Urban Traffic Flow Prediction Model with CPSO/SSVM Algorithm under the Edge Computing Framework

Urban traffic flow prediction has always been an important realm for smart city build-up. With the development of edge computing technology in recent years, the network edge nodes of smart cities are able to collect and process various types of urban traffic data in real time, which leads to the possibility of deploying intelligent traffic prediction technology with real-time analysis and timely feedback on the edge. In view of the strong nonlinear characteristics of urban traffic flow, multiple dynamic and static influencing factors involved, and increasing difficulty of short-term traffic flow prediction in a metropolitan area, this paper proposes an urban traffic flow prediction model based on chaotic particle swarm optimization algorithm-smooth support vector machine (CPSO/SSVM). The prediction model has built a new second-order smooth function to achieve better approximation and regression effects and has further improved the computational efficiency of the smooth support vector machine algorithm through chaotic particle swarm optimization. Simulation experiment results show that this model can accurately predict urban traffic flow.

Smooth Support Vector Machine for Suicide-Related Behaviours Prediction

Suicide-related behaviours need to be prevented on psychiatric patients. Prediction of those behaviours based on patient medical records would be very useful for the prevention by the psychiatric hospital. This research focused on developing this prediction at the only one psychiatric hospital of Bali Province by using Smooth Support Vector Machine method, as the further development of Support Vector Machine. The method used 30.660 patient medical records from the last five years. Data cleaning gave 2665 relevant data for this research, includes 111 patients that have suicide-related behaviours and under active treatment. Those cleaned data then were transformed into ten predictor variables and a response variable. Splitting training and testing data on those transformed data were done for building and accuracy evaluation of the method model. Based on the experiment, the best average accuracy at 63% can be obtained by using 30% of relevant data as data testing and by using training data which has one-to-one ratio in number between patients that have suicide-related behaviours and patients that have no such behaviours. In the future work, accuracy improvement need to be confirmed by using Reduced Support Vector Machine method, as the further development of Smooth Support Vector Machine.