检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hwang, Uiwon Lee, Jonghyun Shin, Juhyeon Yoon, Sungroh Division of Digital Healthcare Yonsei University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In the face of the deep learning model’s vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although the potential benefits of applying data augmentation to SFDA are attractive, several challenges arise such as the dependence on prior knowledge of class-preserving transformations and the increase in memory and computational requirements. In this paper, we propose Source-free Domain Adaptation Through the Lens of Data Augmentation (SF(DA)2), a novel approach that leverages the benefits of data augmentation without suffering from these challenges. We construct an augmentation graph in the feature space of the pretrained model using the neighbor relationships between target features and propose spectral neighborhood clustering to identify partitions in the prediction space. Furthermore, we propose implicit feature augmentation and feature disentanglement as regularization loss functions that effectively utilize class semantic information within the feature space. These regularizers simulate the inclusion of an unlimited number of augmented target features into the augmentation graph while minimizing computational and memory demands. Our method shows superior adaptation performance in SFDA scenarios, including 2D image and 3D point cloud datasets and a highly imbalanced dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Wheat Agricultural Residences for Bioenergy Generation in Morocco

Wheat Agricultural Residences for Bioenergy Generation in Mo...

引用

Renewable Energy and Hydrogen Technologies (GlobConHT), IEEE IAS Global Conference on

作者： Meisam Mahdavi Francisco Jurado Konrad Schmitt Stephen Bayne Manohar Chamana Department of Electrical Engineering University of Jaén Linares Jaén Spain Electrical & Computer Engineering Department Texas Tech University Lubbock TX USA Renewable Energy Program Texas Tech University Lubbock USA

Morocco is one of the important producers of wheat in Africa, in which this crop is the first agricultural product in the country. In spite of obtaining a huge quantity of wheat residues in the Moroccan agriculture sector, a small portion of this great bioenergy resource is reused for energy generation in the country. This is a big challenge for Morocco because its energy sector highly depends on costly fossil fuel imports. Furthermore, the country has to decrease harmful gases emission based on the Paris and Kyoto agreements. Regarding the importance of rainfall amount and water resources available for this agricultural product that is the main feedstock of Moroccan food, the use of wheat biomass to produce energy will remove high pressure from both the national energy and agriculture sectors. Besides that, the problems related to crop residue removal are reduced by using wheat biomass. Also, the use of wheat residues for energy generation pushes farmers to prevent the open firing of wheat straws and unnecessary air pollutants release. Thus, the present paper, for the first time, calculates possible energy production from wheat straws and root biomasses in Morocco, aiming to provide useful information for Morocco's energy sector.

关键词： Productivity Firing Plants (biology) Hydrogen Crops Air pollution Fossil fuels

来源：评论

学校读者我要写书评

暂无评论

More Efficient Training Strategy to Leverage Neurons in Neural Network

More Efficient Training Strategy to Leverage Neurons in Neur...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Cheng-Fu Liou Yi-Cheng Yu Research Labs (MZAIR Labs) Meta Zen Artificial Intelligence Tainan Taiwan Graduate Degree Program of College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

Comparing the structures of current neural networks and the biological brain, it can be observed that many mechanisms correspond to each other according to their functions. From the perspective of the biological brain, different components have different long-term or short-term memory effects, such as the hippopotamus. However, current neural networks do not pay much attention to this aspect. In this work, we incorporated many hypotheses or theories inspired by the territory of neurobiology to retain the learned knowledge. To start with, we follow the inspiration of the synaptic homeostasis hypothesis (SHY) [1] and add an additional training stage to the training process of the model, which can ensure that only the most important information remains intact and the insignificant synapse can be pruned. In other words, we divide the overall training process into two learning stages: synaptogenesis and synaptic sparsifying. We experimentally demonstrate that our novel learning strategy significantly outperforms the traditional solution in training a sequence of tasks at different times on three public datasets, which supports that the proposed method is more efficient for resource-limited edge devices.

关键词： Training Industrial electronics Neurons Homeostasis Task analysis Biological neural networks Synapses

来源：评论

学校读者我要写书评

暂无评论

Accumulating Curriculum Knowledge Based on Neural Network Isolated Algorithm

Accumulating Curriculum Knowledge Based on Neural Network Is...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Cheng-Fu Liou Yi-Cheng Yu Meta Zen Artificial Intelligence Research Labs (MZAIR Labs) Tainan Taiwan Graduate Degree Program of College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

Feeding the training data to neural networks in a specific sequence, from the simple data to the difficult data, utilizing curriculum learning can enhance performance improvements over the typical learning strategy based on shuffling training samples randomly, without any additional computational costs. This training approach has been successfully applied in all fields of machine learning. However, the current curriculum learning will gradually introduce difficult samples until the model eventually performs joint training. In addition, our experimental results find and demonstrate how the order of training tasks arranged according to the difficulty of different tasks influences the reuse percentage of model capacity, allowing us to observe the impact of curriculum learning on model performance from different perspectives. Finally, we also separately conduct three ablations analyses of our model to comprehensively enhance the understanding of the impacts of the proposed approach and further demonstrate its scalability to a standard large-scale dataset, i.e., the ImageNet dataset.

关键词： Training Industrial electronics Scalability Knowledge based systems Training data Machine learning Multitasking

来源：评论

学校读者我要写书评

暂无评论

Picosecond optical-to-x-ray (Cd,Mg)Te radiation detectors

Picosecond optical-to-x-ray (Cd,Mg)Te radiation detectors

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Cheng, J. Komissarov, I. Chen, G. Chakraborty, D. Kutcher, S. Chen, H. Trivedi, S. Sobolewski, Roman Materials Science Graduate Program University of Rochester RochesterNY14627 United States Laboratory for Laser Energetics University of Rochester RochesterNY14623 United States Department of Electrical and Computer Engineering University of Rochester RochesterNY14627 United States Brimrose Technology Corp SparksMD21152 United States

We developed a dual optical/x-ray ultrafast photodetector based on in-house grown Cdo * Mg0.03Te single crystals. The detector is characterized by ~200 ps full-width-at-half-maximum, readout-electronics limited photor... 详细信息

ISBN: (纸本)9781957171258

关键词： X ray detectors

来源：评论

学校读者我要写书评

暂无评论

On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss

arXiv

引用

arXiv 2024年

作者： Oh, Yeongtak Lee, Saehyung Hwang, Uiwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of

Large-scale language-vision pre-training models, such as CLIP, have achieved remarkable text-guided image morphing results by leveraging several unconditional generative models. However, existing CLIP-guided image morphing methods encounter difficulties when morphing photorealistic images. Specifically, existing guidance fails to provide detailed explanations of the morphing regions within the image, leading to misguidance. In this paper, we observed that such misguidance could be effectively mitigated by simply using a proper regularization loss. Our approach comprises two key components: 1) a geodesic cosine similarity loss that minimizes inter-modality features (i.e., image and text) on a projected subspace of CLIP space, and 2) a latent regularization loss that minimizes intra-modality features (i.e., image and image) on the image manifold. By replacing the naïve directional CLIP loss in a drop-in replacement manner, our method achieves superior morphing results on both images and videos for various benchmarks, including CLIP-inversion. © 2024, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Load Profile Effect on Shunt Capacitor Placement in Radial Distribution Feeders

Load Profile Effect on Shunt Capacitor Placement in Radial D...

引用

IEEE Kansas Power and Energy Conference

作者： Meisam Mahdavi Augustine Awaafo Konrad Schmitt Manohar Chamana Department of Electrical Engineering University of Jaén Linares Jaén Spain Electrical and Computer Engineering Department Texas Tech University Lubbock TX USA Renewable Energy Program Texas Tech University Lubbock USA

Capacitor placement in electric power systems is an effective way to minimize energy losses, especially in distribution systems, where power losses are more than transmission ones. On the other hand, time-varying load levels affect energy losses amount in such networks. Therefore, load profile has an important role in determining the amount of power losses and the optimal place of shunt capacitors in radial feeders. However, embedding load variability in the capacitor placement problem enhances the computational burden and processing time, while its ignorance leads to inaccurate calculation of energy losses and subsequent optimal locations of capacitor banks. Hence, most of specialized studies have ignored load changes in their capacitor placement models because of computational burden and processing time increase. Accordingly, the present paper intent to evaluate the effect of consumption patterns on capacitor placement proposals in order to understand the importance of load variability consideration in reducing power losses through reactive power compensation. The analysis has been carried out using a mathematical program.ing language in several distribution systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Art: Pattern Recognition of Wifi Detected Occupancy in Commercial Buildings

Fuzzy Art: Pattern Recognition of Wifi Detected Occupancy in...

引用

Annual Conference of the Canadian Society of Civil engineering, CSCE 2021

作者： Simma, Krishna Chaitanya Jagadeesh Caudell, Thomas P. Bogus, Susan M. Mammoli, Andrea Department of Civil Construction and Environmental Engineering University of New Mexico AlbuquerqueNMMSC01 1070 United States Department of Electrical and Computer Engineering University of New Mexico AlbuquerqueNMMSC01 1070 United States Customer Technologies Program Electric Power Research Institute 3420 Hillview Ave Palo AltoCA94304 United States

ISBN: (纸本)9789811905025

Research that predicts occupancy patterns in commercial buildings has gained in significance ever since the influence of occupants on building energy consumption became evident. Studies have employed a variety of sensory systems to collect the occupancy data and understand human behaviors throughout buildings. However, establishing a dedicated sensor network to collect occupancy data can become expensive for building owners. In this context, obtaining occupancy data from an existing WiFi network could eliminate the cost concerns. Data within the WiFi routers provide sufficient information for accurate estimates of occupancy. To estimate occupancy levels, this work proposes to learn and recognize WiFi connection using an Adaptive Resonance Theory (ART) artificial neural network. A detailed understanding of occupancy patterns using the WiFi data is helpful for developing heating and cooling schedules that optimize HVAC energy consumption. For this study, occupancy data was collected over a 17-week semester at the University of New Mexico using existing WiFi routers located in a large lecture hall used by multiple classes. This data was used to learn patterns of repetition using the neural network. The results show that if the 24-h occupancy profiles can be subdivided into smaller time segments defined by external schedules such as lecture start and end times or other constraints, significant patterns can be detected. A detailed understanding of these patterns can greatly facilitate occupancy load forecasting for effective building management (e.g. HVAC operation). © 2023, Canadian Society for Civil engineering.

关键词： Office buildings

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Normal and ASD EEG Data Using Hjorth Parameters

Comparative Analysis of Normal and ASD EEG Data Using Hjorth...

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Muliyadi Muliyadi Melinda Melinda Yuwaldi Away Syahrul Gazali Doctoral Program School of Engineering Post Graduate Program Universitas Syiah Kuala Banda Aceh Indonesia Electrical Engineering Department Politeknik Negeri Lhokseumawe Aceh Indonesia Dept. Electrical Engineering and Computer Engineering Faculty Universitas Syiah Kuala Banda Aceh Indonesia Dept. Neurology Universitas Syiah Kuala Banda Aceh Indonesia Mahar Mardjono National Brain Center Hospital Jakarta Indonesia

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

The increasing prevalence of autism spectrum disorder (ASD) in recent decades has underscored the need for more accurate and objective diagnostic methods. Electroencephalography (EEG) holds promise as a tool in ASD neurobiological research due to its ability to capture neural oscillatory activity with high temporal resolution. This study aims to analyze the neurophysiological differences between individuals with ASD and neurotypical populations by examining EEG data using Hjorth parameters. The preprocessing stage involved using a Butterworth filter to enhance EEG signal quality by eliminating noise in the frequency range of 4-40 Hz. The Hjorth parameters, including Activity, Mobility, and Complexity, were used to assess the statistical characteristics of the EEG signals. The analysis was conducted on EEG data collected from 5 typical individuals and 5 ASD ASD subjects. Our findings reveal that the Hjorth Activity parameter is notably lower in the ASD group across all regions, with the most significant differences observed in the left and right frontal areas, where average activity measures 0.236 μV 2 and 0.060 μV 2 in ASD individuals, compared to 0.512 μV 2 and 0.138 μV 2 in the neurotypical group. However, the Hjorth Complexity and Mobility values remained consistent between the two groups, implying that the fundamental structure of the EEG signals is relatively preserved. These findings offer insights into the neurobiological mechanisms of ASD and suggest the potential use of Hjorth parameters in developing more targeted interventions for individuals with ASD.

关键词： Human computer interaction Autism Frontal lobe Noise Neural activity Electroencephalography Complexity theory Signal resolution Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Deformable Image Registration Using Vision Transformers for Cardiac Motion Estimation from Cine Cardiac MRI Images 1

引用

Functional Imaging and Modeling of the Heart - 12th International Conference, FIMH 2023, Proceedings

作者： Upendra, Roshan Reddy Simon, Richard Shontz, Suzanne M. Linte, Cristian A. Center for Imaging Science Rochester Institute of Technology RochesterNY United States Biomedical Engineering Rochester Institute of Technology RochesterNY United States Electrical Engineering and Computer Science University of Kansas LawrenceKS United States Bioengineering Program University of Kansas LawrenceKS United States Institute for Information Sciences University of Kansas LawrenceKS United States

ISBN: (数字)9783031353024

ISBN: (纸本)9783031353017

Accurate cardiac motion estimation is a crucial step in assessing the kinematic and contractile properties of the cardiac chambers, thereby directly quantifying the regional cardiac function, which plays an important role in understanding myocardial diseases and planning their treatment. Since the cine cardiac magnetic resonance imaging (MRI) provides dynamic, high-resolution 3D images of the heart that depict cardiac motion throughout the cardiac cycle, cardiac motion can be estimated by finding the optical flow representation between the consecutive 3D volumes from a 4D cine cardiac MRI dataset, thereby formulating it as an image registration problem. Therefore, we propose a hybrid convolutional neural network (CNN) and Vision Transformer (ViT) architecture for deformable image registration of 3D cine cardiac MRI images for consistent cardiac motion estimation. We compare the image registration results of our proposed method with those of the VoxelMorph CNN model and conventional B-spline free form deformation (FFD) non-rigid image registration algorithm. We conduct all our experiments on the open-source Automated Cardiac Diagnosis Challenge (ACDC) dataset. Our experiments show that the deformable image registration results obtained using the proposed method outperform the CNN model and the traditional FFD image registration method. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image registration

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：