检索结果-内蒙古大学图书馆

SICE Annual Conference

作者： Nobuyuki Yoshikawa ryoichi Takase Information Technology R&D Lab. Mitsubishi Electric Kanagawa Japan Research & Development Group Hitachi Ltd Tokyo Japan

The gain penalty method is investigated to ensure the stability of the closed-loop system consisting of a neural network controller and a target plant. The gain penalty is defined to constrain the L 2 gain of the closed-loop system in order to satisfy the small-gain theorem. To apply the gain penalty method for the target plant which do not have finite L 2 gain, the imaginary feedback gain is introduced to be the plant that has a finite L 2 gain. Numerical experiments are performed on two types of linear time-invariant (LTI) systems to investigate the property of the proposed methods in terms of learning efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gas anomaly data detection based on hybrid neural network 7

Gas anomaly data detection based on hybrid neural network

引用

2022 7th International Conference on Electronic technology and Information Science, ICETIS 2022

作者： Li, Xiaolong Xu, Junwu Liao, Jiayin Wang, Chaoqun Chen, Xiaohui Li, Fang School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Product Development Department Shanghai Academy of Spaceflight Technology Shanghai China Gas Intelligent Application Technology R&D Center Shanghai Aerospace Energy Co. Ltd Shanghai China

ISBN: (纸本)9783800757794

The accurate measurement of gas flow is directly related to the economic benefits and social interests of gas enterprises. Moreover, as a kind of time-series data, there is a serious imbalance in the distribution of positive and negative samples in the data, which leads to low accuracy and difficulty in detecting gas anomaly data. To address these problems, a cost-sensitive hybrid network model is proposed in this paper. The model combines the stronger local feature learning ability of CNN network and the better sequence feature learning ability of GrU network, and then introduces a cost-sensitive loss function to solve the problem of inaccurate classification accuracy due to skewed data distribution. The experimental results show that using this model can find the outliers in the measurement data more accurately, which has some reference significance for the accurate measurement of traffic. © VdE VErLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Flow of gases

来源：评论

学校读者我要写书评

暂无评论

Implementation of Precision Education System Based on Machine Learning Model 1

引用

7th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Shanmugasundar, G. Chohan, Jasgurpreet Singh Kalita, Kanak Department of Mechanical Engineering Sri Sai Ram Institute of Technology Chennai600044 India Department of Mechanical Engineering and University Center for Research & Development Chandigarh University Mohali140413 India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi600062 India Jadara University Research Center Jadara University Irbid21110 Jordan

ISBN: (数字)9783031733185

ISBN: (纸本)9783031733178

Precision Education (PE) is an approach that emphasizes the use of various forms of technology to personalize students’ educational opportunities according to their unique requirements. In order to facilitate effective learning that is suited to the needs of each individual, it is necessary to have complete information about the learning process. PE describes a personalized approach to classroom instruction. We propose dignified reinforcement Learning (drL) which includes all the essential elements required for PE, in order to determine the impact of developing multimodal innovations on individualized learning. The system aims to address issues with the standard model of education analysis, such as insufficient internal validity, predictive validity, timeliness, comparability, and understandability, in order to provide more precise instruction. Networking sites, the digital classroom, the intelligent agent, and the panel are the four fundamental aspects of an rL-based technology. Through model-based rL, the head attribute of the continuous educational environment gathers and processes a multimodal flow of student records from the various modules to create laws of appropriate behaviors that optimize the long-term benefits for both the individual and the computer. To demonstrate the usefulness of the proposed model, experimental evidence was presented using a subset of multimodal data. Practical and theoretical implications for future digital learning approaches and investigations may be drawn from rL systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

development of Python-Based Applications for Virtual Instrument Control Using PyQt5, PyVISA, and SCPI Protocol

Development of Python-Based Applications for Virtual Instrum...

引用

Emerging Trends in Information technology and Engineering (ic-ETITE), Conference on

作者： Abhishek Singh rao deepak Sai Anita Taterao Mahajan Vaibhav Pratap Singh rahul Neiwal Haribabu Pasupuleti Sudarsan S d Internet of Things (IoT) Group Centre for Development of Advanced Computing Bangalore Bengaluru India R&D in IT Group Ministry of Electronics and Information Technology Delhi India Centre for Development of Advanced Computing Bangalore Bengaluru India

This work aims to create desktop applications to enable virtual access and control to prominent lab equipment like signal generators, oscilloscopes, spectrum analyzers, etc. The developed applications utilize PyQt5 and PyVISA Python libraries, enabling the creation of Graphical User Interfaces (GUIs) and virtual instrument communication. The applications support USB and Ethernet connection between the PC and the instruments. We demonstrate Python-enabled applications to remotely access a Vector Signal Generator, an Oscilloscope and in conjugation, also use an OEM's Spectrum Analyzer PC application to complete a framework for remote signal generation, analysis, and acquisition which can be useful in various research and testing scenarios in the modern hybrid work culture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Study on the Slat Noise of 30P30N High-Lift Airfoil Basd on High-Order Wall-resolved Large-Eddy Simulation

arXiv

引用

arXiv 2024年

作者： Zhang, Keli Lin, Shizhi Liu, Peiqing Liu, Shihao Liu, Kai Beihang University Beijing100191 China Rankyee Technology Beijing Beijing100097 China School of Aeronautic Science and Engineering China Solver R&D and Development Center CTO

This study presents wall-resolved large-eddy simulations (WrLES) of a high-lift airfoil, based on high-order flux reconstruction (Fr) commercial software dimaxer, which runs on consumer level GPUs. A series of independence tests are conducted, including various Ffowcs Williams-Hawkings sampling surfaces, different mesh densities, simulations at 4tℎ and 5tℎ order accuracies, and varying spanwise lengths, to establish best practice for predicting slat noise through high-order WrLES. The results show excellent agreement with experimental data while requiring significantly fewer computational resources than traditional second-order methods. An investigation on the effects of reynolds number (re) is performed by scaling the airfoil size, with reynolds numbers ranging from 8.55 × 105 to a real aircraft level of 1.71 × 107. By applying simple scaling through Strouhal number (St), spanwise correction, and distance from the receiver, the far-field noise spectra for different reynolds numbers can be coincided. Additionally, simulations are performed at four angles of attack: 3◦, 5.5◦, 9.5◦, and 14◦. The results indicate that higher angles of attack lead to a less intense feedback loop, resulting in lower tonal noise frequencies and reduced noise amplitude. The maximum noise reduction observed is over 14dB when comparing 14◦ to 3◦. Furthermore, an improved formula is proposed to enhance the prediction of slat noise tonal frequencies and to better elucidate the mechanism behind tonal noise generation. Copyright © 2024, The Authors. All rights reserved.

关键词： reynolds number

来源：评论

学校读者我要写书评

暂无评论

Novel Gender and Age Prediction from real Time Facial Images using Linear regression Algorithm 8

Novel Gender and Age Prediction from Real Time Facial Images...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Nalini, N. Shahila, d. Ferlin deva rosi, A. Tamilselvi, M. Giri, Jayant Sherideh, Ala'a Al Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India Saveetha University Saveetha School of Engineering Department of Ece Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India Zarqa University College of Information Technology Department of Cyber Security zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (纸本)9798350367904

The proposed novel algorithm utilizes linear regression in real-time facial image analysis for predicting both gender and age. By leveraging features extracted from facial data, the model aims to provide accurate and instantaneous predictions. The emergence of social media platforms has made the automatic classification of gender and age increasingly relevant. real-time frame processing is possible with OpenCV. The expected gender and age are provided as the output, and this frame is provided as the input. The capacity to autonomously ascertain age and gender from facial images because of its versatility in facial analysis applications. However, the current models are still behind the required accuracy level, which is required for these models to be used in real-world applications, because of the significant intraclass variance of face images (such as difference in lighting, position, scale, and occlusion). In this work, a deep learning framework uses an ensemble of residual and attentional convolutional networks to reliably determine the gender and age group of facial photographs. By employing an attention mechanism, this model can concentrate on the important and instructive aspects of the face, increasing its prediction accuracy to 90.15%. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Ensemble Approach for Optimizing Variable rigidity Joints in robotic Manipulators Using MOALO-MOdA 6th

Ensemble Approach for Optimizing Variable Rigidity Joints in...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Shanmugasundar, G. Pal, Subham Chohan, Jasgurpeet Singh Kalita, Kanak Department of Mechanical Engineering Sri Sairam Institute of Technology Chennai India Department of Aerospace Engineering and Applied Mechanics Indian Institute of Engineering Science and Technology Shibpur India Department of Mechanical Engineering and University Centre for Research and Development Chandigarh University Mohali India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi India

ISBN: (纸本)9783031503290

A novel ensemble-based optimization technique is proposed for designing a robot manipulator variable stiffness joint. A multi-objective optimization is performed by considering the maximization of generated torque and the minimization of the weight of the joints. This investigation considers three design parameters (i.e., inner stator width, outer stator width, and magnet height) to maximize torque and reduce weight. Multi-objective ant lion optimization (MOALO) and multi-objective dragonfly algorithm (MOdA) optimization techniques are employed to generate Pareto fronts. These multiple Pareto fronts from the same algorithm are collated and condensed using non-dominated sorting (NdS) to reject the most dominant solutions. These new and improved Pareto fronts are called MOALO and MOdA ensembles. Next, the MOALO and MOdA ensemble Pareto front solutions are collated together, and NdS is performed again. The resulting Pareto front containing solutions of both MOALO and MOdA is referred to as the MOALO-MOdA ensemble. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Pareto Optimization of Laminated Composite Plates with Non-dominated Sorting Whale Optimization Algorithm (NSWOA) Ensemble 6th

Pareto Optimization of Laminated Composite Plates with Non-d...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Shanmugasundar, G. Pal, Subham Chohan, Jasgurpeet Singh Kalita, Kanak Department of Mechanical Engineering Sri Sairam Institute of Technology Chennai India Department of Aerospace Engineering and Applied Mechanics Indian Institute of Engineering Science and Technology Shibpur India Department of Mechanical Engineering University Centre for Research & Development Chandigarh University Mohali India Department of Mechanical Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Avadi India

ISBN: (纸本)9783031501500

Plates are non-curve structural elements used in civil, aerospace and marine constructions. Optimization of these structures is important for its longevity and safe design. This study uses a novel non-dominated sorting whale optimization algorithm (NSWOA) ensemble technique to optimize the design of laminated composite plates. The objective of the study is to maximize the fundamental frequency and frequency separation. The orientations of the fiber in each layer are considered the design variables. This study considers a rectangular plate with a symmetric arrangement of lamina under simply supported boundary conditions. The results obtained through the implementation of the NSWOA ensemble technique are presented, and this will assist in future research. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Laminating

来源：评论

学校读者我要写书评

暂无评论

development of Low-Carbon Affordable Apartments in the Hot and Humid Climate of Indonesia: Construction of a Full-Scale Experimental House 5th

Development of Low-Carbon Affordable Apartments in the Hot a...

引用

5th International Conference on Building Energy and Environment, COBEE 2022

作者： Alfata, Muhammad Nur Fajri Trihamdhani, Andhang rakhmat Kubota, Tetsu Asawa, Takashi Directorate for Settlements and Housing Engineering Development Ministry of Public Works and Housing Jakarta Selatan Indonesia YKK AP R&D Center Indonesia Tangerang Indonesia Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan School of Environment and Society Tokyo Institute of Technology Meguro City Japan

ISBN: (纸本)9789811998218

A full-scale experimental house to develop comprehensive passive cooling techniques for affordable apartments in the hot and humid climate of Indonesia was constructed in the city of Tegal in 2020. It is a 2- to 3-storey apartment building with a pilotis on the ground floor, consisting of 12 units with a total floor area of approximately 2000 m2. This study explains the passive design concept of the experimental house, focusing on the ventilation strategies using a vertical void, and presents the results of a preliminary field measurement of indoor thermal environments. Major thermal parameters were measured under different ventilation conditions. The results showed that the structural cooling effect by the nocturnal ventilation was apparent, but it was difficult to achieve indoor thermal comfort during the peak hours by the nocturnal ventilation alone. This implies that further additional passive cooling techniques such as radiant floor cooling and evaporative cooling are necessary. Moreover, the effect of indoor wind speed on thermal comfort of the tropical occupants should be considered more in detail. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Ventilation

来源：评论

学校读者我要写书评

暂无评论

HappyCruise - Integrated Information System of personalized information and security in the tourism industry. 13

HappyCruise - Integrated Information System of personalized ...

引用

13th International Conference on Information, Intelligence, Systems and Applications, IISA 2022

作者： Kotsopoulos, Konstantinos I. Pavlidis, George Viennas, Emmanouil Baratis, Evdoxios Giannopoulou, Georgia Papadopoulos, Alexandros Spilios, Manos Alexogianni, Paraskevi Sakkopoulos, Evangelos R&d Lab Omega Technology Patra Greece University of Patras Department of Computer Engineering and Informatics Rio Achaia26504 Greece Software Development Modus Sa Athens Greece Software Development Intraway Ltd Athens Greece University of Piraeus Department of Informatics Piraeus Greece

ISBN: (数字)9781665463904

ISBN: (纸本)9781665463904

HappyCruise project offers cruise passengers a comprehensive solution that provides personalized security and information to reduce the feeling of insecurity and highlight the competitive advantages of Cruise destinations, offering a more comprehensive visit experience based on their interests and the available time while enhancing the Branding of the city and the port. The creation of a robust, useful, and engaging traveler mobile application with essential features is proposed. It combines offering information about suggested points of interests and other activities in the limited time of a cruise passenger's visit, security through a simple and intuitive alert system which informs the Cruise Security through a web interface about the passenger's Id, the type of the danger and the geographical position of the passenger. The passenger can also receive notifications from the ship's staff regarding the cruise schedule, the remaining time of staying at the port and of any important security messages. The mobile application also integrates a series of motivation teasers including gamified notifications with suggestions based on the passengers' interest, nearby points of interests presented with augmented reality, guidance to destinations with augmented reality navigation arrows, suggested services and products in the port area. Additionally, a biometric passenger identification system utilizing face recognition technology is used providing a quick and reliable check-in that eliminates the need of submitting passport or boarding card many times. © 2022 IEEE.

关键词： Biometrics

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：