Recently, emotional electroencephalography (EEG) has been of great importance in brain–computer interfaces, and it is more urgent to realize automatic emotion recognition. The EEG signal has the disadvantages of being non-smooth, non-linear, stochastic, and susceptible to background noise. Additionally, EEG signal processing network models have the disadvantages of a large number of parameters and long training time. To address the above issues, a novel model is presented in this paper. Initially, a deep sparse autoencoder network (DSAE) was used to remove redundant information from the EEG signal and reconstruct its underlying features. Further, combining a convolutional neural network (CNN) with long short-term memory (LSTM) can extract relevant features from task-related features, mine the correlation between the 32 channels of the EEG signal, and integrate contextual information from these frames. The proposed DSAE + CNN + LSTM (DCRNN) model was experimented with on the public dataset DEAP. The classification accuracies of valence and arousal reached 76.70% and 81.43%, respectively. Meanwhile, we conducted experiments with other comparative methods to further demonstrate the effectiveness of the DCRNN method.

Detecting ship targets in remote sensing images within complex scenarios faces numerous challenges. The limited feature information of small-scale targets and their random orientation angles often result in missed and false detections. To address these issues, this paper proposes a Multi-Scale Rotated Detection Network (MSRO-Net) for detecting rotated ship targets in remote sensing images. The network adopts a CNN-Transformer hybrid architecture for collaborative feature extraction and integrates our proposed Coordinate-Aware Pyramid Feature Aggregation module (CAPP). This backbone network retains the capability of local feature extraction while also connecting global context and capturing long-range dependencies. The model can gather information from any position in the sequence, extract contextual information of targets at different scales, and enhance global feature representation. Additionally, this paper proposes an Upsampling Feature Reconstruction Pyramid (ARFPN-C), based on Adaptive Rotated Convolution (ARC). This network combines ARC adaptive rotating convolution with a multi-scale feature fusion mechanism to enhance the model’s perceptual capability, addressing the issues of limited target feature information and random orientation angles. The proposed algorithm is validated on two public remote sensing image datasets, HRSC2016 and DOTA. The mAP07, mAP12 on the HRSC2016 dataset, as well as the mAP in the ship category of the DOTA dataset, show a significant advantage over other commonly used object detection algorithms, with accuracies of 90.70%, 98.98%, and 89.46%, respectively. These results further validate the accuracy and effectiveness of the proposed MSRO-Net in object detection.

In recent years, facial expression recognition has played an important role in the field of human-computer interaction, and the application of deep learning technology has enabled it to develop more rapidly. In this paper, we create a lightweight network model for real-time emotion classification to recognize student facial expressions. The system includes: using Haar cascade for face detection, combined with the idea of Xception to propose a lightweight CNN network model, using pre-activation in the residual block to optimize the model and reduce the impact of overfitting. The experimental results on the FER2013 database show that our model has a better expression classification effect than other state-of-the-art methods. Besides, our model uses fewer parameters, which reduces the complexity of network training. When real-time emotional recognition of students, the system can help teachers adjust their teaching methods according to the emotional state of students.

Facial emotions are the most intuitive way to react to changes in inner emotions. We propose a facial emotion recognition method that combines auxiliary classifiers (Acs) and multi-scale CBAM (MCBAM) by improving the Xception network model. And we design a lightweight network model AMDCNN. We introduce Acs in the middle layers of the model. The features extracted from the middle layer portion of the model are utilized to aid in emotion recognition. Finally, the recognition results of the Acs and the main classifier are adaptively weighted and fused to obtain better emotion recognition results. This enables better utilization of the feature information extracted from the intermediate layers and further reduces the feature loss caused by the downsampling process of the convolutional layer. The CBAM does not increase the number of parameters and computation too much, and it enables the model to better focus on the important areas of the face. We apply it to the proposed lightweight model and improve it further. The width is increased by introducing a multi-branch convolutional structure and utilizing convolutional layers with different kernel sizes. This allows for more adequate spatial and channel features during feature extraction, allowing the model to more accurately focus on important facial regions. Our proposed model was experimentally validated on datasets of FER2013, FERPlus, RAF-DB and CK+, with accuracies of 69.82%, 85.40%, 86.77% and 99.49%, respectively. The number of parameters of the proposed model is only 1.6M. Our model is a good competitive advantage compared with other lightweight models.

Satellite sensors often capture remote sensing images that contain various types of stripe noise. The presence of these stripes significantly reduces the quality of the remote images and severely affects their subsequent applications in other fields. Despite the existence of many stripe noise removal methods in the research, they often result in the loss of fine details during the destriping process, and some methods even generate artifacts. In this paper, we proposed a new unidirectional variational model to remove horizontal stripe noise. The proposed model fully considered the directional characteristics and structural sparsity of the stripe noise, as well as the prior features of the underlying image, to design different sparse constraints, and the ${\mathsf{\ell }}_p$ quasinorm was introduced in these constraints to better describe these sparse characteristics, thus achieving a more excellent destriping effect. Moreover, we employed the fast alternating direction method of multipliers (ADMM) to solve the proposed non-convex model. This significantly improved the efficiency and robustness of the proposed method. The qualitative and quantitative results from simulated and real data experiments confirm that our method outperforms existing destriping approaches in terms of stripe noise removal and preservation of image details.