Birla Institute of Technology, Mesra
Faculty Image

Lakshman Mahto

Joined Institute on : 13-Dec-2024

  • CQEDS
  • PhD
Contact Address

R.N.: 241/09, Centre for Quantitative Economics and Data Science, Birla Institute of Technology Mesra, Ranchi Ranchi-835215, Jharkhand, India

13B At-Paikatand, Post-Kulgo PS-Dumri, District-Giridih 825106, Jharkhand, India

  • Phone Office - 6200824744
  • Phone Residence - 6200824744
  • Email - lakshman@bitmesra.ac.in
Work Experience

Teaching : 9 Years

Research : 2 Years

Individual: 11 Years


Teaching : 9 Years

Research : 2 Years

Individual: 11 Years
Professional Background

ACADEMIC POSITION:

December 2024 – Present: Assistant Professor, Quantitative Economics and Data Science, Birla Institute of Technology Mesra, Ranchi, India.

December 2021 – December 2024: Assistant Professor (Mathematics), Humanities & Science, Indian Institute of Information Technology Dharwad, India.

July 2019 – December 2021: Assistant Professor (Grade-II, Level-11) (Mathematics), Humanities & Science, Indian Institute of Information Technology Dharwad, India.

August 2017 – July 2019: Assistant Professor (Grade-II, Level-10) (Mathematics), Humanities & Science, Indian Institute of Information Technology Dharwad, India. 

August 2016 – August 2017:  Assistant Professor (Contractual) (Mathematics), Humanities & Science, Indian Institute of Information Technology Dharwad, India.  

February 2015 – August 2016:  Postdoctoral Fellow (Mathematics), The Institute of Mathematical Sciences Chennai, India. Adviser: Dr. S. Kesavan.

September 2014–January 2015: Project Assistant (A DST sponsored project on differential equations), School of Basic Science, Indian Institute of Technology Mandi India.  Adviser: Dr. Syed Abbas. 

February 2010– September 2010: Senior Research Fellow (A DST project on statistical techniques), Applied Mathematics, Birla Institute of Technology Mesra, India. Adviser: Dr. Manish Trivedi.
Research Areas

My research centers on advancing learning-driven autonomy in decision systems that must perform reliably amid dynamic and uncertain environments. I develop end-to-end architectures that integrate perception, prediction, and planning, grounded in dynamical systems theory, statistical learning, and optimization. My group builds multimodal generative predictors (e.g., conditional variational autoencoders), risk-aware planners (differentiable model predictive control with certified safety and stability guarantees), and scalable solvers (convexification techniques and distributionally robust optimization). These tools enable applications in intelligent mobility-including autonomous and assisted driving, traffic flow management, and logistics optimization as well as socio-economic dynamics, such as migration and stress forecasting, crime risk modeling, and equitable resource allocation. Our emphasis is on safety, robustness, and interpretability, achieved through formal guarantees and reproducible, open-source pipelines, with a clear trajectory toward real-world deployment in collaboration with institutional partners.
Award and Honours
  1. CSIR-NET
  2. GATE
  3. IMSc Institute Postdoctoral Fellowship.

 
Publications

A. Conference proceedings:
1. L. Mahto, Learning algorithms for non-linear dynamical systems, control and autonomy, Conference on Applied AI and Scientific Machine Learning (CASML 2024), Indian Institute of Science, Bangalore, India, 2024.
2. Mahto, L., Computational and statistical complexities of learning algorithm for nonlinear dynamical systems, Indo-German conference on computational mathematics (IGCM-2023) held at Indian Institute of Science, Bangalore, India, 2023.
3. Chauhan, A., Jagadish, D.N. and Mahto, L., Multimodality Data Fusion for COVID-19 Diagnosis. In 2021 IEEE International Conference on Big Data (Big Data) (pp. 4659-4666),15 Dec, 2021, doi:10.1109/BigData52589.2021.9671302, ISBN: 978-1-6654-3902-2.
4. Jagadish D.N., Chauhan A., Mahto L, Autonomous Vehicle Path Prediction Using Conditional Variational Autoencoder Networks. In: Karlapalem K. et al. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science, vol 12712, 129–139. Springer, Cham. https://doi.org/10.1007/978-3-030-75762-5_11 ,ISSN: 978-3-030-75762-5. (H-index: 182).
5. A. Chauhan, S. Kumar, L. Mahto and J. D. N, "Detection of Reckless Driving using Deep Learning," 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA, 2020, pp. 853-858, doi: 10.1109/ICMLA51294.2020.00139, ISSN: 978-1-7281-8470-8. (H-index: 18).
6. J. D. N, L. Mahto and A. Chauhan, "Density Based Clustering Methods for Road Traffic Estimation," 2020 IEEE REGION 10 CONFERENCE (TENCON), Osaka, Japan, 2020, pp. 885-890, doi: 10.1109/TENCON50793.2020.9293790, ISSN: 978-1-7281-8455-5. (H-index: 38).
7. Jagadish, D. N., Mahto, L., Chauhan A. (2021) Deep Learning and Density Based Clustering Methods for Road Traffic Prediction. In: Singh S.K., Roy P., Raman B., Nagabhushan P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1378, 332–343, Springer, Singapore. https://doi.org/10.1007/978-981-16-1103-2_29, ISSN: 978-981-16-1103-2. 
8. Mahto, L., Abbas, S., Existence, and uniqueness of a solution of Caputo fractional differential equations, AIP Conf. Proc. 1479, 896-899 (2012). https://doi.org/10.1063/1.4756286 , ISSN: 78-0-7354-1091-6. (H-index: 75)
9. Abbas, S., Mahto, L., Existence of almost periodic solution of a model of phytoplankton allelopathy with delay, AIP Conf. Proc. 1479, 900-905 (2012). https://doi.org/10.1063/1.4756287, ISSN: 78-0-7354-1091-6. (H-index: 75)

B. Workshop proceedings:
1. Mahto, L., Chauhan, A., An approximate gradient-based hyper-parameter optimization in a neural network architecture, NeurIPS 12th workshop on Optimization in Machine Learning (OPT2020), 2020. https://opt-ml.org/papers/2020/paper_62.pdf 
2. D N., Jagadish, Chauhan, A., Mahto, L., Deep Learning Techniques for Autonomous Vehicle Path Prediction, AAAI workshop on the AI for Urban Mobility Workshop (AI4UM 2021). https://aaai.org/Conferences/AAAI-21/ws21workshops/

C. Journal:
1. Jagadish, D.N., Chauhan, A. & Mahto, L. Conditional Variational Autoencoder Networks for Autonomous Vehicle Path Prediction. Neural Process Lett 54, 3965–3978 (2022). https://doi.org/10.1007/s11063-022-10802-z ISSN: 370-4621.
2. Mahto, L.; Abbas, S., Hafayed, M., Srivastava, H.M., Approximate Controllability of Sub Diffusion Equation with Impulsive Condition. Mathematics, MDPI 2019, 7, 190. https://doi.org/10.3390/math7020190, ISSN: 2227-7390. (SCI indexed, IF=2.7, Q2).
3. Abbas, S., Mahto, L., Favini, A., Hafayed, M., Dynamical analysis of a fractional model of phytoplankton allelopathy, Differential Equations and Dynamical Systems, Springer, 24 (3), pp 267–280, July 2016. http://link.springer.com/article/10.1007/s12591014-0219-5, ISSN: 971-3514.  (Scopus indexed, Q3).
4. Mahto, L., Abbas, S., PC-almost automorphic solution of impulsive fractional functional differential equations, Mediterranean Journal of Mathematics, Springer, 12 (3), pp 771–790, July 2015.  http://link.springer.com/article/10.1007/s00009-014-0449-3, ISSN: 1660-5446. (SCI indexed, IF=1.4, Q2).
5. Abbas, S., Mahto, L., Hafayed, M., Alemi, F.M., Asymptotic almost automorphic solution of impulsive neural network with almost automorphic coefficients, Neurocomputing, Elsevier, 142 (22), October, 326-334, 2014). https://doi.org/10.1016/j.neucom.2014.04.028, ISSN: 0925-2312. (SCI indexed, IF=5.5, Q1)
6. Mahto, L., Abbas, S., Approximate controllability and optimal control of impulsive fractional functional differential equations, J. Abstr. Differ. Equ. Appl., 4 (2), 44–59, 2013.  Doi: http://mathres-pub.org/jadea/4/2/approximate-controllability-and-optimalcontrol-impulsive-fractionalfunctional, ISSN: 2158-611X. (Mathscinet indexed, MCQ=0.3).
7. Mahto, L., Abbas, S., Favini, A., Analysis of Caputo impulsive fractional-order differential equations with applications, Int. J. Differ. Equ., 2013, Art. ID 704547, 11 pp, 2012. http://dx.doi.org/10.1155/2013/704547  , ISSN: 1687-9643 (Scopus indexed, Q3)

D. Book chapters:
1. Abbas S., Mahto L. (2019) Piecewise Continuous Stepanov-Like Almost Automorphic Functions with Applications to Impulsive Systems. In: Dutta H., Ko?inac L., Srivastava H. (eds) Current Trends in Mathematical Analysis and Its Interdisciplinary Applications. Birkhäuser, Cham. https://doi.org/10.1007/978-3-030-15242-0_4. ISBN: 978-3-030-15241-3  

E. Books:
1. Mahto, Lakshman. "Introduction to probability and statistics: a computational framework of randomness." arXiv preprint arXiv:2401.08622 (2023).
Current Sponsored Projects

Deep Learning Model for Autonomous Navigation on Indian Roads funded by SERB-DST under core research grants as a Co-PI, Status-Ongoing at IIIT Dharwad 2023-2026, Amount: 1761905.