Investigating the intersection of statistical theory and real-world applications
PLOS One
Childhood malnutrition remains a major public health concern in Nepal and other low-resource settings, while conventional case-finding approaches are labor-intensive and frequently unavailable in remote areas. This study provides one of the first applications of machine learning and deep learning to identify child malnutrition in Nepal. We systematically compared 16 algorithms spanning deep learning, gradient boosting, and traditional machine learning families, using data from the Nepal Multiple Indicator Cluster Survey (MICS) 2019. A composite malnutrition indicator was constructed by integrating stunting, wasting, and underweight status, and model performance was evaluated using ten metrics, with emphasis on F1-score and recall to account for substantial class imbalance and the high cost of failing to detect malnourished children. Among all models, TabNet achieved the highest scores among evaluated models, likely attributable to its attention-based architecture. A consensus feature importance analysis identified maternal education, household wealth index, and child age as the primary predictors of malnutrition, followed by geographic characteristics, vaccination status, and meal frequency. Collectively, these results demonstrate a scalable, survey-based screening framework for identifying children at elevated risk of malnutrition and for guiding targeted nutritional interventions. The proposed approach supports Nepal’s progress toward the Sustainable Development Goals and offers a transferable methodological template for similar low-resource settings globally.
Read MorePublic Health Nutrition
This study investigates childhood anemia in Nepal using NDHS 2022 data from 1,855 children aged 6–59 months. It evaluates 48 demographic, socioeconomic, maternal, and child-health features using four feature-selection methods and identifies five consistently important predictors: child age, recent fever, household size, maternal anemia, and deworming history. Eight traditional machine-learning and two deep-learning models were then compared, with logistic regression achieving the highest recall and F1-score, DNN achieving the highest accuracy, and SVM showing the highest AUC. Overall, the findings demonstrate that machine-learning approaches can effectively support childhood anemia risk prediction, while interpretable factors such as child age, infection, maternal anemia, and deworming history may be useful for public health screening and risk stratification in Nepal.
Read MoreSTAR Journal of Applied Mathematics, Statistics, and Computational Science
This article develops a unified mathematical framework for applying Lotka–Volterra predator–prey dynamics to economic and financial systems. It demonstrates that the Goodwin growth-cycle model is algebraically equivalent to the Lotka–Volterra model, generating endogenous periodic business cycles; extends the framework to a debt-capital model that captures Minsky’s Financial Instability Hypothesis and shows how stochastic shocks drive financial instability; introduces a three-species model exhibiting a Hopf bifurcation; and proves that a stochastic agent-based buyer-seller model with herding converges to the deterministic Lotka-Volterra dynamics as the number of agents becomes large.
Agricultural Topic Classification for Low-Resource South Asian Languages: A Multilingual Dataset, Baseline Evaluation, and Cross-Lingual Transfer Benchmark
Random Schrodinger Operators on Data Graphs: A Data Science Perspective on Robust Spectral Embedding
Developed SARIMA models in predicting crime patterns across Chicago using 24 years of historical data.
Math for Data Science by Omar Hijab (Second Edition)
Comprehensive review of mathematical foundations essential for data science and machine learning.
Math for Data Science by Omar Hijab (First Edition)
Comprehensive review of mathematical foundations essential for data science and machine learning.
Research at the Interface of Applied Mathematics and Machine Learning CBMS Conference
University of Houston, Houston, TX, USA
Data Science Week 2025 (Virtual)
Purdue University Fort Wayne, Fort Wayne, IN, USA
iLead Student Leadership Conference, Florida Atlantic University
Florida Atlantic University, Boca Raton, FL, USA
Florida Sectional Conference, Mathematical Association of America
Embry-Riddle Aeronautical University, Daytona Beach, FL, USA