This paper presents the literature review on wireless technologies that could be used for Vehicle to Vehicle and Vehicle to Infrastructure communication. It presents the current and emerging technologies together with the results of the research made to prove the usability of network technologies in demanding vehicular data communication.
Writing styles can be described by stylometric features. They are quantitative in nature, often continuous, which either limits techniques used in mining to those capable of calculations on this form, or adds discretisation to initial pre-processing of data. The paper describes research on unsupervised and supervised discretisation applied in the stylometric domain for the task of authorship attribution. The recognition of authorship is executed as classification performed by chosen inducers capable of operating on both continuous and categorical attributes.
We propose the new application of the spatio-temporal filtering (STF) method, which is a detection of visual evoked potentials applied to brain-computer interfaces (BCI). STF aims in creating a new, enhanced channel basing on the current and the neighbouring samples from all the input channels . The new channel of the better quality facilitates quick detection of visual evoked potential in the EEG recording by reducing number of averaging operations. The BCI experiments include precise information on the times the specific events took place. This feature allowed us to design very accurately the learning step which is based on generalized eigendecomposition and aims in determining the spatio-temporal filter weights. STF based algorithm allows to achieve good results for enhancement and detection of visual evoked potentials applied for brain-computer interfaces. Advantageous classification accuracies obtained with the use of combined spatial and temporal approach suggest the method can contribute to improvement of the existing solutions and stimulate development of more accurate and faster EEG based interfaces between machines and humans.
The article explores the possibilities of using convolutional neural networks to recognize the type of tennis shots. The study compares two architectures of such networks: Inception-v3 and MobileNet. Two datasets consisting of images of tennis players making an impact are analyzed in order to identify the type and phase of impact. The images in each of the collections were assigned to the respective five following classes: backhand preparation phase, backhand shot, forehand preparation phase, forehand shot and non-shot. In each of them there is a tennis player silhouette and a racket skeleton consisting of markers. Images of tennis players are generated from motion recordings made using motion capture technology. The networks were trained with different values of the learning rate. In addition, the network training time and match results for the best-trained models are presented. In view of the parameters considered, the MobileNet network has proved to be a better model.
