TY  - JOUR
SN  - 1664-462X
KW  - Introduction: Jackfruit cultivation is highly affected by leaf diseases that reduce yield
KW  -  fruit quality
KW  -  and farmer income. Early diagnosis remains challenging due to the limitations of manual inspection and the lack of automated and scalable disease detection systems. Existing deep-learning approaches often suffer from limited generalization and high computational cost
KW  -  restricting real-time field deployment.

Methods: This study proposes CNNAttLSTM
KW  -  a hybrid deep-learning architecture integrating Convolutional Neural Networks (CNN)
KW  -  Long Short-Term Memory (LSTM) units
KW  -  and an attention mechanism for multi-class classification of algal leaf spot
KW  -  black spot
KW  -  and healthy jackfruit leaves. Each image is divided into ordered 56×56 spatial patches
KW  -  treated as pseudo-temporal sequences to enable the LSTM to capture contextual dependencies across different leaf regions. Spatial features are extracted via Conv2D
KW  -  MaxPooling
KW  -  and GlobalAveragePooling layers; temporal modeling is performed by LSTM units; and an attention mechanism assigns adaptive weights to emphasize disease-relevant regions. Experiments were conducted on a publicly available Kaggle dataset comprising 38
KW  - 019 images
KW  -  using predefined training
KW  -  validation
KW  -  and testing splits.

Results: The proposed CNNAttLSTM model achieved 99% classification accuracy
KW  -  outperforming the baseline CNN (86%) and CNN?LSTM (98%) models. It required only 3.7 million parameters
KW  -  trained in 45 minutes on an NVIDIA Tesla T4 GPU
KW  -  and achieved an inference time of 22 milliseconds per image
KW  -  demonstrating high computational efficiency. The patch-based pseudo-temporal approach improved spatial?temporal feature representation
KW  -  enabling the model to distinguish subtle differences between visually similar disease classes.

Discussion: Results show that combining spatial feature extraction with temporal modeling and attention significantly enhances robustness and classification performance in plant disease detection. The lightweight design enables real-time and edge-device deployment
KW  -  addressing a major limitation of existing deep-learning techniques. The findings highlight the potential of CNNAttLSTM for scalable
KW  -  efficient
KW  -  and accurate agricultural disease monitoring and broader precision agriculture applications
ID  - uninimx27153
TI  - CNNAttLSTM: an attention-enhanced CNN?LSTM architecture for high-precision jackfruit leaf disease classification
N2  - Introduction: Jackfruit cultivation is highly affected by leaf diseases that reduce yield, fruit quality, and farmer income. Early diagnosis remains challenging due to the limitations of manual inspection and the lack of automated and scalable disease detection systems. Existing deep-learning approaches often suffer from limited generalization and high computational cost, restricting real-time field deployment.

Methods: This study proposes CNNAttLSTM, a hybrid deep-learning architecture integrating Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) units, and an attention mechanism for multi-class classification of algal leaf spot, black spot, and healthy jackfruit leaves. Each image is divided into ordered 56×56 spatial patches, treated as pseudo-temporal sequences to enable the LSTM to capture contextual dependencies across different leaf regions. Spatial features are extracted via Conv2D, MaxPooling, and GlobalAveragePooling layers; temporal modeling is performed by LSTM units; and an attention mechanism assigns adaptive weights to emphasize disease-relevant regions. Experiments were conducted on a publicly available Kaggle dataset comprising 38,019 images, using predefined training, validation, and testing splits.

Results: The proposed CNNAttLSTM model achieved 99% classification accuracy, outperforming the baseline CNN (86%) and CNN?LSTM (98%) models. It required only 3.7 million parameters, trained in 45 minutes on an NVIDIA Tesla T4 GPU, and achieved an inference time of 22 milliseconds per image, demonstrating high computational efficiency. The patch-based pseudo-temporal approach improved spatial?temporal feature representation, enabling the model to distinguish subtle differences between visually similar disease classes.

Discussion: Results show that combining spatial feature extraction with temporal modeling and attention significantly enhances robustness and classification performance in plant disease detection. The lightweight design enables real-time and edge-device deployment, addressing a major limitation of existing deep-learning techniques. The findings highlight the potential of CNNAttLSTM for scalable, efficient, and accurate agricultural disease monitoring and broader precision agriculture applications.
Y1  - 2026/01//
A1  - Tuteja, Gaurav
A1  - Al-Yarimi, Fuad Ali Mohammed
A1  - Ikram, Amna
A1  - Gupta, Rupesh
A1  - Rehman, Ateeq Ur
A1  - Singh, Jeewan
A1  - Delgado Noya, Irene
A1  - Dzul López, Luis Alonso
VL  - 16
UR  - http://doi.org/10.3389/fpls.2025.1720471
JF  - Frontiers in Plant Science
AV  - public
ER  -