Unsupervised Learning Approach Research Articles

A coupled approach of spatial dielectric mapping and unsupervised machine learning for damage detection and severity segmentation in polymer matrix composites

The inevitable presence of moisture within a polymer composite has allowed for the development of a novel dielectric nondestructive evaluation (NDE) technique which capitalizes on the behavior of moisture under an applied electromagnetic field. Relative permittivity of water which is bound to the polymer network differ significantly from that of water which is not bound to the network, and the preferential diffusion of this “free” water to damage sites permits the creation of spatial permittivity maps. Presently, this technique has shown capability for damage detection but has not achieved quantification, which is crucial for industry use. The introduction of machine learning algorithms to existing techniques in this field has proven valuable, thus, a machine learning approach for data processing and damage quantification to the existing dielectric technique was developed and applied in this work. BMI/Quartz samples and S2-Glass/Epoxy samples were fabricated and subjected to impact damage via drop tower. The BMI samples were impacted centrally at 9 J and the S2-Glass samples were subjected to two impact events of differing energies, 5 and 3 J. An unsupervised K-means clustering algorithm was applied to the acquired dielectric scans at different gravimetric moisture contents which has provided promising results for all samples. Specifically, within the two impact samples, the algorithm assigned a higher cluster center to the site with more damage, indicating the technique has the capability to both detect and quantify impact damage at all moisture levels examined.

A Review of Machine Learning Approaches for Rumour Detection: Techniques, Challenges, and Future Directions (Machine Learning for Rumour Detection)

Rumours and misinformation propagate rapidly across online social networks, posing significant challenges to maintaining the integrity of information dissemination. In recent years, machine learning (ML) techniques have emerged as promising tools for automating the detection and mitigation of rumours. This review paper provides a comprehensive examination of the advancements in rumour detection using ML approaches. The paper begins by outlining the landscape of rumour dissemination in online social networks, highlighting the characteristics and challenges associated with rumour detection. Subsequently, it systematically categorizes and analyzes various ML methods employed for rumour detection, including supervised, unsupervised, and semi-supervised learning approaches. Furthermore, the review delves into the diverse features and representations utilized in ML models for rumour detection, such as textual content, user engagement patterns, network structures, and temporal dynamics. It discusses the strengths and limitations of different feature sets and their impact on the effectiveness of rumour detection systems. Moreover, the paper explores the intricacies of dataset construction and evaluation methodologies for training and testing rumour detection models. It examines commonly used benchmark datasets and evaluation metrics, emphasizing the importance of robust evaluation frameworks for assessing the performance of ML-based rumour detection systems accurately. Additionally, the review identifies key challenges and open research questions in the field of rumour detection using ML, including handling evolving rumour patterns, addressing adversarial attacks, and enhancing the interpretability and explain ability of ML models. It also discusses potential directions for future research aimed at advancing the state-of-the-art in rumour detection and mitigation.

Anomaly Detection in the Automotive Stamping Process: An Unsupervised Machine Learning Approach

In metal forming, such as stamping of automotive parts, unsupervised machine learning models offer a transformative approach to real-time quality control, especially when labelled data are scarce. Leveraging clustering algorithms and autoencoders, we develop a machine learning system capable of autonomously monitoring sensor data and identifying deviations suggestive of potential defects. The system offers multiple benefits including rapid intervention, reduced part defects and lower stoppages required to rectify defects. The use of unsupervised machine learning models also adds a layer of adaptability, allowing the system to continually refine its understanding of what constitutes a ‘normal’ operation. Empirical evaluation demonstrates the potential of the developed system in detecting anomalies in production data collected from dynamic automotive manufacturing environments.

Label-free morphometric characterization of T cells for cell and gene therapy research and development.

Abstract Identification, characterization, and minimally invasive isolation of T cells is critical for developing cellular therapies. Here we used VisionSort, an artificial intelligence (AI)-driven cellular analysis and sorting platform, to characterize and isolate human T cell subsets with therapeutically relevant phenotypes, label-free. By capturing single-cell digital phenotypes, we characterized human T-cells and generated ‘ground truth’ functional profiles for 1) glycolysis level, 2) exhaustion state 3) activation or resting profiles and 4) viability. A set of machine-learning derived classifiers was generated to identify these phenotypic classes label-free. The classifiers showed area under the curve (AUC) performance ranges for detecting specific, phenotypically defined T-cell populations between 0.923 and 0.995. Using a combination of supervised and unsupervised machine learning approaches, we also show identification of follicular helper T (Tfh) cells from other CD4+ T cells based on morphology alone. When we analyzed the morphological profiles of T cell subsets by unsupervised machine learning using uniform maniform projection and approximation (UMAP), we found that both gamma delta (γδ) T cells were distinct from alpha beta (αβ) T cells and CD8+ T cells were distinct from CD4+ T cells. Here we report on the use of AI-based cytometry to characterize and isolate phenotypically defined T cell subsets label-free, with applications in basic life science and cell therapy R&D.

Dissecting shared e-scooters usage patterns and its impact on other transportation modes: A case study of Portland city

The study analyzed the survey data from the 2018 Portland E-scooter Pilot Program and aims to determine (i) who uses shared e-scooters and why they use them, and (ii) whether there is any association between e-scooter usage and the usage of other modes of transportation. To accomplish the first objective, the study identifies the users of shared e-scooters based on their travel behavior using an unsupervised machine learning approach, latent class analysis (LCA). The LCA model grouped e-scooter users into three distinct classes: Class 1 (Recreational Enthusiasts) −occasional and frequent users for recreation, Class 2 (Commute Riders) −frequent users for work, and Class 3 (Intermittent Joyriders) −occasional and one-time users for recreation. Furthermore, a set of ordered logit models is employed to determine the second objective based on the identified classes of e-scooter users, their socio-demographic characteristics, and the built environment variables. The results of ordered logit models revealed that compared to Commute Riders, both Recreational Enthusiasts and Intermittent Joyriders exhibit less interest in increasing the usage of available transportation modes after adopting e-scooters. Notably, low-income e-scooter users show a higher probability of increasing their usage across various transportation modes, including public transportation, driving, shared mobility services, personal bikes, shared bikes, and walking. The study offers valuable insights to guide city planners and policymakers in developing effective strategies for the deployment of e-scooters, targeting each group of users.

Ensemble Approach Using k-Partitioned Isolation Forests for the Detection of Stock Market Manipulation

Stock market manipulation, defined as any attempt to artificially influence stock prices, poses significant challenges by causing financial losses and eroding investor trust. The prevalent reliance on supervised learning models for detecting such manipulations, while showing promise, faces notable hurdles due to the dearth of labeled data and the inability to recognize novel manipulation tactics beyond those explicitly labeled. This study ventures into addressing these gaps by proposing a novel detection framework aimed at identifying suspicious hourly manipulation blocks through an unsupervised learning approach, thereby circumventing the limitations of data labeling and enhancing the adaptability to emerging manipulation strategies. Our methodology involves the innovative creation of features reflecting the behavior of stocks across various time windows followed by the segmentation of the dataset into k subsets. This setup facilitates the identification of potential manipulation instances via a voting ensemble composed of k isolation forest models, which have been chosen for their efficiency in pinpointing anomalies and their linear computational complexity—attributes that are critical for analyzing vast datasets. Evaluated against eight real stocks known to have undergone manipulation, our approach demonstrated a remarkable capability to identify up to 89% of manipulated blocks, thus significantly outperforming previous methods that do not utilize a voting ensemble. This finding not only surpasses the detection rates reported in prior studies but also underscores the enhanced robustness and adaptability of our unsupervised model in uncovering varied manipulation schemes. Through this research, we contribute to the field by offering a scalable and efficient unsupervised learning strategy for stock manipulation detection, thereby marking a substantial advancement over traditional supervised methods and paving the way for more resilient financial markets.

Gut microbiota composition in travellers is associated with faecal lipocalin-2, a mediator of gut inflammation.

We examined the gut microbiota of travellers returning from tropical areas with and without traveller's diarrhoea (TD) and its association with faecal lipocalin-2 (LCN2) levels. Participants were recruited at the Hospital Clinic of Barcelona, Spain, and a single stool sample was collected from each individual to perform the diagnostic of the etiological agent causing gastrointestinal symptoms as well as to measure levels of faecal LCN2 as a biomarker of gut inflammation. We also characterised the composition of the gut microbiota by sequencing the region V3-V4 from the 16S rRNA gene, and assessed its relation with the clinical presentation of TD and LCN2 levels using a combination of conventional statistical tests and unsupervised machine learning approaches. Among 61 participants, 45 had TD, with 40% having identifiable etiological agents. Surprisingly, LCN2 levels were similar across groups, suggesting gut inflammation occurs without clinical TD symptoms. Differential abundance (DA) testing highlighted a microbial profile tied to high LCN2 levels, marked by increased Proteobacteria and Escherichia-Shigella, and decreased Firmicutes, notably Oscillospiraceae. UMAP analysis confirmed this profile's association, revealing distinct clusters based on LCN2 levels. The study underscores the discriminatory power of UMAP in capturing meaningful microbial patterns related to clinical variables. No relevant differences in the gut microbiota composition were found between travellers with or without TD. The findings suggest a correlation between gut microbiome and LCN2 levels during travel, emphasising the need for further research to discern the nature of this relationship.

Early detection of closed-loop slugging patterns in offshore oil wells with unsupervised learning approaches

In offshore wells, severe slugs are frequent problems that can limit oil production. It has already been proven that active pressure control can mitigate this effect, but defining the setpoint is still a manual task that requires constant human intervention. This study proposes a novel approach utilizing machine learning to aid the search for optimal production levels while preventing severe slugging. Two unsupervised machine learning methods, namely Self-Organizing Maps (SOM) and Generative Topographic Mapping (GTM), were evaluated for the early detection of slugging patterns in offshore oil wells. This study utilizes simulated FOWM model data to construct the necessary database. Additionally, real-world well data underwent SOM and GTM analysis, providing valuable insights from practical contexts. Both SOM and GTM showed promising results. However, GTM outperformed SOM in terms of mapping orientation and prediction scores. In addition, the GTM was easier to optimize in terms of hyperparameters for map tuning.

Empirically derived symptom profiles in adults with attention-Deficit/hyperactivity disorder: An unsupervised machine learning approach

Background Attention-deficit/hyperactivity disorder (ADHD) is associated with various cognitive, behavioral, and mood symptoms that complicate diagnosis and treatment. The heterogeneity of these symptoms may also vary depending on certain sociodemographic factors. It is therefore important to establish more homogenous symptom profiles in patients with ADHD and determine their association with the patient’s sociodemographic makeup. The current study used unsupervised machine learning to identify symptom profiles across various cognitive, behavioral, and mood symptoms in adults with ADHD. It was then examined whether symptom profiles differed based on relevant sociodemographic factors. Methods Participants were 382 adult outpatients (62% female; 51% non-Hispanic White) referred for neuropsychological evaluation for ADHD. Results Employing Gaussian Mixture Modeling, we identified two distinct symptom profiles in adults with ADHD: “ADHD-Plus Symptom Profile” and “ADHD-Predominate Symptom Profile.” These profiles were primarily differentiated by internalizing psychopathology (Cohen’s d = 1.94-2.05), rather than by subjective behavioral and cognitive symptoms of ADHD or neurocognitive test performance. In a subset of 126 adults without ADHD who were referred for the same evaluation, the unsupervised machine learning algorithm only identified one symptom profile. Group comparison analyses indicated that female patients were most likely to present with an ADHD-Plus Symptom Profile (χ2 = 5.43, p < .001). Conclusion The machine learning technique used in this study appears to be an effective way to elucidate symptom profiles emerging from comprehensive ADHD evaluations. These findings further underscore the importance of considering internalizing symptoms and patients’ sex when contextualizing adult ADHD diagnosis and treatment.

County-level prioritization for managing the Covid-19 pandemic: a systematic unsupervised learning approach

PurposeThe COVID-19 pandemic has posed many challenges in almost all sectors around the globe. Because of the pandemic, government entities responsible for managing health-care resources face challenges in managing and distributing their limited and valuable health resources. In addition, severe outbreaks may occur in a small or large geographical area. Therefore, county-level preparation is crucial for officials and organizations who manage such disease outbreaks. However, most COVID-19-related research projects have focused on either state- or country-level. Only a few studies have considered county-level preparations, such as identifying high-risk counties of a particular state to fight against the COVID-19 pandemic. Therefore, the purpose of this research is to prioritize counties in a state based on their COVID-19-related risks to manage the COVID outbreak effectively.Design/methodology/approachIn this research, the authors use a systematic hybrid approach that uses a clustering technique to group counties that share similar COVID conditions and use a multi-criteria decision-making approach – the analytic hierarchy process – to rank clusters with respect to the severity of the pandemic. The clustering was performed using two methods, k-means and fuzzy c-means, but only one of them was used at a time during the experiment.FindingsThe results of this study indicate that the proposed approach can effectively identify and rank the most vulnerable counties in a particular state. Hence, state health resources managing entities can identify counties in desperate need of more attention before they allocate their resources and better prepare those counties before another surge.Originality/valueTo the best of the authors’ knowledge, this study is the first to use both an unsupervised learning approach and the analytic hierarchy process to identify and rank state counties in accordance with the severity of COVID-19.

Exploring the InSAR Deformation Series Using Unsupervised Learning in a Built Environment

As a city undergoes large-scale construction and expansion, there is an urgent need to monitor the stability of the ground and infrastructure. The time-series InSAR technique is an effective tool for measuring surface displacements. However, interpreting these displacements in a built environment, where observed displacements consist of mixed signals, poses a challenge. This study uses principal component analysis (PCA) and the k-means clustering method for exploring deformation series within an unsupervised learning context. The PCA method extracts the dominant components in deformation series, whereas the clustering method identifies similar deformation series. This method was tested on Kunming City (KMC) using C-band Sentinel-1, X-band TerraSAR-X, and L-band ALOS-2 PALSAR-2 data acquired between 2017 to 2022. The experiment demonstrated that the suggested unsupervised learning approach can group PS points with similar kinematic characteristics. Five types of deformation kinematic characteristics were discovered in the three SAR datasets: upward, slight upward, stability, slight downward, and downward. According to the results, less than 20% of points exhibit significant motion trends, whereas 50% show small velocity values but still demonstrate movement trends. The remaining 30% are relatively stable. Similar clustering results were obtained from the three datasets using unsupervised methods, highlighting the effectiveness of identifying spatial–temporal patterns over the study area. Moreover, It was found that clustering based on kinematic characteristics enhances the interpretation of InSAR deformation, particularly for points with small deformation velocities. Finally, the significance of PCA decomposition in interpreting InSAR deformation was discussed, as it can better represent series with noise, enabling their accurate identification.

Assessment of TGx-DDI genes for genotoxicity in a comprehensive panel of chemicals

Background The TGx-DDI biomarker identifies transcripts specifically induced by primary DNA damage. Profiling similarity of TGx-DDI signatures can allow clustering compounds by genotoxic mechanism. This transcriptomics-based approach complements conventional toxicology testing by enhancing mechanistic resolution. Methods Unsupervised hierarchical clustering and t-distributed stochastic neighbor embedding (tSNE) were utilized to assess similarity of publicly-available per- and polyfluoroalkyl substances (PFAS) and ToxCast chemicals based on TGx-DDI modulation. TempO-seq transcriptomic data after highest chemical concentrations were analyzed. Results Clustering discriminated between genotoxic and non-genotoxic compounds while drawing similarity among chemicals with shared mechanisms. PFAS largely clustered distinctly from classical mutagens. However, dynamic range across PFAS types and durations indicated variable potential for DNA damage. tSNE visualization reinforced phenotypic groupings, with genotoxins clustering separately from non-DNA damaging agents. Discussion Unsupervised learning approaches applied to TGx-DDI profiles effectively categorizes chemical genotoxicity potential, aiding elucidation of biological response pathways. This transcriptomics-based strategy gives further insight into the role and effect of individual TGx-DDI biomarker genes and complements existing assays by enhancing mechanistic resolution. Overall, TGx-DDI biomarker profiling holds promise for predictive safety screening.

An unsupervised machine learning approach for real-time damage detection in bridges

The bridge network is progressively aging, with an alarming proportion of bridges over 100 years. This situation engenders substantial risks to the overall reliability of transportation networks, requiring innovative methods for efficient management. Monitoring can provide a direct source of information about structural behavior generating alerts when changes occur. Real-time alerts enable effective infrastructure management and decision-making during damage or anomalous situations. However, monitoring can result in a large amount of data that is often difficult to convert into valuable information in real time. This paper presents an approach for real-time detection of abrupt damage occurrence in bridges using unsupervised anomaly detection algorithms and strain/acceleration measurements. The approach incorporates the separation of measurements into events having the same loading nature and the construction of three feature matrices based on statistical features, time-frequency features, and wavelet spectrum features. It includes the evaluation of five anomaly detection algorithms including Isolation Forest, One-Class Support Vector Machine, Robust Random Cut Forest, Local Outlier Factor, and Mahalanobis Distance. The approach is illustrated with a case study of a steel-bascule-railway bridge, that has experienced a brittle cracking event during monitoring. Results highlight the robustness of One-Class Support Vector Machine, Isolation Forest, and Local Outlier Factor algorithms in promptly detecting abrupt changes across different features. The separation of strain and acceleration data into loading-based events, coupled with the comparison of previous and new event features, provides robust feature matrices for effective damage detection. Enhanced detection and higher scores are particularly attributed to time-frequency domain features during damage occurrence. The presented approach can be used as a base on how to perform real-time anomaly detection within the context of bridge monitoring.

A network of transcriptomic signatures identifies novel comorbidity mechanisms between schizophrenia and somatic disorders

The clinical burden of mental illness, in particular schizophrenia and bipolar disorder, are driven by frequent chronic courses and increased mortality, as well as the risk for comorbid conditions such as cardiovascular disease and type 2 diabetes. Evidence suggests an overlap of molecular pathways between psychotic disorders and somatic comorbidities. In this study, we developed a computational framework to perform comorbidity modeling via an improved integrative unsupervised machine learning approach based on multi-rank non-negative matrix factorization (mrNMF). Using this procedure, we extracted molecular signatures potentially explaining shared comorbidity mechanisms. For this, 27 case–control microarray transcriptomic datasets across multiple tissues were collected, covering three main categories of conditions including psychotic disorders, cardiovascular diseases and type II diabetes. We addressed the limitation of normal NMF for parameter selection by introducing multi-rank ensembled NMF to identify signatures under various hierarchical levels simultaneously. Analysis of comorbidity signature pairs was performed to identify several potential mechanisms involving activation of inflammatory response auxiliarily interconnecting angiogenesis, oxidative response and GABAergic neuro-action. Overall, we proposed a general cross-cohorts computing workflow for investigating the comorbid pattern across multiple symptoms, applied it to the real-data comorbidity study on schizophrenia, and further discussed the potential for future application of the approach.

Medical nearest-word embedding technique implemented using an unsupervised machine learning approach for Bengali language

Abstract The rapid growth of natural language processing (NLP) applications, such as text summarization, speech recognition, information extraction, and machine translation, has led to the development of structured query language (SQL) for extracting information from structured data. However, due to limited resources, converting Natural Language (NL) queries to SQL in Bengali is challenging. This article proposes an unsupervised machine learning model to find semantically Bengali closed words that can generate SQL from NL queries in Bengali. The main objective of the proposed system is to provide support in the creation of patient-oriented explanations and educational resources by simplifying intricate medical terminology. The major findings of the proposed system are as follows: The use of machine translation in the field of medicine facilitates the dissemination of healthcare information to a diverse international audience and improves the performance of entity recognition tasks, including the identification of medical conditions, drugs, or procedures within clinical notes or electronic health data. This system allows a naive user to extract health-related information from a healthcare-structured database without any knowledge of SQL. The system accepts a query and generates a response according to the query in Bengali language. Query tokenization and stop word removal are carried out in the preprocessing stage, and unsupervised machine learning techniques are implemented to process the input query sentence. Tokenized words are converted into vectors using the skip-gram model, with noise-contrastive estimation (NCE) applied to discriminate between actual and irrelevant words. Stochastic gradient descent (SGD) optimizes the model by randomly choosing a small amount of data from the dataset and using cosine similarity to measure closer words. The semantically closer words are found using an unsupervised learning method to generate the SQL.

Analyzing Heterogeneous Networks With Missing Attributes by Unsupervised Contrastive Learning.

Heterogeneous information networks (HINs) are potent models of complex systems. In practice, many nodes in an HIN have their attributes unspecified, resulting in significant performance degradation for supervised and unsupervised representation learning. We developed an unsupervised heterogeneous graph contrastive learning approach for analyzing HINs with missing attributes (HGCA). HGCA adopts a contrastive learning strategy to unify attribute completion and representation learning in an unsupervised heterogeneous framework. To deal with a large number of missing attributes and the absence of labels in unsupervised scenarios, we proposed an augmented network to capture the semantic relations between nodes and attributes to achieve a fine-grained attribute completion. Extensive experiments on three large real-world HINs demonstrated the superiority of HGCA over several state-of-the-art methods. The results also showed that the complemented attributes by HGCA can improve the performance of existing HIN models.

Neuroinflammation in Recent Onset Mental Health Disorders – Developing Multi-level Signatures of Early-stage Depression and Psychosis in Young Adults

IntroductionAn early and comprehensive neurobiological characterization of severe mental disorders could elucidate mechanistic pathways, aid the development of novel therapeutics, and therefore enable timely and targeted intervention in at-risk youth and young adults. Therefore, we present an unsupervised transdiagnostic machine learning approach to investigate shared and distinct patterns of early-stage depressive and psychotic disorders on multiple clinical and neurobiological levels.ObjectivesTo derive multi-level neurobiological and clinical signatures of early-stage affective and psychotic disorders in adolescents and young adults.MethodsFrom the multicenter prospective European PRONIA cohort, we acquired data from 678 individuals (51% female) comprising young, minimally medicated in- and outpatients with clinical high-risk (CHR) states for psychosis, with recent-onset depression (ROD) or psychosis (ROP), and healthy control (HC) individuals. Within repeated nested cross-validation frameworks, we employed Sparse Partial Least Squares Analysis to detect associations between blood markers and grey matter volume (GMV), followed by support vector machine prediction of these signatures using biographical, clinical, neurocognitive, proteomic, and functional data.ResultsOur results demonstrated a psychosis staging signature separating ROP from CHR individuals via GMV patterns in the cortico-thalamo-cerebellar circuitry with a blood marker set of elevated of IL-6, TNF-α and CRP (ρ = 0.272; P = 0.002). A depression signature separated ROD from HC individuals via altered GMV in the limbic system with a blood marker set of elevated IL-1ß, IL-2, IL-4, S100B and BDNF (ρ = 0.186; P = 0.021). Only the psychosis staging signature showed a distinct proteomic enrichment regarding innate immune response, abnormal neutrophil function, cellular senescence, and anti-inflammatory drugs (Balanced Accuracy (BAC) = 87.73%; Area Under the Curve (AUC) = 0.94). Childhood trauma differentially predicted psychosis and depression signatures, while past level of functioning, personality and quality of life was predictive of both signatures (BAC = 67.19-78.00%; AUC = 0.71-0.83).Image:Image 2:Image 3:ConclusionsPsychosis and depression exhibit distinct multi-level signatures evident in early disease stages. Enhanced insight into these signatures could help delineate individual trajectories and potentially new mechanisms for pharmacological treatment.Disclosure of InterestNone Declared

Exploring the interpretability of the BERT model for semantic similarity

This study addresses the issue of semantic similarity in sentences using the BERT model through various aggregation techniques, such as max-pooling, mean-pooling, and an LSTM network applied to the output of the BERT model. Subsequently, the linguistic interpretability of the BERT-Base transformer model is analyzed through the unsupervised learning approach, specifically through dimensionality reduction using autoencoders and clustering algorithms, utilizing the representation of the classification token CLS. The results highlight that the CLS classification token achieves better abstractions than the proposed methods. In terms of interpretability, it is observed that sequence length is relevant in the early layers, with a gradual decrease across the layers. Additionally, attention to semantic similarity is concentrated in the intermediate and upper layers, especially in layers 6, 8, 9, and 10. All these findings were obtained by addressing the semantic similarity task using the STS-Benchmark dataset.

Assessing heterogeneous groundwater systems: Geostatistical interpretation of well logging data for estimating essential hydrogeological parameters

This research presents an unsupervised learning approach for interpreting well-log data to characterize the hydrostratigraphical units within the Quaternary aquifer system in Debrecen area, Eastern Hungary. The study applied factor analysis (FA) to extract factor logs from spontaneous potential (SP), natural gamma ray (NGR), and resistivity (RS) logs and correlate it to the petrophysical and hydrogeological parameters of shale volume and hydraulic conductivity. This research indicated a significant exponential relationship between the shale volume and the scaled first factor derived through factor analysis. As a result, a universal FA-based equation for shale volume estimation is derived that shows a close agreement with the deterministic shale volume estimation. Furthermore, the first scaled factor is correlated to the decimal logarithm of hydraulic conductivity estimated with the Csókás method. Csókás method is modified from the Kozeny-Carman equation that continuously estimates the hydraulic conductivity. FA and Csókás method-based estimations showed high similarity with a correlation coefficient of 0.84. The use of factor analysis provided a new strategy for geophysical well-logs interpretation that bridges the gap between traditional and data-driven machine learning techniques. This approach is beneficial in characterizing heterogeneous aquifer systems for successful groundwater resource development.

An Unsupervised Learning Approach to Evaluate Questionnaire Data—What One Can Learn from Violations of Measurement Invariance

An Unsupervised Learning Approach to Evaluate Questionnaire Data—What One Can Learn from Violations of Measurement Invariance