检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lei, Tao Xu, Yetong Ning, Hailong Lv, Zhiyong Min, Chongdan Jin, Yaochu Nandi, Asoke K. The Shaanxi Joint Laboratory of Artificial Intelligence Shaanxi University of Science and Technology Xi’an710021 China The School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China The School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China The Faculty of Technology Bielefeld University Bielefeld33619 Germany The Department of Electronic and Electrical Engineering Brunel University London Uxbridge MiddlesexUB8 3PH United Kingdom Xi’an Jiaotong University Xi’an710049 China

Popular Transformer networks have been successfully applied to remote sensing (RS) image change detection (CD) identifications and achieve better results than most convolutional neural networks (CNNs), but they still suffer from two main problems. First, the computational complexity of the Transformer grows quadratically with the increase of image spatial resolution, which is unfavorable to very high-resolution (VHR) RS images. Second, these popular Transformer networks tend to ignore the importance of fine-grained features, which results in poor edge integrity and internal tightness for largely changed objects and leads to the loss of small changed objects. To address the above issues, this Letter proposes a Lightweight Structure-aware Transformer (LSAT) network for RS image CD. The proposed LSAT has two advantages. First, a Cross-dimension Interactive Self-attention (CISA) module with linear complexity is designed to replace the vanilla self-attention in visual Transformer, which effectively reduces the computational complexity while improving the feature representation ability of the proposed LSAT. Second, a Structure-aware Enhancement Module (SAEM) is designed to enhance difference features and edge detail information, which can achieve double enhancement by difference refinement and detail aggregation so as to obtain fine-grained features of bi-temporal RS images. Experimental results show that the proposed LSAT achieves significant improvement in detection accuracy and offers a better tradeoff between accuracy and computational costs than most state-of-the-art CD methods for VHR RS images. Copyright © 2023, The Authors. All rights reserved.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

AI - Enhanced Hospital Language Interpretation Services using Cloud Computing for Effective Communication

AI - Enhanced Hospital Language Interpretation Services usin...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Sree Southry S N. Mohankumar Thanalakshmi S R. Aiyshwariva Devi C. Srinivasan T. R. GaneshBabu Department of Electronics and Communication Engineering Sona College of Technology Salem Tamil Nadu India Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India Department of Management Studies Gojan School of Business and Technology Redhills Chennai Tamil Nadu India Artificial Intelligence and Data Science R.M.K. College of Engineering and Technology Puduvoyal Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Electronics and Communication Muthayammal Engineering College (Autonomous) Namakkal Tamil Nadu India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

Impaired communication between patients and healthcare professionals due to language problems may hurt the quality of treatment and patient outcomes. The objective is to develop an AI -driven., cloud-based NLP system for real-time., precise language interpretation., enabling seamless interaction in multilingual health care environments. The solution to this problem is a cloud-based language interpretation service for hospitals powered by artificial intelligence (AI). As a real-time translation service., it employs advanced natural language processing (NLP) models trained in situations and vocabulary particular to healthcare. This technology provides quick implementation., smooth interaction with current healthcare systems., and ongoing development via machine learning by using the scalability and flexibility of cloud computing. Both patients and medical staff may benefit from the intuitive interface's support for text-based and speech-based communication. Security measures are put in place to comply with regulations and safeguard patient confidentiality. Automated documenting of translated interactions is made possible by integration with electronic health records (EHR)., which helps with the continuity of treatment. Continuous improvement is guided by monitoring tools that measure system performance and user satisfaction. Enhance patient care and results by bridging language barriers in healthcare by promoting clear and accurate communication.

关键词： Cloud computing Translation Accuracy Hospitals Computational modeling Medical services Real-time systems Natural language processing Security Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Distributed Collaborative Sensing and Spectrum Access Approach for Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Peng, Yuhuai Li, Yuan Guo, Yu Zhang, Dawei Khan, Fazlullah Alturki, Ryan Alshawi, Bandar Northeastern University College of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Xihu District Hangzhou China Zhengzhou University School of Computer and Artificial Intelligence Henan Zhengzhou450001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China KKR and KSR Institute of Technology and Sciences Department of Computer Science and Engineering Andhra Pradesh Guntur India Division of Research and Development Lovely Professional University Phagwara India University Centre of Research and Development Chandigarh University Mohali India Umm Al-Qura University Department of Software Engineering College of Computing Makkah Saudi Arabia Umm Al-Qura University College of Computing Department of Computer and Network Engineering Makkah Saudi Arabia

Cognitive radio (CR) provides key technical support for the seamless communication of consumer electronic (CE) devices through distributed cooperative sensing and spectrum access. However, its openness and dynamic nature introduce potential security risks and challenges. Due to the openness of wireless communication, spectrum sensing and access are vulnerable to malicious attacks, and resource-constrained devices cannot effectively implement artificial intelligence (AI)-driven encryption and access control strategies. To address these limitations, this study proposes a blockchain-based distributed collaborative sensing method for CE devices. In the proposed method, after sensing, the smart contracts verify node legitimacy using the ring signature method. The malicious users are rejected by the outlier detection method, which improves the collaborative anti-interference ability. In addition, by using a centralized training and distributed execution architecture, a secure spectrum sensing strategy based on multi-agent reinforcement learning is designed. The proposed strategy ensures that each node makes independent decisions, which enhances the adaptability of the CE ecosystem. The proposed method is verified by extensive simulations, and the results show that it can maintain spectrum awareness of more than 95.72% and an access success rate of 91.19% under malicious attacks. Moreover, communication overhead is significantly reduced by approximately 93.53%. © 1975-2011 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

SmartTrap: An On-Field Insect Monitoring System Empowered by Edge Computing Capabilities

SmartTrap: An On-Field Insect Monitoring System Empowered by...

引用

IEEE International Conference on Research, Innovation and Vision for the Future

作者： Quan M. Nguyen Duy A. Pham Dong T. Pham An D. Le Nguyen Q. H. Vo Hien B. Vo School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Vietnam Joint Lab Artificial Intelligence and Data Science Universität Osnabrück Osnabrück Germany Graduate School of Bioresource and Bioenvironmental Sciences Kyushu University Fukuoka Japan Department of Electrical and Computer Engineering University of California San Diego San Diego USA Department of Electrical and Computer Engineering Vietnamese-German University Binh Duong Vietnam

Fruit flies pose a significant threat to fruit yields, necessitating immediate detection solutions for effective pest management. In this study, we present our approach using YOLOv7 and the Jetson Nano 4GB for rapid and accurate fruit fly detection. Our methodology attains an Average Precision (AP) of 0.993 at an Intersection over Union threshold (IoU) of 0.75, facilitating almost instantaneous enumeration of ensnared fruit flies in field conditions, thereby augmenting the efficacy of pest management practices. Concurrently, the system transmits this data to either a local or cloud-based server, assisting end-users in accurately identifying regions with elevated fruit fly densities to strategically administer pesticides. This targeted approach has significant implications for sustainable agriculture as it reduces the need for widespread spraying. Moreover, our versatile method adapts for detecting other pests like aphids or beetles, serving as a valuable tool in agriculture and beyond.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time-sensitive Learning for Heterogeneous Federated Edge intelligence

arXiv

引用

arXiv 2023年

作者： Xiao, Yong Zhang, Xiaohan Li, Yingyu Shi, Guangming Krunz, Marwan Nguyen, Diep N. Hoang, Dinh Thai The School of Electronic Information and Communications The Huazhong University of Science and Technology Wuhan430074 China The Peng Cheng Laboratory Guangdong Shenzhen518055 China Guangdong Guangzhou510555 China The School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan430074 China The School of Artificial Intelligence The Xidian University Shaanxi Xi'An710071 China The Department of Electrical and Computer Engineering The University of Arizona TucsonAZ85721 United States The School of Electrical and Data Engineering University of Technology Sydney Faculty of Engineering and Information Technology SydneyNSW120558 Australia

Real-time machine learning (ML) has recently attracted significant interest due to its potential to support instantaneous learning, adaptation, and decision making in a wide range of application domains, including self-driving vehicles, intelligent transportation, and industry automation. In this paper, we investigate real-time ML in a federated edge intelligence (FEI) system, an edge computing system that implements federated learning (FL) solutions based on data samples collected and uploaded from decentralized data networks, e.g., Internet-of-Things (IoT) and/or wireless sensor networks. FEI systems often exhibit heterogenous communication and computational resource distribution, as well as non-i.i.d. data samples arrived at different edge servers, resulting in long model training time and inefficient resource utilization. Motivated by this fact, we propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model with desirable accuracy. Training acceleration solutions for both TS-FL with synchronous coordination (TS-FL-SC) and asynchronous coordination (TS-FL-ASC) are investigated. To address the straggler effect in TS-FL-SC, we develop an analytical solution to characterize the impact of selecting different subsets of edge servers on the overall model training time. A server dropping-based solution is proposed to allow some slow-performance edge servers to be removed from participating in the model training if their impact on the resulting model accuracy is limited. A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, the local epoch number (the number of model training iterations per coordination), and the data batch size (the number of data samples for each model training iteration). Motivated by the fact that data samples at the slowest edge server may exhibit special characteristics that canno

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Multi-Sensor Information Fusion for Equipment Fault Diagnosis

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Lin, Tantao Ren, Zhijun Zhu, Linbo Zhu, Yongsheng Feng, Ke Ding, Weiping Yan, Ke Beer, Michael Xi'an Jiaotong University Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing System Xi'an710049 China Xi'an Jiaotong University Frontier Institute of Science and Technology Xi'an710049 China Xi'an Jiaotong University School of School of Chemical Engineering and Technology Xi'an710049 China Xi'an Jiaotong University School of Mechanical Engineering Xi'an710049 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science Macau999078 China Leibniz University Institute for Risk and Reliability Hannover30167 Germany University of Liverpool Department of Civil and Environmental Engineering LiverpoolL69 3BX United Kingdom Tongji University International Joint Research Center for Resilient Infrastructure International Joint Research Center for Engineering Reliability and Stochastic Mechanics Shanghai200092 China

In contrast to fault diagnosis relying solely on a single sensor, the method of multi-sensor information fusion for fault diagnosis (MSIFFD) broadens the spectrum of available information sources. It is renowned for its high accuracy and reliability, traits that have attracted growing attention within the research community and led to the generation of a substantial body of publications. However, there is currently a lack of a comprehensive and systematic review in this domain. Thereby, this review aims to thoroughly explore all research achievements in the field of MSIFFD. At the outset, an analysis is undertaken to delineate the fusion level of multi-sensor information, with a specific focus on its location and types of inputs and outputs within the information flow. Subsequently, an examination of the six primary fundamental operations for amalgamating multi-sensor information is undertaken to clarify the motivations and processes involved in information fusion across various operations. Following this, factors influencing fusion diagnostics and strategies aimed at improving their performance are examined to explore approaches for enhancing fusion accuracy. The subsequent sections delve into the analysis of sensor types and application scenarios, providing a reference guide for practical applications. Finally, this review outlines potential future challenges in the field of MSIFFD and provides a range of recommendations and possible solutions for consideration. © 1963-2012 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

An Efficient Techniques for Disease Prediction from Medical data Using data Mining and Machine Learning 5

An Efficient Techniques for Disease Prediction from Medical ...

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Kumar Bhatnagar, Anjani Madan, Parul Rana, Ajay Sharma, Sandeep Sonawane, Sameer Josphine, C. Vimala Quantum University Research Scholar Uttarakhand Roorkee India Graphic Era Deemed to Be University Department of CSE Uttarakhand Dehradun India Amity University Uttar Pradesh Greater Noida India Lloyd Institute of Engineering and Technology Department of EC Uttar Pradesh Greater Noida India Bharati Vidyapeeth's Institute of Management Studies & Research Department of Postgraduate Studies Navi-Mumbai India R. M. K Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Kavaraipettai India

ISBN: (纸本)9798350398267

Individuals are susceptible to numerous ailments in today's global setting, with people living highly automated lives under tremendous job pressure, both at home and at work. Such disorders have recently been on the rise at an alarming pace. As a result, the healthcare business must assume a prominent position soon, accountable for people's health, a better society, and a successful country at large. Healthcare prices are rising as the demand for health amenities grows. Healthcare facilities with improved detection, diagnostics, and treatment procedures are desperately needed. With growing digitization and computing techniques in place, a massive amount of data is being generated and used for diagnostic and detection approaches. This data might be used to obtain data for anticipating disease illnesses, commencing preventative measures, and improving treatment procedures long before the diseases progressed. Powerful computing technologies must be used to build the finest intelligence of forecasting and decision-making abilities evaluated by an expert. Modern data mining methods are used to the obtained to analyze such characteristics that may reveal crucial and critical indications regarding the existence and progression of the medical condition. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Als: Active Learning-Based Image Segmentation Model for Skin Lesion

SSRN

引用

SSRN 2022年

作者： Shu, Xiu Yang, Yunyun Xie, Ruicheng Liu, Jun Chang, Xiaojun Wu, Boying School of Science Harbin Institute of Technology Shenzhen China Information Systems Technology and Design Singapore University of Technology and Design Singapore Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia School of Mathematics Harbin Institute of Technology Harbin China

Medical image segmentation requires experienced doctors to provide accurate segmentation results as ground truth, since it involves plentiful medical knowledge. The deep learning-based model requires a large number of medical images and ground truth, during the training stage, which brings a heavy workload to the doctor. Therefore, based on the differences between medical images, we designed an active learning model to select more representative images for doctors to obtain the ground truth, which saves their time in segmenting similar medical images. Eventually, these representative images will serve as training sets and test sets, training a more accurate segmentation model. In this paper, we propose the active learning-based segmentation (ALS) model for medical images, in which we use the mean structure similarity index measure to measure how similar the two images are. Then we select some highly similar images from the entire training set. To our knowledge, we are the first to apply the active learning strategy based on the mean structure similarity index measure to medical image segmentation. Finally, we reduce the amount of data to 75%, 50%, 25%, and 12.5% to validate our ALS model. We use the selected images after active learning training and the medical semantic segmentation model to segment medical images, and the active learning model can reduce the cost of labeling and obtain accurate segmentation results through experiments, and even better than the segmentation results with a large number of highly similar data. © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A lightweight Federated Learning-based Intrusion detection model for Internet of Things

A lightweight Federated Learning-based Intrusion detection m...

引用

IEEE International Conference on Multi Topic

作者： Noshina Tariq Mamoona Humayun Ghadah Naif Alwakid Bushra Almas NZ Jhanjhi Muhammad Zakwan Department of Artificial Intelligence and Data Science National University of Computer and Emerging Sciences Islamabad Pakistan School of Arts Humanities and Social Sciences University of Roehampton London United Kingdom Department of Computer Science College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Institute of Information Technology Quaid-i-Azam University Islamabad Pakistan School of Computer Science Taylor’s University Selangor Malaysia Department of Avionics Engineering Air University Islamabad Pakistan

ISBN: (数字)9798331507213

ISBN: (纸本)9798331507220

The advancement of sophistication in botnet intrusions on Internet of Things (IoT) systems and the resources required by traditional IDS make strong security solutions necessary, which reduce resource usage while enhancing detection capability. Therefore, this paper tests the performance and performance comparison of classification models based on lightweight Federated Learning (FL) for IoT botnet intrusion detection using Random Forest (RF), XGBoost, and LightGBM classifiers. Utilizing a large-scale dataset from IoT traffic, the three models were tested in metrics such as confusion matrices, ROC curves, and Precision-Recall curves. The results show that the RF and XGBoost classifiers achieve high AUCs of 1.00, thereby, there is no trade-off between sensitivity and specificity. On the other hand, LightGBM scored a low of 0.58 AUC. The results show that robust ensemble methods can be applied to handle complex and imbalanced datasets commonly presented in IoT traffic in FL environments.

关键词： Radio frequency Measurement Federated learning Botnet Intrusion detection Sensitivity and specificity Internet of Things Ensemble learning Security Random forests

来源：评论

学校读者我要写书评

暂无评论

Noise multiplication and bandwidth of photodetectors employed with Taylor dispersion in micro optical fiber channel system

引用

Journal of Optical Communications 2024年第0期45卷 s1383-s1398页

作者： Nagendram, Sanam Babu, Gade Harish Ahammad, Shaik Hasane Kiran, Kasi Uday Anwer, Twana Mohammed Kak Hossain, Md. Amzad Rashed, Ahmed Nabih Zaki Amin, Marwa Hamed Department of Artificial Intelligence KKR & KSR Institute of Technology and Sciences Guntur India Department of ECE CVR College of Engineering Hyderabad India Department of ECE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Department of ECE Koneru Lakshmaiah Education Foundation Guntur522502 India Department of Physics College of Education Salahaddin University-Erbil Kurdistan Region Erbil44002 Iraq Institute of Theoretical Electrical Engineering Faculty of Electrical Engineering and Information Technology Ruhr University Bochum Bochum44801 Germany Department of Electrical and Electronic Engineering Jashore University of Science and Technology Jashore7408 Bangladesh Electronics and Electrical Communications Engineering Department Faculty of Electronic Engineering Menoufia University Menouf32951 Egypt Department of VLSI Microelectronics Institute of Electronics and Communication Engineering Saveetha School of Engineering SIMATS Tamilnadu Chennai602105 India

This work has clarified the noise multiplication and bandwidth of photodetectors employed with Taylor dispersion in micro optical fiber channel system. The simulation performance evaluation of slide and squeeze film damping and fluidics mechanics. The damping ratio versus gap distance for a cantilever beam and a mass suspended from beams are determined. The damping ratio with gap size for a suspended mass with and without holes is reported. The damping ratio variations with the gap distance variations for a mass suspended from beams is clarified. The velocity field for fluid flow in a circular channel, a square channel, a rectangular channel, a parabolic channel and a triangular channel is estimated. Besides the velocity field for the fluid flow in a channel with and without slip is outlined. The spreading of a diffusion front in one dimension in a resting fluid and the dispersion coefficient in a square channel [Taylor dispersion in micro fluidic channels] are clarified. The 2D diffusion profile of a solute in a T mixer and normalized concentration versus the channel width for the solute at the outlet of H filter are determined. © 2023 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Photodetectors

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：