With the goal of automatic sea ice mapping during the summer sea ice melt cycle, this study involved designing a fully automatic sea ice segmentation method based on a deep learning semantic segmentation network applicable to summer SAR images, which achieved high accuracy and the fully automatic extraction of sea ice segmentation during the summer ice melt cycle by optimizing the process, improving the pixel-level semantic segmentation network, and introducing high-resolution sea ice concentration features. Firstly, a convolution-based, high-resolution sea ice concentration calculation method is proposed and was applied to the deep learning task. Secondly, the proposed DF-UHRNet network was improved upon by designing high- and low-level fusion modules, introducing an attention mechanism, and reducing the number of convolution layers and other operations, and it can effectively fuse high- and low-scale semantic features and global contextual information based on reducing the overall number of network parameters, enabling it to achieve pixel-level classification. The results show that this method meets the needs associated with the automatic mapping and high-precision classification of thin ice, one-year ice, open water, and multi-year ice and effectively reduces the model size.

Introduction: The automatic and precise classification of epilepsy types using electroencephalogram (EEG) data promises significant advancements in diagnosing patients with epilepsy. However, the intricate interplay among multiple electrode signals in EEG data poses challenges. Recently, Graph Convolutional Neural Networks (GCN) have shown strength in analyzing EEG data due to their capability to describe complex relationships among different EEG regions. Nevertheless, several challenges remain: (1) GCN typically rely on predefined or prior graph topologies, which may not accurately reflect the complex correlations between brain regions. (2) GCN struggle to capture the long-temporal dependencies inherent in EEG signals, limiting their ability to effectively extract temporal features.Methods: To address these challenges, we propose an innovative epileptic seizure classification model based on an Iterative Gated Graph Convolutional Network (IGGCN). For the epileptic seizure classification task, the original EEG graph structure is iteratively optimized using a multi-head attention mechanism during training, rather than relying on a static, predefined prior graph. We introduce Gated Graph Neural Networks (GGNN) to enhance the model's capacity to capture long-term dependencies in EEG series between brain regions. Additionally, Focal Loss is employed to alleviate the imbalance caused by the scarcity of epileptic EEG data.Results: Our model was evaluated on the Temple University Hospital EEG Seizure Corpus (TUSZ) for classifying four types of epileptic seizures. The results are outstanding, achieving an average F1 score of 91.5% and an average Recall of 91.8%, showing a substantial improvement over current state-of-the-art models.Discussion: Ablation experiments verified the efficacy of iterative graph optimization and gated graph convolution. The optimized graph structure significantly differs from the predefined EEG topology. Gated graph convolutions demonstrate superior performance in capturing the long-term dependencies in EEG series. Additionally, Focal Loss outperforms other commonly used loss functions in the TUSZ classification task.

The table recognition model rows and columns aggregated network (RCANet) uses a semantic segmentation approach to recognize table structure, and achieves better performance in table row and column segmentation. However, this model uses ResNet18 as the backbone network, and the model has 11.35 million parameters and a volume of 45.5 M, which is inconvenient to deploy to lightweight servers or mobile terminals. Therefore, from the perspective of model compression, this paper proposes the lightweight rows and columns attention aggregated network (LRCAANet), which uses the lightweight network ShuffleNetv2 to replace the original RCANet backbone network ResNet18 to simplify the model size. Considering that the lightweight network reduces the number of feature channels, it has a certain impact on the performance of the model. In order to strengthen the learning between feature channels, the rows attention aggregated (RAA) module and the columns attention aggregated (CAA) module are proposed. The RAA module and the CAA module add the squeeze and excitation (SE) module to the original row and column aggregated modules, respectively. Adding the SE module means the model can learn the correlation between channels and improve the prediction effect of the lightweight model. The experimental results show that our method greatly reduces the model parameters and model volume while ensuring low-performance loss. In the end, the average F1 score of our model is only 1.77% lower than the original model, the parameters are only 0.17 million, and the volume is only 0.8 M. Compared with the original model, the parameter amount and volume are reduced by more than 95%.

The study of separating the vocal from the accompaniment in single-channel music is foundational and critical in the field of music information retrieval (MIR). Mainstream music-separation methods are usually based on the frequency-domain characteristics of music signals, and the phase information of the music is lost during time–frequency decomposition. In recent years, deep learning models based on speech time-domain signals, such as Conv-TasNet, have shown great potential. However, for the vocal and accompaniment separation problem, there is no suitable time-domain music-separation model. Since the vocal and the accompaniment in music have a higher synergy and similarity than the voices of two speakers in speech, separating the vocal and accompaniment using a speech-separation model is not ideal. Based on this, we propose VAT-SNet; this optimizes the network structure of Conv-TasNet, which sets sample-level convolution in the encoder and decoder to preserve deep acoustic features, and takes vocal embedding and accompaniment embedding generated by the auxiliary network as references to improve the purity of the separation of the vocal and accompaniment. The results from public music datasets show that the quality of the vocal and accompaniment separated by VAT-SNet is improved in GSNR, GSIR, and GSAR compared with Conv-TasNet and mainstream separation methods, such as U-Net, SH-4stack, etc.

Objective: Epileptic seizure classification using EEG signals remains a significant challenge due to complex spatial-temporal dependencies, limited labeled data, and severe class imbalance. Methods: We propose a self-supervised learning framework, ASGPF (Adaptive Spatio-Graph Pretraining Framework), for EEG-based seizure classification. At its core is a novel Spatio-Graph Learning Cell (SGLC), which integrates a Graph Learning module to dynamically construct EEG topology, a Gated Graph Neural Network to extract spatial features across EEG channels, and a Gated Recurrent Unit to capture long-term temporal dependencies. ASGPF uses self-supervised sequence-to-sequence pretraining on unlabeled EEG to learn robust representations, enabling accurate seizure classification with a lightweight model that consists of the pretrained encoder and a simple prediction layer. Results: Extensive experiments on the TUSZ dataset demonstrate that our method significantly outperforms current state-of-the-art approaches, achieving weighted F1-scores of 83.8% for four-class and 73.5% for eight-class seizure classification tasks, respectively. Notably, with only 25% of labeled data, the proposed model achieves comparable performance to the best baseline trained on 75% of data, validating the effectiveness of ASGPF under data scarcity and class imbalance. Conclusion: ASGPF effectively learns discriminative EEG representations through adaptive spatial-temporal modeling and self-supervised pretraining, enabling accurate seizure classification with minimal labeled data. Significance: This work introduces a data-efficient EEG analysis framework for seizure classification, enabling accurate prediction with minimal labeled data and showing strong potential for clinical application in resource- and label-constrained environments.

Remote sensing image color correction faces challenges due to diverse acquisition conditions and sensor variations. Existing methods often require one-to-one training and large amounts of domain-specific annotated data, limiting scalability and generalization. To tackle these issues, we propose PCED-Match, a novel color layer decomposition and alignment framework. It decomposes RGB images into homogeneous color layers and performs layer-wise color style alignment under physical constraints. Trained once on a general RGB dataset, PCED-Match generalizes well to diverse remote sensing imagery without domain-specific retraining or large-scale annotations. Extensive experiments on the WHU Building and Inria Aerial Image Labeling datasets demonstrate the effectiveness of our method. Integrated into mainstream segmentation models (U-Net++, DeepLabv3, SegFormer), PCED-Match consistently outperforms existing approaches in mIoU, F1-score and Pixel Accuracy, achieving superior color consistency and semantic preservation. Our method source code and related data collection of links available on https://github.com/freesui1984/PCED-Match