Comparative Modelling of Strength Properties of Hydrated-Lime Activated Rice- Husk-Ash (HARHA) Modifed Soft Soil for Pavement Construction Purposes by Artifcial Neural Network (ANN) and Fuzzy Logic (FL) Onyelowe, K. C. a* , Alaneme, G. U. a , Onyia, M. E. b , Bui Van, D. c , Dimonyeka, M. U. d , Nnadi E. a , Ogbonna, C. a , Odum, L. O. d , Aju, D. E. a , Abel, C. e , Udousoro I. M. f & Onukwugha, E. g a Department of Civil Engineering, Michael Okpara University of Agriculture, Umudike, P. M. B. 7267, Umuahia 440109, Abia State, Nigeria b Department of Civil Engineering, Faculty of Engineering, University of Nigeria, Nsukka, Nigeria c Faculty of Civil Engineering, Hanoi University of Mining and Geology, Hanoi, Vietnam d Cross River Institute of Technology and Management, Cross River State, Nigeria e Department of Computer Engineering, Michael Okpara University of Agriculture, Umudike, P. M. B. 7267, Umuahia 440109, Abia State, Nigeria. f Department of Science Education, Michael Okpara University of Agriculture, Umudike, P. M. B. 7267, Umuahia 440109, Abia State, Nigeria. g Department of Civil Engineering, Faculty of Engineering, Federal Polytechnic Nekede, Owerri, Nigeria *Corresponding author: konyelowe@mouau.edu.ng Received 02 September 2020, Received in revised form 01 October 2020 Accepted 17 October 2020, Available online 28 February 2021 ABSTRACT Artifcial neural network and fuzzy logic based model soft-computing techniques were adapted in the research study for the evaluation of the expansive clay soil-HARHA mixture’s consistency limit, compressibility and mechanical strength properties. The problematic clay soil was stabilized with varying proportions of HARHA (stabilizing agent) which is an agricultural waste derivative from the milling of rice ranging from 0% to 12%; the utilization of the alkaline activated wastes encourages its recycling and re-use to obtain sustainable, eco-efcient and eco-friendly engineered infrastructure for use in the construction industry with economic benefts also. The obtained laboratory and experimental responses were taken as the system database for the ANN and fuzzy logic model development; the soil-HARHA proportions with their corresponding compaction and consistency limit characteristics were feed to the network as the model input variables while the mechanical strength (California-bearing-ratio (CBR), unconfned-compressive-strength (UCS) and Resistance value (R-values)) responses of the blended soil mixture were the model target variables. For the ANN model, feed forward back propagation and Levernberg Marquardt training algorithm were utilized for the model development with the optimized network architecture of 8-6-3 derived based on MSE performance criteria; while for the fuzzy logic model, the mamdani FIS with both triangular and trapezoidal membership function with both models formulated, simulated and computed using MATLAB toolbox. The models were compared in terms of accuracy of prediction using MAE, RMSE and coefcient of determination and from the computed results, 0.2750, 0.4154 and 0.9983 respectively for ANN model while 0.3737, 0.6654 and 0.9894 respectively was obtained for fuzzy logic model. The two models displayed robust characteristics and performed satisfactorily enabling the optimization of the solid waste derivatives utilization for soil mechanical properties improvement for engineering purposes. Keywords: California bearing ratio (CBR); Unconfned compressive strength (UCS); Resistance value (R-V); Activated rice-husk-ash; Soil stabilization; Fuzzy logic (FL); Artifcial neural networks (ANN); hydrated-lime; soil strength properties Jurnal Kejuruteraan 33(2) 2021: 365-384 https://doi.org/10.17576/jkukm-2021-33(2)-20 INTRODUCTION A conventional way of soil stabilization for fexible pavements with expansive soil involves the provision of stifer load bearing characteristic material base over the soft expansive subgrade. From in situ CBR and shear strength assessment, the required base materials thickness is determined; for soft expansive soil subgrade the required thickness of the base materials often goes so high (Miao and Liu 2001). In such case, chemical stabilization method is utilized which result in substantial base thickness reduction using mixture combination and optimization techniques that will result in performance improvement of the subgrade in terms of strength properties of the stabilized soil (Louaf et al. 2015). Several mineral additives/admixtures utilized to achieve this chemical soil modifcation mostly are materials possessing alumina-silicate content which have pozzolanic behaviour and tend to improve its binding ability to obtain