检索结果-内蒙古大学图书馆

American control Conference (ACC)

作者： Congran Zhao Wei Lin School of Mathematics and Statistics Jiangsu Normal University Xuzhou China Dept. of Electrical Systems and Computer Engineering Case Western Reserve University Cleveland Ohio USA

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

Sampled-data control via output feedback is studied for a family of strongly nonlinear systems with state and input delays. Under sample and hold, a delay-free output feedback control scheme is developed based on the emulation method, adding a power integrator (AAPI) technique, and recursive design of nonlinear observers. With the aid of Lyapunov-Krasovskii functional theorem, together with the idea of homogeneous domination, we prove that the proposed sampled-data output feedback controller makes the hybrid closed-loop systems with delays and uncertainty globally asymptotically stable, if the input delay and sampling period are limited. The family of time-delay uncertain systems under consideration goes beyond the Lipschitz or linear growth condition and is genuinely nonlinear as it contains uncontrollable/unobservable linearization and is not stabilizable, even locally, by any linear or smooth feedback. Application of the sampled-data control scheme presented in this paper is illustrated by an example with simulation.

关键词： Uncertain systems Uncertainty Emulation Observers Delays Closed loop systems Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Feature of Solar Radiation Forecast Services Use for Solar Plants 8

Feature of Solar Radiation Forecast Services Use for Solar P...

引用

8th IEEE International Conference on Energy Smart systems, ESS 2022

作者： Verbytskyi, Ievgen Lukianov, Mykola Strzelecki, Ryszard National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. of Electronic Devices and Systems Kyiv Ukraine Gdańsk University of Technology Faculty of Electrical and Control Engineering Gdańsk Poland

ISBN: (数字)9798350334418

ISBN: (纸本)9798350399202

Many countries, including Ukraine, are beginning to regulate the generation of energy produced from renewable energy sources more tightly to mitigate power imbalances. For this reason, electricity energy providers from renewable sources are forced to forecast energy generation and pay penalties if their forecast doesn't match with real energy generation. Renewable energy providers may use weather forecast as well as install energy storage system to minimize the penalties. The main purpose of the study is the review common cloudiness forecast services, uncertainty interval calculation of solar radiation for these services based on comparing with real solar radiation, estimating the opportunity of combining forecast data from several sources to minimize error and analysing the profit from the power plant using forecast services. © 2022 IEEE.

关键词： Solar radiation

来源：评论

学校读者我要写书评

暂无评论

Design and Experimental Verification of a Laser Engraving Machine

Design and Experimental Verification of a Laser Engraving Ma...

引用

Emerging Power Technologies (ICEPT), International Conference on

作者： Malik Shahaan Khalid Syed Muhammad Jaleed Arslan Zafar Sohaib Ali Khan Hafiz Zia Ur Rehman Zeashan Hameed Khan Dept. of Mechatronics Engineering Air University Islamabad Pakistan Department of Computer & Information Systems Engineering (CIS) N.E.D UET Karachi Pakistan Dept. of Avionics Engineering CAE NUST Islamabad Pakistan

This paper aims to develop a low-cost laser engraving machine. Materials like plastics, acrylic, glass, wood, cardboard, and leather have been used to engrave desired inputs. It have been found that this laser engraving process has a higher precision and accuracy as compared to traditional embellishing and embossing. The laser beam acquires thermal energy, which emerges from the machine and engraves the material. CREO 2.0 software is used for the 3D modeling and simulation of the machine. Arduino and different controller boards are tried and used in assembling the machine in less time. Different dependency and dimensional tests are conducted in order to validate the machine. The results are found to be satisfactory in terms of quality and cost. The final assembly is experimentally verified which is based on a 2D gantry that is mounted with a laser LED payload for laser engraving on various compatible materials.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Virtualization of Tiny Embedded systems with a robust real-time capable and extensible Stack Virtual Machine REXAVM supporting Material-integrated Intelligent systems and Tiny Machine Learning

arXiv

引用

arXiv 2023年

作者： Bosse, Stefan Bornemann, Sarah Lüssem, Björn University of Bremen Dept. Mathematics & Computer Science Bremen Germany University of Siegen Dept. Mech. Engineering Siegen Germany University of Bremen Dept. Electrical Engineering Bremen Germany Institute for Microsensors -actuators and -systems Bremen Germany

In the past decades, there has been a significant increase in sensor density and sensor deployment, driven by a significant miniaturization and decrease in size down to the chip level, addressing ubiquitous computing, edge computing, as well as distributed sensor networks. Material-integrated and intelligent systems (MIIS) provide the next integration and application level, but they create new challenges and introduce hard constraints (resources, energy supply, communication, resilience, and security). Commonly, low-resource systems are statically programmed processors with application-specific software or application-specific hardware (FPGA). This work demonstrates the need for and solution to virtualization in such low-resource and constrained systems towards resilient distributed sensor and cyber-physical networks using a unified low-resource, customizable, and real-time capable embedded and extensible stack virtual machine (REXAVM) that can be implemented and cooperate in both software and hardware. In a holistic architecture approach, the VM specifically addresses digital signal processing and tiny machine learning. The REXAVM is highly customizable through the use of VM program code generators at compile time and incremental code processing at run time. The VM uses an integrated, highly efficient just-in-time compiler to create Bytecode from text code. This paper shows and evaluates the suitability of the proposed VM architecture for operationally equivalent software and hardware (FPGA) implementations. Specific components supporting tiny ML and DSP using fixed-point arithmetic with respect to efficiency and accuracy are discussed. An extended use-case section demonstrates the usability of the introduced VM architecture for a broad range of applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition in Free Living Using a Wearable Sensor: A Two-Stage Approach

Human Activity Recognition in Free Living Using a Wearable S...

引用

International Conference on Awareness Science and Technology (iCAST)

作者： Tianhui Li Xue Zhou Kota Kokubun Wenxi Chen Division of Information System The University of Aizu Aizu-Wakamatsu Japan Dept. of Computer and Information Systems The University of Aizu Aizu-Wakamatsu Japan Dept. of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Japan

A novel two-stage approach for human activity recognition (HAR) using a wearable sensor is proposed in this study. The goal is to achieve both coarse-level and fine-level recognition of activities. The study focuses on five common activities: desk-working, driving, walking, downstairs, and upstairs. Three-axis acceleration signals were collected using a wrist-worn accelerometer sensor, and the activities were annotated during the participant’s daily routines. The acceleration data were preprocessed through segmentation, feature extraction, and normalization. In the first stage, a traditional machine learning model (decision tree) was used for coarse-level classification, distinguishing between activities with exercise and without exercise. In the second stage, deep learning models were employed for fine-level classification to recognize specific activities within the coarse classes. The performance of the models was evaluated using accuracy, sensitivity, and specificity. The proposed approach showed promising results with accuracies of 93.53%, 93.52%, 85.70%, 98.11%, and 85.91% respectively for desk-working, driving, walking, downstairs, and upstairs, demonstrating the effectiveness of the two-stage strategy for HAR. The proposed two-stage approach outperforms the one-stage method (decision tree classifier and deep learning model), particularly in imbalanced data, achieving a graceful equilibrium between sensitivity and specificity. The study highlights the importance of considering the complexity and variability of daily activities for accurate classification and resource optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VECOM: Variation Resilient Encoding and Offset Compensation Schemes for Reliable ReRAM Based DNN Accelerator

arXiv

引用

arXiv 2023年

作者： Jang, Je-Woo Nguyen, Thai-Hoang Yang, Joon-Sung School of Electrical and Electronic Engineering Yonsei University Seoul Korea Republic of Dept. of Semiconductor Systems Engineering Yonsei University Seoul Korea Republic of Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

Resistive Random-Access Memory (ReRAM)-based Processing In-Memory (PIM) Accelerator has emerged as a promising computing architecture for memory-intensive applications, such as Deep Neural Networks (DNNs). However, due to its immaturity, ReRAM devices often suffer from various reliability issues, which hinder the practicality of the PIM architecture and lead to a severe degradation in DNN accuracy. Among various reliability issues, device variation and offset current from High Resistance State (HRS) cell have been considered as major problems in a ReRAM-based PIM architecture. Due to these problems, the throughput of the ReRAM-based PIM is reduced as fewer wordlines are activated. In this paper, we propose VECOM, a novel approach that includes a variation-resilient encoding technique and an offset compensation scheme for a robust ReRAM-based PIM architecture. The first technique (i.e., VECOM encoding) is built based on the analysis of the weight pattern distribution of DNN models, along with the insight into the ReRAM's variation property. The second technique, VECOM offset compensation, tolerates offset current in PIM by mapping the conductance of each Multi-level Cell (MLC) level added with a specific offset conductance. Experimental results in various DNN models and datasets show that the proposed techniques can increase the throughput of the PIM architecture by up to 9.1 times while saving 50% of energy consumption without any software overhead. Additionally, VECOM is also found to endure low R-ratio ReRAM cell (up to 7) with a negligible accuracy drop. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

EHR based Prediction and Diet Recommender For Diabetes using Blockchain

EHR based Prediction and Diet Recommender For Diabetes using...

引用

Smart Technologies and systems for Next Generation Computing (ICSTSN), International Conference on

作者： Poonguzhali N N. Amarabalan School of Computer and Systems Sciences Jawaharlal Nehru University New Delhi India Dept. of Electrical and Electronics Engineering Manakula Vinayagar Institute of Technology Puducherry India

ISBN: (数字)9798350391565

ISBN: (纸本)9798350391572

Diabetes is an illness which is triggered due to high blood sugar levels. Ignoring diabetes is undesirable since the condition can have adverse impacts on the heart, kidneys, cholesterol levels, eyes, and almost all other organs. Diabetes will be easier to manage the earlier it is detected. To do this, researchers use a variety of machine learning techniques to more accurately forecast the onset of early diabetes in human bodies or in its patients. By constructing models using datasets that are available, machine learning techniques produce more accurate predictions. In the proposed work, Random Forest Algorithm is used to predict diabetes, as this technique outperforms in terms of accuracy. Individuals with diabetes, maintaining an appropriate diet is crucial. The majority of them aim to assist users in managing their blood sugar levels. A person’s weekly meal preparation habits can be attributed to a myriad of intersecting elements, such as taste, healthfulness, financial constraints, personal preferences, and lifestyle. An individual might experience it difficult to choose what to eat. To assist with the management of diabetes, the proposed system advises using a customized meal planning strategy. The diet plan suggested in the system is based on decision tree technique which is diabetic-friendly that is also socially, economically, and culturally acceptable and that can satisfy all nutritional needs while being mindful of calories. Following the prediction of diabetes and the suggestion of a diet plan, the patient’s medical information is stored in the EHR for convenient access.

关键词： Heart Accuracy Machine learning algorithms Predictive models Prediction algorithms Diabetes Blockchains

来源：评论

学校读者我要写书评

暂无评论

Cardiac Condition Detection Model Using Alexnet and Time-Frequency Representation of ECG Signals

Cardiac Condition Detection Model Using Alexnet and Time-Fre...

引用

E-Health and Bioengineering Conference (EHB)

作者： Mihai Aron Teofil Ilie Ursache Gladiola Petroiu Cristian Rotariu Dept. of Biomedical Sciences Grigore T. Popa University of Medicine and Pharmacy of Iasi Faculty of Medical Bioengineering Iaşi Romania Dept. of Automatic Control and Applied Informatics Gheorghe Asachi Technical University Faculty of Automatic Control and Computer Engineering Iaşi Romania

ISBN: (数字)9798331532147

ISBN: (纸本)9798331532154

Cardiac conditions are one of the leading causes of death worldwide. To address this, we designed a model that can detect cardiac conditions from a patient's electrocardiogram (ECG). This will convert the 1D ECG signal into a 2D scalogram using wavelet transforms with Morlet wavelets. With the help of a network based on the AlexNet convolutional neural network, it distinguishes between a normal ECG signal and one indicative of arrhythmia or congestive heart failure. The resulting model performs well, achieving a classification accuracy of 92.20% and providing a robust approach for detecting cardiac conditions.

关键词： Wavelet transforms Training Time-frequency analysis Accuracy Biological system modeling Electrocardiography Predictive models Congestive heart failure Convolutional neural networks Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Meteorological Factors’ Effect on Daily Heart Rate Variability Over Five Years

Evaluation of Meteorological Factors’ Effect on Daily Heart...

引用

International Conference on Awareness Science and Technology (iCAST)

作者： Kota Kokubun Tianhui Li Wenxi Chen Dept. of Computer and Information Systems The University of Aizu Aizu-Wakamatsu Japan Division of Information System The University of Aizu Aizu-Wakamatsu Japan Dept. of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Japan

The aim of this study is to investigate the effect of meteorological factors on heart rate variability (HRV) derived from daily electrocardiogram (ECG) data. Daily meteorological data were obtained from the Japan Meteorological Agency’s database. Daily ECG data were measured while bathing for five years. The subject was a healthy male in his fifties. After collecting ECG data, R-R intervals were calculated to perform HRV analysis in time domain and frequency domain. The evaluation of link between meteorological factors and HRV parameters was realized by utilizing meteorological factors’ importance calculated by Random Forest, and Steel-Dwass significant difference analysis of the values. Additionally, the evaluation was also performed by analyzing the obtained meteorological factors’ importance values using Granger Causality test. In Steel-Dwass test, several significant differences (p<0.05) were found, especially the importance value of air temperature was significantly different in three HRV parameters. I n Granger Causality test, we evaluate the temperature’s importance value for three HRV parameters, and there were significant differences (p<0.05) for HF and LF/HF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Xception CNN-Ensemble Learning Based Facial Emotion Recognition

Xception CNN-Ensemble Learning Based Facial Emotion Recognit...

引用

International Conference on Computing Communication control and Automation (ICCUBEA)

作者： Supriya Shirsath Vaishali Vikhe Pratap Vikhe Dept. of Computer Engineering Pravara Rural Engineering College Ahmednagar India Dept. of Instrumentation & Control Engineering Pravara Rural Engineering College Ahmednagar India

ISBN: (纸本)9781665484527

Emotions in human is an effective medium to study the mindset of a person. Since, expression on the face of human is significant approach to understand the condition and communicate with him to release the pressure or stress of person. The emotions and behavior have a strong relationship and is noteworthy in non-verbal form of communication. The advancement in medical science and use of image processing tools like Artificial Intelligence (AI) and Machine Learning (ML), can be helpful to recognize emotion, detect stress and depression level of a person. Thus, in this research work emotion recognition system is developed using Convolution Neural Networks (CNNs) with increased dept. and width. CNNs have been shown to enhance prediction accuracy. In terms of proper emotion categorization and accurate prediction, the suggested ensemble technique is effective. In this paper Xception CNN architecture is proposed for accurate facial emotions prediction along with an ensemble model, using Max Voting ensemble technique, mainly contributes in accurate classification. In proposed technique trained CNN models were loaded and for each trained model prediction probabilities were generated. Furthermore, it is then used for Max Voting to generate final emotion prediction. The CNN models are trained and evaluated on FER-2013 dataset.

关键词： Training Emotion recognition Computational modeling Face recognition Anxiety disorders Neural networks Machine learning

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：