Adaptive Classification Research Articles

Enhancing Evolving Domain Generalization through Dynamic Latent Representations

Domain generalization is a critical challenge for machine learning systems. Prior domain generalization methods focus on extracting domain-invariant features across several stationary domains to enable generalization to new domains. However, in non-stationary tasks where new domains evolve in an underlying continuous structure, such as time, merely extracting the invariant features is insufficient for generalization to the evolving new domains. Nevertheless, it is non-trivial to learn both evolving and invariant features within a single model due to their conflicts. To bridge this gap, we build causal models to characterize the distribution shifts concerning the two patterns, and propose to learn both dynamic and invariant features via a new framework called Mutual Information-Based Sequential Autoencoders (MISTS). MISTS adopts information theoretic constraints onto sequential autoencoders to disentangle the dynamic and invariant features, and leverage an adaptive classifier to make predictions based on both evolving and invariant information. Our experimental results on both synthetic and real-world datasets demonstrate that MISTS succeeds in capturing both evolving and invariant information, and present promising results in evolving domain generalization tasks.

Global annual wetland dataset at 30 m with a fine classification system from 2000 to 2022

Wetlands play a key role in maintaining ecological balance and climate regulation. However, due to the complex and variable spectral characteristics of wetlands, there are no publicly available global 30-meter time-series wetland dynamic datasets at present. In this study, we present novel global 30 m annual wetland maps (GWL_FCS30D) using time-series Landsat imagery on the Google Earth Engine platform, covering the period of 2000–2022 and containing eight wetland subcategories. Specifically, we make full use of our prior globally distributed wetland training sample pool, and adopt the local adaptive classification and spatiotemporal consistency checking algorithm to generate annual wetland maps. The GWL_FCS30D maps were found to achieve an overall accuracy and Kappa coefficient of 86.95 ± 0.44% and 0.822, respectively, in 2020, and show great temporal variability in the United States and the European Union. We expect the dataset would provide vital support for wetland ecosystems protection and sustainable development.

Research on a Cross-Domain Few-Shot Adaptive Classification Algorithm Based on Knowledge Distillation Technology.

With the development of deep learning and sensors and sensor collection methods, computer vision inspection technology has developed rapidly. The deep-learning-based classification algorithm requires the acquisition of a model with superior generalization capabilities through the utilization of a substantial quantity of training samples. However, due to issues such as privacy, annotation costs, and sensor-captured images, how to make full use of limited samples has become a major challenge for practical training and deployment. Furthermore, when simulating models and transferring them to actual image scenarios, discrepancies often arise between the common training sets and the target domain (domain offset). Currently, meta-learning offers a promising solution for few-shot learning problems. However, the quantity of supporting set data on the target domain remains limited, leading to limited cross-domain learning effectiveness. To address this challenge, we have developed a self-distillation and mixing (SDM) method utilizing a Teacher-Student framework. This method effectively transfers knowledge from the source domain to the target domain by applying self-distillation techniques and mixed data augmentation, learning better image representations from relatively abundant datasets, and achieving fine-tuning in the target domain. In comparison with nine classical models, the experimental results demonstrate that the SDM method excels in terms of training time and accuracy. Furthermore, SDM effectively transfers knowledge from the source domain to the target domain, even with a limited number of target domain samples.

A Review on Automated Sleep Study.

In recent years, research on automated sleep analysis has witnessed significant growth, reflecting advancements in understanding sleep patterns and their impact on overall health. This review synthesizes findings from an exhaustive analysis of 87 papers, systematically retrieved from prominent databases such as Google Scholar, PubMed, IEEE Xplore, and ScienceDirect. The selection criteria prioritized studies focusing on methods employed, signal modalities utilized, and machine learning algorithms applied in automated sleep analysis. The overarching goal was to critically evaluate the strengths and weaknesses of the proposed methods, shedding light on the current landscape and future directions in sleep research. An in-depth exploration of the reviewed literature revealed a diverse range of methodologies and machine learning approaches employed in automated sleep studies. Notably, K-Nearest Neighbors (KNN), Ensemble Learning Methods, and Support Vector Machine (SVM) emerged as versatile and potent classifiers, exhibiting high accuracies in various applications. However, challenges such as performance variability and computational demands were observed, necessitating judicious classifier selection based on dataset intricacies. In addition, the integration of traditional feature extraction methods with deep structures and the combination of different deep neural networks were identified as promising strategies to enhance diagnostic accuracy in sleep-related studies. The reviewed literature emphasized the need for adaptive classifiers, cross-modality integration, and collaborative efforts to drive the field toward more accurate, robust, and accessible sleep-related diagnostic solutions. This comprehensive review serves as a solid foundation for researchers and practitioners, providing an organized synthesis of the current state of knowledge in automated sleep analysis. By highlighting the strengths and challenges of various methodologies, this review aims to guide future research toward more effective and nuanced approaches to sleep diagnostics.

Multiple Artifact Detection Based on Adaptive Scalp Region Selection and Classifier Fusion

Multiple Artifact Detection Based on Adaptive Scalp Region Selection and Classifier Fusion

GLC_FCS30D: the first global 30 m land-cover dynamics monitoring product with a fine classification system for the period from 1985 to 2022 generated using dense-time-series Landsat imagery and the continuous change-detection method

Abstract. Land-cover change has been identified as an important cause or driving force of global climate change and is a significant research topic. Over the past few decades, global land-cover mapping has progressed; however, long-time-series global land-cover-change monitoring data are still sparse, especially those at 30 m resolution. In this study, we describe GLC_FCS30D, a novel global 30 m land-cover dynamics monitoring dataset containing 35 land-cover subcategories and covering the period 1985–2022 in 26 time steps (maps were updated every 5 years before 2000 and annually after 2000). GLC_FCS30D has been developed using continuous change detection and all available Landsat imagery based on the Google Earth Engine platform. Specifically, we first take advantage of the continuous change-detection model and the full time series of Landsat observations to capture the time points of changed pixels and identify the temporally stable areas. Then, we apply a spatiotemporal refinement method to derive the globally distributed and high-confidence training samples from these temporally stable areas. Next, local adaptive classification models are used to update the land-cover information for the changed pixels, and a temporal-consistency optimization algorithm is adopted to improve their temporal stability and suppress some false changes. Further, the GLC_FCS30D product is validated using 84 526 globally distributed validation samples from 2020. It achieves an overall accuracy of 80.88 % (±0.27 %) for the basic classification system (10 major land-cover types) and 73.04 % (±0.30 %) for the LCCS (Land Cover Classification System) level-1 validation system (17 LCCS land-cover types). Meanwhile, two third-party time-series datasets used for validation from the United States and Europe Union are also collected for analyzing accuracy variations, and the results show that GLC_FCS30D offers significant stability in terms of variation across the accuracy time series and achieves mean accuracies of 79.50 % (±0.50 %) and 81.91 % (±0.09 %) over the two regions. Lastly, we draw conclusions about the global land-cover-change information from the GLC_FCS30D dataset; namely, that forest and cropland variations have dominated global land-cover change over past 37 years, the net loss of forests reached about 2.5 million km2, and the net gain in cropland area is approximately 1.3 million km2. Therefore, the novel dataset GLC_FCS30D is an accurate land-cover-dynamics time-series monitoring product that benefits from its diverse classification system, high spatial resolution, and long time span (1985–2022); thus, it will effectively support global climate change research and promote sustainable development analysis. The GLC_FCS30D dataset is available via https://doi.org/10.5281/zenodo.8239305 (Liu et al., 2023).

Facial mask-wearing prediction and adaptive gender classification using convolutional neural networks

The world has lived an exceptional time period caused by the Coronavirus pandemic. To limit Covid-19 propagation, governments required people to wear a facial mask outside. In facial data analysis, mask-wearing on the human face creates predominant occlusion hiding the important oral region and causing more challenges for human face recognition and categorisation. The appropriation of existing solutions by taking into consideration the masked context is indispensable for researchers. In this paper, we propose an approach for mask-wearing prediction and adaptive facial human-gender classification. The proposed approach is based on convolutional neural networks (CNNs). Both mask-wearing and gender information are crucial for various possible applications. Experimentation shows that mask-wearing is very well detectable by using CNNs and justifies its use as a prepossessing step. It also shows that retraining with masked faces is indispensable to keep up gender classification performances. In addition, experimentation proclaims that in a controlled face-pose with acceptable image quality' context, the gender attribute remains well detectable. Finally, we show empirically that the adaptive proposed approach improves global performance for gender prediction in a mixed context.

Hybrid SSVEP + P300 brain-computer interface can deal with non-stationary cerebral responses with the use of adaptive classification

IntroductionThe non-stationarity of electroencephalograms (EEG) has a substantial effect on the performance of classifiers in brain-computer interface (BCI) systems. To tackle this challenge, an adaptable version of the linear discriminant analysis (LDA) classifier was proposed. Accuracy is crucial when using BCIs for neurorestorative tasks or memory improvement. The accurate comprehension of brain responses facilitates more focused interventions, which may improve neurorestorative outcomes. BCIs equipped with adaptive classifiers are useful for personalizing therapies to individual requirements and for improving neurorestorative processes. Notably, neurorestorative interventions that yield consistent, accurate, and reliable outcomes are more likely to inspire trust and elicit satisfaction in users. MethodsThe proposed classifier continuously modified its parameters in accordance with EEG signals. The covariance matrix and mean values for each pair of classes were the updating parameters. The proposed classifier modified the model parameters by prioritizing current signal data over older signal history. The proposed classifier was tested using a hybrid SSVEP + P300 BCI system. Results and conclusionsThe proposed classifier had an estimated classification accuracy of 97.4%, and was more effective than pooled mean LDA and conventional multiclass LDA classifiers. Increased classification accuracy may increase the responsiveness of neurorestorative interventions and increase the usefulness of BCIs in neurorestoration.

Multi-label classification with imbalanced classes by fuzzy deep neural networks

Multi-label classification is an advantageous technique for managing uncertainty in classification problems where each data instance is associated with several labels simultaneously. Such situations are frequent in real-world scenarios, where decisions rely on imprecise or noisy data and adaptable classification methods are preferred. However, the problem of class imbalance represents a common characteristic of several multi-label datasets, in which the distribution of samples and their corresponding labels is non-uniform across the data space. In this paper, we propose a multi-label classification approach utilizing fuzzy logic in order to deal with the class imbalance problem. To eliminate the need for an expert to determine the logical rules of inference, deep neural networks are adopted, which have proven to be exceptionally effective for such problems. By combining both fuzzy inference systems and deep neural networks, the strengths and weaknesses of each approach can be mitigated. As a further development, a symbolic representation of time series is put in place to reduce data dimensionality and speed up the training procedure. This allows for more flexibility in model application, in particular with respect to time constraints arising from the causality of observed time series. Tests carried out on a multi-label classification dataset related to the current and voltage profiles of several household appliances show that the proposed model outperforms four baseline models for time series classification.

Adaptive fuzzy-evidential classification based on association rule mining

As one of the most promising classification approaches, association classification (AC) integrates data classification and association discovery techniques for generating a compact set of classification association rules. Recently, the fuzzy set and evidence theories are successively applied into AC in order to improve the classification performance in terms of accuracy and interpretability. However, from the perspectives of applicability and universality, there still exists two important issues in the current AC framework. On one hand, several key parameters, such as the number of fused rules in classification and the minimum support threshold in association discovery, are difficult to be accurately predefined in practice. On the other hand, the fixed grid-based fuzzy partition is not benefit to adapt for those datasets with large number of features. In this paper, an association rule-based adaptive fuzzy-evidential classification framework (AR-AFEC) is developed for overcoming the above limitations. To do so, an optimal rule fusion strategy and a dynamic minimum support threshold setting scheme are proposed for adaptively learning the parameters during classification and association mining respectively. In addition, an entropy-based trapezoidal fuzzy partition technique is proposed to adaptively obtain the fuzzy sets defined on each continuous feature domain. Experiments on 26 benchmark datasets and a human activity recognition application demonstrate that the proposal can achieve better accuracy than some state-of-the-art rule-based classification approaches, using less rules with more general structure.

An efficient epileptic seizure detection by classifying focal and non-focal EEG signals using optimized deep dual adaptive CNN-HMM classifier

An efficient epileptic seizure detection by classifying focal and non-focal EEG signals using optimized deep dual adaptive CNN-HMM classifier

Comparison of Multivariate Adaptive Regression Splines and Classification Regression Tree for Prediction of Body Weight of Bapedi Sheep

Comparison of Multivariate Adaptive Regression Splines and Classification Regression Tree for Prediction of Body Weight of Bapedi Sheep

Anticipative Bayesian classification for data streams with verification latency

Most of the existing adaptive classification algorithms in non-stationary data streams require recent labelled data for their updates. Such recent labels are often missing. For stream classification under verification latency only few approaches exist. Most of them assume clustered data or homogeneous drift in all features, which limits their applicability. We address this by proposing Anticipative Bayesian stream Classifier (ABClass), an approach that is capable of integrating and automatically selecting from different components. In its Bayesian classification framework, ABClass combines density estimation techniques, extended to extrapolate drift patterns over time, with unsupervised parameter tuning and unsupervised model selection. ABClass allows for multivariate density estimation and extrapolation techniques. In this work, we assume conditional independence between features given the class label for modelling feature-specific drift patterns. ABClass is generative and can also be used for explaining and visualising concept drift patterns. It is generic, making it easy to include further types of drift models, both for the class-conditional feature distribution and for the class prior distribution. The experimental evaluation on several real-world data streams shows its competitiveness compared to other state-of-the-art approaches. ABClass is in most cases ten- to hundred-times faster than its competitors, both for model fitting and for prediction.

Adaptive LDA Classifier Enhances Real-Time Control of an EEG Brain-Computer Interface for Decoding Imagined Syllables.

Brain-Computer Interfaces (BCIs) aim to establish a pathway between the brain and an external device without the involvement of the motor system, relying exclusively on neural signals. Such systems have the potential to provide a means of communication for patients who have lost the ability to speak due to a neurological disorder. Traditional methodologies for decoding imagined speech directly from brain signals often deploy static classifiers, that is, decoders that are computed once at the beginning of the experiment and remain unchanged throughout the BCI use. However, this approach might be inadequate to effectively handle the non-stationary nature of electroencephalography (EEG) signals and the learning that accompanies BCI use, as parameters are expected to change, and all the more in a real-time setting. To address this limitation, we developed an adaptive classifier that updates its parameters based on the incoming data in real time. We first identified optimal parameters (the update coefficient, UC) to be used in an adaptive Linear Discriminant Analysis (LDA) classifier, using a previously recorded EEG dataset, acquired while healthy participants controlled a binary BCI based on imagined syllable decoding. We subsequently tested the effectiveness of this optimization in a real-time BCI control setting. Twenty healthy participants performed two BCI control sessions based on the imagery of two syllables, using a static LDA and an adaptive LDA classifier, in randomized order. As hypothesized, the adaptive classifier led to better performances than the static one in this real-time BCI control task. Furthermore, the optimal parameters for the adaptive classifier were closely aligned in both datasets, acquired using the same syllable imagery task. These findings highlight the effectiveness and reliability of adaptive LDA classifiers for real-time imagined speech decoding. Such an improvement can shorten the training time and favor the development of multi-class BCIs, representing a clear interest for non-invasive systems notably characterized by low decoding accuracies.

Quantitative Forecasting of Malaria Parasite Using Machine Learning Models: MLR, ANN, ANFIS and Random Forest.

Malaria continues to be a major barrier to socioeconomic development in Africa, where its death rate is over 90%. The predictive power of many machine learning models-such as multi-linear regression (MLR), artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFISs) and Random Forest classifier-is investigated in this study using data from 2207 patients. The dataset was reduced from the initial dataset of thirty-two criteria samples to fifteen. Assessment measures such as the root mean square error (RMSE), mean square error (MSE), coefficient of determination (R2), and adjusted correlation coefficient R were used. ANFIS, Random Forest, MLR, and ANN are among the models. After training, ANN outperforms ANFIS (97%), MLR (92%), and Random Forest (68%) with the greatest R (99%) and R2 (99%), respectively. The testing stage confirms the superiority of ANN. The paper also presents a statistical forecasting sheet with few errors and excellent accuracy for MLR models. When the models are assessed with Random Forest, the latter shows the least results, thus broadening the modeling techniques and offering significant insights into the prediction of malaria and healthcare decision making. The outcomes of using machine learning models for precise and efficient illness prediction add to an expanding body of knowledge, assisting healthcare systems in making better decisions and allocating resources more effectively.

A Novel Approach Utilizing Domain Adversarial Neural Networks for the Detection and Classification of Selective Sweeps.

The identification and classification of selective sweeps are of great significance for improving the understanding of biological evolution and exploring opportunities for precision medicine and genetic improvement. Here, a domain adaptation sweep detection and classification (DASDC) method is presented to balance the alignment of two domains and the classification performance through a domain-adversarial neural network and its adversarial learning modules. DASDC effectively addresses the issue of mismatch between training data and real genomic data in deep learning models, leading to a significant improvement in its generalization capability, prediction robustness, and accuracy. The DASDC method demonstrates improved identification performance compared to existing methods and excels in classification performance, particularly in scenarios where there is a mismatch between application data and training data. The successful implementation of DASDC in real data of three distinct species highlights its potential as a useful tool for identifying crucial functional genes and investigating adaptive evolutionary mechanisms, particularly with the increasing availability of genomic data.

Adaptive Pair-Weight Vector Projection Classifier for Semi-Supervised Classification

Manifold regularization is a popular technology based on graph theory and has been widely applied to nonparallel hyperplane classifiers for semi-supervised learning. However, these classifiers adopt the fixed similarity matrix that may be sensitive to noises and outliers. Thus, we propose a novel nonparallel hyperplane classifier, named the adaptive pair-weight vector projection (APVP) classifier, for semi-supervised classification tasks. The proposed APVP unifies projection learning and graph construction into a general framework. For projection learning, APVP achieves two projection vectors by solving the pair-wise optimization problems in which we need to simultaneously maximize the between-class scatter of data and minimize both the within-class scatter of data and the adaptive manifold regularization. For graph construction, the adaptive similarity matrix is constructed during the procedure of optimization. Thus, APVP can weaken the effect of noises and outliers by the adaptive similarity matrix and strengthen the discriminant capability by the Fisher criterion. To classify unseen data, we also design a new classification rule. Experimental results show that APVP has good performance in semi-supervised scene.

Retracted: An Improved Particle Swarm Optimization-Powered Adaptive Classification and Migration Visualization for Music Style

Retracted: An Improved Particle Swarm Optimization-Powered Adaptive Classification and Migration Visualization for Music Style

DML‐OFA: Deep mutual learning with online feature alignment for the detection of COVID‐19 from chest x‐ray images

SummaryCOVID‐19 is a novel coronavirus‐induced disease and automatic identification of COVID‐19 using computer‐assisted methods can facilitate faster diagnostic efficiency. Current research typically employs a single model for COVID‐19 identification, while implicit and complementary knowledge between heterogeneous networks is neglected. To address these issues, we propose a new model based on deep mutual learning with online feature alignment called DML‐OFA to more effectively diagnose COVID‐19. First, we use a traditional deep mutual learning (DML) framework to allow two parallel heterogeneous networks to learn from each other to form two effective feature extractors. In addition, we embed the adaptive feature fusion classifier and logits ensembling module in the proposed DML‐OFA, which can simultaneously learn implicit complementary knowledge from feature maps and logits. We evaluated DML‐OFA on four public datasets: Covid‐chestxray‐dataset, ChestXRay2017, Coronavirus‐dataset and COVIDx. The results showed that our model attains 97.10 Accuracy, 97.28 Specificity, 96.21 Recall, 97.45 Precision, and 96.82 F1‐score, which outperforms other previous related works.

A novel adaptive generalized domain data fusion-driven kernel sparse representation classification method for intelligent bearing fault diagnosis

Dictionary learning has gradually attracted attention due to its powerful feature representation ability. However, the time-shift property of collected signals hinders the recognition of various bearing states. In addition, existing dictionary learning methods are mostly designed based on a single domain, while common data fusion methods used in data-driven cannot be directly extended to dictionary learning. In this paper, a novel adaptive generalized domain data fusion-driven kernel sparse representation classification method (AGDFDK-SRC) is proposed. First, to avoid the effect of the time-shift property on dictionary learning, a class-specific kernel sub-dictionary learning method is proposed, by which the non-linear signal data is mapped into high-dimensional feature space via a kernel trick. Second, the class-specific kernel sub-dictionaries are learned by kernel K-singular value decomposition in a data-driven manner. Then, an adaptive generalized domain data fusion strategy is developed for dictionary learning, which implements data fusion of multiple domain signals to enhance the feature mining ability and representation ability of the learned dictionary. Finally, a kernel sparse classification method is designed to achieve intelligent bearing fault diagnosis. Two bearing datasets are exploited to verify the recognition performance of AGDFDK-SRC, indicating that the AGDFDK-SRC obtains superior average classification accuracies of 98.23% and 99.50%, respectively.