Gaussian Mixture Research Articles

Learning glass transition temperatures via dimensionality reduction with data from computer simulations: Polymers as the pilot case

Machine learning methods provide an advanced means for understanding inherent patterns within large and complex datasets. Here, we employ the principal component analysis (PCA) and the diffusion map (DM) techniques to evaluate the glass transition temperature (Tg) from low-dimensional representations of all-atom molecular dynamic simulations of polylactide (PLA) and poly(3-hydroxybutyrate) (PHB). Four molecular descriptors were considered: radial distribution functions (RDFs), mean square displacements (MSDs), relative square displacements (RSDs), and dihedral angles (DAs). By applying Gaussian Mixture Models (GMMs) to analyze the PCA and DM projections and by quantifying their log-likelihoods as a density-based metric, a distinct separation into two populations corresponding to melt and glass states was revealed. This separation enabled the Tg evaluation from a cooling-induced sharp increase in the overlap between log-likelihood distributions at different temperatures. Tg values derived from the RDF and MSD descriptors using DM closely matched the standard computer simulation-based dilatometric and dynamic Tg values for both PLA and PHB models. This was not the case for PCA. The DM-transformed DA and RSD data resulted in Tg values in agreement with experimental ones. Overall, the fusion of atomistic simulations and DMs complemented with the GMMs presents a promising framework for computing Tg and studying the glass transition in a unified way across various molecular descriptors for glass-forming materials.

Acoustic emission monitoring of damage modes in reinforced concrete beams by using narrow partial power bands

This work presents an acoustic emission (AE) based method, named a series of narrow partial power bands (SN2PB), to monitor the damage mechanisms within reinforced concrete beams during quasi-static bending tests. Unlike conventional time-domain methods, which give a global view of the involved cracking modes, SN2PB has the advantage of obtaining information on cracking modes within each AE hit in reduced frequency bands. SN2PB is applied by dividing the frequency content of each AE signal into narrow bands. Results show that the same AE signal can contain shear and tension cracking signatures at the lower and upper frequency bands, respectively. This work shows also the presence of a transitional domain between the two distinct bands. Changes and fluctuations corresponding to the involved mechanisms during the entire mechanical tests are therefore followed and visualized in the form of a heatmap. Moreover, the densities of the shear and tensile mechanisms at an instant are also determined using a Gaussian Mixture Model. Results show that the separation obtained using the SN2PB method is more advantageous than that of the conventional method based on the average frequency and the RA parameter.

Genetic diversity insights from population genomics and machine learning tools for Nordic Arctic charr (Salvelinus alpinus) populations

Arctic charr (Salvelinus alpinus) is a salmonid species of high ecological and commercial value in the Holarctic region. Nevertheless, more information is needed about its underlying genetic diversity and population structure in the Nordics, especially regarding farmed populations. High-throughput sequencing was applied in three Arctic charr populations of anadromous or landlocked origin from Finland, Norway and Sweden. More specifically, the animals from the Swedish and Norwegian populations originated from a major egg supplier and producer, respectively. Furthermore, in the case of the Finnish population, the sampled animals originated from the only active conservation program for Arctic charr in the country with a potential interest in farming. Using double-digest restriction site-associated DNA sequencing (ddRAD-seq) on more than 500 fish, over 2000 single nucleotide polymorphisms (SNPs), both in the form of individual SNPs and as read haplotypes, were used to study the genetic diversity and structure of those populations. Genetic diversity metrics were similar between the Norwegian and the Swedish populations. However, substantially lower (40–50 %) genetic diversity was found in the Finnish population. Moreover, considerable genetic differentiation was implied between the studied populations as the mean fixation index (FST) was above 0.1 in all pairwise comparisons. All populations were easily discernible through either principal component analysis (PCA) or discriminant analysis of principal components (DAPC). In addition, unsupervised machine learning models such as K-means, Gaussian and Bayesian Gaussian mixtures were assessed for their ability to detect genetic clusters. A preceding dimensionality reduction step by PCA resulted in all three models, suggesting that the most probable number of clusters was three. Overall, our study affirmed the utility of the developed ddRAD-seq genotyping method and unveiled the genetic structure of the studied populations, both of which could contribute to their more efficient management by captive breeding.

Biologically inspired adaptive crack network reconstruction based on slime mould algorithm.

The dynamic crack propagation trajectories play a crucial role in enhancing our understanding of spatial mechanisms involved in crack expansion. However, visualization of internal cracks under complex crack conditions has always been a challenge. Biological networks have been honed by many cycles of evolutionary selection pressure and are likely to yield reasonable solutions to such combinatorial optimization problems. This study applied the slime mould algorithm to improve the accuracy of internal crack localization in rocks and employed Minimum spanning tree and Gaussian mixture model to construct the crack propagation trajectories. By introducing the concept of bond length, the evolution characteristics of crack levels were effectively characterized. Research results showed that this approach effectively preserves essential crack localization information while mitigating the influence of interfering parameters, providing crack characterization results that exhibit high consistency with actual fracture patterns. The curves of cumulative bond length and relative bond length over time conform to the trend of a Growth/Sigmoidal curve. The strength of the bond was correlated with the temporal process of crack propagation. This result could be helpful for analyzing crack trajectories and predicting rock stability.

A stochastic algorithm for quantile regression models with fixed effects

In this paper, we present a stochastic algorithm for parameter estimation based on panel quantile regression model. We propose an easy-to-implement estimator based on the proposed algorithm. We profile the quantile-specific fixed effects as functions of the parameters of interest based on the Gaussian mixture representation of the asymmetric Laplace (AL) likelihood and eliminate the fixed effects through a data transformation. Parameters of interest can be estimated via quantile regression. Under a set of sufficient conditions, the proposed estimator is consistent and asymptotically normal when n and T both go to infinity. The proposed estimator is illustrated via both simulations and real data examples.

Predicting Electric Vehicle Charging Demand in Residential Areas Using POI Data and Decision‐Making Model

Transport electrification is a crucial element of the ongoing energy transition, essential for achieving carbon peaking and carbon neutrality goals. The proliferation of electric vehicles (EVs) introduces significant challenges to power distribution network stability due to their aggregated charging load in residential areas, particularly during peak electricity consumption periods. This paper proposes a method to predict the spatiotemporal distribution of EV charging demand in residential areas using geographic information points of interest (POI) data features and a decision‐making model. Utilizing real historical data, probability distribution models for EV users' arrival times and charging characteristics were constructed using Gaussian Mixture Models (GMM). The spatiotemporal characteristics of EV travel and charging behaviors were analyzed, and a comprehensive charging decision model incorporating both emergency and stochastic scenarios was developed. The model's efficacy in capturing the probability distributions of characteristic variables was validated through a case study. The results demonstrate the model's potential for accurately predicting EV charging demand, providing valuable insights for infrastructure planning and resource allocation. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Single Station Seismic Event Location With a Neural‐Guided Mixture Model: Model‐Based Weighting for Improved Accuracy

AbstractIn many regions of the world with complex seismic activity, the availability of seismic stations is limited. This motivated us to develop a probabilistic method for single‐station earthquake location. Single station location methods may provide an efficient and cost‐effective way to monitor small‐magnitude seismic events over large areas of the world. This method relies on the outputs of two neural networks, which predict the initial spatial location of specific areas (convolutional) used in the prior probability and seismic phase recognition (combination of convolutional and Long Short Term Memory) used in the likelihood function. These estimates and a 3D travel time likelihood function are used in a Bayesian framework. In this model, the initial spatial location is expressed as a Multivariate Gaussian Mixture Model, and the likelihood function refines the localization using the arrival time difference between S and P waves in a 3D space. The likelihood function uses a Fast Marching Eikonal method with a 3D velocity structure. We tested this method on the Ridgecrest 2019 seismic sequence (Mw = 7.1) and on West Texas and found promising results for locating with a single station. Our approach demonstrates that using a Bayesian model with strong priors obtained through deep learning algorithms is effective. Our model can predict epicenter and depth with mean errors of 7.55 km in longitude, 13.54 km in latitude and 0.630 km in depth at the two different locations studied. This method demonstrates the effectiveness of combining deep learning for initial estimations with probabilistic 3D location refinement.

Weighted support vector machine for extremely imbalanced data

Based on an asymptotically optimal weighted support vector machine (SVM) that introduces label shift, a systematic procedure is derived for applying oversampling and weighted SVM to extremely imbalanced datasets with a cluster-structured positive class. This method formalizes three intuitions: (i) oversampling should reflect the structure of the positive class; (ii) weights should account for both the imbalance and oversampling ratios; (iii) synthetic samples should carry less weight than the original samples. The proposed method generates synthetic samples from the estimated positive class distribution using a Gaussian mixture model. To prevent overfitting to excessive synthetic samples, different misclassification penalties are assigned to the original positive class, synthetic positive class, and negative class. The proposed method is numerically validated through simulations and an analysis of Republic of Korea Army artillery training data.

A refined output-only modal identification technique for structural health monitoring of civil infrastructures

The increasing installation of structural health monitoring systems has raised the need for efficient and rapid data interpretation algorithms. Operational modal analysis is currently one of the most used techniques for extracting modal properties, and some attempts have been made to automate this procedure. However, automated techniques often require manual calibration of hyperparameters and show inconsistencies across different case studies. This paper proposes a refined version of the automated frequency domain decomposition (AFDD) using the modal assurance criterion (MAC) to obtain natural frequencies and mode shapes. Sensitivity analyses were conducted on the ambient vibration response of the Yonghe cable-stayed bridge in China, accounting for influential factors including noise levels, acceleration record length, sensor layouts. A novel approach is then introduced to interpret the results of the sensitivity analyses. The approach consists in plotting the result of each analysis in a stabilization diagram and then using a Gaussian mixture model that clusters the poles into core and outliers. This allows to identify regions where the MAC thresholds are optimal. By comparing the results of all the sensitivity analyses it was possible to define a single optimal MAC threshold, avoiding the need for fixing a value based on the user’s experience. Three substantially different case studies were analyzed to extensively test the methodology: the Yonghe cable-stayed bridge, the PolyU footbridge in Hong Kong, and Moletta Tower in the Circus Maximus archeological site in Italy. The analysis compared the proposed AFDD algorithm to the traditional frequency domain decomposition and covariance-driven stochastic subspace identification. Specifically, the efficiency in identifying close frequencies, weakly excited modes, spurious peaks, and complex modes was evaluated for each method, which highlighted the robustness of the proposed optimized AFDD. The analysis showcases peculiar characteristics and drawbacks of each method when trying to identify complex vibrational modes of the specific case studies. It was found that the proposed AFDD procedure performs better than traditional methods despite it may misidentify complex modes due to the constraints of a narrower modal domain and similar geometries.

An algorithm for multi-damage size estimation of composite laminates

Localization and size estimation of composite damage are challenging but essential for composite performance evaluation. This paper proposes a new methodology for the size estimation of multi-damage in composite laminates using Lamb wave technology. The pure A0 modal of Lamb wave is excited to avoid dispersion and multi-modal effects of Lamb wave. An extraction algorithm is introduced to obtain the first wave packet and time-of-flight. According to the results obtained by the extraction algorithm, the Bayesian-hybrid localization algorithm based on the reconstruction algorithm for probabilistic inspection of damage and modified delay-and-sum (MDAS) is performed to localize damages. The damage boundaries are obtained through convex enveloping a series of damage boundary points identified by MDAS. An adaptive Gaussian mixture model based on Akaike’s Information Criterion and Bayesian Information Criterion is designed to remove abnormal boundary points. The proposed method is numerically investigated and validated through multi-damage experiments. The results demonstrate that it can accurately estimate the locations and boundaries of multi-damage in composite laminates.

Relationship Between Aquatic Factors and Sulfide and Ferrous Iron in Black Bloom in Lakes: A Case Study of a Eutrophic Lake in Eastern China

Black bloom is a very serious water pollution phenomenon in eutrophic lakes, with Fe(II) and S(−II) being the key limiting factors for this problem. In this paper, three different machine learning methods, namely, Random Forest (RF), Gaussian Mixture Model (GMM), and Bayesian Network (BN), were used to explore the complex interactions among Fe(II), S(−II), and other aquatic factors in the estuary of Chaohu Lake to better characterize and monitor water degradation by black bloom. The results of RF showed that total nitrogen (TN), ammonia, total phosphorous (TP), suspended sediment concentration (SSC), and oxidation–reduction potential (ORP), which were chosen from 11 factors, had the most important relationships with Fe(II) and S(−II). The 69 sampling sites were divided in three groups identified as worst, worse, and bad according to the observed values of seven factors using the GMM. Then, the BN model was applied to three observation groups. The results showed that the structures of the interaction networks were different between the groups. S(−II) controlled only SSC production in the bad and worse group sites, while SSC was determined by both S(−II) and Fe(II) in the worst group. Ammonia and TN exhibited the most direct importance for S(−II) and Fe(II) production in all observation groups. According to the indications from the BNs, potential management strategies for different water pollution conditions were developed. Finally, the threshold values of Fe(II), S(−II), TP, ammonia, TN, SSC, and ORP, which were 0.80 mg/L, 0.04 mg/L, 0.45 mg/L, 3.44 mg/L, 4.15 mg/L, 55 mg/L, and 135 mv, respectively, were determined on the basis of the BN models. These values will be helpful to develop accurate strategies of oxygenation to quickly eliminate black bloom in the lake.

Improved automated parallel implementation of GMM background subtraction on a multicore digital signal processor

<p><span>Scene segmentation is an essential step in a wide range of video processing applications, for instance, object recognition and tracking. The Gaussian mixture model (GMM) for background subtraction (BS) has gained widespread usage in scene segmentation, despite its known computational intensity. To tackle this challenge, we propose a practical solution to accelerate processing through a parallel implementation on an embedded multicore platform. In this paper, we present an improved automated parallel implementation of the GMM algorithm using the Orphan directive provided by open multiprocessing (OpenMP). Experimental assessments conducted on the eight cores of the C6678 digital signal processor (DSP) demonstrate significant advancements in parallel efficiency, particularly when handling high-resolution frames, including high-definition (HD) and full-HD resolutions. The achieved parallel efficiency surpasses the results obtained with classical OpenMP scheduling modes, encompassing dynamic, static, and guided approaches. Specifically, the parallel efficiency reaches approximately 82% for full-HD resolution frames and, 99.3% for low-resolution frames, respectively.</span></p>

Estimating Vehicle Turn-In Rate of Expressway Rest Areas via ETC Gantry Data – An ADPC-GMM Approach

Vehicle turn-in rate is a critical and widely adopted input for expressway rest area design and operation. With the implementation of expressway ETC gantries, the ERA turn-in rate can be further estimated by measuring the travel speed distribution via ETC gantry data. This paper proposed an adaptive density peak clustering Gaussian mixture model (ADPC-GMM) for ERA turn-in rate estimation. The ADPC algorithm is applied to generate the GMM’s inputs accommodating to the traffic characteristic of ERA expressway segments and GMM would further provide the turn-in rate estimation results. To validate the model precision, the turn-in rate data of four selected ERAs in Sichuan, China, as well as the ETC gantry data of their corresponding expressway sections are obtained. According to the estimation results, the MAE and RMSE are 0.0228 and 0.0267 for the passenger car scenario and 0.0264 and 0.0356 for the commercial truck scenario, respectively. These results are also at the lowest level compared with the results acquired from ordinary GMM, K-Means and DBSCAN algorithms. The proposed method has good applicability for vehicle turn-in rate estimation and can be deployed at different ERAs, especially those ERAs without traffic monitoring.

Parkinson’s Disease Interstage Prognostic Biomarkers for Early Detection through Hybrid Machine Learning Model

Background: Parkinson’s Disease (PD) is a neurodegenerative condition that takes 15 to 20 years to exhibit the symptoms. However, during the initial stages of the disease, there are microlevel changes in the body that are typically undetected. The pathogenesis of Parkinson’s disease requires understanding of these microlevel changes. Objectives: The objective of the present study is to develop a hybrid ensembled machine learning pipeline model for identifying inter-stage Parkinson’s Disease (PD) biomarkers for understanding disease progression as well as etiology. Methods: The proposed work was carried out on the dataset GSE202667 from Gene Expression Omnibus, containing time-resolved RNA signatures of CD4+ T cells at various stages. Differentiating genes were identified in different interstage groups. Two types of unsupervised learning methods- distance-based (K-means, Agglomerative, Density-Based Spatial Clustering of Application with Noise) and probability-based (Hidden Markov Model, Gaussian Mixture Model Latent Dirichlet Allocation) were applied. The best algorithms were selected and applied to optimize clusters. Enrichment analysis was conducted on the top 10 PD biomarkers in each category. Findings: The top 10 PD biomarkers in each category are identified and gene set enrichment analysis resulted into their enrichment in three KEGG Pathways and depletion in two GO molecular functions. These biomarkers’ depletion is observed in 215 Reactome pathways and enrichment in 18 Reactome pathways. Twelve GO-Cellular components had an enrichment whereas 111 GO-Cellular components had a depletion in the gene set. A total of 25 GO-Biological process components were enriched, while 339 GO-Biological process components were depleted. Novelty: The proposed hybrid ensembled machine learning pipeline model works as a tool to identify Parkinson’s Disease biomarkers from omics data. The model contributes to identify implicit patterns in omics data in order to unveil Parkinson’s disease progress mechanism through biomarkers discovery. Keywords: Gaussian Mixture Model clustering, Early Detection, k-means clustering, Machine learning, Parkinson’s Disease Interstage Biomarkers

Expert opinion elicitation for assisting deep learning based Lyme disease classifier with patient data

BackgroundDiagnosing erythema migrans (EM) skin lesion, the most common early symptom of Lyme disease, using deep learning techniques can be effective to prevent long-term complications. Existing works on deep learning based EM recognition only utilizes lesion image due to the lack of a dataset of Lyme disease related images with associated patient data. Doctors rely on patient information about the background of the skin lesion to confirm their diagnosis. To assist deep learning model with a probability score calculated from patient data, this study elicited opinions from fifteen expert doctors. To the best of our knowledge, this is the first expert elicitation work to calculate Lyme disease probability from patient data. MethodsFor the elicitation process, a questionnaire with questions and possible answers related to EM was prepared. Doctors provided relative weights to different answers to the questions. We converted doctors' evaluations to probability scores using Gaussian mixture based density estimation. We exploited formal concept analysis and decision tree for elicited model validation and explanation. We also proposed an algorithm for combining independent probability estimates from multiple modalities, such as merging the EM probability score from a deep learning image classifier with the elicited score from patient data. ResultsWe successfully elicited opinions from fifteen expert doctors to create a model for obtaining EM probability scores from patient data. ConclusionsThe elicited probability score and the proposed algorithm can be utilized to make image based deep learning Lyme disease pre-scanners robust. The proposed elicitation and validation process is easy for doctors to follow and can help address related medical diagnosis problems where it is challenging to collect patient data.

Robust extraction of pneumonia-associated clinical states from electronic health records

Mining of electronic health records (EHR) promises to automate the identification of comprehensive disease phenotypes. However, the realization of this promise is hindered by the unavailability of generalizable ground-truth information, data incompleteness and heterogeneity, and the lack of generalization to multiple cohorts. We present here a data-driven approach to identify clinical states that we implement for 585 critical care patients with suspected pneumonia recruited by the SCRIPT study, which we compare to and integrate with 9,918 pneumonia patients from the MIMIC-IV dataset. We extract and curate from their structured EHRs a primary set of clinical features (53 and 59 features for SCRIPT and MIMIC-IV, respectively), including disease severity scores, vital signs, and so on, at various degrees of completeness. We aggregate irregular time series into daily frequency, resulting in 12,495 and 94,684 patient-day pairs for SCRIPT and MIMIC, respectively. We define a "common-sense" ground truth that we then use in a semisupervised pipeline to optimize choices for data preprocessing, and reduce the feature space to four principal components. We describe and validate an ensemble-based clustering method that enables us to robustly identify five clinical states, and use a Gaussian mixture model to quantify uncertainty in cluster assignment. Demonstrating the clinical relevance of the identified states, we find that three states are strongly associated with disease outcomes (dying vs. recovering), while the other two reflect disease etiology. The outcome associated clinical states provide significantly increased discrimination of mortality rates over standard approaches.

Inferring sediment-discharge event types in an Alpine catchment from sub-daily time series

Abstract. Fluvial sediment dynamics in mountain rivers are changing rapidly in a degrading cryosphere, raising the potential for erosive rainfall and runoff and detrimental effects on downstream areas. Hence, we need to understand better what characterises and drives episodic pulses of water and suspended solids in rivers. Here, we infer different types of such sediment-discharge events from 959 automatically detected events based on 16 metrics derived from 15 min time series of streamflow and suspended sediment concentrations from Vent–Rofental in the high Ötztal Alps, Austria. We use principal component analysis to extract uncorrelated event characteristics and cluster event types with a Gaussian mixture model. We interpret the thus inferred event types with catchment metrics describing antecedent conditions, hydrometeorological forcing, and fraction of catchment area with freezing temperatures and snow cover. We find event magnitude, hysteresis, and event shape complexity to be the main factors characterising the overall event regime. The most important characteristics distinguishing the event types are suspended sediment and streamflow magnitude and complexity of the hydro- and sedigraphs. Sediment-discharge hysteresis is less relevant for discerning event types. We derive four event types that we attribute to (1) compound rainfall–melt extremes, (2) glacier and seasonal snowmelt, (3) freeze–thaw-modulated snowmelt and precipitation events, and (4) late-season glacier melt. Glacier and snowmelt events driven by warm conditions and high insolation were the most frequent and contributed some 40 % to annual suspended sediment yield on average; compound rainfall–melt extremes were the rarest but contributed the second-highest proportion (26 %). Our approach represents a reproducible method for objectively estimating the variety of event-scale suspended sediment transport conditions in mountain rivers, which can provide insights into the contribution of different drivers to annual sediment yields in current and future regimes. Our findings highlight the importance of both meltwater and rainfall–runoff as drivers of high-magnitude suspended sediment fluxes in mountain rivers.

A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration

Color transfer, an essential technique in image editing, has recently received significant attention. However, achieving a balance between holistic color style transfer and local detail refinement remains a challenging task. This paper proposes an innovative color transfer method, named BHL, which stands for Balanced consideration of both Holistic transformation and Local refinement. The BHL method employs a statistical framework to address the challenge of achieving a balance between holistic color transfer and the preservation of fine details during the color transfer process. Holistic color transformation is achieved using optimal transport theory within the generalized Gaussian modeling framework. The local refinement module adjusts color and texture details on a per-pixel basis using a Gaussian Mixture Model (GMM). To address the high computational complexity inherent in complex statistical modeling, a parameter estimation method called the unit-wise Riemannian information gradient (uRIG) method is introduced. The uRIG method significantly reduces the computational burden through the second-order acceleration effect of the Fisher information metric. Comprehensive experiments demonstrate that the BHL method outperforms state-of-the-art techniques in both visual quality and objective evaluation criteria, even under stringent time constraints. Remarkably, the BHL method processes high-resolution images in an average of 4.874 s, achieving the fastest processing time compared to the baselines. The BHL method represents a significant advancement in the field of color transfer, offering a balanced approach that combines holistic transformation and local refinement while maintaining efficiency and high visual quality.

Evaluation of Clustering Techniques for Solar Irradiance Prediction for Optimal Design of Microgrids in Rural Communities

Abstract The electrification of rural communities is crucial from both social and economic perspectives, aligned with Sustainable Development Goal 7: “Affordable and Clean Energy”. This study presents a comprehensive comparison of clustering techniques, including k-means, Gaussian Mixture Models (GMM), Hierarchical Clustering, Density-based Spatial Clustering of Applications with Noise (DBSCAN), and Agglomerative Clustering, aimed at enhancing solar irradiance prediction. Leveraging historical climate data from a rural community in the coastal region of Ecuador, each technique is evaluated using error metrics such as Mean Absolute Error (MAE) and Coefficient of Determination R2. This assessment identifies the most effective clustering technique in this specific context. In order to delve deeper into these comparisons, simulations are conducted in AMPL to validate and refine the selection of techniques. In this process, it is considered the sizing and design of a microgrid within the Barcelona community, Ecuador, which integrates various energy sources, including solar. Additionally, a penalty system is introduced for unmet energy demands during less critical periods, thereby optimizing efficiency and enhancing energy availability within the community. In conclusion, this paper introduces a scalable methodology to improve solar irradiance prediction, emphasizing the significance of comparing clustering techniques as its main contribution. This advancement in prediction accuracy has the potential to enhance the feasibility and efficiency of renewable energy systems for rural communities, thereby fostering sustainable economic growth and bolstering efforts in climate change mitigation and adaptation.

The fluency vs. disfluency dichotomy in writing processes as reflected in the structure of the inter-key intervals empirical distribution

ABSTRACT The broader aim of this study is the corpus-based investigation of the written language production process. To this end, temporal markers have been keylog recorded alongside the writing processes to exploit pauses to segment the speech product into linear units of performance. However, identifying these pauses requires selecting the relevant interkey intervals (IKI) between production microevents. Different models have been applied to identify such components in the empirical distribution of these delays, in particular Gaussian mixture models (GMM), yet no consensus has emerged regarding the number and interpretation of these components. Here, we analyze IKI distributions from a corpus of keylogs and show that a model with two components is robustly selected across a large range of participants. Furthermore, we show that the contents of these modes are consistent with a fluency vs. disfluency interpretation of the modes by identifying which kinds of events fall into each mode.