检索结果-内蒙古大学图书馆

Dynamic Quantum Federated Learning for UAV-Based Autonomous Surveillance

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8158-8170页

作者： Park, Soohyun Son, Seok Bin Jung, Soyi Kim, Joongheon Sookmyung Women's University Division of Computer Science Seoul04310 Korea Republic of Korea University School of Electrical Engineering Seoul02841 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of

In recent years, unmanned aerial vehicles (UAVs) have proven their effectiveness in surveillance due to their superior mobility. By utilizing multiple UAVs with collaborated learning, surveillance of a huge area while consuming minimum resources is possible. However, the performance of UAV collaborative learning systems is still severely limited because the number of parameters in a classical NN is generally very large, which is unsuitable for unstable wireless communication. To address this issue, this paper uses a quantum neural network (QNN), which has large computational capabilities and uses fewer parameters to overcome the problems caused by many parameters. However, it is still difficult to send all the parameters of the QNN to the server under poor channel conditions. Therefore, this paper proposes dynamic quantum federated learning (DQFL), a novel framework designed for UAVs employing quantum computing (QC) and federated learning (FL). The proposed DQFL uses a dynamic quantum neural network (DQNN) with a multi-depth circuit and employs dynamic control of the circuit layer to improve the efficiency of local parameter transmission between UAVs in unstable wireless communication environments. Extensive simulations conducted under real-world autonomous surveillance conditions demonstrate the robustness of DQFL to non-iidness, varying signal-to-noise ratios (SNRs), and poor communication channel conditions in the UAV environment. © 1967-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Streamlined Method for Detecting Strawberry Leaf Diseases Utilizing Deep Learning Techniques 3

A Streamlined Method for Detecting Strawberry Leaf Diseases ...

引用

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

作者： Singh, Jashandeep Singh, Gursharan School of Computer Science and Engineering Lovely Professional University Phagwara India Department of Computer Science and Engineering Lovely Professional University Phagwara India

ISBN: (纸本)9798331527549

Strawberry leaf scorch presents major risks to fruit yields through its harmful effects on plant health so early detection methods are vital for growers. This research analyzes how different Convolutional Neural Networks classify strawberry leaf diseases while fixing problems found in earlier studies about speed and diagnosis precision. The proposed research evaluated five CNN models namely AlexNet, DenseNet, ResNet, MobileNet, and EfficientNet through implementation on a total of 6146 images that showcased both healthy and scorch-affected strawberry leaves. The proposed research optimized feature extraction techniques and added model comparison to find the most effective configuration. EfficientNet achieved higher accuracy and precision than all test models when detecting diseases in samples. The strong disease identification abilities of DenseNet and MobileNet show promise for developing better ways to manage agricultural health problems. This study expands precision agriculture methods while helping farmers sustain their operations through modern machine learning tools. © 2025 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Heterogeneous Federated Learning via Approximate DNN Accelerators

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第6期44卷 2054-2066页

作者： Pfeiffer, Kilian Balaskas, Konstantinos Siozios, Kostas Henkel, Jorg Karlsruhe Institute of Technology Chair for Embedded Systems Karlsruhe76131 Germany University of Patras Department of Computer Engineering and Informatics Patras26504 Greece Aristotle University of Thessaloniki Department of Physics Thessaloniki54124 Greece

In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped from the collaborative training. However, dropping devices in FL can degrade training accuracy and introduce bias or unfairness. Several works have tackled this problem on an algorithm level, e.g., by letting constrained devices train a subset of the server neural network (NN) model. However, it has been observed that these techniques are not effective w.r.t. accuracy. Importantly, they make simplistic assumptions about devices’ resources via indirect metrics, such as multiply accumulate (MAC) operations or peak memory requirements. We observe that memory access costs (that are currently not considered in simplistic metrics) have a significant impact on the energy consumption. In this work, for the first time, we consider on-device accelerator design for FL with heterogeneous devices. We utilize compressed arithmetic formats and approximate computing, targeting to satisfy limited energy budgets. Using a hardware-aware energy model, we observe that, contrary to the state of the art’s moderate energy reduction, our technique allows for lowering the energy requirements (by 4× ) while maintaining higher accuracy. © 1982-2012 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Data Storage Method for Pulse-to-Pulse Optimizations

IEEE Transactions on Radar Systems

引用

IEEE Transactions on Radar Systems 2024年 2卷 899-909页

作者： Van Hoosier, Trevor Alexander, Jordan Montgomery, Mariah Egbert, Austin Roessler, Justin Baylis, Charles Marks, Robert J. Baylor University Department of Electrical and Computer Engineering WacoTX76798 United States Purdue University Elmore Family School of Electrical and Computer Engineering West LafayetteIN47907 United States

Due to increasing congestion in the radar frequencies due to reallocations, the pressure upon radar systems to avoid interference through dynamically changing operating frequency has intensified. Many modern radar systems (often called 'cognitive radar' systems) often have the ability to sense and avoid interference. Through the use of reconfigurable transmitter circuitry, the front end can be quickly reconfigured following a change in frequency to maximize output power and, hence, detection range. With the implementation of a fast, plasma-switch impedance tuner paired with an efficient circuit optimization, the ability to change tuner setting within a single radar pulse repetition interval (PRI) has been previously demonstrated. To carry out impedance-tuning optimization measurements for each PRI, an efficient data storage and lookup method is needed. In this article, we demonstrate how hybrid storage with a hash table can be used with an efficient, cache replacement algorithm on a software-defined radio (SDR) platform to enable continuous operation with pulse-to-pulse optimization. This data storage approach minimizes overhead in storage of circuit optimization settings, allowing faster optimization of the circuit to maximize output power. By maximizing output power quickly, it is expected that the radar will experience better signal-to-interference-plus-noise ratio and accurate detection of targets at greater ranges. © 2023 IEEE.

关键词： Power amplifiers

来源：评论

学校读者我要写书评

暂无评论

BAHGRF^(3):Human gait recognition in the indoor environment using deep learning features fusion assisted framework and posterior probability moth flame optimisation

引用

CAAI Transactions on Intelligence Technology 2025年第2期10卷 387-401页

作者： Muhammad Abrar Ahmad Khan Muhammad Attique Khan Ateeq Ur Rehman Ahmed Ibrahim Alzahrani Nasser Alalwan Deepak Gupta Saima Ahmed Rahin Yudong Zhang Foundation University Islamabad IslamabadPakistan Department of Artificial Intelligence College of Computer Engineering and SciencePrince Mohammad Bin Fahd UniversityAl KhobarSaudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadhSaudi Arabia Department of Computer Science Maharaja Agrasen Institute of TechnologyDelhiIndia United International University DhakaBangladesh School of Informatics University of LeicesterLeicesterUK

Biometric characteristics are playing a vital role in security for the last few *** gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework for human gait classification in video sequences using deep learning(DL)fusion assisted and posterior probability-based moth flames optimization(MFO)is *** the first step,the video frames are resized and finetuned by two pre-trained lightweight DL models,EfficientNetB0 and *** models are selected based on the top-5 accuracy and less number of ***,both models are trained through deep transfer learning and extracted deep features fused using a voting *** the last step,the authors develop a posterior probabilitybased MFO feature selection algorithm to select the best *** selected features are classified using several supervised learning *** CASIA-B publicly available dataset has been employed for the experimental *** this dataset,the authors selected six angles such as 0°,18°,90°,108°,162°,and 180°and obtained an average accuracy of 96.9%,95.7%,86.8%,90.0%,95.1%,and 99.7%.Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state-of-the-art techniques.

关键词： deep learning feature fusion feature optimization gait classification indoor environment machine learning

来源：评论

学校读者我要写书评

暂无评论

Determination of Brain Tumors with Neural Networks and CT Scan Imagery 2

Determination of Brain Tumors with Neural Networks and CT Sc...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Ragam, Prashanth Gorantla, Bhavitha Sonakshi Eshtamsetti, Yasaswini Maji, Sayanatika Pavithra, Danaveni School of Computer Science and Engineering VIT-AP University Andhrapradesh India Gokaraju Rangaraju Institute of Engineering and Technology Department of Computer Science Engineering Hyderabad India

ISBN: (纸本)9798350366570

The process of brain tumor detection is paramount in the field of medical diagnostics. Early iden- tification of a brain tumor significantly enhances the chances of a patient restoring from it. In recent years, Artificial Intel- ligence has emerged as a promising tool that has efficiently assisted brain tumor detection. This research paper intro-duces an Artificial Intelligence system specifically designed to detect brain tumors based on medical imaging data, like Computed Tomography scans. It is harnessing the power of advanced machine learning algorithms, including deep learning and accuracy of brain tumor detection, facilitating timely medical action and proper treatment planning for patients. We have taken models Support Vector Machine (SVM), Radial Basis Function Neural Network (RBFNN), and Back Propagation Neural Network (BPNN) to train on the Computed Tomography images of the brain collected from the Kaggle and achieved an accuracy of 88.88% using RBFNN and BPNN models. © 2024 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Achieving Seamless Semantic Interoperability and Enhancing Text Embedding in Healthcare IoT: A Deep Learning Approach with Survey

引用

SN computer Science 2024年第1期5卷 99页

作者： Purushothaman, Sony Shanmugam, G. Siva Nagarajan, Sureshkumar School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science Govt. Model Engineering College Kerala Kochi India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamil Nadu Krishnakovil India

Achieving semantic interoperability in healthcare is one of the significant challenges in the rapidly expanding healthcare sector. On the other hand, IoT in healthcare can provide patient-centric treatment mechanisms to help resolve these issues. When several healthcare organizations are generating heterogeneous medical information, semantic interoperability becomes essential to develop better treatment plans and better medical research. In this article, we discuss the applications of healthcare IoT, a comparative study of existing solution paradigms for achieving semantic interoperability and its enabling technologies. The comprehensive analysis of semantic interoperability has versatile dimensions to meet this, and it establishes deep learning-based directions. In continuing the background work, we proposed a new deep learning model called MedRelBERT with six embeddings to remove linguistic ambiguities in medical documents. The survey also examines the bibliographic evaluation of Web of Science articles discussing semantic interoperability solutions. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Deep learning Internet of medical things Privacy Semantic interoperability

来源：评论

学校读者我要写书评

暂无评论

Improving bot detection of fake followers on Twitter via a hybrid B-HC optimisation algorithm 5

Improving bot detection of fake followers on Twitter via a h...

引用

5th IEEE International Conference on Electrical, computer and Communication Technologies, ICECCT 2023

作者： Alzeyadi, Haider Duran, Fecir Informatics Institute Department of Computer Science Gazi University Ankara Turkey Gazi University Engineering Faculty of Technology Department of Computer Engineering Ankara Turkey

ISBN: (纸本)9781665493604

Sophisticated cyber threats are seen on Online Social Networks (OSNs) social media accounts automated to imitate human behaviours has an impactful effect on distorting public thoughts and opinions. OSNs are weaponized to diffuse deception, misinformation, and malicious activities, that forms a serious threat to society. The deceptive nature of imitating human behaviour has become a challenging and crucial task to detect automated accounts (socialbots). This research, however, proposes a hybrid metaheuristic optimisation algorithm for socialbot detection. Specifically, a hybrid B-Hill Climbing (B-HC) optimisation algorithm works in tandem with a k-NN nearest neighbour classifier to accurately select a relevant feature subset. It is applied to be tested for fake followers account on Twitter data. Experimental results showed that the proposed method is better than the traditional and the latest feature selection techniques as well as the rule-set methods. The B-HC alongside with k-NN method achieved promising results using only relevant feature subset. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Eye Disease Classification Based on Fundus Images Using Convolutional Neural Network 25

Eye Disease Classification Based on Fundus Images Using Conv...

引用

25th International Electronics Symposium, IES 2023

作者： Denandra, Rafi Fariza, Arna Prayogi, Yanuar Risah Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

The eye is a vital organ in the human body. Through the eyes, humans can absorb over 80% of visual information used to carry out various daily activities. However, in Indonesia, there are many cases of vision impairments that, if not properly addressed, can lead to blindness. Examples of such impairments include cataracts, glaucoma, and diabetic retinopathy. Currently, there are many research studies on eye diseases that are aided by technologies like Artificial Intelligence (AI). One of the AI technologies that is commonly developed is Convolutional Neural Network (CNN). CNN is a deep learning framework that excels in solving image or picture classification problems because its architecture applies convolution layers, which can break down images to extract features and easily reduce the high dimensionality without losing the image's information itself. In this study, the author used various CNN models to find the most suitable model for classifying eye diseases, including EfficientNet, ResNet, Inception V3, and many others. Through various model training experiments, the accuracy for the ResNet50 model was found to be 95% with a loss of 17%, followed by Xception with an accuracy of 95% and a loss of 21%, and EfficientNetV2B2 with an accuracy of 92% and a loss of 25%. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrating AI and IoT for Enhanced Predictive Healthcare Monitoring: A Comprehensive Study on Breast Cancer Patient-Centric Approach

Integrating AI and IoT for Enhanced Predictive Healthcare Mo...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Saravanan, M.S. Thisin, Syed Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Department Of Computer Science And Engineering Tamilnadu Chennai India Visvesvaraya College Of Engineering And Technology Jawaharlal Nehru Technological University Department Of Computer Science And Engineering Hyderabad India Saveetha School Of Engineering India

ISBN: (纸本)9798350364828

In the contemporary healthcare landscape, various intelligent automated approaches are revolutionizing healthcare tasks. Learning concepts are pivotal for activities like comprehending acquired data and monitoring patient behavior. Amid patient-centric concerns, addressing data heterogeneity, extraction, and prediction challenges is crucial. To enhance patient monitoring using care indicators like cost and stay length, we propose an AI and IoT-integrated automated approach, while tackling heterogeneity. Employing certain rules for data extraction to form a distinct representation, our model integrates pre-treatment information and employs a modified Combined Random Forest, LSTM, and BiLSTM algorithm for predictive posttreatment monitoring. This framework, synergizing AI, IoT, and advanced neural networks, facilitates real-time health monitoring, especially focusing on breast cancer patients. Embracing pre-treatment, in-treatment, and post-treatment phases, our model aims for accurate diagnosis, improved cost-efficiency, and extended stays. The evaluation underscores scalability, reliability enhancement, and validates the framework's efficacy in transforming healthcare practices. © 2024 IEEE.

关键词： Automation

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：