检索结果-内蒙古大学图书馆

First International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP)

作者： Benjaset Maneeloke Sudchai Boonto Peerayot Sanposh Yodyium Tipsuwan Natthawut Chinthaned Warit Tanaprasitpattana Dept. of Electrical Engineering Kasetsart University Bangkok Thailand Dept. of Control Systems and Instrumentation Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand Dept. of Computer Engineering Kasetsart University Bangkok Thailand

ISBN: (数字)9798331505400

ISBN: (纸本)9798331505417

This paper presents a novel methodology for closed-loop system identification of unstable nonlinear systems using the Koopman operator with Extended Dynamic Mode Decomposition with control (EDMDc). The study highlights the critical role of selecting appropriate observable functions to develop accurate and efficient Koopman models. We demonstrate that the resulting Koopman models exhibit excellent fitting and validation properties and retain the stabilizability of the original nonlinear systems. These models are verified through time and frequency responses under closed-loop control using a Linear Quadratic Regulator (LQR), confirming their effectiveness. Future work will extend this framework to more complex systems and incorporate machine learning techniques to refine the selection of observable functions. This approach aims further to enhance the adaptability and robustness of Koopman-based control strategies.

关键词： Time-frequency analysis Adaptation models Regulators Accuracy Fitting Machine learning Robustness Closed loop systems Complex systems Frequency control

来源：评论

学校读者我要写书评

暂无评论

Empirical Characterization of Doppler in Industrial Wireless Channels

Empirical Characterization of Doppler in Industrial Wireless...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Dreyelian Morejón Jon Montalbán Eneko Iradier Mohamed Kashef Hany Richard Candell Pablo Angueira Dept. Communication Engineering UPV/EHU Bilbao Spain Dept. Electronics Technology UPV/EHU Bilbao Spain Dept. Computer Languages and Systems UPV/EHU Bilbao Spain NIST: National Institute of Standards and Technology Gaithersburg USA

This paper analyzes the temporal variation of the radio propagation channel in industrial environments. The results have been obtained by processing empirical data from the National Institute of Standards and technology (NIST) in a field measurement campaign, at different industrial premises, with various dimensions and clutter densities. The paper analyzes the shape of the Doppler spectra and related parameters such as Doppler bandwidth and coherence time. The results are supplemented with maximum Delay Times and RMS Delay Spread data. The influence of factors such as the operational frequency band, environment, and polarization is also analyzed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Kernel-based multi-step predictors for data-driven analysis and control of nonlinear systems through the velocity form

arXiv

引用

arXiv 2024年

作者： Verhoek, Chris Tóth, Roland The Control Systems group The Dept. of Electrical Engineering The Eindhoven University of Technology Netherlands The Institute for Computer Science and Control Budapest Hungary

We propose kernel-based approaches for the construction of a single-step and multi-step predictor of the velocity form of nonlinear (NL) systems, which describes the time-difference dynamics of the corresponding NL system and admits a highly structured representation. The predictors in turn allow to formulate completely data-driven representations of the velocity form. The kernel-based formulation that we derive, inherently respects the structured quasi-linear and specific time-dependent relationship of the velocity form. This results in an efficient multi-step predictor for the velocity form and hence for nonlinear systems. Moreover, by using the velocity form, our methods open the door for data-driven behavioral analysis and control of nonlinear systems with global stability and performance guarantees. © 2024, CC BY-NC-SA.

关键词： Nonlinear simulations

来源：评论

学校读者我要写书评

暂无评论

SimBusters: Bridging Simulation Gaps in Intelligent Vehicles Perception

SimBusters: Bridging Simulation Gaps in Intelligent Vehicles...

引用

IEEE Symposium on Intelligent Vehicle

作者： Alberto Justo Javier Araluce Javier Romera Mario Rodriguez-Arozamena Leonardo González Sergio Díaz TECNALIA Basque Research and Technology Alliance (BRTA) Derio Spain Dept. of Computer Systems Engineering Mondragon University Bilbao Spain

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Recent advances in automated vehicle technology rely heavily on simulated environments for training and testing. However, a significant challenge lies in bridging the gap between simulated and real-world scenarios, as discrepancies between these environments can affect the performance and reliability after that transition, especially in perception. Particularly, LiDAR sensors are highly affected in this matter due to disparities in pointcloud distribution and intensity. Therefore, this paper presents an innovative approach to bridge the gap between simulation and reality. For it, we test and validate a realistic LiDAR library, PCSim, within the CARLA simulator, providing an enhanced simulation environment. Our method involves integrating perception models, pre-trained on real-world datasets, in this environment. Then, we develop a Real2Sim domain adaptation method to transfer these models into the library, leveraging their performance. Finally, we evaluate the 3D object detection models in PCSim LiDARs to prove our *** have assessed this proposal in PCSim, obtaining promising results in mitigating the simulation-reality gap. Our evaluations provide a guidance for future effective transition from virtual environments to real-world applications.

关键词： Training Adaptation models Solid modeling Laser radar Three-dimensional displays Intelligent vehicles Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Detecting Stealthy False Data Injection Attacks in State of Charge Estimation Using Sensor Encoding

Detecting Stealthy False Data Injection Attacks in State of ...

引用

2024 IEEE Power and Energy Society General Meeting, PESGM 2024

作者： Trevizan, Rodrigo D. O'brien, Victoria A. Rao, Vittal S. Energy Storage Technology and Systems Sandia National Laboratories AlbuquerqueNM United States Electric Grid Security and Communications Sandia National Laboratories AlbuquerqueNM United States Texas Tech University Electrical and Computer Eng. Dept. LubbockTX United States

This paper introduces a method for detecting stealthy false data injection attacks on the sensors of state of charge estimation algorithms used in battery management systems (BMSs). This method is based on sensor encoding, which is the active modification of sensor data streams. This method implements low-cost verification of the integrity of measurement data, allowing for the detection of stealthy additive attack vectors. It is considered that these attacks are crafted by malicious actors with knowledge of system models and who are capable of tampering with any number of measurements. The solution involves encoding all vulnerable measurements. The effectiveness of the method is demonstrated by simulations, where a stealthy attack on an encoded measurement vector captured by a BMS generates large residuals that trigger a chi-squared anomaly detector. Within the context of a defense-in-dept. strategy, this method can be combined with other cybersecurity controls, such as encryption of data-in-transit, to equip cyberphysical systems with an additional line of defense against cyberattacks. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

QVal: A Novel Routing Algorithm for Dragonfly Networks

QVal: A Novel Routing Algorithm for Dragonfly Networks

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Javier Navaridas Jose A. Pascual Dept. of Computer Architecture and Technology University of the Basque Country (UPV/EHU) Donostia-San Sebastián Spain

Dragonfly is becoming one of the networks of choice for high-performance computer systems as it offers a sweet spot in terms of cost, simplicity, performance, fault-tolerance and power. In a Dragonfly topology, compute nodes are connected to routers forming fully-connected groups, which are then connected to every other group. This provides very high connectivity with very low diameter which are desired characteristics of high performance interconnection networks. In this work, we propose Quick Valiant, a new routing algorithms for dragonfly networks which leverages Valiant routing with novel proxy selection criteria which reduce the utilization of network resources and eases congestion under pathological loads. These criteria restrict the possible proxies to these that are adjacent to either the local or the remote router, codenamed QVL and QVR, respectively. We compare our proposals with canonical routing functions and observe reductions of average path length of up to 27% and throughput improvements of up to 46% when compared with Valiant routing. Out of these criteria, restricting to local proxies only, QVL, obtains the best results in all scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Demand Side Management for Commercial Buildings: Multiple Heating systems Based Optimization in Real-Time

Demand Side Management for Commercial Buildings: Multiple He...

引用

IEEE International Conference on Engineering, technology and Innovation

作者： Ahmet Köse Ivan Sukhanov Juri Belikov Aleksei Tepljakov Eduard Petlenkov Product development R8 Technologies OÜ Tallinn Estonia Dept. of Software Science Tallinn University of Technology Tallinn Estonia Dept. of Computer Systems Tallinn University of Technology Tallinn Estonia

ISBN: (数字)9798350362435

ISBN: (纸本)9798350362442

The real estate sector has a dramatic impact on global carbon dioxide emissions, approximately 70% of the emissions are produced by or are due to building operations. The increasing demand for heating buildings poses a significant challenge in terms of emissions, and the European Parliament has set ambitious targets in response to this challenge, including a 40% reduction in final energy consumption and a 42.5% cut in primary energy consumption by 2030. With rising global electricity costs, there is significant interest in exploring energy-efficient alternatives for building operations. Although comprehensive heating and heating systems are widespread throughout the European Union, most technical systems lack robust applications of machine learning algorithms in daily operations. This work presents a data-driven approach that optimizes in real-time the operation of heating systems in multiple segments of the real estate sector. The application is based on a supervised learning model. More than 60% reduction in heating energy costs is achieved by implementing the nonlinear model with proactive optimization with hourly electricity market prices, weather forecasts, and estimated occupancy profiles in buildings. At the same time, the work describes a data-driven approach that targets the use of existing hardware and infrastructure, avoiding additional investments while achieving significant energy savings, and also reducing the load of human operations. The proposed application is deployed during the heating season and is driven by real data collected at 15-minute intervals.

关键词： Heating systems Energy consumption Demand side management Buildings Heat engines Europe Weather forecasting Real-time systems Energy efficiency Optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Random Forest Classifier for Detection of Alzheimer's Using OASIS

Optimizing Random Forest Classifier for Detection of Alzheim...

引用

Silchar Subsection Conference (SILCON), IEEE

作者： Karri Sai Sanjana Reddy Kishor Kumar Reddy C. Srinath Doss Kari Lippert Dept. of Computer Science and Engineering Stanley College of Engineering and Technology for Women Hyderabad India Faculty of Engineering and Technology Botho University Botswana Dept. of Systems Engineering University of South Alabama Alabama USA

ISBN: (数字)9798331540821

ISBN: (纸本)9798331540838

Alzheimer's disease (AD) is a progressive brain disorder impacting behavior, memory, and cognition, with over a million cases reported annually in India. The risk significantly increases beyond age 65. Early diagnosis and treatment can result in better recovery. We propose a predictive model using the Random Forest algorithm and the OASIS dataset for early AD diagnosis, leveraging MRI data, clinical notes, genetic markers, and cognitive test results. Our model was evaluated against several others, including Decision Tree, AdaBoost, SVM, and Logistic Regression. With a 97.3% accuracy and a 2.7% error rate, our Random Forest Classifier o utperformed t he others, demonstrating superior predictive power for early AD diagnosis and potentially improving patient care.

关键词： Training Accuracy Transfer learning Predictive models Prediction algorithms Genetics Classification algorithms Alzheimer's disease Random forests Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

A Trustable LSTM-Autoencoder Network for Cyberbullying Detection on Social Media Using Synthetic Data

A Trustable LSTM-Autoencoder Network for Cyberbullying Detec...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Akter, Mst Shapna Shahriar, Hossain Cuzzocrea, Alfredo Wu, Fan Rodriguez-Cardenas, Juanjose University of West Florida Department of Intelligent Systems and Robotics United States University of West Florida Center of Cybersecurity United States University of Calabria IDEA Lab Rende Italy Tuskegee University Dept. of Computer Science Tuskegee United States Kennesaw State University Dept. of Information Technology Georgia United States

ISBN: (纸本)9798350324457

Social media cyberbullying has a detrimental effect on human life. As online social networking grows daily, the amount of hate speech also increases. Such terrible content can cause depression and actions related to suicide. This paper proposes a trustable LSTM-Autoencoder Network for cyberbullying detection on social media using synthetic data. We have demonstrated a cutting-edge method to address data availability difficulties by producing machine-translated data. However, several languages such as Hindi and Bangla still lack adequate investigations due to a lack of datasets. We carried out experimental identification of aggressive comments on Hindi, Bangla, and English datasets using the proposed model and traditional models, including Long Short-Term Memory (LSTM), Bidirectional Long ShortTerm Memory (BiLSTM), LSTM-Autoencoder, Word2vec, Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-trained Transformer 2 (GPT-2) models. We employed evaluation metrics such as f1-score, accuracy, precision, and recall to assess the models' performance. Our proposed model outperformed all the models on all datasets, achieving the highest accuracy of 95%. Our model achieves state-of-the-art results among all the previous works on the dataset we used in this paper. © 2023 IEEE.

关键词： Cyber-bullying Deep Learning Natural Language Processing Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Pursuit-Evasion on a Sphere and When It Can Be Considered Flat 63

Pursuit-Evasion on a Sphere and When It Can Be Considered Fl...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Milutinovic, Dejan Moll, Alexander Von Manyam, Satyanarayana G. Casbeer, David W. Weintraub, Isaac E. Pachter, Meir Electrical and Computer Engineering Dept. University of California Santa Cruz Santa CruzCA United States Control Science Center Aerospace Systems Directorate Air Force Research Laboratory DaytonOH45435 United States Dcs Corporation DaytonOH United States Air Force Institute of Technology Wright-Patterson Afb Dept. of Electrical Engineering OH United States

ISBN: (纸本)9798350316339

In planar pursuit-evasion differential games considering a faster pursuer and slower evader, the interception points resulting from equilibrium strategies lie on the Apollonius circle. This property is instrumental for leveraging geometric approaches for solving multiple pursuit-evasion scenarios in the plane. Here, we study a pursuit-evasion differential game on a sphere and generalize the planar Apollonius set to the spherical domain. We find that the interception point from the equilibrium strategies can leave the Apollonius set boundary and present a condition to keep the intercept point on the boundary. This condition allows for generalizing planar pursuitevasion strategies to the sphere. © 2024 IEEE.

关键词： Spheres

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：