Publications

Peer-reviewed papers and preprints.

Journal Articles

[16] Learning to detect PII: Tabular vs Document Classification models for network traffic analysis. Rishika Kohli, Shaifu Gupta, Manoj Gaur, S. S. Dhavala.
Journal of Information Security and Applications, 2025. (accepted) · paper

[15] Artificial intelligence for advancing eye care in resource-poor settings: Assessing the predictive accuracy of an AI-model for diabetic retinopathy screening in India. Rohan Chawla, Prachi Karkhanis, Malay Shah, Aritra Das, Rishabh Sharma, Dhwani Almaula, Pradeep Venkatesh, Harsh Vardhan Singh, Mukul Kumar, Ramanuj Samanta, Vinod Kumar, Amar Shah, Bhavin Vadera, Nakul Jain, Akanksha Sen, Shyamsundar Shreedhar, Vipin Garg, Soma Dhavala, Kowshik Ganesh, Srinivas Rana, Radhika Tandon.
Global Epidemiology, 2025. (accepted)

[14] quantile-Long Short Term Memory (qLSTM): A Robust, Time Series Anomaly Detection Method. S. Jyotirmoy, S. Santanu, S. S. Dhavala, S. Saha.
IEEE Transactions on Artificial Intelligence, 2024. (accepted)

[13] Estimation and Applications of Quantiles in Deep Binary classification tasks. A. Tambwekar, A. Maiya, S. S. Dhavala, S. Saha.
IEEE Transactions on Artificial Intelligence, 2021.

[12] LipGene: Lipschitz continuity guided adaptive learning rates for fast convergence on Microarray Expression Data Sets. Tejas Prashanth, Snehanshu Saha, Sumedh Basarkod, Suraj Aralihalli, Soma S. Dhavala, Sriparna Saha, Raviprasad Aduri.
IEEE Transactions on Computational Biology, 2021.

[11] AdaSwarm: Augmenting gradient-based optimizers in Deep Learning with Swarm Intelligence. R. Mohapatra, S. Saha, C. Coello, A. Bhattacharya, S. S. Dhavala, S. Saha.
IEEE Transactions on Emerging Topics in Computational Intelligence, 2022.

[10] A Methodology to Design Heuristics for Model Selection Based on Characteristics of Data: Application to Investigate When the Negative Binomial Lindley (NB-L) is Preferred Over the Negative Binomial (NB). M. Shirazi, S. S. Dhavala, D. Lord, S. R. Geedipally.
Accident Analysis and Prevention, Vol. 107, pp. 186–194, 2017.

[09] A Semiparametric Negative Binomial Generalized Linear Model for Modeling Over-Dispersed Count Data with a Heavy Tail: Characteristics and Applications to Crash Data. Mohammad A. Shirazi, Soma S. Dhavala, Sreenivas Geedipally, Dominique Lord.
Accident Analysis and Prevention, Vol. 91, pp. 10–18, 2016.

[08] Emulation of Numerical Models with Over-specified Basis Functions. A. Chakraborty, D. Bingham, S. S. Dhavala, C. C. Kuranz, R. P. Drake, M. J. Grosskopf, E. Rutter, B. R. Torralva, J. P. Holloway, R. G. McClarren, B. K. Mallick.
Technometrics, Vol. 59, No. 2, pp. 153–163, 2016.

[07] A caution about using the Deviance Information Criterion while modeling traffic crashes. Sreenivas Geedipally, Dominique Lord, Soma S. Dhavala.
Safety Science, Vol. 62, pp. 495–498, 2014.

[06] Bayesian object classification of gold nanoparticles. Bledar A. Konomi, Soma S. Dhavala, Jianhua Huang, Subrata Kundu, David Huitink, Hong Liang, Yu Ding, Bani K. Mallick.
Annals of Applied Statistics, Vol. 7, No. 2, pp. 640–668, 2013.

[05] Evaluation of Corn Hybrids Expressing Cry1F, Cry1A.105, Cry2Ab2, Cry34Ab1/Cry35Ab1, and Cry3Bb1 Against Southern United States Insect Pests. Melissa W. Siebert, Steve Nolting, Soma S. Dhavala, William Henrix, Craig Chism, Scott D. Stewart, John N. All, Fred Musser, David Buntin, Samuel Luke.
Journal of Economic Entomology, Vol. 32, No. 5, pp. 1825–1835, 2012.

[04] The Negative-Binomial-Generalized-Lindley Model: Characteristics and Application using Crash Data. Sreenivas Geedipally, Dominique Lord, Soma S. Dhavala.
Accident Analysis and Prevention, Vol. 45, No. 2, pp. 258–265, 2011.

[03] Characterizing the Performance of the Conway-Maxwell Poisson Generalized Linear Model. Royce A. Francis, Srinivas Reddy Geedipally, Seth D. Guikema, Soma S. Dhavala, Dominique Lord, Sara LaRocca.
Risk Analysis, Vol. 32, No. 1, pp. 167–183, 2011.

[02] The Salmonella enterica serotype Typhi Vi capsular antigen is expressed after entering the ileal mucosa. Quynh T. Tran, Gabriel Gomez, Sangeeta Khare, Sara D. Lawhon, Manuela Raffatellu, Andreas J. Baumler, Dharani Ajithdoss, Soma S. Dhavala, L. Garry Adams.
Infection & Immunity, Vol. 78, No. 1, pp. 527–535, 2010.

[01] Bayesian Modeling of MPSS data: Gene Expression Analysis of Bovine Salmonella infection. Soma S. Dhavala, Bani K. Mallick, Sangeeta Khare, Sara Lawhon, Raymond J. Carroll, L. G. Adams.
Journal of the American Statistical Association, Vol. 105, No. 491, pp. 956–967, 2010.

Book Chapters

[06] Deploying COVID-19 Case Forecasting Models in the Developing World. Sansiddh Jain, Avtansh Tiwari, Nayana Bannur, Ayush Deva, Siddhant Shingi, Vishwa Shah, Mihir Kulkarni, Namrata Deka, Keshav Ramaswami, Vasudha Khare, Harsh Maheshwari, Soma Dhavala, Jithin Sreedharan, Jerome White, Srujana Merugu, Alpan Raval.
AI for Social Good, Part 2.

[05] Probabilistic Programming with Pyro. Prakash Bisht, S. S. Dhavala.
(work in progress)

[04] A New Approach for Momentum Particle Swarm Optimization. R. Mohapatra, R. R. Talesara, S. Govil, S. Saha, S. S. Dhavala, T. Sudarshan.
In S. Patnaik, X.-S. Yang, I. Sethi (eds.), Advances in Machine Learning and Computational Intelligence (Algorithms for Intelligent Systems). Springer, Singapore, 2021.

[03] AI for Education.
UNESCO Blue Dot Magazine, pp. 47–49, 2019.

[02] Discussion of “Bayesian models for sparse regression analysis of high dimensional data by Sylvia Richardson, Leonardo Bottolo, Jeffrey Rosenthal”. Soma Dhavala, Rajesh Talluri, Bani K. Mallick, Faming Liang, Mingqi Wu.
Bayesian Statistics, Vol. 9, Proceedings of the Ninth Valencia International Conference on Bayesian Statistics, Oxford University Press, pp. 539–568, 2011. ISBN 978-0-19-969458-7.

[01] Bayesian Model-based Principal Component Analysis. Bani K. Mallick, Shubhankar Ray, Soma Dhavala.
Frontiers of Statistical Decision Making and Bayesian Analysis, in Honor of James O. Berger, eds. Ming-Hui Chen, Dipak K. Dey, Peter Mueller, Dongchu Sun, Keying Ye. Springer, New York, 2010. ISBN 978-1-4419-6943-9.

Conference Proceedings

[18] Lattice-Based Vector Quantization for Low-Bit Quantization-Aware Training. Rishika Kohli, Soma S. Dhavala, Shaifu Gupta, Manoj S. Gaur.
Proceedings of Machine Learning Research, Conference on Parsimony and Learning (CPAL), 2026. (accepted)

[17] Health Sentinel: An AI Pipeline For Real-time Disease Outbreak Detection. Devesh Pant, Rishi Raj Grandhe, Jatin Agrawal, Jushaan Singh Kalra, Sudhir Kumar, Saransh Khanna, Vipin Samaria, Mukul Paul, Satish V. Khalikar, Vipin Garg, Himanshu Chauhan, Pranay Verma, Akhil Vssg, Neha Khandelwal, Soma S. Dhavala, Minesh Mathew.
Proceedings of the Fourth Workshop on NLP for Positive Impact (NLP4PI), 2025. (accepted)

[16] QuantProb: Generalizing Probabilities along with Predictions for a Pre-trained Classifier. Aditya Challa, Soma S. Dhavala, Snehanshu Saha.
40th Conference on Uncertainty in Artificial Intelligence (UAI), 2024. (accepted)

[15] Automatic Interpretation of Line Probe Assay Test for TB. J. Agrawal, M. Kumar, A. Tiwari, S. Danisetty, S. Dhavala, N. Jain, P. Balraj, N. Singh, S. Shingi, J. Kurada, R. Rao, S. Anand, N. Kumar.
AAAI, 2024. (accepted)

[14] HMC-PSO: A Hamiltonian Monte Carlo and Particle Swarm Optimization-based optimizer. Omatharv Bharat Vaidya, Rithvik Terence DSouza, Soma Dhavala, Snehanshu Saha, Swagatam Das.
29th International Conference on Neural Information Processing (ICONIP), New Delhi, 2022. (accepted)

[13] A Deep Learning Framework for Machine Learning Interoperability. Shakkeel Ahmed, Prakash Bisht, Ravi S. Mula, Soma S. Dhavala.
1st International Conference on AI-ML Systems, Bangalore, India, ACM, 2021. (accepted)

[12] LALR: Theoretical and Experimental validation of Lipschitz Adaptive Learning Rate in Regression and Neural Networks. Snehanshu Saha, Tejas Prashanth, Suraj Aralihalli, Sumedh Basarkod, T. S. B. Sudarshan, Soma S. Dhavala.
International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 2020. (accepted)

[11] Auto-generation of diagnostic assessments and their quality evaluation. Soma S. Dhavala, Chirag Bhatia, Joy Bose, Keyur Faldu, Aditi Avasthi.
Educational Data Mining Conference (EDM), Virtual, 2020. (accepted)

[10] MOOC2.0: A Case for India. Raviteja Garlapati, Soma S. Dhavala, Nagaraju Pappu.
Knowledge Discovery and Data Mining Conference (KDD), New York, NY, 2014.

[09] A comparison between the Geometric Mean Estimator and the bias-corrected Geometric Mean Estimator for Lognormal Median. Zgenglei Gao, Iain Proctor, Soma Dhavala, Klauss Hammel.
Pesticide Behaviour in Soils, Water and Air, University of York, York, September 2013.

[08] A Bayesian Semiparametric Hierarchical Model for Analyzing Differential Expression in Sequence-Based Gene Expression Data.
Presentation, Joint Statistical Meetings, Washington DC, August 1–6, 2009.

[07] A sequential Bayesian approach to distributed estimation in wireless sensor networks.
Poster, Joint Statistical Meetings, Denver, CO, August 3–7, 2008.

[06] Characterizing the Performance of a Bayesian Conway-Maxwell Poisson GLM. with S. Geedipally, S. D. Guikema, D. Lord.
Paper presented at the 2008 Joint Statistical Meetings, Denver, CO, August 3–7, 2008.

[05] Gene Expression Analysis of Bovine Salmonella infection. with Sujay Datta, Bani K. Mallick, Sangeeta Khare, Sara Lawhon, Raymond J. Carroll, L. G. Adams.
Poster, ABCS Workshop on Bioinformatics, Computational Biology and Systems Biology, TAMU, College Station, February 22–23, 2008.

[04] An empirical Bayesian kernel density estimator.
Poster, AMSTAT Conference of Texas Statisticians, Austin, Texas, March 31 – April 1, 2006.

[03] Importance sampling in PET collimators. with R. L. Harrison, P. N. Kumar, Yiping Shao, T. K. Lewellen.
IEEE Nuclear Science Symposium Conference Record, Vol. 4, pp. 2559–2561, October 19–25, 2003.

[02] Acceleration of SimSET photon history generation. with R. L. Harrison, P. N. Kumar, Yiping Shao, R. Manjeshwar, T. K. Lewellen, F. P. Jansen.
IEEE Nuclear Science Symposium Conference Record, Vol. 3, pp. 1835–1838, November 10–16, 2002.

[01] On the Use of Chirp Transform. with K. M. M. Prabhu.
International Conference on Robotics, Vision and Parallel Processing for Automation, Universiti Sains Malaysia, Vol. 1, pp. 218–225, July 14–16, 1999.

Consulting Acknowledgements

Work to which I contributed in a consulting / advisory role and was acknowledged (not as an author).

[09] Maintaining user trust through uncertainty aware inference. Chandan Agarwal, Ashish Papanai, Jerome White.
Workshop on Deployable AI, AAAI, 2024.

[08] Highway Safety Analytics and Modeling (book). D. Lord, X. Qin, S. Geedipally.
Elsevier, 2021.

[07] Development of a Random Parameters Negative Binomial-Lindley Generalized Linear Model to analyze Over-Dispersed Data. M. R. R. Shaon, X. Qin, A. Shirazi, D. Lord, S. Geedipally.
Analytic Methods in Accident Research, Vol. 18, pp. 33–44, 2018.

[06] Characteristics Based Heuristics to Select a Logical Distribution between the Poisson Gamma and the Poisson Lognormal for Crash Data Modeling. M. Shirazi, D. Lord.
97th Annual Meeting of the Transportation Research Board (TRB), 2017. (under revision)

[05] Exploring the Application of the Negative Binomial-Generalized Exponential Model for Analyzing Traffic Crash Data with Excess Zeros. Prathyusha Vangala, Dominique Lord, Srinivas Reddy Geedipally.
Analytic Methods in Accident Research, Vol. 7, pp. 29–36, 2015.

[04] Morphologic and Cytokine Profile Characterization of Salmonella enterica Serovar Typhimurium Infection in Calves With Bovine Leukocyte Adhesion Deficiency. J. S. Nunes, S. D. Lawhon, C. A. Rossetti, S. Khare, J. F. Figueiredo, T. Gull, R. C. Burghardt, A. J. Baumler, R. M. Tsolis, H. L. Andrews-Polymenis, L. G. Adams.
Veterinary Pathology, Vol. 47, No. 2, pp. 322–333, 2010.

[03] The negative binomial Lindley distribution as a tool for analyzing crash data characterized by a large amount of zeros. Dominique Lord, Srinivas Reddy Geedipally.
Accident Analysis and Prevention, Vol. 43, pp. 1738–1742, 2011.

[02] Assessing circuit breaker performance using condition-based data and Bayesian approach. Satish Natti, Mladen Kezunovic.
Electric Power Systems Research, Vol. 81, pp. 1796–1804, 2011.

[01] Estimation of two parameter multilevel item response models with predictors — simulations and substantiation for an Urban school district. Prathiba Natesan.
Ph.D. Thesis, Texas A&M University, 2007.