检索结果-内蒙古大学图书馆

End-to-end differentiability and tensor processing unit computing to accelerate materials’ inverse design

npj Computational Materials 2023年第1期9卷 1072-1083页

作者： Han Liu Yuhan Liu Kevin Li Zhangji Zhao Samuel S.Schoenholz Ekin D.Cubuk Puneet Gupta Mathieu Bauchy SOlids inFormaTics AI-Laboratory(SOFT-AI-Lab) College of Polymer Science and EngineeringSichuan UniversityChengdu 610065China AIMSOLID Research Wuhan 430223China Physics of AmoRphous and Inorganic Solids Laboratory(PARISlab) Department of Civil and Environmental EngineeringUniversity of CaliforniaLos AngelesCA 90095USA Department of Computer Science University of CaliforniaLos AngelesCA 90095USA Google Research Brain TeamMountain ViewCAUSA Department of Electrical and Computer Engineering University of CaliforniaLos AngelesCA 90095USA

Numerical simulations have revolutionized material ***,although simulations excel at mapping an input material to its output property,their direct application to inverse design has traditionally been limited by their high computing cost and lack of ***,taking the example of the inverse design of a porous matrix featuring targeted sorption isotherm,we introduce a computational inverse design framework that addresses these challenges,by programming differentiable simulation on TensorFlow platform that leverages automated end-to-end *** to its differentiability,the simulation is used to directly train a deep generative model,which outputs an optimal porous matrix based on an arbitrary input sorption isotherm ***,this inverse design pipeline leverages the power of tensor processing units(TPU)—an emerging family of dedicated chips,which,although they are specialized in deep learning,are flexible enough for intensive scientific *** approach holds promise to accelerate inverse materials design.

关键词： enough inverse isotherm

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Model for Clinical Time Series Prediction: Enhancing ICU Readmission Prediction 14

An Attention-Based Model for Clinical Time Series Prediction...

引用

14th International Conference on computer and Knowledge Engineering, ICCKE 2024

作者： Madinei, Hananeh Sadat Keyvanpour, Mohammad Reza Shojaedini, Seyed Vahab Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Alzahra University Tehran Iran Department of Computer Engineering Faculty of Engineering Alzahra University Tehran Iran Department of Electrical Engineering Iranian Research Organization for Science and Technology Tehran Iran

ISBN: (纸本)9798331511272

— In recent years, time series prediction has become a highly interesting topic in various applied areas, including clinical time series analysis. Hospitals and other clinical healthcare systems collect Electronic Health Records. These records contain important information that needs to be mined. This information provides a solid basis for predicting hospital readmission, helping to improve healthcare, enhance patient outcomes, and optimize hospital resources. This study introduces a novel deep learning attention-based approach for predicting 30-day ICU readmissions using clinical time series information extracted from the MIMIC III dataset. This approach incorporates time-aware positional encoding into the attention mechanism to enhance predictive performance by capturing the temporal representation of data and considering the temporal order of clinical time series data. This model is compared with cutting-edge models. The significant enhancements in the model performance achieved by the proposed method highlight the effectiveness of incorporating time-aware positional encoding in capturing temporal dependencies and improving prediction outcomes. These results underscore the potential of advanced attention mechanisms in clinical time series analysis. ©2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

LASS: A Novel and Economical Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization 31

LASS: A Novel and Economical Data Augmentation Framework Bas...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yanyue Li, Pengfei Lai, Yilong He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King's College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9798891761964

As more than 70% of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are hesitant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the reliance on a specific structure is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, large-scale data augmentation based on large language models faces an apparent disadvantage, the expensive costs. Therefore, in this paper, we propose LASS, a novel data augmentation framework based on both LArge and Small language models for debiaSing opinion summarization. Specifically, a small number of synthesized negative reviews is obtained by rewriting the positive text via a large language model. Then, a disentangle reconstruction model is trained based on the generated data. After training, a large amount of synthetic data can be obtained by decoding the new representation obtained from the combination of different sample representations and filtering based on perplexity degree and sentiment classification. Experiments have proved that LASS can effectively alleviate emotional bias, similar to using only large models, but in a more economical way. © 2025 Association for Computational Linguistics.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

M³FuNet: An Unsupervised Multivariate Feature Fusion Network for Hyperspectral Image Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2024年 62卷 1-15页

作者： Chen, Huayue Long, Haoyu Chen, Tao Song, Yingjie Chen, Huiling Zhou, Xiangbing Deng, Wu Key Laboratory of Optimization Theory and Applications at China West Normal University of Sichuan Province School of Computer Science China West Normal University Nanchong637002 China China West Normal University School of Geographical Science Nanchong637002 China Shandong Technology and Business University School of Computer Science and Technology Yantai264005 China Wenzhou University Computer Science Department Wenzhou325035 China Sichuan Tourism University School of Information and Engineering Chengdu610100 China Civil Aviation University of China School of Electronic Information and Automation Tianjin300300 China

Hyperspectral image (HSI) spectral-spatial joint feature (FE) extraction methods generally suffer from low feature retention and weak spatial-spectral dependence, which will lead to single-class feature confrontation (SCFC). To solve this problem, an unsupervised multivariate feature fusion network (M3FuNet) is developed in this article. In M3FuNet, multiscale supervector matrix correction (MSMC) and multiscale random convolution dispersion (MRCD) are used as the spectral and spatial feature extraction method, and the feature retention of spectral and spatial features is improved to achieve feature calibration by feature fusion and decision fusion, called 'multivariate feature fusion.' The MSMC is employed to correct the supervector matrix to reduce the intraclass variance in superpixel homogeneous regions and overcome the phenomenon of supervector block drift (SvBD). The MRCD uses random convolution and Gaussian smoothing to extract deep spatial features. Because of the similar feature representation ability of the MSMC and MRCD, the obtained spectral-spatial joint features have high feature retention and strong spectral-spatial dependence. Finally, this M3FuNet is used for realizing the classification of HSI. Three common HSI datasets are used to validate the effectiveness of the M3FuNet. The experiment results show that the M3FuNet has a superior performance compared with several state-of-the-art (SOTA) HSI classification methods. The code of the proposed M3FuNet is available at https://***/aichou233/M3FuNet. © 1980-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Attention-Augmented Parametric Kernel Graph Neural Network (APKGNN) for Node Classification 22

Attention-Augmented Parametric Kernel Graph Neural Network (...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Bose, Avishek Hsu, William H. Oak Ridge National Laboratory Computer Science and Mathematics Division Oak RidgeTN United States Kansas State University Department of Computer Science and Engineering ManhattanKS United States

ISBN: (纸本)9798350345346

We present a new graph neural network, the Attention-based Parametric-Kernel augmented Graph Neural Network (APKGNN), developed for node classification tasks. Despite extensive work on modeling multi-faceted relationships between connected nodes of a graph, the effect of attention on edge features mapped to relationships has not yet been analyzed through learning representation. This study derives such an attention vector by first calculating node features corresponding to endpoints of an edge and then aggregating these with extracted local intrinsic patches of a given graph to generate augmented local patch vectors. This process uses a parametric kernel based on Gaussian mixture models (GMMs) to embed local neighborhoods of the graph in local patches. The patch vectors then convolve with the above node features to produce an updated node representation. We show that this new learning representation (APKGNN) achieves higher node classification accuracy on tasks - both standard benchmarks (Cora, PubMed, Citeseer) and new experimental short text corpora where nodes correspond to text documents and words. This implementation of the GNN convolution layer outperforms state-of-the-art (SOTA) algorithms, achieving higher training, validation, and test accuracy by a significant margin on three standard benchmark data sets under both SOTA experimental settings and those for new testbeds. © 2023 IEEE.

关键词： APKGNN attention vector local patch multi-processing neighborhood sampling parametric kernel

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based few-shot person re-identification from top-view RGB and depth images

引用

Neural Computing and Applications 2024年第31期36卷 19365-19382页

作者： Abed, Almustafa Akrout, Belhassen Amous, Ikram Miracl Laboratory Enet’com University of Sfax National School of Electronics and Telecommunications of Sfax Road Tunis City El Ons Sfax3018 Tunisia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj11942 Saudi Arabia Sfax University Sfax3021 Tunisia

Person re-identification (re-id) attempts to match a person from the images of different time steps. Existing deep learning approaches either use appearance or geometry features for re-id which does not provide the required robustness because of higher intra-class similarity. Existing supervised re-id approaches utilize Convolutional Neural Networks (CNNs) and identity-labeled images to train, where the person images are taken by the sensors from a horizontal view. The horizontal view exposes the privacy of the people because of their facial appearance in the image. Moreover, person re-id includes new unseen people;however, CNN does not have the ability to identify the new unseen people because of a lack of continual learning. Privacy-preserved computer vision-assisted person re-id systems can benefit from visual appearance and geometry features extracted from top-view RGB and depth input. This paper presents the privacy-preserved person top-view re-id few-shot network which uses the appearance and geometry features. The EfficientNet is used for appearance-based features from RGB input, while PointNet is used to extract the geometry features from the point cloud which is made from the RGB-D image registration. Concatenated features from EfficientNet and PointNet are fed to the two-layer Bi-LSTM network for person identification. Finally, the whole network is converted into a few-shot network to achieve continual learning by removing the output layer and joining the similarity measurement unit. This approach is based on CNN and fine-tunes a TVPR/2 dataset acquired by using a top-view arrangement that is publicly available. The experimental results on TVPR/2 and GODPR datasets show that the proposed re-id network outperforms other state-of-the-art networks. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Retail stores

来源：评论

学校读者我要写书评

暂无评论

A Comparison Study Between Otsu’s Thresholding, Fuzzy C-Means, and K-Means for Breast Tumor Segmentation in Mammograms 4th

A Comparison Study Between Otsu’s Thresholding, Fuzzy C-Mea...

引用

4th International Conference on Image Processing and Capsule Networks, ICIPCN 2023

作者： Mohamed Saleck, Moustapha Ould Taleb, Nagi El Moustapha El Arby Chrif, Mohamed Benany Mohamed Mahmoud, El LAROSERI Laboratory Department of Computer Sciences Faculty of Sciences University of Chouaib Doukkali El Jadida Morocco Computer Sciences Department Higher Institute of Digital Nouakchott Mauritania Department of Mathematics and Computer Science University of Nouakchott AL Aasriya Nouakchott Mauritania

ISBN: (纸本)9789819970926

Currently, the technique of digital mammography is considered the first screening tool used for detecting breast cancer in early stages. The shape and margin of masses in mammograms play a crucial role in the classification of benign and malignant tumors. Several machine learning (ML) algorithms have demonstrated high performance in breast mass edge segmentation from mammograms. The main objective of this paper is to present a comparative study of three algorithms of ML where: C-means clustering, K-means clustering, and Otsu’s thresholding for automatically detecting the lesion edges on mammogram images. Two groups (C = 2) are assigned to clustering as output for each method. In order to achieve high accuracy in contour extraction, only relevant pixels are selected as inputs. This study will highlight the advantages and disadvantages of these algorithms, which are expected to improve the detection of breast masses contours in mammographic images. The mini-MIAS database is used to evaluate the obtained results which show a higher performance in terms of segmentation accuracy when using fuzzy C-means algorithm. However, a faster lesion extraction process can be achieved by utilizing the K-means clustering and Otsu’s threshold. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Robust Framework for Epileptic Seizure Diagnosis: Utilizing GRU-CNN Architectures in EEG Signal Analysis 20

A Robust Framework for Epileptic Seizure Diagnosis: Utilizin...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Nikoupour, Maryam Keyvanpour, Mohammad Reza Shojaedini, Seyed Vahab Alzahra University Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Tehran Iran Alzahra University Faculty of Engineering Department of Computer Engineering Tehran Iran Iranian Research Organization for Science and Technology Department of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350383942

Seizures that take place repeatedly and without provocation are referred to as epilepsy. Epilepsy can be diagnosed with electroencephalography (EEG). One of the most influential challenges of the past few years has been the use of deep learning algorithms to replace manual inspection of medical signals by specialists, such as epilepsy signal classification. This paper presents a multi-label classification approach for epileptic seizures using deep learning. UCI machine learning repository's epileptic seizure dataset has been used to classify epileptic seizure patients. 178 features are present in each of the 11500 samples in the dataset. Based on a variety of criteria, the proposed method may have a positive impact on epilepsy diagnosis, in most cases by approximately 6% compared with existing methods utilizing long short-term memory (LSTM) and autoencoder. It is possible thus to develop and apply gated recurrent unit-based methods with good potential for categorizing EEG signals for epilepsy diagnosis based on gated recurrent unit (GRU)-CNN based methods. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Improving the Interpretability through Maximizing Mutual Information for EEG Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 744-757页

作者： Yang, Hua Philip Chen, C.L. Chen, Bianna Zhang, Tong North Carolina State University Department of Computer Science United States South China University of Technology Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition The School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center The Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Trustworthy Graph Neural Networks (GNNs) for EEG emotion recognition should identify emotions accurately and elucidate corresponding rationales. Current GNNs have achieved notable performance by dynamically modeling emotional connections between EEG channels. However, these GNNs lack interpretability due to the absence of explicit rationale behind their predictions. This paper conducts a comprehensive identification of important EEG channels to enhance the interpretability of EEG emotion recognition from the perspective of mutual information. Specifically, an Adjacency-Explainable Graph Neural Network (AEG) for ante-hoc interpretability is proposed to capture genuine EEG emotional connections, which gives a theoretical guarantee to remove spurious connections. Moreover, a Channel-wise Adaptive Class Activation Mapping Explainer (CACA) for post-hoc interpretability is developed to locate the EEG channels that contribute most to predictions. Experimental results on three datasets, i.e., SEED, SEED-IV, and DREAMER, prove that imbuing training processes with enhanced interpretability ensures significant performance improvements in emotion recognition. Quantitative comparisons of post-hoc interpretability also demonstrate the superiority of CACA. Furthermore, this paper illustrates two potential applications of the proposed methodologies, showing their broader utility and significance. © 2010-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Mapper4Live: Using Control Structures to Embed Complex Mapping Tools into Ableton Live

Mapper4Live: Using Control Structures to Embed Complex Mappi...

引用

International Conference on New Interfaces for Musical Expression, NIME 2022

作者： Boettcher, Brady Malloch, Joseph Wang, Johnty Wanderley, Marcelo M. Input Devices and Musical Interaction Laboratory CIRMMT McGill University Canada Graphics and Experiential Media Laboratory Faculty of Computer Science Dalhousie University Canada

This paper presents Mapper4Live, a software plugin made for the popular digital audio workstation software Ableton Live. Mapper4Live exposes Ableton’s synthesis and effect parameters on the distributed libmapper signal mapping network, providing new opportunities for interaction between software and hardware synths, audio effects, and controllers. The plugin’s uses and relevance in research, music production and musical performance settings are explored, detailing the development journey and ideas for future work on the project. © 2022, International Conference on New Interfaces for Musical Expression. All rights reserved.

关键词： Mapping

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：