Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data

Chondrodima, Eva; Georgiou, Harris V.; Pelekis, Nikos; Theodoridis, Yannis

doi:10.1016/j.jjimei.2022.100086

Cited by 13 publications

(2 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of the nonsymmetric version of the algorithm, which is based on the same basic principles with standard FM, there are N diferent operational parameters to be determined, as it is allowed diferent number of fuzzy sets in each dimension. In this case, an optimization procedure is necessary in order to produce an RBF network with optimal confguration within a logical computation time, most common of which include metaheuristic search methods belonging to evolutionary computation [36] and swarm intelligence [25,37].…”

Section: Fuzzy Means Algorithm For Rbf Network Trainingmentioning

confidence: 99%

Chess Position Evaluation Using Radial Basis Function Neural Networks

2023

View full text Add to dashboard Cite

The game of chess is the most widely examined game in the field of artificial intelligence and machine learning. In this work, we propose a new method for obtaining the evaluation of a chess position without using tree search and examining each candidate move separately, like a chess engine does. Instead of exploring the search tree in order to look several moves ahead, we propose to use the much faster and less computationally demanding estimations of a properly trained neural network. Such an approach offers the benefit of having an estimation for the position evaluation in a matter of milliseconds, while the time needed by a chess engine may be several orders of magnitude longer. The proposed approach introduces models based on the radial basis function (RBF) neural network architecture trained with the fuzzy means algorithm, in conjunction with a novel set of input features; different methods of network training are also examined and compared, involving the multilayer perceptron (MLP) and convolutional neural network (CNN) architectures and a different set of input features. All methods were based upon a new dataset, which was developed in the context of this work, derived by a collection of over 1500 top-level chess games. A Java application was developed for processing the games and extracting certain features from the arising positions in order to construct the dataset, which contained data from over 80,000 positions. Various networks were trained and tested as we considered different variations of each method regarding input variable configurations and dataset filtering. Ultimately, the results indicated that the proposed approach was the best in performance. The models produced with the proposed approach are suitable for integration in model-based decision-making frameworks, e.g., model predictive control (MPC) schemes, which could form the basis for a fully-fledged chess-playing software.

show abstract

Section: Fuzzy Means Algorithm For Rbf Network Trainingmentioning

confidence: 99%

Chess Position Evaluation Using Radial Basis Function Neural Networks

2023

View full text Add to dashboard Cite

show abstract

“…PSO-NSFM and CR-GTFS together established a comprehensive framework for precisely forecasting PT-ETA using real-world data sources. The suggested technique was validated through experiments using GTFS data, outperforming cutting-edge prediction accuracy and computation speed [9].…”

Section: Related Workmentioning

confidence: 99%

Artificial RBF Neural Network for Big Data Analysis and New Cases Prediction

Alrufaye¹

2022

wjps

View full text Add to dashboard Cite

AI-based treatments have shown promise in a variety of fields, particularly those directly connected to human health. Some AI processors are used to categorize and distinguish groupings and patterns, while others are used to forecast future values based on data from previous study and the environment in which that data was employed. An artificial neural network that employs radial basis functions as activation functions is known as a radial basis function network. The radial basis functions input and the neural parameters are combined linearly to produce the network output. There are several applications for radial-based functional networks, such as function approximation, classification, time series prediction, and system control. In this paper, the RBF network will be used in two phases: the data training phase, where the data is trained with the inputs and outputs to obtain new values for the outputs and compare them with the original outputs, and the testing phase, where only the inputs are entered without the outputs and the outputs are evaluated using the RMSE calculation, where it reached a performance of RMSE of 0.018. In the training phase of utilizing the system, the mistake rate was 0.04 and the success rate was 96%; in the testing phase, the error rate was 0.05 and the success rate was 95%.

show abstract