Search Results (18)

This study explores advanced process monitoring for one-shot drilling of aeronautical stacks made of aluminium 2024 and carbon fibre-reinforced polymer (CFRP) laminates using a 4.8 mm diameter drilling tool and unsupervised machine learning techniques. An experimental campaign is conducted to collect thrust force and torque signals at a 10 kHz sampling rate during the drilling process. These signals are employed for real-time process monitoring, focusing on material change detection and anomaly identification, where anomalies are defined as holes that fail to meet predefined quality criteria. An innovative approach based on unsupervised learning is proposed to enable automatic material change identification, signal segmentation, feature extraction, and hole quality assessment. Specifically, a semi-supervised approach based on a Gaussian Mixture Model (GMM) and 1D Convolutional AutoEncoder (1D-CAE) is employed to detect deviations from normal drilling conditions. The proposed method is benchmarked against state-of-the-art supervised techniques, including logistic regression (LR) and Support Vector Machines (SVMs). Results show that these traditional models struggle with class imbalance, leading to overfitting and limited generalisation, as reflected by the F1 scores of 0.78 and 0.75 for LR and SVM, respectively. In contrast, the proposed semi-supervised approach improves anomaly detection, achieving an F1 score of 0.87 by more effectively identifying poor-quality holes. This study demonstrates the potential of deep learning-based semi-supervised methods for intelligent process monitoring, enabling adaptive control in the drilling process of hybrid stacks and detecting anomalous holes. While the proposed approach effectively handles small and imbalanced datasets, further research into the application of generative AI could enhance performance, aiming for F1 scores above 0.90, thereby supporting adaptation in real industrial environments with high performance. Full article

The popularity of cryptocurrency exchanges has surged in recent years, accompanied by the proliferation of new digital platforms and tokens. However, the issue of credit risk and the reliability of crypto exchanges remain critical, highlighting the need for indicators to assess the safety of investing through these platforms. This study examines a unique, hand-collected dataset of 228 cryptocurrency exchanges operating between April 2011 and May 2024. Using various machine learning algorithms, we identify the key factors contributing to exchange shutdowns, with trading volume, exchange lifespan, and cybersecurity scores emerging as the most significant predictors. Since individual machine learning models often capture distinct data characteristics and exhibit varying error patterns, we employ a forecast combination approach by aggregating multiple predictive distributions. Specifically, we evaluate several specifications of the generalized linear pool (GLP), beta-transformed linear pool (BLP), and beta-mixture combination (BMC). Our findings reveal that the beta-transformed linear pool and the beta-mixture combination achieve the best performances, improving forecast accuracy by approximately 4.1% based on a robust H-measure, which effectively addresses the challenges of misclassification in imbalanced datasets. Full article

Learning distance metrics and distinguishing between samples from different classes are among the most important topics in machine learning. This article proposes a new distance metric learning approach tailored for highly imbalanced datasets. Imbalanced datasets suffer from a lack of data in the minority class, and the differences in class density strongly affect the efficiency of the classification algorithms. Therefore, the density of the classes is considered the main basis of learning the new distance metric. It is possible that the data of one class are composed of several densities, that is, the class is a combination of several normal distributions with different means and variances. In this paper, considering that classes may be multimodal, the distribution of each class is assumed in the form of a mixture of multivariate Gaussian densities. A density-based clustering algorithm is used for determining the number of components followed by the estimation of the parameters of the Gaussian components using maximum a posteriori density estimation. Then, the Bhattacharya distance between the Gaussian mixtures of the classes is maximized using an iterative scheme. To reach a large between-class margin, the distance between the external components is increased while decreasing the distance between the internal components. The proposed method is evaluated on 15 imbalanced datasets using the k-nearest neighbor (KNN) classifier. The results of the experiments show that using the proposed method significantly improves the efficiency of the classifier in imbalance classification problems. Also, when the imbalance ratio is very high and it is not possible to correctly identify minority class samples, the proposed method still provides acceptable performance. Full article

Electroencephalography (EEG)-based applications in brain–computer interfaces (BCIs), neurological disease diagnosis, rehabilitation, etc., rely on supervised approaches such as classification that requires given labels. However, with the ever-increasing amount of EEG data, incomplete or incorrectly labeled or unlabeled EEG data are increasing. It likely degrades the performance of supervised approaches. In this work, we put forward a novel unsupervised exploratory EEG analysis solution by clustering based on low-dimensional prototypes in latent space that are associated with the respective clusters. Having the prototype as a baseline of each cluster, a compositive similarity is defined to act as the critic function in clustering, which incorporates similarities on three levels. The approach is implemented with a Generative Adversarial Network (GAN), termed W-SLOGAN, by extending the Stein Latent Optimization for GANs (SLOGAN). The Gaussian Mixture Model (GMM) is utilized as the latent distribution to adapt to the diversity of EEG signal patterns. The W-SLOGAN ensures that images generated from each Gaussian component belong to the associated cluster. The adaptively learned Gaussian mixing coefficients make the model remain effective in dealing with an imbalanced dataset. By applying the proposed approach to two public EEG or intracranial EEG (iEEG) epilepsy datasets, our experiments demonstrate that the clustering results are close to the classification of the data. Moreover, we present several findings that were discovered by intra-class clustering and cross-analysis of clustering and classification. They show that the approach is attractive in practice in the diagnosis of the epileptic subtype, multiple labelling of EEG data, etc. Full article

Chromophoric dissolved organic matter (CDOM) is a mixture of various types of organic matter and a useful parameter for monitoring complex inland surface waters. Remote sensing has been widely utilized to detect CDOM in various studies; however, in many cases, the dataset is relatively imbalanced in a single region. To address these concerns, data were acquired from hyperspectral images, field reflection spectra, and field monitoring data, and the imbalance problem was solved using a synthetic minority oversampling technique (SMOTE). Using the on-site reflectance ratio of the hyperspectral images, the input variables R_rs (452/497), R_rs (497/580), R_rs (497/618), and R_rs (684/618), which had the highest correlation with the CDOM absorption coefficient a_CDOM (355), were extracted. Random forest and light gradient boosting machine algorithms were applied to create a CDOM prediction algorithm via machine learning, and to apply SMOTE, low-concentration and high-concentration datasets of CDOM were distinguished by 5 m⁻¹. The training and testing datasets were distinguished at a 75%:25% ratio at low and high concentrations, and SMOTE was applied to generate synthetic data based on the training dataset, which is a sub-dataset of the original dataset. Datasets using SMOTE resulted in an overall improvement in the algorithmic accuracy of the training and test step. The random forest model was selected as the optimal model for CDOM prediction. In the best-case scenario of the random forest model, the SMOTE algorithm showed superior performance, with testing R², absolute error (MAE), and root mean square error (RMSE) values of 0.838, 0.566, and 0.777 m⁻¹, respectively, compared to the original algorithm’s test values of 0.722, 0.493, and 0.802 m⁻¹. This study is anticipated to resolve imbalance problems using SMOTE when predicting remote sensing-based CDOM. It is expected to produce and implement a machine learning model with improved reliable performance. Full article

Imbalanced data present a pervasive challenge in many real-world applications of statistical and machine learning, where the instances of one class significantly outnumber those of the other. This paper examines the impact of class imbalance on the performance of Gaussian mixture models in classification tasks and establishes the need for a strategy to reduce the adverse effects of imbalanced data on the accuracy and reliability of classification outcomes. We explore various strategies to address this problem, including cost-sensitive learning, threshold adjustments, and sampling-based techniques. Through extensive experiments on synthetic and real-world datasets, we evaluate the effectiveness of these methods. Our findings emphasize the need for effective mitigation strategies for class imbalance in supervised Gaussian mixtures, offering valuable insights for practitioners and researchers in improving classification outcomes. Full article

The development of internet technology has brought us benefits, but at the same time, there has been a surge in network attack incidents, posing a serious threat to network security. In the real world, the amount of attack data is much smaller than normal data, leading to a severe class imbalance problem that affects the performance of classifiers. Additionally, when using CNN for detection and classification, manual adjustment of parameters is required, making it difficult to obtain the optimal number of convolutional kernels. Therefore, we propose a hybrid sampling technique called Borderline-SMOTE and Gaussian Mixture Model (GMM), referred to as BSGM, which combines the two approaches. We utilize the Quantum Particle Swarm Optimization (QPSO) algorithm to automatically determine the optimal number of convolutional kernels for each one-dimensional convolutional layer, thereby enhancing the detection rate of minority classes. In our experiments, we conducted binary and multi-class experiments using the KDD99 dataset. We compared our proposed BSGM-QPSO-1DCNN method with ROS-CNN, SMOTE-CNN, RUS-SMOTE-CNN, RUS-SMOTE-RF, and RUS-SMOTE-MLP as benchmark models for intrusion detection. The experimental results show the following: (i) BSGM-QPSO-1DCNN achieves high accuracy rates of 99.93% and 99.94% in binary and multi-class experiments, respectively; (ii) the precision rates for the minority classes R2L and U2R are improved by 68% and 66%, respectively. Our research demonstrates that BSGM-QPSO-1DCNN is an efficient solution for addressing the imbalanced data issue in this field, and it outperforms the five intrusion detection methods used in this study. Full article

In age-related sarcopenia, the gradual loss of skeletal muscle mass, function and strength is underpinned by an imbalanced rate of protein synthesis/breakdown. Hence, an adequate protein intake is considered a valuable strategy to mitigate sarcopenia. Here, we investigated the effects of a 12-week oral supplementation with branched-chain amino acids (BCAAs: leucine, isoleucine, and valine) with recognized anabolic properties, in 17-month-old (AGED) C57BL/6J male mice. BCAAs (2:1:1) were formulated in drinking water, alone or plus two L-Alanine equivalents (2ALA) or dipeptide L-Alanyl-L-Alanine (Di-ALA) to boost BCAAs bioavailability. Outcomes were evaluated on in/ex vivo readouts vs. 6-month-old (ADULT) mice. In vivo hind limb plantar flexor torque was improved in AGED mice treated with BCAAs + Di-ALA or 2ALA (recovery score, R.S., towards ADULT: ≥20%), and all mixtures significantly increased hind limb volume. Ex vivo, myofiber cross-sectional areas were higher in gastrocnemius (GC) and soleus (SOL) muscles from treated mice (R.S. ≥ 69%). Contractile indices of isolated muscles were improved by the mixtures, especially in SOL muscle (R.S. ≥ 20%). The latter displayed higher mTOR protein levels in mice supplemented with 2ALA/Di-ALA-enriched mixtures (R.S. ≥ 65%). Overall, these findings support the usefulness of BCAAs-based supplements in sarcopenia, particularly as innovative formulations potentiating BCAAs bioavailability and effects. Full article

In this paper, we study the problem of privacy-preserving data synthesis (PPDS) for tabular data in a distributed multi-party environment. In a decentralized setting, for PPDS, federated generative models with differential privacy are used by the existing methods. Unfortunately, the existing models apply only to images or text data and not to tabular data. Unlike images, tabular data usually consist of mixed data types (discrete and continuous attributes) and real-world datasets with highly imbalanced data distributions. Existing methods hardly model such scenarios due to the multimodal distributions in the decentralized continuous columns and highly imbalanced categorical attributes of the clients. To solve these problems, we propose a federated generative model for decentralized tabular data synthesis (HT-Fed-GAN). There are three important parts of HT-Fed-GAN: the federated variational Bayesian Gaussian mixture model (Fed-VB-GMM), which is designed to solve the problem of multimodal distributions; federated conditional one-hot encoding with conditional sampling for global categorical attribute representation and rebalancing; and a privacy consumption-based federated conditional GAN for privacy-preserving decentralized data modeling. The experimental results on five real-world datasets show that HT-Fed-GAN obtains the best trade-off between the data utility and privacy level. For the data utility, the tables generated by HT-Fed-GAN are the most statistically similar to the original tables and the evaluation scores show that HT-Fed-GAN outperforms the state-of-the-art model in terms of machine learning tasks. Full article

Polaron quasiparticles are formed when a mobile impurity is coupled to the elementary excitations of a many-particle background. In the field of ultracold atoms, the study of the associated impurity problem has attracted a growing interest over the last fifteen years. Polaron quasiparticle properties are essential to our understanding of a variety of paradigmatic quantum many-body systems realized in ultracold atomic gases and in the solid state, from imbalanced Bose–Fermi and Fermi–Fermi mixtures to fermionic Hubbard models. In this topical review, we focus on the so-called repulsive polaron branch, which emerges as an excited many-body state in systems with underlying attractive interactions such as ultracold atomic mixtures, and is characterized by an effective repulsion between the impurity and the surrounding medium. We give a brief account of the current theoretical and experimental understanding of repulsive polaron properties, for impurities embedded in both fermionic and bosonic media, and we highlight open issues deserving future investigations. Full article

Increasing concentrations of the antidepressants amitriptyline and paroxetine were determined recently in marine habitats. However, their impact on marine biota is understudied, despite multiple undesirable effects they have on the environment. An important behavioral aspect that is increasingly measured following exposure to contaminants is the migration of fauna from contaminated areas. Hence, our aim was to better understand the migration pattern of marine meiobenthic fauna, but with a main focus on nematodes, following the exposure to both antidepressants, alone or in mixture. The experiment was carried out in microcosms, which comprised an uncontaminated upper and a lower contaminated compartment, where amitriptyline was added, alone or mixed with paroxetine, at concentrations of 0.4 and 40 µg L⁻¹. The overall abundance of meiobenthic groups decreased significantly following exposure to amitriptyline in both compartments, a pattern augmented by the mixture with paroxetine. The migration of nematodes towards the upper compartments of microcosms was triggered by the level of contamination with antidepressants. As such, the species Terschellingia longicaudata showed no significant change in abundance, suggesting tolerance to both antidepressants. On the other hand, the abundances of nematode taxa Cyatholaimus prinzi, Calomicrolaimus sp., Calomicrolaimus honestus, Neochromadora sp., Chromadorina sp. and Chromadorina minor decreased significantly following the exposure to both antidepressants, even at low concentrations. At the end of the experiment, the dominant migratory nematodes belonged to deposit-feeders and omnivores-carnivores trophic guilds, with tail shapes of e/f types and body-sizes longer than 2 mm. Such functional traits increase their mobility in sediments and the chance to move away from contaminated habitats. Moreover, the sex ratio was imbalanced in the favor of males in contaminated lower compartments with mixtures of the lowest and highest concentrations of amitriptyline and paroxetine, suggesting that these drugs also affect the hormone system. In conclusion, the exposure to the antidepressants amitriptyline and paroxetine triggered important changes within nematode communities, as changes in taxonomic composition were a result of migration and survival of tolerant taxa, but equally acting on the hormone system and leading to unbalanced sex-ratio among the residents. Full article

There is insufficient information regarding the stoichiometric variation and coupling status of carbon (C), nitrogen (N), phosphorus (P), and potassium (K) in the leaves of nutrient-enriched greenhouse agroecosystems with increasing planting time. Therefore, we assessed the variation in elemental stoichiometry ratios in soil and cucumber (Cucumis sativus L.) leaves, and the coupling status of elemental utilization in the leaves under continuous cropping systems using natural (only soil; i.e., control soil, CO) and artificial (soil + straw + chicken + urea; i.e., straw mixture soil, ST) soil via monitoring studies for 11 years in a solar greenhouse. Soil organic C, total N, and total P concentrations increased by 63.4%, 72.7%, and 144.3% in the CO, respectively, after 11 years of cultivation (compared to the first year), and by 18.1%, 24.3%, and 117.7% in the ST under continuous cropping conditions, respectively. Total K concentrations remained unchanged in both soils. Moreover, the availability of these soil elements increased to different degrees in both soils after 11 years of planting. Additionally, the leaf P concentration increased by 9.8% in the CO, while leaf N and K concentrations did not change, suggesting decoupling of P utilization from that of N and K in leaves under a continuous cropping system. These findings suggest that imbalanced soil nutrients under continuous cropping conditions results in decoupling of P from N and K in the utilization of leaf nutrients. Full article

Despite the benefits of quantitative data generated by massively parallel sequencing, resolving mitotypes from mixtures occurring in certain ratios remains challenging. In this study, a bioinformatic mixture deconvolution method centered on population-based phasing was developed and validated. The method was first tested on 270 in silico two-person mixtures varying in mixture proportions. An assortment of external reference panels containing information on haplotypic variation (from similar and different haplogroups) was leveraged to assess the effect of panel composition on phasing accuracy. Building on these simulations, mitochondrial genomes from the Human Mitochondrial DataBase were sourced to populate the panels and key parameter values were identified by deconvolving an additional 7290 in silico two-person mixtures. Finally, employing an optimized reference panel and phasing parameters, the approach was validated with in vitro two-person mixtures with differing proportions. Deconvolution was most accurate when the haplotypes in the mixture were similar to haplotypes present in the reference panel and when the mixture ratios were neither highly imbalanced nor subequal (e.g., 4:1). Overall, errors in haplotype estimation were largely bounded by the accuracy of the mixture’s genotype results. The proposed framework is the first available approach that automates the reconstruction of complete individual mitotypes from mixtures, even in ratios that have traditionally been considered problematic. Full article

This research aimed to indicate mechanisms involved in protection against the imbalanced generation of reactive oxygen species (ROS) during heavy metals (HMs) exposition of Silene vulgaris ecotypes with different levels of metal tolerance. Specimens of non-metallicolous (NM), calamine (CAL), and serpentine (SER) ecotypes were treated in vitro with Zn, Pb, and Cd ions applied simultaneously in concentrations that reflected their contents in natural habitats of the CAL ecotype (1× HMs) and 2.5- or 5.0-times higher than the first one. Our findings confirmed the sensitivity of the NM ecotype and revealed that the SER ecotype was not fully adapted to the HM mixture, since intensified lipid peroxidation, ultrastructural alternations, and decline in photosynthetic pigments’ content were ascertained under HM treatment. These changes resulted from insufficient antioxidant defense mechanisms based only on ascorbate peroxidase (APX) activity assisted (depending on HMs concentration) by glutathione-S-transferase (GST) and peroxidase activity at pH 6.8 in the NM ecotype or by GST and guaiacol-type peroxidase in the SER one. In turn, CAL specimens showed a hormetic reaction to 1× HMs, which manifested by both increased accumulation of pigments and most non-enzymatic antioxidants and enhanced activity of catalase and enzymes from the peroxidase family (with the exception of APX). Interestingly, no changes in superoxide dismutase activity were noticed in metallicolous ecotypes. To sum up, the ROS scavenging pathways in S. vulgaris relied on antioxidants specific to the respective ecotypes, however the synthesis of polyphenols was proved to be a universal reaction to HMs. Full article

An important problem in machine learning is that, when using more than two labels, it is very difficult to construct and optimize a group of learning functions that are still useful when the prior distribution of instances is changed. To resolve this problem, semantic information G theory, Logical Bayesian Inference (LBI), and a group of Channel Matching (CM) algorithms are combined to form a systematic solution. A semantic channel in G theory consists of a group of truth functions or membership functions. In comparison with the likelihood functions, Bayesian posteriors, and Logistic functions that are typically used in popular methods, membership functions are more convenient to use, providing learning functions that do not suffer the above problem. In Logical Bayesian Inference (LBI), every label is independently learned. For multilabel learning, we can directly obtain a group of optimized membership functions from a large enough sample with labels, without preparing different samples for different labels. Furthermore, a group of Channel Matching (CM) algorithms are developed for machine learning. For the Maximum Mutual Information (MMI) classification of three classes with Gaussian distributions in a two-dimensional feature space, only 2–3 iterations are required for the mutual information between three classes and three labels to surpass 99% of the MMI for most initial partitions. For mixture models, the Expectation-Maximization (EM) algorithm is improved to form the CM-EM algorithm, which can outperform the EM algorithm when the mixture ratios are imbalanced, or when local convergence exists. The CM iteration algorithm needs to combine with neural networks for MMI classification in high-dimensional feature spaces. LBI needs further investigation for the unification of statistics and logic. Full article