检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Shipei Ding, Yuandong Zhang, Chi Cao, Zhiguang Jin, Yan School of Computer Science Huazhong University of Science and Technology China School of Computing and Information Systems Singapore Management University Singapore Singapore

ISBN: (纸本)157735897X

This paper proposes a dual divide-and-optimize algorithm (DualOpt) for solving the large-scale traveling salesman problem (TSP). DualOpt combines two complementary strategies to improve both solution quality and computational efficiency. The first strategy is a grid-based divide-and-conquer procedure that partitions the TSP into smaller sub-problems, solving them in parallel and iteratively refining the solution by merging nodes and partial routes. The process continues until only one grid remains, yielding a high-quality initial solution. The second strategy involves a path-based divide-and-optimize procedure that further optimizes the solution by dividing it into sub-paths, optimizing each using a neural solver, and merging them back to progressively improve the overall solution. Extensive experiments conducted on two groups of TSP benchmark instances, including randomly generated instances with up to 100,000 nodes and real-world datasets from TSPLIB, demonstrate the effectiveness of DualOpt. The proposed DualOpt achieves highly competitive results compared to 10 state-of-the-art algorithms in the literature. In particular, DualOpt achieves an improvement gap up to 1.40% for the largest instance TSP100K with a remarkable 104x speed-up over the leading heuristic solver LKH3. Additionally, DualOpt demonstrates strong generalization on TSPLIB benchmarks, confirming its capability to tackle diverse real-world TSP applications. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

DeepUIR-Net: Underwater Image Restoration Using Residual-UNet with Optimized Efficient Channel Attention Network Integration 2nd

DeepUIR-Net: Underwater Image Restoration Using Residual-UNe...

引用

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Rayvanth, N. Amruth, S. Jaya Suryaa, E. Resmi, S. Singh, Rimjhim Padam Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031845420

The underwater image restoration task targets retaining the true colors of the underwater scenarios captured in the images by rectifying the distorted colors to critically analyze the ocean scenarios and resources. This area has been explored using different deep learning techniques such as Convolutional neural networks, Residual Networks, and various other models that made use of post-processing techniques for the final enhanced outputs. Hence, this study proposes a novel approach by fine-tuning the Residual-UNet architecture and combining it with an Efficient Channel Attention network in an optimized architecture for the task of underwater image restoration. Channel attention mechanisms have a great ability to reduce model complexity by making use of fewer parameters and increasing the performance of the model. One such mechanism, called Efficient Channel Attention, has been incorporated into the Residual-UNet model to extract features efficiently and obtain an enhanced underwater image that is true to the ground truth image by making use of the HardSwish activation function. The dataset used to train the Residual-UNet model is LSUI (Large Scale Underwater Images), a benchmark dataset consisting of various real underwater images. The proposed model obtained SSIM and PSNR values of 0.9998 and 74.851 dB respectively and outperformed other models by a margin of 4%. To determine the superiority of the Efficient Channel Attention network optimally integrated into the Residual-UNet model, various base models without this attention module have also been trained and evaluated. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Autonomous Landing of AirSim Simulated Quadcopter in Unreal Engine 15

Reinforcement Learning-Based Autonomous Landing of AirSim Si...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Paladugula, Pruthvi Don, S. Vemulapalli, Nehith Sai Prabhat, Guggilam Sai Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Dept. of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9798350370249

This paper presents a novel approach for landing an autonomous quadcopter using reinforcement learning (RL) in the AirSim simulation environment running on Unreal Engine. The complicated dynamics and unpredictability of quadcopter landing procedures make them difficult to execute and frequently reduce the efficacy of conventional control techniques. In order to overcome these difficulties, the suggested RL model interacts with an incredibly lifelike simulation to learn the best landing techniques, which faithfully replicates physical principles. Impressing with notable improvements in landing precision and resilience in many scenarios, this model holds potential to improve unmanned aerial vehicle operations. By utilizing reinforcement learning within a practical simulation setting, this study advances the creation of more effective and flexible autonomous landing systems for unmanned aerial vehicles (UAVs), potentially leading to benefits in practical uses. ©2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Towards characterizing bug fixes through dependency-level changes in Apache Java open source projects

引用

science China(Information sciences) 2022年第7期65卷 102-120页

作者： Di CUI Lingling FAN Sen CHEN Yuanfang CAI Qinghua ZHENG Yang LIU Ting LIU School of Computer Science and Technology Xi'an Jiaotong University College of Cyber Science Nankai University College of Intelligence and Computing Tianjin University Department of Computer Science Drexel University School of Computer Science and Engineering Nanyang Technological University School of Cyber Science and Engineering Xi'an Jiaotong University

The complexity and diversity of bug fixes require developers to understand bug fixes from multiple perspectives in addition to fine-grained code changes. The dependencies among files in a software system are an important dimension to inform software quality. Recent studies have revealed that most bug-prone files are always architecturally connected with dependencies, and as one of the best practices in the industry,changes in dependencies should be avoided or carefully made during bug fixing. Hence, in this paper, we take the first attempt to understand bug fixes from the dependencies perspective, which can complement existing code change perspectives. Based on this new perspective, we conducted a systematic and comprehensive study on bug fixes collected from 157 Apache open source projects, involving 140456 bug reports and182621 bug fixes in total. Our study results show that a relatively high proportion of bug fixes(30%) introduce dependency-level changes when fixing the corresponding 33% bugs. The bugs, whose fixes introduce dependency-level changes, have a strong correlation with high priority, large fixing churn, long fixing time,frequent bug reopening, and bug inducing. More importantly, patched files with dependency-level changes in their fixes, consume much more maintenance costs compared with those without these changes. We further summarized three representative patch patterns to explain the reasons for the increasing costs. Our study unveils useful findings based on qualitative and quantitative analysis and also provides new insights that might benefit existing bug prediction techniques. We release a large set of benchmarks and also implement a prototype tool to automatically detect dependency-level changes from bug fixes, which can warn developers and remind them to design a better fix.

关键词： empirical software engineering software maintenance software evolution software architecture software design

来源：评论

学校读者我要写书评

暂无评论

Fall Detection using LiDAR Sensor with PointNet++ 4

Fall Detection using LiDAR Sensor with PointNet++

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Ayyagari, Anish Sai Ahmed, Syed Ashfaq Venkatakrishnan, Shri Thangavel, Senthil Kumar Jeyakumar, G. Nalluri, Madhusudana Rao Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

In today's world, fall incidents pose a significant risk to the elderly, often resulting in severe consequences. Falls can cause damage to the body, especially in elders, where it can be *** is vital to detect falls in order to provide assistance. The simple solution is to install cameras in required areas, which would constantly monitor the area for any falls occurring, this poses a privacy issue in high-risk regions such as bathrooms and toilets. Keeping this in mind, this paper proposes the use of LiDAR sensors that do not cause any invasion of privacy for fall detection. The paper further uses the Pointnet++ to detect fall from the LiDAR scans. The model achieves an accuracy of 85.1 % and precision of 84.8 % on a 70-30 split of the dataset and an accuracy of 86.3 % and precision of 86.2 % on an 80-20 split of the dataset. © 2025 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Mining Evidence about Your Symptoms: Mitigating Availability Bias in Online Self-Diagnosis 25

Mining Evidence about Your Symptoms: Mitigating Availability...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI 2025

作者： Zhang, Junti Zhu, Zicheng Li, Jingshu Lee, Yi-Chieh Institute of Data Science National University of Singapore Singapore Singapore School of Computing National University of Singapore Singapore Singapore Computer Science School of Computing National University of Singapore Singapore Singapore Computer Science National University of Singapore Singapore Singapore

ISBN: (纸本)9798400713941

People frequently exposed to health information on social media tend to overestimate their symptoms during online self-diagnosis due to availability bias. This may lead to incorrect self-medication and place additional burdens on healthcare providers to correct patients' misconceptions. In this work, we conducted two mixed-method studies to identify design goals for mitigating availability bias in online self-diagnosis. We investigated factors that distort self-assessment of symptoms after exposure to social media. We found that availability bias is pronounced when social media content resonated with individuals, making them disregard their own evidences. To address this, we developed and evaluated three chatbot-based symptom checkers designed to foster evidence-based self-reflection for bias mitigation given their potential to encourage thoughtful responses. Results showed that chatbot-based symptom checkers with cognitive intervention strategies mitigated the impact of availability bias in online self-diagnosis. © 2025 Copyright held by the owner/author(s).

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Modality-Specific Interactive Attack for Vision-Language Pre-Training Models

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5663-5677页

作者： Zhang, Haiqi Tang, Hao Sun, Yanpeng He, Shengfeng Li, Zechao Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China The Hong Kong Polytechnic University Centre for Smart Health Hong Kong Singapore Management University School of Computing and Information Systems Singapore

Recent advances have heightened the interest in the adversarial transferability of Vision-Language Pre-training (VLP) models. However, most existing strategies constrained by two persistent limitations: suboptimal utilization of crossmodal interactive information, and inherent discrepancies across hierarchical textual representation. To address these challenges, we propose the Modality-Specific Interactive Attack (MSIAttack), a novel approach that integrates semantic-level image perturbations with embedding-level text perturbations, all while maintaining minimal inter-modal constraints. In our image attack methodology, we introduce Multi-modal Integrated Gradients (MIG) to guide perturbations toward the core semantics of images, enriched by their associated deeply text information. This technique enhances transferability by capturing consistent features across various models, thereby effectively misleading similar-model perception areas. Additionally, we employ a momentum iteration strategy in conjunction with MIG, which amalgamates current and historical gradients to expedite the perturbation updates. For text attacks, we streamline the perturbation process by operating exclusively at the embedding level. This reduces semantic gaps across hierarchical structures and significantly enhances the generalizability of adversarial text. Moreover, we delve deeper into how semantic perturbations with varying degrees of similarity affect the overall attack effectiveness. Our experimental results on image-text retrieval tasks using the multi-modal datasets Flickr30K and MSCOCO underscore the efficacy of MSI-Attack. Our method achieves superior performance, setting a new state-of-the-art benchmark, all without the need for additional mechanisms. 2005-2012 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Metaheuristic Optimisation for Lung Cancer Image Classification: Leveraging MOEA, PSO, and ACO Algorithms 3

Hybrid Metaheuristic Optimisation for Lung Cancer Image Clas...

引用

3rd International Conference on Machine Learning and Data Engineering, ICMLDE 2024

作者： Thambi, Sharanya Vanraj Ishvarya, G. Kammari, Kavya Sree Sahay, Apurvanand Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

In the critical domain of cancer classification, accurately identifying lung cancer scans as malignant or benign is paramount. This study proposes a novel approach that leverages a hybrid metaheuristic combination of algorithms. Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and the Knapsack Algorithm are utilized for feature selection. Subsequently, Convolutional Neural Networks (CNNs), recognised as state-of-the-art in medical image classification, are employed. Among the three algorithms, ACO performed the best. Following this, Multi-Objective Evolutionary Algorithms (MOEAs), Particle Swarm Optimisation, and the Simplex Algorithm were used, respectively, to fine-tune hyperparameters and enhance Classification accuracy. The best result was obtained by using ACO for feature selection and PSO for hyperparameter tuning, achieving an accuracy of 98.83%. The study conducts a comparative analysis of different algorithmic combinations to validate the proposed methodology's efficacy. This comparative analysis of optimisation algorithms significantly maximises the accuracy of lung cancer classification. © 2025 The Authors. Published by Elsevier B.V.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Predicting and Evaluating Anomaly Detection and Traffic Analysis on Software Defined Networks Using a Hybrid Machine Learning Approach 5th

Predicting and Evaluating Anomaly Detection and Traffic Anal...

引用

5th International Conference on computing and Network Communications, CoCoNet 2023

作者： Darshan, S. Radhika, N. Radhika, G. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9789819745395

In the rapidly evolving landscape of Software Defined Networks (SDNs), network security is of paramount importance. This research paper presents a comprehensive study on anomaly detection and traffic analysis in SDNs using machine learning algorithms. The study addresses a critical research gap by proposing an effective methodology for detecting network anomalies and analyzing traffic patterns. Leveraging a carefully selected dataset, we evaluate the performance of Logistic Regression, Decision Tree, Random Forest, Neural Networks and Hybrid Models. The results demonstrate the superior performance of the hybrid model built using Decision Tree and Neural Networks and the competitive accuracy of Neural Networks in SDN anomaly detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

QuickPark: Efficient Parking with Real-Time Pre-Booking 3

QuickPark: Efficient Parking with Real-Time Pre-Booking

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Dharshan, J.Y. Amarnath, Arjun R. Adithya, Gadamsetty Siva Belwal, Meena Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

The parking is one of the biggest problems. One of the emerging features of parking management is congestion in urban centres due to the increase in the number of vehicles on the road, which has added anxiety to drivers. These conventional or legacy parking systems fail to respond adequately to the increasing needs, especially in Smart City contexts. To this end, a Smart Parking Management System (SPMS) is developed with real-time data, incorporating a parking sensor, parking information, an easy-to-navigate parking lot, and favourable methods of payment accepted. This prototype optimises parking space, provides better convenience to drivers, and leads to the sustainability of such a structure in the urban area. The proposed SPMS promises to be a revolutionary and practical approach to addressing some of the modern parking management issues in delivering an efficient mobility regime. © 2025 IEEE.

关键词： Parking

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：