检索结果-内蒙古大学图书馆

On the Role of Priors in Bayesian Causal Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Geiger, Bernhard C. Kern, Roman Signal Processing and Speech Communication Laboratory Graz University of Technology Inf-feldgasse 16c Graz8010 Austria Know Center Research GmbH Sandgasse 34 Graz8010 Austria Institute for Interactive Systems and Data Science Graz University of Technology Sandgasse 36 Graz8010 Austria

In this work, we investigate causal learning of independent causal mechanisms from a Bayesian perspective. Confirming previous claims from the literature, we show in a didactically accessible manner that unlabeled data (i.e., cause realizations) do not improve the estimation of the parameters defining the mechanism. Furthermore, we observe the importance of choosing an appropriate prior for the cause and mechanism parameters, respectively. Specifically, we show that a factorized prior results in a factorized posterior, which resonates with Janzing and Schölkopf’s definition of independent causal mechanisms via the Kolmogorov complexity of the involved distributions and with the concept of parameter independence of Heckerman et al. Copyright © 2025, The Authors. All rights reserved.

关键词：

Mobility in China, 2020: a tale of four phases

学校读者我要写书评

暂无评论

National science Review 2021年第11期8卷 110-120页

作者： Suoyi Tan Shengjie Lai Fan Fang Ziqiang Cao Bin Sai Bing Song Bitao Dai Shuhui Guo Chuchu Liu Mengsi Cai Tong Wang Mengning Wang Jiaxu Li Saran Chen Shuo Qin Jessica R.Floyd Zhidong Cao Jing Tan Xin Sun Tao Zhou Wei Zhang Andrew J.Tatem Petter Holme Xiaohong Chen Xin Lu College of Systems Engineering National University of Defense Technology WorldPop School of Geography and Environmental ScienceUniversity of Southampton School of Mathematics and Big Data Foshan University State Key Laboratory on Blind Signal Processing State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Chinese Evidence-Based Medicine Center National Clinical Research Center for Geriatrics West China Hospital Sichuan University Big Data Research Center University of Electronic Science and Technology of China West China Biomedical Big Data Center West China Hospital Sichuan University Tokyo Tech World Hub Research Initiative Institute of Innovative Research Tokyo Institute of Technology School of Business Central South University Institute of Big Data and Internet Innovations Hunan University of Technology and Business

2020 was an unprecedented year,with rapid and drastic changes in human mobility due to the COVID-19 *** understand the variation in commuting patterns among the Chinese population across stable and unstable periods,we used nationwide mobility data from 318 million mobile phone users in China to examine the extreme fluctuations of population movements in 2020,ranging from the Lunar New Year travel season(chunyun), to the exceptional calm of COVID-19 lockdown,and then to the recovery *** observed that cross-city movements,which increased substantially in chunyun and then dropped sharply during the lockdown,are primarily dependent on travel distance and the socio-economic development of *** the Lunar New Year holiday,national mobility remained low until mid-February,and COVID-19 interventions delayed more than 72.89 million people returning to large *** network analysis revealed clusters of highly connected cities,conforming to the social-economic division of urban agglomerations in *** the mass migration back to large cities was delayed,smaller cities connected more densely to form new *** the recovery period after travel restrictions were lifted,the netflows of over 55% city pairs reversed in direction compared to before the *** findings offer the most comprehensive picture of Chinese mobility at fine resolution across various scenarios in China and are of critical importance for decision making regarding future public-health-emergency response,transportation planning and regional economic development,among others.

关键词： human mobility travel restrictions COVID-19 mobile phone data behavioral response

Estimation Of Gravimetric Vegetation Moisture In The Western United States Using A Multi-Sensor Approach

学校读者我要写书评

暂无评论

Estimation Of Gravimetric Vegetation Moisture In The Western...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： David Chaparro Thomas Jagdhuber Maria Piles François Jonard Mercè Vall-Llossera Adriano Camps Carlos López-Martínez Anke Fluhrer Roberto Fernández-Morán Martin J. Baur Andrew F. Feldman Dara Entekhabi German Aerospace Center Microwaves and Radar Institute Wessling Germany Institute of Geography University of Augsburg Augsburg Germany Image Processing Lab Universitat de València València Spain Earth Observation and Ecosystem Modelling Laboratory SPHERES Research Unit Université de Liège (ULiege) Liège Belgium Department of Signal Theory and Communications and Institut d’Estudis Espacials de Catalunya CommSensLab Universitat Politècnica de Catalunya (UPC) Barcelona Spain ASPIRE Visiting International Professor UAE University CoE Al Ain UAE Department of Geography University of Cambridge Cambridge UK NASA Postdoctoral Program Biospheric Sciences Laboratory NASA Goddard Space Flight Center Greenbelt MD USA Civil and Environmental Engineering Massachusetts Institute of Technology Cambridge MA USA

Vegetation optical depth (VOD) depends on the water, structure, and biomass of vegetation. Here, we propose a multi-sensor approach to isolate the water component from the VOD and to retrieve gravimetric vegetation moisture (m g ) in the western United States. The approach estimates VOD from radar and LiDAR data and minimizes the differences between these estimates and SMAP/AMSR2 VOD observations. This minimization allows to obtain the best fitting value of m g with help of a dielectric model. Results are consistent both in space (drier vegetation in arid areas) and time (drier vegetation in drier months). The mg estimates are in the same range than in situ mg data, with some underestimation (bias ~ -0.07 kg/kg). Statistical results are reasonable (r ~ 0.45, RMSE ≤0.10 kg/kg), yet the different spatial and temporal representation of in situ and remote measurements have an impact in the direct comparisons. Our results highlight the potential for developing new vegetation moisture datasets based on VOD decomposition.

关键词：

Distribution Preserving Deep Semi-Nonnegative Matrix Factorization

学校读者我要写书评

暂无评论

Distribution Preserving Deep Semi-Nonnegative Matrix Factori...

IEEE International Conference on Systems, Man and Cybernetics

作者： Zhuolin Tan Anyong Qin Yongqing Sun Yuan Yan Tang School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Signal and Information Processing Chongqing China NTT Media Intelligence Laboratories Yokosuka Japan Zhuhai UM Science & Technology Research Institute University of Macau Macau China

ISBN: (纸本)9781665442084

Deep semi-nonnegative matrix factorization can obtain the hidden hierarchical representations according to the unknown attributes of the given data. On the other hand, the inherent structure of the each data cluster can be described by the distribution of the intra-class data. Then one hopes to learn a new low dimensional representation which can preserve the intrinsic structure embedded in the original high dimensional data space perfectly. Here we propose a novel distribution preserving deep semi-nonnegative matrix factorization method (DPNMF) to achieve this goal. As a result, the manifold structures in the raw data are well preserved in the feature space being from the top layer. The experimental results on the real-world datasets show that the proposed algorithm has good performance in terms of cluster accuracy and normalized mutual information (NMI).

关键词： Manifolds Conferences Clustering algorithms Approximation algorithms Mutual information Cybernetics

Tigc-Net: Transformer-Improved Graph Convolution Network for Spatio-Temporal Prediction

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Chen, Kai Yang, Chunfeng Zhou, Zhengyuan Liu, Yao Ji, Tianjiao Sun, Weiya Chen, Yang School of Cyber Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China The College of Software Engineering Southeast University Nanjing210096 China Laboratory of Image Science and Technology The School of Computer Science and Engineering Southeast University Nanjing210096 China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of Radiology Zhongda Hospital Southeast University Nanjing210009 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing210096 China NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention Beijing China Beijing Institute of Tracking and Communication Technology Beijing100094 China

Modeling spatio-temporal sequences is an important topic yet challenging for existing neural networks. Most of the current spatio-temporal sequence prediction methods usually capture features separately in temporal and spatial dimensions or employ multiple mutually independent local spatio-temporal graphs to represent a spatio-temporal sequence. The first kind of method mentioned above is difficult to mine the complex spatio-temporal correlations, while the other is limited for the accuracy of long-term predictions. To handle these issues, this paper proposes a Transformer-Improved Graph Convolution Network for spatio-temporal prediction. Specifically, the temporal location encoding method is exploited to derive the spatio-temporal characteristics of the sequence utilizing a spatio-temporal feature fusion network. In addition, a spatio-temporal attention network is developed to enhance the spatio-temporal correlation of the sequence, and the dynamic spatial features of sequence are further extracted through the adaptive graph convolution network. A private dataset and a public dataset are employed to demonstrate the performance of the proposed TIGC-Net. The qualitative and quantitative results show that the proposed TIGC-Net can extract dynamic spatiotemporal properties more effectively, enhance the spatio-temporal correlation of sequences and improve the prediction accuracy compared with four stateof-the-art. © 2022, The Authors. All rights reserved.

关键词： Convolution

Robust acoustic scene classification using a multi-spectrogram encoder-decoder framework

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pham, Lam Phan, Huy Nguyen, Truc Palaniappan, Ramaswamy Mertins, Alfred McLoughlin, Ian University of Kent School of Computing Medway Kent United Kingdom Signal Processing and Speech Communication Lab Graz University of Technology Austria Institute for Signal Processing University of Lubeck Germany National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei China

This article proposes an encoder-decoder network model for Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording from its acoustic signature. We make use of multiple low-level spectrogram features at the front-end, transformed into higher level features through a well-trained CNN-DNN front-end encoder. The high level features and their combination (via a trained feature combiner) are then fed into different decoder models comprising random forest regression, DNNs and a mixture of experts, for back-end classification. We report extensive experiments to evaluate the accuracy of this framework for various ASC datasets, including LITIS Rouen and IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 Task 1, 2017 Task 1, 2018 Tasks 1A & 1B and 2019 Tasks 1A & 1B. The experimental results highlight two main contributions;the first is an effective method for high-level feature extraction from multi-spectrogram input via the novel C-DNN architecture encoder network, and the second is the proposed decoder which enables the framework to achieve competitive results on various datasets. The fact that a single framework is highly competitive for several different challenges is an indicator of its robustness for performing general ASC tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)

A novel TSK fuzzy system incorporating multiview collaborative transfer learning for personalized epileptic EEG detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Andong Deng, Zhaohong Lou, Qiongdan Choi, Kup-Sze Shen, Hongbin Wang, Shitong School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Key Laboratory of Digital Design and Software Technology Wuxi214122 China Centre for Smart Health Hong Kong Polytechnic University Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

—In clinical practice, electroencephalography (EEG) plays an important role in the diagnosis of epilepsy. EEG-based computer-aided diagnosis of epilepsy can greatly improve the accuracy of epilepsy detection while reducing the workload of physicians. However, there are many challenges in practical applications for personalized epileptic EEG detection (i.e., training of detection model for a specific person), including the difficulty in extracting effective features from one single view, the undesirable but common scenario of lacking sufficient training data in practice, and the no guarantee of identically distributed training and test data. To solve these problems, we propose a TSK fuzzy system-based epilepsy detection algorithm that integrates multi-view collaborative transfer learning. To address the challenge due to the limitation of single-view features, multi-view learning ensures the diversity of features by extracting them from different views. The lack of training data for building a personalized detection model is tackled by leveraging the knowledge from the source domain (reference scene) to enhance the performance of the target domain (current scene of interest), where mismatch of data distributions between the two domains is resolved with adaption technique based on maximum mean discrepancy. Notably, the transfer learning and multi-view feature extraction are performed at the same time. Furthermore, the fuzzy rules of the TSK fuzzy system equip the model with strong fuzzy logic inference capability. Hence, the proposed method has the potential to detect epileptic EEG signals effectively, which is demonstrated with the positive results from a large number of experiments on the CHB-MIT dataset. © 2021, CC BY-NC-ND.

关键词： Electrophysiology

Steady-state Analysis of Bipolar Transistor

学校读者我要写书评

暂无评论

Steady-state Analysis of Bipolar Transistor

Progress in Electromagnetic Research Symposium (PIERS)

作者： Yeqiang Yan Xingang Ren Shuping He Xiaotao Huang Zhixiang Huang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan China Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Lingnan Normal University Zhanjiang China

ISBN: (纸本)9781665409889

Numerical simulation of semiconductor devices enable the quick obtain of the device physical characteristics. However, the trial productions of the semiconductor devices have the disadvantages of long cycle and high cost. Therefore, it is necessary to carry out numerical simulation investigating semiconductor devices. We propose the coupling approach and the decoupling-Gummel method to solve the semiconductor equations. The results of the two methods are compared with the commercial software. Numerical experiment indicates that the results obtained by our method are accurate. When the transistor is at a low voltage bias, the decoupling method converges faster than the coupling method. In the case of high voltage bias, the decoupling method has a slower convergence speed than the coupling method, even difficult to converge for higher voltage bias. However, the coupling method has higher memory requirements than the Gummel method. Therefore, we need to balance the advantages of the coupling method and the Gummel method when conduct the numerical simulation.

关键词： Couplings Bipolar transistors Voltage Production Numerical simulation Mathematical models Software

Weakly Supervised Joint Whole-Slide Segmentation and Classification in Prostate Cancer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pati, Pushpak Jaume, Guillaume Ayadi, Zeineb Thandiackal, Kevin Bozorgtabar, Behzad Gabrani, Maria Goksel, Orcun IBM Research Europe Switzerland Department of Pathology Brigham and Women’s Hospital Harvard Medical School United States Department of Pathology Massachusetts General Hospital Harvard Medical School United States Cancer Program Broad Institute of Harvard MIT United States Data Science Program Dana-Farber Harvard Cancer Center United States Computer-Assisted Applications in Medicine ETH Zurich Switzerland Signal Processing Laboratory 5 EPFL Switzerland EPFL Switzerland Department of Information Technology Uppsala University Sweden

The segmentation and automatic identification of histological regions of diagnostic interest offer a valuable aid to pathologists. However, segmentation methods are hampered by the difficulty of obtaining pixel-level annotations, which are tedious and expensive to obtain for Whole-Slide images (WSI). To remedy this, weakly supervised methods have been developed to exploit the annotations directly available at the image level. However, to our knowledge, none of these techniques is adapted to deal with WSIs. In this paper, we propose WHOLESIGHT, a weakly-supervised method, to simultaneously segment and classify WSIs of arbitrary shapes and sizes. Formally, WHOLESIGHT first constructs a tissue-graph representation of the WSI, where the nodes and edges depict tissue regions and their interactions, respectively. During training, a graph classification head classifies the WSI and produces node-level pseudo labels via post-hoc feature attribution. These pseudo labels are then used to train a node classification head for WSI segmentation. During testing, both heads simultaneously render class prediction and segmentation for an input WSI. We evaluated WHOLESIGHT on three public prostate cancer WSI datasets. Our method achieved state-of-the-art weakly-supervised segmentation performance on all datasets while resulting in better or comparable classification with respect to state-of-the-art weakly-supervised WSI classification methods. Additionally, we quantify the generalization capability of our method in terms of segmentation and classification performance, uncertainty estimation, and model calibration. © 2023, CC BY-NC-ND.

关键词： image segmentation