检索结果-内蒙古大学图书馆

Enhancing security in Distributed Drone-based Litchi Fruit Recognition and Localization systems

computers, Materials & Continua 2025年第2期82卷 1985-1999页

作者： Liang Mao Yue Li Linlin Wang Jie Li Jiajun Tan Yang Meng Cheng Xiong Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Application Technology Research Institute Shenzhen Polytechnic UniversityShenzhen518055China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China

This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations. Our method incorporates depth information to ensure precise localization and utilizes a streamlined detection network centered on the RepVGG module. This module replaces the traditional C2f module, enhancing detection performance while maintaining speed. To bolster the detection of small, distant fruits in complex settings, we integrate selective Kernel Attention (sKAttention) and a specialized small-target detection layer. This adaptation allows the system to manage difficult conditions, such as variable lighting and obstructive foliage. To reinforce security, the tasks of recognition and localization are distributed among multiple drones, enhancing resilience against tampering and data manipulation. This distribution also optimizes resource allocation through collaborative processing. The model remains lightweight and is optimized for rapid and accurate detection, which is essential for real-time applications. Our proposed system, validated with a D435 depth camera, achieves a mean Average Precision (mAP) of 0.943 and a frame rate of 169 FPs, which represents a significant improvement over the baseline by 0.039 percentage points and 25 FPs, respectively. Additionally, the average localization error is reduced to 0.82 cm, highlighting the model’s high precision. These enhancements render our system highly effective for secure, autonomous fruit-picking operations, effectively addressing significant performance and cybersecurity challenges in agriculture. This approach establishes a foundation for reliable, efficient, and secure distributed fruit-picking applications, facilitating the advancement of autonomous systems in contemporary agricultural practices.

关键词： Objective detection deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning applications in the Internet of Things: a review, tools, and future directions

引用

Evolutionary Intelligence 2024年第5-6期17卷 3621-3654页

作者： Raoufi, Parisa Hemmati, Atefeh Rahmani, Amir Masoud Department of Computer Engineering Central Tehran Branch Islamic Azad University Tehran Iran Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology Yunlin64002 Taiwan

The emergence of the Internet of Things (IoT) has enabled the proliferation of interconnected devices and sensors, generating vast amounts of often complex and unstructured data. Deep learning (DL), a subfield of machine learning (ML), has shown great promise in addressing the challenges of processing and analyzing such data. Considering the increasing importance of DL and data analysis, we decided to review the articles of the last few years in this field to pave the way for researchers. In this article, we used the systematic literature review (sLR) method, and in line with that, we selected and analyzed 56 articles published from 2019 to April 2024. We first discuss the DL models used in the IoT field and clarify their specific use cases. secondly, we outline an analysis of research areas in DL-based IoT. In addition, our research extends to the tools and simulators used to evaluate studies in the DL-based IoT domain. We also examine the DL-based IoT research datasets. Finally, our review identifies future directions and open issues in DL-based IoT. We aim to contribute to an accurate understanding of the current state, challenges, and potential breakthroughs at the intersection of DL and the IoT. © The Author(s), under exclusive licence to springer-Verlag GmbH Germany, part of springer Nature 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

OpenClinicalAI: An open and dynamic model for Alzheimer's Disease diagnosis

引用

EXPERT sYsTEMs WITH APPLICATIONs 2025年 261卷

作者： Huang, Yunyou Liang, Xiaoshuang Xie, Jiyue Lu, Xiangjiang Miao, Xiuxia Liu, Wenjing Zhang, Fan Kang, Guoxin Ma, Li Tang, suqin Zhan, Jianfeng Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin Peoples R China Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Guilin Med Univ Guilin Peoples R China Int Open Benchmark Council Delaware CA USA

Although Alzheimer's disease (AD) cannot be reversed or cured, timely diagnosis can significantly reduce the burden of treatment and care. Current research on AD diagnosis models usually regards the diagnosis task as a typical classification task with two primary assumptions: (1) All target categories are known a priori;(2) The diagnostic strategy for each patient is consistent, that is, the number and type of model input data for each patient are the same. However, real-world clinical settings are open, with complexity and uncertainty in terms of both subjects and the resources of the medical institutions. This means that diagnostic models may encounter unseen disease categories and need to dynamically develop diagnostic strategies based on the subject's specific circumstances and available medical resources. Thus, the AD diagnosis task is tangled and coupled with the diagnosis strategy formulation. To promote the application of diagnostic systems in real- world clinical settings, we propose OpenClinicalAI for direct AD diagnosis in complex and uncertain clinical settings. This is the first end-to-end model to dynamically formulate diagnostic strategies and provide diagnostic results based on the subject's conditions and available medical resources. OpenClinicalAI combines reciprocally coupled deep multi-action reinforcement learning (DMARL) for diagnostic strategy formulation and multicenter meta-learning (MCML) for open-set recognition. The experimental results show that OpenClinicalAI achieves better performance and fewer clinical examinations than the state-of-the-art model. Our method provides an opportunity to embed the AD diagnostic system into the current healthcare system to cooperate with clinicians to improve current healthcare.

关键词： Real-world clinical setting Alzheimer's disease Diagnose AI Deep learning

来源：评论

学校读者我要写书评

暂无评论

Ensemble Knowledge Distillation for Federated semi-supervised Image Classification

引用

Tsinghua science and Technology 2025年第1期30卷 112-123页

作者： Ertong shang Hui Liu Jingyang Zhang Runqi Zhao Junzhao Du School of Computer Science and Technology Xidian UniversityXi’an 710126China Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of EducationXi’an 710126China Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province Xi’an 710126China

Federated learning is an emerging privacy-preserving distributed learning paradigm,in which many clients collaboratively train a shared global model under the orchestration of a remote *** current works on federated learning have focused on fully supervised learning settings,assuming that all the data are annotated with ground-truth ***,this work considers a more realistic and challenging setting,Federated semi-supervised learning(FssL),where clients have a large amount of unlabeled data and only the server hosts a small number of labeled *** to reasonably utilize the server-side labeled data and the client-side unlabeled data is the core challenge in this *** this paper,we propose a new FssL algorithm for image classification based on consistency regularization and ensemble knowledge distillation,called *** algorithm uses the global model as the teacher in consistency regularization methods to enhance both the accuracy and stability of client-side unsupervised learning on unlabeled ***,we introduce an additional ensemble knowledge distillation loss to mitigate model overfitting during server-side retraining on labeled *** experiments on several image classification datasets show that our EKDFssL outperforms current baseline methods.

关键词： federated learning semi-supervised learning federated semi-supervised learning knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Decoding Brain Age: A self-supervised Graph Neural Network Framework for EEG Analysis

Decoding Brain Age: A Self-Supervised Graph Neural Network F...

引用

2024 IEEE sensors Conference

作者： Cook, Zara Zhao, Chengzong Murray, Livia Kesan, Jivan Belacel, Nabil Doesburg, sam M. Medvedev, George Vakorin, Vasily A. Xi, Pengcheng Natl Res Council Canada Waterloo ON Canada Univ Waterloo Waterloo ON Canada Natl Res Council Canada Digital Technol Ottawa ON Canada Simon Fraser Univ Biomed Physiol & Kinesiol Burnaby BC Canada Fraser Hlth Author Div Neurol Vancouver BC Canada

ISBN: (纸本)9798350363524;9798350363517

Electroencephalogram (EEG) recordings are valuable for capturing neuro-physiological states, with brain age prediction providing key insights into brain health. To scale this diagnostic technique, we propose a computer-aided system using self-supervised learning (ssL) and Graph Neural Networks (GNNs) for EEG analysis. ssL reduces the need for fully labeled data by pre-training models on large unlabeled EEG datasets. We tackle temporal-spectral feature learning challenges with GNNs, employing graph-based representations of EEG data to depict the brain's interconnectedness and extract meaningful features. Furthermore, we enhance the explainability of brain age predictions by visualizing channel-wise maps, highlighting critical EEG channels influencing the model's decisions.

关键词： EEG Analysis Brain Age Prediction self-supervised learning Graph Neural Networks

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity ML-based Methods for Malware Classification

引用

computers, Materials & Continua 2024年第9期80卷 4833-4857页

作者： Mahmoud E.Farfoura Ahmad Alkhatib Deema Mohammed Alsekait Mohammad Alshinwan sahar A.El-Rahman Didi Rosiyadi Diaa salama Abd Elminaam Cybersecurity Department Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Computer Systems Program-Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairo11629Egypt Research Center for Artificial Intelligence and Cybersecurity Electronics and Informatics OrganizationNational Research and Innovation Agency(BRIN)KST Samaun SamadikunBandung40135Republic of Indonesia Jadara Research Center Jadara UniversityIrbid21110Jordan MEU Research Unit Middle East UniversityAmman11831Jordan

The article describes a new method for malware classification,based on a Machine learning(ML)model architecture specifically designed for malware detection,enabling real-time and accurate malware *** an innovative feature dimensionality reduction technique called the Interpolation-based Feature Dimensionality Reduction Technique(IFDRT),the authors have significantly reduced the feature space while retaining critical information necessary for malware *** technique optimizes the model’s performance and reduces computational *** proposed method is demonstrated by applying it to the BODMAs malware dataset,which contains 57,293 malware samples and 77,142 benign samples,each with a 2381-feature *** the IFDRT method,the dataset is transformed,reducing the number of features while maintaining essential data for accurate *** evaluation results show outstanding performance,with an F1 score of 0.984 and a high accuracy of 98.5%using only two reduced *** demonstrates the method’s ability to classify malware samples accurately while minimizing processing *** method allows for improving computational efficiency by reducing the feature space,which decreases the memory and time requirements for training and *** new method’s effectiveness is confirmed by the calculations,which indicate significant improvements in malware classification accuracy and *** research results enhance existing malware detection techniques and can be applied in various cybersecurity applications,including real-timemalware detection on resource-constrained *** and scientific contribution lie in the development of the IFDRT method,which provides a robust and efficient solution for feature reduction in ML-based malware classification,paving the way for more effective and scalable cybersecurity measures.

关键词： Malware detection ML-based models dimensionality reduction feature engineering

来源：评论

学校读者我要写书评

暂无评论

Exploring innovative interconnection between project based Teaching in Mathematics and CLIL

引用

sN social sciences 2024年第11期4卷 1-24页

作者： Bairy, shailaja Inamdar, Neeta Manipal Centre for European Studies Manipal Academy of Higher Education Karnataka Manipal 576104 India Madhava Kripa School Karnataka Manipal 576104 India Symbiosis Centre for Higher Education Research and Policy Advocacy (SCHERPA) Symbiosis International (Deemed University) Pune India

Recent research findings indicate the need for narrowing the gap between the sciences and languages, through student-centred pedagogies in a dynamic classroom. Mathematics, being inherently unique and closely connected to both ‘sciences’ and ‘Humanities’ is at the heart of effective thinking. Coupling these proved to be mutually beneficial for the subjects and impacted positively on quality of learning. Moreover, the learning in 21st century is driven not only by mastery of content but also by producing, synthesizing and evaluating information from a wide variety of subjects and sources, with an understanding of and respect for diverse cultures. It implies that the active exploration of real world challenges and problems helps deeper understanding of the subject. Integration of Multidisciplinary project based Teaching (PBT) [that anchors on principles of Content and Language Integrated learning (CLIL)] into school curriculum, meets the requisites for ‘learning for life and work’ in the 21st century. This evidence-based research paper illustrates and explores the IsA (British council’s International school Award) multidisciplinary project, CLIL project;both being the methods that could innovatively blend mathematics with languages. Authors’ experience-based reflections of such multidisciplinary projects (local/international) integrated with CLIL approach and Math Navigator micro-projects by ABC Company (name changed for anonymity) form the basis for a new workable/flexible pedagogical plan provided in this paper. This newly designed project plan hopes to serve as a ready-reckoner for 21st century educators. It is very relevant in today’s post–COVID scenario of education and implementation of National Education Policy (NEP) 2020 in India. © The Author(s), under exclusive licence to springer Nature switzerland AG 2024.

关键词： CLIL International school Award Math Navigator project based Teaching

来源：评论

学校读者我要写书评

暂无评论

Toward Organizational Design Principles: An Explorative Interdisciplinary Case study Investigating Digitally supported learning spaces in Higher Education 8th

Toward Organizational Design Principles: An Explorative Inte...

引用

8th EAI International Conference on Design, learning and Innovation, DLI 2023

作者： Ørngreen, Rikke Knudsen, sara Paasch Hautopp, Heidi Jensen, Rune Gram Hagel Research Group Department of Culture and Learning Aalborg University Copenhagen Campus Copenhagen Denmark Aalborg University Aalborg Denmark

ISBN: (纸本)9783031673061

Educational institutions are tasked with reimagining physical spaces and pedagogical methods to align with digitally supported learning environments. This study investigates the first steps of this transformation through a project on pedagogical innovations in a university setting. The research questions examined are as follows: What type of knowledge is gained from an explorative design approach to knowledge generation during educational development? How can this knowledge be presented and operationalized on an organizational level? Using a design-oriented perspective and inspiration from design-based implementation research, this study examines several activities carried out in The Classroom of the Future project. The activities were investigations of both existing classrooms and further possibilities within, for example, the use of active learning spaces, outdoor spaces, XR, and sony Edge Analytics technologies. The research design incorporates both qualitative and quantitative methods. The analysis shows how strategic and operational considerations interrelate, and the findings emphasize the value of cross-disciplinary collaboration in distilling local design principles. These principles can inform the specific strategy and organization at the local university level and be inspirational for other educational institutions. The findings may be of particular interest to universities and educational programs that work within problem- and project-based learning paradigms. © ICsT Institute for computer sciences, social Informatics and Telecommunications Engineering 2024.

关键词： computer aided instruction

来源：评论

学校读者我要写书评

暂无评论

A Facial Expression Recognition Method Integrating Uncertainty Estimation and Active learning

引用

computers, Materials & Continua 2024年第10期81卷 533-548页

作者： Yujian Wang Jianxun Zhang Renhao sun School of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China Data Space Research Institute of Hefei Comprehensive National Science Center Hefei230088China

The effectiveness of facial expression recognition(FER)algorithms hinges on the model’s quality and the availability of a substantial amount of labeled expression ***,labeling large datasets demands significant human,time,and financial *** active learning methods have mitigated the dependency on extensive labeled data,a cold-start problem persists in small to medium-sized expression recognition *** issue arises because the initial labeled data often fails to represent the full spectrum of facial expression *** paper introduces an active learning approach that integrates uncertainty estimation,aiming to improve the precision of facial expression recognition regardless of dataset scale *** method is divided into two primary ***,the model undergoes self-supervised pre-training using contrastive learning and uncertainty estimation to bolster its feature extraction ***,the model is fine-tuned using the prior knowledge obtained from the pre-training phase to significantly improve recognition *** the pretraining phase,the model employs contrastive learning to extract fundamental feature representations from the complete unlabeled *** features are then weighted through a self-attention mechanism with rank ***,data from the low-weighted set is relabeled to further refine the model’s feature extraction *** pre-trained model is then utilized in active learning to select and label information-rich samples more *** results demonstrate that the proposed method significantly outperforms existing approaches,achieving an improvement in recognition accuracy of 5.09%and 3.82%over the best existing active learning methods,Margin,and Least Confidence methods,respectively,and a 1.61%improvement compared to the conventional segmented active learning method.

关键词： Expression recognition active learning self-supervised learning uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Understanding How Parents Deal With the Health Advice They Receive: A Qualitative study and Implications for the Design of Message-based Health Dissemination systems for Child Health

Understanding How Parents Deal With the Health Advice They R...

引用

2024 ACM Designing Interactive systems Conference, DIs 2024

作者： Félix, Beatriz Braga, Cristiana Ntinga, Xolani Till, sarina Meoli, Leina Van Heerden, Alastair Melo, Ricardo Verdezoto, Nervo Densmore, Melissa Nunes, Francisco Fraunhofer Portugal AICOS Porto Portugal Human Sciences Research Council Pietermaritzburg South Africa University of Cape Town Cape Town South Africa Human Sciences Research Council University of the Witwatersrand Pietermaritzburg South Africa Cardiff University Cardiff United Kingdom

ISBN: (纸本)9798400705830

Message-based health information dissemination systems can potentially improve maternal and child health (MCH). By conveying health information to parents, sMs- and chatbot-based systems can support parents’ learning and empower them to make better health decisions for their children. However, there is limited design advice for creating message-based dissemination systems for MCH. To help address this gap, we conducted 14 participatory workshops with 42 parents from Portugal and south Africa, exploring how parents learned to care for their children’s health. Our findings showed how parents reflected on the health advice they received, by assessing the fit of the advice to their child’s characteristics, their values and beliefs, the advice’s feasibility, or the intention and competence of the advice giver. based on these insights, we propose four design implications for creating message-based health information dissemination systems tailored to parents and their children. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Information dissemination

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：