About

Anirban DasGupta is a Professor of Statistics at Purdue University. His research interests include asymptotics, probability, inequalities, and probability and analysis. He earned his B.S. and M.S. degrees from the Indian Statistical Institute in 1977 and 1978, respectively, and completed his Ph.D. at the same institute in 1984. Throughout his career, he has held various editorial positions, including editor of the Institute of Mathematical Statistics Collections and Volumes Series and the Lecture Notes-Monograph Series, as well as associate editor roles for several prominent statistical journals. He has been recognized as a Fellow of the Institute of Mathematical Statistics since 1993 and has received multiple awards, including being named one of the Top Ten Outstanding Teachers in the College of Science at Purdue in 1987 and 1997. His contributions to the field are marked by his involvement in statistical research, editorial leadership, and recognition as a distinguished educator.

Research topics

• Physics
• Astronomy
• Astrophysics
• Computer Science
• Quantum mechanics
• Demography

Selected publications

• Data-driven gradient optimization-based approach for robust distribution system state estimation

  Sustainable Energy Grids and Networks · 2026-04-20

  article
  PublisherDOI

• Impact of m-Health Guided Alternate Nostril Yogic Breathing on Anxiety Levels in Parents of Children with Autism Spectrum Disorder: An Interprofessional Approach

  Journal of the Epidemiology Foundation of India · 2026-02-24

  articleOpen access

  Introduction: A unique stressor has been witnessed in the parents of children who are diagnosed with autism spectrum disorder (ASD) and often suffer from higher levels of stress, anxiety and depression compared to the parents of neurotypical children. Hence, Alternate Nostril Yogic Breathing (ANYB) has been used in the study, commonly known for balancing autonomic nervous system. Recognizing the time constraints faced by parents of children with ASD, the research hypothesizes that a guided 5-minute video on ANYB through mHealth will mitigate anxiety, depression, and stress levels, subsequently protecting parents from associated health risks. The present study aims to evaluate the effectiveness of ANYB administered through mobile (m) -Health on the depression, anxiety, and stress levels of parents of children with ASD. Additionally, it seeks to explore the facilitators and barriers of this intervention. Methods: This mixed-method study including quasi-experimental design and focus group discussion. The study enrolled 74 participants, 30 in the intervention and 44 in the control arm. The Depression Anxiety Stress Scale 21 (DASS21) is the tool used to assess mental health before and after intervention. The intervention group (n=30) received training in ANYB with 5-minute guided m-Health video to practice daily for 2 months, combined with parental training. The control group (n=30) received only parental training. Findings: At pre-intervention phase, the baseline data shows (80.0%) of the subjects were suffering from depression, 100% from anxiety and 43.3% from stress. Post intervention reductions in Depression (63.3%), Anxiety (43.3%) and Stress (0%) among parents of children with ASD in experimental group, while the control group showed no such change. Conclusions: The study emphasizes the importance of m-Health guided ANYB that turns out to be an accessible, acceptable, and impactful solution to reduce stress, anxiety, and depression among parents of children with ASD.

  PublisherDOI

• Local Fragments, Global Gains: Subgraph Counting using Graph Neural Networks

  2026-02-22

  articleOpen accessSenior author

  Subgraph counting is a fundamental task for analyzing structural patterns in graph-structured data, particularly crucial for applications in computational biology and social network analysis, where identifying recurring motifs reveals functional properties and organizational structures. We propose a novel three-stage differentiable learning algorithm that computes the counts of various patterns by learning to combine the counts of its subpatterns. Our approach leverages localized versions of Weisfeiler-Leman (WL) algorithms and introduces a novel fragmentation technique that decomposes complex subgraphs into simpler patterns. This technique enables exact counting of all induced subgraphs of size at most 4 using just 1-WL. This method significantly improves upon existing Graph Neural Network (GNN) based approaches for subgraph counting, being computationally efficient, making it well-suited for learning combinatorial algorithms.

  PublisherDOI

• Disease classification through advanced neural networks

  Elsevier eBooks · 2026-01-01

  book-chapter1st authorCorresponding
  PublisherDOI

• Glaucoma Classification from Fundus Images Using Meta-Learning Models

  2025-03-06 · 1 citations

  article1st authorCorresponding

  The present paper introduces a novel method for the accurate classification of glaucoma with minimal labeled samples using a combination of meta-learning and data augmentation techniques. The proposed model is trained to learn generalized features from fundus images and can efficiently adapt to new, unseen classes with only a few labeled examples. Extensive experiments on the 1000 Fundus image dataset demonstrate the improved classification accuracy and robustness of the proposed method over existing few-shot learning techniques and traditional deep learning models. The results underline the potential of few-shot learning for real-world applications in glaucoma screening, particularly in environments where availability of large, labeled datasets is restricted.

  PublisherDOI

• Linear Programming Based Approximation to Individually Fair k-Clustering with Outliers

  2025-11-12 · 1 citations

  articleSenior author

  Individual fairness guarantees are often desirable properties to have, but they become hard to formalize when the dataset contains outliers. Here, we investigate the problem of developing an individually fair <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex>-median and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex>-means clustering algorithm for datasets that contain outliers. That is, given <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$n$</tex> points and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> centers, we want that for each point which is not an outlier, there must be a center within the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\frac{n}{k}$</tex> nearest neighbours of the given point. While a few of the recent works have looked into individually fair clustering, this is the first work that explores this problem in the presence of outliers for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex>-clustering. For this purpose, we define and solve a linear program (LP) that helps us identify the outliers. We exclude these outliers from the dataset and apply a rounding algorithm that computes the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> centers, such that the fairness constraint of the remaining points is satisfied. We also provide theoretical guarantees that our method leads to a guaranteed approximation of the fair radius as well as the clustering cost. We also demonstrate our techniques empirically on real-world datasets.

  PublisherDOI

• Locating Femoral Vein by Anatomic Landmarks: A Cadaveric Study

  Cureus · 2025-03-27 · 1 citations

  articleOpen accessSenior author

  BACKGROUND: In circumstances of emergency or challenging peripheral access, the femoral vein serves as a vital intravenous access channel. The vein is commonly located by palpating the femoral arterial pulse inferior to the mid-inguinal point or by the 'V' technique. As femoral arterial pulse may not be non-palpable in some cases, some distances from nearby anatomic landmarks might help to locate the femoral vein for cannulation. MATERIALS AND METHODS: In 54 dissected cadaveric lower limbs, the distances of the femoral vein from the anterior superior iliac spine, the symphysis pubis, and the skin surface were measured to prepare a dataset for locating the vein with the help of these data. The values were statistically analyzed. RESULT: The mean distance of the femoral vein from the anterior superior iliac spine was 80.16±8.96 mm, the mean distance from the symphysis pubis was 66.77±11.08 mm, and the mean depth of the femoral vein from the skin surface was 20.93±8.84 mm. All the distances and skin depths were higher in female limbs; however, only the depth from the skin surface was statistically significant across the genders. CONCLUSION: These datasets might be useful as additional support while performing femoral vein cannulation in complicated and challenging cases where the facility of radiological monitoring is not available.

  PublisherOA PDFDOI

• Current Internet of Things Technology for Smart Cities

  IEEE Instrumentation & Measurement Magazine · 2025-09-01 · 1 citations

  article1st authorCorresponding

  Smart cities signify urban spaces that use Artificial Intelligence (AI), Information and Communication Technology (ICT), and the Internet of Things (IoT) to create sustainable, efficient, and safe environments for residents. Smart cities integrate cloud computing, sensors, edge computing, and data science to enable real-time data exchange and enhance decision-making for city management. According to the International Data Corporation (IDC), global investment in smart city initiatives is projected to reach $135 billion by 2026 [1]. This projection is based on the increasing demand for innovative technologies to enhance urban living conditions, especially in the post-COVID-19 era. This article explores the latest impactful IoT technologies in smart cities, their applications across various sectors, and their existing challenges.

  PublisherDOI

• Classification of Driving Condition Images for Semi-autonomous Vehicles Through Data Augmentation and Transfer Learning

  2025-01-01

  book-chapter
  PublisherDOI

• Enhanced Gradient-Optimized Tree Boosting Approach for Distribution System State Estimation Considering Non-Gaussian Colored Noise

  2025-08-04

  article

  Estimating state variables in distribution systems becomes difficult when dealing with non-Gaussian colored noise. Traditional Forecasting-aided state estimation (FASE) techniques struggle with this challenge due to their reliance on Gaussian and white noise assumptions. However, in real-world scenarios, noise can be non-Gaussian and colored, which can degrade the performance of FASE methods. To overcome this problem, we propose a state estimation algorithm based on a data-driven model. In contrast to traditional FASE techniques, it does not make any assumptions. Hence, we propose a data-driven solution based on enhanced gradient-optimized tree boosting (EGOTB) for state estimation in distribution systems, which can tackle the problem of non-Gaussian colored noise. The performance of the proposed method on the IEEE-123 bus system to validate its effectiveness.

  PublisherDOI

Frequent coauthors

• J. van den Brand

  69 shared

• A. Heidmann

  45 shared

• R. Frey

  41 shared

• M. Wąs

  Laboratoire d’Annecy de Physique des Particules

  40 shared

• E. Chassande–Mottin

  Laboratoire AstroParticule et Cosmologie

  40 shared

• T. Briant

  Collège de France

  39 shared

• T. Jacqmin

  Laboratoire Kastler Brossel

  38 shared

• M. Bejger

  Nicolaus Copernicus Astronomical Center

  38 shared

Education

• B.S.

  Indian Statistical Institute

  1977

• M.S.

  Indian Statistical Institute

  1978

• Ph.D.

  Indian Statistical Institute

  1984

Awards & honors

• Editor, Institute of Mathematical Statistics Collections and…
• Editor, Institute of Mathematical Statistics Lecture Notes-M…
• Invited talk at IMS Annual Meeting, Banff (2002)
• Associate Editor, Sankhya (1997)
• Top Ten Outstanding Teachers in College of Science (1997)