WMW-A: Rank-based two-sample independent test for small sample sizes through an auxiliary sample

Two-sample independent test methods are widely used in case-control studies to identify significant changes or differences, for example, to identify key pathogenic genes by comparing the gene expression levels in normal and disease cells. However, due to the high cost of data collection or labelling, many studies face the small sample problem, for which the traditional two-sample test methods often lose power. We propose a novel rank-based nonparametric test method WMW-A for small sample problem by introducing a three-sample statistic through another auxiliary sample. By combining the case, control and auxiliary samples together, we construct a three-sample WMW-A statistic based on the gap between the average ranks of the case and control samples in the combined samples. By assuming that the auxiliary sample follows a mixed distribution of the case and control populations, we analyze the theoretical properties of the WMW-A statistic and approximate the theoretical power. The extensive simulation experiments and real applications on microarray gene expression data sets show the WMW-A test could significantly improve the test power for two-sample problem with small sample sizes, by either available unlabelled auxiliary data or generated auxiliary data.

Multiscale Information Fusion for Hyperspectral Image Classification Based on Hybrid 2D-3D CNN

Hyperspectral images are widely used for classification due to its rich spectral information along with spatial information. To process the high dimensionality and high nonlinearity of hyperspectral images, deep learning methods based on convolutional neural network (CNN) are widely used in hyperspectral classification applications. However, most CNN structures are stacked vertically in addition to using a onefold size of convolutional kernels or pooling layers, which cannot fully mine the multiscale information on the hyperspectral images. When such networks meet the practical challenge of a limited labeled hyperspectral image dataset—i.e., “small sample problem”—the classification accuracy and generalization ability would be limited. In this paper, to tackle the small sample problem, we apply the semantic segmentation function to the pixel-level hyperspectral classification due to their comparability. A lightweight, multiscale squeeze-and-excitation pyramid pooling network (MSPN) is proposed. It consists of a multiscale 3D CNN module, a squeezing and excitation module, and a pyramid pooling module with 2D CNN. Such a hybrid 2D-3D-CNN MSPN framework can learn and fuse deeper hierarchical spatial–spectral features with fewer training samples. The proposed MSPN was tested on three publicly available hyperspectral classification datasets: Indian Pine, Salinas, and Pavia University. Using 5%, 0.5%, and 0.5% training samples of the three datasets, the classification accuracies of the MSPN were 96.09%, 97%, and 96.56%, respectively. In addition, we also selected the latest dataset with higher spatial resolution, named WHU-Hi-LongKou, as the challenge object. Using only 0.1% of the training samples, we could achieve a 97.31% classification accuracy, which is far superior to the state-of-the-art hyperspectral classification methods.

Cross domain meta-network for sketch face recognition

Because of the large modal difference between sketch image and optical image, and the problem that traditional deep learning methods are easy to overfit in the case of a small amount of training data, the Cross Domain Meta-Network for sketch face recognition method is proposed. This method first designs a meta-learning training strategy to solve the small sample problem, and then proposes entropy average loss and cross domain adaptive loss to reduce the modal difference between the sketch domain and the optical domain. The experimental results on UoM-SGFS and PRIP-VSGC sketch face data sets show that this method and other sketch face recognition methods.

Discriminative Center Loss for Face Photo-Sketch Recognition

Face photo-sketch recognition refers to the process of matching sketches to photos. Recently, there has been a growing interest in using a convolutional neural network to learn discriminatively deep features. However, due to the large domain discrepancy and the high cost of acquiring sketches, the discriminative power of the deeply learned features will be inevitably reduced. In this paper, we propose a discriminative center loss to learn domain invariant features for face photo-sketch recognition. Specifically, two Mahalanobis distance matrices are proposed to enhance the intra-class compactness during inter-class separability. Moreover, a regularization technique is adopted on the Mahalanobis matrices to alleviate the small sample problem. Extensive experimental results on the e-PRIP dataset verified the effectiveness of the proposed discriminative center loss.

Storage Location Assignment with Fuzzy PROMETHEE Method in Warehouse Systems with Uncertain Demand

Storage location assignment is an important decision problem in warehouse operations management. Because the main purpose of the storage location assignment system is to create various parameters to facilitate the diagnosis and positioning of the products in the warehouse. In addition, time spent on storage activities is an important factor in the demand cycle. However, uncertainty in product demands causes various problems in assigning products to storage locations. Therefore, it is necessary to research viable and sustainable tools in cases of uncertainty. One of these tools is fuzzy decision making methods, which are frequently used in the literature and give effective results. In this study, it is proposed to rank the products with the Fuzzy PROMETHEE (F-PROMETHEE) method under qualitative criteria for warehouse systems where the demand is uncertain and assign them to the most suitable storage locations according to this rank. The effectiveness of the proposed approach has been tested with a small sample problem. Criteria addressed for this problem are demand, profitability and sensitivity. Solution results have shown that the proposed approach is effective.

Learning Deep Hierarchical Spatial–Spectral Features for Hyperspectral Image Classification Based on Residual 3D-2D CNN

Every pixel in a hyperspectral image contains detailed spectral information in hundreds of narrow bands captured by hyperspectral sensors. Pixel-wise classification of a hyperspectral image is the cornerstone of various hyperspectral applications. Nowadays, deep learning models represented by the convolutional neural network (CNN) provides an ideal solution for feature extraction, and has made remarkable achievements in supervised hyperspectral classification. However, hyperspectral image annotation is time-consuming and laborious, and available training data is usually limited. Due to the “small-sample problem”, CNN-based hyperspectral classification is still challenging. Focused on the limited sample-based hyperspectral classification, we designed an 11-layer CNN model called R-HybridSN (Residual-HybridSN) from the perspective of network optimization. With an organic combination of 3D-2D-CNN, residual learning, and depth-separable convolutions, R-HybridSN can better learn deep hierarchical spatial–spectral features with very few training data. The performance of R-HybridSN is evaluated over three public available hyperspectral datasets on different amounts of training samples. Using only 5%, 1%, and 1% labeled data for training in Indian Pines, Salinas, and University of Pavia, respectively, the classification accuracy of R-HybridSN is 96.46%, 98.25%, 96.59%, respectively, which is far better than the contrast models.

Combining Inter-Subject Modeling with a Subject-Based Data Transformation to Improve Affect Recognition from EEG Signals

Existing correlations between features extracted from Electroencephalography (EEG) signals and emotional aspects have motivated the development of a diversity of EEG-based affect detection methods. Both intra-subject and inter-subject approaches have been used in this context. Intra-subject approaches generally suffer from the small sample problem, and require the collection of exhaustive data for each new user before the detection system is usable. On the contrary, inter-subject models do not account for the personality and physiological influence of how the individual is feeling and expressing emotions. In this paper, we analyze both modeling approaches, using three public repositories. The results show that the subject’s influence on the EEG signals is substantially higher than that of the emotion and hence it is necessary to account for the subject’s influence on the EEG signals. To do this, we propose a data transformation that seamlessly integrates individual traits into an inter-subject approach, improving classification results.