检索结果-内蒙古大学图书馆

Conference on Data Science and Machine Learning Applications (CDMA)

作者： Zeeshan Haider Ahmad Taher Azar Suliman Mohamed Fati Ibraheem Kasim Ibraheem Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Ibraheem Kasim Ibraheem is with Department of Electrical Engineering College of Engineering University of Baghdad Baghdad Iraq

ISBN: (数字)9798331539696

ISBN: (纸本)9798331539702

The growing interest in artificial intelligence (AI) as a diagnostic aid has spurred significant research into deep learning-based colorectal cancer polyp detection and localization. The motivation behind this research stems from the occasional missed diagnosis of polyps by medical experts due to fatigue or inexperience, which can lead to serious complications like colorectal cancer. In this research, we explore the effect on the accuracy of polyp detection and localization, employing variants of the state-of-the-art detection model YOLOv9. Four variants of YOLOv9 (gelan-e, gelan-c, yolov9-c, and yolov9-e) are trained on two datasets: CVC-CLinicDB and Kvasir combined as one dataset and LDPolyp Video as the second separate dataset. Results show that the YOLOv9 variants show their superiority when evaluated on five test datasets as compared to YOLOv8, the most recent YOLO series model.

关键词： Location awareness YOLO Deep learning Analytical models Accuracy Colorectal cancer Data science Fatigue Multiaccess communication Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Fractional Order Ultra-Local Model-Based Sliding-Mode-Assissted Disturbance Observer and Model-Free Control

Fractional Order Ultra-Local Model-Based Sliding-Mode-Assiss...

引用

2024 International Conference Automatics and Informatics, ICAI 2024

作者： Zhang, Liuchang Wang, Haoping Tian, Yang Zhuang, Xincheng Azar, Ahmad Taher Ahmed, Saim Nanjing University of Science and Technology Dept. School of Automation Nanjing China Prince Sultan University Dept. Automated Systems & Soft Computing Lab Riyadh Saudi Arabia Prince Sultan University Dept. College of Computer and Information Sciences Riyadh Saudi Arabia

ISBN: (纸本)9798350353907

This paper puts forward a fractional order sliding-mode-assisted disturbance observer-based model-free control (FO-SAMDOMFC) methodology for fractional order system with disturbance. First, the system dynamic model is rewritten as a fractional order ultra-local model (ULM), and a SMADO is designed to estimate the lumped disturbance term. Then, A closed-loop control law is proposed on the basis of the ULM with the objective of guaranteeing the convergence of the tracking error. Next, a proof of the stability of the closed-loop system is given based on the fractional extension of Lyapunov's direct method. Finally, the simulation compared with other controllers based on MATLAB/Simulink is realized, and the simulation results validate the proposed method. © 2024 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Human Brain Stroke Prediction using Machine Learning Methods with Synthetic Minority Oversampling Approach

Human Brain Stroke Prediction using Machine Learning Methods...

引用

Women in Data Science at Prince Sultan University (WiDS PSU), International Conference of

作者： Muhammad Mujahid Noor Ayesha Ahmad Taher Azar Tanzila Saba Zeeshan Haider Artificial Intelligence and Data Analytics (AIDA) Lab CCIS Prince Sultan University Riyadh School of Clinical Medicine Zhengzhou University Zhengzhou China College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia

ISBN: (数字)9798350395839

ISBN: (纸本)9798350395846

The brain is considered to be the principal anatomical component of the human body. A stroke is a medical condition defined by cerebral injury that occurs as a consequence of blood vessel rupture within the brain. Symptoms might become apparent when there is an interruption in the brain circulation of blood and other vital chemicals. Stroke is widely acknowledged as a significant medical disorder because to its elevated mortality rates, enduring cognitive impairments, and concomitant comorbidities. The timely recognition of the numerous prodromal manifestations linked to a stroke has the capacity to attenuate its magnitude. The primary objective of this study is to utilize machine learning methodologies in order to predict the likelihood of an early-stage occurrence of a cerebral stroke. In order to assess the efficacy of the algorithm, a dataset for stroke prediction was acquired via the Kaggle platform. Various preprocessing techniques are applied to normalize and clean the dataset for stroke prediction. This research utilized many classification models including Random Forest, Ada Boost, LightGBM,, Decision Tree (DT), Logistic Regression (LR),and Support vector machine (SVM) to perform classification tasks. The Random Forest classifier has a higher level of classification accuracy in comparison to alternative machine learning classifiers, obtaining an impressive accuracy rate of 99.45%. The results of the investigation revealed that machine learning approaches demonstrated a higher level of performance in comparison to alternative methods.

关键词： Support vector machines Deep learning Accuracy Machine learning algorithms Computed tomography Stroke (medical condition) Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Fractional-order Fixed-time Non-singular Sliding Mode Control for Nonlinear Robotic Manipulators

引用

IFAC-PapersOnLine 2023年第2期56卷 8105-8110页

作者： Saim Ahmed Ahmad Taher Azar Ibrahim A. Hameed Automated Systems and Soft Computing Lab (ASSCL) College of Computer and Information Sciences Prince Sultan University Riyadh 11586 Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha 13518 Egypt Department of ICT and Natural Sciences Norwegian University of Science and Technology Larsgårdsve-gen 2 6009 Ålesund Norway

In this study, fractional-order non-singular fixed-time terminal sliding mode control (FoFxNTSM) for nonlinear robotic manipulators in the existence of uncertainties and external disturbances is examined. To begin, the concept of fractional-order fixed-time non-singular terminal sliding mode control is introduced. This method combines the benefits of NTSM (which provides fast convergence speed, smooth and singularity-free control inputs) with the advantages of a fractional-order constants (which improves position tracking effectiveness). Lyapunov analysis yields the fixed-time stability of the closed-loop system. To evaluate and illustrate the performance of the proposed strategy, the relevant simulation results are presented.

关键词： Fixed-time SMC nonlinear robotic manipulators fractional-order control fast convergence

来源：评论

学校读者我要写书评

暂无评论

Fractional Order Ultra-Local Model-Based Sliding-Mode-Assissted Disturbance Observer and Model-Free Control

Fractional Order Ultra-Local Model-Based Sliding-Mode-Assiss...

引用

Automatics and Informatics (ICAI), International Conference

作者： Liuchang Zhang Haoping Wang Yang Tian Xincheng Zhuang Ahmad Taher Azar Saim Ahmed Dept. School of Automation Nanjing University of Science and Technology Nanjing China Dept. Automated Systems & Soft Computing Lab Prince Sultan University Riyadh Saudi Arabia Dept. College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia

ISBN: (数字)9798350353907

ISBN: (纸本)9798350353914

This paper puts forward a fractional order sliding-mode-assisted disturbance observer-based model-free control (FO-SAMDOMFC) methodology for fractional order system with disturbance. First, the system dynamic model is rewritten as a fractional order ultra-local model (ULM), and a SMADO is designed to estimate the lumped disturbance term. Then, A closed-loop control law is proposed on the basis of the ULM with the objective of guaranteeing the convergence of the tracking error. Next, a proof of the stability of the closed-loop system is given based on the fractional extension of Lyapunov’s direct method. Finally, the simulation compared with other controllers based on MATLAB/Simulink is realized, and the simulation results validate the proposed method.

关键词： Accuracy System dynamics Simulation Noise Mathematical models Disturbance observers Stability analysis Noise measurement MATLAB Informatics

来源：评论

学校读者我要写书评

暂无评论

Unknown Disturbance Estimator Based Adaptive Nonsingular Fast Terminal Sliding-Mode Control for n-DOF Nonlinear Robotic systems

Unknown Disturbance Estimator Based Adaptive Nonsingular Fas...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Ziyu Duan Yang Tian Haoping Wang Saim Ahmed Ahmad Taher Azar Chakib Ben Njima Nanjing University of Science and Technology Nanjing China College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt University of Sousse Tunisia

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

This paper develops an improved second-order filter unknown disturbance estimator (UDE) with adaptive nonsingular fast terminal sliding mode control (ANFTSMC) to solve the trajectory tracking problem of uncertainties and external disturbances in robotic system. The developed UDE -ANFTSMC controller not only uses the advantages of NFTSM theory to ensure fast convergence speed, avoid singularity and robustness to uncertainties and external disturbances, but also uses UDE to estimate and suppress unknown disturbances in the system. Firstly, UDE is introduced, and then the ANFTSM control scheme is designed with a NTFSM surface. Lyapunov stability theory was used for stability analysis, and the manipulator mathematic model and SolidWorks’ prototype were used to demonstrate the effectiveness of the proposed control scheme.

关键词： Adaptation models Adaptive systems Uncertainty Accuracy Trajectory tracking Prototypes Manipulators

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation and Optimizer Tuning for Polyp Segmentation

Data Augmentation and Optimizer Tuning for Polyp Segmentatio...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Zeeshan Haider Ahmad Taher Azar Tanzila Saba Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Artificial Intelligence & Data Analytics (AIDA) Lab Prince Sultan University Riyadh Saudi Arabia

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

Automatic segmentation of polyps is a very challenging problem in the scope of medical imaging. This challenge is often faced due to a lack of quality datasets. In this research, we explore the effect on the accuracy of colorectal cancer polyp segmentation due to augmentation and various optimizers while training the segmentation model. The effect of augmentation and optimizers on the polyp segmentation is studied separately. The augmentation effect is observed by changing the percentage of augmentation in each experiment whereas the optimizer effect is studied by changing the optimizer for each experiment. The experiments are performed with 8 optimizers and 10 different augmentation strategies.

关键词： Training Image segmentation Automation Accuracy Training data Data augmentation Tuning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning for Understanding Diversity: Applying Feature Engineering and Cluster Analysis to Deaf and Hard of Hearing Data

Unsupervised Learning for Understanding Diversity: Applying ...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Anisha Poly P K Nizar Banu Ahmad Taher Azar Nashwa Ahmad Kamal Department of Computer Science CHRIST (Deemed to be University) Bangalore India College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Faculty of Engineering Cairo University Giza Egypt

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

As e-Learning emerges as a promising tool for instruction delivery, personalizing the e-Learning platform for DHH learners will benefit them to improve their learning engagement and educational attainment. This study aims to collect and analyze the different features unique to DHH learners and analyze the significant features among them. This study highlights the importance of addressing the diversity among DHH learners, while creating a personalized learning environment for them. With this focus, we employ the K-Means clustering algorithm to group the learners based on similar needs and preferences and identified that distinguishing clusters can be formed within the DHH group. We also tried to understand the significant features contributing to forming well separated groups. These results provide valuable insights into the diverse preferences and requirements when they interact with the learning materials. These findings emphasize the significance of personalized approach for DHH learners in educational settings and serve as the stepping stone to develop a personalized learning environment for them.

关键词： Electronic learning Automation Clustering algorithms Auditory system Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Fractional Integral Sliding Mode Control for Euler-Lagrange System

Fractional Integral Sliding Mode Control for Euler-Lagrange ...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Saim Ahmed Ahmad Taher Azar Ibraheem Kasim Ibraheem Nashwa Ahmad Kamal Farah Ayad Abdul-Majeed Chakib Ben Njima Automated Systems and Soft Computing Lab (ASSCL) College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial intelligence Benha University Benha Egypt Department of Computer Techniques Engineering Dijlah University College Baghdad Iraq Faculty of Engineering Cairo University Giza Egypt Aeronautical Department College of Technical Engineering Alfarahidi University Baghdad Iraq University of Sousse Tunisia

This research focuses on fractional-order fixed-time integral terminal sliding mode control (FoFxITSM) for Euler-Lagrange systems in the presence of uncertainty and external disturbances. First, the concept of fractional-order fixed-time integral terminal sliding mode control (FoFxITSM) is laid out and discussed in detail. This methodology enhances the efficiency of position tracking by combining the characteristics of ITSM, which include chatter-free control inputs, rapid fixed-time convergence, and non-singularity. Additionally, this method includes a fractional-order parameter to improve performance of the proposed method. A Lyapunov analysis is used to determine the closed-loop system's ability to maintain its fixed-time stability. To test and demonstrate the performance of the suggested method, the simulation results of the proposed scheme applied on the 2-DOF robot are provided.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Power of Few: Dynamic Interaction Modeling in Few-Shot Learning Using Graph Neural Networks and Attention Mechanisms

The Power of Few: Dynamic Interaction Modeling in Few-Shot L...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Vikrant Shokeen Sandeep Kumar Amit Sharma Ahmad Taher Azar Nashwa Ahmad Kamal Chakib Ben Njima Department of Computer Science & Engineering Maharaja Surajmal Institute of Technology Delhi India IMS Engineering College Ghaziabad Uttar Pradesh India College of Computer & Information Sciences Prince Sultan University Riyadh Saudi Arabia Automated Systems & Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Faculty of Engineering Cairo University Giza Egypt University of Sousse Tunisia

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

Few-shot learning represents a paradigm shift in deep learning, which is defined by massive amounts of data and computing capacity. It solves these issues by utilizing novel training approaches and optimization goals. This shift also applies to meta-learning and provides an alternative to standard deep learning, which requires a lot of resources. The conventional technique indirectly infers the underlying structure between classes in the context of classification problems. In contrast, this work attempts to clearly portray the links between classes, which is a substantial change from previous techniques. This study looks into embedding adaptability for novel data in a high computing power environment. This is accomplished by investigating a dynamic interaction between samples utilizing their centroids inside a support. To better capture the subtle interactions between classes, this study uses Graph Neural Networks (GNNs) in conjunction with attention processes. The ability to explicitly characterize class relationships boosts the flexibility and efficacy of few-shot learning, demonstrating how it can turn limited input and processing resources into maximum results. The research extends the potential of deep learning in situations where large-scale datasets and powerful computers are not readily available, offering up new avenues for real-world applications.

关键词： Training Metalearning Computers Automation Computational modeling Computer architecture Graph neural networks

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：