Fig. 07 — Research & Publications
Data-driven models for materials that matter
A selection of peer-reviewed work spanning high-performance concrete, geotechnical reinforcement and the machine learning methods used to model them. Full record on Google Scholar →
Concrete & Composite Materials
UHPC, GGBS & silica-fume systems, fibre reinforcement and FRP-confined columns — strength, permeability and durability prediction.
Geotechnical Reinforcement
Geogrid-reinforced subgrade soils and ground improvement, modelled with soft-computing regression techniques.
Sustainable Pavements
Recycled-waste modified asphalt mixtures (e.g. fibre-modified stone mastic asphalt) evaluated for durable, lower-impact road materials.
Fig. 08 — Selected Publications
Peer-reviewed journal articles
Prediction of rapid chloride permeability of ground granulated blast furnace slag and silica-fume based ultra-high performance concrete using hybrid gradient boosting algorithms
Structural Concrete, 27(1), 1085–1111R. Kumar, S. Prakash, S. Sirimontree, W. Wipulanusat, C. Thongchom.
Machine learning and nonlinear finite element analysis of fibre-reinforced polymer-confined concrete–steel double-skin tubular columns under axial compression
Structural Concrete, 26, 248H. F. Isleem, T. Qiong, N. D. K. R. Chukka, R. Kumar, T. V. Nagaraju, A. Y. Hamed.
Investigating the impact of biaxial geogrid reinforcement on subgrade soil strength enhancement: a machine learning analysis using the MARS model
Indian Geotechnical Journal, 56(3), 1194–1213M. Harshitha, R. Kumar, J. C. Vidyashree, U. Agrawal, S. Sathvik.
Estimation of the compressive strength of ultra-high performance concrete using machine learning models
Intelligent Systems with ApplicationsR. Kumar, D. R. Kumar, W. Wipulanusat, C. Thongchom, P. Samui, B. Rai.
Eco-friendly asphalt design: machine learning analysis of stone mastic asphalt containing shredded cigarette-butt fibres
With H. A. Varalakshmi et al.Evaluates recycled cigarette-butt fibres as a sustainable additive in stone mastic asphalt, addressing durable pavement design and waste management together.
A comparative study of AdaBoost and K-Nearest Neighbor regressors for the prediction of compressive strength of ultra-high performance concrete
Civil Engineering / MaterialsBenchmarks ensemble and instance-based regressors for UHPC strength prediction.
Deep learning-based artificial neural network model for the axial shortening strength of concrete-filled steel tubular (CFST) columns
Structural Engineering / Machine LearningANN-based prediction of axial behaviour in composite steel-concrete columns.
Fig. 09 — Applied & Student Research
Mentoring project teams
Structural model review
Supervising undergraduate design-and-build projects, from concept through to a working scaled structural model.
Project Open Day — Best Project of Social Relevance
Mentored student teams recognised at the Department of Civil Engineering's Project Open Day.