检索结果-内蒙古大学图书馆

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Sanghyun Cho Hye-Lynn Kim Jung-Hun Lee Hyuk-Chul Kwon Department of Information Convergence Engineering Pusan National University Busan South Korea R&D Center AI LAB HDC LABS Seoul South Korea Department of Artificial Intelligence Dong-Eui University Busan South Korea Department of Computer Science and Engineering Pusan National University Busan South Korea

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Previous works with auto-regressive pre-trained language model achieved state-of-art results in semantic parsing tasks. On the other hand, these models generate answers directly, it is difficult to get selected cells for generated answers and answers that require numerical reasoning. In this paper, we present a self-training framework to generate logical forms with weakly supervised question answering. Self-training framework composed of the training procedure and pseudo label correction procedure. In the training procedure, we train models to generate column and row positions of answer cells with supervised training data whose tagged answer cells are a subset of the input table cells. In the pseudo label correction procedure, we correct the tagged dataset for training the model. Furthermore, to enhance the correcting accuracy, we employed reinforcement learning, incorporating a reward function that yields a greater reward as the computed correct answer approaches the benchmark correct answer. Ultimately, we observed an improvement in accuracy from 47.1 to 54.06, a 6.89 increase, using the tapex-base model. Furthermore, we managed to outperform the existing performance, achieving 64.17, using the OmniTab model. Thus, our proposed method, SWING, a self-learning table parsing framework, has shown improved performance in numerical reasoning cases, and can predict rationale cells that allow auto-regressive PLM to compute answers without the need for logical form.

关键词： Training Computational modeling Semantics Training data Reinforcement learning Tagging Question answering (information retrieval) Cognition Data models Numerical models

来源：评论

学校读者我要写书评

暂无评论

Optimizing BIM drawing element placement through reinforcement learning

引用

Automation in Construction 2025年 175卷

作者： Kim, Yije Park, Jeongjun Oh, Jiyong Bum, Junghyun Chin, Sangyoon Department of Convergence Engineering for Future City Sungkyunkwan University Suwon16419 Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Artificial Intelligence Sungkyunkwan University Suwon16419 Korea Republic of Sungkyun AI Research Institute Sungkyunkwan University Suwon Korea Republic of School of Civil Architectural Engineering & Landscape Architecture Sungkyunkwan University Suwon16419 Korea Republic of

Building information modeling (BIM) enhances communication in the architecture, engineering, and construction industry and automates drawing generation. However, optimizing the placement of drawing elements remains a challenge. This paper proposes a framework using proximal policy optimization to improve BIM drawing element placement, focusing on floor plan-type drawings in the construction documentation phase. Deep reinforcement learning ensures stable performance in high-dimensional, sparse-data environments. Experiments on a dataset of 150 drawings showed that the interference ratio among drawing elements converged to zero within 0.05 s to 5 min, improving readability. Compared with conventional BIM processes, the proposed framework reduced "element position adjustment" time and commands by 93.9 % and 94.3 %, respectively, leading to an overall reduction of 25 % in work time and 17.9 % in commands. These results validate the framework's effectiveness in improving productivity and reducing manual effort. It enhances readability, minimizes human errors, and allows designers to focus on essential tasks. © 2025 Elsevier B.V.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Techno-economic optimization and environmental analysis of a solar-powered Electric Vehicles (EVs) charger system for a greener transportation ecosystem

引用

Energy Reports 2025年 13卷 5803-5814页

作者： Mohammed H. Alsharif Faisal Alsaif Manish Kumar Singla Saibal Manna Mun-Kyeom Kim Department of AI Convergence Electronic Engineering Sejong University 209 Neungdong-ro Gwangjin-gu Seoul 05006 South Korea Department of Electrical Engineering College of Engineering King Saud University Riyadh 11421 Saudi Arabia Department of Bioscience Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India Applied Science Research Center Applied Science Private University Amman 11931 Jordan Department of Electrical and Computer Engineering ABES Engineering College Ghaziabad UP India School of Energy System Engineering Chung-Ang University 84 Heukseok-ro Dongjak-gu Seoul 06974 South Korea

As the electric vehicle (EV) sector continues to grow, the environmental benefits of EVs increasingly depend on the energy sources powering charging stations, which are often supplied by the conventional electrical grid. Therefore, the adoption of sustainable charging solutions is becoming essential. This study investigates the integration of solar energy into EV charging infrastructure as a strategy to reduce greenhouse gas (GHG) emissions, aligning with Sustainable Development Goals (SDGs) 7 and 13. Focused on a 7 kW Level 2 charger, the analysis addresses optimal solar system sizing, energy output, economic feasibility, environmental impact, and sensitivity considerations. The proposed system including a 34 kW photovoltaic (PV) array, a 192-unit battery storage system, and an 8 kW inverter delivers consistent performance under real-world conditions, factoring in system losses, seasonal solar variations, and battery efficiency. The PV system generates 62,294 kWh annually, meeting an EV demand of 38,325 kWh/year and yielding a surplus of 31.54 %. The battery storage provides 66.4 hours of autonomy, ensuring energy availability during low solar generation periods. Economically, the system’s net present cost (NPC) is $192,420, with an initial capital cost of $94,800, 60.76 % of which is attributed to battery investments. Battery replacements constitute 97.34 % of total replacement costs, while operation and maintenance (O&M) expenses total $38,567. A salvage value of $12,638 helps reduces overall lifecycle costs. Environmentally, the solar-powered system achieves an 87.5 % reduction in GHG emissions, emitting only 1917 kg CO 2 /year compared to 15,330 kg CO 2 /year for grid-based charging. These findings demonstrate that solar-powered EV charging offers both a cost-effective and environmentally sustainable solution, contributing meaningfully to global sustainability efforts.

关键词： EVs Electric vehicle Eco-friendly transportation SDGs Energy reliability Economic feasibility Sustainable energy GHG EVCS Solar energy PV Carbon emissions Climate change

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Smart Dynamic Feature Analysis based Approach by utilizing deep learning to improve the Breast Cancer Detection

引用

IEEE Access 2025年 13卷 81643-81665页

作者： Shim, Seong-O Hussain, Lal Alsolami, Eesa Alkinani, Monagi H. University of Jeddah College of Computer Science and Engineering Department of Computer and Network Engineering Jeddah Saudi Arabia University of Azad Jammu and Kashmir Department of Computer Science and Information Technology King Abdullah Campus Chatter Kalas Muzaffarabad 13100 Pakistan University of Azad Jammu and Kashmir Department of Computer Science Neelum Campus Neelum Campus Athmuqam 13230 Pakistan University of Jeddah College of Computer Science and Engineering Department of Cybersecurity Jeddah Saudi Arabia University of Jeddah College of Computer Science and Engineering Department of Computer Science and AI Jeddah Saudi Arabia

Breast cancer remains one of the important global health concerns with high rates of mortality, highlighting the significance of more sophisticated diagnostic methods. Conventional methods, generally comprised of costly imaging and invasive biopsies, are of high burdens. Motivated by the limitations, the present study comes up with an innovative automated solution for the identification of breast cancer using deep learning analysis of mammograms. Moving away from the traditional approaches with inherent pre-processing and feature extraction constraints, this research focuses on a two-pronged improvement strategy: improved mammogram quality and highly optimized deep learning architecture. Specifically, we present a new Optimized InceptionResNetV2 model significantly optimized through the thoughtful addition of large data augmentation to increase robustness, LeakyReLU activation to facilitate gradient flow and accelerate learning, and MeanDropout regularization to mitigate overfitting and improve generalization. The model was also trained using Quantization Aware Training (QAT) to enable efficient deployment on low-resource devices without significant performance degradation. The performance on our proposed approach for the massive mammogram dataset reflects an evident improvement in detection performance over traditional techniques. Our InceptionResNetV2 optimized achieved state-of-the-art accuracy with outstanding measures of 98.06% sensitivity, 97.05%, positive predictive value (PPV) and specificity of 99.60%, negative predictive value (NPV) of 86.83%, 97.94% accuracy, F1-score of 96.90%, Matthews correlation coefficient (MCC) of 90.67%, and AUC of 0.9939. The benefits of proposed system are that it can deliver a more efficient, precise, and possibly cost-effective diagnostic tool for breast cancer. Through synergistic integration of architectural optimization, sophisticated regularization methods, and deployment-aware training, our proposed system enables earlier

关键词： Breast Cancer Dynamics Feature engineering Optimized Deep Learning Post-Training Quantization Smart Model

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

arXiv

引用

arXiv 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan The Beijing Key Laboratory of Network System Architecture and Convergence The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing China Singapore The Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Department of Computer Science North Carolina State University RaleighNC27695 United States The Beijing Key Laboratory of Network System Architecture and Convergence China The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025, CC BY-NC-SA.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Multilingual Table Question Answering for Low-Resource Languages via Selective Question Translation and Cross-Lingual Adaptation

Multilingual Table Question Answering for Low-Resource Langu...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Sanghyun Cho Minho Kim Hye-Lynn Kim Jung-Hun Lee Hyuk-Chul Kwon Department of Information Convergence Engineering Pusan National University Busan South Korea Division of Artificial Intelligence Engineering Korea Maritime and Ocean University Busan South Korea R&D Center AI LAB HDC LABS Seoul South Korea Department of Artificial Intelligence Dong-Eui University Busan South Korea Department of Computer Science and Engineering Pusan National University Busan South Korea

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Table question answering datasets have been released in various table sources and diverse tasks. However, most of these table question answering datasets are constructed in resource-rich languages like English. For low-resource languages, it is necessary to create new datasets or translate existing ones to train models on table question answering tasks. This process requires substantial costs and manpower. Table data, unlike natural text, is structured in a way that is less affected by word order and language-specific characteristics. In this paper, we propose a method to minimize the costs associated with translating and applying new table question answering datasets. By leveraging the characteristics of table data, we suggest translating only the question data of the question answering table datasets into multiple languages. To minimize the performance degradation caused by using the native table data of the original dataset and not directly utilizing the table data in the target language, we applied adaptation methods using contrastive learning and adversarial training. To enhance the reasoning capabilities required for table question answering without diminishing performance in languages other than the one used for pre-training, we further pre-trained a RoBERTa-based multilingual encoder on table data using SQL data. The proposed cross-lingual adaptation demonstrated performance improvements in most of the languages evaluated. Additionally, the pre-training using SQL data significantly improved performance across all languages, even though the pre-training table data consisted of English data.

关键词： Training Degradation Structured Query Language Adaptation models Translation Costs Contrastive learning Question answering (information retrieval) Cognition Multilingual

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic- like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. Firstly, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic- like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. The source code will be made publicly available. ©1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

The Distributed Intelligent Collaboration to UAV-Assisted VEC: Joint Position Optimization and Task Scheduling

引用

IEEE Internet of Things Journal 2025年

作者： Yi, Meng Lee, Vincent C.S. Yang, Peng Li, Peisong Zhang, Yifan Wei, Wei Gao, Honghao Southeast University School of Computer Science and Engineering Nanjing211189 China Monash University Faculty of IT Department of DS and AI ClaytonVIC3800 Australia Southeast University School of Computer Science and Engineering the Key Laboratory of Computer Network and Information Integration Ministry of Education Nanjing211189 China Xidian University Hangzhou Institute of Technology Hangzhou311200 China Southeast University-Monash University Joint Graduate School Suzhou215123 China Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Shanghai University School of Computer Engineering and Science Shanghai200444 China

Deploying Unmanned Aerial Vehicles (UAVs) as aerial base stations enhances the coverage and performance of communication networks in Vehicular Edge Computing (VEC) scenarios. However, due to the limited communication range and energy capacity of UAVs, they cannot continuously cover entire areas or sustain long flights. Therefore, achieving full communication coverage of a target area with a minimal number of UAVs and efficient task offloading remains a significant challenge. To address this problem, the UAV-assisted Two-stage Intelligent Collaboration (UTIC) method is proposed in this paper to tackle the joint position optimization and task scheduling issue. Firstly, a UAV-assisted Two-stage Task Scheduling (UTTS) system model is designed to optimize the allocation process. Secondly, an Enhanced Particle Swarm Optimization (E-PSO) algorithm is designed to determine the optimal positions of UAVs, ensuring complete coverage of all mobile vehicles (MVs) with the minimum number of UAVs. Thirdly, Deep Deterministic Policy Gradient (DDPG) method is employed to find the optimal scheduling decisions for MVs, considering energy consumption, delay, and task priorities. Simulation results demonstrate that the proposed UTIC method can achieve nearly 20% reduction in UAV deployment and outperform three other classical reinforcement learning (RL) algorithms in terms of reducing system cost. © 2025 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

ReSup: Reliable Label Noise Suppression for Facial Expression Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Zhang, Xiang Lu, Yan Yan, Huan Huang, Jinyang Gu, Yu Ji, Yusheng Liu, Zhi Liu, Bin University of Science and Technology of China School of Cyber Science and Technology Hefei230026 China Hefei University of Technology School of Computer and Information Hefei230601 China AI Lab Shanghai200030 China Guizhou Normal University School of Computer and Information Guiyang230601 China National Institute of Informatics Tokyo101-8430 Japan The University of Electro-Communications Department of Computer and Network Engineering Tokyo1828585 Japan

Because of the ambiguous and subjective property of the facial expression, the label noise is widely existing in the FER dataset. For this problem, in the training phase, current methods often directly predict whether the label is noised or not, aiming to reduce the contribution of the noised data. However, we argue that this kind of method suffers from the low reliability of such noise data decision operation. It makes that some mistakenly abounded clean data are not utilized sufficiently and some mistakenly kept noised data disturbing the model learning. In this paper, we propose a more reliable noise-label suppression method called ReSup. First, instead of directly predicting noised or not, ReSup makes the noise data decision by modeling the distribution of noise and clean labels simultaneously according to the disagreement between the prediction and the target. Specifically, to achieve optimal distribution modeling, ReSup models the similarity distribution of all samples. To further enhance the reliability of our noise decision results, ReSup uses two networks to jointly achieve noise suppression. Specifically, ReSup utilize the property that two networks are less likely to make the same mistakes, making two networks swap decisions and tending to trust decisions with high agreement. Extensive experiments on popular datasets shows the effectiveness of ReSup. © 2010-2012 IEEE.

关键词： Affective computing facial expression label noise label noise modeling label noise suppression

来源：评论

学校读者我要写书评

暂无评论

Complex Problems Solution as a Service Based on Predictive Optimization and Tasks Orchestration in Smart Cities

引用

computers, Materials & Continua 2021年第10期69卷 1271-1288页

作者： Shabir Ahmad Jehad Ali Faisal Jamil Taeg Keun Whangbo DoHyeun Kim Department of IT Convergence Engineering Gachon UniversitySujeong-GuSeongnam-SiGyeonggi-Do461-701Korea Department of Computer Engineering and Department of AI Convergence NetworkAjou UniversitySuwonKorea Computer Engineering Department Jeju National UniversityJeju63243Korea

Smart cities have different contradicting goals having no apparent *** selection of the appropriate solution,which is considered the best compromise among the candidates,is known as complex *** city administrators face different problems of complex nature,such as optimal energy trading in microgrids and optimal comfort index in smart homes,to mention a *** paper proposes a novel architecture to offer complex problem solutions as a service(CPSaaS)based on predictive model optimization and optimal task orchestration to offer solutions to different problems in a smart *** model optimization uses a machine learning module and optimization objective to compute the given problem’s *** task orchestration module helps decompose the complex problem in small tasks and deploy them on real-world physical sensors and *** proposed architecture is hierarchical and modular,making it robust against faults and easy to *** proposed architecture’s evaluation results highlight its strengths in fault tolerance,accuracy,and processing speed.

关键词： Internet of things complex problem solving task modeling embedded IoT systems predictive optimization artificial cognition task orchestration

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：