Neural Networks for Automatic Posture Recognition in Ambient-Assisted Living

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 7; p. 2609
• Main Authors: Guerra, Bruna Maria Vittoria, Schmid, Micaela, Beltrami, Giorgio, Ramat, Stefano
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 29.03.2022; MDPI
• Subjects: Accuracy; Aged; Algorithms; Ambient Intelligence; ambient-assisted living; Analysis; Artificial Intelligence; Assisted living facilities; Cameras; Classification; Datasets; Deep learning; human action recognition; Human Activities; Human acts; Human behavior; Humans; Machine learning; Neural networks; Neural Networks, Computer; Online data bases; Posture; Sensors; Support vector machines; deep learning; human action recognition; kinect; neural networks; visual sensor-based; ambient-assisted living; machine learning; artificial intelligence; feature selection
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22072609

Human Action Recognition (HAR) is a rapidly evolving field impacting numerous domains, among which is Ambient Assisted Living (AAL). In such a context, the aim of HAR is meeting the needs of frail individuals, whether elderly and/or disabled and promoting autonomous, safe and secure living. To this goal, we propose a monitoring system detecting dangerous situations by classifying human postures through Artificial Intelligence (AI) solutions. The developed algorithm works on a set of features computed from the skeleton data provided by four Kinect One systems simultaneously recording the scene from different angles and identifying the posture of the subject in an ecological context within each recorded frame. Here, we compare the recognition abilities of Multi-Layer Perceptron (MLP) and Long-Short Term Memory (LSTM) Sequence networks. Starting from the set of previously selected features we performed a further feature selection based on an SVM algorithm for the optimization of the MLP network and used a genetic algorithm for selecting the features for the LSTM sequence model. We then optimized the architecture and hyperparameters of both models before comparing their performances. The best MLP model (3 hidden layers and a Softmax output layer) achieved 78.4%, while the best LSTM (2 bidirectional LSTM layers, 2 dropout and a fully connected layer) reached 85.7%. The analysis of the performances on individual classes highlights the better suitability of the LSTM approach.