Journal of Advanced Research in Modeling and Simulation

Deep Learning-Based Plant Disease Detection Using a Cascaded ResNet50–EfficientNetB0 Architecture

Yogita V Badgujar — 2026-09-29

More than 70% of the people depends on the agriculture in India.Because of large area it is difficult for farmers to maintain crop regularly and decreases income due to plant disease.Plant disease detection is difficult in agriculture area.It affects on crop quality and quantity.Human can’t detect disease on infected leaf with naked eye.Disease detection is important to provide solution to prevent this disease.THe deep-learning method using Convolutional Neural Networks (CNNs),which has shown better results.By pipelining ResNet50 and EfficientNetB0,the system achieves more confidence and accuracy than traditional machine learning models.In Traditional methods visual inspection depends on human expert which requires more time and can be inaccurate.Best result can be achieved by using two models that is ResNet50 and EfficientNetB0 gives more confidence and accuracy than traditional machine learning.No human intervention required.Plant disease detection using Convolutional Neural Network (CNN’s) gives better result.This technique classify plant species and dignose disease from leaf image and helps to protect crops and gives high output quality.

SleepSpectralAE: Time-Frequency Autoencoder for Automated Sleep Disorder Screening

Swati Patil — 2026-09-29

An AutoEncoder for Time-Frequency Analysis of EEG Data to Help Automate the Screening Process for Sleep Disorders. SleepSpectralAE, a lightweight autoencoder based on the time-frequency domain of EEG was developed for the purpose of automating sleep disorder screening. The autoencoder creates an encoding of multichannel spectrograms into a low dimension, or latent space, that captures noise as well as subtle differences in the EEG signal related to Sleep Physiology abnormal phenomenon. The AutoEncoder was trained and evaluated using records of overnight polysomnography consisting of different types of sleep pathology including obstructive sleep apnea and periodic limb movement disorder. Results of the numerical experiments demonstrate that the reconstruction errors in the latent space of SleepSpectralAE provide a means of differentiating normal sleep segments from those associated with Sleep Pathology. The AUC for event detection of apnea events was 0.91 and a decrease in the false positive rate of 27% was observed compared to the baseline convolutional AE. These findings suggest that time-frequency autoencoding is a unique way to initially screen for Sleep Disorders in either a clinical or home-monitoring environment.

Plant Disease Detection and Classification Using Deep Learning: A Review

Om B Mandaliya — 2026-09-29

Plant diseases are one of the major challenges in modern agriculture because they can significantly reduce crop yield, quality, and economic value. Early and accurate identification of plant diseases is therefore essential for taking timely preventive and corrective measures. Traditional disease identification methods mainly depend on visual inspection and expert knowledge, which can be time-consuming, costly, and difficult to apply over large agricultural areas. With the development of artificial intelligence, deep learning has become a promising approach for automatic plant disease recognition. Unlike traditional image-processing techniques, deep learning models can automatically learn important features such as color changes, spots, patterns, and texture variations directly from plant images.

This review presents the major developments in deep-learning-based plant disease detection and classification. It covers convolutional neural networks (CNNs), advanced CNN architectures, transfer learning, disease detection and localization, mobile-based disease recognition systems, data augmentation techniques, learning from limited datasets, and hyperspectral imaging for detecting diseases at an early stage. The review also examines the role of visualization and interpretability techniques, including heat maps and saliency maps, which help researchers and users understand the regions of a leaf that influence a model's prediction. These techniques can improve confidence in automated disease diagnosis and support the practical use of deep learning in agriculture.

The reviewed studies show that deep learning models can achieve high classification accuracy, particularly when trained and tested using large, well-prepared datasets collected under controlled conditions. However, a significant reduction in performance may occur when models are applied to images captured in natural agricultural environments, where variations in lighting, background, leaf orientation, plant variety, disease

severity, and image quality are common. Limited availability of accurately labeled images, especially for early-stage diseases, is another important challenge. In addition, highly accurate models may require considerable computational resources, which can make deployment on mobile and low-cost agricultural devices difficult. Therefore, future research should focus on developing lightweight and efficient models, collecting larger and more diverse real-world datasets, improving early disease detection, and using explainable artificial intelligence techniques. Overall, deep learning has strong potential to support farmers and agricultural experts by providing faster, more accessible, and reliable plant disease detection systems, but further validation in real-world conditions is necessary before widespread practical adoption

AI-Driven Banana Leaf Disease Detection Using Deep Learning Models

Ashish K. Patil — 2026-09-29

The stability of the global food supply and agricultural economies is critically dependent on crop health, which is persistently threatened by a variety of plant diseases. To safeguard yields, minimize excessive pesticide use, and promote sustainable cultivation, the implementation of rapid and precise disease identification systems is paramount. Conventional techniques that depend on visual inspection by agronomists are not only slow and subjective but also unfeasible for widespread monitoring. The rise of sophisticated artificial intelligence (AI) and deep learning has now enabled the development of automated, non-destructive diagnostic tools using computer vision. This study conducts a detailed comparative assessment of several deep learning models tailored to detect specific, high-impact diseases in banan plants namely Black Sigatoka, Yellow Sigatoka, Panama Disease, and Potassium Deficiency while also categorizing healthy leaves. We trained and evaluated a suite of architectures, including a custom Convolutional Neural Network (CNN), MobileNetV2, EfficientNet, and DenseNet, on a meticulously prepared dataset of leaf imagery. Our findings indicate that MobileNetV2 outperformed other models, attaining superior classification accuracy and a consistent balance between precision and recall across all disease categories. This highlights its suitability as an efficient and dependable framework for automated plant disease diagnosis. The research confirms that AI-powered systems can offer farmers a practical, real-time solution for crop health monitoring, facilitating informed agricultural management and reinforcing the principles of precision agriculture

Student Performance Prediction Using Machine Learning

Ojas Sunil Patil — 2026-09-29

Student academic performance is an important indicator of learning progress and can be influenced by several factors, including attendance, internal marks, previous academic performance, assignments and study habits. Traditional evaluation generally depends on manual analysis of student records, which can become time-consuming when the number of students increases. This paper proposes a Student Performance Prediction System using Machine Learning to analyse relevant academic data and provide an estimated prediction of a student's expected performance. The proposed approach includes data collection, preprocessing, model training, testing and evaluation, selection of a suitable machine learning model, and prediction for new student records. Previous studies have applied algorithms such as Naïve Bayes, Decision Tree, Support Vector Machine, K-Nearest Neighbour, Random Forest and other ensemble or hybrid approaches for student performance prediction. The proposed system focuses on a simple and efficient approach that can assist in identifying students who may require academic support at an early stage. The prediction is intended as an estimate and is not a guaranteed result.