检索结果-内蒙古大学图书馆

Subjective and Objective Quality Assessments of AI-Generated Images for Language E-Learning

IEEE Access 2025年 13卷 100667-100682页

作者： Chibuike Onuoha Vu Hai Dang Nguyen Duc Nam Truong Thu Huong Pham Ngoc Nam Truong Cong Thang Department of Computer Science and Information Systems The University of Aizu Aizuwakamatsu Japan School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Vietnam College of Engineering and Computer Science VinUniversity Hanoi Vietnam

AI-generated images (AIGIs) are becoming popular and can be employed in many applications, owing to Generative AI (GAI). Researchers have developed models that can be used to generate images for different scenarios. In addition, researchers have proposed datasets of natural scene images for language learning and different AIGI-quality datasets for general applications. For e-learning, particularly in the context of language learning, no AIGI dataset is currently available. To fill this gap, we first proposed an AIGI quality dataset for language learning. Both subjective and objective assessments have been conducted on the proposed dataset. The findings from subjective assessment show that higher perceptual quality also corresponds to a more substantial alignment. It also shows that the average MOS scores of images generated from Stability AI models are similar and lower than images generated by the Dall.E3 model. The results of the objective assessment indicate that the performance of off-the-shelf quality models is generally low. In addition, results from finetuning learning-based quality models show that significant gains and improvements can be achieved using the dataset. The results of the alignment evaluation show that the HPS model is the best, and realistic images in the dataset produced the best alignment correlation compared to the other styles in the dataset. The findings also show that multimodal large language models, such as vision-enabled GPT-4 (GPT-4V), still struggle to produce alignment scores that correlate with humans.

关键词： Electronic learning Visualization Text to image Quality of experience Quality assessment Diffusion models Training data Training Generators Generative AI

来源：评论

学校读者我要写书评

暂无评论

MRIAD: A Pre-clinical Prevalence Study on Alzheimer’s Disease Prediction Through Machine Learning Classifiers 4th

MRIAD: A Pre-clinical Prevalence Study on Alzheimer’s Dise...

引用

4th Joint International Conference on Deep Learning, Big Data and Blockchain, DBB 2023

作者： Loba, Jannatul Mia, Md. Rajib Mahmud, Imran Mahi, Md. Julkar Nayeen Whaiduzzaman, Md. Ahmed, Kawsar Department of Software Engineering Daffodil International University Dhaka Bangladesh School of Information Systems Queensland University of Technology Brisbane Australia Department of Electrical and Computer Engineering University of Saskatchewan Saskatoon Canada

ISBN: (纸本)9783031423161

Alzheimer’s disease (AD) is a neurological illness that worsens with time. The aged population has expanded in recent years, as has the prevalence of geriatric illnesses. There is no cure, but early detection and proper treatment allow sufferers to live normal lives. Furthermore, people with this disease’s immune systems steadily degenerate, resulting in a wide range of severe disorders. Neuroimaging Data from magnetic resonance imaging (MRI) is utilized to identify and detect the disease as early as possible. The data is derived from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) collection of 266 people with 177 structural brain MRI imaging, DTI, and PET data for intermediate disease diagnosis. When neuropsychological and cognitive data are integrated, the study found that ML can aid in the identification of preclinical Alzheimer’s disease. Our primary objective is to develop a model that is reliable, simple, and rapid for diagnosing preclinical Alzheimer’s disease. According to our findings (MRIAD), the Logistic Regression (LR) model has the best accuracy and classification prediction of about 98%. The ML model is also developed in the paper. This article profoundly, describes the possibility to getting into Alzheimer’s disease (AD) information from the pre-clinical or non-preclinical trial datasets using Machine Learning Classifier (ML) approaches. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

AggFollower: Aggressiveness Informed Car-Following Modeling

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Chen, Xianda Yuan, Xinyi Zhu, Meixin Zheng, Xinhu Shen, Shaojie Wang, Xuesong Wang, Yinhai Wang, Fei-Yue Guangzhou China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong SAR China School of Transportation Engineering Tongji University Shanghai China Department of Civil and Environmental Engineering University of Washington Seattle WA USA State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection, acceleration pattern, and fuel consumption. However, existing car-following research used limited categories of driving style through pre-defined patterns and failed to encode driving style into data-driven car-following models. To address these limitations, we propose the Aggressiveness Informed Car-Following (AICF) modeling approach, which embeds driving style as a dynamic input feature in data-driven car-following models. In detail, We design driving aggressiveness tokens using four physical quantities (jerk, acceleration, relative speed, and relative spacing) to capture the heterogeneity of driving aggressiveness. These tokens were then embedded into a physics-informed Long Short-Term Memory (LSTM) based car-following model for trajectory prediction. To evaluate the effectiveness of our approach, we conducted extensive experiments based on 12,540 car-following events extracted from the HighD dataset and 24,093 events from the Lyft dataset. Compared to models devoid of considerations for driving aggressiveness levels, AICF exhibits superior efficacy in mitigating the Mean Square Error (MSE) of spacing and collision rate. To the best of our knowledge, this is the first work to directly incorporate real-time driving aggressiveness tokens as input features into data-driven car-following models, enabling a more comprehensive understanding of aggressiveness in car-following behavior. IEEE

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

DeepGCN based on variable multi‐graph and multimodal data for ASD diagnosis

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 879-893页

作者： Shuaiqi Liu Siqi Wang Chaolei Sun Bing Li Shuihua Wang Fei Li College of Electronic and Information Engineering Hebei UniversityBaodingChina Machine Vision Technology Innovation Center of Hebei Province BaodingChina The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijingChina School of Computer Science and Technology Henan Polytechnic UniversityJiaozuoChina

Diagnosing individuals with autism spectrum disorder(ASD)accurately faces great chal-lenges in clinical practice,primarily due to the data's high heterogeneity and limited sample *** tackle this issue,the authors constructed a deep graph convolutional network(GCN)based on variable multi‐graph and multimodal data(VMM‐DGCN)for ASD ***,the functional connectivity matrix was constructed to extract primary ***,the authors constructed a variable multi‐graph construction strategy to capture the multi‐scale feature representations of each subject by utilising convolutional filters with varying kernel ***,the authors brought the non‐imaging in-formation into the feature representation at each scale and constructed multiple population graphs based on multimodal data by fully considering the correlation between *** extracting the deeper features of population graphs using the deep GCN(DeepGCN),the authors fused the node features of multiple subgraphs to perform node classification tasks for typical control and ASD *** proposed algorithm was evaluated on the Autism Brain Imaging Data Exchange I(ABIDE I)dataset,achieving an accuracy of 91.62%and an area under the curve value of 95.74%.These results demon-strated its outstanding performance compared to other ASD diagnostic algorithms.

关键词： machine learning medical image processing medical signal processing

来源：评论

学校读者我要写书评

暂无评论

Optimization of Quality Process Control and Preventive Maintenance Strategy: A Case Study

引用

Operations Research Forum 2024年第4期5卷 84页

作者： Sadraoui, Youssef Er-ratby, Mohamed Kadiri, Moulay Saddik Kobi, Abdessamad Laboratory of Process Engineering Computer Science and Mathematics LIPIM National School of Applied Sciences of Khouribga Sultan Moulay Slimane University Beni Mellal Morocco Laboratory of Science and Engineering Techniques LaSTI National School of Applied Sciences of Khouribga Sultan Moulay Slimane University Beni Mellal Morocco LARIS Angevin Laboratory for Systems Engineering Research Polytech Angers University of Angers Angers France

The studied process concerns a wet grinding and cycloning unit, set up to ensure that the particle size it processes complies with the requirements in terms of pipe transport mode. Frequent shutdowns, low reliability, the risk of delivering a product with inappropriate particle size, and the lack of operational parameters’ control are all obstacles for the unit, having enormous repercussions on its relevance and performance. To improve this situation, the implementation of an innovative 5-month quality and process control study has proven crucial to establish a culture of quality among operators, aiming to achieve the targeted grain size. However, the innovative aspects of our approach lie in its thoroughness and inclusiveness since it addresses the process both qualitatively and quantitatively, focusing not only on theoretically modeling and simulating the grinding circuit but also providing an integrated method to address every component of the unit. By going through the seven stages of this study, we were able to enhance the overall performance of the unit controlling the particle size at the output. After establishing a set of quality control tools, we observed a remarkable development in mastering various parameters influencing the targeted particle size. The benefits generated by the study are extremely satisfying for the unit at different levels, particularly in terms of quality, process control, and resource optimization. Furthermore, the integration of maintenance management into the process has proven essential to ensure the reliability and sustainability of the installation, thereby contributing significantly to the overall efficiency of the unit. Graphical Abstract: (Figure presented.) © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Optimization Preventive maintenance Process capability Quality Statistical process control SPC Wet grinding

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Model for Early Detection of Dementia Using Blood Biosamples

Federated Learning Model for Early Detection of Dementia Usi...

引用

2023 IEEE International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2023

作者： Elsersy, Mohamed Sherif, Ahmed Imam, Ahmad Abdel-Aliem Khan Mamun, Mohammad M. R. Khalil, Kasem Haitham, Mohamed Higher Colleges of Technology Computer and Information Systems Dept. Abu Dhabi United Arab Emirates University of Southern Mississippi School of Computing Sciences and Computer Engineering MS United States William Carey University College of Osteopathic Medicine Mississippi MS United States Tennessee Technological University Electrical and Computer Engineering Department TN United States University of Mississippi Electrical and Computer Engineering Department MS United States Cairo Egypt

ISBN: (纸本)9798350322347

Alzheimer's disease (AD) is a serious, long-term health problem that causes much pain and loss for the person with it and their family. Its early and accurate detection might result in a substantial reduction of the disease outcomes and consequences. Blood biosamples are a simple and inexpensive technique in medical testing. This paper proposes diagnostic models for blood biosamples based on federated learning (FL) and its modifications to detect AD early. Our experiments used blood biosample data sets from the ADNI website to evaluate our models. Our performance analysis indicates that our algorithms are more accurate and achieve an accuracy of 87% for early detection. © 2023 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

UWB Channel Modeling and Simulation with Continuous Frequency Response

引用

China Communications 2022年第11期19卷 88-98页

作者： Kai Mao Qiuming Zhu Xijuan Ye Ruirui Feng Fuqiao Duan Yang Miao Maozhong Song The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space College of Electronic and Information EngineeringNanjing University of Aeronautics and AstronauticsNanjing 211106China The Radio Systems Faculty of Electrical Engineering Computer Science and Mathematics(EEMCS)University of Twentethe Netherlands

Ultra-wideband(UWB)technology is a prospective technology for high-rate transmission and accurate localization in the future communication ***-of-art channel modeling approaches usually divide the UWB channel into several sub-band channels and model them *** considering frequency-dependent channel parameters,a novel analytical UWB channel model with continuous frequency response is *** composite effect of all frequency components within the UWB channel on the channel impulse response(CIR)of delay domain is derived based on the continuous channel transfer function(CTF)of frequency *** this basis,a closed-form simulation model for UWB channels and geometry-based parameter calculation method are developed,which can guarantee the continuity of channel characteristics on the frequency domain and greatly reduce the simulation ***,the proposed method is applied to generate UWB channel with 2 GHz bandwidth at sub-6GHz and millimeter wave(mmWave)bands,*** channel measurements are also carried out to validate the proposed *** simulated CIR and power gain are shown to be in good agreement with the measurement ***,the comparison results of power gain and Doppler power spectral density(DPSD)show that the proposed UWB channel model Received:Apr.23,2022 Revised:Jun.09,2022 Editor:Wei Fan achieves a good balance between the simulation accuracy and efficiency.

关键词： ultra-wideband(UWB)channel continuous frequency response frequency-dependent channel parameters simulation model channel measurement

来源：评论

学校读者我要写书评

暂无评论

Hybrid Scenario Generation Method for Stochastic Virtual Bidding in Electricity Market

引用

CSEE Journal of Power and Energy systems 2021年第6期7卷 1312-1321页

作者： Dongliang Xiao Wei Qiao the School of Electric Power Engineering South China University of TechnologyGuangzhou 510641China the Power and Energy Systems Laboratory Department of Electrical and Computer EngineeringUniversity of Nebraska-LincolnLincolnNE 68588-0511 USA

Stochastic optimization can be used to generate optimal bidding strategies for virtual bidders in which the uncertain electricity prices are represented by using *** paper proposes a hybrid scenario generation method for electricity price using a seasonal autoregressive integrated moving average(SARIMA)model and historical *** electricity price spikes are first identified by using an outlier detection ***,the historical data are decomposed into base and spike ***,the base and spike component scenarios are generated by using the SARIMA-and historical data-based methods,***,the electricity price scenarios are obtained by combining the base and spike component *** studies are carried out for a virtual bidder in the PJM electricity market to validate the proposed *** optimal bidding strategies of the virtual bidder are generated by solving a stochastic optimization problem using the electricity price scenarios generated by the proposed method,the SARIMA method,and a historical data-based method,*** study results show that the proposed method is better than the SARIMA method in preserving statistical properties of the electricity price in the generated scenarios and is better than the historical data-based method in predicting the future trend of the electricity price and,therefore,can help the virtual bidder earn more profit in the electricity market.

关键词： Electricity market electricity price scenario generation stochastic optimization virtual bidding

来源：评论

学校读者我要写书评

暂无评论

GNN-Assisted BiG-AMP: Joint Channel Estimation and Data Detection for Massive MIMO Receiver

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 4631-4646页

作者： Liu, Zishen Wu, Nan He, Dongxuan Yuan, Weijie Li, Yonghui Quek, Tony Q. S. School of Information and Electronics Beijing Institute of Technology Beijing100081 China School of System Design and Intelligent Manufacturing Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China School of Electrical and Information Engineering The University of Sydney SydneyNSW2008 Australia Singapore University of Technology and Design 487372 Singapore Department of Electronic Engineering Kyung Hee University Yongin17104 Korea Republic of

In this paper, we develop a graph neural network (GNN)-assisted bilinear inference approach to enhance the receiver performance of the MIMO system through message passing-based joint channel estimation and data detection (JCD). Specifically, based on the bilinear generalized approximate message passing (BiG-AMP) framework and conditional correlation of signal, we propose a GNN-assisted BiG-AMP (GNN-BiGAMP) approach, which integrates a GNN module into the data-detection-loop to compensate the inaccurate marginal likelihood approximation. By leveraging the coupling between the channel and received symbols, a bilinear GNN-assisted BiG-AMP (BiGNN-BiGAMP) JCD receiver is further proposed. This method incorporates two GNNs with similar graph representation into the bilinear posterior estimation loops, which not only compensates for approximation errors but also alleviates performance loss due to premature variance convergence, thereby enhancing the receiver performance significantly. To fully exploit the supervised information from channel estimation and data detection, we propose a multitask learning based training scheme, which coordinates GNNs with different tasks in two loops. Simulation results show that our proposed GNN-assisted JCD receivers significantly outperform other JCD counterparts in terms of both channel estimation and data detection. © 2025 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Quality Process Control and Preventive Maintenance Optimization of a Grinding Unit: A Case Study 10

Quality Process Control and Preventive Maintenance Optimizat...

引用

10th International Conference on Optimization and Applications, ICOA 2024

作者： Sadraoui, Youssef Er-Ratby, Mohamed Kadiri, Moulay Saddik Kobi, Abdessamad National School of Applied Sciences Sultan Moulay Slimane University LIPIM Laboratory of Process Engineering Computer Science and Mathematics Khouribga Morocco National School of Applied Sciences Sultan Moulay Slimane University LASTI Laboratory of Science and Engineering Techniques Khouribga Morocco Polytech Angers University of Angers LARIS Angevin Laboratory for Systems Engineering Research France

ISBN: (纸本)9798350387353

The studied process is a grinding and hydroclassification unit designed to ensure that the grain size it processes is in line with the specifications for the pipe's transport mode. Obstacles to the unit's operational process include frequent stops, plant's low reliability, product delivery with an inappropriate grain size, and a lack of control over operating parameters. These factors have a significant impact on the unit's relevance and, consequently, its performance. We created a quality culture among operators with '0 grain quality loss' through the implementation of the quality and processes control study, which was essential to improve the situation. Thus, by completing the seven project stages, we were able to enhance and optimize the grinding and hydroclassification unit's overall performance and capability to regulate the grain size quality. We noticed a notable improvement in regulating the several parameters that affect the targeted particle size after we established tools for unit quality control, such as control and monitoring charts, reaction matrices, intervention flow charts and operational standards. The unit has seen a great deal of satisfaction from the project in terms of quality, process control and resources optimization. Moreover, the incorporation of preventive maintenance into this process has shown to be crucial in guaranteeing the reliability and durability of the installation, thereby substantially improving the unit's overall efficiency. © 2024 IEEE.

关键词： Preventive maintenance

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：