A focal loss and sequential analytics approach for liver disease classification and detection

The focal loss has demonstrated its effectiveness in many real-world applications such as object detection and image classification, but its theoretical understanding has been limited so far. In this paper, we first prove that the focal loss is classification-calibrated, i.e., its minimizer surely yields the Bayes-optimal classifier and thus the use of the focal loss in classification can be theoretically justified. However, we also prove a negative fact that the focal loss is not strictly proper, i.e., the confidence score of the classifier obtained by focal loss minimization does not match the true class-posterior probability. This may cause the trained classifier to give an unreliable confidence score, which can be harmful in critical applications. To mitigate this problem, we prove that there exists a particular closed-form transformation that can recover the true class-posterior probability from the outputs of the focal risk minimizer. Our experiments show that our proposed transformation successfully improves the quality of class-posterior probability estimation and improves the calibration of the trained classifier, while preserving the same prediction accuracy.

Hematopoietic cancer is a malignant transformation in immune system cells. Hematopoietic cancer is characterized by the cells that are expressed, so it is usually difficult to distinguish its heterogeneities in the hematopoiesis process. Traditional approaches for cancer subtyping use statistical techniques. Furthermore, due to the overfitting problem of small samples, in case of a minor cancer, it does not have enough sample material for building a classification model. Therefore, we propose not only to build a classification model for five major subtypes using two kinds of losses, namely reconstruction loss and classification loss, but also to extract suitable features using a deep autoencoder. Furthermore, for considering the data imbalance problem, we apply an oversampling algorithm, the synthetic minority oversampling technique (SMOTE). For validation of our proposed autoencoder-based feature extraction approach for hematopoietic cancer subtype classification, we compared other traditional feature selection algorithms (principal component analysis, non-negative matrix factorization) and classification algorithms with the SMOTE oversampling approach. Additionally, we used the Shapley Additive exPlanations (SHAP) interpretation technique in our model to explain the important gene/protein for hematopoietic cancer subtype classification. Furthermore, we compared five widely used classification algorithms, including logistic regression, random forest, k-nearest neighbor, artificial neural network and support vector machine. The results of autoencoder-based feature extraction approaches showed good performance, and the best result was the SMOTE oversampling-applied support vector machine algorithm consider both focal loss and reconstruction loss as the loss function for autoencoder (AE) feature selection approach, which produced 97.01% accuracy, 92.60% recall, 99.52% specificity, 93.54% F1-measure, 97.87% G-mean and 95.46% index of balanced accuracy as subtype classification performance measures.

India stands tall as one of the world’s largest rice-producing countries. A major part of Indian agriculture consists of rice as the principal food crop. Rice farming in India is challenged by diseases that can infest and destroy the crops causing detrimental losses to the farmers. Thus, the detection of diseases like “leaf smut”, “brown spot”, and “bacterial leaf blight” becomes a need of the hour. In this paper, we have proposed a way that can efficiently detect and classify these three diseases through image processing. The research can help in knowing if the rice crop is infested with the diseases or not. Images of the infected crop can be used in a real-life scenario and one can know if it is infested with any of the three diseases mentioned. The detection and classification of these diseases have been made possible using various state-of-the-art classification models, like support vector machine (SVM), random forest, KNN, naive Bayes, and neural network.

Hyperspectral image (HSI) classification has been extensively applied for analyzing remotely sensed images. HSI data consist of multiple bands that provide abundant spatial information. Convolutional neural networks (CNNs) have emerged as powerful deep learning methods for processing visual data. In recent work, CNNs have shown impressive results in HSI classification. In this paper, we propose a hierarchical neural network architecture called feature extraction with hybrid spectral CNN (FE-HybridSN) to extract superior spectral–spatial features. FE-HybridSN effectively captures more spectral–spatial information while reducing computational complexity. Considering the prevalent issue of class imbalance in experimental datasets (IP, UP, SV) and real-world hyperspectral datasets, we apply the focal loss to mitigate these problems. The focal loss reconstructs the loss function and facilitates effective achievement of the aforementioned goals. We propose a framework (FEHN-FL) that combines FE-HybridSN and the focal loss for HSI classification and then conduct extensive HSI classification experiments using three remote sensing datasets: Indian Pines (IP), University of Pavia (UP), and Salinas Scene (SV). Using cross-entropy loss as a baseline, we assess the hyperspectral classification performance of various backbone networks and examine the influence of different spatial sizes on classification accuracy. After incorporating focal loss as our loss function, we not only compare the classification performance of the FE-HybridSN backbone network under different loss functions but also evaluate their convergence rates during training. The proposed classification framework demonstrates satisfactory performance compared to state-of-the-art end-to-end deep-learning-based methods, such as 2D-CNN, 3D-CNN, etc.

This paper presents a novel two-stage artificial intelligence approach for liver disease detection and classification using standard Liver Function Test (LFT) parameters. While numerous studies have addressed binary classification of liver disease presence, few have attempted to identify specific liver conditions using only LFT data. Our approach combines a Neural Network for initial disease detection (95.9% accuracy) with a Support Vector Machine for specific disease classification (79% accuracy), enabling identification of hepatitis, fibrosis, and cirrhosis. This practical approach utilizes commonly available blood test parameters, ensuring its suitability for healthcare settings with limited resources while maintaining strong diagnostic accuracy

The Agriculture Industry has a momentous role in the development of any country. India facing heavy losses in crop production because of the plant diseases like fungal, bacterial, and viral. Indian farmers are still using traditional techniques for farming and especially the detection of diseases in a plant. Indian farmers are using naked eye observation to check the health of the plant and because of that sometimes wrong detection and classification of diseases cause heavy losses in crop production. It may be prevented using plant disease detection and classification techniques. In this paper, we present the survey and implementation of different plant disease detection and classification approach using machine learning and spectroscopy.

Crops’ production and quality of yields are heavily affected by crop diseases which cause adverse impacts on food security as well as economic losses. In India, agriculture is a prime source of income in most rural areas. Hence, there is an intense need to employ novel and accurate computer vision-based techniques for automatic crop disease detection and their classification so that prophylactic actions can be recommended in a timely manner. In literature, numerous computer vision-based techniques by utilizing divergent combinations of machine learning, deep learning, CNN, and various image-processing techniques along with their associated merits and demerits have already been discussed. In this study, we systematically reviewed recent research studies undertaken by a variety of scholars and researchers of fungal and bacterial plant disease detection and classification and summarized them based on vital parameters like type of crop utilized, deep learning/machine learning architecture used, dataset utilized for experiments, performance matrices, types of disease detected and classified, and highest accuracy achieved by the model. As per the analysis carried out, in the category of machine learning-based approaches, 70% of studies utilized real-field plant leaf images and 30% utilized laboratory condition plant leaf images for disease classification while in the case of deep learning-based approaches, 55% studied employed laboratory-conditioned images from the PlantVillage dataset, 25% utilized real-field images, and 20% utilized open image datasets. The average accuracy attained with deep learning-based approaches is quite higher at 98.8% as compared to machine learning-based approaches at 92.2%. In the case of deep learning-based methods, we also analyzed the performances of pretrained and training from scratch models that have been utilized in various studies for plant leaf disease classification. Pretrained models perform better with 99.64% classification accuracy compared to training from scratch models which achieved 98.64% average accuracy. We also highlighted some major issues encountered in the computer vision-based disease detection and classification approach used in literature and provided recommendations that will help and guide researchers to explore new dimensions in crop disease recognition.

As a very popular framework, federated learning can help heterogeneous participants cooperate training global models without the local data being exposed. It not only takes advantage of massive raw data, but also fundamentally protects the privacy of participants. An unavoidable challenge is that class imbalance brought by many participants will seriously affect the model performance and even damage the convergence. Introducing Focal loss to dynamically adjust the weight of samples in the training process is a good choice for relieving this issue. In our experiments, we find a trade-off between the convergence and the final accuracy of using focal loss and cross-entropy in traditional federated XGBoost. For this property, we propose hyperparametric linear and exponential sliding to combine the advantages of both methods. A complete experiment proved that sliding rather than direct cohesion was necessary. Meanwhile, linear sliding performs well than just using focal loss in three of the four class imbalances scenarios, and exponential sliding performs the best in all four scenarios. There are even two that exceed the cross-entropy with a finite number of communication rounds.

Deep learning-based models have been employed for the detection and classification of skin diseases through medical imaging. However, deep learning-based models are not effective for rare skin disease detection and classification. This is mainly due to the reason that rare skin disease has very a smaller number of data samples. Thus, the dataset will be highly imbalanced, and due to the bias in learning, most of the models give better performances. The deep learning models are not effective in detecting the affected tiny portions of skin disease in the overall regions of the image. This paper presents an attention-cost-sensitive deep learning-based feature fusion ensemble meta-classifier approach for skin cancer detection and classification. Cost weights are included in the deep learning models to handle the data imbalance during training. To effectively learn the optimal features from the affected tiny portions of skin image samples, attention is integrated into the deep learning models. The features from the finetuned models are extracted and the dimensionality of the features was further reduced by using a kernel-based principal component (KPCA) analysis. The reduced features of the deep learning-based finetuned models are fused and passed into ensemble meta-classifiers for skin disease detection and classification. The ensemble meta-classifier is a two-stage model. The first stage performs the prediction of skin disease and the second stage performs the classification by considering the prediction of the first stage as features. Detailed analysis of the proposed approach is demonstrated for both skin disease detection and skin disease classification. The proposed approach demonstrated an accuracy of 99% on skin disease detection and 99% on skin disease classification. In all the experimental settings, the proposed approach outperformed the existing methods and demonstrated a performance improvement of 4% accuracy for skin disease detection and 9% accuracy for skin disease classification. The proposed approach can be used as a computer-aided diagnosis (CAD) tool for the early diagnosis of skin cancer detection and classification in healthcare and medical environments. The tool can accurately detect skin diseases and classify the skin disease into their skin disease family.

H2K – A robust and optimum approach for detection and classification of groundnut leaf diseases

In the remote sensing, supervised deep learning has recently achieved great success of information extraction. However, it requires a large training data in order to effectively learn. In building change classifications, collecting such training data is an extremely expensive and time-consuming process, because of the rarity of positive classes. Learning of a data set including rare classes has two major problems, (1) class imbalance and (2) overfitting. In this study, we verify the effectiveness of focal loss in the building change classification. From our experimental results, not only the class imbalance but also the overfitting is affected the down-weighting effect of the focal loss. The focal loss automatically adjusts learning speed for each class.

In this paper, we study the problem of imbalanced text classification based on the pre-trained language models. We propose the Adaptable Focal Loss (AFL) method to solve this problem. Firstly, we use the word embeddings from the pre-trained models to construct the sentence level prior by the sum of the word embeddings in the sentence. Then, we extend the Focal Loss, which is widely used in the field of object detection, by replacing the task-special parameters with the scaled-softmax of the distance between the fine-tuned embeddings and the prior embeddings from the pre-trained models. By removing the task-special parameters in Focal Loss, not only can the parameters of arbitrary imbalanced proportion distribution be adjusted automatically according to the task, but also the sentences that are difficult to classify can be given a higher weight. Experimental results show that our methods can easily combine with the common classifier models and significantly improve their performances.KeywordsImbalanced text classificationPre-trained modelsAdaptive trainingFocal loss

In this paper, we propose a novel end-to-end learnable architecture based on Dense Convolutional Networks (DCN) for the classification of electrocardiogram (ECG) signals. This architecture is based on two main modules: the first is a generative module and the second is a discriminative one. The task of the generative module is to convert the one dimensional ECG signal into an image by means of fully connected, up-sampling, and convolution layers. The discriminative module takes as input the generated image and carries out feature learning and classification. To handle the data imbalance problem characterizing the ECG data, we propose to use the focal loss (FL) that is based on the idea of reshaping the standard cross-entropy loss such that it reduces the loss assigned to well-classified ECG beats. In the experiments, we validate the method using the well-known MIT-BIH arrhythmia database in four different scenarios, using four classes in the first scenario, five in the second and 12 in the third. Finally, supraventricular versus the other three and ventricular versus the other three from the scenario with four classes are used as the fourth scenario. The results obtained show that the method proposed here achieves a significant accuracy improvement over all previous state-of-the-art methods.

This paper proposes an improved deep residual neural network for the classification of breast cancer as either benign or malignant. Inspired by the success of using focal loss in object detection, we present a new focal loss for pathological image classification to solve the class imbalance problem encountered during training stage. Furthermore, we introduce a multi-scale acquisition structure into ResNet to get a larger range of receptive fields for each network layer and represent features at multiple scales. Data enhancement and migration learning are also used to optimize the initial parameters solving the problem of overfitting in the network. Experimental results show that our approach achieves higher accuracy of classification compared to previous methods.

As the rapid development of information and communication technology systems offers limitless access to data, the risk of malicious violations increases. A network intrusion detection system (NIDS) is used to prevent violations, and several algorithms, such as shallow machine learning and deep neural network (DNN), have previously been explored. However, intrusion detection with imbalanced data has usually been neglected. In this paper, a cost-sensitive neural network based on focal loss, called the focal loss network intrusion detection system (FL-NIDS), is proposed to overcome the imbalanced data problem. FL-NIDS was applied using DNN and convolutional neural network (CNN) to evaluate three benchmark intrusion detection datasets that suffer from imbalanced distributions: NSL-KDD, UNSW-NB15, and Bot-IoT. The results showed that the proposed algorithm using FL-NIDS in DNN and CNN architecture increased the detection of intrusions in imbalanced datasets compared to vanilla DNN and CNN in both binary and multiclass classifications.