Multidimensional Datasets Research Articles

Whole-Brain Electrophysiology and Calcium Imaging in Drosophila during Sleep and Wake.

Sleep is likely a whole-brain phenomenon, with most of the brain probably benefiting from this state of decreased arousal. Recent advances in our understanding of some potential sleep functions, such as metabolite clearance and synaptic homeostasis, make it evident why the whole brain is likely impacted by sleep: All neurons have synapses, and all neurons produce waste metabolites. Sleep experiments in the fly Drosophila melanogaster suggest that diverse sleep functions appear to be conserved across all animals. Studies of brain activity during sleep in humans typically involve multidimensional data sets, such as those acquired by electroencephalograms (EEGs) or functional magnetic resonance imaging (fMRI), and these whole-brain read-outs often reveal important qualities of different sleep stages, such as changes in frequency dynamics or connectivity. Recently, various techniques have been developed that allow for the recording of neural activity simultaneously across multiple regions of the fly brain. These whole-brain-recording approaches will be important for better understanding sleep physiology and function, as they provide a more comprehensive view of neural dynamics during sleep and wake in a relevant model system. Here, we present a brief summary of some of the findings derived from sleep activity recording studies in sleeping Drosophila flies and discuss the value of electrophysiological versus calcium imaging techniques. Although these involve very different preparations, they both highlight the value of multidimensional data for studying sleep in this model system, like the use of both EEG and fMRI in humans.

Multidimensional trait variability in a widespread, Paleoarctic macrophyte: functional, spectral and genetic drivers

Understanding how environmental conditions and plant functional variation are mutually related is critical to improving our comprehension of plant adaptations. In this context, our knowledge of the interlinks between plant functional, spectral and genetic traits and environmental filters is still very limited, especially for wetland species. To gain new insights on this topic, a multidimensional dataset, centred on the widespread macrophyte species Nuphar lutea, was assembled by collecting data on functional traits (including spectral traits), genetic metrics and environmental determinants from 28 plots spanning north‐central Italy. A strong environmental filter acts on all traits (morphological, biochemical, spectral and the genetic diversity metrics) resulting in significant local control over trait patterns, exemplified by the discrimination value of water electrical conductivity. This is further reinforced by the key contribution of sediment variables in explaining traits variation. Site‐specific environmental conditions were reflected in different patterns of genetic diversity, suggesting a long‐term effect of environmental filters on genotypes as well. High water conductivity – in our study sites indicative of long‐term hydrogeological settings – is linked to more acquisitive behaviour in N. lutea and a progressive reduction in its genetic diversity, while high nutrients availability in sediments promotes higher leaf traits performance. This study better explores how high variability in leaf traits reinforces current genetic and mechanistic knowledge about competitive strategies in the key aquatic plant N. lutea, by testing the effectiveness of a novel integrative approach to assess multiple sources of plant functional variation.

Hybrid ML-MDKL feature subset selection and classification technique accompanied with rat swarm optimizer to classify the multidimensional breast cancer mammogram image

Breast cancer is a pathological condition characterized by the abnormal proliferation of cells inside the breast tissue. The biggest challenge at the moment is determining the most optimal subset from large datasets. Numerous methodologies have been presented for the purpose of selecting the most suitable subset from datasets with high dimensions. However, the outcomes have proven to be insufficient in effectively addressing extensive quantities of multidimensional datasets. This publication presents a proposal for an efficient approach of selecting numerous feature subsets and performing classification on Multidimensional Datasets (MDD). In this study, the Moment Invariant Wavelet Feature Extraction (MI-WFE) approach is employed for the purpose of feature extraction. The New Adaptive Hybrid Levy Flight based Cuckoo Search Optimization Algorithm is employed to identify the most pertinent subset of features. This study presents a novel approach, referred to as H-RS-LVCSO, which aims to enhance the local search capability and optimization speed of the algorithm. This is achieved through the hybridization of the Rat Swarm Optimizer with the levy flight based cuckoo search optimization technique. In this study, it is suggested a hybridized approach for classifying breast cancer, utilizing a Multilayer Multiple Deep Kernel Learning (ML-MDKL) Classifier in conjunction with the standard Support Vector Machine (SVM) Classifier. The simulation of the suggested method is conducted using the MATLAB software. The approach under consideration is evaluated in comparison to two pre-existing methods. The suggested method demonstrates an accuracy improvement of 10.58% compared to existing methods. Furthermore, it outperforms these methods by 17.5% in terms of accuracy. The proposed method exhibits a precision improvement of 6.52% and 14.23% compared to the existing methods.

RNN-based CO2 minimum miscibility pressure (MMP) estimation for EOR and CCUS applications

Accurate estimation of minimum miscibility pressure (MMP) is crucial for assessing the efficiency of most miscible and immiscible processes, specifically CO2-based enhanced oil recovery (EOR) methods and Carbon capture utilization and sequestration (CCUS). The experimental procedure for MMP prediction is often time-consuming and costly. On the other hand, the empirical models that have been historically used could work based on limited input parameters, ignore the importance of others and are not necessarily accurate. The novelty of the current study is using an explainable deep-learning approach, Recurrent neural network (RNN), to train a model using a multi-dimensional (22 features) dataset with 544 rows of data. The Dataset comprises mole fractions of injected gas (pure and impure CO2). Out of those features, eight subsets of parameters (labelled X_1 to X_8) were used to develop models. The multi-dimensionality of the dataset makes it suitable to study the effects of various parameters on MMP, specifically in conditions of interest to CCUS-EOR applications. Among the multiple inputs tested, the model trained with X_1 and X_8 input parameters (including mole fraction of different hydrocarbon and nonhydrocarbon components and reservoir temperature) resulted in the most accurate estimations of MMP (R2 = 0.99). To further enhance the explainability of the model, feature importance and shapely values analysis were conducted on the developed models, and the impact of each input feature on MMP was elaborated. Temperature, volatile/intermediate, and nonhydrocarbon components are the most influential parameters depending on the subset of parameters chosen. Moreover, the developed model using X_8 inputs performed significantly better (37 % more accurately) than three well-known empirical models from the literature.

Rapid and green discrimination of bovine milk according to fat content, thermal treatment, brand and manufacturer via colloidal fingerprinting

Addressing food safety and detecting food fraud while fulfilling greenness requisites for analysis is a challenging but necessary task. The use of sustainable techniques, with limited pretreatment, non-toxic chemicals, high throughput results, is recommended. A combination of Field Flow Fractionation (FFF), working in saline carrier and with minimal preprocessing, and chemometrics was for the first time applied to bovine milk grouping. A set of 47 bovine milk samples was analyzed: a single analysis yielded a characteristic multidimensional colloidal dataset, that once processed with multivariate tools allowed simultaneously for different discriminations: fat content, thermal treatment, brand and manufacturing plant. The analytical methodology is fast, green, simple, and inexpensive and could offer great help in the field of quality control and frauds identification. This work represents also the first attempt to identify milk sub-typologies based on colloidal profiles, and the most complete study concerning multivariate analysis of FFF fingerprint.

An Ensemble Method for the Regression Model Parameter Adjustments: Direct Approach

Intelligence analysis of tabular datasets in the field of biomedical engineering is a complex task. This is explained both by the multidimensional datasets and the complex relationships between the components of the set, and by the high price of the error in the prediction. The task becomes more difficult in the case of limited data for training, which often occurs in this field. This is due to the enormous time, material, or human resources required to collect enough data to implement training procedures with classical machine learning tools. This paper presents a new approach to solving this task. The author has developed a new ensemble method for the regression model parameters adjustments (direct approach) with the possibility of cyclically increasing the accuracy of intellectual analysis of short datasets. The basis of the method is the use of the rational fraction and two machine learning algorithms for its parametric identification. Modeling of the method's efficiency on a real-world short set of data from the field of biomedical engineering demonstrated the high accuracy of the developed method's operation. In particular, the prediction accuracy of the General Regression Neural Network was increased by more than 14% (based on the coefficient of determination. That is why the developed method can be used to solve various applied biomedical engineering tasks in the case of the need to analyze small amounts of data

LogRule: Efficient Structured Log Mining for Root Cause Analysis

Accurate, timely Root Cause Analysis (RCA) is essential to successful IT operations as a primary step to incident remediation. RCA automation using data mining techniques in large heterogeneous systems is, however, a challenging task, because it requires correlating multimodal information across various data sources. An increasing number of services are migrating to structured logging to enable automated monitoring and debugging of complex large-scale systems. In this paper, we leverage structured logs and association rule mining (ARM) to automate RCA. We propose the LogRule algorithm, which automatically analyzes structured logs to generate a list of explanations for an event of interest. It achieves 0.921 F1-score for the diagnosis task, while computing results 37x faster compared to the state-of-the-art solution based on FP-growth, making it a time-efficient, accurate, and interpretable ARM-based RCA algorithm. Evaluation results show that LogRule enables RCA in complex multidimensional datasets, where the execution time of the current state-of-the-art algorithm is prohibitively large.

Analysis and predictability of technologists' perception of MR exam complexity

IntroductionAs MRI becomes a routine clinical diagnostic method, its complexity of techniques, protocols and scanning is growing. On the other hand, aggravated by the ubiquitous shortage of workforce, technologists' stress level and burnout rates are increasing. In this context, our study aims to shed light on technologists’ perceived complexity of MR exams, by analyzing a multidimensional dataset composed of workflow, patient, and operational details, and further predicting perceived exam complexity. MethodsIn this IRB-approved study, data about imaging workflow, exam context, and patient characteristics were collected over one year from MR modality logfiles and from technologist questionnaires, including the perceived exam complexity. The association of individual factors with complexity was analyzed via Fisher's exact tests and Cramér's V values. Predictability of exam complexity was further evaluated via ROC analysis of three different multivariate classifiers. ResultsRetakes, delays, and extended exam duration are associated with perceived complexity (V ≥ 0.2). From the set of possible predictors, patient mobility and communication ability have the most influence on perceived complexity (V > 0.2), followed by special equipment needs (pulse oximetry, intubation, or ECG), protocol details and other patient characteristics. Feasibility of predicting the perceived exam complexity from a multivariate set of exam and patient details known at the time of scheduling has been demonstrated (AUC = 0.73), and suitable classification algorithms have been identified. ConclusionPerceived exam complexity is associated with various factors. Our results suggest that it can be predicted sufficiently well to support early operational decision making. Some factors, however, may not be readily available in hospital IT systems and must be obtained before scheduling. Implications for practiceResults and observations of this study could be utilized to assist operational scheduling in the radiology department and reduce MR technologists’ stress levels.

Identifying Depression Through Machine Learning Analysis of Omics Data: Scoping Review.

Depression is one of the most common mental disorders that affects >300 million people worldwide. There is a shortage of providers trained in the provision of mental health care, and the nursing workforce is essential in filling this gap. The diagnosis of depression relies heavily on self-reported symptoms and clinical interviews, which are subject to implicit biases. The omics methods, including genomics, transcriptomics, epigenomics, and microbiomics, are novel methods for identifying the biological underpinnings of depression. Machine learning is used to analyze genomic data that includes large, heterogeneous, and multidimensional data sets. This scoping review aims to review the existing literature on machine learning methods for omics data analysis to identify individuals with depression, with the goal of providing insight into alternative objective and driven insights into the diagnostic process for depression. This scoping review was reported following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Searches were conducted in 3 databases to identify relevant publications. A total of 3 independent researchers performed screening, and discrepancies were resolved by consensus. Critical appraisal was performed using the Joanna Briggs Institute Critical Appraisal Checklist for Analytical Cross-Sectional Studies. The screening process identified 15 relevant papers. The omics methods included genomics, transcriptomics, epigenomics, multiomics, and microbiomics, and machine learning methods included random forest, support vector machine, k-nearest neighbor, and artificial neural network. The findings of this scoping review indicate that the omics methods had similar performance in identifying omics variants associated with depression. All machine learning methods performed well based on their performance metrics. When variants in omics data are associated with an increased risk of depression, the important next step is for clinicians, especially nurses, to assess individuals for symptoms of depression and provide a diagnosis and any necessary treatment.

Weighted distance classification method based on data intelligence

AbstractIn today's world, data is essential for enhancing an organization's development and decision‐making processes. Implementing artificial intelligence is necessary to analyse data and make meaningful recommendations. Machine learning distance classification methods are used to classify observations in various algorithms, such as K‐nearest neighbours (KNN), learning vector quantization and support vector machines, and are commonly used in academia and industry. However, this procedure faces a significant challenge in finding optimal parameters (i.e., distance metrics and the desired number of neighbours) in multidimensional datasets. This study presents a novel variation of a general method for classifying new observations. The method defines a new measure called closeness, which represents the proximity between an observation and the distribution. The advantages of this method are the use of both parametric and non‐parametric distance metrics and the ability to classify observations in cases where the simple method does not provide a clear answer. This method was demonstrated using KNN over three datasets and was observed to succeed in providing correct classifications, while the simple KNN method did not. The results showed that the proposed method increased the accuracy score to 40.7% in two of the three cases and that the closeness values were well defined by the proximity between the new observation and the given distribution. In addition, the F1 score increased up to 47.97%. The innovative method introduced here may be examined and used in various distance classification algorithms.

A feature-weighted suppressed possibilistic fuzzy c-means clustering algorithm and its application on color image segmentation

The possibilistic fuzzy c-means clustering (PFCM) algorithm is a hybridization of possibilistic c-means clustering (PCM) and fuzzy c-means clustering (FCM) algorithms. However, there are two main problems in PFCM. One is that the Euclidean distance employed in PFCM always disregards the imbalance among sample features because it treats all features of data equally, which easily causes misclassification for feature-imbalanced multidimensional data. The other is that PFCM always produces significant center deviations and overlapping centers for multiclass datasets with strong noise injection, due to the difficulty of PFCM in the membership-weight parameter setting and the lack of between-class relationships in possibilistic memberships. Therefore, a feature-weighted suppressed possibilistic fuzzy c-means clustering (FW-S-PFCM) algorithm is presented by introducing a feature-weighted method and “suppressed competitive learning” strategy into the PFCM algorithm in this paper. First, the FW-S-PFCM algorithm introduces a feature-weight matrix into the objective function that can automatically assign feature-weight values to different features and different clusters according to the distribution of samples, thus overcoming the influence of feature imbalance and improving clustering effects for noisy multidimensional datasets. Second, combined with the feature-weight matrix, a “suppressed competitive learning” strategy is designed to resolve the center-overlapping problem in noisy multiclass dataset clustering. Specifically, partial crucial points of each class near the center are selected according to a cluster core generated by a cross-section of a threshold on the possibilistic membership surface. Third, their possibilistic memberships participate in the suppressed learning process to overcome the lack of between-class relationships. Last, a segmentation algorithm for noisy color images based on FW-S-PFCM is proposed combined with the feature-weight method and noise-identification ability of possibilistic memberships. Experiments on synthetic data, UCI data and color image segmentation demonstrate that the proposed FW-S-PFCM algorithm can overcome the partial center-overlapping problem and improve clustering performance on complex datasets with feature imbalance and strong noise injection. The proposed algorithm can also reduce the iteration number, sensitivity to membership weights, and initializations of PFCM.

Machine learning and tectonic setting determination: Bridging the gap between Earth scientists and data scientists

Technological progress and the rapid increase in geochemical data often create bottlenecks in many studies, because current methods are designed using limited number of data and cannot handle large datasets. In geoscience, tectonic discrimination illustrates this issue, using geochemical analyses to define tectonic settings when most of the geological record is missing, which is the case for most of the older portion of the Earth’s crust. Basalts are the primary target for tectonic discrimination because they are volcanic rocks found within all tectonic settings, and their chemical compositions can be an effective way to understand tectonics-related mantle processes. However, the classical geochemical discriminant methods have limitations as they are based on a limited number of 2 or 3-dimensional diagrams and need successive and subjective steps that often offers non-unique solutions. Also, weathering, erosion, and orogenic processes can modify the chemical composition of basalts and eliminate or obscure other complementary geotectonic records. To address those limitations, supervised machine learning techniques (a part of artificial intelligence) are being utilized more often as a tool to analyze multidimensional datasets and statistically process data to tackle big data challenges. This contribution starts by reviewing the current state of tectonic discrimination methods using supervised machine learning. Deep learning, especially Convolutional Neural Network (CNN) is the most accurate approach. However, it requires a large dataset and considerable processing time, and the gain of accuracy can be at the expense of interpretability. Therefore, this study designed guidelines for data pre-processing, tectonic setting classification and objectively evaluating the model performance. We also identify research gaps and propose potential directions for the application of supervised machine learning to tectonic discrimination research, aimed at closing the divide between earth scientists and data scientists.

Deep Neural Network-Based Fusion Localization Using Smartphones

Indoor location-based services (LBS) have tremendous practical and social value in intelligent life due to the pervasiveness of smartphones. The magnetic field-based localization method has been an interesting research hotspot because of its temporal stability, ubiquitousness, infrastructure-free nature, and good compatibility with smartphones. However, utilizing discrete magnetic signals may result in ambiguous localization features caused by random noise and similar magnetic signals in complex symmetric and large-scale indoor environments. To address this issue, we propose a deep neural network-based fusion indoor localization system that integrates magnetic and pedestrian dead reckoning (PDR). In this system, we first propose a ResNet-GRU-LSTM neural network model to achieve magnetic localization more accurately. Afterward, we put forward a multifeatured-driven step length estimation. A hierarchy GRU (H-GRU) neural network model is proposed, and a multidimensional dataset using acceleration and a gyroscope is constructed to extract more valid characteristics. Finally, more reliable and accurate pedestrian localization can be achieved under the particle filter framework. Experiments were conducted at two trial sites with two pedestrians and four smartphones. Results demonstrate that the proposed system achieves better accuracy and robustness than other traditional localization algorithms. Moreover, the proposed system exhibits good generality and practicality in real-time localization with low cost and low computational complexity.

Spectral Background-subtracted Activity Maps

High-resolution solar spectroscopy provides a wealth of information from photospheric and chromospheric spectral lines. However, the volume of data easily exceeds hundreds of millions of spectra on a single observation day. Therefore, methods are needed to identify spectral signatures of interest in multidimensional data sets. Background-subtracted activity maps (BaSAMs) have previously been used to locate features of solar activity in time series of images and filtergrams. This research note shows how this method can be extended and adapted to spectral data.

Efficient Multidimensional Functional Data Analysis Using Marginal Product Basis Systems

In areas ranging from neuroimaging to climate science, advances in data storage and sensor technology have led to a proliferation in multidimensional functional datasets. A common approach to analyzing functional data is to first map the discretely observed functional samples into continuous representations, and then perform downstream statistical analysis on these smooth representations. It is well known that many of the traditional approaches used for 1D functional data representation are plagued by the curse of dimensionality and quickly become intractable as the dimension of the domain increases. In this article, we propose a computational framework for learning continuous representations from a sample of multidimensional functional data that is immune to several manifestations of the curse. The representations are constructed using a set of separable basis functions that are defined to be optimally adapted to the data. We show that the resulting estimation problem can be solved efficiently by the tensor decomposition of a carefully defined reduction transformation of the observed data. Roughness-based regularization is incorporated using a class of differential operator-based penalties. Relevant theoretical properties are also discussed. The advantages of our method over competing methods are thoroughly demonstrated in simulations. We conclude with a real data application of our method to a clinical diffusion MRI dataset. Supplementary materials for this article are available online.

A live-cell platform to isolate phenotypically defined subpopulations for spatial multi-omic profiling.

Numerous techniques have been employed to deconstruct the heterogeneity observed in normal and diseased cellular populations, including single cell RNA sequencing, in situ hybridization, and flow cytometry. While these approaches have revolutionized our understanding of heterogeneity, in isolation they cannot correlate phenotypic information within a physiologically relevant live-cell state with molecular profiles. This inability to integrate a live-cell phenotype-such as invasiveness, cell:cell interactions, and changes in spatial positioning-with multi-omic data creates a gap in understanding cellular heterogeneity. We sought to address this gap by employing lab technologies to design a detailed protocol, termed Spatiotemporal Genomic and Cellular Analysis (SaGA), for the precise imaging-based selection, isolation, and expansion of phenotypically distinct live cells. This protocol requires cells expressing a photoconvertible fluorescent protein and employs live cell confocal microscopy to photoconvert a user-defined single cell or set of cells displaying a phenotype of interest. The total population is then extracted from its microenvironment, and the optically highlighted cells are isolated using fluorescence activated cell sorting. SaGA-isolated cells can then be subjected to multi-omics analysis or cellular propagation for in vitro or in vivo studies. This protocol can be applied to a variety of conditions, creating protocol flexibility for user-specific research interests. The SaGA technique can be accomplished in one workday by non-specialists and results in a phenotypically defined cellular subpopulations for integration with multi-omics techniques. We envision this approach providing multi-dimensional datasets exploring the relationship between live cell phenotypes and multi-omic heterogeneity within normal and diseased cellular populations.

Combining remote sensing and tracking data to quantify species' cumulative exposure to anthropogenic change.

Identifying when and where organisms are exposed to anthropogenic change is crucial for diagnosing the drivers of biodiversity declines and implementing effective conservation measures. Accurately measuring individual-scale exposure to anthropogenic impacts across the annual cycle as they move across continents requires an approach that is both spatially and temporally explicit-now achievable through recent parallel advances in remote-sensing and individual tracking technologies. We combined 10 years of tracking data for a long-distance migrant, (common cuckoo, Cuculus canorus), with multi-dimensional remote-sensed spatial datasets encompassing thirteen relevant anthropogenic impacts (including infrastructure, hunting, habitat change, and climate change), to quantify mean hourly and total accumulated exposure of tracked individuals to anthropogenic change across each stage of the annual cycle. Although mean hourly exposure to anthropogenic change was greatest in the breeding stage, accumulated exposure to changes associated with direct mortality risks (e.g., built infrastructure) and with climate were greatest during the wintering stage, which comprised 63% of the annual cycle on average for tracked individuals. Exposure to anthropogenic change varied considerably within and between migratory flyways, but there were no clear between-flyway differences in overall exposure during migration stages. However, more easterly autumn migratory routes were significantly associated with lower subsequent exposure to anthropogenic impacts in the winter stage. Cumulative change exposure was not significantly associated with recent local-scale population trends in the breeding range, possibly because cuckoos from shared breeding areas may follow divergent migration routes and therefore encounter very different risk landscapes. Our study highlights the potential for the integration of tracking data and high-resolution remote sensing to generate valuable and detailed new insights into the impacts of environmental change on wild species.

Multidimensional Knapsack 0-1 Solution With Algorithm Evolution Pso-Ga

This paper develops the particle swarm optimization (PSO) method and uses a genetic algorithm (GA) by changing the distribution of articles in the initialization of the initial position. PSO at this time the search and speed of particles will always go to the best solution so that by narrowing the search area will be faster by updating the best position of PSO. While the Genetic algorithm plays a role to get an expanded search area for PSO solutions by utilizing crossover and mutation in GA. So that GA will expand the range of candidates for the best solution in PSO. From each of the advantages of PSO Update and GA will be combined to get Evolutionary PSO-GA (EVPGA) that can minimize error and speed up computation (itation) in finding the best solution. By using the Multidimensional Knapsack data set, the results of EVPGA get an average speed of 24.9s with an error of 1.49%.

Game analysis of product specifications for design optimisation using big sales data

Product specifications that precisely describe customers’ preference for product comparison and purchase decision-making are critical to product competitiveness. Competitive specifications’ determination requires a better understanding of the comparison-oriented product competition mechanism. Big sales data that consist of comprehensive and multi-dimensional datasets of products are valuable sources for the investigation of the specification competition mechanism. In this work, the relative satisfaction hypothesis and rational comparison hypothesis are proposed on the basis of product competition analysis. A framework is proposed to support rational design decisions in the context of competitiveness-oriented design optimisation. This framework is based on game analysis of product specifications using big sales data. Initially, competing products in the market are collected and modelled for game analysis. To monitor the competition mechanism of specifications amongst competing products, the relative satisfaction is then defined to evaluate the comparison results of product specifications. By comparing different specifications and their combinations, four design scenarios (i.e. dominant, dominated, equivalent and mixed design) are identified for design evaluation. Similarities amongst specifications are considered for supporting both homogeneous and differentiated competition. Ultimately, a bi-level optimisation model is proposed for enhancing product competitiveness. A case study illustrates the implementation of the proposed method.

Synthetic Generation of Multidimensional Data to Improve Classification Model Validity

This article aims to compare Generative Adversarial Network (GAN) models and feature selection methods for generating synthetic data in order to improve the validity of a classification model. The synthetic data generation technique involves generating new data samples from existing data to increase the diversity of the data and help the model generalize better. The multidimensional aspect of the data refers to the fact that it can have multiple features or variables that describe it. The GAN models have proven to be effective in preserving the statistical properties of the original data. However, the order of data augmentation and feature selection is crucial to build robust and accurate predictive models. By comparing the different GAN models with feature selection methods on multidimensional datasets, this article aims to determine the best combination to support the validity of a classification model in multidimensional data.