As a generalization of complex fuzzy set (CFS), interval-valued complex fuzzy set (IVCFS) is a new research topic in the field of CFS theory, which can handle two different information features with the uncertainty. Distance is an important tool in the field of IVCFS theory. To enhance the applicability of IVCFS, this paper presents some new interval-valued complex fuzzy distances based on traditional Hamming and Euclidean distances of complex numbers. Furthermore, we elucidate the geometric properties of these distances. Finally, these distances are used to deal with decision-making problem in the IVCFS environment.

With the rapid development of remote sensing technology, change detection (CD) methods based on remote sensing images have been widely used in land resource planning, disaster monitoring, and urban expansion, among other fields. The purpose of CD is to accurately identify changes on the Earth’s surface. However, most CD methods focus on changes between the pixels of multitemporal remote sensing image pairs while ignoring the coupled relationships between them. This often leads to uncertainty about edge pixels with regard to changing objects and misclassification of small objects. To solve these problems, we propose a CD method for remote sensing images that uses a coupled dictionary and deep learning. The proposed method realizes the spatial-temporal modeling and correlation of multitemporal remote sensing images through a coupled dictionary learning module and ensures the transferability of reconstruction coefficients between multisource image blocks. In addition, we constructed a differential feature discriminant network to calculate the dissimilarity probability for the change area. A new loss function that considers true/false discrimination loss, classification loss, and cross-entropy loss is proposed. The most discriminating features can be extracted and used for CD. The performance of the proposed method was verified on two well-known CD datasets. Extensive experimental results show that the proposed method is superior to other methods in terms of precision, recall, F₁-score, , and .

Deep networks-based models have achieved excellent performances in various applications for extracting discriminative feature representations by convolutional neural networks (CNN) or recurrent neural networks (RNN). However, CNN or RNN may not work when handling data without temporal/spatial structures. Therefore, finding a new technique to extract features instead of CNN or RNN is a necessity. Gradient Boosted Decision Trees (GBDT) can select the features with the largest information gain when building trees. In this paper, we propose an architecture based on the ensemble of decision trees and neural network (NN) for multiple machine learning tasks, e.g., classification, regression, and ranking. It can be regarded as an extension of the widely used deep-networks-based model, in which we use GBDT instead of CNN or RNN. This architecture consists of two main parts: (1) the decision forest layers, which focus on learning features from the input data, (2) the fully connected layers, which focus on distilling knowledge from the decision forest layers. Powered by these two parts, the proposed model could handle data without temporal/spatial structures. This model can be efficiently trained by stochastic gradient descent via back-propagation. The empirical evaluation results of different machine learning tasks demonstrate the the effectiveness of the proposed method.

Sparse spectral unmixing assumes the constituent spectra (endmembers) can be selected from a given spectral library and seeks sparse combination coefficients (abundances) of endmembers to reconstruct the input hyperspectral image. The existing methods extensively exploit the prior information of abundances and design various regularizations on abundances. In this paper, taking advantage of the low-rank property of the reconstructed image, we propose a generic unmixing model by incorporating a low-rank regularization on the data reconstruction term to the traditional sparse unmixing models. The low-rank reconstruction regularization plays a role in attenuating noise and errors, therefore helps our models achieve better sparse recovery results while preserving details. We illustrate two models which combine the low-rank reconstruction term with sparse and joint sparse abundances regularizers, respectively. A series of simulation and real-world data are used to evaluate the performances of the proposed models, and their results are compared with that obtained by state-of-the-art algorithms. Both visual comparison and quantitative evaluation are presented to show the effectiveness of our methods.

Multimodal apparent personality traits analysis is a challenging issue due to the asynchrony among modalities. To address this issue, this paper proposes a Progressive Adaptive Crossmodal Reinforcement (PACMR) approach for multimodal apparent personality traits analysis. PACMR adopts a progressive reinforcement strategy to provide a multi-level information exchange among different modalities for crossmodal interactions, resulting in reinforcing the source and target modalities simultaneously. Specifically, PACMR introduces an Adaptive Modality Reinforcement Unit (AMRU) to adaptively adjust the weights of self-attention and crossmodal attention for capturing reliable contextual dependencies of multimodal sequence data. Experiment results on the public First Impressions dataset demonstrate the effectiveness of the proposed method.