检索结果-内蒙古大学图书馆

IEEE Transactions on AgriFood Electronics 2025年

作者： Sun, Mingchun Zhao, Rongqiang Liu, Hongfang Jin, Jing Liu, Jie Harbin Institute of Technology Faculty of Computing Harbin150001 China National Key Laboratory of Smart Farm Technologies and Systems Harbin150001 China Heilongjiang Academy of Agriculture Science Jiamusi154000 China Department of Control Science and Engineering Harbin Institute of Technology Harbin150001 China

Soil-available potassium content is essential for agricultural crop management. The electrochemical measurement method exhibits advantages of high speed, low cost, and simple operation. However, it encounters challenges, such as poor signal reproducibility, limited sample accessibility, and restrictions on measurement accuracy. To address these issues, the Nernst informed neural network (NINN)-based electrochemical measurement of soil-available potassium content is proposed. The framework for the electrochemical soil-available potassium content measurement is established. The proposed method is developed to exploit the nonlinear relationship between the electrical signal and the soil-available potassium content end-to-end with a single potassium ions-selective electrode. The NINN in the proposed method is developed to improve the measurement accuracy on the dataset with a limited number of samples by integrating Nernst mechanism into the network. The potassium-content dynamic estimation in the proposed method is developed to overcome the uncertainties of the dilution factor and influence of interfering ions. The practical measurement exhibits the mean absolute percentage error in a low range and the time within 10 min. Experimental results demonstrate that the proposed method improves the accuracy compared to purely data-driven models and reduces the electrochemical measurement costs. Furthermore, the proposed method also exhibits the superiority in terms of measurement speed;operational complexity compared to the commercial products relied on spectroscopy. The proposed method can contribute to the advancement of the measurement of soil nutrients. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Fatigue Load Prediction of Large Wind Turbine by Big Data and Deep Learning

Fatigue Load Prediction of Large Wind Turbine by Big Data an...

引用

Electrical, Automation and Computer engineering (ICEACE), International Conference on

作者： Jiayue Wu Qinmin Yang Nanlin Jin Low Carbon Electrical Power and Energy Technology xXi'an Jiaotong-Liverpool University Suzhou China College of Control Science and Engineering Zhejiang University Hangzhou China Department of Computing Xi'an Jiaotong-Liverpool University Suzhou China

This paper introduces a fatigue load prediction framework for the nacelle of wind turbines utilizing operational data sourced from the supervisory control and data acquisition (SCADA) system of a Wind Farm. The primary objective revolves around achieving precise fatigue load predictions for the nacelle, forecasting 15 minutes in advance. Firstly, a series of data preprocessing steps were implemented on the wind turbine data procured from the SCADA system to enhance the model's generalization capability and robustness, including 3-Sigma outlier detection, sample point selection, as well as filtering and de-noising techniques. Then, the gate recurrent unit (GRU) was tuned and trained as the optimal model for long time-series forecasting of SCADA parameter channels. Subsequently, the support vector regression (SVR) model, refined with grid search methodology, was employed to establish the intricate relationship between SCADA parameters and fatigue loads. Finally, the predicted SCADA parameter values were fed into the optimized SVR model to derive fatigue load prediction results for wind turbines. Experimental results indicated that the proposed model framework can effectively predict fatigue loads on the nacelle of wind turbines utilizing the SCADA data in real scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Target Tracking Using a Swarm of UAVs by Q-learning Algorithm

Multi-Target Tracking Using a Swarm of UAVs by Q-learning Al...

引用

Sensor Signal Processing for Defence (SSPD)

作者： Seyed Ahmad Soleymani Shidrokh Goudarzi Xingchi Liu Lyudmila Mihaylova Wenwu Wang Pei Xiao Centre for Vision Speech and Signal Processing (CVSSP) The University of Surrey UK School of Computing and Engineering University of West London UK Department of Automatic Control and Systems Engineering The University of Sheffield UK Institute for Communication Systems (5GIC) The University of Surrey UK

This paper proposes a scheme for multiple un-manned aerial vehicles (UAVs) to track multiple targets in challenging 3-D environments while avoiding obstacle collisions. The scheme relies on Received-Signal-Strength-Indicator (RSSI) measurements to estimate and track target positions and uses a Q-Learning (QL) algorithm to enhance the intelligence of UAVs for autonomous navigation and obstacle avoidance. Considering the limitation of UAVs in their power and computing capacity, a global reward function is used to determine the optimal actions for the joint control of energy consumption, computation time, and tracking accuracy. Extensive simulations demonstrate the effectiveness of the proposed scheme, achieving accurate and efficient target tracking with low energy consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simple Discretization Scheme for Gain Matrix Conditioning

arXiv

引用

arXiv 2022年

作者： O'Connor, Daniel L. Siang, Lim C. Elnawawi, Shams Control Consulting Inc. Great FallsMT United States Department of Process Control Engineering Refinery BurnabyBC Canada College of Computing Georgia Institute of Technology AtlantaGA United States

In industrial model predictive controllers (MPCs), models generated from regression-based system identification methods typically contain small or even physically non-existent degrees of freedom. control issues can arise when the steady-state optimizer uses these small degrees of freedom to calculate targets for plant operation due to matrix ill-conditioning. Mathematical techniques like Relative Gain Array (RGA) and Singular Value Decomposition (SVD) are helpful for analyzing controller gain interactions and identifying conditioning issues, which can be corrected relatively easily in small models. However, these techniques are difficult and tedious to apply for larger, more complex models. This paper describes a novel, non-iterative, RGA-based, binning technique for discretizing the gain matrix and quickly solving 2×2 conditioning issues for any model size, while guaranteeing gain adjustments below a certain threshold. Higher order interactions are also discussed. © 2022, CC BY.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Triple IRS-Aided Communications: Row-Column Sparsity Enhanced Bayesian Tensor Learning for Channel Estimation

引用

IEEE Transactions on Communications 2025年

作者： Hu, Limei Shao, Xiaodan Qiu, Tingzhi Chen, Feng Cheng, Lei Wu, Qingqing Southwest University College of Artificial Intelligence College of Electronic and Information Engineering Brain-Inspired Computing and Intelligent Control of Chongqing Key Laboratory National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing 400715 China University of Waterloo Department of Electrical and Computer Engineering Waterloo N2L 3G1 ON Canada Zhejiang University College of Information Science and Electronic Engineering Hangzhou 310058 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai China

Channel acquisition presents a major challenge in deploying intelligent reflecting surfaces (IRS) aided communication systems, due to massive reflective elements that create a complex multi-path channel and increase channel dimensions. For an IRS-aided communication system, complete channel includes three parts: From the users to IRS, from the IRS to BS, and from the BS back to the IRS. Thus, a generalized multi-IRS cascaded communication system with three cascaded IRSs is considered. Unfortunately, existing channel estimation methods focus on single or double IRS cascades, which is not applicable to the case of triple cascaded IRS channel estimation directly. In this paper, we study the uplink channel estimation for triple cascaded IRSs aided single-user single-input single-output (SISO) systems. Specifically, the triple IRS cascaded channel is typically sparse. It permits us to characterize the channel estimation as a problem of sparse matrix recovery. Then, the sparse learning is explored to achieve robust channel estimation with limited training overhead. Particularly, the sparse channel matrices of the cascaded triple IRS channels have a common row-column block sparsity structure. However, a unique challenge lies in characterizing and enhancing such a common row-column sparsity. To tackle this issue, we apply a random matrix prior to promote the common row-column-wise sparsity of the channel matrix, and then an efficient Bayesian tensor inference algorithm is proposed to estimate the IRS channel. Finally, simulation results confirm that the proposed scheme outperforms traditional counterparts in terms of accuracy. © 1972-2012 IEEE.

关键词： Bayesian learning common row-column sparsity tensor modeling Triple intelligent reflecting surface (IRS)

来源：评论

学校读者我要写书评

暂无评论

Real-time Semantic Segmentation of Solar Photovoltaic Arrays for Autonomous UAV Flights 43

Real-time Semantic Segmentation of Solar Photovoltaic Arrays...

引用

43rd Chinese control Conference, CCC 2024

作者： Li, Nanyan Chen, Hao Sun, Zhigang Gao, Jing Yi, Dewei Liu, Cunjia Su, Jinya Southeast University School of Automation Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Cse Ministry of Education Nanjing210096 China State Grid Jiangsu Integrated Energy Service CO. Ltd Nanjing210096 China Jiangsu Sudian Industry Management CO. Ltd Nanjing210096 China University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom Loughborough University Department of Aeronautical and Automotive Engineering LoughboroughLE11 3TU United Kingdom

ISBN: (纸本)9789887581581

This paper considers the real-time semantic segmentation of solar PhotoVoltaic (PV) arrays using down-facing cameras onboard Unmanned Aerial Vehicles (UAVs) to support autonomous navigation for ultra-low altitude industrial inspection. Various semantic segmentation algorithms, including SegNet, UNet, Deeplabv3+, and their respective variants, are compared to identify the most suitable one that strikes a balance between segmentation and real-time performance. Subsequently, each video frame is processed by the selected segmentation network to create a solar array mask. This mask is then optimally fitted to diverse solar array shapes to determine angular and horizontal deviations between the image center and the solar array center-line. The algorithms are validated on a self-constructed dataset of 594 solar PV array UAV images, encompassing varied environmental conditions and solar farm layouts. The top-performing network, lightweight vgg 16bn-Unet, achieves 99.4% overall accuracy and 98.2% Intersection over Union (IoU), while the most balanced network, mobilev3-Deeplabv3+, attains 98.9% accuracy and 96.5% IoU, with a 27.59 fps (using an NVIDIA GeForce MX150 GPU) suitable for real-time UAV flights. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

IARS SegNet: Interpretable Attention Residual Skip connection SegNet for melanoma segmentation

arXiv

引用

arXiv 2023年

作者： Narayanan, Shankara Sikha, O.K. Benitez, Raul Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore641112 India Department of Automatic Control Universitat Politècnica de Catalunya Av. d’Eduard Maristany Barcelona08019 Spain Barcelona08034 Spain

Skin lesion segmentation plays a crucial role in the computer-aided diagnosis of melanoma. Deep Learning models have shown promise in accurately segmenting skin lesions, but their widespread adoption in real-life clinical settings is hindered by their inherent black-box nature. In domains as critical as healthcare, interpretability is not merely a feature but a fundamental requirement for model adoption. This paper proposes IARS SegNet an advanced segmentation framework built upon the SegNet baseline model. Our approach incorporates three critical components: Skip connections, residual convolutions, and a global attention mechanism onto the baseline Segnet architecture. These elements play a pivotal role in accentuating the significance of clinically relevant regions, particularly the contours of skin lesions. The inclusion of skip connections enhances the model’s capacity to learn intricate contour details, while the use of residual convolutions allows for the construction of a deeper model while preserving essential image features. The global attention mechanism further contributes by extracting refined feature maps from each convolutional and deconvolutional block, thereby elevating the model’s interpretability. This enhancement highlights critical regions, fosters better understanding, and leads to more accurate skin lesion segmentation for melanoma diagnosis. This study primarily focuses on the interpretation of performance improvements in the base model resulting from the integration of each of these three components. To comprehensively assess the performance gain achieved with each addition, we employ two sets of evaluation metrics, quantifying performance based on both regions and contours. The results underscore the superior segmentation capabilities of the proposed architecture compared to the SegNet and U-Net models. Notably, it provides interpretable results, particularly when applied to the PH2 dataset. Copyright © 2023, The Authors. All rights reserved

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Influence of the variables describing brain signals on the performance of the Naive Bayesian Classifier

Influence of the variables describing brain signals on the p...

引用

2022 Progress in Applied Electrical engineering, PAEE 2022

作者： Kawala-Sterniuk, Aleksandra Zygarlicki, Jaroslaw Lysiak, Adam Grochowicz, Barbara Pelc, Mariusz Bauer, Waldemar Baczkowicz, Dawid Krecisz, Krzysztof Dylag, Katarzyna A. Wieczorek, Wiktoria Kahankova, Radana Martinek, Radek Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics Opole Poland University of Greenwich School of Computing and Mathematical Sciences London United Kingdom Agh University of Science and Technology Department of Automatic Control and Robotics Krakow Poland Opole University of Technology Faculty of Physical Education and Physiotherapy Opole Poland St. Louis Children Hospital Krakow Poland Jagiellonian University in Krakow-Collegium Medicum Department of Pathophysiology Krakow Poland Jagiellonian University in Krakow-Collegium Medicum Department of Bioinformatics and Telemedicine Krakow Poland Vsb - Technical University Ostrava Department of Cybernetics and Biomedical Engineering-FEECS Ostrava-Poruba Czech Republic

ISBN: (纸本)9781665455152

In this paper various variables describing brain signals such as near-infrared spectroscopy (NIRS) and electroencephalography (EEG) on the Naive Bayesian Classifier were presented. Analysis of biomedical signals is a very challenging task - therefore the authors of this work decided to analyse two types of brain signals - EEG and NIRS, which have different features, character, nature and are differently prone to various artifacts occurrence. The applied classifiers can be applied for various features extraction and pattern comparisons, which is useful in diagnostic processes. © 2022 IEEE.

关键词： Near infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

House Price Prediction System Using Ensemble Learning Approach

House Price Prediction System Using Ensemble Learning Approa...

引用

International Conference on Parallel Distributed and Grid computing (PDGC)

作者： Abhishek Kumar Paras Jain Priyank Pandey Shyamalendu Das Vishan Kumar Gupta Dhiraj Kumar Gupta Department of CSE MMHA & PU Patna Bihar India School of Computing Science Engineering and Artificial Intelligence VIT Bhopal University Kothrikalan Bhopal MP India Department of CSE Graphic Era Deemed to be University Dehradun India Humanities Department SRMCEM Lucknow India Amity School of Engineering and Technology Amity University Mohali Punjab India Department of Quality Control Sun Pharmaceutical Industrial Limited Halol Vadodara Gujrat India

ISBN: (数字)9798331521349

ISBN: (纸本)9798331521356

The real estate industry is among the most active and critically important industries for any economy. An accurate forecast of the prices of houses is very important to the buyers, sellers, investors and the policy makers. In years gone by, other methods of valuation have been used, but new advancements have been made in machine learning meaning the prediction speeds and the level of accuracy have been boosted. In this article, I would like to know how the development of various sophisticated models of ML can be used to forecast house prices: the most used models, the most favorite datasets and informative features, as well as the appropriate evaluation measures. Real estate is a continually expanding business that is prominently involved in the world economy. To precisely estimate house prices is always a daunting task due to various factors that vary from physical to non-physical factors include size, location, market, and economic conditions. Digital advancements especially, the incorporation of machine learning in the analysis of financial markets, housing and other sectors has enabled real estate specialists, banks and other institutions and government bodies analyze trends and develop sophisticated models to predict housing prices more effectively than conventional analytical models. In the context of this article’s expanse, we provide a deeper look into the components of house price prediction, with additional information on datasets, feature engineering, specific algorithms, optimization tactics, known difficulties, and future developments.

关键词： Training Analytical models Accuracy Biological system modeling Computational modeling Machine learning Predictive models Stakeholders Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Protecting Personalized Trajectory with Differential Privacy under Temporal Correlations

arXiv

引用

arXiv 2024年

作者： Cao, Mingge Zhu, Haopeng Min, Minghui Li, Yulu Li, Shiyin Zhang, Hongliang Han, Zhu School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of CyberScience and Engineering Wuhan University Wuhan430072 China School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States

Location-based services (LBSs) in vehicular ad hoc networks (VANETs) offer users numerous conveniences. However, the extensive use of LBSs raises concerns about the privacy of users’ trajectories, as adversaries can exploit temporal correlations between different locations to extract personal information. Additionally, users have varying privacy requirements depending on the time and location. To address these issues, this paper proposes a personalized trajectory privacy protection mechanism (PTPPM). This mechanism first uses the temporal correlation between trajectory locations to determine the possible location set for each time instant. We identify a protection location set (PLS) for each location by employing the Hilbert curve-based minimum distance search algorithm. This approach incorporates the complementary features of geo-indistinguishability and distortion privacy. We put forth a novel Permute-and-Flip mechanism for location perturbation, which maps its initial application in data publishing privacy protection to a location perturbation mechanism. This mechanism generates fake locations with smaller perturbation distances while improving the balance between privacy and quality of service (QoS). Simulation results show that our mechanism outperforms the benchmark by providing enhanced privacy protection while meeting user’s QoS requirements. Copyright © 2024, The Authors. All rights reserved.

关键词： Location based services

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：