Rural settlements play a crucial role in shaping the macro-level dynamics of rural development. To explore these changes within the framework of rural revitalization, this study incorporates a key factor—economics—and develops a cellular automata (CA) model to simulate rural settlement dynamics. This model is based on a novel swarm intelligence algorithm, the ant lion optimizer (ALO). Four experimental groups were designed by combining various economic and other influencing factors. The simulation results indicated that, compared to the total agricultural and industrial output value, the per capita net income of farmers has a more significant impact on the distribution of rural settlements. Integrating relevant economic factors notably enhances the simulation accuracy of the model, with the experimental group incorporating per capita net income achieving the best performance. This group demonstrated an overall accuracy of 96.31%, a rural settlement accuracy of 71.99%, and a Kappa coefficient of 0.7003, along with a Moran’s I value of 0.661. Furthermore, the ALO-CA model exhibited superior training and simulation accuracy when compared to models based on other swarm intelligence algorithms. Specifically, compared to the PSO-CA model, the ALO-CA model achieved improvements of 3.40%, 2.77%, and 4.81% in terms of Kappa coefficient, overall accuracy, and rural settlement accuracy, respectively. Based on the optimal experimental group, this study successfully predicted the spatial distribution of rural settlements in Jintan District for the year 2027. The prediction results indicate a trend toward intensification in the evolution of rural settlements.

With continual population growth in the densely populated cities, e.g., Singapore, traffic congestion is the main transportation problem. As such, Public Transport is deemed as the most sustainable mode of transport. However, pubic transport is often plagued with the First and Last Mile Problem (FLMP), reducing its appeal especially in the densely populated city areas. The FLMP leads to a wide range of complications, in particular, human congestion in public transport. In this research, after a comprehensive discussion of FLMP problem in densely populated city areas, a case study in Singapore, i.e., the Kent Ridge Campus of National University of Singapore (KRC-NUS), has been conducted based on the survey and spatio-temporal analyses. In addition to the investigation of FLMP status in the case study area, a new campus shuttle bus route from an alternative MRT station (Haw Par Villa Station) has also been proposed based on the Tabu Search to alleviate the human congestion and current FLMP status for KRC-NUS. This research not only has successfully addressed the FLMP in the case study area, but also can be a good reference for other areas in densely populated cities to help mitigate FLMPs.