Search NASA⌕ Search

SEARCH · Search NASA

Results for “Logistic Regression”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging

There are several supervised machine learning methods used for the application of automated morphological classification of galaxies; however, there has not yet been a clear comparison of these different methods using imaging data, or an investigation for maximizing their effectiveness. We carry out a comparison between several common machine learning methods for galaxy classification [Convolutional Neural Network (CNN), K-nearest neighbour, logistic regression, Support Vector Machine, Random Forest, and Neural Networks] by using Dark Energy Survey (DES) data combined with visual classifications from the Galaxy Zoo 1 project (GZ1). Our goal is to determine the optimal machine learning methods when using imaging data for galaxy classification. We show that CNN is the most successful method of these ten methods in our study. Using a sample of ~2800 galaxies with visual classification from GZ1, we reach an accuracy of ~0.99 for the morphological classification of ellipticals and spirals. The further investigation of the galaxies that have a different ML and visual classification but with high predicted probabilities in our CNN usually reveals the incorrect classification provided by GZ1. We further find the galaxies having a low probability of being either spirals or ellipticals are visually lenticulars (S0), demonstrating that supervised learning is able to rediscover that this class of galaxy is distinct from both ellipticals and spirals. We confirm that ~2.5 percent galaxies are misclassified by GZ1 in our study. After correcting these galaxies’ labels, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result).

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗
DOE OSTI2023

A User-Centered Design Exploration of Factors That Influence the Rideshare Experience

The rise of real-time information communication through smartphones and wireless networks enabled the growth of ridesharing services. While personal rideshare services (individuals riding alone or with acquaintances) initially dominated the market, the popularity of pooled ridesharing (individuals sharing rides with people they do not know) has grown globally. However, pooled ridesharing remains less common in the U.S., where personal vehicle usage is still the norm. Vehicle design and rideshare services may need to be tailored to user preferences to increase pooled rideshare adoption. Based on a large, national U.S. survey (N = 5385), the results of exploratory and confirmatory factor analyses suggested that four key factors influence riders’ willingness to consider pooled ridesharing: comfort/ease of use, convenience, vehicle technology/accessibility, and passenger safety. A binomial logistic regression was conducted to determine how the four factors influence one’s willingness to consider pooled ridesharing. The two factors that positively influence riders’ willingness to consider pooled ridesharing are vehicle technology/accessibility (B = 1.10) and convenience (B = 0.94), while lack of passenger safety (B = –0.63) and comfort/ease of use (B = –0.17) are pooled ridesharing deterrents. Understanding user-centered design and service factors are critical to increase the use of pooled ridesharing services in the future.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2024

A Hybrid Anomaly Detection Approach for Obfuscated Malware

With the rapid evolution of malicious software, cyber threats have become increasingly sophisticated, employing advanced obfuscation techniques to evade traditional detection methods. This study presents a hybrid anomaly detection approach applied to obfuscated malware. Even though there is a large body of research in this field, existing malware detection techniques have some drawbacks, such as requiring large amounts of data, trustworthiness (imprecise results) of algorithms, and advanced obfuscation. To overcome these challenges, there is a need to employ solid and efficient techniques for malware detection. This paper proposes a hybrid approach, combining an autoencoder with traditional machine-learning methods to create an efficient malware detection framework. We used the malware memory dataset (MalMemAnalysis-2022) to evaluate this framework. The results indicate that our proposed approach can detect obfuscated malware when a deep autoencoder used for feature learning is combined with logistic regression, and it is extremely fast with an Accuracy, Detection Rate (DR), Matthew Correlation Coefficient(MCC), and Statistical Parity Difference

malware detection, Hybrid Anomly Detection, Obfusc↗
DOE OSTI2022

Supervised Learning for Distribution Secondary Systems Modeling: Improving Solar Interconnection Processes

The current interconnection process and hosting capacity analysis for distributed energy resources (DERs), such as photovoltaics (PV) and battery energy storage systems, are based on analyzing grid network constraints (voltage and thermal) using only medium-voltage distribution network models. This is because most utilities do not have secondary low-voltage system models that connect service transformers and residential customers. This is important because in many cases the main impact of interconnecting DERs could occur on the low-voltage distribution systems. This paper proposes a supervised learning method to approximate local secondary models to improve the interconnection process. The proposed supervised learning method includes a decision tree model that predicts the secondary topology and a logistic regression model that predicts conductor types. The case studies demonstrate the benefits of including secondary low-voltage circuits in the interconnection process. We report the proposed modeling methodology is readily scalable and thus can reduce the cost and effort of PV interconnection for the industry and stakeholders.

14 SOLAR ENERGY↗
DOE OSTI2020

A spatial-statistical investigation of surface expressions associated with cyclic steaming in the Midway-Sunset Oil Field, California

In the Midway Sunset Oil Field in Central California, operators inject steam into the shallow diatomite formation to enhance heavy oil recovery through imbibition, wettability alteration, and viscosity reduction, among other mechanisms. The injected steam, however, does not always remain in the reservoir or return through the wells. In two zones in the study area, the steam comes out at the surface, creating sinkholes, seeps, and steam outlets. These phenomena, called “surface expressions,” pose safety and environmental hazards. Even though these surface expressions are a widespread problem in Central California, they are not well documented and understood. Possible causes of the surface expressions include: high injection pressure, structurally controlled flow patterns, leakage of steam through old improperly abandoned wells, high injection volumes, or flow along naturally occurring faults, among other possible factors. This work examines attributes of the zones with surface expressions in order to determine factors that may contribute to their occurrence. Spatial statistical analysis using logistic regression, random forests, and classification trees is used to explore the relationship between the surface expressions and geological and production-related attributes. The results point to a significant spatial correlation between the surface expressions and two predictors: concentration of plugged wells and geologic seal thickness. The results guide follow-up studies to further investigate the role of well abandonment and seal thickness in the occurrence of surface expressions.

02 PETROLEUM↗
DOE OSTI2021

Deep Learning Classification of Cheatgrass Invasion in the Western United States Using Biophysical and Remote Sensing Data

Cheatgrass (Bromus tectorum) invasion is driving an emerging cycle of increased fire frequency and irreversible loss of wildlife habitat in the western US. Yet, detailed spatial information about its occurrence is still lacking for much of its presumably invaded range. Deep learning (DL) has demonstrated success for remote sensing applications but is less tested on more challenging tasks like identifying biological invasions using sub-pixel phenomena. We compare two DL architectures and the more conventional Random Forest and Logistic Regression methods to improve upon a previous effort to map cheatgrass occurrence at >2% canopy cover. High-dimensional sets of biophysical, MODIS, and Landsat-7 ETM+ predictor variables are also compared to evaluate different multi-modal data strategies. All model configurations improved results relative to the case study and accuracy generally improved by combining data from both sensors with biophysical data. Cheatgrass occurrence is mapped at 30 m ground sample distance (GSD) with an estimated 78.1% accuracy, compared to 250-m GSD and 71% map accuracy in the case study. Furthermore, DL is shown to be competitive with well-established machine learning methods in a limited data regime, suggesting it can be an effective tool for mapping biological invasions and more broadly for multi-modal remote sensing applications.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

The effect of modeling dose uncertainty on low-boom community noise dose-response curves

In logistic dose-response modeling, failing to account for uncertainty in estimated doses can cause an artificial flattening or attenuation of the slope of the summary curve. In Lee et al. [J. Acoust. Soc. Am. 147(4), pp. 2222-2234 (2020)], data from two NASA low-amplitude sonic boom community noise survey tests were modeled using a Bayesian multilevel logistic regression (MLR) statistical model that assumed there was no uncertainty in the noise dose estimates. However, in these community tests, the noise dose uncertainty was estimated by Page et al. [NASA/CR-2014-218180 and NASA/CR-2020-220589/Volume I] using a leave-one-out method. In the current work, a term was added to extend the Bayesian MLR model to account for the estimated noise dose uncertainty quantified in the Page et al. analyses. This uncertainty term was included in two ways, either as classical or as Berkson uncertainty, and yield similar results. When the uncertainty is accounted for in the Bayesian MLR model, the dose-response curves become 5-10% steeper, but the difference in the noise dose that elicits a 5% highly annoyed response is small (less than 1 dB). This result is encouraging for future X-59 community tests whose survey area will be sparsely populated with noise monitors.

X-59↗
DOE OSTI2025

Exploring the environmental drivers of human blastomycosis cases in the Midwestern United States

Blastomycosis is a fungal infection endemic to the eastern United States (US) and Canada caused by the inhalation of the fungi Blastomyces spp. Currently, the environmental drivers of disease dynamics are poorly understood. The goal of our work was to explore what environmental conditions are associated with the annual presence of blastomycosis cases, and therefore are potentially explanatory of the ecological niche of Blastomyces. We examined the relationships between reported cases of blastomycosis in three Midwestern US states (Michigan, Minnesota, and Wisconsin) from 2007–2017 in relation to eleven hypothesized environmental conditions, including climate, stream and soil mineral content, and land cover variables. Then, we fit logistic regression models to explore the relationships between the environmental variables and yearly blastomycosis case occurrence. Mean soil moisture, stream sediment mercury content, percent of water within the county, and woody wetlands land cover were all positively associated with the presence of annual cases, with woody wetlands having the most consistent signal across the three states. We also found significant differences in the likelihood of case presence between US states that were not explained by the variables in our model, suggesting state-level differences in case reporting and disease awareness. Our results provide a perspective on potential biological hypotheses to further test regarding environmental controls on the life cycle and ecological niche of Blastomyces.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Open Specy 1.0: Automated (Hyper)spectroscopy for Microplastics

Microplastic spectral analysis is one of the most time-consuming processes in studying microplastic pollution, often requiring days per sample. Researchers are transitioning to automated batch and hyperspectral image analysis techniques to enhance efficiency. Open Specy, initially aimed at manual single-spectrum analysis, has now integrated automated methods. This updated version, Open Specy 1.0, introduces several new features, including two algorithms for automated processing (smoothing and particle compression), an extensive library containing over 40,000 open-source Raman and FTIR spectra, and two machine learning classifiers (logistic regression and k medoids) developed from this library. Furthermore, it includes a revamped user interface, an R package, and a benchmark data set for testing future advancements in automated techniques. Researchers evaluated various configurations for hyperspectral smoothing, particle identification, compression, and splitting, to achieve combined recovery rates between 50 and 150% particle counts, identities, and sizes with a coefficient of variation (CV) of less than 40% (the accredited standard). Mean absorbance times the standard deviation provided a consistent particle identification. Hyperspectral smoothing led to a 96% combined recovery rate and reduced variability (CV = 38%) compared to the 86% recovery (CV = 83%) of nonsmoothed controls. Additionally, compressing spectra for particles was significantly faster (>3x) and showed similar accuracy but with reduced variability than processing each pixel individually. Key challenges persist in automating spectral analysis, particularly in refining particle splitting algorithms, and improving identification routines to minimize false positives and negatives. In conclusion, new methods in sample preparation for better stabilization and dispersion of particles could overcome some of these issues.

13 HYDRO ENERGY↗
DOE OSTI2021

IoT Intrusion Detection Taxonomy, Reference Architecture, and Analyses

This paper surveys the deep learning (DL) approaches for intrusion-detection systems (IDSs) in Internet of Things (IoT) and the associated datasets toward identifying gaps, weaknesses, and a neutral reference architecture. A comparative study of IDSs is provided, with a review of anomaly-based IDSs on DL approaches, which include supervised, unsupervised, and hybrid methods. All techniques in these three categories have essentially been used in IoT environments. To date, only a few have been used in the anomaly-based IDS for IoT. For each of these anomaly-based IDSs, the implementation of the four categories of feature(s) extraction, classification, prediction, and regression were evaluated. We studied important performance metrics and benchmark detection rates, including the requisite efficiency of the various methods. Four machine learning algorithms were evaluated for classification purposes: Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and an Artificial Neural Network (ANN). Therefore, we compared each via the Receiver Operating Characteristic (ROC) curve. The study model exhibits promising outcomes for all classes of attacks. The scope of our analysis examines attacks targeting the IoT ecosystem using empirically based, simulation-generated datasets (namely the Bot-IoT and the IoTID20 datasets).

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

Modeling and managing risk early in software development

In order to improve the quality of the software development process, we need to be able to build empirical multivariate models based on data collectable early in the software process. These models need to be both useful for prediction and easy to interpret, so that remedial actions may be taken in order to control and optimize the development process. We present an automated modeling technique which can be used as an alternative to regression techniques. We show how it can be used to facilitate the identification and aid the interpretation of the significant trends which characterize 'high risk' components in several Ada systems. Finally, we evaluate the effectiveness of our technique based on a comparison with logistic regression based models.

Briand, Lionel C.↗
DOE OSTI2023

Epidemiologic Factors Supporting Triage of Infected Dog Patients Admitted to a Veterinary Hospital Biological Isolation and Containment Unit

The teaching hospital of the Faculty of Veterinary Medicine at the University of Lisbon hosts a Biological Isolation and Containment Unit (BICU) for the hospitalization of both confirmed and suspected animals of an infectious disease. This study targets the BICU dog population to identify and characterize the most frequent infectious diseases recorded in a 7-year period. Several epidemiologic factors were analyzed for their significance to triage infected cases. During the study period, 534 dogs were admitted, of which 263 (49.3%) had a confirmed infectious disease diagnosis: parvovirosis (49.4%; n = 130); leptospirosis (21.7%; n = 57); multidrug-resistant (MDR) bacterial infection; (10.6%; n = 28), and canine distemper (9.9%; n = 26). Several potential risk factors for these diseases were identified: age under 2 years old (p < 0.001), incomplete vaccination for parvovirosis (p < 0.001), age ≥ 10 years old (p < 0.001), and the presence of concomitant disorders for MDR-infected cases (p = 0.03). Logistic regression models were constructed to classify cases and controls. The sensitivity and specificity estimates were very high (>0.83) for parvovirosis, MDR, and distemper infections. A lower sensitivity (0.77) was obtained for identifying cases with leptospirosis. In conclusion, infectious diseases are frequent, hence, it is essential to decrease their occurrence through effective preventive measures such as vaccination. The constructed logistic models can also help in triaging admitted dogs with a potential infectious disease.

Machado, Inês Cunha (ORCID:0000000238151125)↗
NASA NTRS1998

Distribution and observed associations of orthostatic blood pressure changes in elderly general medicine outpatients

Factors associated with orthostatic blood pressure change in elderly outpatients were determined by surveying 398 medical clinical outpatients aged 65 years and older. Blood pressure was measured with random-zero sphygmomanometers after patients were 5 minutes in a supine and 5 minutes in a standing position. Orthostatic blood pressure changes were at normally distributed levels with systolic and diastolic pressures dropping an average of 4 mm Hg (standard deviation [SD]=15 mm Hg) and 2 mm Hg (SD=11 mm Hg), respectively. Orthostatic blood pressure changes were unassociated with age, race, sex, body mass, time since eating, symptoms, or other factors. According to multiple linear regression analysis, supine systolic pressure, chronic obstructive pulmonary disease (COPD), and diabetes mellitus were associated with a decrease in systolic pressure on standing. Hypertension, antiarthritic drugs, and abnormal heartbeat were associated with an increase in systolic pressure on standing. For orthostatic diastolic pressure changes, supine diastolic pressure and COPD were associated with a decrease in diastolic pressure on standing. Congestive heart failure was associated with an increase in standing diastolic pressure. Using logistic regression analysis, only supine systolic pressure was associated with a greater than 20-mm Hg drop in systolic pressure (n=53, prevalence=13%). Supine diastolic pressure and COPD were the only variables associated with a greater than 20-mm Hg drop in diastolic pressure (n=16, prevalence=4%). These factors may help physicians in identifying older persons at risk for having orthostatic hypotension.

Non-NASA Center↗
DOE OSTI2024

Sex Differences in Odds of Brain Metastasis and Outcomes by Brain Metastasis Status after Advanced Melanoma Diagnosis

Sex differences in cancer are well-established. However, less is known about sex differences in diagnosis of brain metastasis and outcomes among patients with advanced melanoma. Using a United States nationwide electronic health record-derived de-identified database, we evaluated patients diagnosed with advanced melanoma from 1 January 2011–30 July 2022 who received an oncologist-defined rule-based first line of therapy (n = 7969, 33% female according to EHR, 35% w/documentation of brain metastases). The odds of documented brain metastasis diagnosis were calculated using multivariable logistic regression adjusted for age, practice type, diagnosis period (pre/post-2017), ECOG performance status, anatomic site of melanoma, group stage, documentation of non-brain metastases prior to first-line of treatment, and BRAF positive status. Real-world overall survival (rwOS) and progression-free survival (rwPFS) starting from first-line initiation were assessed by sex, accounting for brain metastasis diagnosis as a time-varying covariate using the Cox proportional hazards model, with the same adjustments as the logistic model, excluding group stage, while also adjusting for race, socioeconomic status, and insurance status. Adjusted analysis revealed males with advanced melanoma were 22% more likely to receive a brain metastasis diagnosis compared to females (adjusted odds ratio [aOR]: 1.22, 95% confidence interval [CI]: 1.09, 1.36). Males with brain metastases had worse rwOS (aHR: 1.15, 95% CI: 1.04, 1.28) but not worse rwPFS (adjusted hazard ratio [aHR]: 1.04, 95% CI: 0.95, 1.14) following first-line treatment initiation. Among patients with advanced melanoma who were not diagnosed with brain metastases, survival was not different by sex (rwOS aHR: 1.06 [95% CI: 0.97, 1.16], rwPFS aHR: 1.02 [95% CI: 0.94, 1.1]). This study showed that males had greater odds of brain metastasis and, among those with brain metastasis, poorer rwOS compared to females, while there were no sex differences in clinical outcomes for those with advanced melanoma without brain metastasis.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2001

Prediction of coronary artery disease in patients undergoing operations for mitral valve degeneration

OBJECTIVES: We sought to develop and validate a model that estimates the risk of obstructive coronary artery disease in patients undergoing operations for mitral valve degeneration and to demonstrate its potential clinical utility. METHODS: A total of 722 patients (67% men; age, 61 +/- 12 years) without a history of myocardial infarction, ischemic electrocardiographic changes, or angina who underwent routine coronary angiography before mitral valve prolapse operations between 1989 and 1996 were analyzed. A bootstrap-validated logistic regression model on the basis of clinical risk factors was developed to identify low-risk (< or =5%) patients. Obstructive coronary atherosclerosis was defined as 50% or more luminal narrowing in one or more major epicardial vessels, as determined by means of coronary angiography. RESULTS: One hundred thirty-nine (19%) patients had obstructive coronary atherosclerosis. Independent predictors of coronary artery disease include age, male sex, hypertension, diabetes mellitus,and hyperlipidemia. Two hundred twenty patients were designated as low risk according to the logistic model. Of these patients, only 3 (1.3%) had single-vessel disease, and none had multivessel disease. The model showed good discrimination, with an area under the receiver-operating characteristic curve of 0.84. Cost analysis indicated that application of this model could safely eliminate 30% of coronary angiograms, corresponding to cost savings of $430,000 per 1000 patients without missing any case of high-risk coronary artery disease. CONCLUSION: A model with standard clinical predictors can reliably estimate the prevalence of obstructive coronary atherosclerosis in patients undergoing mitral valve prolapse operations. This model can identify low-risk patients in whom routine preoperative angiography may be safely avoided.

Non-NASA Center↗
NASA NTRS2011

Tissue Doppler Imaging Combined with Advanced 12-Lead ECG Analysis Might Improve Early Diagnosis of Hypertrophic Cardiomyopathy in Childhood

Optimization of early diagnosis of childhood hypertrophic cardiomyopathy (HCM) is essential in lowering the risk of HCM complications. Standard echocardiography (ECHO) has shown to be less sensitive in this regard. In this study, we sought to assess whether spatial QRS-T angle deviation, which has shown to predict HCM in adults with high sensitivity, and myocardial Tissue Doppler Imaging (TDI) could be additional tools in early diagnosis of HCM in childhood. Methods: Children and adolescents with familial HCM (n=10, median age 16, range 5-27 years), and without obvious hypertrophy but with heredity for HCM (n=12, median age 16, range 4-25 years, HCM or sudden death with autopsy-verified HCM in greater than or equal to 1 first-degree relative, HCM-risk) were additionally investigated with TDI and advanced 12-lead ECG analysis using Cardiax(Registered trademark) (IMED Co Ltd, Budapest, Hungary and Houston). Spatial QRS-T angle (SA) was derived from Kors regression-related transformation. Healthy age-matched controls (n=21) were also studied. All participants underwent thorough clinical examination. Results: Spatial QRS-T angle (Figure/ Panel A) and septal E/Ea ratio (Figure/Panel B) were most increased in HCM group as compared to the HCM-risk and control groups (p less than 0.05). Of note, these 2 variables showed a trend toward higher levels in HCM-risk group than in control group (p=0.05 for E/Ea and 0.06 for QRS/T by ANOVA). In a logistic regression model, increased SA and septal E/Ea ratio appeared to significantly predict both the disease (Chi-square in HCM group: 9 and 5, respectively, p less than 0.05 for both) and the risk for HCM (Chi-square in HCM-risk group: 5 and 4 respectively, p less than 0.05 for both), with further increased predictability level when these 2 variables were combined (Chi-square 10 in HCM group, and 7 in HCM-risk group, p less than 0.01 for both). Conclusions: In this small material, Tissue Doppler Imaging and spatial mean QRS-T angle deviation, particularly when combined, appear to be sensitive in predicting the risk for developing childhood HCM. Large-scale, prospective studies are needed to confirm this hypothesis.

Femlund, E.↗
DOE OSTI2022

Construction of Women’s All-Around Speed Skating Event Performance Prediction Model and Competition Strategy Analysis Based on Machine Learning Algorithms

Introduction Accurately predicting the competitive performance of elite athletes is an essential prerequisite for formulating competitive strategies. Women’s all-around speed skating event consists of four individual subevents, and the competition system is complex and challenging to make accurate predictions on their performance. Objective The present study aims to explore the feasibility and effectiveness of machine learning algorithms for predicting the performance of women’s all-around speed skating event and provide effective training and competition strategies. Methods The data, consisting of 16 seasons of world-class women’s all-around speed skating competition results, used in the present study came from the International Skating Union (ISU). According to the competition rules, distinct features are filtered using lasso regression, and a 5,000 m race model and a medal model are built using a fivefold cross-validation method. Results The results showed that the support vector machine model was the most stable among the 5,000 m race and the medal models, with the highest AUC (0.86, 0.81, respectively). Furthermore, 3,000 m points are the main characteristic factors that decide whether an athlete can qualify for the final. The 11th lap of the 5,000 m, the second lap of the 500 m, and the fourth lap of the 1,500 m are the main characteristic factors that affect the athlete’s ability to win medals. Conclusion Compared with logistic regression, random forest, K-nearest neighbor, naive Bayes, neural network, support vector machine is a more viable algorithm to establish the performance prediction model of women’s all-around speed skating event; excellent performance in the 3,000 m event can facilitate athletes to advance to the final, and athletes with outstanding performance in the 500 m event are more likely competitive for medals.

Liu, Meng↗