MLS Communication Journal

<a href="/27153/1/fpls-16-1720471.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

CNNAttLSTM: an attention-enhanced CNN–LSTM architecture for high-precision jackfruit leaf disease classification

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.

Producción Científica

Gaurav Tuteja mail , Fuad Ali Mohammed Al-Yarimi mail , Amna Ikram mail , Rupesh Gupta mail , Ateeq Ur Rehman mail , Jeewan Singh mail , Irene Delgado Noya mail irene.delgado@uneatlantico.es, Luis Alonso Dzul López mail luis.dzul@uneatlantico.es,

Tuteja

<a href="/27156/1/s41598-025-29667-y.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Enhancing fault detection in new energy vehicles via novel ensemble approach

New energy vehicles (NEVs) has emerged as a sustainable alternative to conventional vehicles, however have unresolved reliability challenges due to their complex electronic systems and varying operating conditions. Faults in drivetrain and battery systems, occurring at rates up to 12% annually, present significant barriers to the widespread adoption of NEVs. This study proposes a robust fault detection framework that applies multiple machine learning and deep learning models to address these challenges. The research utilizes the benchmark NEV fault diagnosis dataset, which contains real-world sensor data from NEVs. The models tested include logistic regression, passive-aggressive classifier, ridge classifier, perceptron, gated recurrent unit (GRU), convolutional neural network, and artificial neural network. The proposed ensemble GRULogX model stands out among the implemented model, leveraging GRU with logistic regression and other key classifiers, and achieved 99% accuracy, demonstrating high precision and recall. Cross-validation and hyperparameter optimization were adopted to further ensure the model’s generalizability and reliability. This research enhances the fault detection capabilities of NEVs, thereby improving their reliability and supporting the wider adoption of clean energy transportation solutions.

Producción Científica

Iqra Akhtar mail , Mahnoor Nabeel mail , Umair Shahid mail , Kashif Munir mail , Ali Raza mail , Irene Delgado Noya mail irene.delgado@uneatlantico.es, Santos Gracia Villar mail santos.gracia@uneatlantico.es, Imran Ashraf mail ,

Akhtar

<a href="/17885/1/s41598-025-26052-7.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Dual-modality fusion for mango disease classification using dynamic attention based ensemble of leaf & fruit images

Mango is one of the most beloved fruits and plays an indispensable role in the agricultural economies of many tropical countries like Pakistan, India, and other Southeast Asian countries. Similar to other fruits, mango cultivation is also threatened by various diseases, including Anthracnose and Red Rust. Although farmers try to mitigate such situations on time, early and accurate detection of mango diseases remains challenging due to multiple factors, such as limited understanding of disease diversity, similarity in symptoms, and frequent misclassification. To avoid such instances, this study proposes a multimodal deep learning framework that leverages both leaf and fruit images to improve classification performance and generalization. Individual CNN-based pre-trained models, including ResNet-50, MobileNetV2, EfficientNet-B0, and ConvNeXt, were trained separately on curated datasets of mango leaf and fruit diseases. A novel Modality Attention Fusion (MAF) mechanism was introduced to dynamically weight and combine predictions from both modalities based on their discriminative strength, as some diseases are more prominent on leaves than on fruits, and vice versa. To address overfitting and improve generalization, a class-aware augmentation pipeline was integrated, which performs augmentation according to the specific characteristics of each class. The proposed attention-based fusion strategy significantly outperformed individual models and static fusion approaches, achieving a test accuracy of 99.08%, an F1 score of 99.03%, and a perfect ROC-AUC of 99.96% using EfficientNet-B0 as the base. To evaluate the model’s real-world applicability, an interactive web application was developed using the Django framework and evaluated through out-of-distribution (OOD) testing on diverse mango samples collected from public sources. These findings underline the importance of combining visual cues from multiple organs of plants and adapting model attention to contextual features for real-world agricultural diagnostics.

Producción Científica

Muhammad Mohsin mail , Muhammad Shadab Alam Hashmi mail , Irene Delgado Noya mail irene.delgado@uneatlantico.es, Helena Garay mail helena.garay@uneatlantico.es, Nagwan Abdel Samee mail , Imran Ashraf mail ,

Mohsin

<a class="ep_document_link" href="/17862/1/sensors-25-06419.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Edge-Based Autonomous Fire and Smoke Detection Using MobileNetV2

Forest fires pose significant threats to ecosystems, human life, and the global climate, necessitating rapid and reliable detection systems. Traditional fire detection approaches, including sensor networks, satellite monitoring, and centralized image analysis, often suffer from delayed response, high false positives, and limited deployment in remote areas. Recent deep learning-based methods offer high classification accuracy but are typically computationally intensive and unsuitable for low-power, real-time edge devices. This study presents an autonomous, edge-based forest fire and smoke detection system using a lightweight MobileNetV2 convolutional neural network. The model is trained on a balanced dataset of fire, smoke, and non-fire images and optimized for deployment on resource-constrained edge devices. The system performs near real-time inference, achieving a test accuracy of 97.98% with an average end-to-end prediction latency of 0.77 s per frame (approximately 1.3 FPS) on the Raspberry Pi 5 edge device. Predictions include the class label, confidence score, and timestamp, all generated locally without reliance on cloud connectivity, thereby enhancing security and robustness against potential cyber threats. Experimental results demonstrate that the proposed solution maintains high predictive performance comparable to state-of-the-art methods while providing efficient, offline operation suitable for real-world environmental monitoring and early wildfire mitigation. This approach enables cost-effective, scalable deployment in remote forest regions, combining accuracy, speed, and autonomous edge processing for timely fire and smoke detection.

Producción Científica

Dilshod Sharobiddinov mail , Hafeez Ur Rehman Siddiqui mail , Adil Ali Saleem mail , Gerardo Méndez Mezquita mail , Debora L. Ramírez-Vargas mail debora.ramirez@unini.edu.mx, Isabel de la Torre Díez mail ,

Sharobiddinov

<a class="ep_document_link" href="/17849/1/1-s2.0-S2590005625001043-main.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Ultra Wideband radar-based gait analysis for gender classification using artificial intelligence

Gender classification plays a vital role in various applications, particularly in security and healthcare. While several biometric methods such as facial recognition, voice analysis, activity monitoring, and gait recognition are commonly used, their accuracy and reliability often suffer due to challenges like body part occlusion, high computational costs, and recognition errors. This study investigates gender classification using gait data captured by Ultra-Wideband radar, offering a non-intrusive and occlusion-resilient alternative to traditional biometric methods. A dataset comprising 163 participants was collected, and the radar signals underwent preprocessing, including clutter suppression and peak detection, to isolate meaningful gait cycles. Spectral features extracted from these cycles were transformed using a novel integration of Feedforward Artificial Neural Networks and Random Forests , enhancing discriminative power. Among the models evaluated, the Random Forest classifier demonstrated superior performance, achieving 94.68% accuracy and a cross-validation score of 0.93. The study highlights the effectiveness of Ultra-wideband radar and the proposed transformation framework in advancing robust gender classification.

Producción Científica

Adil Ali Saleem mail , Hafeez Ur Rehman Siddiqui mail , Muhammad Amjad Raza mail , Sandra Dudley mail , Julio César Martínez Espinosa mail ulio.martinez@unini.edu.mx, Luis Alonso Dzul López mail luis.dzul@uneatlantico.es, Isabel de la Torre Díez mail ,

Saleem