Non-invasive brain-computer interfaces (BCIs) have been widely used for neural decoding, linking neural signals to control devices. Hybrid BCI systems using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have received significant attention for overcoming the limitations of EEG- and fNIRS-standalone BCI systems. However, most hybrid EEG-fNIRS BCI studies have focused on late fusion because of discrepancies in their temporal resolutions and recording locations. Despite the enhanced performance of hybrid BCIs, late fusion methods have difficulty in extracting correlated features in both EEG and fNIRS signals. Therefore, in this study, we proposed a deep learning-based early fusion structure, which combines two signals before the fully-connected layer, called the fNIRS-guided attention network (FGANet). First, 1D EEG and fNIRS signals were converted into 3D EEG and fNIRS tensors to spatially align EEG and fNIRS signals at the same time point. The proposed fNIRS-guided attention layer extracted a joint representation of EEG and fNIRS tensors based on neurovascular coupling, in which the spatially important regions were identified from fNIRS signals, and detailed neural patterns were extracted from EEG signals. Finally, the final prediction was obtained by weighting the sum of the prediction scores of the EEG and fNIRS-guided attention features to alleviate performance degradation owing to delayed fNIRS response. In the experimental results, the FGANet significantly outperformed the EEG-standalone network. Furthermore, the FGANet has 4.0% and 2.7% higher accuracy than the state-of-the-art algorithms in mental arithmetic and motor imagery tasks, respectively.

Long-range ground targets are difficult to detect in a noisy cluttered environment using either synthetic aperture radar (SAR) images or infrared (IR) images. SAR-based detectors can provide a high detection rate with a high false alarm rate to background scatter noise. IR-based approaches can detect hot targets but are affected strongly by the weather conditions. This paper proposes a novel target detection method by decision-level SAR and IR fusion using an Adaboost-based machine learning scheme to achieve a high detection rate and low false alarm rate. The proposed method consists of individual detection, registration, and fusion architecture. This paper presents a single framework of a SAR and IR target detection method using modified Boolean map visual theory (modBMVT) and feature-selection based fusion. Previous methods applied different algorithms to detect SAR and IR targets because of the different physical image characteristics. One method that is optimized for IR target detection produces unsuccessful results in SAR target detection. This study examined the image characteristics and proposed a unified SAR and IR target detection method by inserting a median local average filter (MLAF, pre-filter) and an asymmetric morphological closing filter (AMCF, post-filter) into the BMVT. The original BMVT was optimized to detect small infrared targets. The proposed modBMVT can remove the thermal and scatter noise by the MLAF and detect extended targets by attaching the AMCF after the BMVT. Heterogeneous SAR and IR images were registered automatically using the proposed RANdom SAmple Region Consensus (RANSARC)-based homography optimization after a brute-force correspondence search using the detected target centers and regions. The final targets were detected by feature-selection based sensor fusion using Adaboost. The proposed method showed good SAR and IR target detection performance through feature selection-based decision fusion on a synthetic database generated by OKTAL-SE.

Nowadays, as noisy labels, also known as erroneous labels, are becoming increasingly ubiquitous in daily life, it is of great importance to be able to learn from them. This study efficiently uses semi-supervised learning to highlight a method utilizing all training data. The proposed algorithm comprises two stages: In the first stage, a small portion of training data regarded as clean samples is selected by the small-loss criteria with a proposed rejection ratio in a mini-batch manner. The proposed rejection ratio is determined by the number of classes regardless of the noise ratio. In the second stage, semi-supervised learning is used to update the parameters of the network with selected clean samples (labeled data) and the remaining noisy samples (unlabeled data) using Renyi entropy regularization for low-density separation among classes. The proposed algorithm is believed to have the capability to train deep neural network robustly to noisy labels, although noise ratio is unknown. Experimental results considering the MNIST and CIFAR-10 datasets confirm that the proposed algorithm achieves the best accuracy among sample-selection methods.

This paper presents a novel double weight-based synthetic aperture radar (SAR) and infrared (IR) sensor fusion method (DW-SIF) for automatic ground target recognition (ATR). IR-based ATR can provide accurate recognition because of its high image resolution but it is affected by the weather conditions. On the other hand, SAR-based ATR shows a low recognition rate due to the noisy low resolution but can provide consistent performance regardless of the weather conditions. The fusion of an active sensor (SAR) and a passive sensor (IR) can lead to upgraded performance. This paper proposes a doubly weighted neural network fusion scheme at the decision level. The first weight ( $\alpha$ ) can measure the offline sensor confidence per target category based on the classification rate for an evaluation set. The second weight ( $\beta$ ) can measure the online sensor reliability based on the score distribution for a test target image. The LeNet architecture-based deep convolution network (14 layers) is used as an individual classifier. Doubly weighted sensor scores are fused by two types of fusion schemes, such as the sum-based linear fusion scheme ( $\alpha \beta$ -sum) and neural network-based nonlinear fusion scheme ( $\alpha \beta$ -NN). The experimental results confirmed the proposed linear fusion method ( $\alpha \beta$ -sum) to have the best performance among the linear fusion schemes available (SAR-CNN, IR-CNN, $\alpha$ -sum, $\beta$ -sum, $\alpha \beta$ -sum, and Bayesian fusion). In addition, the proposed nonlinear fusion method ( $\alpha \beta$ -NN) showed superior target recognition performance to linear fusion on the OKTAL-SE-based synthetic database.