This paper presents an alternative approach to the sequential data classification, based on traditional machine learning algorithms (neural networks, principal component analysis, multivariate Gaussian anomaly detector) and finding the shortest path in a directed acyclic graph, using A* algorithm with a regression-based heuristic. Palm gestures were used as an example of the sequential data and a quadrocopter was the controlled object. The study includes creation of a conceptual model and practical construction of a system using the GPU to ensure the realtime operation. The results present the classification accuracy of chosen gestures and comparison of the computation time between the CPU- and GPU-based solutions.
This paper presents practical capabilities of a system for ceramic mould quality forecasting implemented in an industrial plant (foundry). The main assumption of the developed solution is the possibility of eliminating a faulty mould from a production line just before the casting operation. It allows relative savings to be achieved, and faulty moulds, and thus faulty castings occurrence in the production cycle to be minimized. The numerical computing module (the DEFFEM 3D package), based on the smoothed particle hydrodynamics (SPH) is one of key solutions of the system implemented. Due to very long computing times, the developed numerical module cannot be effectively used to carry out multi-variant simulations of mould filling and solidification of castings. To utilize the benefits from application of the CUDA architecture to improve the computing effectiveness, the most time consuming procedure of looking for neighbours was parallelized (cell-linked list method). The study is complemented by examples of results of performance tests and their analysis.