Recognition of human movements with radar for ambient activity monitoring is a developed area of research that yet presents outstanding challenges to address. In real environments, activities and movements are performed with seamless motion, with continuous transitions between activities of different duration and a large range of dynamic motions, compared with discrete activities of fixed-time lengths which are typically analysed in the literature. This paper proposes a novel approach based on recurrent LSTM and Bi-LSTM network architectures for continuous activity monitoring and classification. This approach uses radar data in the form of a continuous temporal sequence of micro-Doppler or range-time information, differently from from other conventional approaches based on convolutional networks that interpret the radar data as images. Experimental radar data involving 15 participants and different sequences of 6 actions are used to validate the proposed approach. It is demonstrated that using the Doppler-domain data together with the Bi-LSTM network and an optimal learning rate can achieve over 90% mean accuracy, whereas range-domain data only achieved approximately 76%. The details of the network architectures, insights in their behaviour as a function of key hyper-parameters such as the learning rate, and a discussion on their performance across are provided in the paper.@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

This chapter will explore the different sensor and fusion topologies, using active radar sensing in conjunction with other sensing technologies as support for assisted living and healthcare applications. Initially, the sensors and their outputs will be described, with specifics of signal processing of the different sensors and the machine learning for classification detailed. The results of applying these methods to the assisted living scenario will then be presented. This chapter will give insight into activity classification with radar and additional sensing technologies, in particular, wearable inertial and magnetic sensors, focusing on the key information fusion approaches and main improvements using experimental data as validation.@en