This paper presents different information fusion approaches to classify human gait patterns and falls in a radar sensors network. The human gaits classified in this work are both individual and sequential, continuous gait collected by a FMCW radar and three UWB pulse radar placed at different spatial locations. Sequential gaits are those containing multiple gait styles performed one after the other, with natural transitions in between, including fall events developing from walking gait in some cases. The proposed information fusion approaches operate at signal and decision level. For the signal level combination, a simple trilateration algorithm is implemented on the range data from the 3 UWB radar sensors, achieving good classification results with the proposed Bi-LSTM (Bidirectional LSTM neural network) as classifier, without exploiting conventional micro-Doppler information. For the decision level fusion, the classification results of individual radars using the Bi-LSTM network are combined with a robust Naive Bayes Combiner (NBC), and this showed subsequent improvement compared to the single radar case thanks to multi-perspective views of the subjects. Compared to conventional SVM and Random Forest classifiers, the proposed approach yields +20% and +17% improvement in the classification accuracy of individual gaits for the range-only trilateration method and NBC decision fusion method, respectively. When classifying sequential gaits, the overall accuracy for the two proposed methods reaches 93% and 90%, with validation via a ’leaving one participant out’ approach to test the robustness with subjects unknown to the network.@en

This paper discusses a fusion framework with data from multiple, distributed radar sensors based on conventional classifiers, and transfer learning with pre-trained deep networks. The application considered is the classification of gait styles and the detection of critical accidents such as falls. The data were collected from a network comprised of one Ancortek frequency modulated continuous wave radar and three ultra wide-band Xethru radars. The radar systems within the network were placed in three different locations, notably, in front of participants, on the ceiling, and on the right-hand side of the monitored area. The proposed information fusion framework compares feature level fusion, soft fusion with the classifier confidence level, and hard fusion with Naïve Bayes combiner (NBC). Regarding the classifier, linear SVM, Random-Forest Bagging Trees, and five pre-trained neural networks are introduced to the fusion algorithm, where the VGG-16 network yields the best performance (about 84%) with the help of NBC. Compared to the best cases with conventional classifiers, it is reported that 20% and 16% subsequent improvement are achieved for individual usage of single radar and fusion@en