Early and accurate detection of plant diseases is essential for ensuring food security and maintaining sustainable agricultural productivity. However, most deep learning models for plant disease classification rely heavily on large-scale annotated datasets, which are expensive, labor-intensive, and often impractical to obtain in real-world farming environments. To address this limitation, we propose a unified self-supervised learning (SSL) framework that leverages unlabeled plant imagery to learn meaningful and transferable visual representations. Our method integrates three complementary objectives—Bootstrap Your Own Latent (BYOL), Masked Image Modeling (MIM), and contrastive learning—within a ResNet101 backbone, optimized through a hybrid loss function that captures global alignment, local structure, and instance-level distinction. GPU-based data augmentations are used to introduce stochasticity and enhance generalization during pretraining. Experimental results on the challenging PlantDoc dataset demonstrate that our model achieves an accuracy of 77.82%, with macro-averaged precision, recall, and F1-score of 80.00%, 78.24%, and 77.48%, respectively—on par with or exceeding most state-of-the-art supervised and self-supervised approaches. Furthermore, when fine-tuned on the PlantVillage dataset, the pretrained model attains 99.85% accuracy, highlighting its strong cross-domain generalization and practical transferability. These findings underscore the potential of self-supervised learning as a scalable, annotation-efficient, and robust solution for plant disease detection in real-world agricultural settings, especially where labeled data is scarce or unavailable.

Gait analysis is a critical tool for diagnosing and assessing the severity of Parkinson’s disease (PD). This study introduces a novel parallel hybrid architecture combining Conv1D, Efficient Transformers, and Bidirectional GRU layers to analyze gait data for both PD detection and severity staging. Conv1D layers extract local spatial features, Efficient Transformers capture contextual dependencies, and Bidirectional GRUs model temporal patterns in VGRF signals. Designed to balance computational efficiency and scalability, the model demonstrates state-of-the-art performance, achieving 95.7% accuracy in PD detection and 87.3% accuracy in severity staging on the PhysioNet gait dataset. Additionally, the architecture is highly versatile, offering potential for application in other 1D signal analysis tasks.