检索结果-内蒙古大学图书馆

7th International Conference on Sustainable Information engineering and Technology, SIET 2022

作者： Kurniawan, Wijaya Hangos, Katalin M. Marton, Lorinc Faculty of Computer Science University of Brawijaya Malang Indonesia Dept. of Electrical Engineering and Information Systems University of Pannonia Veszprem Hungary Institute for Computer Science and Control Budapest Hungary Dept. of Electrical Engineering Sapientia Hungarian University of Transylvania Targu Mures Romania

ISBN: (纸本)9781450397117

In this paper, the problem of fault estimation and localization in the connecting dynamic elements of distributed heating and cooling systems are treated. The fault represents the physical parameter change related to the heat transfer between the system and the external environment. First, based on the bi-linear dynamic state space model of the system in the presence of a fault, structural observability analysis using Signed Directed Graph (SDG) has been performed to investigate the sensor placement problem. Then, a nonlinear observer with a parameter adaptation algorithm was proposed for fault estimation. The simulation results show that it can successfully detect and estimate the fault. Fault localization along the length of the element has also been attempted, but it has been found that the localization cannot be performed using practically changeable input variables. Frequency domain analysis is presented to discuss this phenomenon. © 2022 ACM.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Identification of Texts Using ML Algorithm for The Accurate Recognition

Identification of Texts Using ML Algorithm for The Accurate ...

引用

2023 International Conference on Power Energy, Environment and Intelligent control, PEEIC 2023

作者： Pasha, M Jahir Kajendran, K. Deshmukh, Shrikala Kumar, G. Sreekanth, N. Pund, Sachin G.Pullaiah College of Engineering and Technology Computer Science and Engineering Kurnool India Panimalar Engineering College Dept. of Computer Science and Engineering Chennai India Amity University Mumbai India Bharati Vidyapeeth College of Engineering Pune India Srm Institute of Science and Technology Faculty of Management Kattankulathur India Mallareddy Engineering College for Women Hyderabad India Shri Ramdeobaba College of Engineering and Management Department of Industrial Engineering Maharashtra Nagpur India

ISBN: (纸本)9798350357769

A Comparative evaluation of device mastering Algorithms for textual content classification textual content category is an vital assignment in herbal language processing, where the aim is to routinely assign a label or category to a given text file. With the increasing quantity of text facts available in diverse domain names, the need for efficient and accurate text class algorithms has turn out to be extra vital. In this paper, we gift a comparative analysis of machine mastering algorithms for text category. We experiment with one of a kind algorithms, such as aid Vector Machines, Naive Bayes, Random Forests, and Multilayer Perceptron, on numerous benchmark datasets. Our results reveal that the choice of set of rules considerably affects the overall performance of textual content classification, and there may be no unmarried high-quality algorithm that works well for all datasets. We also provide insights into the strengths and weaknesses of each set of rules and talk their applicability in specific eventualities. Our findings can guide researchers and practitioners in selecting the maximum suitable system gaining knowledge of algorithm for their text category duties. Textual content classification, device learning, assist vector machines, naive bays, random forests, multilayer perceptron, and comparative analysis. © 2023 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Investigate the Deep Learning Models for White Blood Cell Classification 3

Design and Investigate the Deep Learning Models for White Bl...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Gaikwad, Prajwal. S. Deshmukh, Rakesh K. Pise, Priya Bhopale, Shrikant D. Kalinga University Raipur India AISSMS's Institute of Information Technology Dept. of Computer Engineering Pune India Artificial Intelligence and Data Science Indira College of Engineering and Management Pune India Dr. D.Y. Patil Pratisthan's Colleg of Engineering Salokhenagar Kolhapur India

ISBN: (纸本)9798350381931

For the purpose of illness prediction, the objective of this study is to develop automated models for the categorization of white blood cells (WBCs). In the human immune system, white blood cells (WBCs) function to combat infections and shield the body from external substances. Eosinophils, neutrophils, monocytes, basophils, and lymphocytes are the components that make up these cells;each of these cell types accounts for a different proportion and is responsible for a distinct set of functions overall. The clinical laboratory technique for counting the specific types of white blood cells (WBCs) has long been an essential component of a testing procedure known as a complete blood count (CBC), which is used to aid in the monitoring of individuals' health. However, such manual processes are time-consuming and error-prone for disease detection. The recently proposed machine and deep learning-based solutions for the blood cell classification delivered better results, however, suffered from challenges as well. These challenges motivate us to propose a novel AI-based approach for automatic WBCs classification in this research work. © 2024 IEEE.

关键词： Cells

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

Brain MRI Classification Using Convolutional Neural Networks and VGG19: A Deep Learning Approach for Accurate Brain Disease Diagnosis

Brain MRI Classification Using Convolutional Neural Networks...

引用

Integration of Computational Intelligent System (ICICIS), International Conference on

作者： Sushama Ghodke Sunita Nandgave Dept. of Computer Engineering G H Raisoni College of Engineering and Management Pune India

Brain MRI classification is a critical task in medical imaging analysis for accurate diagnosis of brain diseases. This study presents a deep learning approach utilizing Convolutional Neural Networks (CNNs) and the VGG19 architecture to achieve precise brain disease diagnosis based on brain MRI scans. The proposed methodology leverages the power of CNNs and transfer learning, employing the pre-trained weights of the VGG19 model. The dept. and capability of the VGG19 architecture enable it to extract relevant features from brain MRI scans effectively. The process begins with data preparation and preprocessing to ensure dataset quality and consistency. The VGG19 model is adapted for brain MRI classification by replacing the final layers with task-specific layers. Transfer learning is applied by freezing initial layer weights and fine-tuning the remaining layers on the brain MRI dataset. The training process involves optimization using suitable algorithms and loss functions, with performance monitoring on a validation set. Hyperparameters are fine-tuned to achieve optimal results. The trained model is evaluated on an independent testing set to assess its diagnostic accuracy, utilizing metrics such as accuracy, precision, recall, and F1-score. The proposed deep learning approach demonstrates great potential for accurate brain disease diagnosis based on brain MRI scans. By automating the classification process, it reduces reliance on manual interpretation and enables faster, objective diagnoses. This study contributes to the advancement of medical imaging analysis and emphasizes the significance of deep learning techniques in brain MRI classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DESIGN OF PID controlLER FOR NONLINEAR MAGNETIC LEVITATION SYSTEM USING FUZZY-TUNING APPROACH

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer Science 2022年第2期84卷 45-62页

作者： Ismail, Laith S. Lupu, Ciprian Alshareefi, Hamid Luu, Duc Lich Dept. of Automatic Control University POLITEHNICA of Bucharest Romania Computer Technology Engineering Department Al Turath University Collage Baghdad Iraq Faculty of Mechanical Dynamics Vinh University of Technology Education Nghe an Viet Nam

This paper presents a dynamic model of a magnetic levitation system (Maglev) and suggests a Fuzzy Tuning of a proportional—integral--derivative controller (PID) that uses a fuzzy approach system to determine the PID controller's settings. The controller allows a steel ball to be suspended in free fall in the chosen position in reference to the electromagnet bottom end. The electromagnet levitation system can be controlled with a traditional PID controller, however because of the highly nonlinear of this system, it is unpredictable in the case of load and air gap changes. The fuzzy rules are developed to fuzzy tune PID while considering the control response and behavior of the system to find a solution to this problem. This paper shows excellent stability, rising time, settling time overshoot, and robust response results. The results reveal that this fuzzy PID controller solution can stabilize the ball's location and has strong disturbance rejection. The real time platform is designed for educational laboratory and test all the proposed control systems. © 2022, Politechnica University of Bucharest. All rights reserved.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

A Task Scheduling Algorithm for Hierarchical Hybrid Semi-Distributed System for Balancing Load

A Task Scheduling Algorithm for Hierarchical Hybrid Semi-Dis...

引用

Integration of Computational Intelligent System (ICICIS), International Conference on

作者： Lipika Datta Alok Ranjan Pal Dept. of Computer Science and Engineering College of Engineering and Management Kolaghat West Bengal India

In a distributed system, job submission is permitted on any autonomous node, leading to varying rates of job arrival across nodes. The heterogeneous computational capacities of these autonomous systems can result in overloaded and under-loaded nodes. Achieving uniform load distribution is crucial for efficiency, but it often requires extensive message transmission, causing an increase in network traffic. In centralized systems, load balancing decisions are made by a central server, introducing a single point of failure and significant network congestion near the server, limiting scalability. On the other hand, fully distributed systems offer scalability but lack global information accessible to all nodes. This paper introduces a hybrid hierarchical system, proposing that a select few nodes take on the responsibility of decision-making in the load balancing process, utilizing global information. In scenarios where most nodes lack system-wide global information, they can still contribute to decision-making by transmitting their current load state to a designated node, reducing the overall number of messages. The proposed model efficiently schedules jobs to nodes within a hybrid clustered hierarchical semi-distributed system, taking into account the current load status of each node.

关键词：

来源：评论

学校读者我要写书评

暂无评论

controlling PowerPoint Slide Presentations Through Hand Gestures 1

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Kumar, Ankit Singh, Kamred Udham Kumar, Gaurav Singh, Teekam Choudhury, Tanupriya Kumar, Santosh Department of Computer Engineering & Applications GLA University UP Mathura India School of Computing Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era Deemed to Be University Dehradun India Lavale Campus Pune India Department of Management Jaipuria Institute of Management Jaipur302033 India CSE Dept. Graphic Era Deemed to be University Uttarakhand Dehradun248002 India

ISBN: (数字)9789819997077

ISBN: (纸本)9789819997060

HCI, which stands for "human computer interaction," has been increasingly concerned with natural interaction methods in recent years. There are various ways we interact with computers that have benefited from the development of real-time hand gesture recognition programs. The detection of hand motions calls for the use of a camera. The primary form of participation is the employment of a web camera as a virtual human–computer interaction device. In this body of work, we look into how vision-based HCI methods of the present day make use of hand gestures. In the event that consumers are unable to utilize any type of input device or touch it, this project becomes incredibly useful. Gesture recognition makes it possible to complete an activity without physically accessing the usual input devices (mouse, keyboard, etc.). The user may doodle with his index finger and use his index and middle fingers together to control the pointer's movement on the screen. Using the tips of their index, middle, and ring fingers, the user may erase their artwork. Using their little finger, the user may go on to the next file, and using their thumb finger and pointing to the left, they can return to the previous file. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Learning Models Based on Tension Techniques for Sign Language Recognition

SSRN

引用

SSRN 2023年

作者： Attia, Nehal F. Faheem Said Ahmed, Mohamed T. Alshewimy, Mahmoud A.M. Computer and Automatic Control Dept. Faculty of Engineering Tanta University Tanta Egypt

Among the various ways of self-expression and communication between people, communication by speaking prevails. Speech presents a significant challenge for some disabled people, such as the deaf, hearing impaired, wordless, and dumb persons. Therefore, these people rely on the use of sign language to interact with others. Sign language is a system of movements and visual messages that ensure the integration of these individuals into groups that communicate vocally. On the other side, it is necessary to understand the gestures and linguistic semantics of these individuals. The main objective of this study is to establish a new model that enhances the performance of the existing paradigms in use for the recognition of American Sign Language (ASL). Therefore, three enhanced deep-learning models of YOLOv5 for recognizing the alphabetic and numeric information conveyed by hand motions are presented in this paper. These models depend on using different attention approaches. The suggested models were evaluated using the MU HandImages ASL dataset. The proposed models yielded superior results compared to those achieved by the initial version of YOLOv5. The modified models have reached their maximum accuracy of 98.9%, maximum recall of 97.5%, maximum mAP 0.5 of 99.2%, and maximum mAP 0.5:0.95 of 98.9%. © 2023, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Utilizing Blockchain Technology for Financial Services in Parallel, Distributed, and Grid Computing Frameworks

Utilizing Blockchain Technology for Financial Services in Pa...

引用

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Chokkamreddy, Prakash Palagati, Anusha Rao, Akurathi Lakshmi Pathi Maheswari, P. Mahadevan, Vanitha Balan, Santhosh Kumar School of Management Studies Guru Nanak Institutions Technical Campus Ibrahimpatnam Hyderabad India Dept. of Computer Science and Engineering Guru Nanak Institute of Technology Ibrahimpatnam Hyderabad India Department of Computer Applications KSR College of Arts and Science for Women Tiruchengode India College of Engineering and Technology University of Technology and Applied Sciences Al Mussanah Oman

ISBN: (纸本)9798331510299

Application of blockchain in financial services has opened new ways of efficiency in transaction processing, assets management and security. The application of parallel, distributed, and grid computing with blockchain in improving the functionality of financial services like real time financial transactions, high frequency trading, portfolio and risk analysis is examined in this paper. It has been ascertained that namely parallel and distributed computing together with blockchain are the most suitable for facing increasing needs in data in the sphere of financial services. It also investigates the use of grid computing frameworks and their effects on the correspondingly balanced flows of medium amongst multiple systems. Various issues such as security, privacy violations, and adherence to the law are also reviewed, and existing prospects for developing through smart contracts and consensus mechanisms using blockchain. Exploring how some of the most successful pilot use-cases of blockchain are applicable for future growth in the financial services industry offers insights into how blockchain will soon enter mainstream as a disruptive technology in the broader global financial sector. © 2024 IEEE.

关键词： Smart contract

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：