Unbalanced Sample Research Articles

Usability and Affects Study of a Virtual Reality System Toward Scorpion Phobia Exposure Therapy

In this study, we present a framework to develop and evaluate a virtual reality exposure therapy system with biofeedback toward scorpion phobia treatment. The system is developed based on the methodology for the development of virtual reality educational environments; usability is evaluated with the System Usability Scale (SUS), the affects are measured with the Positive and Negative Affect Schedule (PANAS), and the biofeedback heart rate is measured in real time using a wearable device and the HypeRate app. A descriptive study was conducted with a non-probabilistic convenience sample of undergraduate students. The non-clinical sample consisted of 51 participants (11 women and 40 men) (mean = 20.75, SD = 2.42 years). The system usability score was 75.49, higher than the average of 68. For positive affects, the average value of the overall sample was 28.18, while for negative affects it was 13.67. The results of this preliminary study, while not determining that the system could currently be applied in clinical settings, demonstrate however that the system can initially be considered as a pre-feasibility study, and if the limitations of the unbalanced non-clinical sample are addressed, it could be used in the future for this purpose. The main contribution is the proposed framework to integrate usability and affects evaluation, as well as biofeedback in a VRET system toward scorpion phobia treatment.

Acoustic emission and electromagnetic radiation of coal-rock effective and interference signal identification utilizing generative adversarial learning and image feature mining

Acoustic Emission (AE) and Electromagnetic Radiation (EMR) are playing an increasingly important role in the field of coal and rock dynamic disaster early warning due to their accurate response to the evolution process. However, blasting, drilling, and other coal mine technical activities are easily to produce interference signals, which seriously affect the credibility of early warning information. Moreover, unbalanced samples and complex characteristic characterization cannot achieve accurate identification. This paper presents a novel identification method for effective and interference signal of AE and EMR based on generative adversarial learning and image feature mining. First, Kalman filter is applied to AE and EMR monitoring signals to remove noise and retain key features. The Wasserstein Generative Adversarial Network, then, resolves the imbalance between the sample numbers of effective and various types of interference signals to ensure generalization of the identification. The effective and interference signal samples are further converted graphically by Symmetrized Dot Pattern, and intuitive different distribution characteristics are obtained. Finally, the EfficientNet model accurately identified typical effective and six interference signals collected downhole. The practical case of a coal mine in Liaoning Province shows that the proposed method is feasible and effective, and can provide a basis for reliable early warning of coal and rock dynamic disasters.

Forensic bone age assessment of hand and wrist joint MRI images in Chinese han male adolescents based on deep convolutional neural networks.

In Chinese criminal law, the ages of 12, 14, 16, and 18 years old play a significant role in the determination of criminal responsibility. In this study, we developed an epiphyseal grading system based on magnetic resonance image (MRI) of the hand and wrist for the Chinese Han population and explored the feasibility of employing deep learning techniques for bone age assessment based on MRI of the hand and wrist. This study selected 282 Chinese Han Chinese males aged 6.0-21.0 years old. In the course of our study, we proposed a novel deep learning model for extracting and enhancing MRI hand and wrist bone features to enhance the prediction of target MRI hand and wrist bone age and achieve precise classification of the target MRI and regression of bone age. The evaluation metric for the classification model including precision, specificity, sensitivity, and accuracy, while the evaluation metrics chosen for the regression model are MAE. The epiphyseal grading was used as a supervised method, which effectively solved the problem of unbalanced sample distribution, and the two experts showed strong consistency in the epiphyseal plate grading process. In the classification results, the accuracy in distinguishing between adults and minors was 91.1%, and the lowest accuracy in the three minor classifications (12, 14, and 16 years of age) was 94.6%, 91.1% and 96.4%, respectively. The MAE of the regression results was 1.24 years. In conclusion, the deep learning model proposed enabled the age assessment of hand and wrist bones based on MRI.

Filtering-Assisted Airborne Point Cloud Semantic Segmentation for Transmission Lines.

Point cloud semantic segmentation is crucial for identifying and analyzing transmission lines. Due to the number of point clouds being huge, complex scenes, and unbalanced sample proportion, the mainstream machine learning methods of point cloud segmentation cannot provide high efficiency and accuracy when extending to transmission line scenes. This paper proposes a filter-assisted airborne point cloud semantic segmentation for transmission lines. First, a large number of ground point clouds is identified by introducing the well-developed cloth simulation filter to alleviate the impact of the imbalance of the target object proportion on the classifier's performance. The multi-dimensional features are then defined, and the classification model is trained to achieve the multi-element semantic segmentation of the transmission line scene. The experimental results and analysis indicate that the proposed filter-assisted algorithm can significantly improve the semantic segmentation performance of the transmission line point cloud, enhancing both the point cloud segmentation efficiency and accuracy by more than 25.46% and 3.15%, respectively. The filter-assisted point cloud semantic segmentation method reduces the volume of sample data, the number of sample classes, and the sample imbalance index in power line scenarios to a certain extent, thereby improving the classification accuracy of classifiers and reducing time consumption. This research holds significant theoretical reference value and engineering application potential for scene reconstruction and intelligent understanding of airborne laser point cloud transmission lines.

The phobic brain: Morphometric features correctly classify individuals with small animal phobia.

Specific phobia represents an anxiety disorder category characterized by intense fear generated by specific stimuli. Among specific phobias, small animal phobia (SAP) denotes a particular condition that has been poorly investigated in the neuroscientific literature. Moreover, the few previous studies on this topic have mostly employed univariate analyses, with limited and unbalanced samples, leading to inconsistent results. To overcome these limitations, and to characterize the neural underpinnings of SAP, this study aims to develop a classification model of individuals with SAP based on gray matter features, by using a machine learning method known as the binary support vector machine. Moreover, the contribution of specific structural macro-networks, such as the default mode, the salience, the executive, and the affective networks, in separating phobic subjects from controls was assessed. Thirty-two subjects with SAP and 90 matched healthy controls were tested to this aim. At a whole-brain level, we found a significant predictive model including brain structures related to emotional regulation, cognitive control, and sensory integration, such as the cerebellum, the temporal pole, the frontal cortex, temporal lobes, the amygdala and the thalamus. Instead, when considering macro-networks analysis, we found the Default, the Affective, and partially the Central Executive and the Sensorimotor networks, to significantly outperform the other networks in classifying SAP individuals. In conclusion, this study expands knowledge about the neural basis of SAP, proposing new research directions and potential diagnostic strategies.

Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral image classification

Hyperspectral image (HSI) classification plays a crucial role in remote sensing (RS) applications, enabling the precise identification of materials and land cover based on spectral information. This supports tasks such as agricultural management and urban planning. While sequential neural models like Recurrent Neural Networks (RNNs) and Transformers have been adapted for this task, they present limitations: RNNs struggle with feature aggregation and are sensitive to noise from interfering pixels, whereas Transformers require extensive computational resources and tend to underperform when HSI datasets contain limited or unbalanced training samples. To address these challenges, Mamba architectures have emerged, offering a balance between RNNs and Transformers by leveraging lightweight, parallel scanning capabilities. Although models like Vision Mamba (ViM) and Visual Mamba (VMamba) have demonstrated improvements in visual tasks, their application to HSI classification remains underexplored, particularly in handling land-cover semantic tokens and multi-scale feature aggregation for patch-wise classifiers. In response, this study introduces the Mamba-in-Mamba (MiM) architecture for HSI classification, marking a pioneering effort in this domain. The MiM model features: (1) a novel centralized Mamba-Cross-Scan (MCS) mechanism for efficient image-to-sequence data transformation; (2) a Tokenized Mamba (T-Mamba) encoder that incorporates a Gaussian Decay Mask (GDM), Semantic Token Learner (STL), and Semantic Token Fuser (STF) for enhanced feature generation; and (3) a Weighted MCS Fusion (WMF) module with a Multi-Scale Loss Design for improved training efficiency. Experimental results on four public HSI datasets—Indian Pines, Pavia University, Houston2013, and WHU-Hi-Honghu—demonstrate that our method achieves an overall accuracy improvement of up to 3.3%, 2.7%, 1.5%, and 2.3% over state-of-the-art approaches (i.e., SSFTT, MAEST, etc.) under both fixed and disjoint training-testing settings.

Foreign direct investment, total factor productivity, and economic growth: evidence in middle-income countries

This study examines the relationship between foreign direct investment and total factor productivity on economic growth in 90 middle-income countries. Because middle-income countries often face particular challenges in achieving sustainable economic development. Investigating how FDI and TFP contribute to or hinder economic growth in these countries can provide insight and help policymakers make policy decisions. We employ the dynamic system Generalized Method of Moments to analyze an unbalanced sample with 2714 annual observations from 1990 to 2020. The empirical results show that a percentage increase in foreign direct investment will increase economic growth in middle-income countries by 9.3%. In addition, Total Factor Productivity also has a positive relationship with economic growth due to improved labor quality and production innovations. Furthermore, the results indicate that Total Factor Productivity empowers the positive nexus between Foreign Direct Investment and economic growth. In addition, the main findings are also robust even though we employ alternative economic growth proxies. These findings support economic growth and industrialization theories but do not support labor market dynamics theories. Finally, this study contributes practical suggestions for sustainable economic development in middle-income countries.

Trade Policy Space, Aid for Trade and, Intra-African and External African Manufactured Exports

Boosting intra-African manufactured exports is a critical objective of African leaders. The present analysis examines whether trade policy space and Aid for Trade (AfT) flows can contribute to achieving this objective. The analysis covers an unbalanced sample of 36 African countries over the period from 2004 to 2020, and uses estimators that allow obtaining the short-term (i.e., within-country effect) and long-term (i.e., between-country effect) effects of each regressor. The estimators are the combination of the feasible generalized least squares estimator on the one hand, and the Seemingly Unrelated Regression on the other hand, in the context of a hybrid model. The findings indicate that both trade policy space and AfT flows can help promote - including in a complementary way - African manufactured exports, especially intra-African manufactured exports. In this regard, trade policy space and AfT flows are instrumental in meeting African leaders’ objectives of promoting intra-African trade. The implications of the findings are discussed.

A Measurement of Aggregate Trade Restrictions and Their Economic Effects

Abstract This study develops a new Measure of Aggregate Trade Restrictions (MATR) using data from the IMF's Annual Report on Exchange Arrangements and Exchange Restrictions. MATR is a measure of direct and indirect official government policy related to the international flow of goods and services. MATR is simple, plausible, quantitative, easily updated, based on relevant measures of trade policy and other international restrictions affecting trade (e.g., payment restrictions), and covers an unbalanced sample of up to 157 countries from 1949 to 2019. MATR is strongly correlated with, and—importantly—more comprehensive, in terms of country and time coverage, than existing measures of de jure openness; it is also granular. As such, MATR empowers empirical analysis to increase coverage in research related to trade restrictions and other trade-related openness policies. MATR is used in the study to show that direct and indirect restrictions to trade are associated with significant contractions in output.

An adaptive imbalance robust graph embedding broad learning system fault diagnosis for imbalanced batch processes data

Modern batch processes develop toward higher levels, and devices usually work at normal conditions with generally very few faults. Therefore, fewer fault data are collected than normal data, which makes the normal and fault modes imbalanced, and the fault diagnosis model is incapable focusing on the minority of fault samples as much as on most normal samples, consequently leading to insufficient generalization ability for the model. For that, we propose an adaptive imbalance-robust graph embedding broad learning system (AI-RGEBLS) in this paper. Firstly, it achieves adaptive correction of unbalanced samples by niche technique and synthetic minority over-sampling technique (SMOTE) with improved Mahalanobis distance. Then, broad learning system (BLS) is regularized by graph embedding, and further introduced the L2,1 norm constraint, which makes it possible to enhance the robustness of the model while considering the local manifold information of the data in the feature extraction process. Finally, the incremental learning approach is applied to the model to avoid the disastrous forgetting problem caused by training the whole model from zero. The effectiveness of the proposed method is verified by penicillin fermentation process and semiconductor etching process. It can effectively improve the speed of model training and provide better fault diagnosis for imbalanced batch processes compared with the existing methods.

Fault diagnosis of bearings under variable operating conditions based on domain adaptation

Aiming at the problem of low fault recognition rate caused by different distribution of training samples and test samples and imbalance of various fault data in bearing fault diagnosis, a domain adaptive fault diagnosis method based on improved residual network ( ResNet ) is designed. In the first layer of the diagnosis network, a multi-dimensional convolution structure is used for feature extraction to obtain fault feature information of different dimensions; the local maximum mean difference (LMMD) is used in the domain adaptive layer to align the distribution of the source domain and the target domain to obtain more fine-grained information; the class balance loss function ( CBLoss ) is used to solve the training problem of unbalanced data, and the Adam optimization network is used to realize fault diagnosis. Experimental results show that the proposed improved method can achieve higher diagnosis results under the imbalance of fault sample categories. Experimental verification is carried out on two bearing data sets and collected wind turbine data. The results show that the proposed improved method has certain advantages. The diagnostic performance of the proposed improved method in the case of unbalanced data samples is better than other deep transfer learning methods, and it can be used as an effective cross-condition fault analysis method.

Readers' Comprehension of New Text Formats. Part I. Empirical Evidence from Russian and Research Methodology Behind It

In this article, we review a range of Russian-language studies investigating readers’ interaction with new text formats. We identify the key problems preventing proper generalization of such research data. These include: (1) the absence of agreed terminology for describing texts of new formats shared by most researchers, and (2) the lack of consistency in theoretical approaches for describing cognitive mechanisms underpinning processing of these types of texts by readers. The following factors further complicate comparison and systematization of the data obtained by different research groups: (1) the lack of explicitly described theoretical bases of the hypotheses formulated by researchers, (2) the lack of consistency in describing the putative connections between such theoretical backgrounds and empirically tested hypotheses, (3) heterogeneity of methodological approaches, (4) insufficient, unequal or unbalanced sample sizes, (5) low reliability of statistical approaches and tools used for data analysis, as well as (6) research artefacts confounding the results.

Prediction of Crohn's disease based on deep feature recognition

BackgroundCrohn's disease is a complex genetic disease that involves chronic gastrointestinal inflammation and results from a complex set of genetic, environmental, and immunological factors. By analyzing data from the human microbiome, genetic information can be used to predict Crohn's disease. Recent advances in deep learning have demonstrated its effectiveness in feature extraction and the use of deep learning to decode genetic information for disease prediction. MethodsIn this paper, we present a deep learning-based model that utilizes a sequential convolutional attention network (SCAN) for feature extraction, incorporates adaptive additive interval losses to enhance these features, and employs support vector machines (SVM) for classification. To address the challenge of unbalanced Crohn's disease samples, we propose a random noise one-hot encoding data augmentation method. ResultsData augmentation with random noise accelerates training convergence, while SCAN-SVM effectively extracts features with adaptive additive interval loss enhancing differentiation. Our approach outperforms benchmark methods, achieving an average accuracy of 0.80 and a kappa value of 0.76, and we validate the effectiveness of feature enhancement. ConclusionsIn summary, we use deep feature recognition to effectively analyze the potential information in genes, which has a good application potential for gene analysis and prediction of Crohn's disease.

Morphological dictionary learning based sparse classification for small electric motor state recognition under unbalanced samples

Accurately recognizing sound states in the production line of small electric motors is of great importance for manufacturers to carry out quick repairs and ensure high quality deliveries. Since the number of normal samples is much larger than the number of abnormal samples in practice, resulting in unbalanced data, which poses huge challenges to traditional detection methods. To overcome these difficulties, this study presents a morphological dictionary learning-based sparse classification (MDL-SC) combined with audio data augmentation method for small electric motor state recognition under unbalanced samples. Firstly, audio data augmentation methods such as adding background noise, pitch shifting, time stretching and combined augmentation are investigated for augmenting the number and diversity of samples. Secondly, morphological dictionary learning is proposed for characterizing transient sounds of small electric motors and enhancing the discriminative feature learning capability of the dictionary. Finally, the minimum reconstruction error strategy is relied upon to establish automatic recognition of small electric motor states. Three small motor datasets with unbalanced ratios are established in the experiments to verify the effectiveness of the proposed MDL-SC, which has higher recognition accuracy under unbalanced conditions compared with traditional dictionary learning based sparse classification (DL-SC), k-nearest neighbors, support vector machines and convolutional neural networks. This study can provide some theoretical implications for the later development of online detection of small electric motors or other types of electric motors.

Discovery unbalanced DNA mixtures and evaluation mixing ratio via a droplet digital PCR method.

Small amounts of DNA from a perpetrator collected during crime-scene investigations can be masked by large amounts of DNA from the victim. These samples can provide important information for the perpetrator's conviction. Short tandem repeat (STR) detection system is not sensitive enough to detect trace amounts of minor components in unbalanced mixed DNA. We developed a system using droplet digital polymerase chain reaction (ddPCR) capable of discovering trace components and accurately determining the ratio of mixed DNA in extremely unbalanced mixtures. The non-recombining regions of the X chromosome and Y chromosome were quantified in the DNA of male and female mixtures using duplex ddPCR. Absolute quantification of low-abundance portions of trace samples and unbalanced mixtures was done using different mixing ratios. The ddPCR system could be used to detect low-abundance samples with < 5 copies of DNA components in an extremely unbalanced mixture at a mixing ratio of 10000:1. The high sensitivity and specificity of the system could identify the mixing ratio of mixed DNA accurately. A ddPCR system was developed for evaluation of mixed samples of male DNA and female DNA. Our system could detect DNA quantities as low as 5 copies in extremely unbalanced mixed samples with good specificity and applicability. This method could assist forensic investigators in avoiding the omission of important physical evidence, and evaluating the ratio of mixed male/female trace samples.

Contrastive-Active Transfer Learning-Based Real-Time Adaptive Assessment Method for Power System Transient Stability.

The transient stability assessment based on machine learning faces challenges such as sample data imbalance and poor generalization. To address these problems, this paper proposes an intelligent enhancement method for real-time adaptive assessment of transient stability. In the offline phase, a convolutional neural network (CNN) is used as the base classifier. A model training method based on contrastive learning is introduced, aiming to increase the spatial distance between positive and negative samples in the mapping space. This approach effectively improves the accuracy of the model in recognizing unbalanced samples. In the online phase, when real data with different distribution characteristics from the offline data are encountered, an active transfer strategy is employed to update the model. New system samples are obtained through instance transfer from the original system, and an active sampling strategy considering uncertainty is designed to continuously select high-value samples from the new system for labeling. The model parameters are then updated by fine-tuning. This approach drastically reduces the cost of updating while improving the model's adaptability. Experiments on the IEEE39-node system verify the effectiveness of the proposed method.

Attack detection model for BCoT based on contrastive variational autoencoder and metric learning

With development of blockchain technology, clouding computing and Internet of Things (IoT), blockchain and cloud of things (BCoT) has become development tendency. But the security has become the most development hinder of BCoT. Attack detection model is a crucial part of attack revelation mechanism for BCoT. As a consequence, attack detection model has received more concerned. Due to the great diversity and variation of network attacks aiming to BCoT, tradition attack detection models are not suitable for BCoT. In this paper, we propose a novel attack detection model for BCoT, denoted as cVAE-DML. The novel model is based on contrastive variational autoencoder (cVAE) and deep metric learning (DML). By training the cVAE, the proposed model generates private features for attack traffic information as well as shared features between attack traffic information and normal traffic information. Based on those generated features, the proposed model can generate representative new samples to balance the training dataset. At last, the decoder of cVAE is connected to the deep metric learning network to detect attack aiming to BCoT. The efficiency of cVAE-DML is verified using the CIC-IDS 2017 dataset and CSE-CIC-IDS 2018 dataset. The results show that cVAE-DML can improve attack detection efficiency even under the condition of unbalanced samples.

Deep-Autoencoder-Based Radar Source Recognition: Addressing Large-Scale Imbalanced Data and Edge Computing Constraints

Radar radiation source recognition technology is vital in electronic countermeasures, electromagnetic control, and air traffic management. Its primary function is to identify radar signals in real time by computing and inferring the parameters of intercepted signals. With the rapid advancement of AI technology, deep learning algorithms have shown promising results in addressing the challenges of radar radiation source recognition. However, significant obstacles remain: the radar radiation source data often exhibit large-scale, unbalanced sample distribution and incomplete sample labeling, resulting in limited training data resources. Additionally, in practical applications, models must be deployed on outdoor edge computing terminals, where the storage and computing capabilities of lightweight embedded systems are limited. This paper focuses on overcoming the constraints posed by data resources and edge computing capabilities to design and deploy large-scale radar radiation source recognition algorithms. Initially, it addresses the issues related to large-scale radar radiation source samples through data analysis, preprocessing, and feature selection, extracting and forming prior knowledge information. Subsequently, a model named RIR-DA (Radar ID Recognition based on Deep Learning Autoencoder) is developed, integrating this prior knowledge. The RIR-DA model successfully identified 96 radar radiation source targets with an accuracy exceeding 95% in a dataset characterized by a highly imbalanced sample distribution. To tackle the challenges of poor migration effects and low computational efficiency on lightweight edge computing platforms, a parallel acceleration scheme based on the embedded microprocessor T4240 is designed. This approach achieved a nearly eightfold increase in computational speed while maintaining the original training performance. Furthermore, an integrated solution for a radar radiation source intelligent detection system combining PC devices and edge devices is preliminarily designed. Experimental results demonstrate that, compared to existing radar radiation source target recognition algorithms, the proposed method offers superior model performance and greater practical extensibility. This research provides an innovative exploratory solution for the industrial application of deep learning models in radar radiation source recognition.

Technostress and time spent online. A cross-cultural comparison for teachers and students.

Research shows that ICT is beneficial for academics and students, aiding in overcoming distance barriers, streamlining administration, and improving teaching and learning processes. However, the negative impact of technology, particularly technostress, are garnering attention. In the context of the concerns about technostress among higher education institutions (HEI), the aim of the study is to analyze the technostress creators and inhibitors for university teachers and students in different European countries. The topical concept of digital well-being is seen as "a subjective individual experience of optimal balance between the benefits and drawbacks obtained from mobile connectivity, focusing on the personal perception of what amount of time spent using technology is optimal so that well-being is preserved". To explore specific aspects related to use of technology, two - parallel online surveys for academics (N = 446) and students (N = 660) from four European countries (Romania, Germany, Norway, and Finland) were conducted between November 2022 - January 2023. The surveys included the Technostress scale and the Technostress Inhibitors Scale, the Technology self-efficacy Scale, and a questionnaire focusing on socio-demographic aspects, work experience, academic field, dimensions related to the actual use of technology and participants perception on the optimal use of technology for work, learning or personal tasks, in terms of the period of day/week and amount of time spent. We also inquired about the social support given and received when using technology and the formal and informal rules, expectations, policies, punishments, and rewards regarding the use of technology. The findings suggest that the perceived optimal use of technology is significantly lower than the actual use for all the contexts. Overuse of technology was associated with technostress. Our results also showed that technology self-efficacy and social support from colleagues and teachers are negatively associated with technostress. Country differences regarding technostress and time spent online were also observed. Despite the needed caution in interpreting the results because of the unbalanced sample size across countries, the results could be used to develop research and support interventions within European countries to promote digital well-being, a better work-life balance with further positive effects on academic satisfaction and work/learning productivity.

The informal economy and the entrepreneurial cycle

PurposeThis study aims to explore the direct and indirect relationships among the informal economy, innovation, entrepreneurial and initial public offering (IPO) activity.Design/methodology/approachThis study uses an unbalanced sample of 30 countries over a 15-year period: 2000–2014. The proposed random-effects model is estimated using feasible generalized least squares with robust estimators of variance.FindingsEntrepreneurial activity is positively related to IPO activity. The informal economy negatively moderates the relationships among entrepreneurship, innovation and IPOs.Practical implicationsIPOs are a stage in the entrepreneurial process susceptible of being influenced by country level factors. An appropriate understanding of these factors can contribute to discuss policies that improve the level of IPO activity.Originality/valueThe authors explore the understudied relationship of the informal economy and entrepreneurship. Although entrepreneurial activity can be higher in contexts with more informality, this relationship can turn sour in later stages since it lowers the probability of higher IPO activity by inhibiting formal entrepreneurship and innovation. Hence, the main contribution is to provide evidence of this “hangover” effect.