检索结果-内蒙古大学图书馆

作者： Badshah, Shah Hussain Farhatullah khan, Gul Zaman Hassan, Muhammad Abul Junaid, Hazrat Sohail, Muhammad Mahbob, Muhammad Awais Ahamad, Izaz Ullah, Nadeem Department of Computing and Technology Abasyn University Peshawar Pakistan School of Automation China University of Geosciences Wuhan430074 China Department of Computer Software Engineering University of Engineering and Technology Mardan Pakistan Department of Computer Science and Information Technology University of Malakand Dir Lower Pakistan Department of Computer Science Bahria University Islamabad Pakistan Department of Computer Science University of Engineering and Technology Taxila Pakistan Department of Information Engineering and Computer Science University of Trento Trento38122 Italy

Today, brain tumor is a very dangerous disease that can even cause death. There are many ways to classify Brain MRI images of tumors. Various aspects of current research have limitations;some methods are accurate but take a long time to compute while some algorithms are fast, but with low accuracy. Consequently, a lot of effort is needed in this area. In this paper, our major goal is to reduce computation time and improve the classification accuracy for brain MRI images. This research proposes four phases: preprocessing, feature extraction, feature selection, and classification. During pre-processing, the median filter was used to reduce noise in the images, and the grayscale image size was reduced to further limit the image for efficient use. After that the Gray images are then given as inputs to the Feature extraction phase to select a limited feature from the image namely, texture features, shape features, smoothing features. The images features obtained in the feature’s extraction phase are still large, and we cannot simply feed them to machine learning models for processing due to computational constraints. So, we need to analyze it and pick out some interesting elements from the images. The statistical features namely, variances, mean, correlation are used in the feature selection phase to select more significant features to reduce the size of the features and reduce computational time. These features are combined and labeled in a file to train Machine Learning (ML) algorithms. We used two types of machine learning algorithms in the classification phase: classifier and evolutionary algorithm. The selected classifier algorithms results are combined in a file and we named it S-K-E-L Classifier and it gives us acceptable results in terms of accuracy and time. Similarly, an evolutionary algorithm named P-S-D-G Classifier also gives us acceptable results in terms of accuracy and time. Lastly, we combine both S-K-E-L Classifier and P-S-D-G Classifier in a file with

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Backstepping-Based Interception Control for an underactuated ASV with Experimental Validation

Backstepping-Based Interception Control for an underactuated...

引用

2024 China automation Congress, CAC 2024

作者： Lin, Bin Hu, Zhihuan Duan, Kairong Sun, Zhijian Xie, Wei Zhang, Weidong Wu, Defeng Zhong, Shangkun Department of Automation Shanghai Jiao Tong University Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Department of Automation Shanghai Jiao Tong University Crossocean of Suzhou Technology Co. Ltd. Shanghai China School of Information and Communication Engineering Hainan University Department of Automation Shanghai Jiao Tong University Haikou China School of Marine Engineering Jimei University Xiamen China

ISBN: (纸本)9798350368604

This article puts forward an interception control system designed specifically for an Autonomous Surface Vehicle (ASV). The prime goal of this system is to capture a moving target whose speed may vary, even when there are unknown external disturbances such as waves, wind, and stream currents. By applying the sophisticated backstepping method, it can guarantee that the relative speed between the interceptor ASV and the target globally gets close to a neighborhood of the desired value. The effectiveness of this interception control approach has been thoroughly verified through simulations as well as practical experimental tests. © 2024 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Vector Logic Analysis of Big Data

Vector Logic Analysis of Big Data

引用

2023 IEEE East-West Design and Test Symposium, EWDTS 2023

作者： Hacimahmud, Abdullayev Vugar Khakhanova, Hanna Litvinova, Eugenia Azerbaijan State Oil and Industry University Computer Engineering Department Baku Azerbaijan Kharkov National University of Radioelectronics Design Automation Department Kharkov Ukraine

ISBN: (纸本)9798350314847

The paper is focused on identification of patterns and objects using keywords and data. The following problems are considered: searching for object identifiers based on a truth table, where keywords are formed in columns that determine the similarity and difference of objects in the flow;defining the equivalence classes of keywords based on the analysis of truth table columns, built on a digitized data flow;generating a business process model in the form of a logical vector based on a binary matrix of patterns;using a business process model to verify the actions of operators performing regulatory functionality at the enterprise. Transfer of the von Neumann architecture into memory and replacing the powerful read-write processor with logical vector transactions to reduce energy and time costs when processing big data is proposed. Smart data structures and simple algorithms based on read-write transactions for in-memory big data as address computing are being developed. © 2023 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

PWM-Based Double Integral Sliding Mode Control for Current Control Loop of DC-DC Boost Converter 14

PWM-Based Double Integral Sliding Mode Control for Current C...

引用

14th International Conference on Power, Energy and Electrical engineering, CPEEE 2024

作者： Vongkoon, Pokkrong Benjanarasut, Jirawut Liutanakul, Pisit Division of Instrumentation and Automation Engineering Technology Faculty of Engineering and Technology King Mongkut's University of Technology North Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Thailand

ISBN: (纸本)9781643685199

The use of dc-dc boost converters is common for increasing output voltage and supplying power. These converters, being time-varying nonlinear circuits, encounter uncertainties in load and variations in input voltage and current over a wide range. Nonlinear sliding mode control (SMC) has emerged as a promising strategy, offering advantages in terms of stability and robustness against parameter and load fluctuations. To address switching frequency variations in conventional hysteresis-based SMC, the indirect SMC or pulse-width modulation (PWM)-based SMC has been adopted. However, the adoption of PWM-based SMC raised concerns regarding steady-state error in power converters. Despite incorporating the integral of the state variable into the sliding surface of PWM-based SMC, the steady-state error still exists. Focusing on the current control loop of a dc-dc boost converter with the goal of reducing steady-state error, this study proposes double integral sliding mode control (DISMC), which employs a sliding surface that includes the double integral term of the current error. Simulation and experimental results demonstrate that the proposed approach effectively mitigates the steady-state error of the inductor current. © 2024 The Authors.

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Framework for Decoding Salty Taste Information from EEG Signals: Distinguishing Brain Reactions to Saltiness of Comparable Intensity

引用

Food Science and Human Wellness 2024年

作者： Jingjing Liu Yifei Xu Xingwang Lian Tianming Liu Haohao Ning Xi Jiang Shixin Yu Shikun Liu Lu Huang Xiaojun Sun Jiangyong Li Dongfu Xu School of Automation Engineering， Northeast Electric Power University Department of Computer Science， the University of Georgia School of Life Science and Technology， University of Electronic Science and Technology of China

The perception of salty taste is crucial for individuals to make healthy food choices. Yet， the brain electrophysiological signals underlying salty taste perception have been poorly described. In this study， electroencephalography (EEG) was used to record brain activity induced by NaCl solution as a salty taste stimulus. A combination of a custom delivery device and stimulation paradigm was employed to preserve the salty taste signal clearly. A stimulus-response capture method was proposed that could adapt to individual differences in brain responses to salty taste and accurately segment salty taste response signals. Applying this method to the EEG processing workflow can form a complete data processing framework. The results showed that the neural response induced by salty taste reached a high activity level in the initial stage within a short period (0.2s)， and there was a sustained periodic response within 0.75s after the stimulation. Moreover， the salty taste information in the EEG signal was decoded， and discrimination of two similar concentrations of salty taste solutions was achieved far above the chance level (average identification rate: 89.66%). This study demonstrated experimental paradigms and research methods for understanding salty taste perception， which could provide references for research on other basic tastes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence 38

ControlSynth Neural ODEs: Modeling Dynamical Systems with Gu...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Mei, Wenjie Zheng, Dongzhe Li, Shihua The School of Automation and the Key Laboratory of MCCSE of the Ministry of Education Southeast University Nanjing China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

Neural ODEs (NODEs) are continuous-time neural networks (NNs) that can process data without the limitation of time intervals. They have advantages in learning and understanding the evolution of complex real dynamics. Many previous works have focused on NODEs in concise forms, while numerous physical systems taking straightforward forms, in fact, belong to their more complex quasi-classes, thus appealing to a class of general NODEs with high scalability and flexibility to model those systems. This, however, may result in intricate nonlinear properties. In this paper, we introduce ControlSynth Neural ODEs (CSODEs). We show that despite their highly nonlinear nature, convergence can be guaranteed via tractable linear inequalities. In the composition of CSODEs, we introduce an extra control term for learning the potential simultaneous capture of dynamics at different scales, which could be particularly useful for partial differential equation-formulated systems. Finally, we compare several representative NNs with CSODEs on important physical dynamics under the inductive biases of CSODEs, and illustrate that CSODEs have better learning and predictive abilities in these settings. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Minimum Time Headway in Platooning Systems Under the MPF Topology for Different Wireless Communication Scenario

Minimum Time Headway in Platooning Systems Under the MPF Top...

引用

作者： Abolfazli, Elham Besselink, Bart Charalambous, Themistoklis Aalto University School of Electrical Engineering Department of Electrical Engineering and Automation Espoo02150 Finland University of Groningen Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence Groningen Netherlands University of Cyprus School of Engineering Department of Electrical and Computer Engineering Nicosia1678 Cyprus

The multiple-predecessor following (MPF) topology is used in vehicle platoons to make it robustly string stable and reduce the minimum employable time headway. It has been demonstrated that communication imperfections such as time delays coming from wireless communications can affect string stability as well as the minimum time headway required to guarantee string stability. Specifically, it was shown that the larger the time delay, the longer the minimum time headway will be. However, by utilizing on-board vehicle sensors, such as radar, lidar and cameras, the distance and speed of nearby vehicles can be measured almost instantaneously, i.e., with almost no delay. Another effective parameter on string stability and minimum time headway is the heterogeneity of the vehicles. Due to the immense complexity of the MPF topology, string stability analysis of this topology in literature has been confined to homogeneous platoons. In this paper, we consider the case of heterogeneous platoons under the MPF topology with the use of the combination of sensors and wireless communications for receiving information. Following that, we find conditions to guarantee the internal and string stability for the heterogeneous case and propose the minimum time headway required to guarantee string stability. Finally, we provide a table, in which we propose the minimum time headway for two other wireless communication scenarios as well: (i) having no communication delay and (ii) having fully-delayed information, i.e., all information, whether it comes from the ego vehicle or its predecessors, is delayed. In addition to exploring the analysis of string stability for the vehicles with more possible connections (vehicles after the $r^{th}$ vehicle, when information from $r$ immediate vehicles is used), we study the string stability conditions (with which we aim at avoiding collisions) and find the minimum time headway for the first few vehicles (vehicle $r$ and all its predecessors). Numerical

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

New Skills and Knowledge for Digital Entrepreneurs in the age of Artificial Intelligence 19

New Skills and Knowledge for Digital Entrepreneurs in the ag...

引用

19th European Conference on Innovation and Entrepreneurship, ECIE 2024

作者： Orozova, Daniela Angelova, Nadezhda Zlatev, Zlatin Department of Informatics and Mathematics Faculty of Economics Trakia University Stara Zagora Bulgaria Department of Electrical Engineering Automation Computer Systems and Communications Faculty of Technics and Technologies Trakia University Yambol Bulgaria

ISBN: (纸本)9781917204149

Digital technologies are becoming increasingly complex and integrated, leading to significant transformations in society and the economy. The article aims to explore and summarize the new opportunities and potential risks of the widespread use of artificial intelligence (AI) in all aspects of life, to define the new skills and necessary knowledge of digital entrepreneurs and to highlight the need for transformation in modern education. Recognizing that the relationship between technology and business is two-way and becoming stronger, revealing that well-prepared employees are a guarantee of success and prosperity of companies in various fields, we try to focus on the main groups of qualities, skills and basic knowledge of students in the age of artificial intelligence. The development of the Internet, expansion of connectivity through social networks, the advent of AI, 3D printing, and immersive technologies like Augmented Reality, and Virtual Reality, require new knowledge and skills, leading to new challenges in education. Qualified personnel in this modern world must have solid professional training and systemic thinking (knowledge, skills, accumulated information), developed cognitive abilities, and personal skills based on collecting and analyzing large amounts of diverse information from heterogeneous sources. Questions arise: how can multiple information sources be combined effectively, and how can the fusion of multiple sources provide additional information to support decision-making processes? Combining information obtained from the real world makes the results heterogeneous and more informative. It follows the need to develop machine learning methods to extract relevant information from increasingly complex data sets. The goal is to improve the accuracy of the applied classification algorithms by combining predictions from multiple models, as well as obtaining a more stable final classification evaluation, effective handling of noisy data, adaptation to c

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

State of Charge Estimation for Zinc-Bromine Flow Batteries by Improved Long Short-Term Memory Network and Kalman Filter

State of Charge Estimation for Zinc-Bromine Flow Batteries b...

引用

2024 CPSS and IEEE International Symposium on Energy Storage and Conversion, CPSS and ISESC 2024

作者： Peng, Kaiwen Chen, Bichen Wang, Liguo Sidorov, Denis Dreglea, Aliona Wang, Zongjie School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China School of Electrical Engineering and Automation Northeast Agricultural University Harbin China Melentiev Energy Systems Institute Siberian Branch of the Russian Academy of Sciences Irkutsk Russia University of Connecticut Department of Electrical and Computer Engineering Mansfield United States

ISBN: (纸本)9798350380514

In order to improve the accuracy of estimating the state of charge (SOC) of zinc-bromine flow batteries (ZBFB) in the discharge stage and overcome the problems caused by sudden voltage changes, this paper proposes an algorithm for estimating and correcting the SOC. The core contribution is the proposal of an improved Long Short-Term Memory (LSTM) neural network algorithm, which considers the effect of the circulating pump speed on the battery voltage during the discharge stage, and establishes a neural network model for the battery. The estimation result of the improved LSTM network has a mean square error of 3.322, representing a 12% improvement in estimation accuracy compared to the traditional LSTM network. Additionally, Kalman filtering is employed for error mitigation to further enhance estimation accuracy. After applying the proposed method, the maximum error between the estimated SOC and the actual SOC is 1.91%, and the average error is 0.30%. This indicates that the proposed method improves the accuracy of SOC estimation through enhanced real-time LSTM network estimation and Kalman filtering error cancellation, particularly during voltage sudden change in the discharge of ZBFB. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Hemodynamic Analysis and Diagnosis Based on Multi-Deep Learning Models

引用

Fluid Dynamics & Materials Processing 2023年第6期19卷 1369-1383页

作者： Xing Deng Feipeng Da Haijian Shao School of Automation Key Laboratory of Measurement and Control for CSEMinistry of EducationSoutheast UniversityNanjing210096China School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas Vegas89154USA

This study employs nine distinct deep learning models to categorize 12,444 blood cell images and automatically extract from them relevant information with an accuracy that is beyond that achievable with traditional *** work is intended to improve current methods for the assessment of human health through measurement of the distribution of four types of blood cells,namely,eosinophils,neutrophils,monocytes,and lymphocytes,known for their relationship with human body damage,inflammatory regions,and organ illnesses,in particular,and with the health of the immune system and other hazards,such as cardiovascular disease or infections,more in *** results of the experiments show that the deep learning models can automatically extract features from the blood cell images and properly classify them with an accuracy of 98%,97%,and 89%,respectively,with regard to the training,verification,and testing of the corresponding datasets.

关键词： Blood cell analysis deep learning models classification-detection

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：