Loading...
3 results
Search Results
Now showing 1 - 3 of 3
- Machine learning for the dynamic positioning of UAVs for extended connectivityPublication . Oliveira, Francisco; Luís, Miguel; Sargento, SusanaUnmanned Aerial Vehicle (UAV) networks are an emerging technology, useful not only for the military, but also for public and civil purposes. Their versatility provides advantages in situations where an existing network cannot support all requirements of its users, either because of an exceptionally big number of users, or because of the failure of one or more ground base stations. Networks of UAVs can reinforce these cellular networks where needed, redirecting the traffic to available ground stations. Using machine learning algorithms to predict overloaded traffic areas, we propose a UAV positioning algorithm responsible for determining suitable positions for the UAVs, with the objective of a more balanced redistribution of traffic, to avoid saturated base stations and decrease the number of users without a connection. The tests performed with real data of user connections through base stations show that, in less restrictive network conditions, the algorithm to dynamically place the UAVs performs significantly better than in more restrictive conditions, reducing significantly the number of users without a connection. We also conclude that the accuracy of the prediction is a very important factor, not only in the reduction of users without a connection, but also on the number of UAVs deployed.
- The impact of the spatial sampling resolution on the prediction of vehicular mobilityPublication . Ferreira, Rodrigo; Luís, Miguel; Oliveira, RodolfoThis work characterizes the influence of different spatial sampling resolutions on the prediction of vehicular mobility. By assuming different spatial quantization areas over a region the vehicles move through, we characterize the distribution of trajectories for a fixed number of samples using the data available in a dataset of GPS positions sampled in an urban scenario. Both spatial resolution and the number of GPS samples per trajectory are analyzed, concluding that similar distributions of the trajectories can be obtained when the unitary dimension of the spatial area is approximately 0.05 km 2 and the trajectories last approximately 5 minutes. This is of particular importance to adequate the spatio-temporal sampling variables to the dynamics of the vehicular motion, thus avoiding over-sampling or sub-sampling in the spatial and temporal domains. The paper also proposes a deep-learning approach based on recurrent neural networks to predict future positions of a vehicular trajectory, showing the influence of spatial sampling to predict single and multiple future positions of the trajectory. The accuracy and the computation time of the prediction process are evaluated, showing how the magnitude of the prediction error is influenced by the adopted spatial sampling resolutions.
- An adaptive learning-based approach for vehicle mobility predictionPublication . Irio, Luís; Ip, Andre; Oliveira, Rodolfo; Luís, MiguelThis work presents an innovative methodology to predict the future trajectories of vehicles when its current and previous locations are known. We propose an algorithm to adapt the vehicles trajectories’ data based on consecutive GPS locations and to construct a statistical inference module that can be used online for mobility prediction. The inference module is based on a hidden Markov model (HMM), where each trajectory is modeled as a subset of consecutive locations. The prediction stage uses the statistical information inferred so far and is based on the Viterbi algorithm, which identifies the subset of consecutive locations (hidden information) with the maximum likelihood when a prior subset of locations are known (observations). By analyzing the disadvantages of using the Viterbi algorithm (TDVIT) when the number of hidden states increases, we propose an enhanced algorithm (OPTVIT), which decreases the prediction computation time. Offline analysis of vehicle mobility is conducted through the evaluation of a dataset containing real traces of 442 taxis running in the city of Porto, Portugal, during a full year. Experimental results obtained with the dataset show that the prediction process is improved when more information about prior vehicle mobility is available. Moreover, the computation time of the prediction process is significantly improved when OPTVIT is adopted and approximately 90% of prediction performance can be achieved, showing the effectiveness of the proposed method for vehicle trajectory prediction.