 7,431 images, representing both flame and non-flame scenarios, was collected and augmented for training purposes. Experimental findings indicate that the modified YOLOv8 model achieves a 0.78% gain in mean average precision (mAP) and a 2.05% boost in recall, while reducing the parameter count by 25.34%, with only a marginal decrease in precision by 0.82%. These findings highlight that Light-YOLOv8-Flame offers enhanced detection performance and speed, making it well-suited for real-time fire detection on resource-constrained devices. © 2025, CC BY.

关键词： Response time (computer systems)

来源：评论

学校读者我要写书评

暂无评论

An Improved LVSL with View Consensus 25

An Improved LVSL with View Consensus

引用

Proceedings of the 2025 5th International Conference on Bioinformatics and Intelligent Computing

作者： Yuting Xu Qing Ai Bo Cui School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9798400712203

In multi-view multi-label learning (MVML), each sample can be represented by multiple view features and associated with multiple labels. Most existing MVML algorithms are based on the assumption that all views share the same label set. However, in practice, different views may contain distinct label information, that means a single view cannot fully represent all labels. Based on this issue, the LVSL algorithm effectively learns view-specific labels and obtains superior classification performance. However, LVSL still has the limitation that it fails to consider the correlations between views, leading to suboptimal learning results. In this paper, we propose an improved LVSL algorithm named LVSL_VC (LVSL with view consensus). We incorporate view consensus learning into the original LVSL framework. Firstly, we employ view weights to model view consensus, assuming that views with similar weights will yield similar prediction outputs, conversely, they will be different. Secondly, we integrate the view consensus into the LVSL framework and construct a new classification model. Finally, we utilize an alternating optimization method to solve the problem. Extensive experimental results demonstrate that the LVSL_VC outperforms other state-of-the-art MVML algorithms.

关键词： Multi-view multi-label learning

来源：评论

学校读者我要写书评

暂无评论

Testing Refactoring Engine via Historical Bug Report driven LLM

arXiv

引用

arXiv 2025年

作者： Wang, Haibo Xu, Zhuolin Tan, Shin Hwei Department of Computer Science & Software Engineering Concordia University Montreal Canada

Refactoring is the process of restructuring existing code without changing its external behavior while improving its internal structure. Refactoring engines are integral components of modern Integrated Development Environments (IDEs) and can automate or semi-automate this process to enhance code readability, reduce complexity, and improve the maintainability of software products. Similar to traditional software systems such as compilers, refactoring engines may also contain bugs that can lead to unexpected behaviors. In this paper, we propose a novel approach called RETESTER, a LLM-based framework for automated refactoring engine testing. Specifically, by using input program structure templates extracted from historical bug reports and input program characteristics that are error-prone, we design chain-of-thought (CoT) prompts to perform refactoring-preserving transformations. The generated variants are then tested on the latest version of refactoring engines using differential testing. We evaluate RETESTER on two most popular modern refactoring engines (i.e., ECLIPSE, and INTELLIJ IDEA). It successfully revealed 18 new bugs in the latest version of those refactoring engines. By the time we submit our paper, seven of them were confirmed by their developers, and three were fixed. © 2025, CC BY-NC-SA.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Capturing Temporal Components for Time Series Classification 27th

Capturing Temporal Components for Time Series Classificatio...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Vavilthota, Venkata Ragavendra Ramanathan, Ranjith Aakur, Sathyanarayanan N. Department of Computer Science Oklahoma State University StillwaterOK74078 United States Department of Animal and Food Sciences Oklahoma State University StillwaterOK74078 United States Department of Computer Science and Software Engineering Auburn University Auburn36849 United States

ISBN: (纸本)9783031781063

Analyzing sequential data is crucial in many domains, particularly due to the abundance of data collected from the Internet of Things paradigm. Time series classification, the task of categorizing sequential data, has gained prominence, with machine learning approaches demonstrating remarkable performance on public benchmark datasets. However, progress has primarily been in designing architectures for learning representations from raw data at fixed (or ideal) time scales, which can fail to generalize to longer sequences. This work introduces a compositional representation learning approach trained on statistically coherent components extracted from sequential data. Based on a multi-scale change space, an unsupervised approach is proposed to segment the sequential data into chunks with similar statistical properties. A sequence-based encoder model is trained in a multi-task setting to learn compositional representations from these temporal components for time series classification. We demonstrate its effectiveness through extensive experiments on publicly available time series classification benchmarks. Evaluating the coherence of segmented components shows its competitive performance on the unsupervised segmentation task. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Unsigned Road Incidents Detection Using Improved RESNET From Driver-View Images

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1203-1216页

作者： Li, Changping Wang, Bingshu Zheng, Jiangbin Zhang, Yongjun Chen, C.L. Philip Northwestern Polytechnical University School of Software Xi’an710129 China Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Frequent road incidents cause significant physical harm and economic losses globally. The key to ensuring road safety lies in accurately perceiving surrounding road incidents. However, the highly dynamic nature of traffic introduces significant challenges, particularly in detecting sudden and temporary incidents. In this article, we propose a novel detection framework, multihead attention ResNet with dynamic bottleneck (DB_RESNET_MHA), to identify physical unsigned road incidents. Our approach introduces three key innovations. First, we develop a tailored data augmentation strategy to create images that closely mimic the complex variations found in real-world road environments. Second, we enhance model expressiveness by employing attention mechanisms to nonlinearly integrate convolutional kernels within the residual network. Furthermore, we refine the prediction head by applying spatially distinct attention weights, enabling the model to capture intricate correlations between different features more effectively. To demonstrate the effectiveness of our method, we create a dataset for unsigned road incidents (UnsignRI), comprising a total of 16 323 images that capture 12 distinct types of incidents. It stands out as the most comprehensive dataset in the field, encompassing a wide range of geographical features and incident categories. Experimental results show that DB_RESNET_MHA achieves an average accuracy of 96.2% and a f1-score of 0.955 across various categories of unsigned incidents, surpassing other models. © 2020 IEEE.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Research on Entity Recognition Method for Quality Standards of Concrete Prefabricated Components 1

Research on Entity Recognition Method for Quality Standards ...

引用

1st International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2024

作者： Zhang, Tingshu Tu, Ming Wang, Gefan Chen, Bingyong Zhao, Yishi Shang, Jianga School of Computer Science China University of Geosciences Wuhang China Intelligent Construction System Research Institute China Construction Third Engineering Buerau Group Co.L Wuhang China Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Ministry of Education School of Computer Science China University of Geosciences Wuhang China

ISBN: (纸本)9781643685779

In recent years, the country has released a large number of standard documents related to prefabricated concrete components. Due to the dispersion and complexity of these standards, it is difficult for industry managers to implement them. Therefore, it is imperative to establish a knowledge graph in the field of quality standards for precast concrete components to achieve knowledge management. The construction of knowledge graph first requires named entity recognition, but due to the specificity of the construction industry, entity recognition of the text in this field still suffers from the problems of low recognition accuracy and high resource consumption. Aiming at the low recognition accuracy and high resource consumption in named entity recognition due to the specificity of the industry, this paper proposes a named entity recognition model ALBERT-BiLSTM-SA-CRF for the field of precast concrete component quality standard, which can capture the full text and local feature information more effectively through the combination of BiLSTM and self-attention mechanism, and accurately recognize entities in the standard. Meanwhile, using ALBERT as the word embedding layer can play the role of reducing resource consumption and improving processing efficiency. © 2025 The Authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Weighted layer aggregation with fast and local label expanding method for community detection in multiplex networks

引用

Physica A: Statistical Mechanics and its Applications 2025年 670卷

作者： Shahgholi, Pouya Bouyer, Asgarali Arasteh, Bahman Liu, Xiaoyang Department of software engineering Azarbaijan Shahid Madani University Tabriz Iran Department of software engineering Faculty of Engineering and Natural Science Istinye University İstanbul Turkey Department of Computer Science Khazar University Baku Azerbaijan School of Computer Science and Engineering Chongqing University of Technology Chongqing400054 China

Community detection in multiplex networks has emerged as a crucial research area due to its ability to capture complex interactions across multiple layers of interconnected data. Despite significant advancements, existing methods often face critical challenges, including computational time, resolution limit, free parameter tuning, training models, etc. To overcome these limitations, this paper presents LCDMN (Layer-Coupled Diffusion for Multiplex Networks) algorithm designed for accurate and efficient community detection in multiplex networks. LCDMN employs dynamic scaling and layer coupling to adaptively identify community structures across diverse network configurations, offering improved resilience to network's density and structural ambiguity. LCDMN addresses the challenges of layer diversity by: (1) dynamically weighting layers based on critical parameters such as layer correlation, layer nodes activity variance, and attractiveness, (2) developing a robust node scoring method, (3) the aggregating layers of multiplex network into a single-layer, weighted graph, (4) employing a label diffusion approach with mechanisms for handling overlapping nodes, and (5) refining community structures through a dynamic merging process that adaptively adjusts layer contributions and community boundaries during execution, ensuring context-sensitive resolution of structural ambiguity. Nodes and edges are scored using network topology and structural metrics to efficiently incorporate in label diffusion process for detecting initial communities. The approach balances computational efficiency with precision, enabling the detection of cohesive and well-defined communities in complex networks. Experimental evaluations on real-world and synthetic multiplex networks demonstrate that LCDMN consistently outperforms state-of-the-art methods, such as Infomap, MDLPA, MPBTV, LART, DGFM3 and GenLouvain, in terms of Normalized Mutual Information (NMI), Adjusted Rand Index (ARI), and modularity.

关键词： Community detection Label diffusion Layer aggregation Multiplex networks Similarity

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in qualitative analysis: a practical guide and reflections based on results from using GPT to analyze interview data in a substance use program

引用

Quality and Quantity 2025年 1-24页

作者： Yang, Yang Ma, Liran Institute of Behavioral Research Texas Christian University 2800 South University Drive Fort Worth 76109 TX United States Department of Computer Science and Software Engineering Miami University Oxford OH United States

Language-based text provide valuable insights into people’s lived experiences. While traditional qualitative analysis is used to capture these nuances, new paradigms are needed to scale qualitative research effectively. Artificial intelligence presents an unprecedented opportunity to expand the sale of analysis for obtaining such nuances. The study tests the application of GPT-4—a large language modeling—in qualitative data analysis using an existing set of text data derived from 60 qualitative interviews. Specifically, the study provides a practical guide for social and behavioral researchers, illustrating core elements and key processes, demonstrating its reliability by comparing GPT-generated codes with researchers’ codes, and evaluating its capacity for theory-driven qualitative analysis. The study followed a three-step approach: (1) prompt engineering, (2) reliability assessment by comparison of GPT-generated codes with researchers’ codes, and (3) evaluation of theory-driven thematic analysis on psychological constructs. The study underscores the utility of GPT’s capabilities in coding and analyzing text data with established qualitative methods while highlighting the need for qualitative expertise to guide GPT applications. Recommendations for further exploration are also discussed. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Artificial intelligence ChatGPT and GPT Large language models Qualitative research

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

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

作者： Zhang, Yujun Chen, Yanqu Wang, Jiakai Hu, Jin Tao, Renshuai Liu, Xianglong State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (纸本)9798350368741

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression. © 2025 IEEE.

关键词： Automatic speech recognition natural noise pattern phoneme-level targeted universal adversarial examples

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：