检索结果-内蒙古大学图书馆

8th International Conference on Computer Science and Artificial Intelligence, CSAI 2024

作者： Maseno, Elijah Mwandata Wang, Zenghui Sun, Yanxia Department of Computing and Information Technology Mama Ngina University College Gatundu Nairobi Kenya Department of Electrical and Smart Systems Engineering Centre for Augmented Intelligence and Data Science University of South Africa Florida Gauteng South Africa Department of Electrical and Electronic Engineering Science University of Johannesburg Gauteng Johannesburg South Africa

ISBN: (纸本)9798400718182

As Internet of Things (IoT) technology develops so quickly, security issues with IoT devices have come to light. IoT is an array of intelligent devices connected via a network to provide various services. The amount of data generated by these devices has an impact on how well the current intrusion detection systems (IDS) function. The generated dataset consists of irrelevant features which reduces the performance of IDS, making IoT ecosystem vulnerable to cyberattacks. The researchers have suggested the feature reduction technique as a potential solution to the current problem. The proposed method seeks to reduce the feature count by removing the redundant feature subset. Several machine learning methods have been successfully implemented in this discipline. This study proposed the application of hybrid feature reduction technique. The research combined Convolutional neural network (CNN) and Long short-term memory (LSTM);CNN extracted local features and decreased dimensionality, while LSTM identified long-term relationships in the data. SVM and Random Forest classifiers models were used to classify the chosen feature subset. This study employed the TON_IoT Datasets, an up-to-date dataset, to evaluate the model. During data preprocessing, the study applied SMOTETomek data pre-processing technique to address class imbalance in the dataset. With the decreased feature subset, the classification models fared reasonably well;RF had a 98% accuracy rate while SVM had a 91% accuracy rate, showcasing the suggested methodology’s potential for creating efficient IDS. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Monitoring Lightning Activity on a Wind Turbine in Croatia: Observations During Spring and Summer Season

Monitoring Lightning Activity on a Wind Turbine in Croatia: ...

引用

International Colloquium on Smart Grid Metrology (SmaGriMet)

作者： Franjo Vukovic Bozidar Filipovic-Grcic Nina Stipetic Bojan Franc Department of Energy and Power Systems Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9798350357028

ISBN: (纸本)9798350357035

This paper provides an overview of lightning currents measured on a wind turbine in the southern part of Croatia during the summer and spring months in 2023. The wind turbine has been equipped with two Rogowski coils installed at the base of the tower since July 2022. A high-speed camera has been installed since April 2023. In addition, Croatian territory has been covered by a ground-based lightning location system since 2009, and therefore lightning flash data, including amplitude, timing, and polarity, is also available onsite. This paper presents and briefly reviews lightning events by examining current waveforms, high-speed camera frames of the lightning channels and associated luminosity profiles, and lightning location system data. In the considered period, there were 34 lightning flashes. There were 33 upward flashes initiated from the WT blades and only 1 downward flash initiated from the cloud. In terms of polarity, 18 flashes transferred negative charge to the ground, 12 transferred positive charge, and 4 transferred both positive and negative charges (bipolar flashes).

关键词： Reviews Poles and towers Lightning Metrology Cameras Wind turbines Timing Smart grids Springs Monitoring

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Model Benchmarking of Glaucoma Segmentation Using a Novel Ibn Al-Haitham Fundus Image Dataset

Deep Learning-based Model Benchmarking of Glaucoma Segmentat...

引用

2024 International Conference on Smart computing, IoT and Machine Learning, SIML 2024

作者： Zedan, Mohammad J. M. Zulkifley, Mohd Asyraf Saeed, Bashar Ayad Abdani, Siti Raihanah Universiti Kebangsaan Malaysia Electronic and Systems Engineering Department of Electrical Selangor Malaysia Ninevah University Department of Ophthalmology and Surgery Mosul Iraq Universiti Teknologi MARA School of Computing Sciences Shah Alam Malaysia

ISBN: (纸本)9798350364101

Automated fundus image analysis is critical in diagnosing glaucoma, whereby the optic nerve areas that consist of optic discs and cups need to be precisely mapped, which is a process that requires considerable effort and time. Generally, the application of Artificial intelligence (AI) has made considerable advancements in the fundus imaging-based automated diagnosis of various diseases. Training and assessing the best AI models for glaucoma detection demands a large number of expert-annotated fundus images. However, there is a scarcity of freely available datasets tailored to this need, and even those that are accessible have several constraints, especially for the Middle Eastern country cases. This paper introduces a novel fundus image dataset of 3000 high-resolution, manually annotated color fundus images dedicated to boosting AI-based models for optic disc and cup segmentation. The annotation process was standardized through collaboration among medical experts, ensuring consistent and reliable results. The reliability of each image was assessed using four deep learning-based segmentation models: U-Net, SegNet, FCDenseNet, and PSPNet. The SegNet model outperformed the others, with an accuracy of 98.12%, specificity of 96.35%, and sensitivity of 98.7% for the optic disc and an accuracy of 97%, specificity of 95.4%, and sensitivity of 91.94% for the optic cup. These results not only validate the accuracy of the developed dataset but also demonstrate its potential in advancing disease detection methods, particularly in AI-assisted ophthalmology, leading to new opportunities for advancements in this field. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Design and Control of a Two-Phase Interleaved DC-DC Boost Converter with Constant Power Load for More Electric Aircraft

Design and Control of a Two-Phase Interleaved DC-DC Boost Co...

引用

International Colloquium on Smart Grid Metrology (SmaGriMet)

作者： Milad Andalibi Mario Vašak Laboratory for Renewable Energy Systems University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia

ISBN: (数字)9798350357028

ISBN: (纸本)9798350357035

In this study, a two-phase interleaved synchronous DC-DC boost converter with a CPL (constant power load) in an MEA (more electric aircraft) system was extracted and analyzed. In addition, a backstepping control based on the extracted model is created to assure the system's stability when tracking the required bus voltage in the MEAs. The demand for stable and efficient power converters capable of supplying CPLs in MEA microgrids is growing as aviation shifts from traditional to more electric systems to boost efficiency. The design in this paper is intended to increase power density, improve thermal performance, and reduce current ripple to reduce energy losses. Other criteria such as reliability and efficiency are also considered in the design. In this study, MATLAB simulation was used to analyze the behavior of the converter, the proposed model, and the controller. The results show that by combining the advantages of accurate modeling with interleaved topologies, this method provides a suitable reliable power conversion solution and reliable control for MEA systems. This study contributes to MEA technology by presenting a realistic and high-performance solution that meets the critical requirements for efficiency, dependability, and cost-effectiveness.

关键词： Stability criteria Power system dynamics Power system stability Aerospace electronics Power system reliability Topology Voltage control Aircraft Thermal stability Aerospace control

来源：评论

学校读者我要写书评

暂无评论

Exploring Highly Quantised Neural Networks for Intrusion Detection in Automotive CAN

arXiv

引用

arXiv 2024年

作者： Khandelwal, Shashwat Shreejith, Shanker Reconfigurable Computing Systems Lab Electronic & Electrical Engineering Trinity College Dublin Ireland

Vehicles today comprise intelligent systems like connected autonomous driving and advanced driving assistance systems (ADAS) to enhance the driving experience, which is enabled through increased connectivity to infrastructure and fusion of information from different sensing modes. However, the rising connectivity coupled with the legacy network architecture within vehicles can be exploited for launching active and passive attacks on critical vehicle systems and directly affecting the safety of passengers. Machine learning-based intrusion detection models have been shown to successfully detect multiple targeted attack vectors in recent literature, whose deployments are enabled through quantised neural networks targeting low-power platforms. Multiple models are often required to simultaneously detect multiple attack vectors, increasing the area, (resource) cost, and energy consumption. In this paper, we present a case for utilising custom-quantised MLP's (CQMLP) as a multi-class classification model, capable of detecting multiple attacks from the benign flow of controller area network (CAN) messages. The specific quantisation and neural architecture are determined through a joint design space exploration, resulting in our choice of the 2-bit precision and the n-layer MLP. Our 2-bit version is trained using Brevitas and optimised as a dataflow hardware model through the FINN toolflow from AMD/Xilinx, targeting an XCZU7EV device. We show that the 2-bit CQMLP model, when integrated as the IDS, can detect malicious attack messages (DoS, fuzzing, and spoofing attack) with a very high accuracy of 99.9%, on par with the state-of-the-art methods in the literature. Furthermore, the dataflow model can perform line rate detection at a latency of 0.11 ms from message reception while consuming 0.23 mJ/inference, making it ideally suited for integration with an ECU in critical CAN networks. © 2024, CC BY.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer 41

WISER: Weak Supervision and Supervised Representation Learni...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Shubham, Kumar Jayagopal, Aishwarya Danish, Syed Mohammed Prathosh, A.P. Rajan, Vaibhav Department of Electrical Communication Engineering Indian Institute of Science Karnataka Bengaluru India Department of Information Systems and Analytics School of Computing National University of Singapore Singapore Indian Institute of Technology Bihar Patna India

Cancer, a leading cause of death globally, occurs due to genomic changes and manifests heterogeneously across patients. To advance research on personalized treatment strategies, the effectiveness of various drugs on cells derived from cancers (‘cell lines') is experimentally determined in laboratory settings. Nevertheless, variations in the distribution of genomic data and drug responses between cell lines and humans arise due to biological and environmental differences. Moreover, while genomic profiles of many cancer patients are readily available, the scarcity of corresponding drug response data limits the ability to train machine learning models that can predict drug response in patients effectively. Recent cancer drug response prediction methods have largely followed the paradigm of unsupervised domain-invariant representation learning followed by a downstream drug response classification step. Introducing supervision in both stages is challenging due to heterogeneous patient response to drugs and limited drug response data. This paper addresses these challenges through a novel representation learning method in the first phase and weak supervision in the second. Experimental results on real patient data demonstrate the efficacy of our method WISER (Weak supervISion and supErvised Representation learning) over state-of-the-art alternatives on predicting personalized drug response. Our implementation is available at https://***/kyrs/WISER. Copyright 2024 by the author(s)

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Quantised Neural Network Accelerators for Low-Power IDS in Automotive Networks

arXiv

引用

arXiv 2024年

作者： Khandelwal, Shashwat Walsh, Anneliese Shreejith, Shanker Reconfigurable Computing Systems Lab Electronic & Electrical Engineering Trinity College Dublin Ireland

In this paper, we explore low-power custom quantised Multi-Layer Perceptrons (MLPs) as an Intrusion Detection System (IDS) for automotive controller area network (CAN). We utilise the FINN framework from AMD/Xilinx to quantise, train and generate hardware IP of our MLP to detect denial of service (DoS) and fuzzying attacks on CAN network, using ZCU104 (XCZU7EV) FPGA as our target ECU architecture with integrated IDS capabilities. Our approach achieves significant improvements in latency (0.12 ms per-message processing latency) and inference energy consumption (0.25 mJ per inference) while achieving similar classification performance as state-of-the-art approaches in the literature. © 2024, CC BY.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Improving Performance of Recurrent Neural Networks Using Simulated Annealing for Vertical Wind Speed Estimation

引用

Energy engineering 2023年第4期120卷 775-789页

作者： Shafiqur Rehman HilalH.Nuha Ali Al Shaikhi Satria Akbar Mohamed Mohandes Interdisciplinary Research Center for Renewable Energy and Power Systems(IRC-REPS) KFUPMDhahran31261Saudi Arabia HUMIC Engineering School of ComputingTelkom UniversityBandung40257Indonesia Electrical Engineering Department King Fahd University of Petroleum&Minerals(KFUPM)Dhahran31261Saudi Arabia

An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm *** general,the vertical extrapolation of WS at different heights must consider different parameters fromdifferent locations,such as wind shear coefficient,roughness length,and atmospheric *** novelty presented in this article is the introduction of two steps optimization for the Recurrent Neural Networks(RNN)model to estimate WS at different heights using measurements from lower *** first optimization of the RNN is performed to minimize a differentiable cost function,namely,mean squared error(MSE),using the Broyden-Fletcher-Goldfarb-Shanno ***,the RNN is optimized to reduce a non-differentiable cost function using simulated annealing(RNN-SA),namely mean absolute error(MAE).Estimation ofWS vertically at 50 m height is done by training RNN-SA with the actualWS data a 10–40 m *** estimatedWS at height of 50 m and the measured WS at 10–40 heights are further used to train RNN-SA to obtain WS at 60 m *** procedure is repeated continuously until theWS is estimated at a height of 180 *** RNN-SA performance is compared with the standard RNN,Multilayer Perceptron(MLP),Support Vector Machine(SVM),and state of the art methods like convolutional neural networks(CNN)and long short-term memory(LSTM)networks to extrapolate theWS *** estimated values are also compared with realWS dataset acquired using LiDAR and tested using four error metrics namely,mean squared error(MSE),mean absolute percentage error(MAPE),mean bias error(MBE),and coefficient of determination(R2).The numerical experimental results show that the MSE values between the estimated and actualWS at 180mheight for the RNN-SA,RNN,MLP,and SVM methods are found to be 2.09,2.12,2.37,and 2.63,respectively.

关键词： Vertical wind speed estimation recurrent neural networks simulated annealing multilayer perceptron support vector machine

来源：评论

学校读者我要写书评

暂无评论

Real-time zero-day Intrusion Detection System for Automotive Controller Area Network on FPGAs

arXiv

引用

arXiv 2024年

作者： Khandelwal, Shashwat Shreejith, Shanker Reconfigurable Computing Systems Lab Electronic & Electrical Engineering Trinity College Dublin Ireland

Increasing automation in vehicles enabled by increased connectivity to the outside world has exposed vulnerabilities in previously siloed automotive networks like controller area networks (CAN). Attributes of CAN such as broadcast-based communication among electronic control units (ECUs) that lowered deployment costs are now being exploited to carry out active injection attacks like denial of service (DoS), fuzzing, and spoofing attacks. Research literature has proposed multiple supervised machine learning models deployed as Intrusion detection systems (IDSs) to detect such malicious activity;however, these are largely limited to identifying previously known attack vectors. With the ever-increasing complexity of active injection attacks, detecting zero-day (novel) attacks in these networks in real-time (to prevent propagation) becomes a problem of particular interest. This paper presents an unsupervised-learning-based convolutional autoencoder architecture for detecting zero-day attacks, which is trained only on benign (attack-free) CAN messages. We quantise the model using Vitis-AI tools from AMD/Xilinx targeting a resource-constrained Zynq Ultrascale platform as our IDS-ECU system for integration. The proposed model successfully achieves equal or higher classification accuracy (> 99.5%) on unseen DoS, fuzzing, and spoofing attacks from a publicly available attack dataset when compared to the state-of-the-art unsupervised learning-based IDSs. Additionally, by cleverly overlapping IDS operation on a window of CAN messages with the reception, the model is able to meet line-rate detection (0.43 ms per window) of high-speed CAN, which when coupled with the low energy consumption per inference, makes this architecture ideally suited for detecting zero-day attacks on critical CAN networks. © 2024, CC BY.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

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：