Class Imbalance-Aware Deep Learning Approach for Apple Leaf Disease Recognition

Improved multi-scale inverse bottleneck residual network based on triplet parallel attention for apple leaf disease identification

The problem of class imbalance in machine learning occurs when there is a relatively big disproportional distribution of classes in the data for classification tasks. In many real-world domains, such as in healthcare, finance, and predictive maintenance, the number of data points of a less important class (usually the negative class) is much higher than the class of greater interest (usually the positive or target class). This affects the ability of many learning algorithms to find good classification models. To address that, many approaches for solving this problem have been proposed, prominently including ensemble methods integrated with sampling-based techniques. However, these methods are still prone to the negative effects of sampling-based techniques that alter class distributions via over-sampling or under-sampling, which can lead to overfitting or discarding useful data, respectively, and thus affect performance. In this paper, we propose a new data preprocessing sampling technique dubbed as (sBal) for ensemble methods for binary classification in the case of imbalanced datasets. Our proposed method first turns the imbalanced dataset into several balanced bins/bags. Then multiple base learners are induced on the balanced bags and finally, the classification results are combined using a specific ensemble rule. We evaluated the performance of our proposed method on 50 imbalanced real-world binary datasets and compared its performance with well-known ensemble methods that utilize data preprocessing techniques namely SMOTEBagging, SMOTEBoost, RUSBoost, and RAMOBoost. The results reveal that the proposed method brings considerable improvement in classification performance relevant to the compared methods. We performed statistical significance analysis using Friedman’s non-parametric statistical test with Bergman post-hoc test. The analysis showed that our method performed significantly better than the majority of the methods across many datasets, suggesting a better preprocessing approach than the ones used in compared methods. We also highlight possible extensions to the method that can improve its effectiveness.KeywordsData samplingEnsemble methodsImbalanced datasetsSplit balancingRAMOBoostSMOTEBaggingSMOTEBoost

Apple leaf diseases (ALD) pose a significant challenge to global apple production, and accurately identifying ALD is crucial for reducing pesticide use and improving fruit quality, particularly in the context of smart agriculture. However, traditional approaches rely on single-model feature extraction, failing to account for relationships between different tasks, which limits their applicability in the apple industry. To address this, we design an optimized convolutional neural network–vision transformer (CNN–ViT) hybrid framework named ResViT-AM, focusing on domain-specific enhancement rather than architectural novelty. Instead of proposing a completely new structure, this work refines existing CNN–Transformer paradigms through task-oriented feature fusion and adaptive attention weighting, tailored for apple leaf disease classification under complex orchard conditions. Using a weighted attention fusion mechanism, our model dynamically integrates features extracted by Residual Network 101 (ResNet-101) and vision transformer (ViT), combining proven architectures in a task-adaptive way rather than pursuing architectural innovation, blending the local convolutional details of Residual Network (ResNet) with the global contextual features of ViT. This approach enhances the model’s representation capability and allows parallel processing of multiple tasks, thereby saving training time and computational resources. Additionally, we evaluate on the public AppleLeaf dataset, which reflects real-world outdoor conditions. On its held-out test split, our model achieves 99.14% top-1 accuracy on the AppleLeaf test split, indicating promising performance under complex orchard conditions. Compared with representative convolutional baselines, ResViT-AM shows greater stability and adaptability on challenging cases, offering a competitive and practical solution for automated apple leaf disease diagnosis.

With the increasing rate and types of cyber attacks against information systems and communication infrastructures, many tools are needed to detect and mitigate against such attacks, for example, Intrusion Detection Systems (IDSs). Unfortunately, traditional Signature‐based IDSs (SIDSs) perform poorly against previously unseen adversarial attacks. Anomaly‐based IDSs (AIDSs) use Machine Learning (ML) and Deep Learning (DL) approaches to overcome these limitations. However, AIDS performance can be poor when trained on imbalanced datasets. To address the challenge of AIDS performance caused by these unbalanced training datasets, generative adversarial models are proposed to obtain adversarial attacks from one side and analyse their quality from another. According to extensive usage and reliability criteria for generative adversarial models in different disciplines, Generative Adversarial Networks (GANs) , Bidirectional GAN (BiGAN) , and Wasserstein GAN (WGAN) are employed to serve AIDS. The authors have extensively assessed their abilities and robustness to deliver high‐quality attacks for AIDS. AIDSs are constructed, trained, and tuned based on these models to measure their impacts. The authors have employed two datasets: NSL‐KDD and CICIDS‐2017 for generalisation purposes, where ML and DL approaches are utilised to implement AIDSs. Their results show that the WGAN model outperformed GANs and BiGAN models in binary and multiclass classifications for both datasets.

The class imbalance problem is encountered in real-world applications of machine learning and results in a classifier's suboptimal performance. Researchers have rigorously studied the resampling, algorithms, and feature selection approaches to this problem. No systematic studies have been conducted to understand how well these methods combat the class imbalance problem and which of these methods best manage the different challenges posed by imbalanced data sets. In particular, feature selection has rarely been studied outside of text classification problems. Additionally, no studies have looked at the additional problem of learning from small samples. This paper presents a first systematic comparison of the three types of methods developed for imbalanced data classification problems and of seven feature selection metrics evaluated on small sample data sets from different applications. We evaluated the performance of these metrics using area under the receiver operating characteristic (AUC) and area under the precision-recall curve (PRC). We compared each metric on the average performance across all problems and on the likelihood of a metric yielding the best performance on a specific problem. We examined the performance of these metrics inside each problem domain. Finally, we evaluated the efficacy of these metrics to see which perform best across algorithms. Our results showed that signal-to-noise correlation coefficient (S2N) and Feature Assessment by Sliding Thresholds (FAST) are great candidates for feature selection in most applications, especially when selecting very small numbers of features.

The majority of machine learning algorithms previously designed usually assume that their training sets are well-balanced, but data in the real-world is usually imbalanced. The class imbalance problem is pervasive and ubiquitous, causing trouble to a large segment of the data mining community. As the conventional machine learning algorithms have bad performance when they learn from imbalanced data sets, it is necessary to find solutions to machine learning on imbalanced data sets. This paper presents a novel Isomap-based hybrid re-sampling approach to improve the conventional SMOTE algorithm by incorporating the Isometric feature mapping algorithm (Isomap). Experiment results demonstrate that this hybrid re-sampling algorithm attains a performance superior to that of the re-sampling. It is clear that the Isomap method is an effective means to reduce the dimension of the re-sampling. This provides a new possible solution for dealing with the IDS classification.

We focus on a special category of pattern recognition problems that arise in cases when the set of training patterns is significantly biased towards a particular class of patterns. This is the so-called Class Imbalance Problem which hinders the performance of many standard classifiers. Specifically, the very essence of the class imbalance problem is unravelled by referring to a relevant literature review. It is shown that there exist a wide range of real-world applications involving extremely skewed (imbalanced) data sets and the class imbalance problem stems from the fact that the class of interest occupies only a negligible volume within the complete pattern space.

Class imbalance problem as a significant research problem has been recognized in classification In recent years, where by using the number of approach to rebalancing distributions of class such as; under-sampling or over-sampling for learning datasets to improve accuracy of classification, that give good performance. Many algorithms have been developed for classification, such as Back Propagation (BP) neural networks, decision tree, Bayesian networks etc., and have been used repeatedly in many fields. In this paper, to rebalancing distributions of class for imbalanced Malaria dataset to detect infected and uninfected people by equal percentage we proposed approach Deep Convolutional Generative Adversarial Network (DCGAN) based on the O.S. technique, which are generate the synthetic samples for the minority class for imbalanced Malaria dataset and achieve a balance ratio between classes of majority and minority 100% for imbalanced Malaria dataset. As well as used Deep Learning, applied by using Convolutional Neural Network (CNN). The goal of CNN is to prove the validity of the proposed approach by firstly, will be train the imbalanced Malaria dataset and results are tested before using proposed approach. Secondly, will be training balanced Malaria dataset and results are tested after using proposed approach and comparison between them.

Boosting the oversampling methods based on differential evolution strategies for imbalanced learning

Objective: Machine learning algorithms are based upon the assumption that data are balanced and so they do not provide good results in imbalanced datasets. This study aimed to explain the methods to be used for fitting a highly accurate model which better classifies the class of interest in imbalanced datasets with the class having a lower number of samples. Material and Methods: The study was planned as a methodological research. There are several weighting methods to calculate the class weight. This study included 4 most frequently used weighting methods. These are inverse of number of samples, inverse of square root of number of samples, effective number of examples and sample based class weight methods. In our study, 4 different class weighting methods were used on random forest and support vector machine, and it was explained how those methods affected class-based performances and the overall performance. Results: In simulated datasets, the best performance was achieved using the using the inverse of square root of number of samples class weighting method both on random forest and support vector machine. In real dataset, the best performance was achieved using the sample based class weight class weighting method on support vector machine. Conclusion: It was seen that all of the class weighting methods used in both machine learning methods were found to increase the performance of the class where recurrence was seen, therefore increasing the overall performance. It has been seen how effective the class weighting method is in dealing with the class imbalance problem.

The scenario of classification with imbalanced data-sets has supposed a serious challenge for researchers along the last years. The main handicap is related to the large number of real applications in which one of the classes of the problem has a few number of examples in comparison with the other class, making it harder to be correctly learnt and, what is most important, this minority class is usually the one with the highest interest. In order to address this problem, two main methodologies have been proposed for stressing the significance of the minority class and for achieving a good discrimination for both classes, namely preprocessing of instances and cost-sensitive learning. The former rebalances the instances of both classes by replicating or creating new instances of the minority class (oversampling) or by removing some instances of the majority class (undersampling); whereas the latter assumes higher misclassification costs with samples in the minority class and seek to minimize the high cost errors. Both solutions have shown to be valid for dealing with the class imbalance problem but, to the best of our knowledge, no comparison between both approaches have ever been performed. In this work, we carry out a full exhaustive analysis on this two methodologies, also including a hybrid procedure that tries to combine the best of these models. We will show, by means of a statistical comparative analysis developed with a large collection of more than 60 imbalanced data-sets, that we cannot highlight an unique approach among the rest, and we will discuss as a potential research line the use of hybridizations for achieving better solutions to the imbalanced data-set problem.

Self-training convolutional autoencoder for consumer characteristics identification with imbalance datasets

Learning from imbalanced data has conventionally been conducted on stationary data sets. Recently, there have been several methods proposed for mining imbalanced data streams, in which training data is read in consecutive data chunks. Each data chunk is considered as a conventional imbalanced data set, making it easy to apply sampling methods to balance data chunks. However, one drawback of chunk-based learning methods is that the update of classification models is delayed until a full data chunk is received. Therefore, this paper proposes a new method for online learning from imbalanced data streams, which uses naive Bayes as the base learner. To deal with the problem of class imbalance, a new training instance from the minority class is always involved in learning, but one from the majority class is only used with a small probability. In effect, this method corresponds to an under-sampling technique on imbalanced data streams. We show the effectiveness of the proposed online learning method on ten UCI data sets of various domains. Problems in the performance of naive Bayes on imbalanced data sets are also discussed.

Background: Class imbalance is often discussed as a strenuous task in the realm of sentiment analysis. In an imbalanced classification, few minority class instances are unable to provide sufficient information, therefore direct learning from an unbalanced dataset can produce unsatisfactory results. This work aims to address the problem of class imbalance. Methods: At primary level this study uses a novel Synthetic Minority Oversampling Technique (SMOTE) for balancing the dataset and then proposes an ensemble model, named Ensemble Bagging Support Vector Machine (EBSVM) for opinion mining. To measure the performance of the particular approach, numerous analyses are conducted on both imbalanced and balanced datasets. Then the work compares the effectiveness of the suggested model with three base classifiers (Nave Bayes (NB), Decision Tree (DT), and Support Vector Machine (SVM)). The customer reviews for restaurants is chose as the dataset for this work. Accuracy, precision, recall and F-measure are used as metrics for evaluation. Findings: According to the results, the suggested EBSVM model excels all other individual classifiers with the imbalanced and SMOTE balanced dataset. The balanced EBSVM classifier improves the imbalanced EBSVM Classifier in terms of accuracy. Precision, recall and F-measure of the minority class in the imbalanced classifiers have been improved in balanced Classifiers. Novelty: The performance of opinion mining classifiers for imbalanced and balanced datasets is evaluated in this paper. The work examines not only general opinions, but also specific aspects such as food, service, ambiance, quality, and price. Comparing the suggested model with existing classification algorithms in the literature, it has found that it outperformed the other models. Keywords: Bagging; Accuracy; Ensemble; Precision; Recall; Fmeasure

Nowadays, dealing with imbalanced data represents a great challenge in data mining as well as in machine learning task. In this investigation, we are interested in the problem of class imbalance in Authorship Attribution (AA) task, with specific application on Arabic text data. This article proposes a new hybrid approach based on Principal Components Analysis (PCA) and Synthetic Minority Over-sampling Technique (SMOTE), which considerably improve the performances of authorship attribution on imbalanced data. The used dataset contains 7 Arabic books written by 7 different scholars, which are segmented into text segments of the same size, with an average length of 2900 words per text. The obtained results of our experiments show that the proposed approach using the SMO-SVM classifier, presents high performance in terms of authorship attribution accuracy (100%), especially with starting character-bigrams. In addition, the proposed method appears quite interesting by improving the AA performances in imbalanced datasets, mainly with function words.