检索结果-内蒙古大学图书馆

8th ieee International conference on Computing, Communication, control and Automation, ICCUBEA 2024

作者： Chafale, Jay H. Wadetwar, Renuka S. Giriya, Dhanashree M. Badhiye, Sagarkumar Borkar, Pradnya Shinde, Snehal Nagpur Campus Pune India Indian Institute of Information Technology Nagpur India

ISBN: (纸本)9798350391770

Machine learning techniques and Python programming can be transformed to solve the shortcomings of traditional systems that rely a lot on historical data for credit risk assessments. An essential component of financial decision-making is credit risk analysis, which evaluates borrowers' creditworthiness on the basis of variables like income, credit history, and loan terms. This creative strategy improves accuracy and scalability by utilizing data driven methodologies, automation, and Python's flexible modules such as scikit-learn, NumPy, and Pandas. It also integrates cutting-edge data analytics and technologies like blockchain for safe data exchange, and expands its capacity to include data from unusual sources like social media and geographic data. Real-time credit risk assessments and flexibility in response to changing borrower behavior are made possible by these developments. The dedication to openness and adherence to the law highlights the significance of lending responsibly. This study makes a contribution by showcasing the important developments in credit risk analysis made possible by Python and machine learning. These technologies provide a flexible and adaptive method of evaluating credit risk, which promotes economic stability in the constantly changing financial environment. © 2024 ieee.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

End-Edge-Cloud Collaboration Based False data Injection Attack Detection in Distribution Networks

引用

ieee TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第2期20卷 1786-1797页

作者： Li, Houjun Dou, Chunxia Yue, Dong Hancke, Gerhard P. Zeng, Zeng Guo, Wei Xu, Lei Nanjing Univ Posts & Telecommun Inst Adv Technol Carbon Neutral Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Automat & Artificial Intelligence Nanjing 210023 Peoples R China State Grid Jiangsu Elect Power Co Ltd Informat Commun Branch Nanjing 210003 Peoples R China State Grid Hebei Econ Res Inst Shijiazhuang 050000 Hebei Peoples R China

False data injection attack (FDIA) can pose a severe threat to the distribution networks (DN), and the accurate detection of FDIA plays a key role in the safe and reliable operation of the DN. In this paper, an end-edge-cloud collaboration-based detection framework is proposed to detect FDIA in the DN. First, in order to effectively preserve the privacy of different stakeholders in the DN and solve the problem of data island, a federated learning (FL)-based edge-cloud collaboration mechanism is designed according to the proposed end-edge-cloud collaboration framework to jointly train the local FDIA detection models and eventually build a comprehensive FDIA detection model. Then, considering the temporal-spatial correlation of measurement data, a local data-driven FDIA detection model is proposed based on a novel temporal-spatial graph convolutional network (TSGCN) which can extract temporal-spatial features of the measurement data and improve the FDIA detection performance. In general, compared with the traditional centralized FDIA detection methods, the proposed method can make full use of the computational capacity of distributed edge devices and reduce the pressure of computation on the control centre. Finally, simulation results based on the modified ieee 14-bus and ieee 118-bus distribution systems indicate that the proposed method can effectively improve the accuracy of FDIA detection compared with other methods.

关键词： Distribution networks false data injection attack attack detection end-edge-cloud collaboration graph convolutional network federated learning

来源：评论

学校读者我要写书评

暂无评论

Koopman Operator Approximation Under Negative Imaginary Constraints

引用

ieee control systems LETTERS 2023年 7卷 2767-2772页

作者： Mabrok, Mohamed A. Aksikas, Ilyasse Meskin, Nader Qatar Univ Coll Arts & Sci Dept Math Stat & Phys Math Program Doha Qatar Qatar Univ Coll Engn Elect Engn Dept Doha Qatar

Nonlinear Negative Imaginary (NI) systems arise in various engineering applications, such as controlling flexible structures and air vehicles. However, unlike linear NI systems, their theory is not well-developed. In this letter, we propose a data-driven method for learning a lifted linear NI dynamics that approximates a nonlinear dynamical system using the Koopman theory, which is an operator that captures the evolution of nonlinear systems in a lifted high-dimensional space. The linear matrix inequality that characterizes the NI property is embedded in the Koopman framework, which results in a non-convex optimization problem. To overcome the numerical challenges of solving a non-convex optimization problem with nonlinear constraints, the optimization variables are reformatted in order to convert the optimization problem into a convex one with the new variables. We compare our method with local linearization techniques and show that our method can accurately capture the nonlinear dynamics and achieve better control performance. Our method provides a numerically tractable solution for learning the Koopman operator under NI constraints for nonlinear NI systems and opens up new possibilities for applying linear control techniques to nonlinear NI systems without linearization approximations.

关键词： Negative imaginary systems Koopman operator system identification

来源：评论

学校读者我要写书评

暂无评论

Activity-based Early Autism Diagnosis Using A Multi-dataset Supervised Contrastive learning Approach

Activity-based Early Autism Diagnosis Using A Multi-Dataset ...

引用

ieee/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Rani, Asha Verma, Yashaswi IIT Jodhpur Jodhpur Rajasthan India

ISBN: (纸本)9798350318920;9798350318937

Autism Spectrum Disorder (ASD) is a neurological disorder. Its primary symptoms include difficulty in verbal/non-verbal communication and rigid/repetitive behavior. Traditional methods of autism diagnosis require multiple visits to a human specialist. However, this process is generally time-consuming and may result in a delayed (early) intervention. In this paper, we present a data-driven approach to automate autism diagnosis using video clips of subjects performing simple activities recorded in a weakly constrained environment. This task is particularly challenging since the available training data is small, videos from the two categories ("ASD" and "control") are generally perceptually indistinguishable, and there is no clear understanding of what features would be beneficial in this task. To address these, we present a novel multi-dataset supervised contrastive learning technique to learn discriminative features simultaneously from multiple video datasets with significantly diverse distributions. Extensive empirical analyses demonstrate the promise of our approach compared to competing techniques on this challenging task.

关键词： Algorithms Algorithms and algorithms Applications Biomedical / healthcare / medicine formulations Machine learning architectures Video recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

learning-based Adaptive Admittance controller for Efficient and Safe pHRI in Contact-rich Manufacturing Tasks

Learning-based Adaptive Admittance Controller for Efficient ...

引用

2024 International conference on Intelligent Robots and systems

作者： Niaz, Pouya P. Erzin, Engin Basdogan, Cagatay Koc Univ Robot & Mechatron Lab RML TR-34450 Istanbul Turkiye Koc Univ KUIS AI Ctr TR-34450 Istanbul Turkiye Koc Univ Multimedia Vis & Graph Lab TR-34450 Istanbul Turkiye

ISBN: (纸本)9798350377712;9798350377705

This paper proposes an adaptive admittance controller for improving efficiency and safety in physical human-robot interaction (pHRI) tasks in small-batch manufacturing that involve contact with stiff environments, such as drilling, polishing, cutting, etc. We aim to minimize human effort and task completion time while maximizing precision and stability during the contact of the machine tool attached to the robot's end-effector with the workpiece. To this end, a two-layered learning-based human intention recognition mechanism is proposed, utilizing only the kinematic and kinetic data from the robot and two force sensors. A "subtask detector" recognizes the human intent by estimating which phase of the task is being performed, e.g., Idle, Tool-Attachment, Driving, and Contact. Simultaneously, a "motion estimator" continuously quantifies intent more precisely during the Driving to predict when Contact will begin. The controller is adapted online according to the subtask while allowing early adaptation before the Contact to maximize precision and safety and prevent potential instabilities. Three sets of pHRI experiments were performed with multiple subjects under various conditions. Spring compression experiments were performed in virtual environments to train the data-driven models and validate the proposed adaptive system, and drilling experiments were performed in the physical world to test the proposed methods' efficacy in real-life scenarios. Experimental results show subtask classification accuracy of 84% and motion estimation R-2 score of 0.96. Furthermore, 57% lower human effort was achieved during Driving as well as 53% lower oscillation amplitude at Contact as a result of the proposed system.

关键词： human-robot interaction intention recognition adaptive admittance control subtask detection motion estimation collaborative manufacturing

来源：评论

学校读者我要写书评

暂无评论

An Industrial Private 5G Testbed for Networked Automation systems

An Industrial Private 5G Testbed for Networked Automation Sy...

引用

ieee/ASME International conference on Advanced Intelligent Mechatronics (AIM)

作者： Geng, Jing Kashef (Hany), Mohamed Candell, Richard NIST Smart Connected Syst Div Gaithersburg MD 20899 USA

ISBN: (纸本)9798350355376;9798350355369

Interest in integrating wireless communication capabilities into industrial Cyber-Physical systems (CPS) has surged recently. driven by advantages like ease of deployment, reduced maintenance costs, and asset mobility, CPSs now employ wireless communication for manufacturing control, logistics tracking, process control, and heavy machinery management. While wireless technologies such as ieee 802.11, 5G cellular networks, and redundant ieee 802.15.4 networks offer possible solutions, the challenge to the adoption of these solutions for control systems lies in ensuring reliable and deterministic data delivery. Software-based private 5G implementations emerge as an intriguing solution, offering architectural flexibility, potential cost-effectiveness, and adaptability for diverse traffic types. We present a novel software-based 5G industrial wireless testbed with precision wireless channel measurement and control to support measurement-based research in the application of private 5G networks to these operational scenarios.

关键词： Industrial Wireless 5G cyber-physical systems testbed

来源：评论

学校读者我要写书评

暂无评论

Assurance Guidance for Space Mission use of data-driven Machine learning

Assurance Guidance for Space Mission use of Data-Driven Mach...

引用

ieee Aerospace conference

作者： Feather, Martin S. Guerrini, Steven Slingerland, Philip C. Spolaor, Max CALTECH Jet Prop Lab Pasadena CA USA Aerosp Corp El Segundo CA USA

ISBN: (纸本)9781665490320

We report on our experience developing guidance for assurance personnel on how to assure data-driven Machine learning (ML) systems to be used in the space domain. The impetus for this work stems from the rapid advancement of ML techniques, the positive results of which are inspiring even relatively risk-averse space missions to seek their use. However, assurance personnel, charged with assessing the adequacy of processes and practices followed during space mission developments, are often unfamiliar with these techniques, and lack matured standards to guide their assessments.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-driven Meta-learning Method for CSI Feedback

A Knowledge-Driven Meta-Learning Method for CSI Feedback

引用

ieee International conference on Communications (ieee ICC)

作者： Xiao, Han Tian, Wenqiang Liu, Wendong Zhang, Zhi Shi, Zhihua Guo, Li Shen, Jia OPPO Res Inst Dept Standardizat Beijing Peoples R China

ISBN: (纸本)9781538674628

Accurate and effective channel state information (CSI) feedback is a key technology for massive multiple-input and multiple-output (MIMO) systems. Recently, deep learning (DL) has been introduced to enhance CSI feedback in massive MIMO application, where the massive collected training data and lengthy training time are costly and impractical for realistic deployment. In this paper, a knowledge-driven meta-learning solution for CSI feedback is proposed, where the DL model initialized by the meta model obtained from meta training phase is able to achieve rapid convergence when facing a new scenario during the target retraining phase. Specifically, instead of training with massive data collected from various scenarios, the meta task environment is constructed based on the intrinsic knowledge of spatial-frequency characteristics of CSI for meta training. Moreover, the target task dataset is also augmented by exploiting the knowledge of statistical characteristics of channel, so that the DL model initialized by meta training can rapidly fit into a new target scenario with higher performance using only a few actually collected data in the target retraining phase. The method greatly reduces the demand for the number of actual collected data, as well as the cost of training time for realistic deployment. Simulation results demonstrate the superiority of the proposed approach from the perspective of feedback performance and convergence speed.

关键词： CSI feedback meta-learning MIMO knowledge-driven

来源：评论

学校读者我要写书评

暂无评论

JUICER: data-Efficient Imitation learning for Robotic Assembly

JUICER: Data-Efficient Imitation Learning for Robotic Assemb...

引用

2024 International conference on Intelligent Robots and systems

作者： Ankile, Lars Simeonov, Anthony Shenfeld, Idan Agrawal, Pulkit Harvard Univ Cambridge MA 02138 USA MIT Cambridge MA USA Improbable AI Lab London England

ISBN: (纸本)9798350377712;9798350377705

While learning from demonstrations is powerful for acquiring visuomotor policies, high-performance imitation without large demonstration datasets remains challenging for tasks requiring precise, long-horizon manipulation. This paper proposes a pipeline for improving imitation learning performance with a small human demonstration budget. We apply our approach to assembly tasks that require precisely grasping, reorienting, and inserting multiple parts over long horizons and multiple task phases. Our pipeline combines expressive policy architectures and various techniques for dataset expansion and simulation-based data augmentation. These help expand dataset support and supervise the model with locally corrective actions near bottleneck regions requiring high precision. We demonstrate our pipeline on four furniture assembly tasks in simulation, enabling a manipulator to assemble up to five parts over nearly 2500 time steps directly from RGB images, outperforming imitation and data augmentation baselines. Project website: https://***/.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A Novel Cascading Artificial Neural Networks for Enhanced Distribution Network State Estimation 22

A Novel Cascading Artificial Neural Networks for Enhanced Di...

引用

ieee 22nd Mediterranean Electrotechnical conference (MELECON)

作者： El Iaali, Mohamad Razi, Reza Bruyere, Antoine Francois, Bruno Soares, Joao Univ Lille Junia Cent Lille Arts & Metiers Inst TechnolULR 2697L2EP F-59000 Lille France Polytech Porto LASI Intelligent Syst Associate Lab GECAD Res Grp Intelligent Engn & Comp Adv Innovat Porto Portugal

ISBN: (纸本)9798350387032;9798350387025

The growing integration of renewable energy sources and the widespread adoption of electric vehicles add complexity to power flows in distribution systems. Understanding the system dynamics and implementing control actions are imperative for effective grid management. While measurements in specific nodes are facilitated by smart meters, accurate sensors, communication networks, and electric vehicles, it is costly and, in some cases, impossible to obtain measurements at all nodes. In response to these challenges, this paper introduces a machine learning-based state estimation method, utilizing available measurements and estimating others. By harnessing data-driven techniques, the proposed method aims to provide accurate estimations of voltages and currents in distribution networks, offering valuable insights into flexibilities management and control processes. Specific case study is considered, confirming the efficiency of the suggested state estimation approach and providing insights into its flexibility across a range of scenarios. In addition to the mentioned benefits, the results validate the proposed method, demonstrating a small margin of error. This approach holds significant promises in improving situational awareness for power system operators and enhancing their understanding of the evolving grid dynamics.

关键词： Cascaded ANN Distribution Generation Distribution feeder Machine learning State Estimation

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：