检索结果-内蒙古大学图书馆

Indoor thermal comfort comparison between passive solar house with active solar heating and without active solar heating in Tibetan

引用

Energy and Built Environment 2025年第2期6卷 285-296页

作者： Zhai, Panpan Li, Jinping Lei, Tingzhou Zhu, Junjie Novakovic, Vojislav School of Energy and Power Engineering Lanzhou University of Technology Lanzhou730050 China Collaborative Innovation Center for Supporting Technology of Northwest Low-Carbon Towns Lanzhou730050 China Gansu Key Laboratory of Complementary Energy System of Biomass and Solar Energy Lanzhou730050 China Solar Energy Department Institute for Energy Technology Kjeller2007 Norway Department of Energy and Process Engineering Norwegian University of Science and Technology TrondheimNO-7491 Norway

Passive solar house technology has been spread for many farmers and herdsmen to improve the indoor thermal environment in Tibetan. However, due to lackage of fuels and arid cold in winter, dry cow dung and coal are popularly fired in stove in passive solar houses, which leads to indoor air pollution and poor indoor comfort. For improving indoor thermal comfort of Tibetan, an active solar heating system which consists of 7 sets of tandem solar water heaters with 30 glass evacuated solar tubes, low temperature floor heating and circulation controller was developed and tested for a common house without insulation in Gan-nan Tibetan area. Its indoor environment was compared and evaluated by PMV-PPD and LPD method to that of the same passive solar house heated by coal stove. On sunny, cloudy and snow days, the active solar heating system provided 113.1, 46.4 and 26.3 kWh of heat to room. The indoor humidity and wind speed of the experimental building were better. The indoor temperatures were 17.2-20.7, 14.9-20.5 and 11.0-14.8°C, while the compared building were 8.9-14.8, 10.1-12.1 and 7.2-10.5°C. The maximum temperature difference between head and ankle were 1.7, 1.6 and 0.9℃, and the compared building were 4, 4 and 4.7℃. The PMV-PPD on sunny day were class I and II;on cloudy day were class I, II and III;on snow day was class III. On sunny and cloudy days, the LPD were class I, on snow day was class I, II and III. The PMV-PPD and LPD for typical days of the compared building were class III. During the 179 days, the mean indoor temperature exceeded 14 ℃ for 81 days, the solar active heating system provided 12471 kWh of heat to room. The CO2 emission reduction was 12905 kg. The system's dynamic payback period were 2.57 years. © 2023

关键词： Passive solar

来源：评论

学校读者我要写书评

暂无评论

Personalized Collaborative Search Engine for Decision Making

Personalized Collaborative Search Engine for Decision Making

引用

2024 International Conference on Communication, Computer Sciences and engineering, IC3SE 2024

作者： Murshleen, Mohd. Prabhu, A. Jain, Garima Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of Computer Science & Business System Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350366846

Web search engines are used for retrieving information but still there exists ambiguity in their retrieval process. It is so because traditional search engines laid emphasis on matching of keywords rather than maintaining semantic relations among terms lack of ability to produce precise results, presence of ambiguous keywords and verifying needs of users are few hindrances that are acting as scenario for web search engines. The paper focuses on improving search quality of users by collecting user experiences through creating hierarchical user profile it leads to collaborative search engine that helps in reaching at particular decision then the collected user's data are uploaded to recommendation server which are than displayed a search engines like Google/Yahoo. © 2024 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Experimental and heat transfer studies of MHP-PV/T by Reynolds number and heat transfer coefficient enhancement

引用

Energy and Built Environment 2025年第2期6卷 320-331页

作者： Li, Rui Li, Jinping Zhu, Junjie Zhang, Xuemin Guo, Xiao Novakovic, Vojislav School of Energy and Power Engineering Lanzhou University of Technology Lanzhou730050 China Gansu Key Laboratory of Complementary Energy System of Biomass and Solar Energy Lanzhou730050 China Collaborative Innovation Center for Supporting Technology of Northwest Low-Carbon Towns Lanzhou730050 China Solar Energy Department Institute for Energy Technology Kjeller2007 Norway Department of Energy and Process Engineering Norwegian University of Science and Technology TrondheimNO-7491 Norway

The photovoltaic/thermal (PV/T) system, as an energy conversion system to generate electricity and heat, has great application potential in northwest zone of ample solar energy resource in China. The working media inside the micro heat pipe (MHP) of previous studies was acetone. Compared to acetone, R141b has better stability and lower solubility. For working fluid as R141b in the MHP, higher Reynolds Number (Re) theoretically means better heat transfer. During the typical winter season, when the inclination of the PV panel was 45°, the average power conversion efficiency (PCE) and thermal conversion efficiency (TCE) can reach 12.8 and 26.4 %. Furthermore, in order to reduce the simulation time and facilitate the research, the study establishes the fitting equation of MHP-PV/T surface temperature based on solar radiation intensity and environmental temperature with an average error of 7.6 %. Furthermore, a three-dimensional mathematical model of MHP-PV/T system was developed and validated with experimental results, investigating the Re of R141b in the MHPs and calculating the related heat transfer coefficient (h) based on Re. The simulation showed that the Re and h at the condensation section of the MHP were bigger than those at the evaporation section. The Re and h increased with the water temperature decrease of airfoil heat exchanger and solar radiation intensity rise. Lastly, when water temperature of airfoil heat exchanger was unchanged, the impact of solar radiation intensity on h was greater than Re. When the solar radiation intensity remained unchanged and the water temperature decreased, Re was the main reason for affecting the change of h. The research results will give a scientific foundation and technical application for the MHP-PV/T, as well as more efficient solar energy applications in the future. © 2023

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

Digital Implementation of Depthwise Separable Convolution Network for AI Applications 6

Digital Implementation of Depthwise Separable Convolution Ne...

引用

6th IEEE Pune Section International Conference, PuneCon 2023

作者： Madhuri, Potta Akhter, Nargis Bazil Raj, A.A. Radar System Laboratory Department of Electronics Engineering India Defence Institute of Advanced Technology Rf Photonics Department of Electronics Engineering Pune411025 India

ISBN: (纸本)9798350324204

Convolutional neural networks(CNN) have gained widespread popularity in the fields of computer vision and pattern recognition due to their exceptional accuracy. However, the computational demands of operating large convolutions often necessitate powerful computing platforms like a Graphical Processing Unit (GPU), making it challenging to utilize CNNs on portable devices. To address this issue, advanced CNN models such as MobileNetV2 and Xception employ Depthwise Separable Convolution(DSC) instead of Standard Traditional Convolution(STC) for embedded systems. This approach significantly reduces computations and parameters while only marginally sacrificing accuracy. This innovative model structure is particularly well-suited for implementation on Field-Programmable Gate Arrays(FPGAs). In our research paper, we propose DSc accelerator within CNNs. The design allows flexibility in adapting to FPGAs of various sizes, achieving an excellent balance between hardware resource utilization and processing speed efficiency. We have successfully implemented this using the Verilog Hardware Description Language(HDL), and We have achieved the corresponding outcomes for an image size of 256 × 256 × 3. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking Control of Tracked Vehicle with Consideration of Track Slip and Disturbance 24

Trajectory Tracking Control of Tracked Vehicle with Consider...

引用

24th International Conference on Control, Automation and systems, ICCAS 2024

作者： Huynh, Thinh Nguyen, Van-Trang Kim, Young-Bok Pukyong National University College of Information Technology and Convergence Department of Smart Mobility Engineering Busan48513 Korea Republic of Ho Chi Minh City University of Technology and Education Faculty of Vehicle and Energy Engineering Ho Chi Minh City700000 Viet Nam Pukyong National University Division of Energy Transport System Engineering Department of Mechanical System Engineering Busan48513 Korea Republic of

ISBN: (纸本)9788993215380

Tracked locomotion systems have been widely used for vehicles operating in loose or uneven terrains, thanks to their superior traction. However, track slips and disturbances generated from the track-terrain interaction in such applications significantly affect the accuracy and efficiency of vehicle movement. In this paper, a novel control solution is proposed to deal with this problem. Firstly, the kinematics and dynamics of the vehicle are established, considering the constraints of the track locomotion, track slip, and disturbances. Secondly, the control law for driving torques is designed. In which, a radial basis function neural network is used to estimate the disturbances;ideal traction forces are designed following the backstepping method to ensure the convergence of both tracking and stabilization errors;and the corresponding driving torques are obtained to simultaneously achieve the required traction and compensate for the track slip. Then, simulation studies are conducted, where the proposed control system proves its superiority compared to an established control solution. © 2024 ICROS.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Combating Digital Deception: Machine Learning Approaches for Detecting Political Misinformation and Clickbait on Social Media 6

Combating Digital Deception: Machine Learning Approaches for...

引用

6th International Conference on Advancements in Computing, ICAC 2024

作者： Harindi, Dewmini Perera, Nirmal Liyanage, Chamath Dematagoda, Hirushini Fernando, Harinda Rathnayake, Samadhi Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka

ISBN: (纸本)9798331517878

This paper presents machine learning-based strategies for mitigating the problem of misinformation in social media, with a special focus on political misinformation detection and clickbait detection. The following research work attempts to address the pressing issue of the rapid spread of false or misleading information by making use of deep recurrent neural networks (RNN s) combined with semi-supervised learning methodologies. For political misinformation detection, a hybrid model integrating Long Short-Term Memory (LSTM) networks with fully connected layers was developed, achieving 94.22 % accuracy on the CIC Truth Seeker dataset. Clickbait detection was made using a sequential architecture that combines LSTM and Gated Recurrent Units (GRU) layers with Simple RNN layers to achieve an accuracy of 96% on test data. This study underlines the effectiveness of different machine learning techniques in battling misinformation that would contribute to online dignity in political discourse and ensure better public communication in a digital world. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Based Vascular Stenosis Detection

Transfer Learning Based Vascular Stenosis Detection

引用

2022 International Conference on Emerging Trends in Smart Technologies, ICETST 2022

作者： Noreen, Aqsa Jawaid, Moazzam Narejo, Sanam Memon, Madeha Kumar, Kunal Mehran University of Engineering & Technology Department of Computer System Engineering Jamshoro Pakistan

ISBN: (数字)9781665459358

ISBN: (纸本)9781665459358

One of the leading causes of mortality and morbidity in the global population is coronary artery disease. Clinical data analysis and healthcare professionals have a crucial problem in predicting and diagnosing the disease in order to save lives and prevent people from developing it. Massive volumes of data are gathered by the healthcare sector, some of which contains diagnostic information for cardiac disease and is useful for decision-making. Deep neural networks can also be used to examine and identify cardiac problems. The most common kind of heart disease, atherosclerosis or stenosis, is occurred when coronary arteries are narrowed abnormally. Since blood vessels are also known as the coronary arteries that provide the heart with oxygen, blood, and nutrients, they can get narrowed, which can result in chest pain (angina), pain, and difficulty breathing. As a result, it may result in discomfort, nausea, dizziness, and even a heart attack[1]. This project intends to acquire Cross-Sectional Images from 3-Dimendional CT (computed tomography) using CPR (curve planar reformation) and to train Transfer Learning Model over customized CT data for stenosis detection and quantification. The model we have used is VGG (Visual Geometric Group) model, which refers to a convolutional neural network model proposed by A. Zisserman and K. Simonyan of the University of Oxford. VGG16 is pre-trained model which is trained on ImageNet dataset. The model's training and testing accuracy is 89.08% and 88.52%, respectively. The efficiency of model is measured by its accuracy, recall, precision, and f-score. © 2022 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： Rui Wang Zhiming Zhou Kaiwen Li Tao Zhang Ling Wang Xin Xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of Systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of Systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

来源：评论

学校读者我要写书评

暂无评论

Safety-Critical Randomized Event-Triggered Learning of Gaussian Process With Applications to Data-Driven Predictive Control

引用

IEEE Transactions on Automatic Control 2024年第6期70卷 3920-3935页

作者： Zheng, Kaikai Shi, Dawei Shi, Yang Beijing Institute of Technology MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing100081 China University of Victoria Department of Mechanical Engineering Faculty of Engineering VictoriaBCV8N 3P6 Canada

Safety and data efficiency are important concerns in data-driven control, especially for nonlinear systems with unknown dynamics and subject to disturbances. In this work, we consider a class of control-affine nonlinear systems with partially unknown dynamics and aim to introduce an event-triggered learning-based control approach with guaranteed safety and improved data utilization efficiency. Specifically, a randomized learning approach is employed to evaluate the safety of state trajectories by defining and estimating its confidence interval, with data from a multisample of randomly generated state trajectories. Using the proposed randomized learning algorithm, a nominal trajectory with a high probability safety guarantee is designed, thus ensuring the disturbed system states to remain within a pre-specified range around the nominal trajectory with a sufficiently high probability. Through removing irrelevant data, a local prediction model around the nominal trajectory is learned with satisfactory precision, and is updated online using an event-triggered learning strategy. Based on the learned model, an efficient data-driven predictive controller is designed to force the system states to evolve within the vicinity of the designed safety nominal trajectory. The effectiveness of the proposed event-triggered learning and data-driven control approaches is validated through comprehensive simulation studies. © 1963-2012 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

An Effective Noise Removal Technique for Enhancing Ischemic Brain Stroke Computed Tomography Images 1

An Effective Noise Removal Technique for Enhancing Ischemic ...

引用

1st International Conference on Innovations in Communications, Electrical and Computer engineering, ICICEC 2024

作者： Puneeth, S.P. Poornima, B. PremaSudha, B.G. Patil, N.S. Puneetha, B.H. Jadekar, Ranjana B. Visvesvaraya Technological University Bapuji Institute of Engineering and Technology Davangere Department of Information Science and Engineering Karnataka Belagavi India Visvesvaraya Technological University Siddaganga Institute of Technology Tumkur Department of Mca Karnataka Belagavi India Visvesvaraya Technological University Bapuji Institute of Engineering and Technology Davangere Department of Computer Science and Business System Karnataka Belagavi India Visvesvaraya Technological University Bapuji Institute of Engineering and Technology Davangere Department of Computer Science and Engineering Karnataka Belagavi India

ISBN: (纸本)9798350376517

Ischemic stroke significantly affects millions of people motor and cognitive skill. Early identification of ischemic stroke helps in preventing loss of life. Usually, noise is present in Computed-Tomography (CT) during acquisition and the noise degrades the visibility of anatomical structures and subtle abnormalities, making it difficult for radiologists to accurately diagnose and interpret medical conditions. Thus, denoising CT medical images is crucial in preserving information and restoring images contaminated with noise. The Convolution-Neural-Network (CNN) has been used to remove the noise with good effect;however, the performance resulted in a loss of clarity and fine details preservation that rendered the CT images unsuitable. In addressing this, presented an enhanced noise removal techniques namely Morphology-Aware CNN (MA-CNN) to enhance brain CT image of ischemic stroke patients for better segmentation, classification to enhance diagnosis. The MA-CNN performance is studied in term of Peak-signal-to-noise-ratio (PSNR);the overall result attained shows the proposed model exhibit higher PSNR in comparison with existing denoiser methods and assures good performance in maintaining the quality of the image and fine details' preservation. © 2024 IEEE.

关键词： Convolutional neural networks

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：