Self-training semi-supervised classification based on density peaks of data

G2LCPS: End-to-end semi-supervised landmark prediction with global-to-local cross pseudo supervision for airway difficulty assessment

Difficult tracheal intubation is a major cause of anesthesia-related injuries, including brain damage and death. While deep neural networks have improved difficult airways (DA) predictions over traditional assessment methods, existing models are often black boxes, making them difficult to trust in critical medical settings. Traditional DA assessment relies on facial and neck features, but detecting neck landmarks is particularly challenging. This paper introduces a novel semi-supervised method for landmark prediction, namely G2LCPS, which leverages hierarchical filters and cross-supervised signals. The novelty lies in ensuring that the networks select good unlabeled samples at the image level and generate high-quality pseudo heatmaps at the pixel level for cross-pseudo supervision. The extended versions of the public AFLW, CFP, CPLFW and CASIA-3D FaceV1 face datasets and show that G2LCPS achieves superior performance compared to other state-of-the-art semi-supervised methods, achieving the lowest normalized mean error (NME) of 3.588 when only 1/8 of data is labeled. Notably, the inclusion of the local filter improved the prediction by at least 0.199 NME, whereas the global filter contributed an additional improvement of at least 0.216 NME. These findings underscore the effectiveness of our approach, particularly in scenarios with limited labeled data, and suggest that G2LCPS can significantly enhance the reliability and accuracy of DA predictions in clinical practice. The results highlight the potential of our method to improve patient safety by providing more trustworthy and precise predictions for difficult airway management.

A Critical Analysis of Deep Semi-Supervised Learning Approaches for Enhanced Medical Image Classification

Deep semi-supervised learning (DSSL) is a machine learning paradigm that blends supervised and unsupervised learning techniques to improve the performance of various models in computer vision tasks. Medical image classification plays a crucial role in disease diagnosis, treatment planning, and patient care. However, obtaining labeled medical image data is often expensive and time-consuming for medical practitioners, leading to limited labeled datasets. DSSL techniques aim to address this challenge, particularly in various medical image tasks, to improve model generalization and performance. DSSL models leverage both the labeled information, which provides explicit supervision, and the unlabeled data, which can provide additional information about the underlying data distribution. That offers a practical solution to resource-intensive demands of data annotation, and enhances the model’s ability to generalize across diverse and previously unseen data landscapes. The present study provides a critical review of various DSSL approaches and their effectiveness and challenges in enhancing medical image classification tasks. The study categorized DSSL techniques into six classes: consistency regularization method, deep adversarial method, pseudo-learning method, graph-based method, multi-label method, and hybrid method. Further, a comparative analysis of performance for six considered methods is conducted using existing studies. The referenced studies have employed metrics such as accuracy, sensitivity, specificity, AUC-ROC, and F1 score to evaluate the performance of DSSL methods on different medical image datasets. Additionally, challenges of the datasets, such as heterogeneity, limited labeled data, and model interpretability, were discussed and highlighted in the context of DSSL for medical image classification. The current review provides future directions and considerations to researchers to further address the challenges and take full advantage of these methods in clinical practices.

A self-training algorithm based on the two-stage data editing method with mass-based dissimilarity

A self-training algorithm is a classical semi-supervised learning algorithm that uses a small number of labeled samples and a large number of unlabeled samples to train a classifier. However, the existing self-training algorithms consider only the geometric distance between data while ignoring the data distribution when calculating the similarity between samples. In addition, misclassified samples can severely affect the performance of a self-training algorithm. To address the above two problems, this paper proposes a self-training algorithm based on data editing with mass-based dissimilarity (STDEMB). First, the mass matrix with the mass-based dissimilarity is obtained, and then the mass-based local density of each sample is determined based on its k nearest neighbors. Inspired by density peak clustering (DPC), this study designs a prototype tree based on the prototype concept. In addition, an efficient two-stage data editing algorithm is developed to edit misclassified samples and efficiently select high-confidence samples during the self-training process. The proposed STDEMB algorithm is verified by experiments using accuracy and F-score as evaluation metrics. The experimental results on 18 benchmark datasets demonstrate the effectiveness of the proposed STDEMB algorithm.

Semi-Supervised Deep Learning-Based Multi-component Spectral Calibration Modeling for UV-vis and Near-Infrared Spectroscopy without Information Loss

Spectral analysis is an important method for characterizing and identifying chemical species. However, quantitative spectral analysis of multiple chemical properties in the real world has always been a challenging problem due to the strong correlation, massive noise, and serious information overlapping of the spectral features. Here, we present a new semi-supervised spectral calibration method based on information lossless decoupling of spectral features named NICEM. To realize the separation and extraction of key latent features, the method uses the flow-based model non-linear independent component estimation (NICE) to learn the sample distribution. The spectral data information is transformed into independent latent variables obeying Gaussian distribution by the reversible structure of deep network without information loss, so as to find the essential properties and realize the feature nonlinear decomposition. Moreover, the association between the input latent feature variables and attributes is evaluated by the maximum mutual information coefficient to eliminate the adverse effects of irrelevant information in the latent variable space and mine key information. Since the latent variables are independent in each dimension, the NICEM method is easier to establish an accurate semi-supervised multi-component calibration model even for high overlapping and complex spectral data. The applicability of the proposed spectral modeling method is demonstrated by using three ultraviolet-visible and near-infrared spectral data sets with 15 physical and chemical properties including diesel fuels, corn, and multi-metal ions solution. Results show that the proposed NICEM method has the highest determination coefficient (R2) and significantly improves extrapolation compared with the seven state-of-the-art methods. The proposed method is intuitive because it obviates complex feature engineering and prior knowledge and is a promising spectral calibration tool for quantitative analysis in other spectroscopy applications.

A self-training subspace clustering algorithm based on adaptive confidence for gene expression data

Gene clustering is one of the important techniques to identify co-expressed gene groups from gene expression data, which provides a powerful tool for investigating functional relationships of genes in biological process. Self-training is a kind of important semi-supervised learning method and has exhibited good performance on gene clustering problem. However, the self-training process inevitably suffers from mislabeling, the accumulation of which will lead to the degradation of semi-supervised learning performance of gene expression data. To solve the problem, this paper proposes a self-training subspace clustering algorithm based on adaptive confidence for gene expression data (SSCAC), which combines the low-rank representation of gene expression data and adaptive adjustment of label confidence to better guide the partition of unlabeled data. The superiority of the proposed SSCAC algorithm is mainly reflected in the following aspects. 1) In order to improve the discriminative property of gene expression data, the low-rank representation with distance penalty is used to mine the potential subspace structure of data. 2) Considering the problem of mislabeling in self-training, a semi-supervised clustering objective function with label confidence is proposed, and a self-training subspace clustering framework is constructed on this basis. 3) In order to mitigate the negative impact of mislabeled data, an adaptive adjustment strategy based on gravitational search algorithm is proposed for label confidence. Compared with a variety of state-of-the-art unsupervised and semi-supervised learning algorithms, the SSCAC algorithm has demonstrated its superiority through extensive experiments on two benchmark gene expression datasets.

Prediction of Potentially Suitable Distributions of Codonopsis pilosula in China Based on an Optimized MaxEnt Model

Species distribution models are widely used in conservation biology and invasive biology. MaxEnt models are the most widely used models among the existing modeling tools. In the MaxEnt modeling process, the default parameters are used most often to build the model. However, these models tend to be overfit. Aiming at this problem, this study uses an optimized MaxEnt model to analyze the impact of past, present and future climate on the distributions of Codonopsis pilosula, an economic species, to provide a theoretical basis for its introduction and cultivation. Based on 264 distribution records and eight environmental variables, the potential distribution areas of C. pilosula in the last interglacial, middle Holocene and current periods and 2050 and 2070 were simulated. Combined with the percentage contribution, permutation importance, and jackknife test, the environmental factors affecting the suitable distribution area of this species were discussed. The results show that the parameters of the optimal model are: the regularization multiplier is 1.5, and the feature combination is LQHP (linear, quadratic, hinge, product). The main temperature factors affecting the distribution of C. pilosula are the annual mean temperature, mean diurnal range, and isothermality. The main precipitation factors are the precipitation seasonality, precipitation in the wettest quarter, and precipitation in the driest quarter, among which the annual average temperature contributes the most to the distribution area of this species. With climate warming, the suitable area of C. pilosula exhibits a northward expansion trend. It is estimated that in 2070, the suitable area of this species will expand to its maximum, reaching 2.5108 million square kilometers. The highly suitable areas of C. pilosula are mainly in Sichuan, Gansu, Shaanxi, Shanxi, and Henan Provinces. Our findings can be used to provide theoretical support related to avoiding the blind introduction of C. pilosula.

EEG-Based Driving Fatigue Detection Using a Two-Level Learning Hierarchy Radial Basis Function

Electroencephalography (EEG)-based driving fatigue detection has gained increasing attention recently due to the non-invasive, low-cost, and potable nature of the EEG technology, but it is still challenging to extract informative features from noisy EEG signals for driving fatigue detection. Radial basis function (RBF) neural network has drawn lots of attention as a promising classifier due to its linear-in-the-parameters network structure, strong non-linear approximation ability, and desired generalization property. The RBF network performance heavily relies on network parameters such as the number of the hidden nodes, number of the center vectors, width, and output weights. However, global optimization methods that directly optimize all the network parameters often result in high evaluation cost and slow convergence. To enhance the accuracy and efficiency of EEG-based driving fatigue detection model, this study aims to develop a two-level learning hierarchy RBF network (RBF-TLLH) which allows for global optimization of the key network parameters. Experimental EEG data were collected, at both fatigue and alert states, from six healthy participants in a simulated driving environment. Principal component analysis was first utilized to extract features from EEG signals, and the proposed RBF-TLLH was then employed for driving status (fatigue vs. alert) classification. The results demonstrated that the proposed RBF-TLLH approach achieved a better classification performance (mean accuracy: 92.71%; area under the receiver operating curve: 0.9199) compared to other widely used artificial neural networks. Moreover, only three core parameters need to be determined using the training datasets in the proposed RBF-TLLH classifier, which increases its reliability and applicability. The findings demonstrate that the proposed RBF-TLLH approach can be used as a promising framework for reliable EEG-based driving fatigue detection.

Developing Sustainable Classification of Diseases via Deep Learning and Semi-Supervised Learning

Disease classification based on machine learning has become a crucial research topic in the fields of genetics and molecular biology. Generally, disease classification involves a supervised learning style; i.e., it requires a large number of labelled samples to achieve good classification performance. However, in the majority of the cases, labelled samples are hard to obtain, so the amount of training data are limited. However, many unclassified (unlabelled) sequences have been deposited in public databases, which may help the training procedure. This method is called semi-supervised learning and is very useful in many applications. Self-training can be implemented using high- to low-confidence samples to prevent noisy samples from affecting the robustness of semi-supervised learning in the training process. The deep forest method with the hyperparameter settings used in this paper can achieve excellent performance. Therefore, in this work, we propose a novel combined deep learning model and semi-supervised learning with self-training approach to improve the performance in disease classification, which utilizes unlabelled samples to update a mechanism designed to increase the number of high-confidence pseudo-labelled samples. The experimental results show that our proposed model can achieve good performance in disease classification and disease-causing gene identification.

Label-less Learning for Emotion Cognition

In this paper, we propose a label-less learning for emotion cognition (LLEC) to achieve the utilization of a large amount of unlabeled data. We first inspect the unlabeled data from two perspectives, i.e., the feature layer and the decision layer. By utilizing the similarity model and the entropy model, this paper presents a hybrid label-less learning that can automatically label data without human intervention. Then, we design an enhanced hybrid label-less learning to purify the automatic labeled data. To further improve the accuracy of emotion detection model and increase the utilization of unlabeled data, we apply enhanced hybrid label-less learning for multimodal unlabeled emotion data. Finally, we build a real-world test bed to evaluate the LLEC algorithm. The experimental results show that the LLEC algorithm can improve the accuracy of emotion detection significantly.