This article deals with the study of predicting the confinement effect of carbon fiber reinforced polymers (CFRPs) on concrete cylinder strength using metaheuristics-based artificial neural networks. A detailed database of 708 CFRP confined concrete cylinders is developed from previously published research with information on eight parameters, including geometrical parameters like the diameter (d) and height (h) of a cylinder, unconfined compressive strength of concrete (f_co^'), thickness (nt), the elastic modulus of CFRP (Ef), unconfined concrete strain (?_co), confined concrete strain (?_cc) and the ultimate compressive strength of confined concrete (f_cc^'). Three metaheuristic models are implemented, including particle swarm optimization (PSO), grey wolf optimizer (GWO), and bat algorithm (BA). These algorithms are trained on the data using an objective function of mean square error, and their predicted results are validated against experimental studies and finite element analysis. The study shows that the hybrid PSO model predicted the strength of CFRP-confined concrete cylinders with a maximum accuracy of 99.13% and GWO predicted the results with an accuracy of 98.17%. The high accuracy of axial compressive strength predictions demonstrated that these prediction models are a reliable solution to the empirical methods. The prediction models are especially suitable for avoiding full-scale, time-consuming experimental tests that make the process quick and economical.

This paper focuses on the seismic vulnerabilities of multi-storey buildings in hilly regions like Sikkim and Uttarakhand, where rapid construction is driven by population growth and tourism. The study particularly evaluates step-back buildings on hilly slopes, comparing their vulnerability to standard buildings on flat terrain. Using non-linear analysis to assess structural aspects like displacement and storey drift ratio, the research examines the performance of these buildings in both uphill and downhill orientations against typical three-storey and six-storey structures, respectively. The findings indicate that step-back buildings, especially those without infill walls, are more susceptible to seismic damage. For instance, on the uphill side, a step-back building shows a mean drift ratio 15.11% greater in the X direction and 4.57% greater in the Y direction compared to a three-storey regular building (3SR). This vulnerability is exacerbated when infill walls are absent, with mean drift ratios in step-back buildings being 74.75% and 33% higher in the X and Y directions, respectively. Moreover, at a seismic acceleration of 0.36 g, the mean displacement of a step-back building is 83% greater in the X direction and 51% greater in the Y direction than those with infill walls (SBIN), underscoring the significant role of infill walls in enhancing earthquake resilience. The study also highlights that short columns in step-back buildings are particularly prone to severe damage, especially just above the uppermost foundation level. While infill walls offer substantial mitigation of damage at the Design Basis Earthquake (DBE) level, at the Maximum Considered Earthquake (MCE) level, step-back buildings still endure severe damage compared to regular buildings with infill walls. Consequently, the research establishes that step-back buildings demonstrate greater vulnerability at DBE levels without infill walls and are more susceptible to damage than flat terrain buildings at MCE levels, emphasizing the need for careful design and reinforcement strategies in earthquake-prone hilly areas.