Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
The nature of statistical learning theory
The nature of statistical learning theory
Optimal composition of real-time systems
Artificial Intelligence
Using support vector machines for time series prediction
Advances in kernel methods
Monitoring and control of anytime algorithms: a dynamic programming approach
Artificial Intelligence - special issue on computational tradeoffs under bounded resources
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Predicting Time Series with Support Vector Machines
ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Support Vector Machine Regression for Volatile Stock Market Prediction
IDEAL '02 Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning
Optimizing the distribution of shopping centers with parallel genetic algorithm
Engineering Applications of Artificial Intelligence
Travel-time prediction with support vector regression
IEEE Transactions on Intelligent Transportation Systems
An overview of statistical learning theory
IEEE Transactions on Neural Networks
Support vector machine with adaptive parameters in financial time series forecasting
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Holding strategies are among the most commonly used operation control strategies in transit systems. In this paper, a dynamic holding strategy is developed, which consists of two major steps: (1) judging whether an early bus should be held, and (2) optimizing the holding times of the held bus. A model based on support vector machine (SVM), which contains four input variables (time-of-day, segment, the latest speed on the next segment, and the bus speed on the current segment) for forecasting the early bus departure times from the next stop is also developed. Then, in order to determine the optimal holding times, a model aiming to minimize the user costs is constructed and a genetic algorithm is used to optimize the holding times. Finally, the dynamic holding strategy proposed in this study is illustrated with the microscopic simulation model Paramics and some conclusions are drawn.