检索结果-内蒙古大学图书馆

Real-Time Road Damage Detection Using an Optimized YOLOv9s-Fusion in IoT Infrastructure

IEEE Internet of Things Journal 2025年第11期12卷 17649-17660页

作者： Waseem Khan, Muhammad Obaidat, Mohammad S. Mahmood, Khalid Sadoun, Balqies Sanaullah Badar, Hafiz Muhammad Gao, Wu Center for Bio-inspired System-on-Chip School of Computer Science Northwestern Polytechnical University Xi’an China Sahiwal Campus Pakistan The King Abdullah II School of Information Technology The University of Jordan Amman11942 Jordan The School of Communication and Computing Engineering University of Science and Technology Beijing Beijing100083 China The Amity School of Engineering and Technology Amity University Uttar Pradesh Noida201301 India The Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliu Yunlin64002 Taiwan School of Computer and Information Engineering Henan University Kaifeng475001 China The College of Engineering Al-Balqa’ Applied University Al-Salt19117 Jordan

In IoT-enabled smart infrastructure, accurate and real-time road damage detection is crucial for enhancing road safety and optimizing maintenance processes. However, detecting road damage in complex and dynamic environments presents significant challenges, such as varying lighting conditions, diverse damage types, and the need for fast processing to enable real-time decision-making. This study introduces an advanced approach utilizing the YOLOv9s-Fusion model to overcome these challenges. Leveraging the RDD2022 dataset, which comprises 1,976 annotated images of road damage from China, we employ comprehensive data preprocessing to create optimal conditions for model training. The YOLOv9s-Fusion model integrates innovative features, including a Transformer-based auxiliary module and enhanced feature extraction layers, specifically designed to detect fine-grained damage patterns accurately. Experimental results demonstrate that the model outperforms existing approaches, achieving notable improvements in mean Average Precision (mAP) and F1-score. Ablation studies further validate the impact of our modifications, highlighting the model’s robustness in real-time detection across diverse conditions. This IoT-centric approach sets a new standard for autonomous road damage detection, significantly advancing vehicle navigation and smart infrastructure management capabilities. © 2014 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A Design Study on Integrated Complex Coefficient Filters with Peripheral Circuits for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, information and Systems 2025年第1期145卷 16-24页

作者： Shouno, Kazuhiro Sato, Lina Fukagawa, Kanta Tanimoto, Hiroshi Muto, Cosy Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan

This paper proposes a measurement technique for an integrated complex filter. The proposed method is based on two measurement methods with integrated circuitry for calibration. It is accomplished by applying square waves to an FUT (Filter Under Test) instead of sinusoidal waves or by superposing transfer characteristics obtained by applying a single sinusoidal wave to an FUT. In both of the above methods, the output signal connected to the external measurement equipment via a 50 Ω coaxial cable and so on. In this case, the output signal of the FUT should be amplified by internal or external amplifiers, which degrades the response. However, it is cancelled out by the proposed calibration circuitry with some analog switches. In addition to the above, for the RC polyphase filter, the source resistance and the load capacitance degrade the measurement results and their effect is discussed. The validity of the proposal is confirmed through computer simulation for a third-order RCPF whose passband is 8–40 MHz fabricated by Phenitec 0.6 µm CMOS process. It is shown that the measurement error is −1.10 dB for the square-wave method and −1.00 dB and −0.43 degrees for the superposition method at 40 MHz. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

Protecting Your Attention during Distributed Graph Learning: Efficient Privacy-Preserving Federated Graph Attention Network

引用

IEEE Transactions on information Forensics and Security 2025年 20卷 1949-1964页

作者： Zhou, Jinhao Wu, Jun Ni, Jianbing Wang, Yuntao Pan, Yanghe Su, Zhou Waseda University Graduate School of Information Production and Systems Fukuoka808-0135 Japan Queen's University Department of Electrical and Computer Engineering KingstonONK7L 3N6 Canada Xi'An Jiaotong University School of Cyber Science and Engineering Xi'an710049 China

Federated graph attention networks (FGATs) are gaining prominence for enabling collaborative and privacy-preserving graph model training. The attention mechanisms in FGATs enhance the focus on crucial graph features for improved graph representation learning while maintaining data decentralization. However, these mechanisms inherently process sensitive information, which is vulnerable to privacy threats like graph reconstruction and attribute inference. Additionally, their role in assigning varying and changing importance to nodes challenges traditional privacy methods to balance privacy and utility across varied node sensitivities effectively. Our study fills this gap by proposing an efficient privacy-preserving FGAT (PFGAT). We present an attention-based dynamic differential privacy (DP) approach via an improved multiplication triplet (IMT). Specifically, we first propose an IMT mechanism that leverages a reusable triplet generation method to efficiently and securely compute the attention mechanism. Second, we employ an attention-based privacy budget that dynamically adjusts privacy levels according to node data significance, optimizing the privacy-utility trade-off. Third, the proposed hybrid neighbor aggregation algorithm tailors DP mechanisms according to the unique characteristics of neighbor nodes, thereby mitigating the adverse impact of DP on graph attention network (GAT) utility. Extensive experiments on benchmarking datasets confirm that PFGAT maintains high efficiency and ensures robust privacy protection against potential threats. © IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Bridging Gender Disparities in Mental Health: A Bilingual Large Language Model for Multilingual Therapeutic Chatbots 22

Bridging Gender Disparities in Mental Health: A Bilingual La...

引用

22nd International Learning and Technology Conference, L and T 2025

作者： Elboardy, Ahmed Tamer Mohamed, Ziad Khoriba, Ghada Arafa, Tamer Rashed, Essam A. Nile University School of Information Technology and Computer Science Giza Egypt University of Hyogo Graduate School of Information Science Kobe650-0047 Japan University of Hyogo Advanced Medical Engineering Research Institute Himeji670-0836 Japan

ISBN: (纸本)9798331532215

Significant gender disparities and a general lack of support systems compound the state of mental health in developing countries. Women, in particular, face unique challenges due to societal norms and expectations that often restrict their access to mental health services. Additionally, the cultural stigma associated with mental health issues affects both men and women but can be particularly debilitating for women who may be less likely to seek help or disclose their struggles. This study explores the application of Jais-13B, a pre-existing bilingual Large Language Model (LLM) proficient in English and Arabic, tailored to address mental health inquiries. We employed a rich dataset encompassing both languages, essential for fine-tuning and enhancing Jais-13B's responsiveness and empathetic engagement in mental health contexts. The optimization focused on improving the model's ability to deliver accurate and contextually aware responses, which is crucial for effective mental health support. Performance evaluation using the cross-entropy loss function demonstrated that Jais-13B achieved an accuracy of 70.58%, indicating its capability to produce relevant and precise answers to mental health questions. These results showcase Jais-13B's potential to enhance digital mental health interventions significantly, providing accessible care solutions across diverse linguistic landscapes. This study reaffirms the effectiveness of bilingual LLMs in mental health applications and provides insights into their practical implementation, setting a foundational benchmark for future research in multilingual therapeutic chatbots. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning Approach for An Analysis of Real-estate Prices and Transactions

引用

IEEE Access 2025年 13卷 89248-89265页

作者： Yang, Cheng-Hong Lee, Borcy Lin, Yu-Da Tainan University of Technology Department of Information Management Tainan Taiwan National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung Taiwan Kaohsiung Medical University Ph.D. Program in Biomedical Engineering Kaohsiung Taiwan Kaohsiung Medical University School of Dentistry Kaohsiung Taiwan Kaohsiung Medical University Drug Development and Value Creation Research Center Kaohsiung Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu Taiwan

Research on the study of houses, condominiums and buildings in Taiwan’s metropolitan areas continues to be an important area of research. In real estate forecasting and analysis, methods such as statistical analysis and questionnaire data collection are widely used. However, when multidimensional data is considered, these methods are time-consuming and inadequate. This study aimed to build a real estate forecasting model that can adapt to a changing environment. Data were collected from public government databases, the collected data were standardized for accurate clustering, an appropriate data clustering algorithm was applied to the standardized data, and cross-statistical analysis was performed to verify the adopted algorithm. We used a deep learning based on autoencoder algorithm to increase the accuracy of the clustering analysis. A double-bottom map particle swarm optimization (DBM-PSO) clustering algorithm was then used to determine the optimal clustering solution. Cluster analysis and deep learning were conducted on data collected from public websites to understand the factors that led to the sustained increase in housing prices in Taiwan over the past decade. The results of this study indicate that three key factors—the number of real estate transactions, the average unit price of real estate transactions, and the building material and construction index—significantly affected real estate prices in Taiwan. Our results could help researchers and governments to focus on specific aspects of real estate development without being influenced by other related factors. In addition, the relationships between real estate trends and the aforementioned three key factors were determined to obtain valuable information that can enable the Taiwanese government to regulate the property market and prevent excessive growth. The framework proposed in this paper allows researchers and governments to focus on specific aspects of real estate development without being influenced b

关键词： Houses

来源：评论

学校读者我要写书评

暂无评论

Identifying english proficiency by frontal theta activity during english learning

引用

Discover Education 2025年第1期4卷 1-7页

作者： Emsawas, Taweesak Kimura, Tsukasa Ogura, Shintaro Morita, Hironori Abdullajon, Ergashov Grundlehner, Bernard Ogura, Mototsugu Numao, Masayuki Graduate School of Information Science and Technology Osaka University Osaka Japan SANKEN (The Institute of Scientific and Industrial Research) Osaka University Osaka Japan Graduate School of Human Sciences Osaka University Osaka Japan Shinhodo Inc Tokyo Japan imec the Netherlands/Holst Centre Eindhoven Netherlands Faculty of Engineering Department of Information and Computer Science Kyoto Tachibana University Kyoto Japan

Second-language (L2) knowledge of English is an essential communication tool in the contemporary era of globalization in many research and business fields. Among the important tasks in English education is the measurement of student proficiency. While various tests purport to measure proficiency in learning English, repeated preparation and implementation of tests remain major costs in providing English education. We propose that measurement with an electroencephalogram (EEG) might be used for measuring proficiency in L2 learning of English without the repeated preparation and implementation of English tests. In this study, we proposed the use of an EEG as an index of the frontal theta band activity involved in concentration with the use of English materials without the need for the repeated preparation and implementation of English tests. Our experiments recorded the EEG signals of 52 participants, divided into two groups of those with beginner and advanced knowledge of English. All participants were asked to attend three sessions: before, during, and after the English lesson and the frontal theta band activities were analyzed as index of concentration for these lessons. The results showed that the frontal theta band activity for advanced students during the English lesson was larger than that for beginner students. Frontal brain activity reflects a common computation recognizing the need for cognitive control, such as concentration on L2 learning. Without dependence on existing tests, this study proposes a method to measure L2 proficiency more quickly than the methods used in previous neuroscience studies. © The Author(s) 2025.

关键词： Concentration Electroencephalogram (EEG) Second-language acquisition Second-language education Time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

A General Framework for Clustering and Distribution Matching with Bandit Feedback

引用

IEEE Transactions on information Theory 2025年第3期71卷 2116-2139页

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y. F. Scarlett, Jonathan CNRS@CREATE DesCartes Program CREATE Tower 138602 Singapore National University of Singapore Department of Computer Science Queenstown119077 Singapore National University of Singapore School of Computing Department of Information Systems and Analytics Queenstown119077 Singapore National University of Singapore Department of Mathematics Department of Electrical and Computer Engineering Queenstown119077 Singapore Institute of Data Science National University of Singapore Department of Computer Science The Department of Mathematics Queenstown119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank-Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ vanishes. © 1963-2012 IEEE.

关键词： Random variables

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Prediction of Corrosion Inhibition Efficiency of Expired Pharmaceuticals: Model Development and Application

引用

Journal of Bio- and Tribo-Corrosion 2025年第1期11卷 1-12页

作者： Putra, Dzaki Asari Surya Ardyansyah, Nibras Bahy Putranto, Nicholaus Verdhy Trisnapradika, Gustina Alfa Akrom, Muhamad Rustad, Supriadi Dipojono, Hermawan Kresno Maezono, Ryo Faculty of Computer Science Study Program in Informatics Engineering Universitas Dian Nuswantoro Semarang50131 Indonesia Research Center for Materials Informatics Faculty of Computer Science Universitas Dian Nuswantoro Semarang50131 Indonesia Quantum and Nano Technologies Research Group Faculty of Industrial Technology Institut Teknologi Bandung Bandung40132 Indonesia School of Information Science Japan Advanced Institute of Science and Technology Ishikawa923-1292 Japan

Corrosion poses a significant challenge in industries due to material degradation and high maintenance costs, making effective inhibitors essential. Recent studies suggest expired pharmaceuticals as alternative corrosion inhibitors, but identifying the most efficient compounds can be time-consuming. This study applies machine learning models, particularly Gradient Boosting Regressor (GBR), to predict corrosion inhibition efficiency (CIE). The developed model is integrated into a web-based application, enabling real-time, accurate CIE predictions. Results show GBR as the more precise model for predicting CIE, with low error rates. The streamlit-based web application offers a user-friendly platform, facilitating quick identification of suitable inhibitors. It is flexible, supporting analysis beyond corrosion inhibitors, and significantly enhances the efficiency of the evaluation process. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Strain accumulation in the Mentawai Forearc Sliver,Indonesia,inferred from continuous GNSS-derived strain rate

引用

Geodesy and Geodynamics 2025年第1期16卷 1-6页

作者： Leni Sophia Heliani Cecep Pratama Adi Wibowo David Prambudi Sahara Susilo Susilo Sidik Tri Wibowo Ayu Nur Safii Oktadi Prayoga Ajat Sudrajat Mizan Bustanul Fuady Bisri Evi Dwi Kurniasari Sheilla Evelinda Nicholas Genta Setiawan Gunawan Department of Geodetic Engineering Universitas Gadjah MadaYogyakartaIndonesia Department of Computer Science Universitas DiponegoroSemarangIndonesia Global Geophysics Research Group Institut Teknologi BandungBandungIndonesia Research Center for Geological Disaster National Research and Innovation AgencyBandungIndonesia Geospatial Information Agency CibinongIndonesia Meteorological Climatologicaland Geophysical AgencyJakartaIndonesia Graduate School of International Cooperation Studies Kobe UniversityJapan Graduate School of Geodetic Engineering Universitas Gadjah MadaYogyakartaIndonesia

The Mentawai Forearc Sliver(MFS)is characterized by oblique deformation formed as slip partitioned between normal and parallel trench plate *** surge of great earthquakes from 2004 to2012 along the adjacent Sunda trench left a large unbroken segment known as the Mentawai Seismic ***,we adopted continuous Global Navigation Satellite System(GNSS)observation data to identify the present regional crustal deformation using geodetic strain *** principal strain rate,dilatation rate,and maximum shear strain rate are about 0.13 microstrain/yr,0.2 microstrain/yr,and 0.1 microstrain/yr,respectively,with the range of its uncertainties between 0.01 and 0.04 microstrain/*** dilatation and maximum shear strain rates reveal the spatial coverage of strike-slip duplex and backthrust tectonics along the Mentawai Forearc Sliver.

关键词： Mentawai Forearc Dilatation Shear Geodetic

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Fairness Enhancement in Multi-Cell Vehicular VLC System With Optical IRS: A Cooperative Transmission Approach

引用

IEEE Internet of Things Journal 2025年第11期12卷 16931-16946页

作者： An, Nan Yang, Fang Liu, Chang Cheng, Ling Song, Jian Han, Zhu Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Beijing100084 China Center of National Railway Intelligent Transportation System Engineering and Technology Beijing100081 China China Academy of Railway Sciences Corporation Limited Signal and Communication Research Institute Beijing100081 China University of the Witwatersrand School of Electrical and Information Engineering Johannesburg2050 South Africa Tsinghua University Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Beijing100084 China Tsinghua University Shenzhen International Graduate School Shenzhen518055 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

In multi-cell downlink vehicular visible light communication (VLC) systems, vehicles at a cell edge experience lower achievable data rates compared with those at a cell center, primarily due to the weaker channel gain and inter-cell interference, leading to unfairness among vehicles. In this paper, a cooperative transmission approach is proposed for a vehicular VLC system with optical intelligent reflecting surface (OIRS) to enhance the max-min fairness of the system by leveraging the additional OIRS-reflected channels and the interference-mitigating capabilities of cooperative transmission. To this end, the system model is established, followed by the formulation of a resource allocation problem aiming at enhancing max-min fairness, in which the minimum achievable data rate among vehicles is optimized. Then, an effective resource algorithm is proposed, transforming the original problem into an equivalent form and subsequently decomposing it into three subproblems, focusing on OIRS assignment, subchannel allocation, and power adjustment, respectively. By employing a block coordinate descent algorithm, the three subproblems are solved iteratively until convergence. In addition, simulation results confirm the improvement in max-min fairness brought by OIRS and the proposed cooperative transmission approach. Moreover, compared with various baselines, the proposed resource allocation algorithm significantly enhances in the max-min fairness for the vehicular VLC system, crucial for this application. © 2014 IEEE.

关键词： Resource allocation

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：