检索结果-内蒙古大学图书馆

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Syed Omar Ballari Angalkuditi Srinivas Manish Gupta Kiran Dhobal Pathan Shahnavajkhan Akabarkhan Dasari Veera Reddy Department of Civil Engineering Guru Nanak Institutions Technical Campus Ibrahimpatnam Telangana Department of CSE Koneru Lakshmaiah Education Foundation Lovely Professional University Phagwara Uttaranchal Institute of Technology Uttaranchal University Faculty of Computer Science Shri C.J. Patel College of Computer Studies Sankalchand Patel University School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

The terminology "computer vision" refers to the method that leverages technologies of intelligent systems such as artificial intelligence (AI) to enable computers to gather useful information from visual sources. The automated activities are demonstrated previously using computer vision understanding. The definition, examples, as well as uses of computer vision, are covered in this article. For computer vision to be totally successful there must be a huge collection. When they lack the knowledge required to execute the task at hand, these systems periodically discover trends, which cause this to occur. Hence, the research has evaluated the notion of computer vision in diverse fields of operations through the literature review as well as in the analysis and discussion portion of the study. Since the literature review and data analysis of the research is done through secondary sources, an imperative notion of review has been gathered and presented. Therefore, the significance of computer vision in assembling intelligent systems like AI and other new technologies has given discussed in the research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revealing Key Amino Acids on HMGB1 Box A Domain which can be used for Peptide Targeting

引用

Neuroscience Applied 2024年 3卷

作者： O.M. Apaydin O. Sensoy S. Baday Istanbul Technical University Institute of Computer Science Department Informatics Istanbul Türkiye Istanbul Technical University Department of Artificial Intelligence and Data Engineering- Faculty of Computer Informatics and Engineering Istanbul Türkiye

来源：评论

学校读者我要写书评

暂无评论

Adapting to climate change: Long-term impact of wind resource changes on China's power system resilience

arXiv

引用

arXiv 2023年

作者： Ruan, Jiaqi Meng, Xiangrui Zhu, Yifan Liang, Gaoqi Sun, Xianzhuo Wu, Huayi Xiao, Huijuan Lu, Mengqian Gao, Pin Li, Jiapeng Wong, Wai-Kin Xu, Zhao Zhao, Junhua Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen518172 China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen518055 China Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong SAR Hong Kong School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen518172 China School of Electrical Engineering Xi'an Jiaotong University Xi'An710049 China Forecast Development Division Hong Kong Observatory Hong Kong Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China

Modern society's reliance on power systems is at risk from the escalating effects of wind-related climate change. Yet, failure to identify the intricate relationship between wind-related climate risks and power systems could lead to serious shortand long-term issues, including partial or complete blackouts. Here, we develop a comprehensive framework to assess China's power system resilience across various climate change scenarios, enabling a holistic evaluation of the repercussions induced by wind-related climate change. Our findings indicate that China's current wind projects and planning strategies could be jeopardized by wind-related climate change, with up to a 12% decline in regional wind power availability. Moreover, our results underscore a pronounced vulnerability of power system resilience amidst the rigors of hastened climate change, unveiling a potential amplification of resilience deterioration, even approaching fourfold by 2060 under the most severe scenario, relative to the 2020 benchmark. This work advocates for strategic financial deployment within the power sector aimed at climate adaptation, enhancing power system resilience to avert profound losses from long-term, wind-influenced climatic fluctuations. © 2023, CC0.

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Study and analysis on an EEG signal based facial emotion recognition

引用

AIP Conference Proceedings 2024年第1期3161卷

作者： A. Mukil S. Sarkar R. Lakshmanan R. Abdulla School of Engineering Asia Pacific University of Technology & Innovation Kuala Lumpur Malaysia 57000 Professor Artificial intelligence and Data Science Department Sri Sairam Engineering College West Tambaram Chennai India

Over the past few years, research into emotion identification through EEG data has flourished. Creating an intelligent framework that can deliver high accuracy for emotion recognition is difficult since EEG signals are noisy, non-linear, and non-stationary. Numerous communication aids based on the concept of memory therapy have been developed. However, verbal feedback or questionnaires are typically used in communication support systems to assess older people’s emotions. This research aims to examine whether or not it is possible to use Electroencephalography (EEG) data for automatic emotion recognition. Advanced neuroimaging methods like electroencephalography have enabled us to replicate and understand a wide range of human emotions more precisely. This physiological signal, i.e., EEG-based method is in stark comparison to traditional non-physiological signal-based methods and has been shown to perform better. As a means of measuring how well our suggested model performs, we conducted tests on a shared database known as DEAP and used a variety of metrics to do so. The results of the studies validated the effectiveness of the proposed strategy, demonstrating that the CNN-based approach can reach an accuracy of 95.20 percent. Electroencephalography signal analysis has become popular for investigating human emotions because of its non-invasive nature. Based on the correlation between facial expressions and brain signals, a two-stage deep learning model is presented in this research for the purpose of emotion recognition. Most studies of emotional states rely on studying lengthy signal segments, often over the duration of the evoked potential, which might introduce numerous other phenomena into the recognition process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inverse learning of black-box aggregator for robust Nash equilibrium

arXiv

引用

arXiv 2024年

作者： Chen, Guanpu Xu, Gehui He, Fengxiang Tao, Dacheng Parisini, Thomas Johansson, Karl Henrik Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Digital Futures Stockholm100 44 Sweden Artificial Intelligence and its Applications Institute School of Informatics University of Edinburgh EdinburghEH8 9AB United Kingdom College of Computing & Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Engineering and Architecture University of Trieste Trieste34127 Italy

In this note, we investigate the robustness of Nash equilibria (NE) in multi-player aggregative games with coupling constraints. There are many algorithms for computing an NE of an aggregative game given a known aggregator. When the coupling parameters are affected by uncertainty, robust NE need to be computed. We consider a scenario where players' weight in the aggregator is unknown, making the aggregator kind of "a black box". We pursue a suitable learning approach to estimate the unknown aggregator by proposing an inverse variational inequality-based relationship. We then utilize the counterpart to reconstruct the game and obtain first-order conditions for robust NE in the worst case. Furthermore, we characterize the generalization property of the learning methodology via an upper bound on the violation probability. Simulation experiments show the effectiveness of the proposed inverse learning approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery

arXiv

引用

arXiv 2022年

作者： Tong, Xin-Yi Xia, Gui-Song Zhu, Xiao Xiang Remote Sensing Technology Institute German Aerospace Center Germany State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University China National Engineering Research Center for Multi-media Software School of Computer Science Institute of Artificial Intelligence Wuhan University China Data Science in Earth Observation Technical University of Munich Germany

High-resolution satellite images can provide abundant, detailed spatial information for land cover classification, which is particularly important for studying the complicated built environment. However, due to the complex land cover patterns, the costly training sample collections, and the severe distribution shifts of satellite imageries caused by, e.g., geographical differences or acquisition conditions, few studies have applied high-resolution images to land cover mapping in detailed categories at large scale. To fill this gap, we present a large-scale land cover dataset, Five-Billion-Pixels. It contains more than 5 billion labeled pixels of 150 high-resolution Gaofen-2 (4 m) satellite images, annotated in a 24-category system covering artificial-constructed, agricultural, and natural classes. In addition, we propose a deep-learning-based unsupervised domain adaptation approach that can transfer classification models trained on labeled dataset (referred to as the source domain) to unlabeled data (referred to as the target domain) for large-scale land cover mapping. Specifically, we introduce an end-to-end Siamese network employing dynamic pseudo-label assignment and class balancing strategy to perform adaptive domain joint learning. To validate the generalizability of our dataset and the proposed approach across different sensors and different geographical regions, we carry out land cover mapping on five megacities in China and six cities in other five Asian countries severally using: PlanetScope (3 m), Gaofen-1 (8 m), and Sentinel-2 (10 m) satellite images. Over a total study area of 60,000 km2, the experiments show promising results even though the input images are entirely unlabeled. The proposed approach, trained with the Five-Billion-Pixels dataset, enables high-quality and detailed land cover mapping across the whole country of China and some other Asian countries at meter-resolution. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Challenges in metaverse in problem-based learning as a game-changing virtual-physical environment for personalized content development

Challenges in metaverse in problem-based learning as a game-...

引用

6th Smart Cities Symposium (SCS 2022)

作者： P.K. Dutta M. Bose A. Sinha R. Bhardwaj S. Ray S. Roy K.B. Prakash School of Engineering and Technology Amity University Kolkata Kolkata India School of Computer Application Amity University Kolkata Kolkata India Department of Mathematics Amity University Kolkata Kolkata India Senior Researcher Petersburg Polytechnic University Artificial Intelligence & Data Science Jio Institute Navi Mumbai India Department of Computer Science and Engineering Konneru Lakshmaih Education Foundation

The benefits and drawbacks of using the metaverse in the field of education are discussed, along with the possibilities and potential issues it will open up. Utilizing the idea of personalised knowledge transfer and the use of an immersive environment to match students' learning pace using horizon classroom, the Metaverse environment can add a new dimension to the field of educational technologies. We have also highlighted the virtualization-based redesign of educational environments using a personalised cloud, which is anticipated to improve learning for students by making it more affordable, collaborative, and useful. The goal is to build a metaversity that can serve as a communication tool for teachers and students anywhere in the world by providing each with an individual avatar. This platform will offer a virtual setting for students to socialise with their friends and peers and receive peer-to-peer learning, which is lacking in the current e-learning environment. The students won't need an entrance score card; instead, they will need critical learning skills to advance and mature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

"Unlocking Electrocatalytic Dynamics with Anti-Mxene Borides Monolayers for Nitrate Reduction"

SSRN

引用

SSRN 2024年

作者： Ho, Thi H. Nguyen, Quynh Anh T. Le, Bich-Tram Truong Kim, Seong-Gon Bui, Viet Q. Laboratory for Computational Physics Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City Viet Nam Faculty of Mechanical - Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City Viet Nam Advanced Institute of Science and Technology The University of Danang 41 Le Duan Danang Viet Nam Department of Science and International Cooperation The University of Danang Danang551000 Viet Nam Department of Physics & Astronomy Center for Computational Sciences Mississippi State University MS39762 United States

In this comprehensive study, we explore the electrocatalytic behavior of novel two-dimensional (2D) monolayers composed of anti-MXene borides (TMB) towards the nitrate reduction reaction (NO3RR) using density functional theory (DFT). The analysis reveals that these TMB monolayers emerge as promising candidates for electrochemical NO3RR, characterized by their exceptional stability, advantageous selectivity, and effective activation properties. Notably, our results highlight the preferential progression of the NO3-to-N2 pathway over the NO3-to-NH3 pathway in these TMB systems, presenting a significant insight into the mechanism of nitrate reduction. Among the monolayers, MnB distinguishes itself with a limiting potential of 0.79 eV, underscoring its substantial potential for application in the electroreduction of nitrate. Additionally, this study sheds light on the broader applicability of these innovative two-dimensional anti-MXene TMB monolayers, suggesting their versatility as electrocatalysts in a variety of potential applications, thereby opening new avenues for future research and development in electrocatalysis. © 2024, The Authors. All rights reserved.

关键词： Electrocatalysis

来源：评论

学校读者我要写书评

暂无评论

Joint Sleep Stage Classification and Prediction in Obstructive Sleep Apnea Using Deep Learning Method

Joint Sleep Stage Classification and Prediction in Obstructi...

引用

亚洲睡眠医学会2021年学术大会暨第十三届中国睡眠研究会年会

作者： Fan Li Rui Yan Lai Wei Rong Liu Fengyu Cong School of Biomedical Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of Technology RWTH Aachen University School of Information Science and Engineering HebeiUniversity of Science & Technology Faculty of Information Technology University of Jyva?skyla? Otolaryngology Department Affiliated Zhongshan Hospital of Dalian University School of Artificial Intelligence Faculty of Electronic Information and Electrical EngineeringDalian University of Technology

This study presents a deep neural network for sleep stage scoring and prediction on patients with OSAHS with different level of AHI using single-channel EEG. To investigate the difference in performance between subjects with different level of AHI,an end-to-end 1-D convolutional neural network combing with CRF is designed. The model considers three consecutive EEG epochs as the model input determining three corresponding stages in the output. For sleep staging task,the central label of the three consecutive epochs is viewed as the ground truth of each input,and the left and right neighbors of the central label are for left and right sleep stage prediction. So,it is a many-to-many strategy compared with the standard one-to-one or many-to-one methods. The designed model was trained and tested on different level of AHI subjects selecting from SHHS dataset,respectively. The obtained mean accuracies for normal,mild,moderate,and severe subjects are 0.86,0.834,0.829,and 0.809,respectively. The observed performance decreased gradually with subjects' AHI increasing. Compared with one-by-one sleep staging results,90-s based input can improve the accuracy of NREM stage from all level subjects. However,for other sleep stages,changes in accuracy of each subset are not uniform. Especially for N1 stage,the performance increases on normal and moderate subsets,while,the other two subsets observe the reduced accuracy. The results demonstrate that the proposed method is not only effective for normal subjects but also available on patients with OSAHS. To our knowledge,this is the first research focusing on exploring the automatic sleep staging difference in different level of AHI. Thus,it can be utilized to monitor sleeping and screen subjects with high probability of OSAHS. Besides,manyto-many strategy is first introduced into automatic sleep staging. This strategy provides the way to real-time sleep staging and sleep intervention.

关键词： OSAHS Sleep Staging Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Identifying molecular signatures and pathways shared between Alzheimer's and Huntington's disorders: A bioinformatics and systems biology approach

引用

Informatics in Medicine Unlocked 2022年 30卷

作者： Mahbub, Nosin Ibna Hasan, Md. Imran Rahman, Md Habibur Naznin, Feroza Islam, Md Zahidul Moni, Mohammad Ali Dept. of Information and Communication Technology Islamic University Kushtia 7003 Bangladesh Dept. of Computer Science and Engineering Islamic University Kushtia 7003 Bangladesh Dept. of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh Dept. of Computer Science and Engineering Pabna University of Science and Technology Bangladesh Artificial Intelligence & Digital Health Data Science School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St Lucia 4072 QLD Australia

Alzheimer's disease and Huntington's disease are considered to be the most lethal illnesses that result in common human disorders. Alzheimer's disease (AD) is a progressive neurological illness distinguished by age-related dementia, mental abnormalities, and poor memory, among other symptoms. However, Huntington's disease (HD) is influenced by genetics as well as a generalized dysfunction of the motor system. Despite the fact that many similar genetic elements have been found in the literature as being interrelated between these two diseases, it is still unclear how people acquire infected with these two neurological disorders. Detecting biomarkers for Alzheimer's and Huntington's disease in brain tissue might help in drug development and treatment. The purpose of this research was to find brain cell transcripts that show levels of gene expression linked to the progression of Alzheimer's and Huntington's disease. A bioinformatics pipeline was used to study one RNA-Seq transcriptomic dataset and one microarray dataset, and 24 significant differentially expressed genes (DEGs) were discovered that were shared by two brain cell datasets. We uncovered disease-gene association networks and signaling pathways, as well as gene ontology (GO) investigations and hub protein identification, to determine the roles of these DEGs. The discovery of significant gene ontologies and molecular pathways increased our understanding of the pathophysiology of these two disorders, and the hub proteins B2M, HLA-A, HLA-E, HLA-B, HLA-C, HLA-F, CANX, HLA-DQA1, HLA-DRA, and HLA-DRB1 might be exploited to design therapeutic interventions. In neurological disorder subjects, we uncovered efficient hypothetical linkages between pathogenic processes in brain cells, implying that brain cells may be exploited to detect and monitor illness origin and development, as well as design pharmacological therapies. © 2022

关键词： Alzheimer's disease Biomarker signatures Differentially expressed genes Huntington's disease Protein-drug interactions Protein-protein interaction

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：