This paper presents a hierarchical sensor fusion approach for human micro-gesture recognition by combining an Ultra Wide Band (UWB) Doppler radar and wearable pressure sensors. First, the wrist-worn pressure sensor array (PSA) and Doppler radar are used to respectively identify static and dynamic gestures through a Quadratic-kernel SVM (Support Vector Machine) classifier. Then, a robust wrapper method is applied on the features from both sensors to search the optimal combination. Subsequently, two hierarchical approaches where one sensor acts as 'enhancer' of the other are explored. In the first case, scores from Doppler radar related to the confidence level of its classifier and the prediction label corresponding to the posterior probabilities are utilized to maximize the static hand gestures classification performance by hierarchical combination with PSA data. In the second case, the PSA acts as an 'enhancer' for radar to improve the dynamic gesture recognition. In this regard, different weights of the 'enhancer' sensor in the fusion process have been evaluated and compared in terms of classification accuracy. A realistic cross-validation method is chosen to test one unknown participant with the model trained by data from others, demonstrating that this hierarchical fusion approach for static and dynamic gestures yields approximately 15% improvement in classification accuracy in the best cases.

@en

A building block strategy for modelling the pressure loss coefficient of flow through a complex geometry is presented. The approach relies on decomposing a complex flow geometry into geometrical building blocks of which the pressure loss coefficients are characterized individually. The different contributions are subsequently combined to describe the pressure loss of the geometry as a whole. This approach is applied and tested to an industrially relevant application: a by-pass pig (Pipeline Inspection Gauge). This is a cylindrical device that travels inside a pipeline and is commonly used in the oil and gas industry for pipeline maintenance. An important factor in determining the ultimate velocity of the device is the pressure drop over the by-pass pig, which is characterized by a pressure loss coefficient due to the by-passing fluids. In this study the pressure loss coefficient of three frequently used by-pass pig geometries in a single phase pipeline is investigated with Computational Fluid Dynamics (CFD). The CFD results are used to validate the simple building block approach for systematic modelling of the pressure loss through the by-pass pigs, which takes the geometry and size of the by-pass opening into account. It is shown that the pressure loss models can capture the CFD results for each of the three pig geometries. The pressure loss models can be combined with pig/pipe-wall friction models to predict the velocity of a by-pass pig in a single phase pipeline, which is important for a safe and effective pigging operation. The applied building block approach may also be suitable to characterize pressure loss coefficients of complex geometries in general.@en