Evolutionary and psychological effects in pre-evolutionary classifications

Planning the future of plant systematics: Report on a special colloquium at the Royal Netherlands Academy of Arts and Sciences.

Plant disease detection is a critical task in agriculture, essential for ensuring crop health and productivity. Traditional methods in this context are often labor-intensive and prone to errors, highlighting the need for automated solutions. While computer vision-based solutions have been successfully deployed in recent years for plant disease identification and localization tasks, these often operate independently, leading to suboptimal performance. It is essential to develop an integrated solution combining these two tasks for improved efficiency and accuracy. This research proposes the innovative Plant Disease Localization and Classification model based on Vision Transformer (PDLC-ViT), which integrates co-scale, co-attention, and cross-attention mechanisms and a ViT, within a Multi-Task Learning (MTL) framework. The model was trained and evaluated on the Plant Village dataset. Key hyperparameters, including learning rate, batch size, dropout ratio, and regularization factor, were optimized through a thorough grid search. Early stopping based on validation loss was employed to prevent overfitting. The PDLC-ViT model demonstrated significant improvements in plant disease localization and classification tasks. The integration of co-scale, co-attention, and cross-attention mechanisms allowed the model to capture multi-scale dependencies and enhance feature learning, leading to superior performance compared to existing models. The PDLC-ViT model evaluated on two public datasets achieved an accuracy of 99.97%, a Mean Average Precision (MAP) of 99.18%, and a Mean Average Recall (MAR) of 99.11%. These results underscore the model's exceptional precision and recall, highlighting its robustness and reliability in detecting and classifying plant diseases. The PDLC-ViT model sets a new benchmark in plant disease detection, offering a reliable and advanced tool for agricultural applications. Its ability to integrate localization and classification tasks within an MTL framework promotes timely and accurate disease management, contributing to sustainable agriculture and food security.

Precision agriculture is one of the solutions that has garnered significant attention from specialists recently, as it enables automatic detection and classification of plant and crop diseases, thereby increasing crop quality and yield, and it is also viewed as a tool for taking proactive measures to mitigate natural disasters, whether related to climate change or damage caused by certain insects. In this regard, our current study intends to develop a model for the automatic identification and classification of date palm disease caused by the Paralatoria Date Scale insect using deep learning techniques. A novel approach based on the combination of two deep learning algorithms is proposed. The first is a VGG16-based backbone, which was used as a feature extractor, and the second is an improved Fully Connected Neural Network, which was used as a classifier. The proposed model was trained using date palm leaflet RGB images of four categories, three of which are damaged to varying degrees, and one of which is healthy. A comparative study was conducted and demonstrated that the proposed model outperformed with an average accuracy of 98.06%, outpacing existing solution and some state-of-the-art methods. This study is meant to help the development and improvement of oasis agriculture, which relies heavily on palms and dates. It can help farmers and farm owners take preventative measures quickly and thus ensure a high-quality crop.

The agriculture industry significantly contributes to economic and population growth through the provision of high-quality food. Plant diseases decrease crop yields, which directly influences food production systems and leads to economic losses. Insufficient diagnosis and treatment of plant diseases can significantly affect agricultural productivity. Accurate identification is essential in order to prevent a severe decline in agricultural yield. Automatic detection models are crucial for accurate plant disease prediction and effective agricultural disease management. Deep Learning (DL) models are in great demand right now for identifying plant diseases because of how well they can anticipate and improve farmers’ crop yields. This study examines various DL algorithms for visual data-based plant disease detection and classification in great detail. Firstly, a brief overview is provided on various plant disease identification and classification systems developed by researchers, which utilize DL algorithms. Subsequently, a comprehensive analysis is undertaken to get deeper insights into the constraints of current algorithms and propose an innovative methodology for categorizing various forms of plant diseases, thereby contributing to the enhancement of agricultural output.

The detection of diseases in rice plants is an essential step in ensuring healthy crop growth and maximizing yields. A real-time and accurate plant disease detection technique can assist in the development of mitigation strategies to ensure food security on a large scale and economical rice crop protection. An accurate classification of rice plant diseases using DL and computer vision could create a foundation to achieve a site-specific application of agrochemicals. Image investigation tools are efficient for the early diagnosis of plant diseases and the continuous monitoring of plant health status. This article presents an Enhanced Sea Horse Optimization with Deep Learning-based Multimodal Fusion for Rice Plant Disease Detection and Classification (ESHODL-MFRPDC) technique. The proposed technique employed a DL-based fusion process with a hyperparameter tuning strategy to achieve an improved rice plant disease detection performance. The ESHODL-MFRPDC approach used Bilateral Filtering (BF)-based noise removal and contrast enhancement as a preprocessing step. Furthermore, Mayfly Optimization (MFO) with a Multi-Level Thresholding (MLT) based segmentation process was used to recognize the diseased portions in the leaf image. A fusion of three DL models was used for feature extraction, namely Residual Network (ResNet50), Xception, and NASNet. The Quasi-Recurrent Neural Network (QRNN) was used for the recognition of rice plant diseases, and its hyperparameters were set using the ESHO method. The performance of the ESHODL-MFRPDC method was validated using the rice leaf disease dataset from the UCI database. An extensive comparison study demonstrated the promising performance of the proposed method over others.

Dense convolutional neural networks based multiclass plant disease detection and classification using leaf images

Resnet-based modified red deer optimization with DLCNN classifier for plant disease identification and classification

A country's inventive growth is dependent on the agricultural sector. Agriculture, the foundation of all nations, offers food and raw resources. Agriculture is hugely important to humans as a food source. As a result, plant diseases detection has become a major concern. Traditional methods for identifying plant disease are available. However, agriculture professionals or plant pathologists have traditionally employed empty eye inspection to detect leaf disease. This approach of detecting plant leaf disease traditionally can be subjective, time-consuming, as well as expensive, and requires a lot of people and a lot of information about plant diseases. It is also possible to detect plant leaf diseases using an experimentally evaluated software solution. Currently, machine learning and deep learning are using in recent years. The agriculture sector is also not a exception for machine learning. In this paper, we applied "Convnets" for plant disease detection and classification. We collected a PlantViallge dataset from Kaggle. It contains images of 15 different classes of plant leaves of three different plants potato, pepper, tomato. We divided the dataset into three datasets and applied Convnets on three datasets. We achieved an accuracy of 98.3%,98.5%,95% for potato plant disease detection, pepper plant disease detection, tomato plant disease detection. Experimental results have shown that our model achieved a good accuracy rate for plant leaf disease detection and classification.

A review is given of the role of traditional morphometrics in plant systematics. The three most commonly used techniques of data analysis – Cluster Analysis, Principal Component Analysis and Discriminant Analysis – are discussed. The kinds of data that can be taken from palm specimens and the problems of using specimens as data sources are outlined. Published systematic studies of palms using traditional morphometrics are reviewed. More recent studies indicate that: hybrid zones between species may be common; infraspecific diversity is greater than previously suspected; there may be more than double the currently accepted number of species; and our current knowledge of morphological variation in palms is superficial. A procedure for scientific systematics is given, which incorporates traditional morphometric methods. © 2006 The Linnean Society of London, Botanical Journal of the Linnean Society, 2006, 151, 103–111.

Plant disease identification and classification play a pivotal role in improving the agricultural sector's efficiency and impact. Traditional laboratory testing methods have inherent limitations, including time-consuming processes and the poten-tial for misdiagnosis when relying on visual inspection alone. To address these challenges, the application of deep learning techniques, particularly convolutional neural networks (CNNs), has significantly reduced the need for manual, on-field efforts by utilizing cutting-edge technology. More recently, vision processing based transformers have emerged as a promising approach to enhance the accuracy of disease classification using high-dimensional visual data. Leveraging self-attention mechanisms and transformer architectures, these models have shown great potential for improving classification accuracy. In this research, we propose a vision transformer-based approach for classifying plant disease images. Our study utilizes the publicly available New Plant Diseases Dataset, comprising 70,295 training images and 17,572 validation images, encompassing 38 distinct plant disease and healthy classes. We fine-tune pre-trained vision transformer and VGG 16 models, achieving impressive validation accuracy rates of 99.16 % and 94 % respectively. Furthermore, we have developed a web-based application using the MobileNet model and deployed it using the Streamlit framework. This application provides a real-time classification of plant leaves, presenting the top three probabilities along with corresponding classes. It has demonstrated a validation accuracy rate of 98.72 % on the New Plant Diseases Dataset.

In recent years, plant disease detection and classification systems have helped in better farming practices. With the advent of artificial intelligence, agriculture automation has seen innovative methods to mitigate risk and losses in farming. In this paper use of deep learning for sugarcane, disease classification is analyzed. Around 1470 images with 5 categories have thoroughly experimented. Transfer learning methods like VGG-16 net and ResNet are compared for an identical set of input parameters. The results obtained show with the limited set of datasets, transfer learning schemes can provide good results. VGG-16 Net and ResNet have shown accuracy around 83.00 % & 91.00 %, respectively.

Plant species recognition is one of the important and difficult research areas. Many existing plant recognition and classification methods cannot meet the requirements of the automatic plant recognition system, due to the irregular, complex, and diverse nature of plant leaves. In this paper, a plant recognition approach is proposed by combining CUR decomposition and weighted kernel sparse representation (WKSR). The proposed method is different from traditional plant leaf classification methods. Instead of establishing a classification model by extracting the color, shape, and texture classifying features, the proposed method directly reduces the dimensionality of image and recognizes the test samples based on WKSR coefficients. In order to reduce the recognition time the proposed method uses class specific dictionary learning for sparse modeling. By using the comparison analysis, the proposed method is verified on four plant leaf datasets namely, Flavia leaf dataset, Swedish leaf dataset, Original leaf images and Leafsnap dataset with existing plant classification methods such as Random Forest, Support Vector Machine and K-Nearest Neighbors. The accuracy of the proposed method is 98% which is the best classification rate.

Farouji AE, Khodayari H. 2016. Evaluation of vegetation types in the West Zagros (Beiranshahr region as a case study), inLorestan Province, Iran. Biodiversita 17: 1-10. The accurate identification of plant communities and their distribution are classical tools for mapping and classification of plants. Plants are strongly sensitive against changing environmental conditions. Moreover, Iran has a special position in Asia which has been creating a diverse ecosystem. Close floristic studies are necessary for precise determination of diversity and uniformity. To determine plant species in different vegetation types in Beiran shahr region, modified multi-scale Whittaker plots were constructed. This studied area was about 20000 ha and located in Northwest to Southwest of Iran. Eighty-nine plots were made in different longitude and latitudes. The minimum and maximum heights were 1101 and 2489 m asl., respectively. Within each modified multi-scale plots, each species was explored. Of 608 species, 498 and 97 are belonging to dicotyledons and monocotyledons, and remained 13 species were Pteridophytes. As measured, Therophyte and Champhyte are the dominant and recessive form of life in studied area. Based on species of each plot and subplots, mean Jaccard's coefficient, number of unique species and mean unique species/plot were estimated for each vegetation type. It is obvious that there is a clear correlation between Slopes of the species-log area curve and Mean number of unique species per plot.

Nowadays, disease damage engenders maximal drawbacks in the farming sector, especially in rice crops, since it moderately decreases the yield plus minimizes health conditions of the paddy plant. During the period of intensive cultivation, the earliest and most accurate diagnosis of the rice plant diseases would help to limit damage, eventually resulting in environmental protection and an improved yield. Crop infections can be nematodes, fervid, fungal, or bacterial, which will deface the crop drastically. In this chapter, we present the plan of rice crop infection identification with the aid of leaf photographs. In this chapter, we propose a prototype for the image classification and detection of diseased rice plant leaves. This work is presented after an all-inclusive experimental investigation of multiple techniques that are used in image processing. The proposed work considers rice crop infection, explicitly brown spot, leaf blast, and bacterial leaf blight. The proposed work uses the traditional classification techniques, namely Decision Tree, Random Forest, Support Vector Machine, and Naive Bayes. Hence, to advance the accurateness of the classifier, various learning techniques are proposed to classify the rice plant diseases. It is easy to draw out knowledge from a smaller dataset, as the data size upsurge analysis of the data becomes demanding.

Agriculture serves as a fundamental pillar of Tunisia’s economy, providing employment and livelihood for a large segment of the population, thereby making it an essential sector for the country. Nevertheless, the sector faces challenges such as reduced agricultural output and quality due to factors like pesticide usage, water scarcity, climate change, and notably, plant diseases. These plant diseases represent one of the most significant threats to global agricultural productivity and quality. Traditional methods of plant disease detection heavily rely on expert identification, which can quickly cause delays in field management and crop disease control. The best strategy to manage these diseases and reduce crop loss is to put protective measures in place as soon as possible. To this purpose, machine learning and deep learning models-based method for the detection and classification of olive leaf disease is developed in order to improve the speed and precision of disease classification. In this study, we explore how machine learning and deep learning techniques may be used to improve agricultural practices and solve these issues. We specifically review the state-of-the-art literature on the use of deep learning and machine learning algorithms in diverse agricultural applications. We also presented a novel method for categorizing olive leaf diseases, by integrating deep learning architectures, VGG16, and fine tuning. Also, in this approach, we simulated a total of two distinct deep models utilizing pre-trained convolutional neural network architectures (VGG19 and VGG16) and along with four machine learning classifiers (RF, SVM, KNN and DT). In addition, we simulated a novel method for categorizing olive leaf diseases, by integrating deep learning architectures, VGG16, and fine tuning, our results findings showed that VGG16 with fine-tuning classifier is the best method for classification of healthy and diseased plant leaves. It achieves a testing accuracy score of 98% to beat the rest of the architectures.