检索结果-内蒙古大学图书馆

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Rastogi, Digant Jain, Manika Rayguru, Madan M. Valluru, Sudarshan K. Delhi Technological University Control of Dynamical Systems and Computation Laboratory Dept. of Electrical Engineering Delhi India

ISBN: (纸本)9798350331790

This paper presents a novel algorithm, IQ-CRL (Improved Q-learning using Classification and Regression with ANN), which is a control architecture that uses the existing Q-learning algorithm and integrates it with Artificial neural Networks (ANNs). The proposed algorithm addresses the limitations of traditional Q-learning by incorporating an adaptive mechanism that leverages ANN to find an optimal control policy that is more accurate and at lower computational expense. IQ-CRL is designed to be used efficiently with dynamical systems such as mobile robots. The objective of this study is to evaluate the performance of IQ-CRL in comparison to classical Q-learning and PID controller. The results show that the IQ-CRL algorithm outperforms both the classical Q-learning and PID controller in terms of learning efficiency, control accuracy and computing complexity. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Design & Validation of ANN based Reinforcement Learning Control Algorithm for Coupled Tank System 8

Design & Validation of ANN based Reinforcement Learning Cont...

引用

8th IEEE International Conference for Convergence in Technology, I2CT 2023

作者： Rastogi, Digant Jain, Manika Rayguru, Madan M. Valluru, Sudarshan K. Delhi Technological University Control of Dynamical Systems and Computation Lab Dept. of Electrical Engineering Delhi India

ISBN: (纸本)9798350334012

This paper presents a framework to apply Reinforcement Learning control algorithm on benchmark nonlinear dynamical systems. This work focuses on a novel Artificial neural Network (ANN) based dynamic programming approach using Value Iteration to obtain optimal control for continuous-time nonlinear system. In particular, Coupled Tank System has been chosen to represent benchmark nonlinear dynamical system. The proposed Artificial neural Network-Reinforcement Learning (ANN-RL) algorithm, Naive Reinforcement Learning (Naive-RL) algorithm and traditional PID control schemes are investigated on coupled tank system. The ANN-RL algorithm performs better than the Naive-RL and PID controllers in terms of steady state error, stability, oscillations and overshoot. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Maneuvering Control of Autonomous Underwater Vehicle (AUV) by Simulated Annealing and Moth Flame Optimization Tuned Controllers

Maneuvering Control of Autonomous Underwater Vehicle (AUV) b...

引用

2022 International Conference on Electronic systems and Intelligent Computing, ICESIC 2022

作者： Valluru, Sudarshan K. Thareia, Hitesh Center for Control of Dynamical Systems and Computation Dept. of Electrical Engineering Delhi Technological University Delhi110042 India

ISBN: (纸本)9781665483858

This paper emphasizes maneuvering control of Autonomous Underwater Vehicle (AUV) with the help of Linear-Proportional Integral Derivative (L-PID) and Fractional Order PID (FOPID) controllers. The values of the gain parameters of L-PID (Kp, Ki, Kd) and FOPID (Kp, Ki, Kd,λ, μ) are tuned by Simulated Annealing (SA) and Moth Flame optimization (MFO) techniques. The performance of both the controllers is compared and the better algorithm to tune the parameters of the controllers is determined. A step function is applied to the system's input to test the AUV, and the corresponding response to the input function is examined. The transient parameters of the AUV, such as rise time, settling time, overshoot, and performance index IT AE were calculated and compared. The investigatory results show that both the algorithms used to tune the FO PID controller accurately steer the AUV. Also, the MFO tuned FOPID controller is more efficient than the SA tuned FOPID controller. © 2022 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Design & Validation of ANN based Reinforcement Learning Control Algorithm for Coupled Tank System

Design & Validation of ANN based Reinforcement Learning Cont...

引用

International Conference for Convergence of Technology (I2CT)

作者： Digant Rastogi Manika Jain Madan M. Rayguru Sudarshan K. Valluru Dept. of Electrical Engineering Control of Dynamical Systems and Computation Lab Delhi Technological University Delhi India

关键词： PI control Heuristic algorithms Artificial neural networks Reinforcement learning Approximation algorithms Stability analysis Steady-state

来源：评论

学校读者我要写书评

暂无评论

Intelligent Control of Mobile Robots with ANN Assisted Improved Q-learning: IQ-CRL Algorithm

Intelligent Control of Mobile Robots with ANN Assisted Impro...

引用

Emerging Technologies (GlobConET), IEEE IAS Global Conference on

作者： Digant Rastogi Manika Jain Madan M. Rayguru Sudarshan K. Valluru Dept. of Electrical Engineering Control of Dynamical Systems and Computation Laboratory Delhi Technological University Delhi India

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Deep neural Network Models using Transfer Learning for Electrocardiogram Signal Classification 6

A Comparative Analysis of Deep Neural Network Models using T...

引用

6th International Conference on Recent Trends on Electronics, Information, Communication and Technology, RTEICT 2021

作者： Rahuja, Nitin Valluru, Sudarshan K. Center for Control of Dynamical Systems and Computation Delhi Technological University Dept. of Electrical Engineering Delhi110042 India

ISBN: (纸本)9781665435598

With the development of computational resources in the past decade, the adoption of deep learning methodologies has taken a steep rise. Particularly, the use of various Convolutional neural Network (CNN) based architectures for various computer vision and image classification problems in healthcare research can be witnessed. In this scope, performance evaluation and comparison of three different CNN architectures for multi-class classification of Electrocardiogram (ECG) signals is presented in this paper. Three distinct classes of ECG signal i.e. Normal Sinus Rhythm (NSR), Arrhythmia (ARR), and Congestive Heart failure (CHF) are utilized in this work, which is representative of an individual's heart conditions. The classification methodology adopted makes use of Continuous Wavelet Transform (CWT) which provides a 2-dimensional time-frequency representation of available samples of ECG signals. ECG dataset was collected from different PhysioBank databases, which provides openly-accessible medical research data. Images with time-frequency representation of ECG signals were applied as input to three CNN architectures namely, AlexNet, GoogLeNet, and SqueezeNet. Using transfer learning approach and modification in certain output layers of three architectures, ECG classification was performed and the performance of three CNN architectures was studied. The results revealed classification accuracy of 97.80%, 97.78% and 97.22% by AlexNet, GoogLeNet and SqueezeNet respectively. AlexNet outperformed GoogLeNet and SqueezeNet models in terms of accuracy as well as training time. © 2021 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

A Deep neural Network Approach to Automatic Multi-Class Classification of Electrocardiogram Signals

A Deep Neural Network Approach to Automatic Multi-Class Clas...

引用

2021 International Conference on Intelligent Technologies, CONIT 2021

作者： Rahuja, Nitin Valluru, Sudarshan K. Delhi Technological University Center for Control of Dynamical Systems and Computation Dept. of Electrical Engineering Delhi110042 India

ISBN: (纸本)9781728185835

Classification of electrocardiogram (ECG) signals is essential for accurate clinical diagnosis of coronary illness. Deep neural Network (DNN) has emerged as a promising tool for feature identification in ECG signals with advancements in signal processing techniques and artificial intelligence. Particularly, Convolutional neural Network (CNN) has enabled intricate feature identification and classification of images. In this scope, an efficient classification methodology utilizing wavelet transform and AlexNet CNN is presented in this paper to classify the ECG signals into three different categories, namely: Arrythmia (ARR), Congestive Heart failure (CHF) and Normal Sinus Rhythm (NSR). Physionet research dataset is utilized in this work. Firstly, all ECG signals are converted to a corresponding scalogram using Continuous Wavelet Transform (CWT). Then, these scalograms are applied as input to AlexNet, which is a pretrained CNN. Finally, transfer learning and fine-tuning are done, and the performance of modified AlexNet is evaluated. The study revealed a good accuracy of 97.3%. © 2021 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

LEARNING EFFICIENT POSITIONAL ENCODINGS WITH GRAPH neural NETWORKS

arXiv

引用

arXiv 2025年

作者： Kanatsoulis, Charilaos I. Choi, Evelyn Jegelka, Stephanie Leskovec, Jure Ribeiro, Alejandro Dept. of Computer Science Stanford University United States School of Computation Information and Technology Technical University of Munich Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology United States Dept. of Electrical and Systems Engineering University of Pennsylvania United States

Positional encodings (PEs) are essential for effective graph representation learning because they provide position awareness in inherently position-agnostic transformer architectures and increase the expressive capacity of Graph neural Networks (GNNs). However, designing powerful and efficient PEs for graphs poses significant challenges due to the absence of canonical node ordering and the scale of the graph. In this work, we identify four key properties that graph PEs should satisfy: stability, expressive power, scalability, and genericness. We find that existing eigenvector-based PE methods often fall short of jointly satisfying these criteria. To address this gap, we introduce PEARL, a novel framework of learnable PEs for graphs. Our primary insight is that message-passing GNNs function as nonlinear mappings of eigenvectors, enabling the design of GNN architectures for generating powerful and efficient PEs. A crucial challenge lies in initializing node attributes in a manner that is both expressive and permutation equivariant. We tackle this by initializing GNNs with random node inputs or standard basis vectors, thereby unlocking the expressive power of message-passing operations, while employing statistical pooling functions to maintain permutation equivariance. Our analysis demonstrates that PEARL approximates equivariant functions of eigenvectors with linear complexity, while rigorously establishing its stability and high expressive power. Experimental evaluations show that PEARL outperforms lightweight versions of eigenvector-based PEs and achieves comparable performance to full eigenvector-based PEs, but with one or two orders of magnitude lower complexity. Our code is available at https://***/ehejin/Pearl-PE. Copyright © 2025, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Experimental validation and control of Laboratory aerial system by IC741-IOPID and IC741-FOP Iλ Controllers: An Analog approach 11

Experimental validation and control of Laboratory aerial sys...

引用

11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020

作者： Valluru, Sudarshan K. Kumar, Gaurav Kumar, Rajul Meena, Ankit Lal Center for Control of Dynamical Systems and Computation Delhi Technological University Dept. of Electrical Engineering Delhi110042 India

ISBN: (纸本)9781728168517

As control and trajectory tracking of hovering aerial vehicles are remarkable objective among researchers and industries. So in this paper, a validated attempt is made to achieve the precise and desired control of the Twin Rotor Aerial System (TRAS) over is motion in horizontal as well as vertical planes. To obtain pitch and yaw angles stabilization and desired trajectory tracking of TRAS the IO-PID and fractional order FOP I-{ lambda} controllers are designed using IC741 operational amplifiers. The designing and transforming integer order scheme into fractional-order crone1 and continued fraction expansion (CFE) methods are used, which ultimately replace feedback capacitor in I-{ lambda} control scheme with an RC ladder fractance device. The designed controllers are tested with a defined disturbance provided to pitch and yaw trajectories and the time taken by both the controllers are compared for testing of stabilization control performances. It is observed from results that IC741-I-{ lambda} controller gives better trajectory tracking and stabilization than IC741-IOPID. © 2020 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Design of Precise FLC for Trajectory Tracking and Stabilization of Twin Rotor MIMO System 6

Design of Precise FLC for Trajectory Tracking and Stabilizat...

引用

6th IEEE International Conference on engineering, Technologies and Applied Sciences, ICETAS 2019

作者： Valluru, Sudarshan K. Kumar, Rajul Kumar, Rahul Center for Control of Dynamical Systems and Computation Delhi Technological University Dept. of Electrical Engineering Delhi110042 India

ISBN: (纸本)9781728140827

A progressive and analytical approach is used for designing the precise fuzzy logic controller to control a Twin Rotor Multiple Input Multiple Output System (TRMS). Two fuzzy logic controllers are designed and tested in simulation for pitch and yaw trajectory tracking, including one degree of freedom each. For the formalization and fuzzy implication of both pitch and yaw fuzzy controllers, Mamdani constructive paradigm is used in this paper. Triangular and Trapezoidal member functions are constructed in Fuzzy Interference System and tuned by using performance evaluation after initial characteristic design as well as experience and parametric investigation about TRMS plant. Performance of Conventional Linear PID controller has been compared in terms of peak overshoot, rise time, settling time with fuzzy logic controller (FLC) for stabilization of pitch and yaw angle. Impulse signals are given as disturbances in simulation to the TRMS output, which resembles as real-time aerial and atmospheric disturbances. The results convey that the stabilization achievement of the fuzzy controller is predominant as compared to the Linear-PID controller. © 2019 IEEE.

关键词： Stabilization

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：