Jackfruit, a vital agricultural crop in Bangladesh, is a key player in ensuring food security and sustaining rural communities’ livelihoods. The escalating challenges posed by plant diseases and the shortcomings of traditional manual disease detection methods underscore the pressing need for an automated, scalable solution. This study introduces JackVisualNet, a cutting-edge hybrid deep learning model tailored for automated detection and classification of jackfruit diseases. This innovative system, which integrates advanced technologies, including pre-trained deep learning architectures, hybrid model design, and intelligent classification algorithms, has the potential to significantly impact food security in Bangladesh. This study leverages a dataset of 2,195 high-resolution images collected from jackfruit fields in Barishal and Khulna, Bangladesh, encompassing diverse disease conditions. Data preprocessing included resizing images to standardized dimensions (224 × 224 × 3) and applying augmentation techniques to improve model robustness. JackVisualNet combines the strengths of VGG19 and DenseNet201, further refined through extensive hyperparameter tuning and a robust ablation study. This hybrid architecture optimally enhances feature extraction and classification, addressing variability in disease prediction. Benchmarking against ResNet50V2, DenseNet201, and VGG19 demonstrates that JackVisualNet achieves superior performance, with accuracies of 99.72%, 99.73%, and 99.72%, precision of 99.73%, 99.73%, and 99.73%, recall of 99.72%, 99.72%, and 99.72%, and an F1-score of 99.73%, 99.73%, and 99.73%, respectively. Beyond classification, the system incorporates predictive analytics for disease-spread trends and a decision-based algorithm that provides actionable insights for farmers. The results highlight JackVisualNet’s capability to revolutionize jackfruit disease management, offering an accessible, scalable, and reliable solution for sustainable agricultural practices. JackVisualNet’s reliability provides a secure and confident solution for farmers, empowering them with actionable insights and promoting efficient disease management, thereby contributing to the resilience of Bangladesh’s agricultural sector.

Lyme disease, caused by the Borrelia burgdorferi bacterium and transmitted through black-legged (deer) tick bites, is becoming increasingly prevalent globally. According to data from the Lyme Disease Association, the number of cases has surged by more than 357% over the past 15 years. According to the Infectious Disease Society of America, traditional diagnostic methods are often slow, potentially allowing bacterial proliferation and complicating early management. This study proposes a novel hybrid deep learning framework to classify Lyme disease rashes, addressing the global prevalence of the disease caused by the Borrelia burgdorferi bacterium, which is transmitted through black-legged (deer) tick bites. This study presents a novel hybrid deep learning framework for classifying Lyme disease rashes, utilizing pre-trained models (ResNet50 V2, VGG19, DenseNet201) for initial classification. By combining VGG19 and DenseNet201 architectures, we developed a hybrid model, SkinVisualNet, which achieved an impressive accuracy of 98.83%, precision of 98.45%, recall of 99.09%, and an F1 score of 98.76%. To ensure the robustness and generalizability of the model, 5-fold cross-validation (CV) was performed, generating an average validation accuracy between 98.20% and 98.92%. Incorporating image preprocessing techniques such as gamma correction, contrast stretching and data augmentation led to a 10–13% improvement in model accuracy, significantly enhancing its ability to generalize across various conditions and improving overall performance. To improve model interpretability, we applied Explainable AI methods like LIME, Grad-CAM, CAM++, Score CAM and Smooth Grad to visualize the rash image regions most influential in classification. These techniques enhance both diagnostic transparency and model reliability, helping clinicians better understand the diagnostic decisions. The proposed framework demonstrates a significant advancement in automated Lyme disease detection, providing a robust and explainable AI-based diagnostic tool that can aid clinicians in improving patient outcomes.