检索结果-内蒙古大学图书馆

arXiv 2022年

作者： He, Hui Zhang, Qi Yi, Kun Shi, Kaize Niu, Zhendong Cao, Longbing The School of Medical Technology Beijing Institute of Technology Beijing100081 China The School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China The Department of Computer Science Tongji University Shanghai201804 China The Data Science and Machine Intelligence Lab University of Technology SydneyNSW2007 Australia The Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education China The DataX Research Centre School of Computing Macquarie University SydneyNSW2109 Australia

Due to the non-stationary nature, the distribution of real-world multivariate time series (MTS) changes over time, which is known as distribution drift. Most existing MTS forecasting models greatly suffer from distribution drift and degrade the forecasting performance over time. Existing methods address distribution drift via adapting to the latest arrived data or self-correcting per the meta knowledge derived from future data. Despite their great success in MTS forecasting, these methods hardly capture the intrinsic distribution changes, especially from a distributional perspective. Accordingly, we propose a novel framework temporal conditional variational autoencoder (TCVAE) to model the dynamic distributional dependencies over time between historical observations and future data in MTSs and infer the dependencies as a temporal conditional distribution to leverage latent variables. Specifically, a novel temporal Hawkes attention mechanism represents temporal factors subsequently fed into feed-forward networks to estimate the prior Gaussian distribution of latent variables. The representation of temporal factors further dynamically adjusts the structures of Transformer-based encoder and decoder to distribution changes by leveraging a gated attention mechanism. Moreover, we introduce conditional continuous normalization flow to transform the prior Gaussian to a complex and form-free distribution to facilitate flexible inference of the temporal conditional distribution. Extensive experiments conducted on six real-world MTS datasets demonstrate the TCVAE’s superior robustness and effectiveness over the state-of-the-art MTS forecasting baselines. We further illustrate the TCVAE applicability through multifaceted case studies and visualization in real-world *** Codes 68Txx Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Cross-Attention Graph Neural Networks for Inferring Gene Regulatory Networks with Skewed Degree Distribution

arXiv

引用

arXiv 2024年

作者： Xiong, Jiaqi Yin, Nan Liang, Shiyang Li, Haoyang Wang, Yingxu Ai, Duo Pan, Fang Wang, Jingjie Department of Gastroenterology Tangdu Hospital Fourth Military Medical University Shaanxi 710038 China Aberdeen Institute of Data Science and Artificial Intelligence South China Normal University Guangzhou528225 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Department of Internal Medicine The No. 944 Hospital of Joint Logistic Support Force of PLA Xiongguan Road Jiu Quan735000 China Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates Department of Dermatology Xijing Hospital Fourth Military Medical University No 127 of West Changle Road Shaanxi Xi’an710032 China

Inferencing Gene Regulatory Networks (GRNs) from gene expression data is a pivotal challenge in systems biology, and several innovative computational methods have been introduced. However, most of these studies have not considered the skewed degree distribution of genes. Specifically, some genes may regulate multiple target genes while some genes may be regulated by multiple regulator genes. Such a skewed degree distribution issue significantly complicates the application of directed graph embedding methods. To tackle this issue, we propose the Cross-Attention Complex Dual Graph Embedding Model (XATGRN). Our XATGRN employs a cross-attention mechanism to effectively capture intricate gene interactions from gene expression profiles. Additionally, it uses a Dual Complex Graph Embedding approach to manage the skewed degree distribution, thereby ensuring precise prediction of regulatory relationships and their directionality. Our model consistently outperforms existing state-of-the-art methods across various datasets, underscoring its efficacy in elucidating complex gene regulatory mechanisms. Our codes used in this paper are publicly available at: https://***/kikixiong/XATGRN. © 2024, CC BY.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

The re-markable 21-cm power spectrum I: Probing the Hi distribution in the post-reionization era using marked statistics

arXiv

引用

arXiv 2024年

作者： Kamran, Mohd Sahlén, Martin Sarkar, Debanjan Majumdar, Suman Department of Physics and Astronomy Uppsala University Box 516 Uppsala751 20 Sweden Department of Physics Trottier Space Institute McGill University QCH3A 2T8 Canada Ciela-Montreal Institute for Astrophysical Data Analysis and Machine Learning QCH2V 0B3 Canada Department of Physics Ben-Gurion University of the Negev Be'er Sheva84105 Israel Department of Astronomy Astrophysics & Space Engineering Indian Institute of Technology Indore Indore453552 India Department of Physics Blackett Laboratory Imperial College LondonSW7 2AZ United Kingdom

The neutral hydrogen (Hi) power spectrum, measured from intensity fluctuations in the 21-cm background, offers insights into the large-scale structures (LSS) of our Universe in the post-reionization era (redshift z −1) we expectedly find that the Hi evolves slowly at early times, but more rapidly at late times. This evolution is not well-captured by the power spectrum of the standard (unmarked) Hi field. We also study how the evolution of the Hi field depends on the chosen smoothing scale for the mark, and how this affects the marked power spectrum. We conclude that the information about the Hi content at low and intermediate densities is important for a correct and consistent analysis of Hi content and evolution based on the 21-cm background. The marked power spectrum can thus provide a less biased statistic for parameter constraints than the normal power spectrum. Copyright © 2024, The Authors. All rights reserved.

关键词： Cosmology

来源：评论

学校读者我要写书评

暂无评论

Adaptive explicit kernel minkowski weighted k-means

arXiv

引用

arXiv 2020年

作者： Aradnia, Amir Haeri, Maryam Amir Ebadzadeh, Mohammad Mehdi Department of Computer Engineering Amirkabir University of Technology Tehran Iran Learning Data-Analytics and Technology Department University of Twente Enschede Netherlands

The K-means algorithm is among the most commonly used data clustering methods. However, the regular K-means can only be applied in the input space and it is applicable when clusters are linearly separable. The kernel K-means, which extends K-means into the kernel space, is able to capture nonlinear structures and identify arbitrarily shaped clusters. However, kernel methods often operate on the kernel matrix of the data, which scale poorly with the size of the matrix or suffer from the high clustering cost due to the repetitive calculations of kernel values. Another issue is that algorithms access the data only through evaluations of K(xi, xj), which limits many processes that can be done on data through the clustering task. This paper proposes a method to combine the advantages of the linear and nonlinear approaches by using driven corresponding approximate finite-dimensional feature maps based on spectral analysis. Applying approximate finite-dimensional feature maps were only discussed in the Support Vector Machines (SVM) problems before. We suggest using this method in kernel K-means era as alleviates storing huge kernel matrix in memory, further calculating cluster centers more efficiently and access the data explicitly in feature space. These explicit feature maps enable us to access the data in the feature space explicitly and take advantage of K-means extensions in that space. We demonstrate our Explicit Kernel Minkowski Weighted K-mean (Explicit KMWK-mean) method is able to be more adopted and find best-fitting values in new space by applying additional Minkowski exponent and feature weights parameter. Moreover, it can reduce the impact of concentration on nearest neighbour search by suggesting investigate among other norms instead of Euclidean norm, includes Minkowski norms and fractional norms (as an extension of the Minkowski norms with p © 2020, CC BY.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy

arXiv

引用

arXiv 2024年

作者： Handa, Palak Mahbod, Amirreza Schwarzhans, Florian Woitek, Ramona Goel, Nidhi Dhir, Manas Chhabra, Deepti Jha, Shreshtha Sharma, Pallavi Thakur, Vijay Chawla, Simarpreet Singh Gunjan, Deepak Kakarla, Jagadeesh Raman, Balasubramanian Research Center for Medical Image Analysis and Artificial Intelligence Department of Medicine Danube Private University Krems Austria Department of Electronics and Communication Engineering Indira Gandhi Delhi Technical University for Women Delhi India Department of Artificial Intelligence and Data Sciences Indira Gandhi Delhi Technical University for Women Delhi India Department of Artificial Intelligence and Machine Learning University School of Automation and Robotics Guru Gobind Singh Indraprastha University Delhi India Department of Electronics and Communication Engineering Delhi Technological University Delhi India Columbia University New YorkNY United States Department of Gastroenterology and HNU All India Institute of Medical Sciences Delhi India Chennai Kancheepuram India Department of Computer Science and Engineering Indian Institute of Technology Roorkee India

We present the Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy. It was virtually organized by the Research Center for Medical Image Analysis and Artificial Intelligence (MIAAI), department of Medicine, Danube Private University, Krems, Austria in collaboration with the 9th International Conference on Computer Vision & Image Processing (CVIP 2024) being organized by the Indian Institute of Information technology, Design and Manufacturing (IIITDM) Kancheepuram, Chennai, India. This document provides an overview of the challenge, including the registration process, rules, submission format, description of the datasets used, qualified team rankings, all team descriptions, and the benchmarking results reported by the organizers. © 2024, CC BY.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Is L2 Physics-Informed Loss Always Suitable for Training Physics-Informed Neural Network?

arXiv

引用

arXiv 2022年

作者： Wang, Chuwei Li, Shanda He, Di Wang, Liwei School of Mathematical Sciences Peking University China Machine Learning Department School of Computer Science Carnegie Mellon University United States National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Center for Data Science Peking University China Zhejiang Lab China

The Physics-Informed Neural Network (PINN) approach is a new and promising way to solve partial differential equations using deep learning. The L2 Physics-Informed Loss is the de-facto standard in training Physics-Informed Neural Networks. In this paper, we challenge this common practice by investigating the relationship between the loss function and the approximation quality of the learned solution. In particular, we leverage the concept of stability in the literature of partial differential equation to study the asymptotic behavior of the learned solution as the loss approaches zero. With this concept, we study an important class of high-dimensional non-linear PDEs in optimal control, the Hamilton-Jacobi-Bellman (HJB) Equation, and prove that for general Lp Physics-Informed Loss, a wide class of HJB equation is stable only if p is sufficiently large. Therefore, the commonly used L2 loss is not suitable for training PINN on those equations, while L∞ loss is a better choice. Based on the theoretical insight, we develop a novel PINN training algorithm to minimize the L∞ loss for HJB equations which is in a similar spirit to adversarial training. The effectiveness of the proposed algorithm is empirically demonstrated through experiments. Our code is released at https://***/LithiumDA/L_inf-PINN. Copyright © 2022, The Authors. All rights reserved.

关键词： Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Deep CNN: A machine learning approach for driver drowsiness detection based on eye state

引用

Revue d'Intelligence Artificielle 2019年第6期33卷 461-466页

作者： Reddy Chirra, Venkata Rami Uyyala, Srinivasulu Reddy Kishore Kolli, Venkata Krishna Department of Computer Applications National Institute of Technology Tiruchirappalli620015 India Machine Learning and Data Analytics Lab Department of Computer Applications National Institute of Technology Tiruchirappalli620015 India Department of Computer Science and Engineering VFSTR Guntur522213 India

Driver drowsiness is one of the reasons for large number of road accidents these days. With the advancement in Computer Vision technologies, smart/intelligent cameras are developed to identify drowsiness in drivers, thereby alerting drivers which in turn reduce accidents when they are in fatigue. In this work, a new framework is proposed using deep learning to detect driver drowsiness based on Eye state while driving the vehicle. To detect the face and extract the eye region from the face images, Viola-Jones face detection algorithm is used in this work. Stacked deep convolution neural network is developed to extract features from dynamically identified key frames from camera sequences and used for learning phase. A SoftMax layer in CNN classifier is used to classify the driver as sleep or non-sleep. This system alerts driver with an alarm when the driver is in sleepy mood. The proposed work is evaluated on a collected dataset and shows better accuracy with 96.42% when compared with traditional CNN. The limitation of traditional CNN such as pose accuracy in regression is overcome with the proposed Staked Deep CNN. © 2019 Lavoisier. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Models in Remote Sensing: Current Progress and Future Trends

arXiv

引用

arXiv 2023年

作者： Li, Xiang Wen, Congcong Hu, Yuan Yuan, Zhenghang Zhu, Xiao Xiang The King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia Department of Electrical and Computer Engineering New York University Abu Dhabi Abu Dhabi129188 United Arab Emirates The Institute of Remote Sensing and Geographic Information Systems Peking University Beijing100871 China Data Science in Earth Observation Technical University of Munich Munich80333 Germany The Munich Center for Machine Learning Munich80333 Germany

The remarkable achievements of ChatGPT and GPT-4 have sparked a wave of interest and research in the field of large language models for Artificial General Intelligence (AGI). These models provide intelligent solutions close to human thinking, enabling us to use general artificial intelligence to solve problems in various applications. However, in remote sensing (RS), the scientific literature on the implementation of AGI remains relatively scant. Existing AI-related research in remote sensing primarily focuses on visual understanding tasks while neglecting the semantic understanding of the objects and their relationships. This is where vision-language models excel, as they enable reasoning about images and their associated textual descriptions, allowing for a deeper understanding of the underlying semantics. Vision-language models can go beyond visual recognition of RS images, model semantic relationships, and generate natural language descriptions of the image. This makes them better suited for tasks requiring visual and textual understanding, such as image captioning, and visual question answering. This paper provides a comprehensive review of the research on vision-language models in remote sensing, summarizing the latest progress, highlighting challenges, and identifying potential research opportunities. Specifically, we review the application of vision-language models in mainstream remote sensing tasks, including image captioning, text-based image generation, text-based image retrieval, visual question answering, scene classification, semantic segmentation, and object detection. For each task, we analyze representative works and discuss research progress. We also summarize the commonly used remote sensing vision-language datasets, codebases, and online accessible resources. Finally, we delineate the limitations of current studies and suggest potential avenues for future advancements. This review aims to provide a comprehensive review of the current research pro

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Systematically Evaluation of Challenge Obfuscated APUFs

arXiv

引用

arXiv 2022年

作者： Gao, Yansong Yao, Jianrong Pang, Lihui Zhang, Zhi Fu, Anmin Xiong, Naixue Kim, Hyoungshick School of Computer Science and Engineering Nanjing University of Science and Technology China School of Electrical Engineering University of South China China Department of Software Sungkyunkwan University Korea Republic of Data61 CSIRO Sydney Australia National Engineering Research Center for E-Learning Central China Normal University Wuhan430079 China

As a well-known physical unclonable function that can provide huge number of challenge response pairs (CRP) with a compact design and fully compatibility with current electronic fabrication process, the arbiter PUF (APUF) has attracted great attention. To improve its resilience against modeling attacks, many APUF variants have been proposed so far. Though the modeling resilience of response obfuscated APUF variants such as XOR-APUF and lightweight secure APUF (LSPUF) have been well studied, the challenge obfuscated APUFs (CO-APUFs) such as feed-forward APUF (FF-APUF), and XOR-FF-APUF are less elucidated, especially, with the deep learning (DL) methods. This work systematically evaluates five CO-APUFs including three influential designs of FF-APUF, XOR-FF-APUF, iPUF, one very recently design (dubbed as MnS1,S2,S3-APUF) and our newly optimized design (dubbed as OAX-FF-APUF), in terms of their reliability, uniformity (related to uniqueness), and modeling resilience. Three DL techniques of GRU, TCN and MLP are employed to examine these CO-APUFs' modeling resilience-the first two are newly explored. With computation resource of a common personal computer, we show that all five CO-APUFs with relatively large scale can be successfully modeled-attacking accuracy higher or close to its reliability. The hyper-parameter tuning of DL technique is crucial for implementing efficient attacks. Increasing the scale of the CO-APUF is validated to be able to improve the resilience but should be done with minimizing the reliability degradation. As the powerful capability of DL technique affirmed by us, we recommend the DL, specifically the MLP technique always demonstrating best efficacy, to be always considered for examining the modeling resilience when newly composited APUFs are devised or to a large extent, other strong PUFs are constructed. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Animation-assisted learning enhances caregivers’ knowledge of anticipatory guidance for children during a well-child clinical visit: A prospective study

引用

Journal of the Formosan Medical Association 2025年

作者： Su, Yu-Tsun Chao, Hsiang-Hao Wang, Jieh-Neng Huang, Iwen Su, Chian-Heng Lin, Chyi-Her Department of Pediatrics E-Da Hospital I-Shou University Kaohsiung Taiwan School of Medicine for International Students College of Medicine I-Shou University Kaohsiung Taiwan Department of Pediatrics National Cheng Kung University Hospital College of Medicine National Cheng Kung University Tainan Taiwan Department of Information and Learning Technology College of Science and Engineering National University of Tainan Taiwan Institute of Epidemiology and Preventive Medicine College of Public Health National Taiwan University Taipei Taiwan Health Data Research Center National Taiwan University Taipei Taiwan

Purpose: To evaluate whether animation-assisted learning (AAL) enhances caregiver's knowledge of anticipatory guidance (AG) for children and determine the influence of the socioeconomic status during a well-child clinical visit. Methods: We prospectively enrolled caregivers who presented for well-child checkups at a tertiary care center. Participants completed a pre-test, watched a 25-min animation on specific AG topics, and then completed a post-test. We collected information on the caregivers’ gender, parity number, educational level, age, and employment status and then analyzed test accuracy relative to select socio-demographic factors. Results: We enrolled 150 caregivers (75 in the ≤3-month group, and 75 in the >3-month-to-7-year group). The pre- and post-AAL accuracy rates were 68.7% ± 14.5% vs. 88.2% ± 9.9% for the ≤3-month and 75.9% ± 13.1% vs. 92.3% ± 10.0% for the >3-month-to-7-year groups. Women, non-primipara caregivers, and college graduates in the ≤3-month group had better pre-test accuracy than their counterparts (p = 0.002, 0.002, and 0.004, respectively). Irrespective of socio-demographic factors, all caregivers demonstrated significantly improved AG knowledge post-AAL. Furthermore, college graduates or unemployed caregivers in the ≤3-month group showed improvements with AAL (p = 0.001 and 0.006, respectively). Conclusions: Caregiver's knowledge level further improved post-AAL regardless of their socio-demographic backgrounds, highlighting AAL's effectiveness across diverse populations. The most substantial improvements were observed among higher-educated or unemployed caregivers with infants aged ≤3 months. © 2025 Formosan Medical Association

关键词： Animation Anticipatory guidance Caregiver Knowledge Well-child visit

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：