Experimental studies are an integral part of modern science, but nature of experiments vary in different scientific areas. Methodological studies (like project 1.1.1.2/VIAA/1/16/112 «Spatiotemporal urban traffic modelling using big data», executor: Dr.sc.ing. Dmitry Pavlyuk) are devoted to enhancing existing models and development of new ones, and experiments in this area are almost purely computational. Our experiments are fully executed in cloud computing – hundreds of processing units handle gigabytes of data during weeks or months. Essentially, not all experiments are successful (to say, majority of experiments are failed) and it’s a very exciting moment when, after weeks of calculations, you observe experimental results. And it’s even more exciting, and the results are interesting and worth to be published.
During the fifth half-year of project 1.1.1.2/VIAA/1/16/112 implementation we executed a lot of computational experiments. Some results are already published:
- Pavlyuk, D., 2020. Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting. Algorithms 13, 39. https://doi.org/10.3390/a13020039
- Pavlyuk, D., 2020. Make It Flat: Multidimensional Scaling of Citywide Traffic Data, in: Kabashkin, I., Yatskiv, I., Prentkovskis, O. (Eds.), Reliability and Statistics in Transportation and Communication, Lecture Notes in Networks and Systems. Springer International Publishing, Cham, pp. 80–89. https://doi.org/10.1007/978-3-030-44610-9_9
Other experiments are still in progress and we hope that the results will have a bit of novelty and we will be happy to present them to scientific community soon.
Ongoing information of project implementation and obtained results is available here.
