检索结果-内蒙古大学图书馆

The User-Controlled K Shortest Paths with Diversity 6

学校读者我要写书评

暂无评论

The User-Controlled K Shortest Paths with Diversity

6th International Workshop on Advanced Algorithms and Control engineering, IWAACE 2022

作者： Wang, Yongqing Huang, Wei Zhang, Honghao School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Country Tianjin Key Laboratory of Intelligent and Novel Software Technology Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781510657755

The user-controlled K shortest path problem with diversity (UKSPD) is a general form of the K shortest path (KSP) problem in graphs. Instead of finding the K shortest from point to point, the UKSPD determines the level of similarity of the K shortest paths through user input parameters. In this paper, we formally describe the UKSPD problem, which acts as a multi-objective optimization problem. Considering the application of genetic algorithm in multi-objective optimization, we propose an improved genetic algorithm to solve the UKSPD problem. The basic mechanism of the whole algorithm is as follows: chromosomes are directly represented as paths, crossover and mutation operations are performed to ensure the connectivity of the paths, and the user input parameter in each iteration determines the similarity of the selected paths. The proposed algorithm is tested on the New York City Map and compared with the improved Dijkstra algorithm, and the experimental results illustrate the effectiveness of the proposed genetic algorithm. © 2022 SPIE.

关键词： Genetic algorithms

Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sun, Yuhong Yin, Zhangyue Huang, Xuanjing Qiu, Xipeng Zhao, Hui Software Engineering Institute East China Normal University China School of Computer Science Fudan University China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. Math Word Problems (MWPs) serve as a crucial benchmark for evaluating LLMs’ reasoning abilities. While most research primarily focuses on improving accuracy, it often neglects understanding and addressing the underlying patterns of errors. Current error classification methods rely on static and predefined categories, which limit their ability to capture the full spectrum of error patterns in mathematical reasoning. To enable systematic error analysis, we collect error samples from 15 different LLMs of varying sizes across four distinct MWP datasets using multiple sampling strategies. Based on this extensive collection, we introduce MWPES-300K, a comprehensive dataset containing 304,865 error samples that cover diverse error patterns and reasoning paths. To reduce human bias and enable fine-grained analysis of error patterns, we propose a novel framework for automated dynamic error classification in mathematical reasoning. Experimental results demonstrate that dataset characteristics significantly shape error patterns, which evolve from basic to complex manifestations as model capabilities increase. With deeper insights into error patterns, we propose error-aware prompting that incorporates common error patterns as explicit guidance, leading to significant improvements in mathematical reasoning performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Systematic errors

MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Yapeng Luo, Yong Zhang, Lefei Wang, Zengmao Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China

Transformer has been extensively explored for hyperspectral image classification. However, transformer poses challenges in terms of speed and memory usage because of its quadratic computational complexity. Recently the Mamba model has emerged as a promising approach, which has strong long-distance modeling capabilities while maintaining a linear computational complexity. However, representing the hyperspectral image is challenging for the Mamba due to the requirement for an integrated spatial and spectral understanding. To remedy these drawbacks, we propose a novel hyperspectral image classification model based on a Mamba model, named MambaHSI, which can simultaneously model long-range interaction of the whole image and integrate spatial and spectral information in an adaptive manner. Specifically, we design a spatial Mamba block to model the long-range interaction of the whole image at the pixel-level. Then we propose a spectral Mamba block to split the spectral vector into multiple groups, mine the relations across different spectral groups, and extract spectral features. Finally, we propose a spatial-spectral fusion module to adaptively integrate spatial and spectral features of a hyperspectral image. To our best knowledge, this is the first image-level hyperspectral image classification model based on the Mamba. We conduct extensive experiments on four diverse hyperspectral image datasets. The results demonstrate the effectiveness and superiority of the proposed model for hyperspectral image classification. This reveals the great potential of Mamba to be the next-generation backbone for hyperspectral image models. Codes are available at https://***/li-yapeng/MambaHSI. Copyright © 2025, The Authors. All rights reserved.

关键词： Image classification

Simulation and analysis of a tomographic imaging system for cloud field measurement in rectangular icing wind tunnels

学校读者我要写书评

暂无评论

Simulation and analysis of a tomographic imaging system for ...

2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024

作者： Zhang, Quan Qing, Chao Zuo, Chenglin Hu, Jiahui Li, Yan School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China Low Speed Aerodynamics Institute China Aerodynamics Research and Development Center Sichuan Mianyang621000 China Key Laboratory of Icing and Anti/De-Icing China Aerodynamics Research and Development Center Mianyang621000 China Intelligent Oil and Gas Laboratory Southwest Petroleum University Chengdu610500 China

ISBN: (数字)9781510689046

ISBN: (纸本)9781510689039

The uniformity of cloud distribution is a critical metric for evaluating the performance of icing wind tunnels, directly affecting the accuracy of experimental results. To address the challenge of measuring cloud distribution in wind tunnels, this paper proposes a solution based on extinction tomography. A rectangular cross-sectional imaging system was developed specifically for rectangular wind tunnel structures, overcoming the limitations of traditional ring-shaped systems. To resolve the issue of insufficient projections, an iterative reconstruction algorithm combined with regularization techniques was employed for accurate image reconstruction. Additionally, the BM3D denoising algorithm was applied to enhance image quality. The results of simulation experiments demonstrate that the system effectively improves the PSNR and SSIM of reconstructed images under both Gaussian and speckle noise conditions, significantly enhancing the accuracy of cloud distribution measurements. © 2025 SPIE.

关键词： Image reconstruction

Safe and Robust Subgame Exploitation in Imperfect Information Games 41

学校读者我要写书评

暂无评论

Safe and Robust Subgame Exploitation in Imperfect Informatio...

41st International Conference on Machine Learning, ICML 2024

作者： Ge, Zhenxing Xu, Zheng Ding, Tianyu Meng, Linjian An, Bo Li, Wenbin Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore Microsoft Corporation RedmondWA United States Skywork AI Singapore School of Intelligence Science and Technology Nanjing University Suzhou Campus Jiangsu Suzhou China

Opponent exploitation is an important task for players to exploit the weaknesses of others in games. Existing approaches mainly focus on balancing between exploitation and exploitability but are often vulnerable to modeling errors and deceptive adversaries. To address this problem, our paper offers a novel perspective on the safety of opponent exploitation, named Adaptation Safety. This concept leverages the insight that strategies, even those not explicitly aimed at opponent exploitation, may inherently be exploitable due to computational complexities, rendering traditional safety overly rigorous. In contrast, adaptation safety requires that the strategy should not be more exploitable than it would be in scenarios where opponent exploitation is not considered. Building on such adaptation safety, we further propose an Opponent eXploitation Search (OX-Search) framework by incorporating real-time search techniques for efficient online opponent exploitation. Moreover, we provide theoretical analyses to show the adaptation safety and robust exploitation of OX-Search, even with inaccurate opponent models. Empirical evaluations in popular poker games demonstrate OX-Search's superiority in both exploitability and exploitation compared to previous methods. Copyright 2024 by the author(s)

关键词：

DDJND: Dual Domain Just Noticeable Difference in Multi-Source Content Images with Structural Discrepancy 39

学校读者我要写书评

暂无评论

DDJND: Dual Domain Just Noticeable Difference in Multi-Sourc...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Miaohui Li, Zhenming Xie, Wuyuan College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen 518060 China

ISBN: (纸本)157735897X

Most existing just noticeable difference (JND) methods primarily integrate specific masking effects in a single domain. However, these single-domain JND methods struggle with the structural discrepancies in multi-source content images, limiting their effectiveness in visual redundancy estimation. To address this issue, we propose a dual domain encoder that combines spatial and frequency features to comprehensively capture visual patterns. Our design includes spatial pattern balance and frequency detail correction modules to balance global and local patterns and correct low- and high-frequency distributions. Additionally, we develop a dual domain decoder to effectively extract multi-scale pattern redundancies and integrate them with detail redundancies in the frequency domain. Experiments demonstrate the effectiveness and robustness of our proposed method in handling structural discrepancies in multi-source content images. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Bode diagrams

CHS: A Clustering-based Hybrid Sampling Algorithm for The Imbalanced Classification 5

学校读者我要写书评

暂无评论

CHS: A Clustering-based Hybrid Sampling Algorithm for The Im...

5th International Conference on computer Information Science and Application Technology, CISAT 2022

作者： Jia, Shengwen Shi, Kai School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Country Tianjin Key Laboratory of Intelligent and Novel Software Technology Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781510660076

The traditional SVM has poor performance in imbalanced classification. To address the issue, a clustering-based hybrid sampling algorithm CHS is proposed in this paper. The majority samples are divided into different clusters by CFSFDP clustering algorithm for hierarchical undersampling. The minority samples are oversampled, and new minority samples are generated near the boundary based on the support vectors. Finally, the moth-flame optimization algorithm (MFO) is used to optimize the new minority samples in order to avoid the generation of noisy samples. The algorithm is applied to 16 KEEL datasets with different imbalance rates and compared with other sampling algorithms. The performance is evaluated by G-mean and AUC, and the experimental results show that CHS can effectively improve the performance of SVM for imbalanced classification. © 2022 SPIE.

关键词： Clustering algorithms

Towards Training-free Anomaly Detection with Vision and Language Foundation Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Jinjin Wang, Guodong Jin, Yizhou Huang, Di State Key Laboratory of Complex and Critical Software Environment Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China

Anomaly detection is valuable for real-world applications, such as industrial quality inspection. However, most approaches focus on detecting local structural anomalies while neglecting compositional anomalies incorporating logical constraints. In this paper, we introduce LogSAD, a novel multi-modal framework that requires no training for both Logical and Structural Anomaly Detection. First, we propose a match-of-thought architecture that employs advanced large multi-modal models (i.e. GPT-4V) to generate matching proposals, formulating interests and compositional rules of thought for anomaly detection. Second, we elaborate on multi-granularity anomaly detection, consisting of patch tokens, sets of interests, and composition matching with vision and language foundation models. Subsequently, we present a calibration module to align anomaly scores from different detectors, followed by integration strategies for the final decision. Consequently, our approach addresses both logical and structural anomaly detection within a unified framework and achieves state-of-the-art results without the need for training, even when compared to supervised approaches, highlighting its robustness and effectiveness. Code is available at https://***/zhang0jhon/LogSAD. Copyright © 2025, The Authors. All rights reserved.

关键词： Anomaly detection

A study on the impact of pre-trained model on Just-In-Time defect prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guo, Yuxiang Gao, Xiaopeng Zhang, Zhenyu Chan, W.K. Jiang, Bo State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Computer Science City University of Hong Kong Hong Kong

Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In this study, we build six models: RoBERTaJIT, CodeBERTJIT, BARTJIT, PLBARTJIT, GPT2JIT, and CodeGPTJIT, each with a distinct pre-trained model as its backbone. We systematically explore the differences and connections between these models. Specifically, we investigate the performance of the models when using Commit code and Commit message as inputs, as well as the relationship between training efficiency and model distribution among these six models. Additionally, we conduct an ablation experiment to explore the sensitivity of each model to inputs. Furthermore, we investigate how the models perform in zero-shot and few-shot scenarios. Our findings indicate that each model based on different backbones shows improvements, and when the backbone’s pre-training model is similar, the training resources that need to be consumed are closer. We also observe that Commit code plays a significant role in defect detection, and different pre-trained models demonstrate better defect detection ability with a balanced dataset under few-shot scenarios. These results provide new insights for optimizing JIT defect prediction tasks using pre-trained models and highlight the factors that require more attention when constructing such models. Additionally, CodeGPTJIT and GPT2JIT achieved better performance than DeepJIT and CC2Vec on the two datasets respectively under 2000 training samples. These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting