Preferential public transport policies provide an important social welfare support for travel by the elderly. However, the travel problems faced by the elderly, such as traffic congestion during peak hours, have not attracted enough attention from transportation-related departments. This study proposes a passenger flow prediction model for the elderly taking public transport and validates it using bus smart card data. The study incorporates short time series clustering (STSC) to integrate the elements of the heterogeneity of bus trips taken by the elderly, and accurately identifies the needs of elderly passengers by analysing passenger flow spatiotemporal characteristics. According to the needs and characteristics of passenger flow, a short time series clustering Seasonal Autoregressive Integrated Moving Average (STSC-SARIMA) model was constructed to predict passenger flow. The analysis of spatiotemporal travel characteristics identified three peak periods for the elderly to travel every day. The number of people traveling in the morning peak was significantly larger compared to other periods. At the same time, compared with bus lines running through central urban areas, multi-community, and densely populated areas, the passenger flow of bus lines in other areas dropped significantly. The study model was applied to Lhasa, China. The prediction results verify that the model has high prediction accuracy and applicability. In addition to the initial application, this predictive model provides new directions for bus passenger flow forecasting to support better public transport policy-making and improve elderly mobility.

Short-term traffic flow prediction is crucial for intelligent transport systems and mitigating traffic congestion. Therefore, precise prediction of real-time traffic conditions is becoming more important. Currently, the existing prediction models lack the ability to effectively extract spatio-temporal characteristics and fail to adequately account for the impact of non-linear noise. To address these issues, the study proposes a hybrid short-term traffic flow prediction model based on spatio-temporal characteristics. First, the method decomposes the initial spatio-temporal traffic sequence data into multiple modal components using the complementary ensemble empirical modal decomposition method. Then, spatio-temporal characteristics are extracted from the decomposed spatio-temporal components using a deep residual network. The predicted values of each factor are combined to obtain the final predicted values. To validate the model, traffic flow data that is collected at point 4909A on the M25 motorway in London is used. The results indicate that the proposed model outperforms other models in terms of accuracy metrics such as root mean square error, mean absolute percentage error, mean absolute error, mean squared error, and coefficient of determination. Therefore, the model has high accuracy and practicality and exhibits great potential for short-term traffic flow prediction.

The current public transportation systems predominantly rely on rigid schedules and service patterns, leading to suboptimal resource allocation that impacts both passengers and transit operators. This inefficiency results in the wastage of resources and dissatisfaction among users. The unsatisfactory passenger experience significantly contributes to the declining ridership, thereby diminishing revenue for transit operators. To specifically address these challenges encountered by Lhasa's public transportation system, we propose a multi-objective model for bus departure timetables. The model aims to synchronize the costs of passenger waiting time and bus operation costs concurrently, accounting for diverse constraints such as actual travel times, operational bus numbers, bus capacity limits, and arrival time distributions. In this research, we establish a multi-objective optimization model with the primary goal of maximizing passenger satisfaction while concurrently optimizing the revenue of the transit company. Implemented in Lhasa, China, we use the Non-Dominated Sorting Genetic Algorithm-Ⅱ to derive Pareto fronts relevant for analysis. The research findings demonstrate a reduction in the frequency of departures by one bus within a one-hour timeframe. Additionally, a substantial 37% decrease is observed in both the count of buses not arriving at stations and the number of passengers waiting at these stations compared to previous timetables. These results suggest promising potential for significant benefits to both the transit company and passengers within the public transportation system.