Open-source Algorithm Research Articles

A Comprehensive Evaluation of Iris Segmentation on Benchmarking Datasets.

Iris is one of the most widely used biometric modalities because of its uniqueness, high matching performance, and inherently secure nature. Iris segmentation is an essential preliminary step for iris-based biometric authentication. The authentication accuracy is directly connected with the iris segmentation accuracy. In the last few years, deep-learning-based iris segmentation methodologies have increasingly been adopted because of their ability to handle challenging segmentation tasks and their advantages over traditional segmentation techniques. However, the biggest challenge to the biometric community is the scarcity of open-source resources for adoption for application and reproducibility. This review provides a comprehensive examination of available open-source iris segmentation resources, including datasets, algorithms, and tools. In the process, we designed three U-Net and U-Net++ architecture-influenced segmentation algorithms as standard benchmarks, trained them on a large composite dataset (>45K samples), and created 1K manually segmented ground truth masks. Overall, eleven state-of-the-art algorithms were benchmarked against five datasets encompassing multiple sensors, environmental conditions, demography, and illumination. This assessment highlights the strengths, limitations, and practical implications of each method and identifies gaps that future studies should address to improve segmentation accuracy and robustness. To foster future research, all resources developed during this work would be made publicly available.

Technical note: A guide to using three open-source quality control algorithms for rainfall data from personal weather stations

Abstract. The number of rainfall observations from personal weather stations (PWSs) has increased significantly over the past years; however, there are persistent questions about data quality. In this paper, we reflect on three quality control algorithms (PWSQC, PWS-pyQC, and GSDR-QC) designed for the quality control (QC) of rainfall data. Technical and operational guidelines are provided to help interested users in finding the most appropriate QC to apply for their use case. All three algorithms can be accessed within the OpenSense sandbox where users can run the code. The results show that all three algorithms improve PWS data quality when cross-referenced against a rain radar data product. The considered algorithms have different strengths and weaknesses depending on the PWS and official data availability, making it inadvisable to recommend one over another without carefully considering the specific setting. The authors highlight a need for further objective quantitative benchmarking of QC algorithms. This requires freely available test datasets representing a range of environments, gauge densities, and weather patterns.

Research on the role of multi-sensor system information fusion in improving hardware control accuracy of intelligent system

Abstract Multi-sensor management and control technology generally constructs a reasonable objective function to solve the optimal control command set to control a limited number of sensors to obtain higher quality measurement information, thus obtaining better target tracking performance. In the process of multi-sensor information fusion, there is not only the problem of information redundancy but also obvious time delay. A sensor fusion algorithm combined with global optimization algorithm is innovatively proposed. According to the key frames saved in the previous steps, feature points in local maps, sensor information, and loop information, a global optimization algorithm based on graph optimization model is constructed to optimize the position and pose of intelligent hardware system and the position of spatial feature points. Moreover, this work studies and experiments on multi-sensor fusion simultaneous localization and mapping (SLAM) comprehensively and systematically, and the experimental results show that the algorithm proposed in this work is superior to common open-source SLAM algorithm in positioning accuracy and mapping effect under special circumstances. Therefore, the method proposed in this work can be applied to intelligent driving of vehicles, vision-assisted movement of robots and intelligent control of unmanned aerial vehicles, thus effectively improving the hardware control accuracy of intelligent systems.

G.A.I.T: gait analysis interactive tool a pipeline for automatic detection of gait events across different motor impairments

We introduce an open-access tool capable of automatically extracting the timing of gait events during unconstrained locomotion across different neuromotor impairments. The gait analysis interactive tool is conceived as an assistant for gait assessment studies, both in healthy participants or in people with motor impairments affecting gait symmetry, regularity, or balance, as usually encountered in patients with neurological disorders. Our open-access pipeline makes it possible to automatically identify the time of key gait events (heel strike, toe off) from a single gyroscope axis (lateral mid-axis), simplifying experimental protocols, and can easily be used in everyday life conditions. The code is user-friendly and interactive. At each stage of analysis, it allows for possible adjustments and manual corrections of undetected or mismatched events. To implement, test, and validate our algorithm, we used three different databases of gait recordings that span from healthy subjects to patients affected by Parkinson’s disease. The pipeline consists of three main sections that allow us to segment, identify, and eventually correct the events within the gait cycle. The algorithm achieved an average accuracy of 99.23% over healthy participants, either with average weight or overweight, and a performance of 94.84% over patients with Parkinson’s disease. Even if gait analysis is a widely studied problem, so far, no open-source algorithm is available. The present work provides an easy tool capable of working with a minimum set of sensors and without any expensive platform or camera-based system. Employing three databases widely different for the environment, and for the subjects’ age and motor impairments highlights the versatility of our approach.

DC_OCEAN: an open-source algorithm for identification of duplicates in ocean databases

A high-quality hydrographic observational database is essential for ocean and climate studies and operational applications. Because there are numerous global and regional ocean databases, duplicate data continues to be an issue in data management, data processing and database merging, posing a challenge on effectively and accurately using oceanographic data to derive robust statistics and reliable data products. This study aims to provide algorithms to identify the duplicates and assign labels to them. We propose first a set of criteria to define the duplicate data; and second, an open-source and semi-automatic system to detect duplicate data and erroneous metadata. This system includes several algorithms for automatic checks using statistical methods (such as Principal Component Analysis and entropy weighting) and an additional expert (manual) check. The robustness of the system is then evaluated with a subset of the World Ocean Database (WOD18) with over 600,000 in-situ temperature and salinity profiles. This system is an open-source Python package (named DC_OCEAN) allowing users to effectively use the software. Users can customize their settings. The application result from the WOD18 subset also forms a benchmark dataset, which is available to support future studies on duplicate checks, metadata error identification, and machine learning applications. This duplicate checking system will be incorporated into the International Quality-controlled Ocean Database (IQuOD) data quality control system to guarantee the uniqueness of ocean observation data in this product.

Assessing the Accuracy of Activity Classification Using Thigh-Worn Accelerometry: A Validation Study of ActiPASS in School-Aged Children.

The ActiPASS software was developed from the open-source Acti4 activity classification algorithm for thigh-worn accelerometry. However, the original algorithm has not been validated in children or compared with a child-specific set of algorithm thresholds. This study aims to evaluate the accuracy of ActiPASS in classifying activity types in children using 2 published sets of Acti4 thresholds. Laboratory and free-living data from 2 previous studies were used. The laboratory condition included 41 school-aged children (11.0 [4.8]y; 46.5% male), and the free-living condition included 15 children (10.0 [2.6]y; 66.6% male). Participants wore a single accelerometer on the dominant thigh, and annotated video recordings were used as a reference. Postures and activity types were classified with ActiPASS using the original adult thresholds and a child-specific set of thresholds. Using the original adult thresholds, the mean balanced accuracy (95% CI) for the laboratory condition ranged from 0.62 (0.56-0.67) for lying to 0.97 (0.94-0.99) for running. For the free-living condition, accuracy ranged from 0.61 (0.48-0.75) for lying to 0.96 (0.92-0.99) for cycling. Mean balanced accuracy for overall sedentary behavior (sitting and lying) was ≥0.97 (0.95-0.99) across all thresholds and conditions. No meaningful differences were found between the 2 sets of thresholds, except for superior balanced accuracy of the adult thresholds for walking under laboratory conditions. The results indicate that ActiPASS can accurately classify different basic types of physical activity and sedentary behavior in children using thigh-worn accelerometer data.

The 4D Camera: An 87 kHz Direct Electron Detector for Scanning/Transmission Electron Microscopy.

We describe the development, operation, and application of the 4D Camera-a 576 by 576 pixel active pixel sensor for scanning/transmission electron microscopy which operates at 87,000 Hz. The detector generates data at ∼480 Gbit/s which is captured by dedicated receiver computers with a parallelized software infrastructure that has been implemented to process the resulting 10-700 Gigabyte-sized raw datasets. The back illuminated detector provides the ability to detect single electron events at accelerating voltages from 30 to 300 kV. Through electron counting, the resulting sparse data sets are reduced in size by 10--300× compared to the raw data, and open-source sparsity-based processing algorithms offer rapid data analysis. The high frame rate allows for large and complex scanning diffraction experiments to be accomplished with typical scanning transmission electron microscopy scanning parameters.

An Automated Analysis of Homocoupling Defects Using MALDI-MS and Open-Source Computer Software.

Conjugated organic polymers have substantial potential for multiple applications but their properties are strongly influenced by structural defects such as homocoupling of monomer units and unexpected end-groups. Detecting and/or quantifying these defects requires complex experimental techniques, which hinder the optimization of synthesis protocols and fundamental studies on the influence of structural defects. Mass spectrometry offers a simple way to detect these defects but a manual analysis of many complex spectra is tedious and provides only approximate results. In this work, we develop a computational methodology for analyzing complex mass spectra of organic copolymers. Our method annotates spectra similarly to a human expert and provides quantitative information about the proportions of signal assigned to each ion. Our method is based on the open-source Masserstein algorithm, which we modify to handle large libraries of reference spectra required for annotating complex mass spectra of polymers. We develop a statistical methodology to analyze the quantitative annotations and compare the statistical distributions of structural defects in polymer chains between samples. We apply this methodology to analyze commercial and lab-made samples of a benchmark polymer and show that the samples differ both in the amount and in the types of structural defects.

Tuning parameters of deep neural network training algorithms pays off: a computational study

AbstractThe paper aims to investigate the impact of the optimization algorithms on the training of deep neural networks with an eye to the interaction between the optimizer and the generalization performance. In particular, we aim to analyze the behavior of state-of-the-art optimization algorithms in relationship to their hyperparameters setting to detect robustness with respect to the choice of a certain starting point in ending on different local solutions. We conduct extensive computational experiments using nine open-source optimization algorithms to train deep Convolutional Neural Network architectures on an image multi-class classification task. Precisely, we consider several architectures by changing the number of layers and neurons per layer, to evaluate the impact of different width and depth structures on the computational optimization performance. We show that the optimizers often return different local solutions and highlight the strong correlation between the quality of the solution found and the generalization capability of the trained network. We also discuss the role of hyperparameters tuning and show how a tuned hyperparameters setting can be re-used for the same task on different problems achieving better efficiency and generalization performance than a default setting.

Enhanced classification and severity prediction of major depressive disorder using acoustic features and machine learning.

Previous studies have classified major depression and healthy control groups based on vocal acoustic features, but the classification accuracy needs to be improved. Therefore, this study utilized deep learning methods to construct classification and prediction models for major depression and healthy control groups. 120 participants aged 16-25 participated in this study, included 64 MDD group and 56 HC group. We used the Covarep open-source algorithm to extract a total of 1200 high-level statistical functions for each sample. In addition, we used Python for correlation analysis, and neural network to establish the model to distinguish whether participants experienced depression, predict the total depression score, and evaluate the effectiveness of the classification and prediction model. The classification modelling of the major depression and the healthy control groups by relevant and significant vocal acoustic features was 0.90, and the Receiver Operating Characteristic (ROC) curves analysis results showed that the classification accuracy was 84.16%, the sensitivity was 95.38%, and the specificity was 70.9%. The depression prediction model of speech characteristics showed that the predicted score was closely related to the total score of 17 items of the Hamilton Depression Scale(HAMD-17) (r=0.687, P<0.01); and the Mean Absolute Error(MAE) between the model's predicted score and total HAMD-17 score was 4.51. This study's results may have been influenced by anxiety comorbidities. The vocal acoustic features can not only effectively classify the major depression and the healthy control groups, but also accurately predict the severity of depressive symptoms.

Systematic conservation prioritization with the prioritizr R package.

Plans for expanding protected area systems (prioritizations) need to fulfill conservation objectives. They also need to account for other factors, such as economic feasibility and anthropogenic land-use requirements. Although prioritizations are often generated with decision support tools, most tools have limitations that hinder their use for decision-making. We outlined how the prioritizr R package (https://prioritizr.net) can be used for systematic conservation prioritization. This decision support tool provides a flexible interface to build conservation planning problems. It can leverage a variety of commercial (e.g., Gurobi) and open-source (e.g., CBC and SYMPHONY) exact algorithm solvers to identify optimal solutions in a short period. It is also compatible with a variety of spatially explicit (e.g., ESRI Shapefile, GeoTIFF) and nonspatial tabular (e.g., Microsoft Excel Spreadsheet) data formats. Additionally, it provides functionality for evaluating prioritizations, such as assessing the relative importance of different places selected by a prioritization. To showcase the prioritizr R package, we applied it to a case study based in Washington state (United States) for which we developed a prioritization to improve protected area coverage of native avifauna. We accounted for land acquisition costs, existing protected areas, places that might not be suitable for protected area establishment, and spatial fragmentation. We also conducted a benchmark analysis to examine the performance of different solvers. The prioritization identified 12,400km2 of priority areas for increasing the percentage of species' distributions covered by protected areas. Although open source and commercial solvers were able to quickly solve large-scale conservation planning problems, commercial solvers were required for complex, large-scale problems.. The prioritizr R package is available on the Comprehensive R Archive Network (CRAN). In addition to reserve selection, it can inform habitat restoration, connectivity enhancement, and ecosystem service provisioning. It has been used in numerous conservation planning exercises to inform best practices and aid real-world decision-making.

Prospective multicenter study using artificial intelligence to improve dermoscopic melanoma diagnosis in patient care

BackgroundEarly detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting.MethodsTherefore, we assessed “All Data are Ext” (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e., providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities.ResultsOverall, the AI shows higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779–0.814 vs. 0.781, 95% CI 0.760–0.802; p = 4.0e−145), obtaining a higher sensitivity (0.921, 95% CI 0.900–0.942 vs. 0.734, 95% CI 0.701–0.770; p = 3.3e−165) at the cost of a lower specificity (0.673, 95% CI 0.641–0.702 vs. 0.828, 95% CI 0.804–0.852; p = 3.3e−165).ConclusionAs the algorithm exhibits a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists, particularly in diagnosing challenging cases.

Fast Algorithms for Computing Fixed-Length Round Trips in Real-World Street Networks

This paper proposes and evaluates algorithms for calculating round trips of a prescribed length on directed street networks. This problem has several real-world applications, such as designing jogging routes and cycling tours. In this work, we focus specifically on methods that avoid the need to download, process, and store large map databases. At the same time, we aim for our methods to be fast, accurate, and capable of handling a wide range of prescribed distances, from just a few meters to many kilometres. To achieve this, our overall strategy involves using a small number of calls to a suitable online mapping service to collect relevant structural information for the problem at hand. All remaining computations are then performed locally on the client. Empirically, we demonstrate that our suggested techniques outperform existing open-source algorithms in terms of both accuracy and runtime requirements. Our most successful approach is based on multi-objective local search, utilizing specialized neighbourhood operators that exploit the underlying graph-theoretical properties of this problem, resulting in runtimes of around 2–3 s on a typical desktop computer.

Validation of a machine learning algorithm for identifying infants at risk of hypoxic ischaemic encephalopathy in a large unseen data set

ObjectiveTo validate a hypoxic ischaemic encephalopathy (HIE) prediction algorithm to identify infants at risk of HIE immediately after birth using readily available clinical data.DesignSecondary review of electronic health record data...

Differences in activity and stability drive transposable element variation in tropical and temperate maize.

Much of the profound interspecific variation in genome content has been attributed to transposable elements (TEs). To explore the extent of TE variation within species, we developed an optimized open-source algorithm, panEDTA, to de novo annotate TEs in a pangenome context. We then generated a unified TE annotation for a maize pangenome derived from 26 reference-quality genomes, which reveals an excess of 35.1 Mb of TE sequences per genome in tropical maize relative to temperate maize. A small number (n = 216) of TE families, mainly LTR retrotransposons, drive these differences. Evidence from the methylome, transcriptome, LTR age distribution, and LTR insertional polymorphisms reveals that 64.7% of the variability is contributed by LTR families that are young, less methylated, and more expressed in tropical maize, whereas 18.5% is driven by LTR families with removal or loss in temperate maize. Additionally, we find enrichment for Young LTR families adjacent to nucleotide-binding and leucine-rich repeat (NLR) clusters of varying copy number across lines, suggesting TE activity may be associated with disease resistance in maize.

Automated Analysis of Stereotypical Movements in Videos of Children With Autism Spectrum Disorder

Stereotypical motor movements (SMMs) are a form of restricted and repetitive behavior, which is a core symptom of autism spectrum disorder (ASD). Current quantification of SMM severity is extremely limited, with studies relying on coarse and subjective caregiver reports or laborious manual annotation of short video recordings. To assess the utility of a new open-source AI algorithm that can analyze extensive video recordings of children and automatically identify segments with heterogeneous SMMs, thereby enabling their direct and objective quantification. This retrospective cohort study included 241 children (aged 1.4 to 8.0 years) with ASD. Video recordings of 319 behavioral assessments carried out at the Azrieli National Centre for Autism and Neurodevelopment Research in Israel between 2017 and 2021 were extracted. Behavioral assessments included cognitive, language, and autism diagnostic observation schedule, 2nd edition (ADOS-2) assessments. Data were analyzed from October 2020 to May 2024. Each assessment was recorded with 2 to 4 cameras, yielding 580 hours of video footage. Within these extensive video recordings, manual annotators identified 7352 video segments containing heterogeneous SMMs performed by different children (21.14 hours of video). A pose estimation algorithm was used to extract skeletal representations of all individuals in each video frame and was trained an object detection algorithm to identify the child in each video. The skeletal representation of the child was then used to train an SMM recognition algorithm using a 3 dimensional convolutional neural network. Data from 220 children were used for training and data from the remaining 21 children were used for testing. Among 319 behavioral assessment recordings from 241 children (172 [78%] male; mean [SD] age, 3.97 [1.30] years), the algorithm accurately detected 92.53% (95% CI, 81.09%-95.10%) of manually annotated SMMs in our test data with 66.82% (95% CI, 55.28%-72.05%) precision. Overall number and duration of algorithm-identified SMMs per child were highly correlated with manually annotated number and duration of SMMs (r = 0.8; 95% CI, 0.67-0.93; P < .001; and r = 0.88; 95% CI, 0.74-0.96; P < .001, respectively). This study suggests the ability of an algorithm to identify a highly diverse range of SMMs and quantify them with high accuracy, enabling objective and direct estimation of SMM severity in individual children with ASD.

A Crowdsourced AI Framework for Atrial Fibrillation Detection in Apple Watch and Kardia Mobile ECGs.

Background: Atrial fibrillation (AFib) detection via mobile ECG devices is promising, but algorithms often struggle to generalize across diverse datasets and platforms, limiting their real-world applicability. Objective: This study aims to develop a robust, generalizable AFib detection approach for mobile ECG devices using crowdsourced algorithms. Methods: We developed a voting algorithm using random forest, integrating six open-source AFib detection algorithms from the PhysioNet Challenge. The algorithm was trained on an AliveCor dataset and tested on two disjoint AliveCor datasets and one Apple Watch dataset. Results: The voting algorithm outperformed the base algorithms across all metrics: the average of sensitivity (0.884), specificity (0.988), PPV (0.917), NPV (0.985), and F1-score (0.943) on all datasets. It also demonstrated the least variability among datasets, signifying its highest robustness and effectiveness in diverse data environments. Moreover, it surpassed Apple's algorithm on all metrics and showed higher specificity but lower sensitivity than AliveCor's Kardia algorithm. Conclusions: This study demonstrates the potential of crowdsourced, multi-algorithmic strategies in enhancing AFib detection. Our approach shows robust cross-platform performance, addressing key generalization challenges in AI-enabled cardiac monitoring and underlining the potential for collaborative algorithms in wearable monitoring devices.

Addressing the Contrast Media Recognition Challenge: A Fully Automated Machine Learning Approach for Predicting Contrast Phases in CT Imaging.

Accurately acquiring and assigning different contrast-enhanced phases in computed tomography (CT) is relevant for clinicians and for artificial intelligence orchestration to select the most appropriate series for analysis. However, this information is commonly extracted from the CT metadata, which is often wrong. This study aimed at developing an automatic pipeline for classifying intravenous (IV) contrast phases and additionally for identifying contrast media in the gastrointestinal tract (GIT). This retrospective study used 1200 CT scans collected at the investigating institution between January 4, 2016 and September 12, 2022, and 240 CT scans from multiple centers from The Cancer Imaging Archive for external validation. The open-source segmentation algorithm TotalSegmentator was used to identify regions of interest (pulmonary artery, aorta, stomach, portal/splenic vein, liver, portal vein/hepatic veins, inferior vena cava, duodenum, small bowel, colon, left/right kidney, urinary bladder), and machine learning classifiers were trained with 5-fold cross-validation to classify IV contrast phases (noncontrast, pulmonary arterial, arterial, venous, and urographic) and GIT contrast enhancement. The performance of the ensembles was evaluated using the receiver operating characteristic area under the curve (AUC) and 95% confidence intervals (CIs). For the IV phase classification task, the following AUC scores were obtained for the internal test set: 99.59% [95% CI, 99.58-99.63] for the noncontrast phase, 99.50% [95% CI, 99.49-99.52] for the pulmonary-arterial phase, 99.13% [95% CI, 99.10-99.15] for the arterial phase, 99.8% [95% CI, 99.79-99.81] for the venous phase, and 99.7% [95% CI, 99.68-99.7] for the urographic phase. For the external dataset, a mean AUC of 97.33% [95% CI, 97.27-97.35] and 97.38% [95% CI, 97.34-97.41] was achieved for all contrast phases for the first and second annotators, respectively. Contrast media in the GIT could be identified with an AUC of 99.90% [95% CI, 99.89-99.9] in the internal dataset, whereas in the external dataset, an AUC of 99.73% [95% CI, 99.71-99.73] and 99.31% [95% CI, 99.27-99.33] was achieved with the first and second annotator, respectively. The integration of open-source segmentation networks and classifiers effectively classified contrast phases and identified GIT contrast enhancement using anatomical landmarks.

Ampycloud: an open-source algorithm to determine cloud base heights and sky coverage fractions from ceilometer data

Abstract. Ceilometers are used routinely at aerodromes worldwide to derive the height and sky coverage fraction of cloud layers. This information, possibly combined with direct observations by human observers, contributes to the production of meteorological aerodrome reports (METARs). Here, we present ampycloud, a new algorithm, and its associated Python package for automatic processing of ceilometer data with the aim of determining the sky coverage fraction and base height of cloud layers above aerodromes. The ampycloud algorithm was developed at the Swiss Federal Office of Meteorology and Climatology (MeteoSwiss) as part of the AMAROC (AutoMETAR/AutoReport rOund the Clock) program to help in the fully automatic production of METARs at Swiss civil aerodromes. ampycloud is designed to work with no direct human supervision. The algorithm consists of three distinct, sequential steps that rely on agglomerative clustering methods and Gaussian mixture models to identify distinct cloud layers from individual cloud base hits reported by ceilometers. The robustness of the ampycloud algorithm stems from the first processing step, which is simple and reliable. It constrains the two subsequent processing steps that are more sensitive but also better suited to handling complex cloud distributions. The software implementation of the ampycloud algorithm takes the form of an eponymous, pip-installable Python package developed on GitHub and made publicly accessible.

A better performing algorithm for identification of implausible growth data from longitudinal pediatric medical records

Tracking trajectories of body size in children provides insight into chronic disease risk. One measure of pediatric body size is body mass index (BMI), a function of height and weight. Errors in measuring height or weight may lead to incorrect assessment of BMI. Yet childhood measures of height and weight extracted from electronic medical records often include values which seem biologically implausible in the context of a growth trajectory. Removing biologically implausible values reduces noise in the data, and thus increases the ease of modeling associations between exposures and childhood BMI trajectories, or between childhood BMI trajectories and subsequent health conditions. We developed open-source algorithms (available on github) for detecting and removing biologically implausible values in pediatric trajectories of height and weight. A Monte Carlo simulation experiment compared the sensitivity, specificity and speed of our algorithms to three published algorithms. The comparator algorithms were selected because they used trajectory information, had open-source code, and had published verification studies. Simulation inputs were derived from longitudinal epidemiological cohorts. Our algorithms had higher specificity, with similar sensitivity and speed, when compared to the three published algorithms. The results suggest that our algorithms should be adopted for cleaning longitudinal pediatric growth data.