检索结果-内蒙古大学图书馆

MILCOM, Military communications Conference

作者： Johannes F. Loevenich Philipp Zißner Paulo H. L. Rettore Jonas Bode Tobias Hürten Thorsten Lampe Roberto Rigolin F. Lopes Secure Communications & Information (SIX) Thales Deutschland Ditzingen Germany Department of Mathematics/Computer Science University of Osnabrück Osnabrück Germany Communication Systems (KOM) Fraunhofer FKIE Bonn Germany

This paper presents a cooperative agent system employing Reinforcement Learning (RL) to quantify path robustness in tactical networks. We implement an environment builder agent generating network graphs with dynamic topologies, constrained by tactical network characteristics and conditions derived from experimental results using real military radios (VHF). Subsequently, the RL agent interacts with this environment, learning to quantify the robustness of feasible transmission paths by solving an optimal control problem. Furthermore, we propose an adversary to evaluate the RL agent’s robustness against adversarial perturbations. Experiments across a large set of network graphs reveal that policy optimization algorithms (PPO and TRPO) outperform others (ARS, DQN and A2C), demonstrating high rewards (∼105) in the absence of adversaries. However, when assessing performance in scenarios with adversarial noise injection, experimental results indicate that iterative, and momentum boosting attack techniques can substantially degrade the RL model’s performance by up to 300% lower rewards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Binocular Disparity Unveils the Mechanisms of Stereo Feature Selectivity: Orientation and Motion

Binocular Disparity Unveils the Mechanisms of Stereo Feature...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Bin Li Yuki Todo Zheng Tang Cheng Tang Division of Electrical Engineering and Computer Science Kanazawa University Kanazawa Japan Division of Electrical Information and Communication Engineering Kanazawa University Kanazawa Japan Department of Intelligence Information Systems University of Toyama Toyama Japan Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Binocular vision serves as the foundation for stereo vision, providing humans with the ability to perceive the three-dimensional information of their surroundings. However, although some cortical neurons are reported with 3D information selectivity, the interconnections between binocular input and cortical neuron firing have yet to be fully established, impeding progress in our understanding of stereo information perception. In this work, we aim to address this issue by examining the causality between retinal input and selective neuron firing. We propose a general mechanism of stereo orientation and motion direction detection based solely on binocular disparity input, which is the difference in visual information between the two eyes. Our results suggest that this disparity-based mechanism is robust and can effectively complete stereo orientation and motion direction detection. Our proposed general perceiving mechanism has the potential to contribute to the resolution of the complex problem of binocular information processing and computation. Further research into this area may help to deepen our understanding of stereo vision and provide insights into the underlying neural mechanisms.

关键词： Visualization Three-dimensional displays Firing Neurons Noise Reliability theory Retina

来源：评论

学校读者我要写书评

暂无评论

Hybrid Near-Far Field Channel Estimation for Holographic MIMO communications

arXiv

引用

arXiv 2024年

作者： Yue, Shaohua Zeng, Shuhao Liu, Liang Eldar, Yonina C. Di, Boya The State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China The Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

Holographic MIMO communications, enabled by large-scale antenna arrays with quasi-continuous apertures, is a potential technology for spectrum efficiency improvement. However, the increased antenna aperture size extends the range of the Fresnel region, leading to a hybrid near-far field communication mode. The users and scatterers randomly lie in near-field and far-field zones, and thus, conventional far-field-only and near-field-only channel estimation methods may not work. To tackle this challenge, we demonstrate the existence of the power diffusion (PD) effect, which leads to a mismatch between the hybrid-field channel and existing channel estimation methods. Specifically, in far-field and near-field transform domains, the power gain of one channel path may diffuse to other positions, thus generating fake paths. This renders the conventional techniques unable to detect those real paths. We propose a PD-aware orthogonal matching pursuit algorithm to eliminate the influence of the PD effect by identifying the PD range, within which paths diffuse to other positions. PD-OMP fits a general case without prior knowledge of near-field and far-field path numbers and the user’s location. The computational complexity of PD-OMP and the Cramér-Rao Lower Bound for the sparse-signal-recovery-based channel estimation are also derived. Simulation results show that PD-OMP outperforms state-of-the-art hybrid-field channel estimation methods. © 2024, CC BY-NC-ND.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Thick Film Interdigitated Electrode Graphite and Carbon Nanotube on Flexible Substrate for Hydrogen Gas Detection

Thick Film Interdigitated Electrode Graphite and Carbon Nano...

引用

2023 IEEE International Conference on Sensors and Nanotechnology, SENNANO 2023

作者： Abu Bakar, Azlinda Nizar Hamidon, Mohd Yaacob, Mohd Hanif Paiman, Suriati Jaafar, Haslina Wan Jusoh, Wan Nursheila Universiti Putra Malaysia Funtional Device Laboratory Institute of Nanoscience and Nanotechnology Selangor Serdang Malaysia Universiti Putra Malaysia Faculty of Engineering Department of Computer and Communication Systems Selangor Serdang Malaysia Universiti Putra Malaysia Faculty of Science Department of Physics Selangor Serdang Malaysia Universiti Putra Malaysia Faculty of Engineering Department of Electrical and Electronic Selangor Serdang Malaysia Universiti Kuala Lumpur Section of Aerospace Malaysians Institute of Aviation Technology Selangor Dengkil Malaysia

ISBN: (纸本)9798350333312

The comparison on the performance of interdigitated electrode (IDE) graphite and carbon nanotube (CNT) using titanium dioxide-multiwall carbon nanotube (TiO2-MWCNT) composite as sensing materials to detect hydrogen gas is presented in this research work. Screen printing technique has been selected to deposited IDE graphite and CNT conductive pastes as the electrode thick film on a flexible substrate, which is continued by firing at 120°C each. TiO2-MWCNT paste was printed as a sensing layer on top of IDE, followed by firing at 350°C. FESEM was used to characterize the morphological analysis of the IDE film. The operating temperature was varied at 27°C, 50°C and 100°C and concentration varied from 100-1000 ppm for gas hydrogen. The gas sensor demonstrated as n-type gas characteristics where the response of the gas sensor produced increased current from the results. The results purpose when the sensor was exposed to hydrogen gas. Therefore, the ability of IDE graphite and CNT as an electrode to harvest the electron from sensing materials were successfully proven. The IDE CNT showed better response compare to IDE graphite, but both electrodes were able to sense 100 - 1000 ppm at the operating temperature of 27°C, 50°C and 100°C. The optimal of operating temperature for IDE graphite is 50°C and IDE CNT is at room temperature for the hydrogen gas detections in this research work. © 2023 IEEE.

关键词： Thick films

来源：评论

学校读者我要写书评

暂无评论

Development of an Artificial Intelligence-Based Prediction System for Short-Term Solar Power Generation

Development of an Artificial Intelligence-Based Prediction S...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Minseok Kang Suhyeon Choi Woohyun Kim Jaehyeon Kim Seokheon Cho Department of Computer Science Yonsei University Seoul Republic of Korea Department of Management Information Systems Kyonggi University Suwon Republic of Korea Department of Information and Communication Chosun University Gwangju Republic of Korea Department of Business Chosun University Gwangju Republic of Korea Qualcomm Institute University of California San Diego La Jolla USA

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The increased occurrence of extreme weather events is closely related to global warming caused by excessive fossil fuel consumption. This has resulted in significant global interest in renewable energy sources, especially solar power, which is showing rapid growth worldwide. However, the excessive and disorganized utilization of solar power systems can cause instability of the existing power system because of a continuous time varying output of solar power systems. Hence, it is crucial to accurately predict the solar power generation for a stable energy supply to the traditional electricity system. This study aims to provide a short-term solar power generation prediction model based on various Artificial Intelligence algorithms and improve its performance. The Multiple Linear Regression, Random Forest Regression, Multi-Layer Perceptron and Long Short-Term Memory algorithms were utilized for a solar power generation prediction model. Also, solar power-related data measured every 15 minutes and hourly meteorological data were used to train and evaluate our proposed prediction models. Several datasets generated by the feature selection process and the addition of the historical solar power-related data as well as the historical weather data were used to enhance a short-term solar power generation prediction model. The comparison of performance results showed that the Multi-Layer Perceptron algorithm-based prediction model using the solar power-related data and the weather data as well as their past data outperforms by achieving the highest value of R-squared $(\mathrm{R}^{2})$ but the lowest value of the Root Mean Squared Error. An architecture of an Artificial Intelligence-based solar power prediction system embedded with this optimal short-term solar power prediction model is proposed.

关键词： Renewable energy sources Predictive models Power system stability Prediction algorithms Data models Solar power generation Random forests Long short term memory Meteorology Load modeling Climate change

来源：评论

学校读者我要写书评

暂无评论

Estimating the AGV load and a battery lifetime based on the current measurement and random forest application

Estimating the AGV load and a battery lifetime based on the ...

引用

IEEE International Conference on Big Data

作者： Krzysztof Hanzel Damian Grzechca Adam Ziebinski Lukas Chruszczyk Artur Janus Department of Telecommunications and Teleinformatics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Electronics Electrical Engineering and Microelectronics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Distributed Systems and Informatics Devices Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Student of Electrical Engineering Faculty of Electrical Engineering Silesian University of Technology Gliwice Poland

The paper describes the energy consumption from the battery based on the current measurements for various cases, i.e., speed (PWL adjustment) and loads. The main purpose of the research is to have additional and reliable information about power consumption and battery life estimation for autonomous guided vehicles (AGV). The authors propose a two-step algorithm. In the first step, a linear classifier was proposed. Then, the KNN classifier was tested; however, it did not give satisfactory results, so it was finally decided to use the random forest to estimate the load and PWL. The time domain current measurement is evaluated, and the beforementioned algorithms process the selected statistical measures. It has been proven that a two-step algorithm allows for achieving high accuracy. Based on the current observation, the paper is a good starting point for further investigation of the AGV because it is usually implemented in the AGV – so it does not require additional hardware. Moreover, it can lead to better energy management and increase battery lifetime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accuracy Evaluation of Stereo Visual SLAM with Unnecessary Feature Point Elimination Using Blur Processing for AR Surgical Support System

Accuracy Evaluation of Stereo Visual SLAM with Unnecessary F...

引用

International Conference on Intelligent Informatics and Biomedical sciences (ICIIBMS)

作者： Masanao Koeda Yuto Kaihara Atsuro Sawada Akihiro Hamada Toshihiro Magaribuchi Osamu Ogawa Katsuhiko Onishi Hiroshi Noborio Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama Japan Department of Urology Graduate School of Medicine Kyoto University Kyoto Japan Faculty of Information Science and Arts Osaka Electro-Communication University Osaka Japan

In this study, we describe an evaluation of the positional accuracy of stereo Visual SLAM with noisy feature points removed by blurring. We constructed an experimental environment that intentionally degrades the accuracy of Visual SLAM. In this environment, we placed the objects that are likely to generate noisy feature points. We evaluated the accuracy of the estimated positions of the original video and the video in which blurred regions of noise in the original video were provided to Visual SLAM. Consequently, we confirmed that the accuracy was improved compared to that of the original video.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Malicious Traffic Classification Methods based on Semi-supervised Learning 9

Efficient Malicious Traffic Classification Methods based on ...

引用

9th International Conference on Dependable systems and Their Applications, DSA 2022

作者： Hu, Xiaoyi Ning, Jinhui Yin, Jie Yang, Jie Adebisi, Bamidele Gacanin, Haris College of Telecommunications and Information Engineering Njupt Nanjing China Jiangsu Police Institute Department of Computer Information and Cyber Security Nanjing China Manchester Metropolitan University Faculty of Science and Engineering Manchester United Kingdom Institute for Communication Technologies and Embedded Systems Rwth Aachen University Aachen Germany

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

The proliferation of mobile communication systems, arrival of high-speed broadband networks and more complex network topologies have exacerbated cyber-threats. Cyber-warfare has become an aspect of modern war-fare that can no longer be overlooked. In recent years, network intrusions launched using the Internet have seriously undermined the security systems of many nations. Classifying malicious network traffic is the first step in network intrusion detection. In this paper, we propose three models using semi-supervised learning-based malicious traffic classification (MTC) methods that effectively improve the classification of traffic using a small proportion of labeled traffic data. Employing three different deep neural networks as feature extraction networks respectively, the proposed models use transductive transfer learning and domain adaptive ideas, and ladder networks as classification layers. Experimental results are provided to validate the proposed methods. © 2022 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Open-Ended Coaxial Probe Based Chloride Concentration Prediction in Water Using Machine Learning Algorithms

Open-Ended Coaxial Probe Based Chloride Concentration Predic...

引用

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Hanima Kannan C H Veena Venugopal Deepa Gupta Parul Mathur Dhanesh G Kurup Priyanka Mathur Department of Electronics and Communication Engineering RF and Wireless Systems Laboratory Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Physical Science Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India School of Engineering and Applied Science Benette University Greater Noida UP India

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

Monitoring chloride levels in water is essential for environmental health, industrial processes, and safe drinking water, as both high and low concentrations can cause harm for living being. This paper presents a novel approach to detecting chloride concentrations using Open-Ended Coaxial Probe (OECP) sensing combined with machine learning algorithms. OECP sensing offers real-time, non-destructive, and precise monitoring, enabling early detection of contaminants. Scattering parameter ( $S$ 11) data across a broad frequency range was collected with varying chloride concentrations in controlled laboratory experiments. Thirteen machine learning algorithms were trained to predict chloride concentrations, with different datasets for training and testing to ensure robustness. Among these, CatBoost demonstrated the best performance. After fine tuning and cross-validation, the CatBoost model achieved a test Mean Square Error (MSE) of 0.00627 and Coefficient of Determination (R2) of 0.9936, showcasing its accuracy for applications in water monitoring, corrosion prevention, and safeguarding public health.

关键词： Machine learning algorithms Water quality Predictive models Real-time systems Sensors Scattering parameters Probes Public healthcare Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

NOMA Cooperative Spectrum Sharing Average Capacity Improvement in 5G Network

NOMA Cooperative Spectrum Sharing Average Capacity Improveme...

引用

sciences and Techniques of Automatic Control and computer Engineering MI-STA, IEEE International Maghreb Meeting of the Conference on

作者： Mohamed Hassan Rashid A. Saeed Rania A. Mokhtar Khalid Hamid Elmustafa Sayed Ali Nidhal Odeh Manwinder Singh Othman O. Khalifa Shayla Islam Department of Wireless Communication Lovely Professional University Phagwara Punjab India Department of Computer Engineering College of Computers and Information Technology Taif University Taif Saudi Arabia Department of Communication Systems Engineering University of Science & Technology Omdurman Sudan Department of Electronics Engineering Sudan University of Science and Technologu (SUST) Khartoum Sudan School of Electrical Computer and Telecommunications Engineering University of Wollongong Australia Department of Electrical and Computer Engineering International Islamic University Malaysia Gombak Malaysia & Libyan Center for Engineering Resarch and Information Technology Bani Waleed Libya Department of Computer Science Institute of Computer Science and Digital Innovation UCSI University Malaysia Kuala Lumpur Malaysia

One of the most effective approaches to satisfying the requirements of the next generation of wireless services is non-orthogonal multiple access (NOMA). Spectrum efficiency and average capacity are two aspects of wireless communication that have become increasingly important as the number of mobile services in use has increased. Using both traditional MIMO and Massive MIMO (M-MIMO), this study proposes two new methods for increasing the average capacity of a 5G network's downlink (DL) NOMA power domain (PD) in conjunction with a Cooperative Cognitive Radio Network (CCRN). The initial method involves NOMA users competing for available rivalry channels (R-CH) on the CCRN. The second technique creates a dedicated channel (D-CH) for NOMA users. The MATLAB program is utilized to evaluate the proposed methods in three scenarios with varying distances, power location coefficients, and transmission power. Successive interference cancellation (SIC) and unstable channel conditions are also considered while assessing the analysis of the proposed system under the assumption of Rayleigh fading. Using DL NOMA PD systems, The results reveal that the higher average capacity of best at transmit power DL NOMA with CCRN (dedicated channel) improved U4 average capacity performance by M-MIMO DL NOMA with CCRN (D-CH) improved by when compared with convention DL NOMA. Formulas in closed form were found for average capacity. The resulting formulas are verified using a Monte Carlo simulation.

关键词：

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：