The rapid growth of Internet of Things (IoT) technologies has transformed modern urban environments into complex smart cities, generating vast amounts of high-dimensional, heterogeneous data. Effectively analyzing this data is crucial for optimizing urban infrastructure, enhancing quality of life, and supporting sustainable development. However, smart city data presents significant challenges, including non-linear dependencies, noisy signals, and high dimensionality. To address these challenges, this study proposes the Dynamic Leader Sibha Algorithm (DLSA), a novel metaheuristic optimization technique inspired by the structured counting dynamics of the Sibha. The DLSA was applied to the Smart Cities Index dataset, leveraging copula functions to model complex, multivariate dependencies and enhance predictive accuracy. The baseline machine learning (ML) evaluation revealed that the ExtraTreesRegressor achieved the lowest mean squared error (MSE) of 0.007462409, highlighting its superior initial performance. Following feature selection using the binary Dynamic Leader Sibha Algorithm (bSiba), the average error was reduced to 0.373245769, significantly improving data quality and model efficiency. Subsequent ML evaluation after feature selection further reduced the MSE of the ExtraTreesRegressor to 0.00151927, reflecting the effectiveness of dimensionality reduction. Finally, hyperparameter optimization using the DLSA achieved a remarkable MSE of $1.32249\times {10}^{-6}$ with the Siba + ExtraTreesRegressor combination, demonstrating the algorithm’s powerful optimization capabilities. These findings indicate that the DLSA framework can significantly enhance the predictive performance of IoT-driven smart city models, offering valuable insights for urban planners, policymakers, and technology developers seeking to build smarter, more resilient cities.

Accurate prediction of concrete compressive strength is fundamental for optimizing mix designs, improving material utilization, and ensuring structural safety in modern construction. Traditional empirical methods often fail to capture the non-linear relationships among concrete constituents, especially with the growing use of supplementary cementitious materials and recycled aggregates. This study presents an integrated machine learning framework for concrete strength prediction, combining advanced regression models—namely CatBoost—with metaheuristic optimization algorithms, with a particular focus on the Somersaulting Spider Optimizer (SSO). A comprehensive dataset encompassing diverse mix proportions and material types was used to evaluate baseline machine learning models, including CatBoost, XGBoost, ExtraTrees, and RandomForest. Among these, CatBoost demonstrated superior accuracy across multiple performance metrics. To further enhance predictive capability, several bio-inspired optimizers were employed for hyperparameter tuning. The SSO-CatBoost hybrid achieved the lowest mean squared error and highest correlation coefficients, outperforming other metaheuristic approaches such as Genetic Algorithm, Particle Swarm Optimization, and Grey Wolf Optimizer. Statistical significance was established through Analysis of Variance and Wilcoxon signed-rank testing, confirming the robustness of the optimized models. The proposed methodology not only delivers improved predictive performance but also offers a transparent framework for mix design optimization, supporting data-driven decision making in sustainable and resilient infrastructure development.