检索结果-内蒙古大学图书馆

8th International Conference on Signal and Image Processing, ICSIP 2023

作者： Zhu, Tianxing Liu, Qin Zhang, Lixiang Tongji University School of Software Engineering Shanghai China Northwestern Polytechnical University School of Computer Science Xi'an China

ISBN: (纸本)9798350397932

Convolutional neural network (CNN) has been broadly adopted on hyperspectral image (HSI) processing due to its impressive feature extraction capabilities. Nevertheless, it is still a challenge for CNN-based hyperspectral image classification methods to extract more effective spectral-spatial features considering all spectral bands. The recent advances of graph convolutional neural networks (GCN), a combination of CNN and graph representation learning, have shown great potential in the HSI. However, the existing GCN-based methods have lower accuracy than the mature CNN methods due problems such as overdependence on the adjacency matrix, usage of a single modal feature. In this paper, we propose the Multi-Feature Fusion Residual Hypergraph Convolution Network (MF-RHCN) for HSI classification. We present a novel Hypergraph Convolution Network that fuses multimodal features effectively, and automatically updates the hyperedge weights, which solves the difficulties encountered by the previous GCN-based hyperspectral classification methods. MF-RHCN first generates hyperedges from features of different modalities to construct a hypergraph representing multimodal features in HSI. Then, the HSI and the extracted hypergraph are input into the hypergraph convolutional neural network for learning. We enhance the hypergraph convolutions with residual connection and input mapping, which helps reduce the over-smoothing issue associated with deep hypergraph models. Sufficient experiments on three datasets have proved the effectiveness of MF-RHCN. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Improving efficiency in rationale discovery for Out-of-Distribution molecular representations

Improving efficiency in rationale discovery for Out-of-Distr...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhang, Jiahui Li, Jiahe Du, Wenjie Zhang, Shuai Wu, Di Wang, Yang University of Science and Technology of China School of Software Engineering Suzhou China University of Science and Technology of China School of Computer Science and Technology Suzhou China

ISBN: (纸本)9798350337488

Graph Neural Networks (GNNs), as the dominant approach in Molecular Representation Learning (MRL), have exhibited remarkable efficacy in diverse tasks, including molecular property prediction and drug discovery. Considering the dynamic and diverse nature of test molecules in real-world contexts, the previous independently and identically distributed (i.i.d.) assumption for training and test molecules is not align with the requirements of practical applications in chemistry. Rationalization has been proposed to enhance the Out-of-Distribution (OOD) generalization of GNN, but a critical concern remains unexplored: low efficiency in rationale discovery. We consider this bottleneck is due to large search space and overly flexible modeling. Here, we introduce a framework called Molecule Stratifier and Invariant Rational Improver (MSIRI) to overcome the challenge. Specifically, MSIRI adopt vector quantization to obtain invariant rationales and the search space is narrowed by substructure and two assumptions based on subgraph matching. Experimental results on ten datasets demonstrate that our approach both achieves significant improvements across various GNN backbones and outperforms other six Out-of-Distribution method, clearly demonstrating its effectiveness in addressing the OOD challenges in MRL. © 2023 IEEE.

关键词： GNN invariant learning molecule representation learning Out-of-Distribution

来源：评论

学校读者我要写书评

暂无评论

Fix the Tests: Augmenting LLMs to Repair Test Cases with Static Collector and Neural Reranker 35

Fix the Tests: Augmenting LLMs to Repair Test Cases with Sta...

引用

35th IEEE International Symposium on software Reliability engineering, ISSRE 2024

作者： Liu, Jun Yan, Jiwei Xie, Yuanyuan Yan, Jun Zhang, Jian State Key Laboratory of Computer Science Institute of Software China Chinese Academy of Sciences Technology Center of Software Engineering Institute of Software China China UCAS School of Intelligent Science and Technology Hangzhou Institute for Advanced Study China

ISBN: (纸本)9798350353884

During software evolution, it is advocated that test code should co-evolve with production code. In real development scenarios, test updating may lag behind production code changing, which may cause compilation failure or bring other troubles. Existing techniques based on pre-trained language models can be directly adopted to repair obsolete tests caused by such unsynchronized code changes, especially syntactic-related ones. However, the lack of task-oriented contextual information affects the repair accuracy on large-scale projects. Starting from an obsolete test, the key challenging task is precisely identifying and constructing Test-Repair-Oriented Contexts (TROCtxs) from the whole repository within a limited token *** this paper, we propose Synter (SYNtactic-breaking- changes-induced TEst Repair), a novel approach based on LLMs to automatically repair obsolete test cases via precise and concise TROCtxs construction. Inspired by developers' programming practices, we design three types of TROCtx: class context, usage context, and environment context. Given an obsolete test case to repair, Synter firstly collects the related code information for each type of TROCtx through static analysis techniques automatically. Then, it generates reranking queries to identify the most relevant TROCtxs, which will be taken as the repair-required key contexts and be input to the large language model for the final test *** evaluate the effectiveness of Synter, we construct a benchmark dataset that contains a set of obsolete tests caused by syntactic breaking changes. The experimental results show that Synter outperforms baseline approaches both on textual- and intent-matching metrics. With the augmentation of constructed TROCtxs, hallucinations are reduced by 57.1%. © 2024 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Competition for roadside camera monocular 3D object detection

引用

National science Review 2023年第6期10卷 34-37页

作者： Jinrang Jia Yifeng Shi Yuli Qu Rui Wang Xing Xu Hai Zhang Baidu Inc. Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University College of Software Jilin University School of Computer Science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION Accurate environment perception is a critical topic in autonomous driving and intelligent *** environmental perception methods mostly rely on on-board ***,limited by the installation height,thereare problems such as blind spots and unstable long-range perception in vehicle perceptual ***,with the rapid improvement of intelligent infrastructure,it has become possible to use roadside cameras for traffic environment *** from the increased height when compared with on-boardsensors,roadside cameras can obtain a larger perceptual field of view and realize long-range observation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PTDA-SWGCL: Predicting tRNA-Disease Associations using Supplementarily Weighted Graph Contrastive Learning

PTDA-SWGCL: Predicting tRNA-Disease Associations using Suppl...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhang, Yuanpeng Qian, Yurong Xiao, Xiaojun Hu, Xiaowen Huang, Zhijian Deng, Lei Xinjiang University School of Software Urumqi China Central South University School of Computer Science and Engineering Changsha China

ISBN: (纸本)9798350337488

tRNAs play a pivotal role in protein synthesis by transporting amino acids to the ribosome according to mRNA instructions. These molecules are essential regulators in various biological processes, and their dysregulation is closely linked to human diseases. Predicting associations between tRNAs and diseases is valuable for uncovering biomarkers that aid in disease prevention, detection, prognosis, diagnosis, and treatment. However, experimental validation of such associations is resource-intensive, necessitating the development of robust computational methods. In this study, we propose PTDA-SWGCL, a novel model for predicting potential tRNA-disease associations. PTDA-SWGCL integrates tRNA and disease similarity information derived from Gaussian kernel similarity, sequence similarity, and semantic similarity. It initializes tRNA and disease embeddings using this similarity information and refines them through supplementarily weight and graph comparison learning training on the tRNA-disease association graph. The final association pair prediction is obtained by the inner product of the tRNA and disease embeddings. Experimental results demonstrate that PTDA-SWGCL outperforms state-of-the-art methods. Case studies confirm its effectiveness in predicting tRNA-disease associations. The code and data are available at https://***/ZYPssss/PTDA-SWGCL. © 2023 IEEE.

关键词： graph contrastive learning similarity supplementary weighting tRNA-disease association

来源：评论

学校读者我要写书评

暂无评论

CSP-RM: Reputation Management Decision Support for Crowdsourcing Service Providers

CSP-RM: Reputation Management Decision Support for Crowdsour...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Wang, Shipeng Li, Qingzhong Cui, Lizhen Jiang, Yali Shen, Zhiqi Yu, Han Shandong University School of Software Jinan China China Nanyang Technological University School of Computer Science and Engineering Singapore

ISBN: (纸本)9798350304855

The increasing popularity of crowdsourcing has resulted in the emergence of multiple crowdsourcing service providers (CSPs), such as Mechnical Turk and Crowdflower, which compete to attract crowd workers (CWs). CWs can share their experience working for various CSPs, which forms the basis of CSP reputation score. This information can be used for trust building and facilitating future CWs' decisions on which CSP to work for. Existing reputation management research in crowdsourcing has mainly focused on controlling task quality and improving revenue from the perspective of CSPs. Little attention has been paid to helping CSPs manage their reputation to attract and retain CWs. In this paper, we propose the Crowdsourcing Service Provider Reputation Management (CSP-RM) framework to bridge this important gap. Based on the current reputation of CSPs, it dynamically balances the trade-off between the reputation maintenance cost and the long-term profit for a given CSP. It performs dynamic commission allocation for a CSP based on Lyapunov optimization to guide the recruitment of CWs, while considering the revenue and the changes in the number of CWs. Extensive experiments based on highly competitive crowdsourcing market demonstrate that CSP-RM makes the most advantageous cost-benefit trade-off compared to existing approaches, outperforming the best baseline by 23.83%, 39.21% and 3.36% in terms of average cumulative revenue, average number of CWs and public reputation, respectively. To the best of our knowledge, it is the first decision support framework for enabling CSPs to recruit more CWs in a highly competitive market, while maintaining their reputation and ensuring long-term benefit. © 2023 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Fast Super-Resolution Network via Dynamic Path Selection 2

Fast Super-Resolution Network via Dynamic Path Selection

引用

2nd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2023

作者： Jia, Longfei Hu, Yuguo Tian, Xianlong Luo, Wenwei University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798350331417

In the context of edge computing environments, where the storage space and computational resources are constrained, complex super-resolution network models face significant challenges during inference. In this paper, we propose a Fast Super-Resolution Network (FSRN) based on the dynamic path selection mechanism. This method employs a policy network to boost the inference process of super-resolution network models, enabling efficient super-resolution tasks under resource limitations. The primary function of the policy network is to intelligently select appropriate inference paths based on input data and available computational resources. Its key objective is to minimize the degradation in super-resolution quality while reducing the computational burden as much as possible. In view of this objective, we designed a reward function to guide the policy network in discovering the optimal strategies. With the guidance of the policy network, we successfully enhanced the inference speed of super-resolution network models on edge devices while efficiently reducing computational overhead. Extensive experiments verify that the proposed method can significantly reduce the inference time at the cost of slight or even no performance degradation. © 2023 IEEE.

关键词： accelerate reasoning edge computing resource constrained Super-resolution

来源：评论

学校读者我要写书评

暂无评论

Adaptive IoT Decision Making in Uncertain Environments 7

Adaptive IoT Decision Making in Uncertain Environments

引用

7th IEEE International Conference on Smart Internet of Things, SmartIoT 2023

作者： Wang, Yan Zheng, Liwei He, Jingjing Cui, Zhanqi Computer School Software Engineering Research Center Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9798350316575

The rapid growth of the Internet of Things (IoT) has led to widespread deployment of IoT systems in domains such as smart homes, healthcare, and transportation. However, IoT systems often operate under uncertainty, making it difficult to predict and control their behavior. In this paper, we propose an adaptive decision making approach for IoT systems in uncertain, dynamic environments. We present a framework with perception, decision and execution layers to handle uncertainty in IoT systems. The perception layer senses the environment and system state. The decision layer employs an optimized deep Q-network algorithm (Ad-DQN) specifically designed to handle uncertain environments, enabling it to make informed decisions based on learned experiences. The execution layer implements the actions. We demonstrate the framework on an intelligent air conditioning system as a case study of an IoT system operating under uncertainty. The Ad-DQN based decision layer adapts the air conditioning control policy to maximize comfort while minimizing energy usage. Experiments show our method outperforms traditional DQN method in uncertain environments. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Virtual Mock Interview Development 13

AI-Driven Virtual Mock Interview Development

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Mishra, Prabhat Kumar Arulappan, Arun Kumar Ra, In-Ho Thanga Mariappan, L. Gina Rose, G. Lee, Young-Seok School of Computer Science Engineering and Information Systems Vit University Vellore India School of Computer and Software Kunsan National University Gunsan Korea Republic of Anna University Department of Computer Technology Chennai India

ISBN: (纸本)9798350373332

The integration of Artificial Intelligence (AI) into educational technologies marks a significant shift in learning methodologies and operational dynamics within educational institutions. At the forefront is an AI-driven virtual mock interview platform designed to address the high Customer Acquisition Costs (CAC) in the edtech sector, especially for interview preparation services. This initiative harnesses a blend of AI technologies, including ADA 2 for creating context-aware embeddings and Machine Learning (ML), to transform the traditional mock interview process into a dynamic, cost-effective system. Central to the platform is its use of advanced Natural Language Processing (NLP) techniques and GPT-4 Large Language Model (LLM), automating the process of mock interviews and providing personalized feedback, ensuring a preparation journey that meets specific candidate needs and mirrors real interview scenarios. A key evaluation among 100 students from a cohort of 1800 demonstrated a 90% cost reduction for three mock interviews, reducing expenses from 3000 to just 300 per candidate. This cost efficiency significantly enhances access to quality interview preparation, improving student satisfaction and accessibility. Moreover, the platform provides valuable insights into student performance, setting a new standard in educational technology by offering an effective, personalized interview preparation experience. This project reflects a holistic approach to student development and the critical role of technology in addressing the evolving needs of learners. © 2024 IEEE.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

A Scheme Library-Based Ant Colony Optimization with 2-Opt Local Search for Dynamic Traveling Salesman Problem

引用

computer Modeling in engineering & sciences 2023年第5期135卷 1209-1228页

作者： Chuan Wang Ruoyu Zhu Yi Jiang Weili Liu Sang-Woon Jeon Lin Sun Hua Wang College of Software Henan Normal UniversityXinxiang453007China College of Computer and Information Engineering Henan Normal UniversityXinxiang453007China School of Computer Science and Engineering South China University of TechnologyGuangzhou510006China School of Computer Science Guangdong Polytechnic Normal UniversityGuangzhou510665China Department of Military Information Engineering Hanyang UniversityAnsan15588South Korea College of Engineering and Science Institute for Sustainable Industries and Liveable CitiesVictoria UniversityMelbourneVIC 8001Australia

The dynamic traveling salesman problem(DTSP)is significant in logistics distribution in real-world applications in smart cities,but it is uncertain and difficult to *** paper proposes a scheme library-based ant colony optimization(ACO)with a two-optimization(2-opt)strategy to solve the DTSP *** work is novel and contributes to three aspects:problemmodel,optimization framework,and ***,in the problem model,traditional DTSP models often consider the change of travel distance between two nodes over time,while this paper focuses on a special DTSP model in that the node locations change dynamically over ***,in the optimization framework,the ACO algorithm is carried out in an offline optimization and online application framework to efficiently reuse the historical information to help fast respond to the dynamic *** framework of offline optimization and online application is proposed due to the fact that the environmental change inDTSPis caused by the change of node location,and therefore the newenvironment is somehowsimilar to certain previous *** way,in the offline optimization,the solutions for possible environmental changes are optimized in advance,and are stored in a mode scheme *** the online application,when an environmental change is detected,the candidate solutions stored in the mode scheme library are reused via ACO to improve search efficiency and reduce computational ***,in the algorithm design,the ACO cooperates with the 2-opt strategy to enhance search *** evaluate the performance of ACO with 2-opt,we design two challenging DTSP cases with up to 200 and 1379 nodes and compare them with other ACO and genetic *** experimental results show that ACO with 2-opt can solve the DTSPs effectively.

关键词： Dynamic traveling salesman problem(DTSP) offline optimization and online application ant colony optimization(ACO) two-optimization(2-opt)strategy

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：