This paper presents a novel method for tomographic measurement and data analysis based on crowdsourcing. X-ray radiography imaging was initially applied to determine silo flow parameters. We used traced particles immersed in the bulk to investigate gravitational silo flow. The reconstructed images were not perfect, due to inhomogeneous silo filling and nonlinear attenuation of the X-rays on the way to the detector. Automatic processing of such data is not feasible. Therefore, we used crowdsourcing for human-driven annotation of the trace particles. As we aimed to extract meaningful flow parameters, we developed a modified crowdsourcing annotation method, focusing on selected important areas of the silo pictures only. We call this method “targeted crowdsourcing”, and it enables more efficient crowd work, as it is focused on the most important areas of the image that allow determination of the flow parameters. The results show that it is possible to analyze volumetric material structure movement based on 2D radiography data showing the location and movement of tiny metal trace particles. A quantitative description of the flow obtained from the horizontal and vertical velocity components was derived for different parts of the model silo volume. Targeting the attention of crowd workers towards either a specific zone or a particular particle speeds up the pre-processing stage while preserving the same quality of the output, quantified by important flow parameters.
The presented paper proposes a hybrid neural architecture that enables intelligent data analysis efficacy to be boosted in smart sensor devices, which are typically resource-constrained and application-specific. The postulated concept integrates prior knowledge with learning from examples, thus allowing sensor devices to be used for the successful execution of machine learning even when the volume of training data is highly limited, using compact underlying hardware. The proposed architecture comprises two interacting functional modules arranged in a homogeneous, multiple-layer architecture. The first module, referred to as the knowledge sub-network, implements knowledge in the Conjunctive Normal Form through a three-layer structure composed of novel types of learnable units, called L-neurons. In contrast, the second module is a fully-connected conventional three-layer, feed-forward neural network, and it is referred to as a conventional neural sub-network. We show that the proposed hybrid structure successfully combines knowledge and learning, providing high recognition performance even for very limited training datasets, while also benefiting from an abundance of data, as it occurs for purely neural structures. In addition, since the proposed L-neurons can learn (through classical backpropagation), we show that the architecture is also capable of repairing its knowledge.
A simple algorithm for respiratory activity detection in data produced by Frequency-Modulated Continuous-Wave (FMCW) radars is presented in this paper. The proposed computational architecture can be directly mapped onto custom digital–analog VLSI hardware, which is a unique approach in research on intelligent FMCW sensor development, offering a potential energy-efficient data analysis solution for target applications, such as preventing human trafficking or providing life-sign detection under limited visibility. The algorithm comprises two main modules. The first one summarizes radar-produced data into a descriptor reflecting the amount of motion that occurs within appropriately determined time intervals. The second one classifies a sequence of the produced descriptors using a recurrent neural network composed of gated recurrent units. To ensure the algorithm’s implementation feasibility, an analog VLSI circuit comprising its main functional blocks has been designed, manufactured, and tested, providing constraints for neural model derivation. The adverse effects of the primary constraint, the severe restriction on admissible weight resolution, have been handled by introducing a novel training loss component and a simple mechanism for diversifying the effective weight sets of different network neurons. Experimental evaluation of the presented method, performed using the dataset of indoor recordings, indicates that the proposed simple, hardware implementation-friendly algorithm provides over 94% human detection accuracy and similar F1 scores.