检索结果-内蒙古大学图书馆

2023 International Conference on Future Energy Solutions, FES 2023

作者： Hassanian, Reza Helgadóttir, Ásdís Riedel, Morris University of Iceland The Faculty of Industrial Engineering Mechanical Engineering and Computer Science Reykjavik Iceland Juelich Supercomputing Centre Germany

ISBN: (纸本)9798350332308

The purpose of this research is to develop a theoretical method for predicting the wake region downstream of the flow from a top view of a vertical axis wind turbine (VAWT) and to examine the wake loss effects of the VAWT. Previous literature has reported that the wake region of the VAWT is not symmetric, and its downstream is similar to a circular cylinder wake street. The airflow of the VAWT is turbulent, and the inviscid incompressible flow can be applied to its range. Therefore, the current study analyzed the flow over a cylinder with circulation to investigate the velocity, pressure coefficient, and tip speed ratio and to observe the similarity between the cylinder and the VAWT. The results of this study demonstrate remarkable similarity, particularly with respect to the asymmetry of the wake region due to the distinct velocity speed in two opposite locations of the VAWT. Moreover, the pressure coefficient functionality and curvature are similar to the available measurements of the VAWT. This model can be further developed and examined under varied conditions to provide a theoretical wake loss model for VAWTs. This will lead to the expansion of VAWTs' applications in green, sustainable, and clean energy production. © 2023 IEEE.

关键词： Vertical axis wind turbine

来源：评论

学校读者我要写书评

暂无评论

Siamese Meets Diffusion for Morphing Attack Detection

Siamese Meets Diffusion for Morphing Attack Detection

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Malik, Shreya Malik, Latesh Malik, Gagan Indian Institute of Information Technology Dept of Computer Science and Engg. Guwahati India Government College of Engineering Dept of Computer Science and Engg. Nagpur India GH Raisoni University Dept of Mechanical Engineering Amravati India

ISBN: (纸本)9798331517953

Biometric systems, such as facial recognition, are increasingly employed for secure identity verification. However, they are susceptible to morphing attacks, wherein images of different individuals are subtly blended to deceive biometric systems. Detecting these morphed images is challenging due to the subtle nature of the modifications. This paper proposes a novel approach that leverages diffusion models and Siamese networks to enhance morph detection capabilities. Diffusion models enable the extraction of fine-grained details by recreating the image after adding noise, while the Siamese network evaluates these details to accurately identify morphed images. Our method emphasizes improved detection accuracy, demonstrating significant potential to strengthen biometric security systems against morphing attacks. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Analyzing Muscle Synergies for Finger Movement Recognition using sEMG Signals 11

Analyzing Muscle Synergies for Finger Movement Recognition u...

引用

11th IEEE International Conference on Signal Processing and Integrated Networks, SPIN 2024

作者： Sarmah, Nilavjyoti Khargharia, Panchal Prakrit Bora, Rajdeep Hazarika, Shyamanta M. Indian Institute of Technology Guwahati Mechanical Engineering Guwahati India Tezpur University Computer Science and Engineering Tezpur India Indian Institute of Technology Guwahati Mechanical Engineering and M F School of DS & AI Guwahati India

ISBN: (纸本)9798350308433

The study focuses on extracting muscle synergy from electromyographic (EMG) signals for recognition of finger movement. The process involves using a non-negative matrix factorization (NNMF) technique to decompose the EMG signal matrix into muscle synergies and their corresponding activation coefficients. The synergy obtained from this process reveals the underlying patterns in the EMG data that help in the classification of finger movements. Other steps include hyperparameter tuning using grid search, feature selection using sequential forward selection (SFS), and classification using support vector machine (SVM). The proposed method shows the effectiveness of NNMF in detecting muscle synergy for accurate classification of finger movements. A classification accuracy of 97.5±1.67% is obtained. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Study of Advantages, Limitations, Applications and Similar Tool of ChatGPT

Comprehensive Study of Advantages, Limitations, Applications...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Rathi, Nayan Bandavade, Prakash Chaubey, Himanshu Jaju, Santosh Thakur, Shruti G H Raisoni College of Engineering Computer Science Engineering Department Maharashtra Nagpur India G H Raisoni College of Engineering Mechanical Engineering Department Maharashtra Nagpur India

ISBN: (纸本)9798331517953

ChatGPT is nothing but a natural language processing model which takes input from humans and gives them the response which is appropriate according to him. ChatGPT gives the data which is already in the search engine and cannot create the data of its own. It is not creative, as it cannot create its own content. It is very powerful tool which helps in writing code, preparing for interview, calculating mathematical solution though it has various drawbacks such as it lacks logical reasoning, cannot calculate complex mathematical calculation like irrational number to the power of irrational number, it also makes grammatical error and it does not have information from recent scenario, you get information which occurred 2 years back. But it has industrial application like it is used as customer support in many companies, used to keep routine of employee in company by providing them proper schedule for work, it is also used to get code which makes works of employee lot more easier, So this are the key points about it. © 2024 IEEE.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Intelligent Modeling Method to Optimal Predictive Model for Metal Powder Injection Molding Gears Using Fuzzy-Logic-Based Multi Objective Design

引用

International Journal of Fuzzy Systems 2023年第6期25卷 2338-2355页

作者： Huang, Wei-Tai Kung, Chien-Yu Chou, Jyh-Horng Department of Mechanical Engineering National Pingtung University of Science and Technology Pingtung Taiwan Department of Mechanical and Computer-Aided Engineering Feng Chia University Taichung407 Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung807 Taiwan

This study will use intelligent modeling to optimize the metal powder injection molding gear process. The robust process combined with fuzzy theory would be used to find process parameters for optimizing process single and multiple quality characteristics. And establish a reverse transfer neural network and adaptive neuro-fuzzy system prediction model. The model hyperparameter structure will be optimized during the modeling process to improve accuracy. The industry can use it to reduce process uncertainty, cost, and extremely a process innovation. The experimental results are single-objective optimization. After optimizing the parameters, the process target displacement, volume shrinkage rate, and powder concentration, compared with the manufacturer's original process, the improvements are increased by 5.79%, 5.66%, and 1.57%. Optimizing multiple quality characteristics has risen by 5.37%, 5.66%, and 0.31%. In the prediction model building part, after the optimization experiment of hyperparameter setting, the accuracy of the backward pass neural network model can reach 96.99%;the accuracy of the adaptive neuro-fuzzy system model can reach 97.45%. © 2023, The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association.

关键词： Injection molding

来源：评论

学校读者我要写书评

暂无评论

An Artificial Intelligence based Prototype of Driver Drowsiness Detection for Intelligent Vehicles

An Artificial Intelligence based Prototype of Driver Drowsin...

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Purohit, Jahanvi Soni, Vaibhav Namdev, Anurag Mishra, Abhishek Samal, Satyajit Manit Department of Computer Science and Engineering MP Bhopal India Iet Department of Mechanical Engineering UP Lucknow India Manit Department of Mechanical Engineering MP Bhopal India

ISBN: (纸本)9798350337617

In the past few decades, the use of autonomous vehicles has been increased at a pacing rate. Autonomous vehicles (AVs) are growing more popular because they alleviate traffic congestion and elevates safety. This is owing to the development of artificial intelligence techniques in numerous applications. Moreover, AVs improve fuel efficiency. As the number of vehicles increasing day by day the travel time also increases because of the traffic jam and it leads to the driver feeling sleepy or drowsy. Driver drowsiness is a serious problem that can lead to fatal accidents on the road. As a result, various studies have been conducted to develop effective driver drowsiness detection systems. This paper provides an overview of the problem of driver drowsiness and its consequences. It also presents a concise summary of the most relevant studies and methods that have been proposed for detecting driver drowsiness. Finally, a proposed method for driver drowsiness detection is discussed in detail. Driver drowsiness is a major cause of accidents on the road, especially during long drives or at night. Drowsy drivers have slower reaction times, impaired judgement, and decreased situational awareness. This can lead to accidents that result in injury or death. As a result, there has been considerable interest in developing effective driver drowsiness detection systems. Several studies have been conducted to detect driver drowsiness using various methods. Some of the most commonly used methods include monitoring the driver's eye movements, head movements, heart rate, and steering wheel movements. Machine learning algorithms have also been used to analyze these signals and determine the driver's level of *** of the proposed methods for driver drowsiness detection involves using a combination of machine learning algorithms and a neural network. The system is trained using a large dataset of drivers in various driving conditions. The system is designed to detect changes in the

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

A Variable Gain Discrete Time Sliding Mode Observer for MMC Capacitor Voltage Estimation 7

A Variable Gain Discrete Time Sliding Mode Observer for MMC ...

引用

7th IEEE International Electrical and Energy Conference, CIEEC 2024

作者： Lei, Yao Tianhao, Li Xinyu, Zhou Xuanang, Dong Yufei, Zhang College of Mechanical Engineering University of Shanghai for Science and Technology China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology China College of Information and Electrical Engineering China Agricultural University China

ISBN: (纸本)9798350359558

Modular Multilevel Converter (MMC) is one of the main development directions in the future medium and low voltage DC transmission and distribution field. In engineering, capacitive voltage sensors are usually configured for all submodules to ensure high reliability measurement, but this makes the hardware structure more complex. This paper proposes a control algorithm for online adjustment of observer gain based on discrete-time sliding mode observer (DTSMO). A weighted error judgment energy function is defined and three modes are distinguished. A transition mode is introduced between the approaching mode and sliding mode, and the gain within each mode is adjusted online according to the size of each component error function. This algorithm suppresses the chattering of traditional DTSMO during parameter changes and reduces the voltage error of each observed SM, this observer can eliminate all capacitive voltage sensors within a single bridge arm, and is designed based on the consideration of uncertain parameters outside of MMC. Its stability and convergence have been mathematically proven. Finally, simulation and experimental results of hardware prototypes has verified that the proposed VDTSMO observer has good steady-state and transient performance. © 2024 IEEE.

关键词： Bridges

来源：评论

学校读者我要写书评

暂无评论

A novel forecasting model for time series using optimized interval division and fuzzy relationships

引用

Neural Computing and Applications 2025年第5期37卷 3869-3885页

作者： PhamToan, Dinh Vo-Van, Tai Faculty of Mechanical - Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City Viet Nam College of Natural Science Can Tho University Can Tho City Viet Nam

This study builds an effective forecasting model for time series based on significant improvements of the fuzzy clustering algorithm. Firstly, we use the universal set, which is the percentage change between two consecutive time points, and divide it into unequal intervals using the automatic clustering algorithm that adjusts the number of clusters. Next, we propose the networks so that establish the fuzzy relationship of the elements in the universal set and the intervals based on the improved inverse fuzzy number. Finally, a new principle for future forecasting is built based on these two improvements. The proposed model details the steps and is clearly illustrated through a specific numerical. The convergence of the proposed algorithm is also considered and addressed. The proposed model has demonstrated effectiveness by outperforming many other models applied to the M3 dataset with 3,003 series, the M4 dataset with 100,000 series, and the well-known benchmark dataset. The proposed model is also applied to forecast the number of people infected and deceased due to COVID-19 in Southeast Asian countries. This application also demonstrates the advantages of the proposed model over many existing models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Multigrain-Multilabel (MGML) Dataset for Smartphone-Based Human Activity Recognition

引用

SN computer science 2024年第7期5卷 859页

作者： Thakur, Tushti Saha, Anindita Mallik, Manjarini Chowdhury, Chandreyee Department of Mechanical Engineering Jadavpur University Kolkata India Department of Information Technology Techno Main Saltlake Kolkata India Department of Computer Science and Engineering Jadavpur University Kolkata India

The efficacy of machine learning-based Human Activity Recognition (HAR) heavily relies on the datasets. Existing benchmark HAR datasets on smartphone accelerometer sensors provide mostly single-labeled, fine-grained activities like walking, sitting, etc. collected in lab set-up. In real life, users hardly perform an activity in isolation. Rather, the activities are often performed in sequence with non-uniform transition duration. So, for faster transitions, fine-grained data annotation is difficult and error-prone. A few existing benchmark datasets report coarse-grained activities like working, cooking, etc. that do not indicate enough information about the constituent fine-grained activities performed. HAR performance in these cases cannot satisfy real-life purposes like physical fitness prediction, or rehabilitation after surgery. To address this challenge, a Multigrain-multilabel (MGML) dataset has been designed by collecting smartphone accelerometer sensor readings from four users. Here, the coarse-grained activities are multi-labeled, and both fine-grained and coarse grained activities are covered. That means one can get information regarding the physical movements of the user from labelling information. The MGML dataset has been evaluated with four machine learning classifiers. We report a baseline classification accuracy of 95.40% for the classifiers considered. Experimentation has been conducted on the entire filtered and feature-engineered data. The effectiveness of feature engineering has also been shown. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Feature engineering Human Activity Recognition Machine learning Multi-labeled dataset Smartphone sensing

来源：评论

学校读者我要写书评

暂无评论

An fNIRS labeling image feature-based customized driving fatigue detection method

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第9期14卷 12493-12509页

作者： Zeng, Lingqiu Zhou, Kun Han, Qingwen Wang, Yang Guo, Gang Ye, Lei College of Computer Science Chongqing University Chongqing400044 China College of Communication Engineering Chongqing University Chongqing400044 China College of Mechanical and Vehicle Engineering Chongqing University Chongqing400044 China

The practicality of driving fatigue detection approaches largely depends on social acceptance. Physiological-based methods perform well, but they are rarely accepted by drivers, while subjective evaluations cannot support real-time detection. However, image-based approaches with relatively high take-up rates, ace detection accuracy problems, thus causing driver dissatisfaction. To satisfy the demand of logistic companies, in this paper, a customized driving fatigue detection method that integrates a subjective evaluation, physiological features and image features is proposed. As a result, a real-time driving fatigue detection system, RefreshingDrive, is designed. First, the relationships between questionnaire results, near-infrared spectroscopy indices, and oxyhemoglobin (HBO) and deoxyhemoglobin (HHB) values are investigated to express the individual differences among fatigue thresholds. Then, a long short-term memory network is constructed to find an individual-oriented HBO+HHB threshold, which is used to divide an image dataset into two subdatasets, namely, a fatigue dataset and a nonfatigue dataset. After that, a facial feature-based fatigue detection method, in which a multitasking cascaded eye convolution network is proposed to extract eye features while a 3D ConvNet is employed to recognize fatigue actions, is presented. Moreover, a fatigue evaluation rule, the Action-Blink Fusion Rule (A-B fusion), is proposed to recognize driving fatigue. Experimental results show that the proposed method achieves a fatigue recognition accuracy of 95.3%. Finally, an on-road test is performed to verify the effectiveness of the proposed approach. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Long short-term memory

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：