检索结果-内蒙古大学图书馆

Classification of a nanocomposite using a combination between Recurrent Neural Network based on Transformer and Bayesian Network for testing the conductivity property

引用

Expert systems with Applications 2025年 270卷

作者： Gazehi, Wejden Loukil, Rania Besbes, Mongi Higher Institute of Information and Communication Technologies University of Carthage Tunisia Laboratory of Robotics Informatics and Complex Systems University of Tunis Manar Tunisia

To enhance trust and adoption of machine learning models, particularly neural Networks, it is crucial to develop methods that allow quantifying and reporting epistemic uncertainties and the random uncertainties which lead to the non accuracy of RNN. To transcend these boundaries, we suggest to use Bayesian techniques, where probability distributions are employed to represent not only the model predictions but also the uncertainty associated with these predictions. Our study encapsulates the use of Bayesian Networks, RNNs based on the transformer and propose an hybrid approach for improving the classification of nanocomposites for evaluating the conductivity. In fact, it presents a comprehensive approach to classify nanocomposites using advanced Deep Learning techniques. Initially, a Bayesian Network (BN) model is employed to analyze and classify the nanocomposites, providing probabilistic insights into their conductive behavior based on the distribution and interaction of nanoparticles. Subsequently, a Recurrent Neural Network (RNN) based on the Transformer architecture is used to enhance the classification accuracy by capturing the sequential dependencies and complex patterns in the data. Finally, we propose a hybrid model that combines the strengths of both Bayesian Networks and RNNs. This integrated approach leverages the probabilistic reasoning of BNs and the Deep Learning capabilities of RNNs to achieve a more robust and accurate classification framework. The experimental results based on metric values indicate that the hybrid model significantly outperforms individual models, providing a powerful tool for the predictive classification of nanocomposites’ conductivity. © 2025 Elsevier Ltd

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

A Multi - Task Control Approach for Active-Assisting Rehabilitation

A Multi - Task Control Approach for Active-Assisting Rehabil...

引用

International Conference on Advanced systems and Electric Technologies (IC_ASET)

作者： Afef Hfaiedh Sondes Jaziri Nahla Khraief Safya Belghith Laboratory of Robotics Informatics and Complex Systems (RISC lab-LR16ES07) University of Tunis EL Manar ENIT Tunisia Laboratory of Robotics Informatics and Complex Systems (RISC lab-LR16ES07) Tunisia

ISBN: (数字)9798350384895

ISBN: (纸本)9798350384901

Control of robotic exoskeleton presents an inter-esting research topic in the last years. However, in the field of healthcare, making informed decisions can be challenging because there is not enough data available describing real-world scenarios. In these cases, we can profit from intelligent algorithms that learn from data and aid decision-making to obtain more robust and reliable decisions. In this work, we propose a control approach for active-assisting rehabilitation. It is based on Reinforcement Learning method namely PILCO, short for Probabilistic Inference for Learning Control. It overcomes the high data challenge and does not require an extensive amount of data to design a model that closely approximates the real-world environment. However, PILCO is limited to learn only single task. Therefore, to alleviate the user's workload in the learning process across multiple tasks, we generalize the predicted policy to encompass novel tasks. The novelty in the proposed approach is that the set of tasks used to test the method are predicted from an electromyography signals by the radial basis function (RBF) algorithm. The test of the proposed approach is applied in a simulation environment of a one Degree of Freedom I-DoF elbow-exoskeleton (EE). The simulation results prove the efficiency of the method and show that tasks performed are most often close to target positions.

关键词： Training Simulation Exoskeletons Reinforcement learning Prediction algorithms Search problems Electromyography

来源：评论

学校读者我要写书评

暂无评论

Single Modality and Joint Fusion for Emotion Recognition on RAVDESS Dataset

引用

SN Computer Science 2024年第6期5卷 669页

作者： Haddad, Syrine Daassi, Olfa Belghith, Safya Laboratory of Robotics Informatics and Complex Systems (RISC Lab-LR16ES07) Tunis Tunisia National Engineering School of Tunis University of Tunis El manar Tunis 1002 Tunisia National Engineering School of Carthage University of Carthage Carthage 2035 Tunisia

Over the last decade, emotion recognition has become a widely researched area worth considering in any project related to affective computing. Due to the limitless applications of this new discipline, the development of emotion recognition systems has emerged as a lucrative opportunity in the corporate sector. Emotion recognition can be detected in many ways, such as face, speech, text, gestures, etc. Hence, this article presents a comprehensive survey of emotion recognition methods, focusing on three key modalities: visual, speech, and audio-visual. Moreover, a novel approach for each modality is proposed, and a comparative analysis is conducted with existing methods to assess their effectiveness. The results of this study revealed that face emotion recognition on the RAVDESS dataset can achieve good results compared to speech emotion recognition, which was the opposite case in previous literature. Combined modalities were found to likely achieve even better results with an accuracy of 89% compared to previous works. Finally, this article concludes by offering new insights and suggestions for future research. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computational models Face emotion recognition Multi-modal emotion recognition RAVDESS dataset Speech emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Gait Phase Recognition using Machine Learning Models with Two Training Methods 15

Multi-Class Gait Phase Recognition using Machine Learning Mo...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mekni, Amal Narayan, Jyotindra Gritli, Hassene Borj Cedria Tunis1164 Tunisia Indian Institute of Technology Guwahati Mechtronics and Robotics Laboratory Department of Mechanical Engineering Assam Guwahati781039 India University of Tunis El Manar le Belvédère Laboratory of Robotics Informatics and Complex Systems RISC Lab-LR16ES07 National Engineering School of Tunis Tunis1002 Tunisia

ISBN: (纸本)9798350370249

Walking is a fundamental human activity, yet understanding its intricacies is crucial for diagnosing and treating various gait abnormalities and musculoskeletal disorders. This study investigates the machine learning-based classification of gait phases into five subphases with two training methods. Using data from 100 individuals obtained from an open-source platform. The gait cycle was divided into the following subphases: Initial Contact, Loading Response, Mid Stance, Terminal Stance, and Pre-Swing. In the first approach, a stratified random sampling method was employed, allocating 80% of data from each subphase for training and 20% for testing. The second method involved training with data from 80% participants and testing with data from 20% participants. Out of different ML algorithms, the Random Forest (RF) achieves the highest performance (99.2%) with similar results across both methods. The k-Nearest Neighbors (k-NN), the Logistic Regression (LR), the Decision Tree (DT), and the Support Vector Machine (SVM) show comparable performance ( 91%) with marginal improvement with the second method. Naive Bayes (NB) has a significantly lower performance ( 77.7%). These findings suggest that RF is a robust and effective algorithm for this task. Furthermore, the study indicates that applying machine learning techniques to datasets divided by subjects presents promising opportunities for creating precise gait analysis systems. This can assist clinicians and researchers in enhancing patient care and gaining deeper insights into human locomotion. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Audio-Visual Information based on Convolutional Neural Network

Emotion Recognition from Audio-Visual Information based on C...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Syrine Haddad Olfa Daassi Safya Belghith Laboratory of Robotics Informatics and Complex Systems (RISC Lab-LR16ES07) National Engineering School of Tunis University of Tunis El Manar Tunis Tunisia Laboratory of Robotics Informatics and Complex Systems (RISC Lab-LR16ES07) National Engineering School of Carthage University of Carthage Carthage Tunisia

In recent years., emotion recognition becomes a heavily researched field to consider in any project related to affective computing. Due to the almost limitless applications of this new discipline., the development of emotion recognition systems has emerged as a lucrative opportunity in the corporate sector. Emotion recognition can be detected in many ways., face., speech., text., gestures., etc. This paper proposes an emotion recognition approach using multiple information sources. Our approach involves both visual and speech information and it is based on Convolutional neural networks. The experiments prove the effectiveness of the proposed approach and the importance of combining visual with audio data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Nanoparticle Classification Through Optimized Artificial Neural Networks

Enhanced Nanoparticle Classification Through Optimized Artif...

引用

Decision Aid Sciences and Application (DASA), International Conference on

作者： Wejden GAZEHI Rania LOUKIL Mongi BESBES Laboratory of Robotics Informatics and complex systems RISC Lab (LR16ES07) ENIT University of Tunis El Manar Tunis Tunisia ISTIC University of Carthage Tunis Tunisia

ISBN: (数字)9798350369106

ISBN: (纸本)9798350369113

This study investigates the effectiveness of Deep Learning techniques in classifying nanoparticles, with a par-ticular focus on how the depth of neural networks influences model performance. Artificial Neural Networks (ANN) were utilized in simulations, exploring configurations ranging from a single hidden layer to four hidden layers to identify the optimal architecture for nanoparticle classification using MATLAB- NN Toolbox. Evaluation metrics include Mean Squared Error (MSE), Root Mean Squared Error (RMSE), the Correlation Coefficient (R), and the Coefficient of Determination $(R^{2})$ . Notably, the minimum value of the MSE achieved was $5.6814 \times 10^{-13}$ with the Bayesian Regularization (BR) technique, while the maximum values of Rand $R^{2}$ were 0.9989 and 0.9977, respectively, with the Levenberg-Marquardt (LM) technique. The results offer insights into model robustness and contribute to selecting an optimal algorithm for analyzing polymeric nanoparticles. This study highlights the potential of ANN to advance precision in nanomaterial classification tasks, supporting further development in this field.

关键词： Nanoparticles Deep learning Correlation coefficient Artificial neural networks Mathematical models Robustness Distance measurement Classification algorithms Polymers MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Intelligent Navigation of Mobile Robots Using Reinforcement Learning with A Comparative Analysis of a modified Q-Learning Method and DQN in Simulated Gym Environment

Research Square

引用

Research Square 2024年

作者： Khlif, Nessrine Khraief, Nahla Belghith, Safya Laboratory of Robotics Informatics and Complex Systems RISC lab - LR16ES07 National Engineering School of Tunis Electrical Engineering Department University of Tunis EL Manar Tunis Tunisia

Purpose: The field of autonomous mobile robots (AMRs) has experienced significant growth in recent years, propelled by advancements in autonomous driving and unmanned aerial vehicles (UAVs). The integration of intelligence into robotic systems necessitates addressing various research challenges, with navigation emerging as a pivotal aspect of mobile robotics. This paper explores the three fundamental questions central to the navigation problem: localization (determining the robot’s position), mapping (creating a representation of the environment), and path planning (determining the optimal route to the destination). The proposed solution to the mobile robot navigation problem involves the seamless integration of these three foundational navigation components. Methods: Our comparative analysis between the Q-learning modified method and a deep Q-network (DQN) in simulated gym pathfinding tasks reveals the efficacy of this approach. The modified Q-learning algorithm consistently outperforms DQN, demonstrating its superior ability to navigate complex environments and achieve optimal solutions. The transition from a definite environment to a simulated gym environment serves as a valuable validation of the method’s applicability in real-world scenarios. By rigorously evaluating our algorithm in a controlled setting, we can ensure its robustness and effectiveness across a broader range of applications. Results: In essence, our study establishes the modified Q-learning algorithm as a promising new approach to addressing the exploration-exploitation dilemma in reinforcement learning. Its superior performance in simulated gym environments suggests its potential for real-world applications in various domains, including robotics, autonomous navigation, and game development. Conclusion: The paper furnishes a comprehensive overview of research on autonomous mobile robot navigation. It begins with a succinct introduction to the diverse facets of navigation, followed by an examinat

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Lower Limb Joint Torque Estimation via Bayesian Regularized Backpropagation Neural Networks

Lower Limb Joint Torque Estimation via Bayesian Regularized ...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Jyotindra Narayan Hassène Gritli Santosha K Dwivedy Department of Mechanical Engineering Mechatronics and Robotics Laboratory Indian Institute of Technology Guwahati Guwahati Assam India Laboratory of Robotics Informatics and Complex Systems (RISC Lab - LR16ES07) National Engineering School of Tunis University of Tunis El Manar Le Belvédère Tunis Tunisia

Prior gait analysis has played a crucial role in assessing overall health and well-being, particularly in individuals of different age groups. Nevertheless, acquiring gait data has necessitated the in-person presence of participants, incurring potential expenses. We introduce a deep learning technique called Bayesian regularized backpropagation neural network (BR-BPNN) to estimate joint torques in lower-limb motion based on anthropometric data and joint movements. The study collects joint movement data from 40 healthy participants (25 males and 15 females) spanning ages 7 to 65, utilizing an established motion-capture system. The input data encompassed various parameters such as age, gender, total body mass, height, thigh length, calf length, ankle-foot length, thigh mass, calf mass, ankle mass, and joint angles for the hip, knee, and ankle. The output data included joint torques calculated for a simplified leg model using the inverse dynamics method derived from the Euler-Lagrangian principle. We presented the conceptual details of the proposed BR-BPNN model and contrast model named Levenberg-Marquardt-based BPNN (LM-BPNN). Performing a comparative analysis, the results revealed that the BR-BPNN model (R train = 0.985, R test = 0.955) excelled in accurately estimating joint torques compared to the LM-BPNN model (R train = 0.973, R test = 0.924). Furthermore, the BR-BPNN model is found to be effective by 87.19%, 77.87%, and 72.73% in estimating hip, knee, and ankle joint torques for a 51-year-old male subject from the testing dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Clustering Algorithm for Sensorless reduced Device Multilevel Inverter based active power filter control

A Machine Learning Clustering Algorithm for Sensorless reduc...

引用

2022 IEEE Information Technologies and Smart Industrial systems, ITSIS 2022

作者： Manai, Lazhar Rihani, Achref Besbes, Mongi National Engineering School of Tunis University of Tunis Laboratory of Robotics Informatics and Complex Systems El Manar B.P No. 37 Tunis Tunisia Higher Institute of Information and Communication Technologies University of Carthage B.P No123 Hammam Chatt1164 Tunisia

ISBN: (纸本)9781665477017

This article's primary goal is to minimize P.I regulators and maximize measurement tools while maintaining inverter capacitor voltage self-balance in order to lower costs and simplify controls. The second goal is to offer a reliable preventative solution for power grid issues. Numerical simulations and practical testing will be used to evaluate the effectiveness of the machine learning control of reduced device multilevel inverter-based active power filter control, and comparisons with alternative strategies are required to show its advantages... © 2022 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Mobile Robot Navigation: An overview

Reinforcement Learning for Mobile Robot Navigation: An overv...

引用

Information Technologies & Smart Industrial systems (ITSIS), IEEE

作者： Nessrine Khlif Nahla Khraief Safya Belghith Laboratory of Robotics Informatics and Complex Systems (RISC lab - LR16ES07) University of Tunis EL Manar Tunis Tunisia

For several years, research shows that interest in autonomous mobile robots is increasing and it has more and more grown. Autonomous mobile robots is an object of discussion but nowadays it's an emerging topic due to the all progress related to field like autonomous driving and UAV (drones). Integrating intelligence into robotic systems requires solving various research problems, including one of the most important problems of mobile robotic systems: navigation. Find the answers to the following three questions: What is the localisation of the robot? Where are the robot going? How can it get there? presenting the solution of mobile robot navigation problem. These questions are answered by basic navigation parts which are localization, mapping and path planning. The paper present an overview of research on autonomous mobile robot navigation. First, a quick introduction to the various features of navigation. We also discuss machine learning and reinforcement learning in mobile robotics. Furthermore, we will discuss some path planning techniques. Some future directions are also suggested.

关键词： Location awareness Navigation Service robots Reinforcement learning Path planning Mobile robots Autonomous vehicles

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：