检索结果-内蒙古大学图书馆

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Tabacaru, Gigi Moldovanu, Simona Barbu, Marian 'Dunarea de Jos' University of Galati Faculty of Automation Computers Electrical Engineering and Electronics Department of Automatic Control and Electrical Engineering Romania 'Dunarea de Jos' University of Galati Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Romania Dunarea de Jos University of Galati The Modelling & Simulation Laboratory Galati800008 Romania

ISBN: (纸本)9798350395440

In this work, an attempt is made for the first time to use the measurement pattern generated by morphological transformation quantified by Hausdorff fractal dimension (HFD) and classified with ensemble learning based on bagging. The proposed work uses three morphological transformations for image preprocessing: hit-and-miss transform (HMT), white (WHT), and black top-hat (BHT). The pattern texture of US breast images is described by extracting the HFD from the regions of interest (ROI) after the ultrasound (US) images have been preprocessed. The main objective of this study was achieved by comparatively analyzing the classification performance of features using the Random Forest (RF), Extra Trees (ET) classifier, and bagging ensemble method based on XGBoot classifier. In presented study, the XGBoost classifier and BHT image processing method give an accuracy of 89.8% in a binary classification, benign versus malignant breast cancer. © 2024 IEEE.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

Trajectory control and Fair Communications for Multi-UAV Networks: A Federated Multi-Agent Deep Reinforcement Learning Approach

引用

IEEE Transactions on Wireless Communications 2025年

作者： Tarekegn, Getaneh Berie Tesfaw, Belayneh Abebe Juang, Rong-Terng Saha, Dola Tarekegn, Robel Berie Lin, Hsin-Piao Tai, Li-Chia Nycu Department of Electrical and Computer Engineering 1001 University Road Hsinchu300 Taiwan Nycu Institute of Electrical and Control Engineering 1001 University Road Hsinchu300 Taiwan National Taipei University of Technology Department of Electrical Engineering and Computer Science Taipei10608 Taiwan National Taipei University of Technology Institute of Aerospace and System Engineering Taipei10608 Taiwan University at Albany Suny Department of Electrical and Computer Engineering AlbanyNY12222 United States

Due to their highly flexible deployment and agility features, unmanned aerial vehicles (UAVs) serving as aerial base stations are increasingly being used in challenging environments, including emergency communication, traffic offloading, and failures of existing communications infrastructure. A reliable and effective communication service requires 3D deployment and autonomous UAV trajectory optimization in each time slot. While most prior approaches focus on trajectory design that maximizes communication coverage or network throughput without considering fairness as well as computation time. This paper presents a multi-UAV trajectory control and fair communication (TCFC) scheme that maximizes ground user data rate and communication coverage while ensuring service fairness in a UAV-aided wireless communications system. The proposed TCFC scheme employs a two-stage learning approach. Firstly, it develops a gated recurrent unit-based link quality estimation model to assess each user's link quality over time. Then, a federated multi-agent deep reinforcement learning (FedMADRL) algorithm is utilized to continuously adjust the trajectory of the UAVs, optimizing communication performance. We evaluated our proposed system using real channel measurement data, i.e., amplitude and phase signal information. The results show that the proposed TCFC scheme reduces computation time by 26.91% and provides comparable network performance with the baseline methods while improving DRL agents' privacy. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Some Use Cases of Security Constrained Economic Dispatch Problem for Outage Work Planning Collaboration System 13

Some Use Cases of Security Constrained Economic Dispatch Pro...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Toyoshima, Ichiro Tatekoji, Takashi Mizutani, Ryota Sato, Hiroaki Toshiba Energy Systems & Solutions Corporation Infrastructure Service Development & Design Department Tokyo Japan Toshiba Energy Systems & Solutions Corporation Power Grid System Solutions Engineering Depattment Kawasaki Japan Toshiba Energy Systems & Solutions Corporation Power Control Computer Systems Department Tokyo Japan

ISBN: (纸本)9798350355079

Outage work planning has been essential to maintain the power grid system. For the operators, the planning is troublesome. It is caused by too complex process. The past few years, we have been developing Outage Work planning Collaboration System (OWCS) with some mathematical optimization techniques. Especially, Security Constrained Economic Dispatch(SCED) is extened in some ways to handle various power grid situations. © 2024 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

RISense: 6G-Enhanced Human Activity Recognition System with RIS and Deep LDA 25

RISense: 6G-Enhanced Human Activity Recognition System with ...

引用

25th IEEE International Conference on Mobile Data Management, MDM 2024

作者： Rizk, Hamada Hashima, Sherief Osaka University Graduate School of Information Science and Technology Suita565-0871 Japan Tanta University Computer and Control Engineering Department Tanta31733 Egypt RIKEN-AIP Computational Learning Theory Team Fukuoka819-0395 Japan Egyptian Atomic Energy Authority Engineering Dept Cairo13759 Egypt

ISBN: (纸本)9798350374551

Human Activity Recognition (HAR) systems hold great potential in aiding disabled and elderly individuals to live independently. Various approaches have been suggested for identifying human activities, including sensors, cameras, wearables, and contactless microwave sensing. This latter method is gaining significant attention due to its ability to address privacy concerns arising from cameras and alleviate discomfort caused by wearables. However, current microwave sensing techniques have a key limitation, requiring controlled and ideal conditions to achieve accurate activity detection. In this paper, we propose RISense, a deep learning-aided system for HAR using Re-configurable Intelligent Surface (RIS). RISense introduces novel modules designed to generate a human activity representational space that ensures separability between activity classes, even in the presence of noisy and distorted Channel State Information (CSI) measurements. These representations are then fed into a Recurrent Neural Network (RNN), which learns the sequential changes in features to accurately estimate the user activity. The evaluation of RISense across two realistic settings, encompassing both non-line-of-sight and multi-floor scenarios, showcases its efficacy. Specifically, RISense achieves an activity recognition accuracy of 98.7%. This performance overcomes the accuracy of state-of-the-art systems by over 15%. These findings highlight the superior efficacy of the proposed methodologies, including integrating RIS and advanced learning techniques. © 2024 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Enhancing Transformer Tracking Using NF-ResNet and ResNeXT Backbones 1

引用

1st International Conference on Machine Intelligence for Research and Innovations, MAiTRI 2023

作者： Verma, Sourabh Singla, Rajesh Verma, Om Prakash Sharma, Richa Gupta, Himanshu Sharma, Tarun Muthanna, Ammar Department of Instrumentation and Control Engineering Dr. B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar India Department of Computer Science—Internet of Things ABES Institute of Technology Ghaziabad India University Meerut India Saint-Petersburg State University of Telecommunications Saint Petersburg Russia

ISBN: (数字)9789819981359

ISBN: (纸本)9789819981342

Residual networks play a foremost role in the domain of tracking, specifically in the extraction of features. The residual networks are using a simple technique of skipping connections to overcome the problem of vanishing gradient. Also, it is using batch normalization after each layer of convolution to accelerate the training by reducing the dependency over the parameters. Though, we have tried to solve these issues by introducing ResNeXt and NF-ResNet one by one into the TransT tracker as feature extractors in the place of ResNet. Finally, we present a ResNeXt-based TransT tracker (named as TransT_NeXt) and NF-Net-based TransT tracker (named as TransT_NFNet). We have evaluated proposed trackers on three large-scale benchmark datasets and four small-scale benchmark datasets but unfortunately, our trackers haven’t performed well. At last, we have discussed about the future work on the basis of this study. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Perimeter Defense Using a Turret with Finite Range and Startup Time

Perimeter Defense Using a Turret with Finite Range and Start...

引用

American control Conference (ACC)

作者： Shivam Bajaj Shaunak D. Bopardikar Alexander Von Moll Eric Torng David W. Casbeer Department of Electrical and Computer Engineering Michigan State University Control Science Center Air Force Research Laboratory Department of Computer Science and Engineering Michigan State University

We consider a perimeter defense problem in a planar conical environment comprising a turret that has a finite range and non-zero startup time. The turret seeks to defend a concentric perimeter against N ≥ 2 intruders. Upon release, each intruder moves radially towards the perimeter with a fixed speed. To capture an intruder, the turret's angle must be aligned with that of the intruder's angle and must spend a specified startup time at that orientation. We address offline and online versions of this optimization problem. Specifically, in the offline version, we establish that in general parameter regimes, this problem is equivalent to solving a Travelling Repairperson Problem with Time Windows (TRP-TW). We then identify specific parameter regimes in which there is a polynomial time algorithm that maximizes the number of intruders captured. In the online version, we present a competitive analysis technique in which we establish a fundamental guarantee on the existence of at best (N – 1)-competitive algorithms. We also design two online algorithms that are provably 1 and 2-competitive in specific parameter regimes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Speech Recognition Using Spectrogram Images and Formant Data with Neural Networks

Speech Recognition Using Spectrogram Images and Formant Dat...

引用

20th International Conference on Dependability of computer Systems, DepCoS-RELCOMEX 2025

作者： Kucharski, Mateusz Skubalska-Rafajlowicz, Ewa Department of Control Systems and Mechatronics Wroclaw University of Science and Technology Wroclaw Poland Department of Computer Engineering Wroclaw University of Science and Technology Wroclaw Poland

ISBN: (纸本)9783031927331

This paper proposes a novel approach to improving speech recognition performance by combining spectrogram images with extracted formant frequency data within a dual input neural network framework. While spectrograms are widely used in speech recognition due to their ability to capture time, frequency, and amplitude information, they may not always effectively highlight the subtle characteristics of formant patterns, especially in low resolution images. To address this, we introduce a hybrid model that integrates spectrogram images with formant parameters derived using the linear predictive coding method. The model utilizes parallel convolutional neural network processing spectrogram images and the other handling time series formant data. Outputs are then concatenated and further processed through fully connected layers. This double channel design enables the network to take advantage of complementary information from both spectral and parametric speech features, leading to improved recognition accuracy. The model is trained and evaluated using the Google Speech Commands dataset, achieving superior results compared to traditional KNN classifiers, formant-only models, and standard spectrogram-based CNNs. The proposed method achieves a 93% recognition accuracy, outperforming conventional approaches and demonstrating the potential of formant-augmented neural networks for more robust speech recognition tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

TTTC News

IEEE Design & Test

引用

IEEE Design & Test 2022年第3期39卷 134-136页

作者： Stefano Di Carlo Control and Computer Engineering Department Politecnico di Torino Torino Italy

The TTTC website always lists the latest features and information for its visitors! To find out more, please visit the website at http://***/

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recent Technological Advances in Solar Photovoltaic System and Its Applications in Building Integrated Photovoltaic System

Recent Technological Advances in Solar Photovoltaic System a...

引用

International Conference on Sustainable Technology and Advanced Computing in Electrical engineering, ICSTACE 2021

作者： Islam, Noorul Nat, Aslam Khan, Rashid Ahmed Department of Electrical Engineering ZH College of Engineering and Technology Aligarh Muslim University Aligarh202002 India Department of Computer Control and Management Engineering Sapienza University of Rome Rome00185 Italy Department of Electrical Engineering National Taiwan University of Science and Technology Taipei10607 Taiwan

ISBN: (纸本)9789811943638

Energy has become an integral part of our life. The fossil fuel present in the environment is very much limited. On the other hand, fossil fuel emits harmful gases such as carbon dioxide, Chlorofluorocarbon (CFC), carbon monoxide, and others which harmed flora and fauna. Therefore, the concern for renewable energy application has become more vital due to the depletion of fossil fuels, rising global warming, and increased consumption of energy. Renewable energy aims to reduce pollution levels, enhancing the local economy and community sustainability. Solar energy is the most promising alternative energy source since it has various advantages over other renewable energy sources. The sun is an unquenchable source of energy capable of addressing all energy requirements of humankind. The solar energy concept has been around for a long time, and technological advancements will make it endure for a longer period. The PV-Effect is a mechanism that can produce an electric current when sunlight strikes the limiting layer of semiconductor materials. A photovoltaic (PV) system is a semiconductor device that produces electricity when exposed to luminosity. A PV module is made up of several solar cells that are coupled in parallel and series. This paper provides an extensive study of advancements in energy extraction techniques from a solar panel, analysing solar PV systems under diverse circumstances. PV technology is hastily evolving compared to alternative renewables, consequently leading to the Building Integrated Photovoltaics (BIPV) systems playing a significant role in the generation of electrical energy. BIPV system is a preferred choice as a building integrated solar energy storage system. It has been categorised into three subparts: Grid-connected BIPV system, BIPV system with a solar battery, and PV-Trombe wall. The BIPV mechanism simultaneously acts as a material for the envelope of the building and power extraction from. © 2022, The Author(s), under exclusive license

关键词： Fossil fuels

来源：评论

学校读者我要写书评

暂无评论

Effects of Social Conditions in a Virtual Exergame for Cognitive Rehabilitation in Multiple Sclerosis 13

Effects of Social Conditions in a Virtual Exergame for Cogni...

引用

13th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2023

作者： Ameri, Keivan Battegazzorre, Edoardo Galletti, Chiara Bottino, Andrea Podda, Jessica Tacchino, Andrea Brichetto, Giampaolo De Michieli, Lorenzo Barresi, Giacinto Politecnico di Torino Department of Control and Computer Engineering Turin Italy Istituto Italiano di Tecnologia Rehab Technologies Lab Genoa Italy Scientific Research Area Italian Multiple Sclerosis Foundation Genoa Italy

ISBN: (纸本)9798350324150

Rehabilitation is essential for individuals with multiple sclerosis (MS) to improve their quality of life and mitigate the progression of the disease. Cognitive deficits, which commonly affect MS patients, significantly impact daily functioning and well-being. This paper focuses on the development of a digital version of the Tangram puzzle using virtual reality (VR) to promote logical reasoning, attention, and social interactions to enhance engagement in cognitive rehabilitation for MS patients. The developed simulation integrates social presence in the form of a non-playable character (NPC) intending to improve player performance and motivation to ultimately promote engagement and adherence to treatment. A user study involving different game modes with the NPC in either a supporting or interfering role, was conducted to evaluate the effectiveness and usability of the Tangram VR exergame. After collecting and analyzing questionnaire scores and performance data, our results suggest that the application was well-received by users, and the introduction of an NPC had an impact in terms of execution times and sense of frustration, depending on its behaviour. Nonetheless, only a limited set of significant differences between modes was found, suggesting that further study is necessary to validate the results fully. © 2023 IEEE.

关键词： Virtual reality

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：