About

Tauhidur Rahman is the Director of The Initiative for Agency and Development and a Professor of Agricultural and Resource Economics at the University of Arizona. He leads interdisciplinary research efforts that integrate insights from economics, law, and behavioral sciences to address critical issues related to poverty, agency, and development. Under his leadership, the initiative focuses on promoting solutions to these challenges through research, education, and policy dialogues. Rahman's work is central to advancing understanding and designing effective development policies and programs that enhance agency and economic development.

Research topics

• Computer Science
• Political Science
• Medical emergency
• Machine Learning
• Medicine
• Systems engineering
• Telecommunications
• Real-time computing
• Engineering
• Embedded system
• Process management
• Business

Selected publications

• The Rise of Social Safety Nets and Social Insurance in the West: Implications for Developing Countries

  The MIT Press eBooks · 2026-03-10

  book-chapterOpen accessSenior author
  PublisherOA PDFDOI

• Cutaneous Microvascular Functional Reserve is Associated with Kidney Function and Histopathologic Injury in CKD: The MAP-CKD Study

  medRxiv · 2026-04-27

  articleOpen access

  Background: Microvascular dysfunction is a key contributor to the development and progression of chronic kidney disease (CKD), yet direct and reproducible assessment of microvascular function in clinical CKD populations remains limited. Laser Doppler flowmetry (LDF) provides a noninvasive, dynamic assessment of skin microvascular blood flow and may serve as a surrogate measure of systemic microvascular health. However, the extent to which LDF-derived measures relate to kidney function, proteinuria, and kidney histopathology in CKD remains unclear. Methods: ) using a standardized forearm LDF protocol. Baseline perfusion was recorded at ~30°C, followed by local heating to 44 °C to induce hyperemia. The percentage change in perfusion unit (PU) was calculated and used to define microvascular functional reserve. Associations between LDF-derived measures with eGFR and urine protein-to-creatinine ratio (uPCR) were assessed using multivariable linear regression adjusted for demographic and clinical covariates. Unsupervised k-means clustering was performed to identify microvascular phenotypes based on resting PU and microvascular function reserve. Associations of LDF measures with glomerulosclerosis (GS) and interstitial fibrosis and tubular atrophy (IFTA) were evaluated in a subset of participants (n = 20) who underwent clinically indicated kidney biopsies. Results: and median uPCR was 0.21 (interquartile range (IQR) 0.11 to 1.20) mg/mg. Higher baseline PU (β = -12; 95% CI, -24 to -1) and reduced percentage change in PU (β = 7; 95% CI, 2 to 13) was associated with lower eGFR, independent of covariates. Baseline PU or percentage change in PU were not associated with uPCR. Unsupervised clustering identified four distinct microvascular phenotypes characterized by graded differences in resting perfusion and microvascular function reserve. Among participants with biopsy data, higher baseline PU and lower percentage change in PU were associated with greater severity of GS and IFTA. Conclusion: In persons with CKD, elevated resting perfusion and impaired microvascular functional reserve were associated with lower eGFR. These findings suggest that LDF-derived measures capture clinically relevant alterations in systemic microvascular function and may serve as a noninvasive biomarker of kidney function and underlying histopathologic injury in CKD.

  PublisherOA PDFDOI

• Automated Dysphagia Screening Using Noninvasive Neck Acoustic Sensing

  Open MIND · 2026-02-02

  preprint

  Pharyngeal health plays a vital role in essential human functions such as breathing, swallowing, and vocalization. Early detection of swallowing abnormalities, also known as dysphagia, is crucial for timely intervention. However, current diagnostic methods often rely on radiographic imaging or invasive procedures. In this study, we propose an automated framework for detecting dysphagia using portable and noninvasive acoustic sensing coupled with applied machine learning. By capturing subtle acoustic signals from the neck during swallowing tasks, we aim to identify patterns associated with abnormal physiological conditions. Our approach achieves promising test-time abnormality detection performance, with an AUC-ROC of 0.904 under 5 independent train-test splits. This work demonstrates the feasibility of using noninvasive acoustic sensing as a practical and scalable tool for pharyngeal health monitoring.

  DOI

• Personalized entropy-informed deep learning for identifying opioid misuse

  Nature Mental Health · 2026-01-05

  articleSenior authorCorresponding
  PublisherDOI

• Automated Dysphagia Screening Using Noninvasive Neck Acoustic Sensing

  ArXiv.org · 2026-02-02

  articleOpen access

  Pharyngeal health plays a vital role in essential human functions such as breathing, swallowing, and vocalization. Early detection of swallowing abnormalities, also known as dysphagia, is crucial for timely intervention. However, current diagnostic methods often rely on radiographic imaging or invasive procedures. In this study, we propose an automated framework for detecting dysphagia using portable and noninvasive acoustic sensing coupled with applied machine learning. By capturing subtle acoustic signals from the neck during swallowing tasks, we aim to identify patterns associated with abnormal physiological conditions. Our approach achieves promising test-time abnormality detection performance, with an AUC-ROC of 0.904 under 5 independent train-test splits. This work demonstrates the feasibility of using noninvasive acoustic sensing as a practical and scalable tool for pharyngeal health monitoring.

  PublisherOA PDF

• Automated Dysphagia Screening Using Noninvasive Neck Acoustic Sensing

  2026-04-21

  article

  Pharyngeal health plays a vital role in essential human functions such as breathing, swallowing, and vocalization. Early detection of swallowing abnormalities, also known as dysphagia, is crucial for timely intervention. However, current diagnostic methods often rely on radiographic imaging or invasive procedures. In this study, we propose an automated framework for detecting dysphagia using portable and noninvasive acoustic sensing coupled with applied machine learning. By capturing subtle acoustic signals from the neck during swallowing tasks, we aim to identify patterns associated with abnormal physiological conditions. Our approach achieves promising test-time abnormality detection performance, with an AUC-ROC of 0.904 under 5 independent train–test splits. This work demonstrates the feasibility of using noninvasive acoustic sensing as a practical and scalable tool for pharyngeal health monitoring.

  PublisherDOI

• The Causal Effect of Happiness and Fear on Test Scores 

  SSRN Electronic Journal · 2026-01-01

  preprintOpen access
  PublisherDOI

• Forecasting Occupational Survivability of Rickshaw Pullers in a Changing Climate with Wearable Data

  ArXiv.org · 2025-10-29

  preprintOpen accessSenior author

  Cycle rickshaw pullers are highly vulnerable to extreme heat, yet little is known about how their physiological biomarkers respond under such conditions. This study collected real-time weather and physiological data using wearable sensors from 100 rickshaw pullers in Dhaka, Bangladesh. In addition, interviews with 12 pullers explored their knowledge, perceptions, and experiences related to climate change. We developed a Linear Gaussian Bayesian Network (LGBN) regression model to predict key physiological biomarkers based on activity, weather, and demographic features. The model achieved normalized mean absolute error values of 0.82, 0.47, 0.65, and 0.67 for skin temperature, relative cardiac cost, skin conductance response, and skin conductance level, respectively. Using projections from 18 CMIP6 climate models, we layered the LGBN on future climate forecasts to analyze survivability for current (2023-2025) and future years (2026-2100). Based on thresholds of WBGT above 31.1°C and skin temperature above 35°C, 32% of rickshaw pullers already face high heat exposure risk. By 2026-2030, this percentage may rise to 37% with average exposure lasting nearly 12 minutes, or about two-thirds of the trip duration. A thematic analysis of interviews complements these findings, showing that rickshaw pullers recognize their increasing climate vulnerability and express concern about its effects on health and occupational survivability.

  PublisherOA PDFDOI

• A Training Framework for Optimal and Stable Training of Polynomial Neural Networks

  ArXiv.org · 2025-05-16

  preprintOpen accessSenior author

  By replacing standard non-linearities with polynomial activations, Polynomial Neural Networks (PNNs) are pivotal for applications such as privacy-preserving inference via Homomorphic Encryption (HE). However, training PNNs effectively presents a significant challenge: low-degree polynomials can limit model expressivity, while higher-degree polynomials, crucial for capturing complex functions, often suffer from numerical instability and gradient explosion. We introduce a robust and versatile training framework featuring two synergistic innovations: 1) a novel Boundary Loss that exponentially penalizes activation inputs outside a predefined stable range, and 2) Selective Gradient Clipping that effectively tames gradient magnitudes while preserving essential Batch Normalization statistics. We demonstrate our framework's broad efficacy by training PNNs within deep architectures composed of HE-compatible layers (e.g., linear layers, average pooling, batch normalization, as used in ResNet variants) across diverse image, audio, and human activity recognition datasets. These models consistently achieve high accuracy with low-degree polynomial activations (such as degree 2) and, critically, exhibit stable training and strong performance with polynomial degrees up to 22, where standard methods typically fail or suffer severe degradation. Furthermore, the performance of these PNNs achieves a remarkable parity, closely approaching that of their original ReLU-based counterparts. Extensive ablation studies validate the contributions of our techniques and guide hyperparameter selection. We confirm the HE-compatibility of the trained models, advancing the practical deployment of accurate, stable, and secure deep learning inference.

  PublisherOA PDFDOI

• Anti-Sensing: Defense against Unauthorized Radar-based Human Vital Sign Sensing with Physically Realizable Wearable Oscillators

  ArXiv.org · 2025-05-16

  preprintOpen accessSenior author

  Recent advancements in Ultra-Wideband (UWB) radar technology have enabled contactless, non-line-of-sight vital sign monitoring, making it a valuable tool for healthcare. However, UWB radar's ability to capture sensitive physiological data, even through walls, raises significant privacy concerns, particularly in human-robot interactions and autonomous systems that rely on radar for sensing human presence and physiological functions. In this paper, we present Anti-Sensing, a novel defense mechanism designed to prevent unauthorized radar-based sensing. Our approach introduces physically realizable perturbations, such as oscillatory motion from wearable devices, to disrupt radar sensing by mimicking natural cardiac motion, thereby misleading heart rate (HR) estimations. We develop a gradient-based algorithm to optimize the frequency and spatial amplitude of these oscillations for maximal disruption while ensuring physiological plausibility. Through both simulations and real-world experiments with radar data and neural network-based HR sensing models, we demonstrate the effectiveness of Anti-Sensing in significantly degrading model accuracy, offering a practical solution for privacy preservation.

  PublisherOA PDFDOI

Recent grants

• Collaborative Research: SCH: Psychophysiological sensing to enhance mindfulness-based interventions for self-regulation of opioid cravings

  NSF · $338k · 2022–2023

Frequent coauthors

• Deepak Ganesan

  36 shared

• Satheesh V. Aradhyula

  University of Arizona

  32 shared

• Dennis C. Cory

  26 shared

• Manasa Kalanadhabhatta

  Amherst College

  26 shared

• Melissa Anne Burns

  21 shared

• Miles H. Kiger

  21 shared

• Zhongyang Zhang

  University of California, San Diego

  19 shared

• Stephanie Carreiro

  University of Massachusetts Chan Medical School

  15 shared

Education

• Ph.D., Information Science

  Cornell University

  2017

Awards & honors

• Grants from World Bank, National Science Foundation, Nationa…