Feature Engineering to Early Detection of Plant Disease Using Image Processing and Artificial Intelligence: A Comparative Analysis

<p class="Normal1">Medicinal plants have been found and utilized in traditional medical practices from ancient times. Many medicinal plants play a vital role in curating many life threatening diseases. Very few of the medicinal herbs are commercially cultivated. Many plant diseases are there which destroys these medicinal plants. Early detection of plant diseases can prevent the huge loss of these medicinal plants. Here, we presented a hybrid model that makes use of SVM along with the traditional convolutional neural network (CNN) for predicting <em>Basil</em> plants leaves diseases. We transformed the conventional CNN model by adding a classification layer Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) after feature extraction and this approach tends to perform better than traditional CNN as we make the dataset balanced by data augmentation and SVN and KNN tend to perform better in case of balanced samples. CNN is used for training, SVM/KNN is used for classification. The advantages of CNN and SVM are used in proposed the CNN and SVM and KNN model. It is assumed that such a combined model would incorporate the benefits of CNN and SVM. Here, we identified the four types of diseases that affect <em>basil</em> plant leaves as Leaf spot, Downy mildew, Fusarium wilt, Fungal, and Healthy. Since there isn’t a standard dataset for <em>basil</em> leaves, we created our own 803 picture data set and used various machine learning techniques to train and evaluate the model. However, over other existing algorithms, our hybrid model i.e., CNN+SVM has produced more accurate results. For five classes of <em>basil</em> plant leaves, the proposed model produced 95.02% accuracy of for leaf diseases.</p>

Agricultural development is a critical strategy for promoting prosperity and addressing the challenge of feeding nearly 10 billion people by 2050. Plant diseases can significantly impact food production, reducing both quantity and diversity. Therefore, early detection of plant diseases through automatic detection methods based on deep learning can improve food production quality and reduce economic losses. While previous models have been implemented for a single type of plant to ensure high accuracy, they require high-quality images for proper classification and are not effective with low-resolution images. To address these limitations, this paper proposes the use of pre-trained model based on convolutional neural networks (CNN) for plant disease detection. The focus is on fine-tuning the hyperparameters of popular pre-trained model such as EfficientNetV2S, to achieve higher accuracy in detecting plant diseases in lower resolution images, crowded and misleading backgrounds, shadows on leaves, different textures, and changes in brightness. The study utilized the Plant Diseases Dataset, which includes infected and uninfected crop leaves comprising 38 classes. In pursuit of improving the adaptability and robustness of our neural networks, we intentionally exposed them to a deliberately noisy training dataset. This strategic move followed the modification of the Plant Diseases Dataset, tailored to better suit the demands of our training process. Our objective was to enhance the network's ability to generalize effectively and perform robustly in real-world scenarios. This approach represents a critical step in our study's overarching goal of advancing plant disease detection, especially in challenging conditions, and underscores the importance of dataset optimization in deep learning applications.

A review on automated plant disease detection: motivation, limitations, challenges, and recent advancements for future research

Application of Artificial intelligence (AI) in agriculture sector plays an important role to enhance the yields by predicting and detecting the plant diseases and improving health of the crop. The early detection of plant diseases is crucial and helpful to the farmers to minimize the crop loss and ensure healthy crop. However, the traditional manual methods, are time consuming, error-prone, and inefficient for large-scale farming. Adopting recent technologies in Artificial Intelligence (AI) and Deep Learning, particularly Convolutional Neural Networks (CNNs) in the recent years have revolutionized the automation process of plant disease detection. However, singlemodal approaches depend on only RGB images often fail to capture critical physiological and biochemical changes in plants. To overcome these limitations, we propose a Single-Stream CNN in Multi-Modal Plant Disease Detection, integrating RGB, thermal, and hyperspectral imaging into a unified model. Unlike traditional multistream architectures that increase computational complexity, our model processes multi-modal data as a single 4-channel input tensor, optimizing feature fusion while maintaining computational efficiency. The proposed architecture, based on a Modified VGG-16 CNN model, which enhances disease detection accuracy by leveraging complementary information from different imaging modalities. Experimental evaluations demonstrate significant improvements in classification accuracy compared to RGB-only models. Furthermore, our model is optimized for real-time deployment on edge computing devices, making it scalable for precision agriculture applications, including automated greenhouse monitoring, drone-based crop surveillance, and IoTintegrated farming systems. This research work highlights the transformative potential of AI-driven multi-modal plant disease detection, flagging the way for more efficient, cost-effective, and scalable agricultural solutions.

Chapter 2 - Current status of plant diseases and food security

In agriculture, early detection of plant diseases is essential to avoid irretrievable damage to crops. However, accurate plant disease diagnosis is usually performed by professionals with high precision instruments which is both expensive and time consuming. To tackle this problem, an image recognition method based on multiple classifier integration is described. The method is composed of three parts. Firstly, a public dataset of diseased and healthy plant leaves is adopted. Secondly, three types of convolutional neural network (CNN) models are fine tuned to classify different diseases of plants and evaluated separately. Finally, the three models are integrated and evaluated for accurately diagnosing plant diseases. Experiment result shows the correctness and efficiency of the approach with a best accuracy of 99.92% on split test set.

The agricultural sector contributes significantly to the gross domestic product of emerging nations. One of the primary factors that reduce agricultural productivity is plant diseases. Detecting plant diseases is a crucial step requiring attention for a productive economy and agriculture. Traditional techniques of crop disease detection are laborious and time-consuming, requiring a great deal of skill and effort. Academicians, researchers and practitioners have recently shown a great interest in the new area of automatic plant disease identification. As soon as they arise on plant leaves, early detection of plant diseases can be aided by machine learning (ML) and deep learning (DL). A comprehensive analysis has been conducted in this review paper to assess the viability to identify plant diseases applying machine learning models. This paper also considers the illnesses and viruses that affect different crops: black gram, chickpea, mungbean and potato. A detailed procedure has been done to recognise and classify plant diseases. The analysis of various ML and DL algorithms adopted by researchers to classify diseases has been explained. Finally, challenges are highlighted to recognise and classify plant diseases utilising ML and DL algorithms, particularly in legume crops. Developing and integrating real-time datasets on plant diseases using advanced models is the future for monitoring, detecting and managing plant ailments.

The diagnosis of the plants is carried out with a visual inspection by experts and a biological examination is the second choice if necessary. They are usually expensive and time consuming. This inspired several computer methodologies to detect plant blights based on their leaf images. We apply a computer methodology on Deep Learning systems based on artificial neural networks, this branch also allows for the early detection of plant diseases, by applying convolutional neural networks (CNNs) familiar with some of the famous architectures, notably the “ResNet” architecture, using an augmented dataset containing images of healthy and diseased leaves (each leaf is manually cut and placed on a uniform background) with acceptable accuracy rates in the research environment. This Deep Learning technique has shown very good performance for various object detection problems. The model fulfills its role by classifying images into two categories (disease-free) and (diseased). According to the results obtained, the developed system achieves better detection performances than those proposed in the state of the art. Finally, to compare their performances, we use the implementation under Anaconda 2019.10.

In recent years, a significant amount of research has focused on analyzing the effectiveness of machine learning (ML) models for malware detection. These approaches have ranged from methods such as decision trees and clustering to more complex approaches like support vector machine (SVM) and deep neural networks. In particular, neural networks have proven to be very effective in detecting complex and advanced malware. This, however, comes with a caveat. Neural networks are notoriously complex. Therefore, the decisions that they make are often just accepted without questioning why the model made that specific decision. The black box characteristic of neural networks has challenged researchers to explore methods to explain black-box models such as SVM and neural networks and their decision-making process. Transparency and explainability give the experts and malware analysts assurance and trustworthiness about the ML models’ decisions. In addition, it helps in generating comprehensive reports that can be used to enhance cyber threat intelligence sharing. As such, this much needed analysis drives our work in this paper to explore the explainability and interpretability of ML models in the field of online malware detection. In this paper, we used the Shapley Additive exPlanations (SHAP) explainability technique to achieve efficient performance in interpreting the outcome of different ML models such as SVM Linear, SVM-RBF (Radial Basis Function), Random Forest (RF), Feed-Forward Neural Net (FFNN), and Convolutional Neural Network (CNN) models trained on an online malware dataset. To explain the output of these models, explainability techniques such as KernalSHAP, TreeSHAP, and DeepSHAP are applied to the obtained results.

Coastal aquifers are vital for sustaining ecosystems and providing freshwater for agriculture and domestic use. However, rising groundwater salinity in these regions demands innovative approaches for accurate modeling and prediction. In recent decades, machine learning (ML) and deep learning (DL) techniques have been extensively used across various water resource management fields, often yielding promising outcomes. This review examines the growing usage of ML and DL techniques in modeling groundwater salinity in coastal aquifers. The analysis is based on 104 peer-reviewed journal articles including the review articles indexed in PubMed, ScienceDirect, Google Scholar, Scopus, and SpringerLink using keywords like "saltwater intrusion", "machine learning", “deep learning”, and "groundwater salinity". The review discusses recent advancements, challenges, and future directions for improving ML model accuracy and applicability. Studies reveal an increasing reliance on ML techniques to predict groundwater salinity and manage seawater intrusion across various coastal geological settings. Researchers have employed a range of ML models, from traditional methods like Artificial Neural Networks and Adaptive Neuro Fuzzy Inference Systems to advanced DL-based models like Convolutional Neural Networks and Long Short-Term Memory Networks, often using ensemble methods to enhance accuracy. Key findings include the top-tier output of ensemble and optimized models, including Random Forest and Grasshopper Optimization Algorithm-XGBoost. These studies highlight the importance of model selection, input variable ranking, and computational efficiency, demonstrating ML's global relevance in environmental management. The review highlights the prospects of ML, DL, and ensemble models to redefine groundwater management in coastal aquifers, offering more effective and sustainable solutions to the challenges posed by groundwater salinity and saltwater intrusion. Future advancements will focus on further integrating DL, explainable artificial intelligence, and ensemble approaches, along with other innovative techniques, to explore sparsely studied variables, model new or unique study areas, and apply ML methods for managing groundwater salinity.

Systematic Review of Machine Learning in Diagnosis of Myeloproliferative Neoplasia

The growing demand for sustainable bioresources has spurred research into algae biomass estimation, a crucial aspect of biofuel production, carbon capture, and wastewater treatment. Despite the development of several methods to estimate algae biomass, a lack of standardized, scalable, and non-invasive biomass estimation models for outdoor environments persists. This study introduces a novel method that utilizes digital image-based RGB analysis of image models, integrated with machine learning (ML) algorithms. Traditional biomass estimation methods typically involve spectrophotometric or chemical analyses, which are labour-intensive and expensive. In contrast, the proposed approach employs low-cost RGB imaging, which enables real-time biomass quantification through image-based analysis. The research process involves data collection from controlled algae cultivation experiments, image preprocessing, and feature extraction using advanced computer vision techniques applied to Chlorella sorokiniana cultivated outdoors. Key features, such as colour indices, texture patterns, and pixel intensity distributions, were extracted from the RGB images. Various ML models, including Random Forest regressor (RFR), Extreme Gradient Boosting regressor (XGBR), and Convolutional Neural Networks (CNNs), were trained and validated to predict algal biomass concentrations. Experimental results demonstrated that the ML models accurately predicted algae biomass, with a correlation coefficient (R²) exceeding 90% in test datasets, showcasing the robustness of the proposed framework. Future research will explore multispectral extensions, adaptive ML models for various algal species, and deployment in real-world industrial settings.

Modern reviews of challenges related to deep learning application in agriculture mention restricted access to open datasets with high-resolution natural images taken in field conditions. Therefore, artificial intelligence solutions trained on these datasets containing low-resolution images and disease symptoms in the advanced stage are not suitable for early detection of plant diseases. The study aims to train a convolutional neural network for apple scab detection in an early stage of disease development. In this study a dataset was collected and used to develop a convolutional neural network based on the sliding-window method. The convolutional neural network was trained using the transfer-learning approach and MobileNetV2 architecture tuned on for embedded devices. The quality analysis in laboratory conditions showed the following accuracy results: F 1 score 0.96 and Cohen’s kappa 0.94; and the occlusion maps — correct classification features.

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a lesser number of training cases than did CNNs. "Deep learning", or ML with image input, in medical imaging is an explosively growing, promising field. It is expected that ML with image input will be the mainstream area in the field of medical imaging in the next few decades.

Agricultural production is one of the main sources of income in most countries. Enormous losses will be incurred if agricultural product is disturbed by plant disease. The key to reduce losses in agricultural product output and quantity is early detection of plant diseases. A diseased plant usually reflecting its disease by showing symptoms on its leaves. A potato leaf disease classification technique by using image processing and artificial neural network method is proposed in this study. The method can be used to determine the potato leaf is either healthy or diseased. With the aid of this technique, farmers can save time and cost in their farming activities. The main goal of this study is to detect potato plant (Solanum tuberosum L.) disease using image processing techniques. The K-Means clustering algorithm is used to segment the disease in potato leaf image. The segmented features of potato leaf disease are then extracted by using Gray Level Co-occurrence Matrix (GLCM) and these features are then fed into ANN for classification. With the proposed system, classification accuracy obtained is 94%.