---

The slope stability analysis is routinely performed by engineers to estimate the stability of river training works, road embankments, embankment dams, excavations and retaining walls. This paper presents a new approach to build a model for the prediction of slope stability state. The support vector machine (SVM) is a new machine learning method based on statistical learning theory, which can solve the classification problem with small sampling, non-linearity and high dimension. However, the practicability of the SVM is influenced by the difficulty of selecting appropriate SVM parameters. In this study, the proposed hybrid harmony search (HS) with SVM was applied for the prediction of slope stability state, in which HS was used to determine the optimized free parameters of the SVM. A dataset that includes 55 data points was applied in current study, while 45 data points (80%) were used for constructing the model and the remainder data points (10 data points) were used for assessment of degree of accuracy and robustness. The results obtained indicate that the SVM-HS model can be used successfully for the prediction of slope stability state for circular failure.

---

This study presents a novel approach for optimizing critical failure surfaces (CFS) in homogeneous soil slopes by incorporating seepage and seismic effects through the Self-Adaptive Enhanced Vibrating Particle System (SA_EVPS) algorithm. The Finite Element Method (FEM) is employed to model fluid flow through porous media, while Bishop's simplified method calculates the Factor of Safety (FOS). Two benchmark problems validate the proposed approach, with results compared against traditional and meta-heuristic methods. The SA_EVPS algorithm demonstrates superior convergence and accuracy due to its self-adaptive parameter optimization mechanism. Visualizations from Abaqus simulations and comprehensive statistical analyses highlight the algorithm's effectiveness in geotechnical engineering applications. The results show that SA_EVPS consistently achieves lower FOS values with smaller standard deviations compared to existing methods, indicating more accurate identification of critical failure surfaces.