This paper proposes Feature fusion and Dilated causal convolution model for Bearing Remaining useful life Prediction (FDBRP), an integrated framework for accurate Remaining Useful Life (RUL) prediction of rolling bearings that combines three key innovations: (1) a data augmentation module employing sliding-window processing and two-dimensional feature concatenation with label normalization to enhance signal representation and improve model generalizability, (2) a feature fusion module incorporating an enhanced graph convolutional network for spatial modeling, an improved multi-scale temporal convolution for dynamic pattern extraction, and an efficient multi-scale attention mechanism to optimize spatiotemporal feature consistency, and (3) an optimized dilated convolution module utilizing interval sampling to expand the receptive field, and combines the residual connection structure to realize the regularization of the neural network and enhance the ability of the model to capture long-range dependencies. Experimental validation showcases the effectiveness of proposed approach, achieving a high average score of 0.756564 and demonstrating a lower average error of 10.903656 in RUL prediction for test bearings compared to state-of-the-art benchmarks. This highlights the superior RUL prediction capability of the proposed methodology.

As a globally important agricultural commodity, the quality of tea is closely linked to its economic and cultural value. Recent advances in artificial intelligence and sensing technologies have facilitated the development of automated tea harvesting systems. Among the various factors affecting tea quality and flavor, leaf age serves as an important indicator of plant health and growth status. Accurate classification of tea leaf age is therefore essential for improving product consistency and optimizing harvest timing. However, existing automated approaches have primarily focused on bud detection or disease diagnosis, while the classification of tea leaf age has received comparatively less attention. To address this gap, a novel framework named SwinT-PGK is proposed, which integrates a Swin Transformer for feature extraction with a hybrid Principal Component Analysis–Genetic Algorithm (PCA–GA) for feature optimization, followed by a k-Nearest Neighbors (KNN) classifier. Under real-world plantation conditions, the method achieves a tea leaf age classification accuracy of 97.52%, using only a 26-dimensional feature vector. This represents a 2.71% improvement over the baseline Swin Transformer model, which relies on a 768-dimensional feature space. These results suggest that SwinT-PGK can effectively reduce feature dimensionality while maintaining high classification performance, offering a practical tool to support informed decision-making in tea cultivation and improve the overall consistency and quality of tea production.

In modern manufacturing, cameras are widely used to record the full workflow of assembly line workers, enabling video-based operational analysis and management. However, these recordings are often excessively long, leading to high storage demands and inefficient processing. Existing keyframe extraction methods typically apply uniform strategies across all frames, which are ineffective in detecting subtle movements. To address this, we propose a keyframe extraction method tailored for assembly line videos, combining optical flow estimation with ORB-based visual features. Our approach adapts extraction strategies to actions with different motion amplitudes. Each video frame is first encoded into a feature vector using the ORB algorithm and a bag-of-visual-words model. Optical flow is then calculated using the DIS algorithm, allowing frames to be categorized by motion intensity. Adjacent frames within the same category are grouped, and the appropriate number of clusters, k, is determined based on the group’s characteristics. Keyframes are finally selected via k-means++ clustering within each group. The experimental results show that our method achieves a recall rate of 85.2%, with over 90% recall for actions involving minimal movement. Moreover, the method processes an average of 274 frames per second. These results highlight the method’s effectiveness in identifying subtle actions, reducing redundant content, and delivering high accuracy with efficient performance.