A combination of genetic algorithm and particle swarm optimization (PSO) for vehicle routing problems with time windows (VRPTW) is proposed in this paper. The improvements of the proposed algorithm include: using the particle real number encoding method to decode the route to alleviate the computation burden, applying a linear decreasing function based on the number of the iterations to provide balance between global and local exploration abilities, and integrating with the crossover operator of genetic algorithm to avoid the premature convergence and the local minimum. The experimental results show that the proposed algorithm is not only more efficient and competitive with other published results but can also obtain more optimal solutions for solving the VRPTW issue. One new well-known solution for this benchmark problem is also outlined in the following.

Landmark visual salience (characterized by features that contrast with their surroundings and visual peculiarities) and semantic salience (characterized by features with unusual or important meaning and content in the environment) are two important factors that affect an individual’s visual attention during wayfinding. However, empirical evidence regarding which factor dominates visual guidance during indoor wayfinding is rare, especially in real-world environments. In this study, we assumed that semantic salience dominates the guidance of visual attention, which means that semantic salience will correlate with participants’ fixations more significantly than visual salience. Notably, in previous studies, semantic salience was shown to guide visual attention in static images or familiar scenes in a laboratory environment. To validate this assumption, first, we collected the eye movement data of 22 participants as they found their way through a building. We then computed the landmark visual and semantic salience using computer vision models and questionnaires, respectively. Finally, we conducted correlation tests to verify our assumption. The results failed to validate our assumption and show that the role of salience in visual guidance in a real-world wayfinding process is different from the role of salience in perceiving static images or scenes in a laboratory. Visual salience dominates visual attention during indoor wayfinding, but the roles of salience in visual guidance are mixed across different landmark classes and tasks. The results provide new evidence for understanding how pedestrians visually interpret landmark information during real-world indoor wayfinding.

To capture both global stationarity and spatiotemporal non-stationarity, a novel mixed geographically and temporally weighted regression (MGTWR) model accounting for global and local effects in both space and time is presented. Since the constant and spatial-temporal varying coefficients could not be estimated in one step, a two-stage least squares estimation is introduced to calibrate the model. Both simulations and real-world datasets are used to test and verify the performance of the proposed MGTWR model. Additionally, an Akaike Information Criterion (AIC) is adopted as a key model fitting diagnostic. The experiments demonstrate that the MGTWR model yields more accurate results than do traditional spatially weighted regression models. For instance, the MGTWR model decreased AIC value by 2.7066, 36.368 and 112.812 with respect to those of the mixed geographically weighted regression (MGWR) model and by 45.5628, −38.774 and 35.656 with respect to those of the geographical and temporal weighted regression (GTWR) model for the three simulation datasets. Moreover, compared to the MGWR and GTWR models, the MGTWR model obtained the lowest AIC value and mean square error (MSE) and the highest coefficient of determination (R²) and adjusted coefficient of determination (R²_adj). In addition, our experiments proved the existence of both global stationarity and spatiotemporal non-stationarity, as well as the practical ability of the proposed method.

Previous studies have demonstrated that non-Euclidean distance metrics can improve model fit in the geographically weighted regression (GWR) model. However, the GWR model often considers spatial nonstationarity and does not address variations in local temporal issues. Therefore, this paper explores a geographically temporal weighted regression (GTWR) approach that accounts for both spatial and temporal nonstationarity simultaneously to estimate house prices based on travel time distance metrics. Using house price data collected between 1980 and 2016, the house price response and explanatory variables are then modeled using both the GWR and the GTWR approaches. Comparing the GWR model with Euclidean and travel distance metrics, the GTWR model with travel distance obtains the highest value for the coefficient of determination ( $R^2$ ) and the lowest values for the Akaike information criterion (AIC). The results show that the GTWR model provides a relatively high goodness of fit and sufficient space-time explanatory power with non-Euclidean distance metrics. The results of this study can be used to formulate more effective policies for real estate management.

Geological disaster risk assessment can quantitatively assess the risk of disasters to hazard-bearing bodies. Visualizing the risk of geological disasters can provide scientific references for regional engineering construction, urban planning, and disaster prevention and mitigation. There are some problems in the current binary classification landslide risk assessment model, such as a single sample type, slow multiclass classification speed, large differences in the number of positive and negative samples, and large errors in classification results. This paper introduces multilevel landslide hazard scale samples, selects multiple types of samples according to the divided multilevel landslide hazard scale grade, and proposes a landslide hazard assessment model based on a multiclass support vector machine (SVM). Due to the objective limitations of the single weighting method, the combined weights are used to determine the vulnerability of the landslide hazard-bearing body, and the analytic hierarchy process (AHP) and entropy method are combined to construct a landslide vulnerability assessment model that considers subjective and objective weights. This paper takes landslide disasters in Xianyang City, Shaanxi Province, as the research object. Based on the landslide hazard assessment model and the landslide vulnerability assessment model, a landslide risk assessment experiment is carried out. It generates the landslide risk assessment zoning map and summarizes the risk characteristics of landslides in various towns. The experimental results verify the feasibility and effectiveness of the proposed model and provide important decision support for decision makers in Xianyang City.

The internal structure of buildings is becoming increasingly complex. Providing a scientific and reasonable evacuation route for trapped persons in a complex indoor environment is important for reducing casualties and property losses. In emergency and disaster relief environments, indoor path planning has great uncertainty and higher safety requirements. Q-learning is a value-based reinforcement learning algorithm that can complete path planning tasks through autonomous learning without establishing mathematical models and environmental maps. Therefore, we propose an indoor emergency path planning method based on the Q-learning optimization algorithm. First, a grid environment model is established. The discount rate of the exploration factor is used to optimize the Q-learning algorithm, and the exploration factor in the ε-greedy strategy is dynamically adjusted before selecting random actions to accelerate the convergence of the Q-learning algorithm in a large-scale grid environment. An indoor emergency path planning experiment based on the Q-learning optimization algorithm was carried out using simulated data and real indoor environment data. The proposed Q-learning optimization algorithm basically converges after 500 iterative learning rounds, which is nearly 2000 rounds higher than the convergence rate of the Q-learning algorithm. The SASRA algorithm has no obvious convergence trend in 5000 iterations of learning. The results show that the proposed Q-learning optimization algorithm is superior to the SARSA algorithm and the classic Q-learning algorithm in terms of solving time and convergence speed when planning the shortest path in a grid environment. The convergence speed of the proposed Q- learning optimization algorithm is approximately five times faster than that of the classic Q- learning algorithm. The proposed Q-learning optimization algorithm in the grid environment can successfully plan the shortest path to avoid obstacle areas in a short time.