检索结果-内蒙古大学图书馆

17th International Conference on Indoor Air Quality and Climate, INDOOR AIR 2022

作者： Alonso, Maria Justo Jørgensen, Rikke Bramming Madsen, Henrik Mathisen, Hans Martin Dep. Energy and Process Engineering Trondheim Norway Dep. Industrial Economics and Technology Management Trondheim Norway Technical University of Denmark Applied Mathematics and Computer Science Kgs. Lyngby Denmark

Demand-controlled ventilation (DCV) is often used in school buildings to save energy by modulating the airflow rates based on the demand. However, other pollutants and indoor air parameters may affect health and are not necessarily correlated to CO2. In this study investigation of correlations between PM2.5, formaldehyde, absolute humidity, CO2 and temperature are performed. Measurements of these parameters were performed between two months and one year, positioned in the supply air in four CO2-based DCV classrooms at four different schools. The time series of measurements were de-trended to avoid overestimating cross-correlation functions. From the measurements we have concluded the need to measure: 1) pollutants related to human activities (CO2) 2) pollutants that infiltrate from processes like combustion or traffic outdoors (PM2.5), and 3) parameters related to other "non-combustion-related activities" indoors, heat sources and moisture loads (temperature). Formaldehyde from building materials seems to be mostly degassed in these older than one-year buildings, but this study should be repeated on newer buildings. © 2022 17th International Conference on Indoor Air Quality and Climate, INDOOR AIR 2022. All rights reserved.

关键词： Formaldehyde

来源：评论

学校读者我要写书评

暂无评论

Satellite Still Image Classification Using CNN

Satellite Still Image Classification Using CNN

引用

Telecommunications Conference (ITC-Egypt), International

作者： B. M. El-den Samar Elbialy Electronics and Communication Dep. Fauclty of engineering Delta University for Science and Technology Gamasa city Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

Satellite still image plays a crucial role in various domains, such as law enforcement, disaster response, and environmental monitoring. The ability to manually identify objects and facilities within these images is often crucial for these applications. However, given the extensive geographic areas that require coverage and the limited number of analysts available, automation has become a necessity. Traditional object detection and classification algorithms have proven to be insufficiently accurate and reliable for solving this problem. Fortunately, deep learning, a branch of machine learning, offers promising solutions for automating such tasks. One particular approach that has achieved success in image understanding is the use of convolutional neural networks (CNNs). Deep learning has experienced substantial advancements in diverse domains, including computer vision and natural language processing, Despite the progress made in this area, there remains a dearth of comprehensive evaluations concerning datasets and techniques tailored specifically for scene classification using satellite still image. This research paper seeks to bridge this gap by conducting a comprehensive analysis of deep learning, its development over time, and its notable applications within the domain of satellite still image.

关键词： Deep learning Scene classification Satellites Natural languages Object detection Telecommunications Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Recognition of Immune Cells: Analysis and Research 19

Intelligent Recognition of Immune Cells: Analysis and Resear...

引用

19th IEEE International Conference on e-Business engineering, ICEBE 2023

作者： Li, Chih-En Liu, Wei-Lun Lai, Kun-Yi Chiang, Yu-Hsiang Yan, Xiaowei Chen, Hao-Xiang Li, Hsu-Ching Cheng, Wan-Shu National Kaohsiung University of Science and Technology Department of Electrical Engineering Kaohsiung Taiwan Institute for Systems Biology Seattle Washington United States Providence University Dep. of Computer Science and Information Management Taichung Taiwan

ISBN: (纸本)9798350325553

Immunotherapy utilizes the potential of the patient's immune system to fight disease. T-lymphocytes have become the central focus of the immune system in the fight against cancer. One of the fundamental studies in immunotherapy is how to accurately identify various types of immune cells. Therefore, the study of immune-related cells will be an important reference for the treatment of COVID19 or other related diseases. In this paper, a series of experiments were conducted with COVID-19 patients as the starting point to design a strategy to identify the important subtypes of CD$4^{+}$T cells. In this paper, an intelligent machine learning algorithm is proposed according to the results of different experiments of linear and nonlinear dimension reduction algorithms, integrating the important characteristics of these two algorithms and improving the performance. Our experimental results show that the algorithm designed based on the front-end experiments can effectively distinguish the important lymphocytes. The proposed algorithm not only improves the performance, but also the dimension reduction procedure keeps the important features of both global and regional data. The experimental results of this paper will be beneficial for the subsequent analysis of the clustering in identifying important subtypes of CD$4^{+}$T cells. Most importantly, this wm significantly improve the procedure of manually integrating and labeling the recorded data after several tedious and monotonous analyses with external software. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Prediction of Electrical Characteristics of a-IGZO TFT Based on Transfer Learning-Based Variational Autoencoder

Prediction of Electrical Characteristics of a-IGZO TFT Based...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Bea, Khean-Thye Wei-Hsuan Lin, Shih-Shin Hu Lin, Da-Zheng Hu, Hsin-Hui Chen, Xiu-Zhi Lin, Ting-Ru Chen, Yen-Lin Chen, Kun-Ming Cheng, Wai Khuen National Taipei University of Technology Dep. of Electronic Engineering Taipei106 Taiwan National Taipei University of Technology Dep. of Computer Science and Information Engineering Taipei106 Taiwan Taiwan Semiconductor Research Institute Hsinchu30078 Taiwan Universiti Tunku Abdul Rahman Faculty of Information and Communication Technology Kampar31900 Malaysia

ISBN: (纸本)9798350337020

In this study, we proposed a transfer-learning based variational autoencoder model for predicting the electrical characteristics in the parameter tuning process of a-IGZO TFT structure design. The result achieve a high R2 score of 0.9704 with a low-computing-power hardware-friendly method that reduced time consumption significantly compared to prior approaches. The findings have practical implications for mitigating the time-consuming nature of TCAD simulations, and the method can expand to various types of input data while ensuring high performance and generalization. We demonstrated significant improvement in generalization and accuracy through a k-fold validation. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Grid-Connected Inverters and Control Methods Under Unbalanced Grid Conditions

A Review of Grid-Connected Inverters and Control Methods Und...

引用

Power Electronic and Drive Systems and Technologies Conference (PEDSTC)

作者： Milad Ghavipanjeh Marangalu Fazal Ur Rehman Naser Vosoughi Kurkdjian Dep. Of Electrical and Computer Engineering Computer Queen’s University Kingston Ontario Canada Dep. Information Engineering Computer Science and Mathematics University of L’Aquila L’Aquila Italy Faculty of Electrical and Computer Engineering San Diego State University San Diego CA USA

ISBN: (数字)9798331533946

ISBN: (纸本)9798331533953

Grid-connected inverters play a pivotal role in integrating renewable energy sources into modern power systems. However, the presence of unbalanced grid conditions poses significant challenges to the stable operation of these inverters. This review paper provides a comprehensive overview of grid-connected inverters and control methods tailored to address unbalanced grid conditions. Beginning with an introduction to the fundamentals of grid-connected inverters, the paper elucidates the impact of unbalanced grid voltages on their performance. Various control strategies, including voltage and current control methods, are examined in detail, highlighting their strengths and limitations in mitigating the effects of grid imbalance. Lastly, the review identifies emerging trends and future research directions in the field, emphasizing the need for innovative solutions to address the evolving challenges posed by unbalanced grid conditions in the context of renewable energy integration.

关键词： Current control Photovoltaic systems Renewable energy sources Technological innovation Reviews Pressing Market research Inverters Power systems Voltage control

来源：评论

学校读者我要写书评

暂无评论

Energy Access Assessment Report Focusing on Energy Poverty and Energy Demand for Rwanda

Energy Access Assessment Report Focusing on Energy Poverty a...

引用

sciences and Techniques of Automatic Control and computer engineering MI-STA, IEEE International Maghreb Meeting of the Conference on

作者： Adimchinobi Asiegbu Ali Almaktoof Abdurazag Khalat Dep. of Electrical Electronics and Computer Engineering Cape Peninsula University of Technology Cape Town South Africa Dep. of Electrical and Electronics Engineering Sabratha University Sabratha Libya

This technical report is a researched document that examines energy access in Rwanda, focusing on energy poverty assessment and energy demand assessment. The key findings and observations can help mitigate the energy access problems and improve access to modern energy in Rwanda. Studies have shown that sub-Saharan African countries have poor access or no access to modern energy, Rwanda being part of sub-Saharan Africa also has Poor access to modern and clean energy. To carefully study these energy access problems and proffer solutions to increase energy access in Rwanda based on realities in today’s Africa, (where most households fall below poverty lines, with social issues, low Purchasing Power Parity (PPP) and Gross Domestic Power (GDP)), an assessment of these energy problems is done based on Energy Poverty Assessment (EPA) and Energy Demand Assessment (EDA) Composite Multidimensional Indicators (CMDI), respectively. Based on the findings of this research, non-poor energy households increased their energy consumption by 29.26% to 0.68 billion kWh. The clean cooking gas usage in Rwanda is very low at 2.1%, The 2016 estimated electricity consumption is 0.5273 billion kWh, growing by 57.41% to 0.83 billion kWh for energy-poor households in 2021, compared to 52.6% predicted by International Energy Agency (IEA). Finally, there is a direct relationship between energy access and economic development including quality of life, standard of living, per capita income, urbanization, modern infrastructure, etc. Thus, the key findings and observations in this research report will improve economic and infrastructural development in Rwanda, if implemented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting 5G Signal Jammers with Autoencoders Based on Loose Observations

Detecting 5G Signal Jammers with Autoencoders Based on Loose...

引用

IEEE Globecom Workshops

作者： Matteo Varotto Stefan Valentin Stefano Tomasin Dep. of Information Engineering University of Padova Padova Italy Dep. of Computer Science Darmstadt University of Applied Sciences Darmstadt Germany Dep. of Information Engineering Dep. of Mathematics University of Padova Padova Italy

Fifth-generation (5G) networks are prone to jamming attacks, which are particularly dangerous in mission-critical applications such as factory automation. In this paper, we present a simple method to detect jamming attacks with machine learning techniques operating on in-phase and quadrature (IQ) modulated signals. In particular, a convolutional autoencoder (CAE) learns the structure of the clean signal to distinguish it from jammed signals in real time. This approach requires only a loose synchronization to the OFDM symbol, while equalization and decoding are not necessary. Despite its simplicity, our technique has shown high detection rates in experiments on a 5G testbed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

COVID-19 detection from Xray and CT scans using transfer learning

COVID-19 detection from Xray and CT scans using transfer lea...

引用

2021 International Conference of Women in Data science at Taif University, WiDSTaif 2021

作者： Berrimi, Mohamed Hamdi, Skander Yahia Cherif, Raoudha Moussaoui, Abdelouahab Oussalah, Mourad Chabane, Mafaza Dep. of Computer Science University of Ferhat Abbes Setif I Setif Algeria Dep. of Computer Science and Engineering University of Oulu Oulu Finland

ISBN: (纸本)9781665449489

Since the novel coronavirus SARS-CoV-2 outbreak, intensive research has been conducted to find suitable tools for diagnosis and identifying infected people in order to take appropriate action. Chest imaging plays a significant role in this phase where CT and Xrays scans have proven to be effective in detecting COVID-19 within the lungs. In this research, we propose deep learning models using Transfer learning to detect COVID-19. Both X-ray and CT scans were considered to evaluate the proposed methods. © 2021 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Advancements in Microwave Technology for Brain Diagnosis: A Comprehensive Survey on Neurodegenerative Diseases, Tumors, and Stroke Detection

Advancements in Microwave Technology for Brain Diagnosis: A ...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Abdel-Aleim, M. Miligy, Ahmed F. Taher, Fatma Abo Sree, Mohamed Fathy Elfeky, Assem H. Abdel Fatah, Sara Yehia Ahram Candian University Arab Academy for Science Technology and Maritime Transport Department of Electronics and Communications Engineering Cairo Egypt Air Defence College Electronics and Communication Dep. Alexandria Egypt College of Technological Innovation Zayed University Dubai United Arab Emirates Arab Academy for Science Technology and Maritime Transport Department of Electronics and Communications Engineering Cairo Egypt Egyptian Chinese University Higher Institute of Engineering and Technology Department of Mechatronics Engineering and Automation Cairo Egypt

ISBN: (纸本)9798350351408

This paper thoroughly investigates recent advances in microwave technology for diagnosing brain-related ailments, focusing on neurodegenerative diseases, tumors, and strokes. It emphasizes the importance of early and precise diagnosis in managing neurological disorders and highlights microwave technology's potential for non-invasive brain imaging. The survey reviews techniques and technologies in brain tumor and stroke detection, providing insights into key parameters like resolution and specificity. Overall, it offers valuable insights into microwave-based brain diagnosis and suggests future research directions for enhancing diagnostic tools. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

FOCUSED ACTIVE LEARNING FOR HISTOPATHOLOGICAL IMAGE CLASSIFICATION

arXiv

引用

arXiv 2024年

作者： Schmidt, Arne Morales-Álvarez, Pablo Cooper, Lee A.D. Newberg, Lee A. Enquobahrie, Andinet Katsaggelos, Aggelos K. Molina, Rafael Dep. of Computer Science and AI University of Granada Granada Spain Dep. of Statistics and Operations Research University of Granada Granada Spain Dep. of Pathology Northwestern University Chicago United States Kitware Inc Carrboro United States Dep. of Electrical Computer Engineering Northwestern University Evanston United States

Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are’distracted’ by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen’s kappa of 0.764 with only 0.69% of the labeled Panda data. © 2024, CC BY.

关键词： Image classification

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：