arXiv subjects

Wenwen Li

Publications and source records attributed to Wenwen Li.

78 records · Page 5Linked to original sources

arXiv2018

Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI

While functional magnetic resonance imaging (fMRI) is important for healthcare/neuroscience applications, it is challenging to classify or interpret due to its multi-dimensional structure, high dimensionality, and small number of samples available. Recent sparse multilinear regression methods based on tensor are emerging as promising solutions for fMRI, yet existing works rely on unfolding/folding operations and a tensor rank relaxation with limited tightness. The newly proposed tensor singular value decomposition (t-SVD) sheds light on new directions. In this work, we study t-SVD for sparse multilinear regression and propose a Sparse tubal-regularized multilinear regression (Sturm) method for fMRI. Specifically, the Sturm model performs multilinear regression with two regularization terms: a tubal tensor nuclear norm based on t-SVD and a standard L1 norm. We further derive the algorithm under the alternating direction method of multipliers framework. We perform experiments on four classification problems, including both resting-state fMRI for disease diagnosis and task-based fMRI for neural decoding. The results show the superior performance of Sturm in classifying fMRI using just a small number of voxels.

cs.CV↗

arXiv2018

Construction of accurate machine learning force fields for copper and silicon dioxide

Recently, the machine learning force field has emerged as a powerful atomic simulation approach for its high accuracy and low computational cost. However, its applications in the multi-component materials are relatively less. In this study, the ML force fields are constructed for both elemental material (Cu) and binary material (SiO2). The atomic environments are described by the structural fingerprint that takes the bond angle into account, and then, different ML techniques, including linear regression, neural network and mixture model method, are used to learn the structure-force relationship. We found that the use of angular structural fingerprint and mixture model method significantly improves the accuracy of ML force fields. In addition, we discussed the effective structural fingerprints auto-selection method based on LASSO and the genetic algorithm. The atomic simulations carried out with ML force fields are in excellent agreement with ab initio calculations.

cond-mat.mtrl-sci↗

arXiv2018

Deep Convolutional Neural Networks for Map-Type Classification

Maps are an important medium that enable people to comprehensively understand the configuration of cultural activities and natural elements over different times and places. Although massive maps are available in the digital era, how to effectively and accurately access the required map remains a challenge today. Previous works partially related to map-type classification mainly focused on map comparison and map matching at the local scale. The features derived from local map areas might be insufficient to characterize map content. To facilitate establishing an automatic approach for accessing the needed map, this paper reports our investigation into using deep learning techniques to recognize seven types of map, including topographic map, terrain map, physical map, urban scene map, the National Map, 3D map, nighttime map, orthophoto map, and land cover classification map. Experimental results show that the state-of-the-art deep convolutional neural networks can support automatic map-type classification. Additionally, the classification accuracy varies according to different map-types. We hope our work can contribute to the implementation of deep learning techniques in cartographical community and advance the progress of Geographical Artificial Intelligence (GeoAI).

stat.ML↗

arXiv2017

Spatial Data Infrastructures

Spatial data infrastructure (SDI) is the infrastructure that facilitates the discovery, access, management, distribution, reuse, and preservation of digital geospatial resources. These resources may include maps, data, geospatial services, and tools. As cyberinfrastructures, SDIs are similar to other infrastructures, such as water supplies and transportation networks, since they play fundamental roles in many aspects of the society. These roles have become even more significant in today's big data age, when a large volume of geospatial data and Web services are available. From a technological perspective, SDIs mainly consist of data, hardware, and software. However, a truly functional SDI also needs the efforts of people, supports from organizations, government policies, data and software standards, and many others. In this chapter, we will present the concepts and values of SDIs, as well as a brief history of SDI development in the U.S. We will also discuss the components of a typical SDI, and will specifically focus on three key components: geoportals, metadata, and search functions. Examples of the existing SDI implementations will also be discussed.

cs.CY↗

arXiv2014

Constructing Gazetteers from Volunteered Big Geo-Data Based on Hadoop

Traditional gazetteers are built and maintained by authoritative mapping agencies. In the age of Big Data, it is possible to construct gazetteers in a data-driven approach by mining rich volunteered geographic information (VGI) from the Web. In this research, we build a scalable distributed platform and a high-performance geoprocessing workflow based on the Hadoop ecosystem to harvest crowd-sourced gazetteer entries. Using experiments based on geotagged datasets in Flickr, we find that the MapReduce-based workflow running on the spatially enabled Hadoop cluster can reduce the processing time compared with traditional desktop-based operations by an order of magnitude. We demonstrate how to use such a novel spatial-computing infrastructure to facilitate gazetteer research. In addition, we introduce a provenance-based trust model for quality assurance. This work offers new insights on enriching future gazetteers with the use of Hadoop clusters, and makes contributions in connecting GIS to the cloud computing environment for the next frontier of Big Geo-Data analytics.

cs.DC↗

arXiv2010

Mach reflection and KP solitons in shallow water

Reflection of an obliquely incident solitary wave onto a vertical wall is studied analytically and experimentally. We use the Kadomtsev-Petviashivili (KP) equation to analyze the evolution and its asymptotic state. Laboratory experiments are performed using the laser induced fluorescent (LIF) technique, and detailed features and amplifications at the wall are measured. We find that proper physical interpretation must be made for the KP solutions when the experimental results are compared with the theory under the assumptions of quasi-two dimensionality and weak nonlinearity. Due to the lack of physical interpretation of the theory, the numerical results were previously thought not in good agreement with the theory. With proper treatment, the KP theory provides an excellent model to predict the present laboratory results as well as the previous numerical results. The theory also indicates that the present laboratory apparatus must be too short to achieve the asymptotic state. The laboratory and numerical results suggest that the maximum of the predicted four-fold amplification would be difficult to be realized in the real-fluid environment. The reality of this amplification remains obscure.

nlin.PS↗