检索结果-内蒙古大学图书馆

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Rohella, Piyush Temara, Sheetal Samanthapudi, Sagar Varma Gupta, Ketan Suganyadevi, K. Payments & Commerce GoDaddy EdmondsWA United States University of The Cumberlands Dept of Computer & Information Sciences WilliamsburgKY United States The Polis Center Indiana University Purdue University Indianapolis Applied Data Science IndianapolisIN United States University of The Cumberlands Dept. of Information Technology WilliamsburgKY United States Sri Eshwar College of Engineering Department of Ece Tamil Nadu Coimbatore India

ISBN: (纸本)9798350394399

This research examines the function of synthetic Intelligence in developing customized purchaser banking reviews. Artificial Intelligent -based total gear is increasingly being followed to offer consumers customized banking reports. Studies into the use of AI in this context will tell the layout of future banking products and services. The primary intention of this research is to understand the modern technological and personal adoption developments related to Artificial Intelligent and customized banking reviews. Particularly, this study will identify the modern use cases of Artificial Intelligent in personalized banking, look into clients' attitudes and motivations towards Artificial Intelligent -enabled banking experiences, and discover the ability possibilities and challenges related to utilizing Artificial Intelligent in growing individualized banking studies for purchasers. Additionally, the role of ethical issues in implementing and the use of Artificial Intelligent in personalized consumer banking experiences may be evaluated. This study is crucial for presenting a better understanding of the function of Artificial Intelligent in developing personalized and moral consumer banking experiences. © 2024 IEEE.

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

Training Physics- Informed Neural Networks via Multi-Task Optimization for Traffic Density Prediction

Training Physics- Informed Neural Networks via Multi-Task Op...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Bo Wang A. K. Qin Sajjad Shafiei Hussein Dia Adriana-Simona Mihaita Hanna Grzybowska Dept. of Computing Technologies Swinburne University of Technology Melbourne Australia Dept. of Civil and Construction Engineering Swinburne University of Technology Melbourne Australia Data Science Institute University of Technology Sydney Sydney Australia Simulation Group Data 61|CSIRO Sydney Australia

Physics-informed neural networks (PINN s) are a newly emerging research frontier in machine learning, which incorporate certain physical laws that govern a given data set, e.g., those described by partial differential equations (PDEs), into the training of the neural network (NN) based on such a data set. In PINN s, the NN acts as the solution approximator for the PDE while the PDE acts as the prior knowledge to guide the NN training, leading to the desired generalization performance of the NN when facing the limited availability of training data. However, training PINNs is a non-trivial task largely due to the complexity of the loss composed of both NN and physical law parts. In this work, we propose a new PINN training framework based on the multi-task optimization (MTO) paradigm. Under this framework, multiple auxiliary tasks are created and solved together with the given (main) task, where the useful knowledge from solving one task is transferred in an adaptive mode to assist in solving some other tasks, aiming to uplift the performance of solving the main task. We implement the proposed framework and apply it to train the PINN for addressing the traffic density prediction problem. Experimental results demonstrate that our proposed training framework leads to significant performance improvement in comparison to the traditional way of training the PINN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Training Physics-Informed Neural Networks via Multi-Task Optimization for Traffic Density Prediction

arXiv

引用

arXiv 2023年

作者： Wang, Bo Qin, A.K. Shafiei, Sajjad Dia, Hussein Mihaita, Adriana-Simona Grzybowska, Hanna Dept. of Computing Technologies Swinburne University of Technology Melbourne Australia Dept. of Civil and Construction Engineering Swinburne University of Technology Melbourne Australia Data Science Institute University of Technology Sydney Sydney Australia Simulation Group Data 61 CSIRO Sydney Australia

Physics-informed neural networks (PINNs) are a newly emerging research frontier in machine learning, which incorporate certain physical laws that govern a given data set, e.g., those described by partial differential equations (PDEs), into the training of the neural network (NN) based on such a data set. In PINNs, the NN acts as the solution approximator for the PDE while the PDE acts as the prior knowledge to guide the NN training, leading to the desired generalization performance of the NN when facing the limited availability of training data. However, training PINNs is a non-trivial task largely due to the complexity of the loss composed of both NN and physical law parts. In this work, we propose a new PINN training framework based on the multi-task optimization (MTO) paradigm. Under this framework, multiple auxiliary tasks are created and solved together with the given (main) task, where the useful knowledge from solving one task is transferred in an adaptive mode to assist in solving some other tasks, aiming to uplift the performance of solving the main task. We implement the proposed framework and apply it to train the PINN for addressing the traffic density prediction problem. Experimental results demonstrate that our proposed training framework leads to significant performance improvement in comparison to the traditional way of training the PINN. Copyright © 2023, The Authors. All rights reserved.

关键词： knowledge management

来源：评论

学校读者我要写书评

暂无评论

Analysis of route efficiency in city bus transportation vulnerable areas

Analysis of route efficiency in city bus transportation vuln...

引用

IEEE International Conference on Big data

作者： Namsik Yoon Innjun Choi Sung Woo Kang Dept. of Industrial Engineering Inha University Incheon Republic of Korea Dept. of Industrial Engineering&Data Science Inha University Incheon Republic of Korea

ISBN: (纸本)9781665480468

City buses are important transportation for citizens who especially living in transportation vulnerable areas. However, public transportation in these areas continuously decreases because of low population density. The low demand puts these areas behind service priorities, The backlog of service priorities exacerbates public transportation, hereby decreasing the population in these *** order to solve the deterioration of public transportation services in transportation vulnerable areas, the optimal route is calculated through the genetic algorithm-based approaches. The methodology automatically creates novel bus routes based on the demands and existing transportation resources. In this paper, each route is regarded as a living organism, and both demand networks and road networks are constructed as an evolutionary environment so that each organism can compete and evolve with each other. In order to verify the methodology, the case study is conducted based on actual data-sets from local government, bus companies, telecommunication company(SK Telecom) in Incheon, Republic of Korea. The second largest island (Yeongjongdo) in Incheon is selected as a transportation vulnerable area by the Incheon institute (public research center for Incheon metropolitan city). The optimal route from the methodology increases the route efficiency without supplementing additional buses to handle the demands, hereby improving the vicious cycle of transportation vulnerable areas.

关键词： Roads Urban areas Sociology Companies Big data Organisms Statistics

来源：评论

学校读者我要写书评

暂无评论

Necessity of Information Security in Safeguarding Smart Grid Infrastructure

Necessity of Information Security in Safeguarding Smart Grid...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： Namra Joshi Achala Khandelwal Shubham Joshi Department of Electrical Engineering SVKM’s Institute of Technology Dhule Maharashtra India Thakur College of Engineering & Technology Kandivali Mumbai Dept. of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

The Indian economy is continuously growing, so the power demand is increasing abruptly. The power extraction from non-conventional energy sources has also increased in the past 10 years. Somehow generation and demand are matched. However, a competent infrastructure is needed to handle power generated from multiple sources. Smart Grid Systems has excellent properties to handle such situations in power systems. The highlights of the fundamentals of smart grid, recent developments in Smart Grid as well as Importance of Information Security in Smart Grid is discussed.

关键词： Power demand Biological system modeling Information security Smart grids Power systems Information and communication technology Protection Standards

来源：评论

学校读者我要写书评

暂无评论

Flexible Multisubject Multiset FMRI data Analysis Using Robust Discriminative Dictionary Learning

Flexible Multisubject Multiset FMRI Data Analysis Using Robu...

引用

Asilomar Conference on Signals, Systems & Computers

作者： Rui Jin Shuai Xu Seung-Jun Kim Vince Calhoun Dept. of Computer Science & Electrical Engineering University of Maryland Baltimore County Baltimore MD Tri-institutional Center for Translational Research in Neuroimaging & Data Science (TReNDS) Atlanta GA

A novel dictionary learning method is proposed for analyzing multi-subject multiset functional magnetic resonance imaging (fMRI) data. It is assumed that the subjects are grouped based on subject-specific attributes, and multiple fMRI data sets are available for each subject. The proposed algorithm can identify four types of neural activation maps from such data sets. First, the maps shared across groups and those that are discriminative of group differences are estimated by incorporating the group attribute labels. Furthermore, the maps that are common across data sets and those unique to a data set are extracted using group sparsity constraints. Notably, the map types can be flexibly determined without pre-specifying the numbers of the maps of different types. Numerical tests on synthetic and real data verify the benefit of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forecasting events in multidimensional electroencephalographic brain data: Application to epileptic seizure prediction.

Forecasting events in multidimensional electroencephalograph...

引用

International Conference on Information Fusion

作者： Yueyang Liu Artemio Soto-Breceda Mark J. Cook Philippa Karoly David B. Grayden Levin Kuhlmann Dean R. Freestone Daniel Schmidt Dept. of Data Science and AI Faculty of Information Technology Monash University Clayton Australia Dept. of Biomedical Engineering The University of Melbourne Melboourne Australia Dept of Medicine St Vincent’s Hospital The University of Melbourne Fitzroy Australia Seer Medical Pty Melbourne Australia

ISBN: (数字)9781737749769

ISBN: (纸本)9798350371420

Forecasting events in multichannel electroencephalographic (EEG) brain recordings remains a formidable task given the noise and complexity in neural systems. Here we compare two dynamical systems motivated approaches to forecasting brain events. The first follows previous state-of-the-art (SOTA) research of time-series features of critical slowing down (autocorrelation, variance) as biomarkers of impending events. The second involves a novel long-term-short-term (LSTM) neural network-based filter to estimate the neurophysiological feature variables of mathematical neural population models of the EEG. Previous critical slowing research presented forecasting results for the best EEG channel, however, in practice the best channel cannot be known a priori. Therefore, here we also consider forecasting by combining the different features across the different EEG channels using logistic regression. One application area where forecasting brain events is important is epileptic seizure prediction. Epileptic seizures are debilitating events and up to 50 million people worldwide with drug-resistant epilepsy could benefit by receiving warnings of impending seizures. Here we apply the above methods to a long-term epileptic seizure prediction dataset from 15 patients. It was found that seizure forecasting with (1) logistic regression and critical slowing features, (2) logistic regression and neurophysiological features, and (3) the best channel using critical slowing features, respectively, achieved median sensitivities of 70,54 and $67 \%$ and median time in low seizure risk of 84,84, and $81 \%$. This indicates that a multichannel model approach can perform as well as the best channel approach, removing the need to find the best channel. It also suggests neurophysiological features could be used to increase time in low risk. Future work exploring other features, machine learning models and their various combinations could yield further improvements.

关键词： Logistic regression Sensitivity Machine learning Predictive models Brain modeling Feature extraction Electroencephalography Recording Forecasting Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

AI in Medicine: CNN Techniques for Pneumonia and Pandemic Pathogen Identification

AI in Medicine: CNN Techniques for Pneumonia and Pandemic Pa...

引用

Advanced Computing & Communication Technologies (ICACCTech), International Conference on

作者： Ganji Ramanjaiah Nagendar Yamsani Smritilekha Das Balajee Maram Ananda Babu Rudrubati Katakam Venkateswara Rao Dept. of Computer Science & Engineering (Data Science) R VR & JC College of Engineering Chowdavaram Guntur Andhra Pradesh India School of Computer Science and Artificial Intelligence SR University Warangal Telangana Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Dept. Of Computer Science & Engineering (AI & DS) Kallam Haranadhareddy Institute of Technology Chowdavaram Guntur Andhra Pradesh India Dept of Computer Science and Engineering Koneru lakshmaiah Education Foundation Vaddeswaram Guntur DT Andhra Pradesh India

ISBN: (数字)9798331519056

ISBN: (纸本)9798331519063

The current paper deals with the applicability of Convolutional Neural Networks in the detection of pneumonia and pandemic pathogens using medical imaging data. Leveraging the transformative power of AI in our study, we have placed a focus on the development and evaluation of a CNN model that will be trained on a heterogeneous dataset of chest X-rays and CT scans. This paper will propose a method for developing a CNN to classify images from a diverse dataset of chest X-rays and CT scans, ensuring diagnostic accuracy and speed to meet the critical challenges involved in disease diagnosis in a timely manner. Our results show that the CNN model has high accuracy, sensitivity, and specificity for the identification of pneumonia and differentiation of pandemic pathogens from others, surpassing conventional diagnostic techniques. What was more important to underline in this study was that the model demonstrated strong performance across multiple datasets and, more importantly, can easily be transplanted to clinical workflows. Improvement in the early detection capacity made this research emblematic of the huge role AI is expected to play in redefining health care, especially with respiratory diseases and pandemic preparedness. Future work will extend to the augmentation of the dataset and the fine-tuning of the model for its full clinical application.

关键词： Pathogens Pneumonia Accuracy Pandemics Computed tomography Sensitivity and specificity Convolutional neural networks Artificial intelligence Medical diagnostic imaging X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Emergency vs Non-Emergency Vehicle Classification: Enhancing Intelligent Traffic Management Systems

Emergency vs Non-Emergency Vehicle Classification: Enhancing...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： Madan S Kishan Shetty Ashwini Kodipalli Trupthi Rao Kumaraswamy S Dept. of Computer Science and Engineering Global Academy of Technology Bengaluru Karnataka India Dept of Artificial Intelligence and Data Science Global Academy of Technology Bengaluru Karnataka India Department of Computer Science and Engineering Global Academy of Technology Bengaluru Karnataka India

Due to its dense population, India frequently experiences traffic congestion, which puts lives in danger by trapping vehicles like ambulances, police cars, and fire trucks which run on road for emergency purpose. It becomes crucial to give these vehicles priority and allow for their easy passage. However, it becomes challenging or even impossible for traffic police to effectively handle such circumstances. Therefore, there is a requirement for an automated system that can locate emergency vehicles in high-traffic areas, alert the controller, or drive itself to direct other vehicles to make room. This study suggests an automated method for identifying emergency vehicles from CCTV footage that makes use of deep convolutional neural networks (CNN). The objective is to effectively identify and classify emergency vehicles in real-time, leveraging the power of advanced object detection techniques. With an accuracy of 91.73% and a loss of 0.2120, the suggested technique outperformed existing optimizers in accurately recognizing and classifying emergency vehicles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Discrimination between Patients with MCI and Alzheimer 1

EEG-Based Discrimination between Patients with MCI and Alzhe...

引用

1st International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2022

作者： Kazimipour, Borhan Boostani, Reza Borhani-Haghighi, Afshin Almatarneh, Sattam Aljaidi, Mohammad Monash University CSE Dept. Melbourne Australia Shiraz University Electrical and Computer Engineering Faculty CSE and IT Dept. Shiraz Iran Namazi Hospital Shiraz University of Medical Sciences Neurology Department Shiraz Iran Zarqa University Faculty of Information Technology Data Science and Artificial Intelligence Department Jordan Zarqa University Department of Computer Science Zarqa Jordan

ISBN: (纸本)9798350332742

There is a high similarity between the signs and symptoms of patients with Alzheimer and those with mild cognitive impairment (MCI). Although several attempts have been made to differentiate these two groups of patients by decoding the fluctuation of their electroencephalogram (EEG), the achieved results are not yet promising. To increase the differentiation rate, in this study, 14 patients with Alzheimer from 13 patients with MCI have been voluntarily enrolled while their EEG signals are recorded in presence of visual stimuli. To suppress the disrupting artifacts and noises (e.g., eye-blink and movement artefact) from the recorded EEGs, independent component analysis is applied. Next, the visual evoke potential (VEP) patterns are extracted by synchronous averaging and then multi-linear principal component analysis (MPCA) is applied to elicit discriminative features from VEPs of the patients. After feature extraction by MPCA, the reduced feature vectors of both groups are applied to a nearest neighbor classifier, leading to 77.35% differentiation accuracy. © 2022 IEEE.

关键词： Principal component analysis

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：