Arkadiusz Klemenko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Arkadiusz Klemenko has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Adrian Kochański1 shared publication
- Maciej Brzeski
Institute of Computer Science and Mathematics, Jagiellonian University, Kraków, Poland
1 shared publication - Marcin Możejko
TensorCell Faculty of Mathematics Informatics and Mechanics TensorCell Faculty of Mathematics and Computer Science University of Warsaw Jagiellonian University
1 shared publication - Paweł Gora
University of Warsaw
1 shared publication
Latest Publications
- Open Access
Investigating performance of neural networks and gradient boosting models approximating microscopic traffic simulations in traffic optimization tasks
We analyze the accuracy of traffic simulations metamodels based on neural networks and gradient boosting models (LightGBM), applied to traffic optimization as fitness functions of genetic algorithms. Our metamodels approximate outcomes of traffic simulations (the total time of waiting on a red signal) taking as an input different traffic signal settings, in order to efficiently find (sub)optimal settings. Their accuracy was proven to be very good on randomly selected test sets, but it turned out that the accuracy may drop in case of settings expected (according to genetic algorithms) to be close to local optima, which makes the traffic optimization process more difficult. In this work, we investigate 16 different metamodels and 20 settings of genetic algorithms, in order to understand what are the reasons of this phenomenon, what is its scale, how it can be mitigated and what can be potentially done to design better real-time traffic optimization methods.
Open AccessInvestigating performance of neural networks and gradient boosting models approximating microscopic traffic simulations in traffic optimization tasks
We analyze the accuracy of traffic simulations metamodels based on neural networks and gradient boosting models (LightGBM), applied to traffic optimization as fitness functions of genetic algorithms. Our metamodels approximate outcomes of traffic simulations (the total time of waiting on a red signal) taking as an input different traffic signal settings, in order to efficiently find (sub)optimal settings. Their accuracy was proven to be very good on randomly selected test sets, but it turned out that the accuracy may drop in case of settings expected (according to genetic algorithms) to be close to local optima, which makes the traffic optimization process more difficult. In this work, we investigate 16 different metamodels and 20 settings of genetic algorithms, in order to understand what are the reasons of this phenomenon, what is its scale, how it can be mitigated and what can be potentially done to design better real-time traffic optimization methods.