Too many input features in applications may lead to over-fitting and reduce the performance of the learning algorithm. Moreover, in most cases, each feature containing different information content has different effects on the prediction target. Therefore, a feature selection method for calculating the importance of each feature, called WKNNGAFS, is proposed in this paper. In this method, the genetic algorithm (GA) is adopted to search the optimal weight vector, the value of the ith component of which corresponds to the contribution degree of the ith feature to the classification from a global perspective. Besides, weighted K-nearest neighbors algorithm (WKNN), which takes both the different contributions of nearest neighbors and the different classification ability of each feature into account, is used to determine the target label. To evaluate the effectiveness of the proposed method, nine existing feature selection methods are compared with it on 13 real datasets, including 6 high dimensional microarray datasets. Experimental results demonstrate the method is more effective and can improve classification performance.

In recent years, the analysis of macro- and micro-expression has drawn the attention of researchers. These expressions provide visual cues to an individual’s emotions, which can be used in a broad range of potential applications such as lie detection and policing. In this paper, we address the challenge of spotting facial macro- and micro-expression from videos and present compelling results by using a deep learning approach to analyze the optical flow features. Unlike other deep learning approaches that are mainly based on Convolutional Neural Networks (CNNs), we propose a Transformer-based deep learning approach that predicts a score indicating the probability of a frame being within an expression interval. In contrast to other Transformer-based models that achieve high performance by being pre-trained on large datasets, our deep learning model, called SL-Swin, which incorporates Shifted Patch Tokenization and Locality Self-Attention into the backbone Swin Transformer network, effectively spots macro- and micro-expressions by being trained from scratch on small-size expression datasets. Our evaluation outcomes surpass the MEGC 2022 spotting baseline result, obtaining an overall F1-score of 0.1366. Additionally, our approach performs well on the MEGC 2021 spotting task, with an overall F1-score of 0.1824 and 0.1357 on the CAS(ME)${}^2$ and SAMM Long Videos, respectively. The code is publicly available on GitHub.

Crack detection is an important task in bridge health monitoring, and related detection methods have gradually shifted from traditional manual methods to intelligent approaches with convolutional neural networks (CNNs) in recent years. Due to the opaque process of training and operating CNNs, if the learned features for identifying cracks in the network are not evaluated, it may lead to safety risks. In this study, to evaluate the recognition basis of different crack detection networks; several crack detection CNNs are trained using the same training conditions. Afterwards, several crack images are used to construct a dataset, which are used to interpret and analyze the trained networks and obtain the learned features for identifying cracks. Additionally, a crack identification performance criterion based on interpretability analysis is proposed. Finally, a training framework is introduced based on the issues reflected in the interpretability analysis.

Sleep disorder is a serious public health problem. Unobtrusive home sleep quality monitoring system can better open the way of sleep disorder‐related diseases screening and health monitoring. In this work, a sleep stage classification algorithm based on multiscale residual convolutional neural network (MRCNN) was proposed to detect the characteristics of electroencephalogram (EEG) signals detected by wearable systems and classify sleep stages. EEG signals were analyzed in each epoch of every 30 seconds, and then 5‐class sleep stage classification, wake (W), rapid eye movement sleep (REM), and nonrapid eye movement sleep (NREM) including N1, N2, and N3 stages was outputted. Good results (accuracy rate of 92.06% and 91.13%, Cohen’s kappa of 0.7360 and 0.7001) were achieved with 5‐fold cross‐validation and independent subject cross‐validation, respectively, which performed on European Data Format (EDF) dataset containing 197 whole‐night polysomnographic sleep recordings. Compared with several representative deep learning methods, this method can easily obtain sleep stage information from single‐channel EEG signals without specialized feature extraction, which is closer to clinical application. Experiments based on CinC2018 dataset also proved that the method has a good performance on large dataset and can provide support for sleep disorder‐related diseases screening and health surveillance based on automatic sleep staging.