检索结果-内蒙古大学图书馆

Unmanned aerial vehicle based multi-person detection via deep neural network models

Frontiers in Neurorobotics 2025年 19卷 1582995页

作者： Alshehri, Mohammed Zahoor, Laiba AlQahtani, Yahya Alshahrani, Abdulmonem AlHammadi, Dina Abdulaziz Jalal, Ahmad Liu, Hui Department of Computer Science King Khalid University Abha Saudi Arabia Faculty of Computer Science Air University Islamabad Pakistan Department of Informatics and Computer Systems King Khalid University Abha Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science and Engineering College of Informatics Korea University Seoul Korea Republic of Cognitive Systems Lab University of Bremen Bremen Germany Guodian Nanjing Automation Company Ltd. Nanjing China Jiangsu Key Laboratory of Intelligent Medical Image Computing School of Future Technology Nanjing University of Information Science and Technology Nanjing China

Introduction: Understanding human actions in complex environments is crucial for advancing applications in areas such as surveillance, robotics, and autonomous systems. Identifying actions from UAV-recorded videos becomes more challenging as the task presents unique challenges, including motion blur, dynamic background, lighting variations, and varying viewpoints. The presented work develops a deep learning system that recognizes multi-person behaviors from data gathered by UAVs. The proposed system provides higher recognition accuracy while maintaining robustness along with dynamic environmental adaptability through the integration of different features and neural network models. The study supports the wider development of neural network systems utilized in complicated contexts while creating intelligent UAV applications utilizing neural networks. Method: The proposed study uses deep learning and feature extraction approaches to create a novel method to recognize various actions in UAV-recorded video. The proposed model improves identification capacities and system robustness by addressing motion dynamic problems and intricate environmental constraints, encouraging advancements in UAV-based neural network systems. Results: We proposed a deep learning-based framework with feature extraction approaches that may effectively increase the accuracy and robustness of multi-person action recognition in the challenging scenarios. Compared to the existing approaches, our system achieved 91.50% on MOD20 dataset and 89.71% on Okutama-Action. These results do, in fact, show how useful neural network-based methods are for managing the limitations of UAV-based application. Discussion: Results how that the proposed framework is indeed effective at multi-person action recognition under difficult UAV conditions. Copyright © 2025 Alshehri, Zahoor, AlQahtani, Alshahrani, AlHammadi, Jalal and Liu.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Framework for Real-time Oil Spill Detection and Classification 2

A Deep Learning Framework for Real-time Oil Spill Detection ...

引用

2nd Workshop on Artificial Intelligence for Perception and Artificial Consciousness, AIxPAC 2024

作者： Patel, Pranshu Desai, Kedar Jain, Rinkal Bhatt, Chintan Vanlanduit, Steve Bruno, Alessandro Mazzeo, Pier Luigi Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar India InViLab Research Group Universiteit Antwerpen Groenenborgerlaan Antwerpen171 2020 Belgium Department of Business Law Economics and Consumer Behaviour "Carlo A. Ricciardi" IULM AI Laboratory IULM University Milan20143 Italy ISASI Institute of Applied Sciences Intelligent Systems-CNR Lecce73100 Italy

Efficient detection of oil spills is critical for minimizing environmental damage. This study introduces a novel approach utilizing deep learning, specifically the YOLOv8 architecture, augmented with advanced computer vision techniques for oil spill detection. Through meticulous dataset curation and model training, the YOLOv8 model achieved an impressive overall accuracy (R-score) of 0.531 and a Mean Average Precision (mAP) of 0.549. Performance varied across different spill types, with the model demonstrating notable accuracy in distinguishing between oil spills and natural features, achieving precision and recall rates of up to 0.75 and 0.68, respectively, for sheen detection. Visualizations such as box loss, class loss, and confusion matrices provide insights into the model’s performance dynamics, revealing a steady decrease in losses and an improvement in accuracy over epochs. In this dataset, the measurements are drone measurements performed by Port of Antwerp Bruges. Furthermore, practical applications showcase the model’s versatility in detecting various oil spill types in both image and video data, affirming its potential for real-world deployment in environmental monitoring and disaster response scenarios. This research represents a significant stride towards more effective oil spill detection, contributing to environmental sustainability and resilience efforts. © 2024 Copyright for this paper by its authors.

关键词： Oil spills

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of PO, SO and SHO Algorithms for Epileptic Seizer Detection

Performance Evaluation of PO, SO and SHO Algorithms for Epil...

引用

2025 International Conference on Ambient Intelligence in Health Care, ICAIHC 2025

作者： Mohapatra, Sumant Kumar Mallik, Puspanjali Swain, K.P. Bhardwaj, Rajat Mehta, Gaurav Verma, Rajit Trident Academy of Technology Department of Etc Bhubaneswar India Siksha 'O' Anusandhan University Department of Cse Bhubaneswar India Amity University Aset Department of Computer Science and Engineering Bengaluru India Chitkara University School of Engineering and Technology India Mm Institute of Management Mullana Haryana Ambala India

ISBN: (纸本)9798331530259

Diseases originated due to the disorder in the neurons present in the brain part of the body is called epilepsy and the symptom observed in other parts of the body is called a seizure. Not only it is a typical disease in human beings but animals are also suffered from this disease. To live an epilepsy-free life, neurologists and researchers contribute their best effort to devise new techniques and presently metaheuristic optimization algorithms and machine learning algorithms are integrated into this field to design powerful EEG devices for accurately detecting the presence of EEG signals. This research paper presents the comparison of three metaheuristic optimization algorithms used in designing EEG detection. In addition, these three algorithms are integrated with Extreme Learning Adoptive Neuro-Fuzzy-Inference System (ELANFIS) as the classifier and Wavelet Packet Transform as the feature extraction technique. For continuing research work, this experiment uses the Bonn University EEG dataset. After a thorough analysis, it is observed that WPT-PO-ELANFIS is the best-performing technique among these three with average accuracy, sensitivity, specificity, and area under curve values as 98.42, 96.75, 97.97.97.65, and 0.989. This research work also can be tested with other popularly available datasets and integrated with real-time applications. © 2025 IEEE.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Distributed Fusion Estimation for Clustered Sensor Networks with Multi-Scale Fading and Multi-Rate Sampling Characteristics

引用

IEEE Transactions on Control of Network Systems 2025年

作者： Xu, Chenhui He, Defeng Lv, Mingqi Du, Haiping Kang, Yu College of Information Engineering China Zhejiang University of Technology College of Geoinformatics Hangzhou310023 China University of Wollongong School of Electrical Computer and Telecommunications Engineering Wollongong2522 Australia University of Science and Technology of China Automation Department Hefei230026 China

This paper addresses the distributed fusion esti- mation problem of clustered sensor networks with multi-rate sampling and multi-scale fading. An eventtriggered distributed two-stage fusion estimation method is proposed for the clustered sensor network. Specifically, a local fusion estimator is firstly constructed to fuse multirate measurements transmitted through small-scale fading channels. The parameters of the estimator are computed by solving linear matrix inequalities (LMIs). Then, the event trigger mechanism (ETM) is utilized to adjust the transmission frequency of local estimates, aiming to conserve the energy of cluster heads. Furthermore, by solving a min-max optimization problem, a global fusion estimator is designed to fuse the local estimates in the presence of the ETM and large-scale fading channels. Sufficient conditions for the stochastic ultimate boundedness of both local and global estimation errors are derived by leveraging differential game theory and LMIs. The comparison simulation results on a DC-power network show the effectiveness and advantages of the proposed method. © 2014 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Multiple Sclerosis Detection with Reinforcement Learning and Differential Evolution

Multiple Sclerosis Detection with Reinforcement Learning and...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jing Yang Jin Yang Chenwei Wu Gaozhe Jiang Yaning Lv Bingyan Liu Feng Xu Department of Computer System and Technology Universiti Malaya Kuala Lumpur Malaysia Mallinckrodt Institute of Radiology Washington University School of Medicine St. Louis USA Evident Battery Inc. Massachusetts USA Institute of Operations Research and Analytics National University of Singapore Singapore School of Mathematics and Statistics Xi'an University of Electronic Science and Technology Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China School of Engineering and Design Technical University of Munich Munich Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multiple Sclerosis (MS) disrupts nerve communication, potentially leading to permanent damage. Convolutional Neural Networks (CNNs) are commonly recommended to accelerate magnetic resonance imaging (MRI) analysis for MS. Traditional CNN-based methods often face challenges with feature selection, imbalanced classification, and hyperparameter optimization, which can reduce their effectiveness. To address these challenges, this paper introduces a reinforcement learning (RL) strategy for tackling feature selection and class imbalance, complemented by an advanced Differential Evolution (DE) algorithm for hyperparameter tuning. The RL algorithm dynamically adapts, enhancing feature selection and class balance, and consistently outperforms traditional static methods by continually optimizing its response to the complex patterns in MS detection. Furthermore, the DE is enhanced with a novel mutation mechanism that utilizes k-means clustering to identify significant clusters. Tested on the SNAC-MS and ISBI datasets, our model demonstrates robust accuracy with average F-measures of 92.873% and 93.783%, respectively, highlighting its effectiveness and adaptability in diagnosing MS.

关键词： Adaptation models Multiple sclerosis Heuristic algorithms Magnetic resonance imaging Signal processing algorithms Clustering algorithms Reinforcement learning Feature extraction Hyperparameter optimization Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sample Utilization in Noise-robust Deep Metric Learning with Subgroup-based Positive-pair Selection

arXiv

引用

arXiv 2025年

作者： Yu, Zhipeng Xu, Qianqian Jiang, Yangbangyan Sun, Yingfei Huang, Qingming The School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive pairs for noisy samples to enhance the sample utilization. Specifically, SGPS first effectively identifies clean and noisy samples by a probability-based clean sample selectionstrategy. To further utilize the remaining noisy samples, we discover their potential similar samples based on the subgroup information given by a subgroup generation module and then aggregate them into informative positive prototypes for each noisy sample via a positive prototype generation module. Afterward, a new contrastive loss is tailored for the noisy samples with their selected positive pairs. SGPS can be easily integrated into the training process of existing pair-wise DML tasks, like image retrieval and face recognition. Extensive experiments on multiple synthetic and real-world large-scale label noise datasets demonstrate the effectiveness of our proposed method. Without any bells and whistles, our SGPS framework outperforms the state-of-the-art noisy label DML methods. Code is available at https://***/smuelpeng/SGPS-NoiseFreeDML. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Network Coding Techniques for Resource Allocation in Wireless Relay Networks

Network Coding Techniques for Resource Allocation in Wireles...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Lalit Khanna Ranganathaswamy M K Balamurugan V Ankita Agarwal Maharishi Rajat Saini Sarmistha Nanda Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Engineering and Technology Mechanical Engineering JAIN (Deemed to be University) Bangalore Karnataka India Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Applications Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Network coding is an applicable technique to enhance the performance of wireless relay networks, in which intermediate nodes are utilized to expand the coverage range and increase communication reliability. The utilization of network coding in these networks should be well addressed by resource allocation such as bandwidth and power allocation. Among them, network coding for resource allocation in wireless relay networks is the most attractive research work. In particular, dynamic network coding is a strategy that varies how we code data according to current conditions in the network so as to achieve the maximum possible throughput during relaying. Dual-joint power and resource combinations have relatively better performance gains due to the efficient channel gain with an additional level of resource utilization for enhanced resource allocation. In addition, network coding schemes, including opportunistic and homomorphic network coding, have been introduced to perform well in an environment with fading channels and enhance data transmitting reliability. These techniques take advantage of the intrinsic diversity in wireless pathways to improve overall network throughput and reduce latency.

关键词： Wireless communication Fading channels Relay networks Bandwidth Quality of service Network coding Performance gain Throughput Resource management Reliability

来源：评论

学校读者我要写书评

暂无评论

FLeS: A Federated Learning-Enhanced Semantic Communication Framework for Mobile AIGC-Driven Human Digital Twins

引用

IEEE Network 2025年

作者： Okegbile, Samuel D. Gao, Haoran Talabi, Oluwasegun Cai, Jun Yi, Changyan Niyato, Dusit Shen, Xuemin University of the Fraser Valley School of Computing AbbotsfordBCV2S 7M8 Canada Concordia University Department of Electrical and Computer Engineering MontrealQCH3G 1M8 Canada Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Jiangsu Nanjing211106 China Nanyang Technological University College of Computing and Data Science Singapore University of Waterloo Department of Electrical and Computer Engineering Canada

Innovative mobile artificial intelligence-generated content (AIGC) can support the evolution and updating processes of virtual twins (VTs) in human digital twin (HDT) systems. With a reliable and efficient automatic data generation process, the requirement for a timely physical-to-virtual synchronization in HDT can be satisfied. While such an AIGC-enabled HDT system can facilitate modelling high fidelity VTs, generating content that represents the true states in the physical environment and providing timely customized services, it may suffer from a poor understanding of contexts, a lack of creativity, and various security and privacy concerns. In this paper, we propose a novel framework, which integrates federated learning (FL) and semantic communication (SemCom) to enhance performance in the AIGC-enabled HDT system while improving accuracy and convergence properties. First, we present a holistic architectural framework for the proposed FL-enhanced SemCom (FLeS) solution for mobile AIGC-enabled HDT systems and discuss its design requirements and challenges. We later present key technologies necessary to realize the FLeS solution, followed by elaborating on important technical issues to suggest future directions. Experimental results demonstrate that FLeS not only facilitates reliable and personalized content generation but also shows better performance when compared to existing solutions. © 1986-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Accuracy in Used Car Pricing Models: A Comparative Analysis of Regression Techniques 6th

Enhancing Predictive Accuracy in Used Car Pricing Models: A ...

引用

6th International Conference on Advanced Informatics for Computing Research, ICAICR 2023

作者： Chaubey, Ved Prakash Sareen, Devang Harshita, Chanda Sharma, Shamneesh Rana, Rattan Pal Singh Batra, Isha upGrad Campus upGrad Education Private Limited Bangalore India School of Computer Science Engineering and Technology Lovely Professional University Punjab Phagwara India Maharishi Markandeshwar Deemed To Be University Haryana Ambala Mullana India

ISBN: (纸本)9783031840586

The most important aspect aimed to develop a prediction model that could calculate a used car’s fair value based on a variety of factors, including the make, model year, fuel type, price, and miles. This study incorporated a lot of data science and machine learning approaches in the process of developing the model, which has a lot of promise and is available to manufacturers and other players in the used automobile market. The information used in this analysis came from a database of used car advertisements. To provide the best prediction accuracy, several regression techniques were evaluated, including decision tree regression, random forest regression, support vector regression, polynomial regression, and linear regression. To gain a deeper understanding of the data set, the research included substantial preprocessing and data visualization prior to the modeling step. To make it possible to evaluate the performance of each regression model, the data set was divided and modified to satisfy their specifications. The regression models were evaluated using the R-squared statistic. The final model presented in this study contains a wider range of used automobile attributes and provides better prediction accuracy when compared to previous investigations. This research promotes the used car industry and aids in the making of more informed judgments by providing a better model for pricing used cars. The benefits of sound data analysis and a range of regression techniques are used to increase the accuracy of such predictive models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Design of a Microprocessors and Microcontrollers Laboratory Course Addressing Complex engineering Problems and Activities

arXiv

引用

arXiv 2025年

作者： Hafiz, Fahim Emon, Md. Jahidul Hoq Hossain, Abid Mukta, Md. Saddam Hossain Islam, Salekul Shatabda, Swakkhar Department of Computer Science and Engineering United International University Plot-2 United City Madani Avenue Badda Dhaka1212 Bangladesh LUT School of Engineering Sciences Lappeenranta-Lahti University of Technology Yliopistonkatu 34 Lappeenranta53850 Finland Department of Electrical and Computer Engineering North South University Plot # 15 Block B Bashundhara R/A Dhaka1229 Bangladesh Department Computer Science and Engineering BRAC University Kha 224 Bir Uttam Rafiqul Islam Ave Dhaka1212 Bangladesh

Background: Microprocessors and microcontrollers are ubiquitous in modern technology, driving applications across diverse fields. To prepare future engineers for Industry 4.0, effective educational approaches are crucial in this technology. Purpose: This paper proposes a novel curriculum for the microprocessors and microcontrollers laboratory course. The proposed curriculum blends structured laboratory experiments with an open-ended project phase while addressing complex engineering problems and activities. Design: Traditional microprocessors and microcontrollers curricula often fail to capture the complexity of real-world applications encountered in Industry 4.0. This curriculum addresses this gap by incorporating experts’ insights from both industry and academia. It trains students with the necessary skills and knowledge to thrive in this evolving technological landscape, preparing them for success upon graduation. After designing the course, we have taken feedback from the students which showed positive learning curve and experiences regarding this designed curriculum. Results: The proposed lab enables students to perform hands-on experiments using advanced microprocessors and microcontrollers where they can leverage their acquired knowledge by working in teams to tackle self-defined complex engineering problems that utilize these devices and sensors. Statistical analysis shows the proposed curriculum significantly improves student learning outcomes, particularly in their ability to both formulate and solve complex engineering problems as well as engaging in complex engineering activities. Conclusions: This curriculum integrates project-based learning, where students define complex engineering problems for themselves. Additionally, this proposed method fosters multidisciplinary learning and equips students with problem-solving skills that can be applied in real-world scenarios. This approach actively engages students, fostering deeper understanding and enhancing

关键词： Students

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：