Hyperspectral images are high-dimensional data that capture detailed spectral information across a wide range of wavelengths, enabling the precise identification and analysis of different materials or objects. However, the high dimensionality of the data also introduces information redundancy and increases the computational overhead, making it necessary to perform band selection to retain the most discriminative and informative bands for the target task. Traditional band selection methods, such as ranking-based, searching-based, and clustering-based approaches, often rely on handcrafted features and heuristic rules, which fail to fully exploit the latent information and complex spatial–spectral relationships in hyperspectral images. To address this issue, this paper proposes a two-stage unsupervised band selection method based on deep reinforcement learning. First, we performed noise estimation preprocessing to filter out bands with high noise levels to reduce the interference in the agent’s learning process. Then, the band selection problem was formulated as a Markov Decision Process (MDP), where the agent learned an optimal band selection strategy through interactions with the environment. In the design of the reward function, the Optimal Index Factor (OIF) was introduced as the evaluation metric to encourage the agent to select bands with high information content and low redundancy, and thereby improve the efficiency and quality of the selection process. Experimental results on three hyperspectral datasets demonstrated that the proposed method could effectively improve the performance of the hyperspectral image band selection.

Background/Aim: Hydrogen sulfide (H₂S) has been found to act as a physiological intercellular messenger to regulate cell survival. In this study, we evaluated whether H₂S could promote cell proliferation and melanin synthesis in human epidermal melanocytes (HEMs). Methods: Primary HEMs were cocultured with sodium hydrosulfide (NaHS, the most widely used H₂S donor) or endogenously overexpressed with cystathionine-γ-lyase (CSE) gene, which is the most predominant H₂S-producing enzyme. Then, cell viability, intracellular melanin content, tyrosinase (TYR) activity, and expression of microphthalmia-associated transcription factor (MITF), TYR, together with TYR-related protein 1 (TRP-1) in both transcript and protein levels, were detected. Results: We first confirmed that NaHS (10–100 μm) increased cell viability, intracellular melanin content, and TYR activity in a dose-dependent manner. Then, we found that endogenous H₂S production also promoted cell proliferation, intracellular melanin content, and TYR activity. In addition, we observed the mRNA and protein expression of MITF, TYR, and TRP-1 was significantly up-regulated after NaHS treatment and CSE gene transfection. Conclusions: This study demonstrates that H₂S promotes cell proliferation and melanin synthesis in HEMs, which indicates pharmacologic regulation of H₂S may be potential treatment for skin disorders caused by loss of melanocytes or dysfunction of melanogenesis.

Remote sensing image classification refers to the task that using algorithms to categorize satellite or aerial imagery into different land cover types. In the real world, long-tailed data distribution is commonly present in remote sensing image classification tasks, causing models to excessively favor sufficient head classes during training and degrading prediction accuracy for scarce tail classes. Although existing methods such as resampling and reweighting can alleviate the issue of data imbalance to a certain extent, they struggle to sufficiently enhance the diversity of tail class samples. In recent years, some works have begun to use diffusion models to generate diverse samples to balance the class distribution. However, these approaches often overlook the distribution inconsistency between generated and real images, which will hinder the improvement of model performance. To tackle these challenges, this article proposes a novel diffusion-noise-based augmentation (DONA) method with a two-stage training process. Before training, our specially designed conditional prompts are used together with the original training set to guide the diffusion model in image generation. Furthermore, we propose two strategies to effectively leverage the generated images, which are applied, respectively, at the end of the first training stage and during the second training stage. First, we design DiffCam-Mix to fuse the background of the generated data with the foreground of the original data, preserving the essential information of the original real images while incorporating the diversity of the generated ones. Second, we use cosine similarity to minimize the differences between the mixed data and their corresponding original data, further calibrating the distribution of different samples. Extensive experiments on three public datasets—SIRI-WHU-LT, PatternNet-LT, and RSI-CB256-LT—demonstrate the effectiveness of the proposed method.