No abstract

This paper presents a novel tensor-based feature learning approach for whole-brain fMRI classification. Whole-brain fMRI data have high exploratory power, but they are challenging to deal with due to large numbers of voxels. A critical step for fMRI classification is dimensionality reduction, via feature selection or feature extraction. Most current approaches perform voxel selection based on feature selection methods. In contrast, feature extraction methods, such as principal component analysis (PCA), have limited usage on whole brain due to the small sample size problem and limited interpretability. To address these issues, we propose to directly extract features from natural tensor (rather than vector) representations of whole-brain fMRI using multilinear PCA (MPCA), and map MPCA bases to voxels for interpretability. Specifically, we extract low-dimensional tensors by MPCA, and then select a number of MPCA features according to the captured variance or mutual information as the input to SVM. To provide interpretability, we construct a mapping from the selected MPCA bases to raw voxels for localizing discriminating regions. Quantitative evaluations on challenging multiclass tasks demonstrate the superior performance of our proposed methods against the state-of-the-art, while qualitative analysis on localized discriminating regions shows the spatial coherence and interpretability of our mapping.

Feature selection is an important step for large-scale image data analysis, which has been proved to be difficult due to large size in both dimensions and samples. Feature selection firstly eliminates redundant and irrelevant features and then chooses a subset of features that performs as efficient as the complete set. Generally, supervised feature selection yields better performance than unsupervised feature selection because of the utilization of labeled information. However, labeled data samples are always expensive to obtain, which constraints the performance of supervised feature selection, especially for the large web image datasets. In this paper, we propose a semi-supervised feature selection algorithm that is based on a hierarchical regression model. Our contribution can be highlighted as: (1) Our algorithm utilizes a statistical approach to exploit both labeled and unlabeled data, which preserves the manifold structure of each feature type. (2) The predicted label matrix of the training data and the feature selection matrix are learned simultaneously, making the two aspects mutually benefited. Extensive experiments are performed on three large-scale image datasets. Experimental results demonstrate the better performance of our algorithm, compared with the state-of-the-art algorithms. © 2014 Springer-Verlag Berlin Heidelberg

Embedded feature selection is effective when both prediction and interpretation are needed. The Lasso and its extensions are standard methods for selecting a subset of features while optimizing a prediction function. In this paper, we are interested in embedded feature selection for multidimensional data, wherein (1) there is no need to reshape the multidimensional data into vectors and (2) structural information from multiple dimensions are taken into account. Our main contribution is a new method called Regularized multilinear regression and selection (Remurs) for automatically selecting a subset of features while optimizing prediction for multidimensional data. Both nuclear norm and the ℓ1-norm are carefully incorporated to derive a multi-block optimization algorithm with proved convergence. In particular, Remurs is motivated by fMRI analysis where the data are multidimensional and it is important to find the connections of raw brain voxels with functional activities. Experiments on synthetic and real data show the advantages of Remurs compared to Lasso, Elastic Net, and their multilinear extensions.

The environment and climate significantly affect the land surface temperature (LST) of a city. Previous studies have revealed that LST exhibits significant spatial heterogeneity primarily caused by a combination of natural factors and human activities. Based on this, the introduction of point of interest data of the "production-living-ecological space" divides the influencing pattern into a comprehensive description of human activities supplemented by natural factors, resulting in the precise influencing factors of spatial heterogeneity of LST. Taking Nanjing (Jiangsu Province, China) as a case study, this study uses Landsat-8 remote sensing images, point of interest data, and other data to establish a geographically weighted regression model that combines natural factors and human activities. The main research results are as follows: (1) The LST of Nanjing ranged from 19.9 °C to 47.6 °C, whereas the distribution trend was "low at both ends and high in the middle." (2) There is no multicollinearity of the influencing factors, the fitting degree of LST and each influencing factor reached 0.87. The regression coefficients were high and exhibited both positive and negative values, implying that spatial heterogeneity exists among the influencing factors and LST. (3) The ranking of how all factors influence the LST followed the order of water area > forest and grassland > ecological space > slope > production space > elevation > living space. The research results have practical significance for improving the quality of life of urban residents and providing a critical theoretical basis for optimizing urban human settlements. Index Terms-Land surface temperature, geographically weighted regression, spatial heterogeneity, human settlements, Nanjing I. INTRODUCTION N April 2020, the World Meteorological Organization released the Report on the State of the Global Climate in 2015−2019, highlighting that the global average temperature in 2019 was 1.1 °C higher than the estimated pre-industrialization average temperature. Moreover, the temperatures in the past five years had been the highest since the establishment of a temperature record. Since the foundation of the People's Republic of China till 2019, the Chinese urban population has increased from 57.65 million to 848.43 million, with the national urban proportion increasing from 10.64% to 60.60%.Due to the rising urban population, large amounts of greenhouse gases have been released into the atmosphere; additionally, vegetation, water bodies, and other natural features have been degraded by construction [1] , thereby changing the land surface temperature (LST). Research has revealed that LST can potentially indicate the ecological Manuscript