Search

The purpose of this endeavour is to improve the plant F1 Score weed detection, and it will accomplish this goal with the assistance of VGG16. The VGG 16 and VGG 19 algorithms are used with varied training and testing splits in order to accomplish the goal of detecting the F1 Score plant weed. The Gpower test that was used to establish the sample size was approximately 80 percent. This was done in order to guarantee accuracy. When it came to each of the categories, the sample size was 10 for each individual. For the purpose of determining the power with g, the parameters that are used are α=0.05 and power=0.80. As a result of the investigation, it has been determined that VGG 16 (92.55 percent) demonstrates a greater level of accuracy in comparison to VGG 19 (90.14 percent), with a significant value of 0.161 (p<0.05). According to the result that has been reached, the accuracy of VGG 16 is superior to the accuracy of VGG 19 when it comes to the detection of weeds in plants that have an F1 Score. [ABSTRACT FROM AUTHOR]

Sweet corn (Zea mays L.) is a tropical plant. Sweet corn is more expensive than regular corn. The continuous use of chemical fertilizers has an impact on poor soil quality. Vermicompost with the addition of Trichoderma sp. is an alternative to improve soil quality and prevent sweet corn plant diseases. Research Objectives 1. Test the potency of vermicompost with the addition of Trichoderma sp. 2. Determining the optimum dose of vermicompost with the addition of Trichoderma sp. This research was conducted at the Lampung State Polytechnic. Research locations include analysis laboratories, factory I laboratories and land POF. The time of the study was March 2022 to June 2022. The study used RAK with 3 replications, consisting of a treatment with vermicompost and 1 treatment (without vermicompost and Trichoderma sp). So that with 3 replications and 7 treatments, there were 21 experimental units (trial units). Each experimental unit consisted of 1 plant and all plants became the object of observation. Stem diameter, plant height, cob weight with husk, cob weight without husk, brix had a significant effect between treatments, while number of leaves, leaf length, intensity of downy mildew and leaf rust disease had no significant effect between treatments. [ABSTRACT FROM AUTHOR]

Despite significant advancements in scientific research and genetics aimed at enhancing agricultural product quality and quantity, we still witness decrease in the production of crops. Factors contributing to this include wars, ethnic conflicts, and particularly plant diseases that can devastate entire crops, significantly impacting agricultural production. Artificial intelligence and computer vision have emerged as transformative solutions to various problems. Employing deep learning through convolutional neural networks (CNNs), have emerged as powerful tools for detecting and classifying plant diseases. The proposed model is the combination of VGG16 and CNN. The proposed model is implemented in python using google colab. The investigated architecture is also evaluated by comparing it with a machine learning model and CNN model. The comparison between proposed and existing models is done based on accuracy, precision and recall. Comparative analysis between KNN, SVM, Random Forest, CNN and proposed has been carried out. The accuracy of 97.89 percent is achieved for the proposed model. [ABSTRACT FROM AUTHOR]

The agriculture sector plays a critical role in ensuring global food security. However, the menace of plant leaf diseases poses a substantial threat to crop production. Early detection is pivotal for effective disease management. Convolutional Neural Networks (CNNs) have emerged as a promising technology for automating plant leaf disease prediction. This abstract provides a succinct overview of our research on CNN-based plant leaf disease prediction. Our study centers on developing a CNN model for automated disease detection and classification in plant leaves. We understood a diverse dataset comprising high-resolution images of healthy and diseased leaves, spanning various plant species and diseases. This dataset diversity bolsters the model's adaptability across diverse agricultural settings. The CNN architecture autonomously extracts pertinent features from input images, facilitating the detection of subtle disease-related patterns. Leveraging transfer learning with pre-trained models like VGG16 or ResNet enhances model generalization while reducing the need for extensive labeled data. Data augmentation methods enrich dataset variety and diminish overfitting, ensuring model robustness under varying conditions. Hyperparameter tuning and cross-validation techniques optimize model performance. The trained CNN model can be integrated into user-friendly applications or deployed on edge devices for real-time disease identification, providing insights into disease severity and treatment recommendations. This research underscores the transformative potential of CNNs in revolutionizing plant disease management, offering rapid, accurate, and accessible tools for early detection. This technology holds the promise of reducing yield losses, decreasing pesticide use, and promoting sustainable agriculture, benefiting both farmers and global food security. [ABSTRACT FROM AUTHOR]

Solanum lycopersicum L. is one of the agricultural crops with high economic value and is widely cultivated in Lampung. Production of tomato plants in Lampung province has decreased several times due to infection with plant diseases, one of which is infection of TYLCV. This virus belongs to the genus Begomovirus, family Geminiviridae, which is transmitted by whitefly vector (Bemisia tabaci Genn.). This study aims to detect the presence of TYLCV that infects tomato plants in Lampung based on symptoms, plant resistance, and virus distribution patterns. The survey results showed that several tomato plants in six locations, namely Agom, Takabau, Kedaton, Gunung Sulah, Sukarame Baru, and Kaliawi Persada Villages in South Lampung Regency and Bandar Lampung Municipality indicated that they were infected with TYLCV. The collection results obtained a total of six samples of tomato plant leaves with a variety of symptoms indicating TYLCV infection, such as mosaic, leaf curling, cupping, yellowing, easily crushed leaves, and stunting. Analysis of plant resistance level showed 50% very susceptible, 33.3% susceptible, and 16.7% moderately resistant. Analysis of the distribution of TYLCV in tomato plants in two regency/municipality in Lampung showed a broad and even distribution pattern of infection. This study proves that TYLCV infection in tomato plants in Lampung, especially in the South Lampung Regency and Municipality of Bandar Lampung has been very severe. [ABSTRACT FROM AUTHOR]

In this study of this research is to improve in accuracy for blast disease in rice crops using K-Nearest Neighbour Algorithm and compared with Random Forest Algorithm. To predict the Rice Blast illness, K-Nearest Neighbour Algorithm and Random Forest in both used, with different training and testing splits. In this case, 169 samples were employed in each of the two groups for an analysis that involved 10 iterations in total. The ClinCalc programme is used as a tool to calculate the setup's correctness for supervised learning. This test's average Gpower is about 80% using G power setting values of 0.05 and 0.80. Novel Supporting Vector Machine and K-Nearest Neighbour's performance at identifying Blast Disease in rice crops will depend on the quality of chosen dataset. The K-Closest Neighbour approach outperforms Random Forest (88.5950%) in terms of both Accuracy and loss, with an Independent Sample T-test of p=0.001 which is considered to be statistically significant. The K-Nearest Neighbour method (88.595%) is more accurate than Random Forest (78.100%) Algorithm. K-Nearest Neighbour can be more effective than Random Forest when dealing with high-dimensional data and when there is a complex relationship between the features and the label for the selected dataset. [ABSTRACT FROM AUTHOR]

The research aims to compare the Convolutional Neural Network (CNN) classifier method with Transfer Learning (TL) to detect different types of plant diseases from diverse agricultural regions. This component handles the gathering and processing of the dataset. A total of two study groups, CNN and TL are used. This research examined the disease in rice leaves using a publicly available data set with a sample size of 3,269 Rice leaf pictures (JPEG/JPG). The data was downloaded from the UCI Repository. The samples were separated into two groups, training samples (80 %) and test samples (20%). For the sample size calculation, the values are Alpha=0.05, Beta=0.02, and G power=80 %. Convolutional neural networks have a 94.88 % accuracy rate, whereas transfer learning has a 91.80 % accuracy rate. P has a significance value of 0.004 (p<0.05), indicating statistical importance. The rate at which the proposed algorithm identifies diseases is assessed and contrasted with the conventional method. The results of the accuracy comparison indicate that the accuracy of the Convolution Classifier (CNN) algorithm surpasses that of TL. [ABSTRACT FROM AUTHOR]

According to the Ministry of Agriculture of the Republic of Indonesia (2019), it was informed that foreign exchange earned from oil palm decreased by 20%, this was due to the large number of old plants that were less productive and also many plants affected by disease. In order to increase oil palm productivity, the President of the Republic Indonesia given Instruction No. 6 of 2019 concerning the National Action Plan for Sustainable Oil Palm Plantations for 2019-2024, with one of the actions to increase national oil palm productivity being strengthened data, coordination, and infrastructure. The aim of this study is to produce mapping of oil palm age based on Google Earth Engine (GEE) toward one data oil palm management. The methodology includes data collection, georeferencing, estimation of oil palm age, and visualization. The result showed mapping and visualization of spatial distribution of oil palm age in Indonesia. For further direction, the oil palm age mapping will be integrated with geodatabase one oil palm data management. [ABSTRACT FROM AUTHOR]

The quantity and quality of food produced are often threatened by plant diseases, which can have a devastating impact. Therefore, early diagnosis of plant diseases is often crucial to prevent production losses. The development of deep learning modelshas opened up new avenues for achieving high accuracy in detecting and mitigating crop diseases. This paper proposes a CNN models for accurately classifying leaf diseases in crops, specifically focusing on rice, corn, and wheat plants. The proposed method utilizes DenseNet169 and InceptionV3 as the base models respectively trained on corn, rice, and wheat disease datasets. The proposed method has successfully achieved an accuracy of 99.89% using DenseNet169 and 99.25% using InceptionV3 for corn leaf disease dataset. The proposed method also obtained an accuracy of 98.52% and 98.58% for the wheat crop disease using DenseNet169 and InceptionV3 models respectively. For the Rice crop, rice dataset is separated into major and minor diseasesin order to comprehend the variety of diseases and obtained an accuracy of 99.18% and 91.77% for major and minor rice crops using DenseNet169 variants respectively. Overall, the proposed approach proves to be successful in accurately classifying diseasesacross rice, corn, and wheat crop diseases, providing reliable and detailed predictions. [ABSTRACT FROM AUTHOR]

Fruit and vegetable cultivation on a large scale requires proper care and protection. During forming, crop yield can be improved if proper care is taken. The chief aspect of improving cultivation is detecting diseases affecting the crops. Besides disease detection, vitamin identification can also increase the type of edible fruits and vegetables cultivated. A new approach has been proposed to detect the diseases affecting the fruits and the vitamins of the fruits based on the comparisons of their images. Transfer learning algorithms can extract various fruit parameters and analyze them for specific requirements. CNN-based CONVNET and ALEXNET algorithms were used to analyze and discriminate based on numerous characteristics and parameters extracted from them. The Algorithm was implemented in MATLAB, and the diseases were detected with 99.6% for ALEXNET and an accuracy of 77.5% for CONVNET. [ABSTRACT FROM AUTHOR]

Agriculture's production is heavily impacted by the state of the economy. Plant disease is increasingly common in agricultural settings and is now easier to detect as a result of the previously described issue. It is receiving more attention due to the monitoring of crops in a wide range of settings. Farmer transitions between different disease control strategies and encounters significant challenges. We are able to identify or detect leaf illnesses, which is how surveillance and monitoring experts usually find them. If the appropriate control measures aren't followed, the plants suffer a major consequence, which symbolizes how the quality of the plants' production will be impacted. The adoption of a mechanical approach or method for identifying diseases is effective and beneficial since it lessens the burdensome work of surveillance in the vast cultivation. The early stages of plant illnesses allow us to identify the signs even before they manifest on the plant's leaves. The early stage denotes the starting period which is one or two days after affecting the disease. The paper's primary objective is to use ResNet50 for early detection of plant disease. ResNet50 has been successfully applied to plant disease image classification tasks and has shown promising results. ResNet architecture, with its deep layers and residual connections, has the ability to capture intricate patterns and features, which is useful for identifying the differences in plant images. The results proved that the ResNet 50 has better accuracy, precision and recall than Support vector machines (SVM), artificial neural networks (ANN), Convolutional neural networks (CNN) for plant disease prediction. [ABSTRACT FROM AUTHOR]

Coffee is an important international commodity, especially for Indonesia, which ranks fourth as the world's coffee producer. However, in the field, coffee plants are susceptible to pests and diseases, which can reduce the yield and quality of the finished product. For farmers who often rely on rain-fed crops and have limited access to financial and technical support, this is a significant obstacle. Image processing and machine learning techniques, particularly deep learning and convolutional neural networks (CNN), can help identify and early detect plant diseases. This study used a quadcopter drone for image acquisition and employed CNN architectures, specifically AlexNet with 50, 75, and 100 epochs, to classify coffee leaves into three classes: healthy, leaf rust, and leaf spot. The best results were achieved by Alexnet with 100 epochs with an accuracy of 93.7%, precision of 98%, and recall of 100%. Thus, it can be concluded that the CNN method using the Alexnet model with 100 epochs and combined with a quadcopter drone can be used to detect coffee plant diseases. [ABSTRACT FROM AUTHOR]

Crop disease is a major concern for farmers as it can lead to significant crop yield and quality losses. Traditional methods of diseasedetection rely on visual inspection, which can be time-consuming and labor-intensive. To overcome these challenges, researchers have developed a new approach that uses Internet of Things (IoT) technology and deep neural networks to predict crop diseases. Agricultural pestsand illnesses significantly diminish yields, often by more than 50% or even causing crop failure. Precision farming now has new dimensionsthanks to farming made possible by technology assisted by IoT and image-processing tools for predicting illness. This approach provides a more accurate and efficient way of detecting crop diseases and allows farmers to take preventative measures to protect their crops from disease. The suggested approach integrates IoT and image processing that use deep learning models to do classification and supports enhanced production by assisting in the prediction of agricultural disease. In conclusion, integrating IoT and deep neural networks in crop disease prediction can potentially revolutionize the agricultural industry. By providing accurate and timely predictions of crop diseases, farmers can take preventative measures to protect their crops and increase their yield and quality. [ABSTRACT FROM AUTHOR]

Indian economy relies heavily on agricultural production. This is one of the factors contributing to how crucial it is to identify plant diseases in tomato leaves in agricultural regions, especially given how prevalent they are there. If safety measures are not taken, plants will suffer greatly, which will affect the quality, volume, or efficiency of the associated goods, as appropriate. In addition to a study of several disease classification methodologies that may be used to locate tomato leaf illnesses, this article uses CNN method and Gray-Level Convolutional Matrix algorithm-based method for tomato leaf disease detection and classification covers an image segmentation methodology that can be used to automatically detect and categorise plant leaf diseases that can be utilised for both automated and manual disease detection on plant leaves and the results obtained assures the effectivity of the proposed method for the tomato leaves. [ABSTRACT FROM AUTHOR]

The productivity of the agricultural sector is crucial to the Indian economy. The presence of illness in plants is very widespread, which is one of the reasons why plant disease detection is important in the agricultural industry. In this area, plants face severe effects if safety precautions are not taken, which affects the quality, quantity, or productivity of the respective products. It is advantageous to utilize an automatic system for spotting plant diseases since it reduces the amount of work needed to keep an eye on large crop farms and can spot disease symptoms as soon as they appear on plant leaves. This article discusses an image segmentation technique that can be used to automatically detect and categorize plant leaf diseases., as well as a study of various disease categorization approaches that can be used to find plant leaf diseases. Image segmentation is done using a neural network and is a critical stage in the plant leaf disease detection process. [ABSTRACT FROM AUTHOR]

Rice is a vital staple crop, and the presence of diseases can significantly impact its production. Consequently, there is an increasing demand to create efficient strategies for recognizing and controlling diseases in rice plants. This paper provides a comprehensive review of the recent advancements in disease identification techniques for rice plants, focusing on the integration of image processing, machine learning, and deep learning methodologies. Despite the progress made, there remains a need for further research to identify and classify additional rice plant diseases beyond the major ones discussed in this paper. By continually exploring new techniques and expanding the scope of disease identification, researchers have the potential to enhance the overall effectiveness of rice disease detection systems. This review serves as a valuable resource for researchers and practitioners in the field, offering insights into the current state of the art and suggesting future directions for advancements in the identification and management of rice plant diseases introduced. [ABSTRACT FROM AUTHOR]

The purpose of this research is to identify and classify leaf diseases in corn plants. In this research, the Convolutional Neural Network (CNN) method is used to classify and identify objects in real time. This research describes an automated method for detecting corn leaf diseases that is based on three steps: pre-processing, feature extraction, and classification. Experimental findings show that the proposed method can efficiently and accurately detect leaf diseases of corn plants. The test results prove that the classification of corn plant diseases through leaf images using deep learning with the convolutional neural network (CNN) method in the experiment obtained an accuracy rate of 95%. This high level of accuracy is expected to help farmers control the spread of corn diseases as early as possible to minimize greater losses. [ABSTRACT FROM AUTHOR]

Cassava plays an important role as a staple food source in Indonesia because of its high production level. However, the productivity of cassava plants can be negatively impacted by pest and disease attacks on the leaves. Although the symptoms of cassava leaf disease can often be identified visually, more expertise is needed to differentiate one disease from another. To overcome this challenge, Convolutional Neural Networks (CNN) was used for disease classification in cassava plants, using a dataset of 10,423 images with data augmentation. The results show that the most effective model is the EfficientNetB0 model, which utilizes a learning rate of 0.0001, 25 epochs, and a dropout rate of 0.4. This model successfully classified cassava plant diseases with an impressive accuracy of 98.09% during the validation stage and achieved a testing accuracy of 90.74%. This research shows the potential of CNN and transfer learning techniques in classifying cassava plant diseases accurately. [ABSTRACT FROM AUTHOR]

A growing field in India that can assist farmers in many ways is the identification of plant diseases. Plant disease reduces the mass production in agriculture. Every time due to heavy loss in agriculture, farmers face many challenges to raise up their needs. This study analyzes various diseases that affect various plants due to the following criteria like environmental condition, types of plant formed from Monocot and Dicot family, crop rotation and Ph value of the soil. The existing system analyzed the diseases based on one of the criteria. Although the strategy is to be followed to identify plant diseases at the early stage with various aspects so that the production in agriculture could be increased. The majority of machine learning algorithms already exist and may be improved upon to yield more accuracy. Xanthomonas wilt, Black and Yellow Sigatoka, Bunchy Top Virus, Black Sigatoka, Fusarium wilt, Cassava Bacterial Blight (CBB), Cassava Brown Steak Disease (CBSD), Cassava Green Mite (CGM), and Cassava Mosaic Disease (CMD), Yellow vein mosaic virus, and Powdery Mildew are a few of the diseases of the plants grown on crop rotation which are the subject of study of this paper. Plant illnesses are classified according to disease in the many open-source datasets that are accessible. For deeper understanding, we have provided a list of references. Here, we've examined the approaches that are now in use for automatically detecting various diseases of plant leaves. We present an approach for accurately identifying early signs of plant diseases from a variety of perspectives. [ABSTRACT FROM AUTHOR]

The agricultural sector is crucial to the economy. The agricultural sector continues to play a significant role in India's economy, accounting for around 15% of GDP. In many parts of the world, agricultural automation has become a pressing topic of discussion. Expert systems, language processing, speech recognition, and machine learning are just some of the artificial intelligence (AI) approaches that have altered not only the quantity but also the quality of agricultural sector positions in response to factors like the increasing global population, the rising global demand for food, and shifts in the environment and the availability of water. The most effective concepts that have played a major role in revolutionizing the agricultural economy throughout the pandemic are artificial intelligence (AI), Machine Learning (ML), and the internet of things (IoT). Constant disease attacks pose a threat to agriculture, lowering both the quality and volume of agricultural goods and having a significant negative impact on the national economy. These days, large-scale agricultural monitoring increasingly includes looking for signs of plant diseases. As a result, catching infections early can lessen their impact and save more crops. Manual disease identification, on the other hand, is laborious, prone to mistakes, and necessitates an in-depth understanding of plant pathogens. Changing from one method of disease control to another is a major challenge for farmers. Automated procedures, on the other hand, are more efficient. Traditional methods for detecting and identifying plant diseases rely on the trained eyes of professionals. In this work we design an automated approach for classifying and detecting plant diseases automatically by using our Application. [ABSTRACT FROM AUTHOR]

Rice is the third highest production crop globally. There are many diseases that will affect the productivity of rice plant. The common rice plant diseases are Rice blast, Shealh Blight, Bacterial leaf blight, brown spot and Rice leaf streak. Early identification of these diseases will play crucial role in crop yield. Recent deep learning architectures can be trained in such a way that it can detect multiple diseases at once. The article aims to provide overview of all those research works that uses deep learning architectures for the identification of rice disease. This paper begins with the introduction of the importance of rice plant disease identification. Then the paper explains the various rice diseases, followed by explaining general deep learning architecture that is used for the identification of Rice plant disease. Then the paper aims to provide information about research papers that uses deep learning architectures for rice disease identification and will try to spot any limitations. At last, the paper aims to provide the future scope of the same. [ABSTRACT FROM AUTHOR]

Cotton is one of the important cash crops in India grown on more than 9 million hectors. Like other crops this also suffers from diseases but the effect on the yield affects many livelihoods. Thus, it is necessary to detect the disease in early phase so that cure can be taken. This paper proposes a Convolutional Neural Network (CNN) model for detecting diseases in cotton plants. The model implements in proposed work utilize transfer learning technique, leveraging pre-trained model that have been trained on extensive datasets. Specifically, the Resnet152v2 model serves as foundational architecture for the model, enabling accurate classification of distinct objects. In addition to Resnet152V2 base, the proposed work incorporates two supplementary dense neural network layers. These additional layers enhance the model capacity to learn complex pattern and improve its classification capabilities. With integration of transfer learning and inclusion of supplementary dense network layer, the model demonstrates its ability to effectively classify objects. In addition to Resnet152a 98.36% accuracy in distinguishing between healthy and diseased cotton plants. [ABSTRACT FROM AUTHOR]

This research aims to develop a Deep learning-based Convolutional Neural Network (CNN) model for detecting tomato plant diseases. Transfer learning involves training the model on a modest dataset by utilizing characteristics from extensive collections of high-resolution images, all while preserving its capacity to generalize effectively. The model builds upon the Inceptionv3 model and incorporates two dense neural network layers to accurately distinguish between the target object and other objects. The accuracy achieved in classifying the presence of tomato plant diseases is 94.06%. [ABSTRACT FROM AUTHOR]

Crop diseases present a substantial threat to worldwide food security, emphasizing the critical importance of timely and precise disease detection to mitigate yield losses and support sustainable agriculture. This study introduces an innovative approach that harnesses the power of Machine Learning (ML) and the Internet of Things (IoT) to revolutionize the detection of crop diseases. Within this framework, IoT sensors strategically deployed across agricultural fields gather real-time environmental data, while high-resolution crop images are captured using drones and on-site cameras. ML models, including Convolutional Neural Networks (CNNs), harness this data to enable early and accurate disease detection. By integrating IoT capabilities, we can correlate disease outbreaks with environmental factors, thereby enhancing the decision-making process. The results are promising, consistently demonstrating high accuracy in disease detection and the potential for reducing the need for chemical treatments. This research paper signifies a significant step towards promoting sustainable farming practices and enhancing global food security. [ABSTRACT FROM AUTHOR]

Farming is the strength of everyone's life. Everyone depends on the products of agriculture. But agricultural products are degrading in quality and quantity nowadays. To increase the yield, then the disease has to be identified early, improve knowledge to do better farming. If agricultural products fall in price, the entire economy suffers. when the farmers ultimately suffer a crushing loss and it leads to a financial boom. Identifying disease at an early stage is the only way to improve productivity. This paper introduces the concept of internet of things technology to perceive data and discusses the role of IoT technology in farming infection and bug nuisance control, including rural disease and bug checking system, gathering illness and creepy crawly bother data using sensor hubs, information preparing and mining, etc. It is suggested to use an IoT-based framework for disease and bug irritation control that consists of three layers and three frameworks. A different way to access horticulture data for the farm can be provided by the framework. In this study, a computerised system has been developed to determine whether a plant is healthy or sick. Plant disease does have a real impact on the normal growth of the plants, their production, and their nature as horticultural products. The goal of this research is to create a robotized framework that can detect the presence of disease in plants. Based on the diversity in plant leaf health status, a computerised disease recognition framework is developed using sensors like temperature, moisture, and colour. The characteristics based on temperature, mugginess, and shading criteria are used to identify the proximity of plant disease. [ABSTRACT FROM AUTHOR]

Agriculture is critical to our country's economic success. It yields the most profit in crop production on the farmer's land. India is a developing country, and agriculture is a major component of the Indian economy, accounting for approximately 17% of GDP. India is also the world's second largest producer and the largest exporter of rice. Being the chief grain of India, the country has the largest area under rice cultivation, but the optimal yield would only be guaranteed if the field is free from diseases, whether it be fungal or bacteria, pests and nutritional deficiencies. The presented study will be very beneficial for the researchers to recognize any diseases, pests and nutritional deficiencies of the rice plant. As pest attacks also result in damage to the entire field, causing a reduction in the optimal yield production. Plant nutrients are also required for plants' good overall health. These nutrients are classified into three classes: primary nutrients, micro-nutrients and macronutrients. Each of these nutrients is essential for plant growth and development, but for optimal rice production at least primary nutritional deficiency should be taken care of which includes nitrogen, potassium and phosphorus. Agricultural crop losses directly attributed to fungus are significant, but to increase the productivity to the fullest pest attacks as well as primary nutrition deficiencies must also be detected. In this paper, we have conducted a literature study on various approaches and analysis of rice plant diseases, pests and nutritional deficiencies have been shown in tables which highlight the number of diseases focused, numbers of pests focused and number of nutritional deficiencies focused by different researchers. [ABSTRACT FROM AUTHOR]

This paper's objective is to improve accuracy in plant leaf disease detection using Machine learning techniques such as K-Nearest Neighbors classifier (KNN) with a sample size of 10 and Novel Convolution Neural Network (CNN). This article consists of 2 groupsi.e Convolutional Neural Network (CNN) and K-Nearest Neighbors Classifier with a sample size of 10 for each group. G Power software is used to determine sample size with a pretest power value is 0.8 and alpha 0.05. The accuracy evaluated using both algorithms is compared and CNN appears to be the most significant with an accuracy of 92.48% and KNN with an accuracy of 74.14% with p=0.041. An Independent sample t-test has been used and analyzed with a confidence level of 95 percent. Results show that the CNN algorithm is significantly better than KNN in detecting plant leaf disease. [ABSTRACT FROM AUTHOR]

The demand for faster algorithms that can extract information from images is becoming increasingly crucial due to the continuously growing volume of image data in practically all disciplines. When using photos in your research, studies, and presentations, it is crucial to assess and evaluate them. Images, like any other source, should be evaluated and reviewed in order to determine their quality, dependability, and appropriateness. Images need to be examined and appraised on several levels. Researchers employ a wide range of methods and datasets for various kinds of image analysis. However, it is still important to survey, analyze, and describe the characteristics and significance of methodologies with support in a variety of applications that will be helpful for new researchers and everyone. The novelty of this review paper is to study the various types of image analysis techniques and datasets used in analyzing the images to detect, identify, and predict disease or any other useful insight content, which are used in various numerous applications such as the medical field, robot vision, pattern recognition, plant disease detection and prediction, and so on. [ABSTRACT FROM AUTHOR]

In India, maize leaf diseases, which may drastically lower yields in maize crops, can have a detrimental influence on both food security and the economy's sustainability. Early detection and accurate diagnosis of many disorders are essential for disease treatment. Traditional methods of disease detection and diagnosis require a lot of labour and a competent team. The convolutional neural network was used in the current study to address this research issue. This specific network has the ability to classify and identify plant leaf diseases at the early stages of the sickness. Based on 9500 images of maize leaf illnesses in 4 classes—stalk rots, Zonate leaf spot, Maydis leaf spot, Turcica leaf spot, and healthy class—this model works well, with an accuracy of 96.91% and a loss of 0.30825. The proposed approach performed better than the benchmark model when it came to forecasting diseases in the maize crop. [ABSTRACT FROM AUTHOR]

Plant disease identification is critical to smart agriculture because it prevents diseases from spreading in the field by recognising them early on. With the purpose of early disease identification and classification, a novel statistical approach-based plant disease detection system is developed. The leaf's sick region has been separated using a unique statistical threshold value, and the characteristics are collected using a co-occurrence matrix with grey levels. This device is designed to collect field images of leaves using a visual sensor. The technology is evaluated using both publicly available datasets and actual field images. A support vector machine is used for categorization to improve accuracy. The performance parameters utilised to assess the performance of the highlighted system are classification accuracy and detection accuracy. The proposed technique outperforms current state-of-the-art methods, with an average detection accuracy of 98.43% and a classification accuracy of nearly 99.9%. [ABSTRACT FROM AUTHOR]

Fungi are the potential pathogen and are responsible for fungal infections and diseases to animals and plants. The global mortality rate due to fungal infections has become comparable to Tuberculosis and Acquired immunodeficiency syndrome, and in agriculture sector a perennial yield loss of ∼20% occurs worldwide due to fungal attack. These issues are exacerbated by the fact that only limited number of conventional antifungal drugs are available at present. Most of the fungi have already started developing resistance to those drugs. Plant is a repository of various important secondary metabolites which possess important pharmacological activities. Resorting to plant for exploration of their antifungal property and novel antifungal compounds become an important option at present time. Indian medicinal plants are associated with antifungal compounds and exhibit strong antifungal property. In this review, we discuss about Indian medicinal plants having antifungal property and their antifungal mode of action, also highlight on their synergistic antifungal activity and patent on herbal remedies for fungal diseases. [ABSTRACT FROM AUTHOR]

This Paper will emphasis on the impact of usage of technology in the farming. This paper takes into consideration of several research papers and summarises a detailed understanding of the concept and future direction requiring further research. As yield loss in harvest is regularly connected with the poor quality seed selection, plant diseases etc., we have made a deep research on application of technology in agriculture to reduce the loss and to improve the yield and profits. From the seed selection till the yield production, the usage of technology and it's impact over the farming was well summarized here. We have thoroughly referred various papers and summarized the use of technology in various cropping stages that includes seed selection, crop pest and disease prediction and nutrient deficiency prediction along with the yield prediction. [ABSTRACT FROM AUTHOR]

The extensive use of synthetic fungicides in controlling plant disease generates detrimental impacts on the environment and human health. In response to this problem, an alternative method was developed, known as biological control using antagonistic microorganisms. The plant rhizosphere is rich in microbes, one of which is a group of fungi. The aim of the present work was to evaluate the biocontrol potential of rhizosphere fungi against Fusarium oxysporum, a phytopathogen that causes anthracnose disease. A total of twenty-seven rhizosphere fungi were isolated from different tissue parts of grape (Vitis vinifera). Results demonstrated that most rhizosphere fungal isolates showed some inhibitory action over the growth of F. oxysporum during dual culture growth. Rhizosphere isolate G11 showed the highest antagonistic activity against F. oxysporum with 86.59% percentage inhibition radial growth (PIRG). In conclusion, rhizosphere fungi isolated from V. vinifera indicate the potential as biocontrol agents. It is hoped that the finding of isolated rhizosphere fungi in this study with antagonistic activity against F. oxysporum pathogen may be used in biocontrol programs for plant disease in the region. [ABSTRACT FROM AUTHOR]

Chemical fungicides resulted in heavy environmental pollution, increased risk of health problems, development of pesticide resistance, reduce soil quality, and produced unsafe agricultural products. Therefore, there is a great increasing interest in discovering and developing new improved fungicides based on natural products as well as introducing measures such as microbial control agents to protect plants from diseases. The ability of Streptomyces to produce various bioactive compounds, led to it being a promising biocontrol agent for a wide range of phytopathogenic fungi. We have screened five Streptomyces isolates for the production of bioactive metabolites that suppress Rhizoctonia solani growth. The screening results revealed five Streptomyces isolates produce bioactive metabolites that inhibit R. solani growth. Streptomyces bobili in No.3 medium, produced the strongest bioactive compound compared to Streptomyces sp. W 28-5, Streptomyces sp. LIPI MC A-132, Streptomyces sp. W 13-5, and Streptosporangium sp. W 26-8, that inhibited 60.94% Rhizoctonia solani growth. The cultivation methods of the actinomycetes influenced the production of their bioactive metabolites and inhibited growth of R.solani. Strain identification was performed by morphological observation and 16S rDNA analyses. The results showed that isolates W13-5, W 28-5, and isolate LIPI MC A-132 were Streptomyces sp; W28-3 was Streptomyces bobili, and isolate W 26-8 was Streptosporangium sp. [ABSTRACT FROM AUTHOR]

The main obstacle in dragon fruit cultivation in Indonesia and abroad is stem canker caused by Neoscytalidium dimidiatum. So far, no adequate control techniques have been found against this pathogen. The most effective and efficient control of plant diseases is resistant clones/varieties. This study aims to determine the resistance of clones/types of dragon fruit Hylocereus costaricensis 01 against stem canker. The study was conducted in disease-endemic areas in Padang Pariaman Regency, West Sumatra, from July 2016 to March 2018. The experiment was arranged in paired blocks design with five replicates and a susceptible clone, H. polyrhizus as the control plant. The percentage of the disease attack and disease severity index were measured every two weeks. The results showed that dragon fruit clone H. costaricensis 01 had high resistance to stem canker. At six months, the percentage of the disease attack and disease severity index in the test plants were 7.81±1.99% and 0.08±0.13 and were significantly different from the control plant with a value of 98.44%±1.99 and 2.23±0.39. Resistance of H. costaricensis 01 to stem canker remained stable when the plant was 20 months old, with the percentage of the disease attack and disease severity index was 6.25% and 0.07±0.13, while the control plant was 100% and 2.48±0.57. The clone of H. costaricensis 01 has high resistance to the pathogen N. dimidiatum. However, the fruit size is small and requires assistance in pollination, so these clones can be used as parents in crosses to produce stem cancer-resistant plants. [ABSTRACT FROM AUTHOR]

Sclerotium rolfsii is a broadly-host pathogen that causes disease in various plants, including Aloe vera (L.) Burm.f., and is commonly controlled with fungicides. Other alternative control methods using bacteria antagonists are worth studying. The study aimed to evaluate the effect of volatile organic compounds (VOCs) trapped on solid agar on the growth of S. rolfsii. The bacterial isolates, i.e., Serratia sp. S108 and Brucella sp. BE60 were streaked on nutrient agar, covered and sealed with trapping agar media and then incubated for 3 days at 28 °C. The trapping media used were water agar (WA) 1.75%, and WA enriched with active carbon (WAC), i.e., 0.25%, 0.375%, and 0.5%. Clove oil (1 ml) was used as a standard VOCs control. The treated trapped agar media were then inoculated with S. rolfsii and incubated for three days at 28 °C. The growth diameter of fungus on the trapped agar was compared with non-treated WA. The experiment was designed completely random, with three replications. Also, the trapped VOCs agar media were seeded with surface sterilized seeds of Brassica juncea L. to know its effect on seed growth. The study showed that the trapped VOCs agar media of WA and WAC inhibited the radial growth of S. sclerotium and B. juncea. The study implies that the trapped VOCs of bacterial isolates could be further investigated as an alternative method to control fungus; however, it should be borne in mind that the VOCs also repressed seed growth. [ABSTRACT FROM AUTHOR]

Phytophthora capsici is a fungal pathogen as the causal agent of foot rot diseases on black pepper which is the most devastating. Chemical fungicide is commonly used to control that disease, but it is not eco-friendly. Nano eucalyptus formulation is an eco-friendly fungicide, due to the active ingredient being eucalyptus oil. The research was conducted at the Laboratory of Plant Diseases, Indonesian Spices and Medicinal Crops Research Institute (ISMCRI), from March to August 2022. A completely randomized design was used, with 5 treatments and 6 replications. The aim of the research is to observe the effect of improving nano eucalyptus (NE) formulation and storage time against the growth of P. capsici in vitro and in vivo. The results of an in vitro test showed that the improvement of the NE formulation (by reducing the particle size of the active ingredient to 14.12 nm) could increase the effectiveness of P. capsici growth inhibition by 8.09 – 16.32% at a concentration of 1-3. Storage of the NE formulation for 11 months did not decrease the effectiveness of the inhibition against the growth of P. capsici. Based on the preliminary in vivo test on Phytophthora leaf spot on black pepper, preventive treatment was better than curative, due to the leaf spot area of NE formulation treatment being smaller than without treatment. [ABSTRACT FROM AUTHOR]

During post-harvest stages, mangoes can suffer from anthracnose diseases (Colletotrichum spp). Chitosan (CS) is widely applied in plant disease control due to its biocompatible and biodegradability. The study aimed to obtain CS formulation against the suppression of fungal growth and severity of anthracnose. The bacterial isolates producing chitinase belong to the Bacillus subtilis. The CS formulas hydrolyzed by chitinase of E Am-1 and E Ag-4 isolates were in the nano dimensions range of 297.1+63.09 nm and 834.8+75.7 nm, respectively. The CS formulas inhibit the growth of Colletotrichum spp. ranged from 36 to 85% under in vitro assay. Disease suppression (DS) of cv. 'Arumanis' with coating formula (artificial inoculation) was 95.28%, and 45.37% (natural infection), whilst the DS of cv. 'Indramayu' was 64.7%, and 57.45%, respectively. Evaluation of the CS formula viability showed that the older formula was less effective than the new formula. The CS formulation had no significant effect on the four mango cultivars tested. The lowest mean severity index is shown by cv. 'Garifta orange', while the highest severity index is shown by cv.'Agrigardina 45'. The AUDPC values ranged from 125.01 to 633.34, with the highest DS value of 76% on cv. 'Arumanis'. This study showed that fruit coating using CS formulation aided by chitinase of E Am-1 and E-Ag-4 can be recommended as an alternative safe method against anthracnose. Further research is needed to obtain a more effective CS-coated formula that could inhibit anthracnose disease in mango during post-harvest storage. [ABSTRACT FROM AUTHOR]

The microbial community plays a vital role in plant growth and development. Bacteria, as a biotic factor, can induce indigenous plant metabolism. The changes in plant metabolism due to disease infection significantly impact its community in plants and soil. This research aimed to study the composition of the bacterial community on the papaya seeds-fruit with crown rot symptoms through Next Generation Sequencing (NGS). Seeds samples were collected from papaya fruits cv. California at the farmer's land in Jember, East Java. The Bacterial abundance, diversity, and functional pathway annotation were carried out through NGS of 16s rRNA sequences. The result of metataxonomics data produces 2111 observed reads with predominant phylum Proteobacteria (83.5%). The most OTUs retrieved from Proteobacteria (1242) and Firmicutes (383) phyla with Shannon and Simpson indices were 5.122 and 0.976, respectively. The dominant pathways based on the predictions of functional annotation were the biosynthesis of secondary metabolites, microbial metabolism, and microbial transport system. Bacterial composition and diversity in the crown rot symptomatic papaya seeds were more crowded with beneficial species such as Proteobacteria and Firmicutes than the pathogen itself. This condition might be triggered as the form of microbial response to the plant metabolic changes during the pathogen infection that affects the microbial community in the plant. This study unravels the information of bacterial community associated with the crown rot symptomatic seed of papaya fruit and provides an insight into the potential bacterial community in papaya seed for further development to be used in plant disease management. [ABSTRACT FROM AUTHOR]

The identification and diagnosis of plant diseases is one of the key factors in determining crop losses in crop production and agriculture. An analytical study of plant diseases is the study of any visible points in any part of a plant that help us to distinguish between two plants, technically or any dots or shades of color. Crop sustainability is one of the key factors in agricultural development. Diagnosis of plant disease requires a lot of work and expertise, a lot of knowledge in the field of plants, and research to diagnose those diseases. Therefore, image processing is used to differentiate plant diseases. Disease diagnosis follows methods for image acquisition, image removal, image classification, and pre-image processing. Leaf color, amount of damage to leaves, leaf area of the unhealthy plant is used for sorting. In this case, we reviewed the learning algorithms of the various machines to identify the leaf diseases of different plants and to determine the best accuracy. [ABSTRACT FROM AUTHOR]

Identification of plant-diseases from leaf imagery is a multidomain task that involves pre-processing of leaves, segmentation for background removal, feature representation & classification operations. Most of the existing deep learning models utilize single Convolutional Neural Network (CNN) for identification of these diseases, which limits their accuracy when number of disease classes are increased. To overcome this issue, a novel Cascade Convolutional Neural Network (CCNN) for improved plant disease detection is discussed in this text. The proposed model initially uses a MobileVNet2 model for differentiation between healthy & unhealthy plant types. The unhealthy plant images are further processed via an ensemble of VGGNet, ResNetV2, and Inception Net CNN models, which assists in identification of multiple disease types. These includes, blights, rots, fungi, spots & cankers. The VGGNet model was observed to efficiently classify between blights, rots and other diseases, while ResNetV2 was capable of efficiently identifying fungi and non-fungi disease types. These classifiers were cascaded with Inception Net CNN, which was able to categorize between spots & cankers, thereby assisting in identification of multiple diseases with high efficiency levels. The proposed model was compared w.r.t. accuracy, precision, and area under the curve (AUC), with standard deep learning techniques. Based on this comparison it was observed that the proposed model achieved 15.4% higher accuracy, 8.5% higher precision, and 5.9% higher AUC which assists in deploying the model for real-time scenarios. [ABSTRACT FROM AUTHOR]

Agriculture accounts for a substantial part of India's economy. Because the disease is a natural occurrence in plants, disease identification is critical in agriculture. It takes a significant amount of time as well as specialized effort. Using image processing, computer vision, and machine learning approaches provides an easy way and efficient method for detecting crop disease. In this approach, the Maize plant leaf is considered for experimentation. The images are taken from the Plant Village dataset with healthy and diseased leaves. This system contains three parts: Image preprocessing, Feature extraction, and classification. The images are preprocessed using the median filter to remove salt and pepper noise. The GLCM technique is used to extract the feature and classified using a Support vector machine and decision tree algorithms. The performance of the system is evaluated using the accuracy parameter. [ABSTRACT FROM AUTHOR]

Diseases of the crop and insect pests are among the main causes of crop loss which is dangerous for agricultural production. Disease recognition is more difficult on the field because it has a complex background and different light intensity. Initial recognition and pests identification can significantly reduce the financial losses caused by pests. Using convolution neural networks, crop diseases can be automatically identified. The identification of a disease is often based on signs such as lesions or spots found in various slices of a plant. The size, color and the amount of these spots can define in great detail the disease that has killed the crop. Public data set is used as a data set. Experimental environment Model works on is a biodiverse environment. [ABSTRACT FROM AUTHOR]

Pea is a plant with many benefits for food, feed, and fertilizer. In Indonesia, pea are widely grown in upland areas because they require optimum growth. In pea cultivation, a disease greatly affects the yield and quality of pea production, namely powdery mildew (Erysiphe pisi D.C). The controls commonly used to control that disease are crop rotation and the use of pesticides. The farmer recognizes that pesticide use is not environmentally friendly and bad for health. Therefore, it requires powdery mildew resistant varieties. The initial stage to achieve this goal is to obtain a powdery mildew resistant genotype is with selection. Indonesia has a high diversity of peas and has been cultivated for a long time, possibly segregation and mutation. Resistance screening to obtain resistant varieties in local genotypes Indonesian pea, the aims is to get information on resistance to powdery mildew and obtains resistant genotypes. This research was conducted in a greenhouse, using 95 genotypes pea. This experiment used a randomized block design (RBD) with 3 replications. The results obtained at the end of this research were 77 genotypes infected with powdery mildew, and 8 genotypes were not infected by powdery mildew. [ABSTRACT FROM AUTHOR]

"The best ever non– alcoholic drink which is consumed in India after water is tea ". India has privileged to stand in thetop listing World in tea production. In India, tea plantation contributes tremendously in the economic development. Nowadays,machine learning is playing significant role in the field of agriculture. With the help of machine learning in tea crop, which results in productivity enhancement and better classification of tea leaves, weather prediction, smart farming, crop disease detection, and to analyze the various effects of soil in future prediction. This paper aims at providing detailed information on various machine learning approaches proposed in the past five years by emphasizing the various techniques used in artificial intelligence in tea crop yield in various states of India and a broad where tea production has contributed in national income. [ABSTRACT FROM AUTHOR]

In recent digital era the production in the field of agriculture increases enormously. However, when the plants and vegetables suffer diseases it will affect crop productivity and lead to economic loss for farmers. Early disease detection and pest control are important for better quality and thereby better yield of crops. In country like India whose major population is involved in agriculture, it is very important to find the disease at early stages. Faster and precise prediction of plant disease could help reducing the losses. Significant advancement and developments in Deep Learning has given the opportunity to improve the performance and accuracy of detection of objects and disease recognition system. Automatic disease detection using image processing techniques provide fast and accurate results. The proposed system cares with a replacement approach to the development of disease recognition model, supported plant and vegetable image classification, by the utilization of deep convolutional neural networks. Advances in computer vision present a chance to expand and enhance a completely unique way of training and therefore the methodology used facilitates a fast and straight forward system implementation in practice. The proposed model enables to distinguish between diseased plants, vegetables from healthy ones in the present environment using CNN. Plants are the source of food on earth. Deep learning techniques are very successful in image classification problems. It will help with accurate prediction of disease with fast and clear data. [ABSTRACT FROM AUTHOR]

Since decade agriculture is the main source of food source. It plays a very vital role in food production. More than sixty percent of the population of earth depends on agriculture sources for their main supply. Various factors such as climate, rain, soil, and insects affects on growth of the plant. Every year more than 15-20 percent crop losses occurs due to plant disease. Potato and tomato mostly used in every kitchen as well as in various industrial productions. These crops are mostly affected with late and early blight disease. The late and inaccurate identification of disease decreases the productivity of the crops. The key purpose of our research is to discover plant disease at an early stage by using the Convolution Neural Network (CNN). For this research we considered Plantvillage dataset of 3580 tomato plant leaf images and 2150 potato plant leaf images. We used CNN customized models. For our research AlexNet model achieves 84.7% accuracy and VGG16 model achieves 96.5% accuracy for tomato and potato plant leaves respectively. [ABSTRACT FROM AUTHOR]

Plant diseases reduce agricultural productivity and, as a result, the economy. This involves the development of estimation techniques for the identification and assessment of plant diseases. If diagnosed early enough, fungal disease, one of the most common illness, may be managed by adopting suitable steps. The goal of this study is to create an expert system for predicting fungal diseases such as bacterial blight, poison hemlock, rot, and base rot/leaf disease are some of the diseases that might affect your plants. A multi-layered training algorithm model can be used to classify diseases. Bacterial blight, root rot, rust, and base rot/leaf blight are some of the diseases that might affect your plants. A mega training algorithm model can be used to classify diseases., which not only efficiently diagnoses plant illnesses but also dramatically increases productivity. The suggested method consists of three major steps: dataset preparation, a detection module, and also exploratory data analysis To begin, the soil sensors system at Sardarkrushinagar Dantiwada Agricultural University in Gujarat, India, captures real-time data as well as satellite data for types of sources and data in an agricultural field. After that, a thorough exploratory data analysis was carried out to get insight into the obtained data. Finally, plant diseases were predicted using the suggested machine learning model. The model outperforms numerous current approaches in terms of accuracy, according to the results of the experiments. The average accuracy in forecasting each illness was found to be greater than 98%. This research also shows that this technology may be used to identify plant diseases more quickly and at a lower cost. [ABSTRACT FROM AUTHOR]

Aim: The main objective of this study is to improve the accuracy in detecting plant leaf diseases by comparing novel recurrent neural networks and logistics regression. Materials and Methods: The sample size N=10 is implement for Recurrent neural network and logistic Regression. The final calculation for the sample are done using G power pretest 80%, threshold 0.05% and CI - 95%. Results: Result proved that Recurrent neural network got significant results with 88.20% accuracy compared to Logistic Regression with 69.96% accuracy. It is observed that significance difference was present between novel recurrent neural network and logistics regression, p= 0.00(2-tailed). Conclusion: Regression neural networks appear to perform significantly better as compared to Logistic Regression with better accuracy for detecting plant leaf disease. [ABSTRACT FROM AUTHOR]

The scope of the paper is to leverage the power of Machine Learning and Deep Learning to detect diseases in crops and to provide solutions for the diseases detected. Farmers usually detect diseases in the crops using their naked eyes, eventually leading them to make wrong predictions regarding diseases in the crops. They might use the wrong fertilizers or more than the usual dose, which could damage the plants, soil, and fields. Thus, this paper focuses on providing solutions for detecting diseases in crops and solutions for the diseases identified. Convolutional Neural Networks are used to identify various diseases in crops since it limits the number of parameters and thereby make the model more efficient. The said model is implemented by making a cross-platform code using Flutter with Dart as the programming language. [ABSTRACT FROM AUTHOR]