检索结果-内蒙古大学图书馆

Moth flame optimization algorithm for efficient feature selection and hybrid classification technique for intrusion detection system

引用

Multimedia Tools and Applications 2025年 1-21页

作者： Keerthanarani, U. Selvakumar, V. Singaravelan, S. Raja, S. Edwin Thenmozhi, K. Shunmugam, D. Arun Dept. of Computer Science and Engineering P.S.R Engineering College Sivakasi India Dept.Of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai Avadi India Dept. Of Computer Science and Engineering Coimbatore Institute of Engineering and Technology Coimbatore India Dept. Of Electronics and Communication Engineering P.S.R Engineering College Sivakasi India

The rapid expansion of the Internet of Things (IoT) brings numerous benefits but further presents fresh difficulties, especially in terms of security. The distributed and interconnected nature of IoT devices makes them susceptible to various security threats. An Intrusion Detection System (IDS) plays a crucial role in safeguarding IoT networks by monitoring, detecting, and responding to potential security incidents. The Internet of Things (IoT) connects billions of devices, sensors, and systems, transforming industries and everyday life. However, this extensive interconnectivity also introduces significant security risks, making Intrusion Detection Systems (IDS) a critical component for safeguarding IoT environments. Feature selection is a crucial aspect of building effective Intrusion Detection Systems (IDS). Selecting relevant features not only helps in achieving better classification accuracy but also contributes to reducing false alarm rates. In the proposed system a moth flame optimizer is utilized to select the efficient features from the dataset, overall accuracy of over 97%. Further it is classified employing Random Forest and J48 classifier which attains high classification accuracy and low false alarm rate. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Development of a Reinforcement Learning-Based Control Education Platform Using Python and LW-RCP

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第1期74卷 118-126页

作者： Lee, Jongbeom Lee, Taegun Ju, Doyoon Sam Lee, Young Dept. of Electrical and Computer Engineering Inha University Incheon Korea Republic of

This paper proposes a reinforcement learning-based control education platform utilizing Python and light-weight rapid control prototyping (LW-RCP). The platform employs the Sim-to-Real technique, in which neural networks are trained in a Python-based simulation environment and applied to real systems. The trained networks are converted into a format compatible with Matlab/Simulink. The lab-built LW-RCP is used to implement a real-time controller under the Simulink environment by incorporating the converted networks. The proposed platform allows students to easily apply reinforcement learning theory to real systems, contributing to the integration of reinforcement learning control into control curriculum. The effectiveness of the proposed platform is demonstrated by implementing a reinforcement learning controller for the pendubot system. The implemented controller performs the swing-up and transition control and exhibits strong disturbance rejection and recovery properties. © 2025 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Statistical Thresholding of Ultrasonic Amplitude Maps for Automated Damage Segmentation

引用

Journal of Aeronautics, Astronautics and Aviation 2025年第3期57卷 319-327页

作者： Yn, Lee Shi Zaludin, Zairil Harley, Joel B. Lee, Jung-Ryul Harmin, Mohammad Yazdi Ciang, Chia Chen Dept. of Aerospace Engineering Universiti Putra Malaysia Selangor Serdang43400 Malaysia Dept. of Electrical and Computer Engineering University of Florida Florida United States Dept. of Aerospace Engineering KAIST Daejeon Korea Republic of

Amplitude maps generated by ultrasound imaging are frequently utilized to visualize invisible damages in thin-walled aero-mechanical structures. Accurate evaluation of damage size from these maps is crucial;however, a reliable automated method for this purpose under the influence of imaging noise is not available. To address this issue, four threshold calculation methods based on statistical analysis of noise content in an amplitude map were developed. These candidates were numerically optimized using amplitude maps containing damages of various sizes and Gaussian noise of differing intensities. The candidate demonstrating the greatest immunity to parameter variations and the highest potential for accurate damage size evaluation was identified. This candidate was then parametrically optimized and benchmarked against k-means clustering. The results demonstrate that the newly proposed statistical thresholding method outperformed k-means clustering, consistently providing high accuracy above 99% even for damages as small as 2 mm and signal-to-noise ratios (SNR) as low as 3 dB. © 2025 The Aeronautical and Astronautical Society of the Republic of China. All rights reserved.

关键词： Thin walled structures

来源：评论

学校读者我要写书评

暂无评论

A Study on Verification of Sewage Treatment Expert Operating Experience Using RNN

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第4期74卷 691-699页

作者： Nahm, Eui-Seok Dept. of AI Computer Engineering Far East University Korea Republic of

In this paper, we proposed a data quality and diversity guarantee plan and a method to verify the expert operation experience using RNN and a data quality and diversity guarantee plan to 1) solve the two problems of the sewage treatment expert driving experience and 2) the limitation of situation recognition and judgment. As a solution to the lack of data quality and diversity, not all data are used, but a method of filtering and using only the part that is the basis for determining the expert's experience was proposed. In addition, RNN was used to solve the problem of the limitation of situation recognition and judgment. The reason why RNN is used among various neural networks is that RNN is a neural network architecture for deep learning that predicts time series or sequential data, and sewage treatment data is also time series or sequential data. According to the proposed technique, a RNN model with a reliability of more than 8% was implemented, and the effectiveness of the proposed technique was verified by applying two experiences and one incorrect experience of actual operation experts of the target sewage treatment plant. As a result of the verification, both the actual driving expert's experiences 1 and 2 were verified as valid, and for incorrect experiences, there were 3,442 data that matched the expert's experience and 4,444 data that did not match, so the proposed method can verify the expert's experience. © The Korean Institute of Electrical Engineers.

关键词： Sewage treatment plants

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Optimizing relay node placement and routing in WBANs using free search krill herd and harmony search algorithm

引用

Multimedia Tools and Applications 2025年第10期84卷 7257-7295页

作者： Patra, Sushree Chinmayee Samal, Tusharkanta Kabat, Manas Ranjan Mishra, Manas Ranjan Barik, Ram Chandra Dept. of Computer Sc. & Engineering Veer Surendra Sai University of Technology Odisha Sambalpur India Dept. of Computer Sc. & Engineering DRIEMS University Odisha Cuttack India Dept. of Computer Sc. & Engineering C.V. Raman Global University Odisha Bhubaneswar India

Wireless Body Area Network (WBAN) plays an important role in healthcare applications like in medical, non-medical and psychological sector for remote monitoring of health conditions of patients. Since the biosensors in WBAN are energy constrained in nature, the architecture of energy efficient and cost sensitive WBAN has attracted the researchers during the last decade. In this paper, a mathematical model for optimization of relay node placement in WBAN using Free Search Krill Herd (FSKH) algorithm because of its diversified phases of searching has been proposed. Furthermore, a routing protocol for energy efficient and reliable for data transmission over WBAN by using Harmony Search (HS) algorithm has been designed. The proposed algorithm has less 11.02%, 6.8% energy consumption in standing position, 5.6% and 11.02% in siting position and 12.5% and 18.75% siting on chair than its counterparts EAWD and Modified EAWD. Throughput has increased significantly by approximately 4–5 times as compare to iM-SIMPLE and *** proposed methodology has also shown greater improvement as its first node is completely exhausted after 28,545 rounds of data transmission while its existing counterpart’s iM-SIMPLE and Co-LAEEBA first node dies at 5100 rounds and 6800 rounds of transmission respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

A High Power Density Active-Clamp Forward-Flyback Converter with Three Planar Transformer for xEV Low Voltage DC-DC Converter

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第3期74卷 468-476页

作者： Kwon, Gyeonghyun Lee, Dongin Jeong, Seongwook Jeong, Yeonho Youn, Hanshin Dept. of Electrical Engineering Incheon National University Korea Republic of Dept. of Electrical Computer and Biomedical Engineering University of Rhode Island KingstonRI United States

This paper proposes an Active-Clamp Forward-Flyback (ACFF) converter with three planar transformers to achieve 4 kW output power. As autonomous driving technology rapidly advances, the demand for higher output power from low-voltage DC-DC converters (LDC) in electric vehicles has significantly increased. Conventionally, two 2 kW ACFF converters with four magnetic cores connected in series-parallel have been used to meet 4 kW power requirement, but this configuration has proven inefficient in terms of size, power density, and cost. The proposed converter improves power density by integrating the four magnetic cores of the conventional 4 kW ACFF converter into three, reducing the overall magnetic volume and allowing for a more compact design. Furthermore, the use of planar magnetic components enables the winding to be embedded in a 4-layer PCB. Copyright © The Korean Institute of Electrical Engineers.

关键词： High frequency transformers

来源：评论

学校读者我要写书评

暂无评论

Improved Object Detection Through a Learning-Based Joint-Initiative Supervised Autonomy (JISA) Framework

Improved Object Detection Through a Learning-Based Joint-Ini...

引用

2025 International Conference on Control, Automation, and Instrumentation, IC2AI 2025

作者： Tarabay, Andrea Daher, Naseem American University of Beirut Dept. of Electrical and Computer Engineering Beirut Lebanon American University of Beirut Dept. of Electrical and Computer Engineering Dept. of Mechanical Engineering Beirut Lebanon

ISBN: (纸本)9798331529604

Object detection is faced with accuracy and robustness limitations due to unstructured environments with objects of different sizes and occlusions. Despite advancements in object detection models, these models have not reached a point to possess a comparable level of perception to humans, thus limiting their ability to effectively address challenges in diverse environments. Hence, adopting a human-in-the-loop approach in autonomous systems can handle complex perception scenarios. To tackle these issues, the Joint-Initiative Supervised Autonomy (JISA) framework is used to allow a human supervisor to intervene once the agent is uncertain of its predictions based on its self-confidence (SC) metric, or when the human deems the prediction incorrect based on his/her situation awareness (SA). However, the existing JISA framework formally defines the levels of autonomy between the human and the agent, but does not provide a means for learning from human interventions. In this paper, we present an enhanced version of JISA in object detection applications by implementing a learning scheme that is inspired by the Interactive Corrections and Reinforcement for an Epistemic and Aleatoric uncertainty-aware Teaching (ICREATe) algorithm. To address these challenges, we evaluate the results of the proposed framework and demonstrate that the model effectively learns and improves its performance through human feedback. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multispectral Images and IoT Based Tea Plantation Monitoring: A Proposed System Architecture 5

Multispectral Images and IoT Based Tea Plantation Monitoring...

引用

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Kariyawasam, K.P.W.D.V. Kahandagamage, P.N. Fernando, M.R.R. Fernandopulle, J.M. Jayasinghearachchi, Vishan Dissanayaka, Kapila Dept. of Software Engineering Sri Lanka Dept. of Information Technology Sri Lanka Dept. of Computer Science Sri Lanka

ISBN: (纸本)9798331530983

In recent years, the Sri Lankan tea industry has fallen behind its competitors in the global tea market. This decline is caused by the challenges in productivity and resource management due to the limitations of traditional crop monitoring methods. This study presents a prototype system architecture that integrates multispectral imagery and IoT technologies to enhance plantation monitoring. The proposed system uses drones to capture high-resolution multispectral images and IoT devices to collect real-time environmental data, providing a comprehensive approach to assessing plant yield and detecting stress. Built on a hexagonal architecture, the system emphasizes modularity, reliability, and scalability by ensuring a clear separation of core functionalities from external components. This design facilitates easy adaptation to various crop types and agricultural contexts, enabling flexibility in deployment and use. This flexible framework can serve as a blueprint for improving decision-making and management practices across diverse plantation environments. © 2025 IEEE.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

GolfPoseNet: Golf-Specific 3D Human Pose Estimation Network

GolfPoseNet: Golf-Specific 3D Human Pose Estimation Network

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Park, BoJeong Kim, JongWoo Mun, SeoYeong Choi, Younglim Kim, Hyunseok Dong-A University Dept. of Electric Engineering Busan Korea Republic of Dong-A University Dept. of Software Innovation Center Busan Korea Republic of Dong-A University Dept. of Computer Engineering Busan Korea Republic of

ISBN: (纸本)9798331510756

This paper aims to develop a robotic golf trainer using a wheeled robot and create a model that accurately recognizes the user's golf motion. Since existing 3D pose models show limitations in golf motion recognition [1], [2], we propose an optimized recognition model by combining various methods and preprocessing golf datasets to overcome these problems. We used HRNet to estimate 2D pose from video frames and fed these data into a transformer-based model to generate three hypotheses through residual linking and embedding layers. These were integrated to finally design a structure to predict 3D pose, and batch normalization, dropout, and LeakyReLU were used to improve the stability and nonlinearity handling of the model. Experimental results show that the proposed model effectively learns temporal information from multi-view 2D pose data without 3D annotation and performs well even when 3D data is scarce. The proposed method can be used in various applications such as human-robot interaction and sports motion analysis including golf, and further research on multiple datasets and real-world environments is expected to improve further and generalize the model's performance. © 2025 IEEE.

关键词： Human robot interaction

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：