Crop leaf disease detection and classification using machine learning and deep learning algorithms by visual symptoms: a review

<span lang="EN-US">A Quick and precise crop leaf disease detection is important to increasing agricultural yield in a sustainable manner. We present a comprehensive overview of recent research in the field of crop leaf disease prediction using image processing (IP), machine learning (ML) and deep learning (DL) techniques in this paper. Using these techniques, crop leaf disease prediction made it possible to get notable accuracies. This article presents a survey of research papers that presented the various methodologies, analyzes them in terms of the dataset, number of images, number of classes, algorithms used, convolutional neural networks (CNN) models employed, and overall performance achieved. Then, suggestions are prepared on the most appropriate algorithms to deploy in standard, mobile/embedded systems, Drones, Robots and unmanned aerial vehicles (UAV). We discussed the performance measures used and listed some of the limitations and future works that requires to be focus on, to extend real time automated crop leaf disease detection system.</span>

The Comparison of Tree-Based Ensemble Machine Learning for Classifying Public Datasets

This study aims to determine the best methods of tree-based ensemble machine learning to classify the datasets used, a total of 34 datasets. This study also wants to know the relationship between the number of records and columns of the test dataset with the number of estimators (trees) for each ensemble model, namely Random Forest, Extra Tree Classifier, AdaBoost, and Gradient Bosting. The four methods will be compared to the maximum accuracy and the number of estimators when tested to classify the test dataset. Based on the results of the experiments above, tree-based ensemble machine learning methods have been obtained and the best number of estimators for the classification of each dataset used in the study. The Extra Tree method is the best classifier method for binary-class and multi-class. Random Forest is good for multi-classes, and AdaBoost is a pretty good method for binary-classes. The number of rows, columns and data classes is positively correlated with the number of estimators. This means that to process a dataset with a large row, column or class size requires more estimators than processing a dataset with a small row, column or class size. However, the relationship between the number of classes and accuracy is negatively correlated, meaning that the accuracy will decrease if there are more classes for classification.

Implementation of content related to children’s rights in schools: How to teach them?—perceptions of future teachers in Serbia, Croatia, and Slovenia

This paper reports on the self-assessment of future teachers regarding their familiarity with the Convention on the Rights of the Child and their competency to teach about children’s rights and participation. A total of 561 future teachers were surveyed in Serbia, Croatia, and Slovenia. They all agreed that, during their studies, they did not acquire sufficient knowledge on children’s rights and participation and were not adequately prepared for teaching this content in schools. The authors further suggest an introduction of new study programs and a significant increase in the number of classes dealing with these topics in day-to-day school practice.

Two-Branch Attention Learning for Fine-Grained Class Incremental Learning

As a long-standing research area, class incremental learning (CIL) aims to effectively learn a unified classifier along with the growth of the number of classes. Due to the small inter-class variances and large intra-class variances, fine-grained visual categorization (FGVC) as a challenging visual task has not attracted enough attention in CIL. Therefore, the localization of critical regions specialized for fine-grained object recognition plays a crucial role in FGVC. Additionally, it is important to learn fine-grained features from critical regions in fine-grained CIL for the recognition of new object classes. This paper designs a network architecture named two-branch attention learning network (TBAL-Net) for fine-grained CIL. TBAL-Net can localize critical regions and learn fine-grained feature representation by a lightweight attention module. An effective training framework is proposed for fine-grained CIL by integrating TBAL-Net into an effective CIL process. This framework is tested on three popular fine-grained object datasets, including CUB-200-2011, FGVC-Aircraft, and Stanford-Car. The comparative experimental results demonstrate that the proposed framework can achieve the state-of-the-art performance on the three fine-grained object datasets.

Hierarchical Unsupervised Partitioning of Large Size Data and Its Application to Hyperspectral Images

In this paper, we propose a true unsupervised method to partition large-size images, where the number of classes, training samples, and other a priori information is not known. Thus, partitioning an image without any knowledge is a great challenge. This novel adaptive and hierarchical classification method is based on affinity propagation, where all criteria and parameters are adaptively calculated from the image to be partitioned. It is reliable to objectively discover classes of an image without user intervention and therefore satisfies all the objectives of an unsupervised method. Hierarchical partitioning adopted allows the user to analyze and interpret the data very finely. The optimal partition maximizing an objective criterion provides the number of classes and the exemplar of each class. The efficiency of the proposed method is demonstrated through experimental results on hyperspectral images. The obtained results show its superiority over the most widely used unsupervised and semi-supervised methods. The developed method can be used in several application domains to partition large-size images or data. It allows the user to consider all or part of the obtained classes and gives the possibility to select the samples in an objective way during a learning process.

Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification

In developing a few-shot classification model using deep networks, the limited number of samples in each class causes difficulty in utilizing statistical characteristics of the class distributions. In this paper, we propose a method to treat this difficulty by combining a probabilistic similarity based on intra-class statistics with a metric-based few-shot classification model. Noting that the probabilistic similarity estimated from intra-class statistics and the classifier of conventional few-shot classification models have a common assumption on the class distributions, we propose to apply the probabilistic similarity to obtain loss value for episodic learning of embedding network as well as to classify unseen test data. By defining the probabilistic similarity as the probability density of difference vectors between two samples with the same class label, it is possible to obtain a more reliable estimate of the similarity especially for the case of large number of classes. Through experiments on various benchmark data, we confirm that the probabilistic similarity can improve the classification performance, especially when the number of classes is large.

Power Profile and Thresholding Assisted Multi-Label NILM Classification

Next-generation power systems aim at optimizing the energy consumption of household appliances by utilising computationally intelligent techniques, referred to as load monitoring. Non-intrusive load monitoring (NILM) is considered to be one of the most cost-effective methods for load classification. The objective is to segregate the energy consumption of individual appliances from their aggregated energy consumption. The extracted energy consumption of individual devices can then be used to achieve demand-side management and energy saving through optimal load management strategies. Machine learning (ML) has been popularly used to solve many complex problems including NILM. With the availability of the energy consumption datasets, various ML algorithms have been effectively trained and tested. However, most of the current methodologies for NILM employ neural networks only for a limited operational output level of appliances and their combinations (i.e., only for a small number of classes). On the contrary, this work depicts a more practical scenario where over a hundred different combinations were considered and labelled for the training and testing of various machine learning algorithms. Moreover, two novel concepts—i.e., thresholding/occurrence per million (OPM) along with power windowing—were utilised, which significantly improved the performance of the trained algorithms. All the trained algorithms were thoroughly evaluated using various performance parameters. The results shown demonstrate the effectiveness of thresholding and OPM concepts in classifying concurrently operating appliances using ML.

On-campus students' remote use of Internet-based library services and resources : is there an impact on students' use of the library in-house

<p>With the increase of Internet access available to on-campus students and a growing number of Internet-based library services and resources available by remote access, ongoing research is necessary to monitor who the remote users are and whether remote use of the library has an impact on the use of the library in-house. This study surveyed on-campus students at the School of Education of the University of Waikato. At the beginning of April 2001 a questionnaire was distributed in a number of classes representing the different levels of the main teacher training programmes. Nearly half of all students enrolled in these programmes were surveyed. In line with findings of previous studies, this study found that a greater number of higher level and older students use the library resources and services by remote access. However, there was also evidence that younger students and students at lower levels increasingly use remote access to the library. The study did not find a clear pattern of how remote use of the library affects on-campus students' use of the library in-house, but identified some trends of remote user behaviour. There was evidence that some remote users are heavier users of the library in-house than on-campus students who use the library in-house only. On the other hand, this study also found that some remote users used the library less in-house as a result of having remote access.</p>

On-campus students' remote use of Internet-based library services and resources : is there an impact on students' use of the library in-house

<p>With the increase of Internet access available to on-campus students and a growing number of Internet-based library services and resources available by remote access, ongoing research is necessary to monitor who the remote users are and whether remote use of the library has an impact on the use of the library in-house. This study surveyed on-campus students at the School of Education of the University of Waikato. At the beginning of April 2001 a questionnaire was distributed in a number of classes representing the different levels of the main teacher training programmes. Nearly half of all students enrolled in these programmes were surveyed. In line with findings of previous studies, this study found that a greater number of higher level and older students use the library resources and services by remote access. However, there was also evidence that younger students and students at lower levels increasingly use remote access to the library. The study did not find a clear pattern of how remote use of the library affects on-campus students' use of the library in-house, but identified some trends of remote user behaviour. There was evidence that some remote users are heavier users of the library in-house than on-campus students who use the library in-house only. On the other hand, this study also found that some remote users used the library less in-house as a result of having remote access.</p>