Classification of Transition Human Activities in IoT Environments via Memory-Based Neural Networks

Abstract

Human activity recognition is a crucial task in several modern applications based on the Internet of Things (IoT) paradigm, from the design of intelligent video surveillance systems to the development of elderly robot assistants. Recently, machine learning algorithms have been strongly investigated to improve the recognition task of human activities. Though, in spite of these research activities, there are not so many studies focusing on the efficient recognition of complex human activities, namely transitional activities, and there is no research aimed at evaluating the effects of noise in data used to train algorithms. In this paper, we bridge this gap by introducing an innovative activity recognition system based on a neural classifier endowed with memory, able to optimize the performance of the classification of both transitional and non-transitional human activities. The system recognizes human activities from unobtrusive IoT devices (such as the accelerometer and gyroscope) integrated in commonly used smartphones. The main peculiarity provided by the proposed system is related to the exploitation of a neural network extended with short-term memory information about the previous activities’ features. The experimental study proves the reliability of the proposed system in terms of accuracy with respect to state-of-the-art classifiers and the robustness of the proposed framework with respect to noise in data.

Improved Spatiotemporal Framework for Human Activity Recognition in Smart Environment

“…A common use case for wearable devices is to determine whether a person is currently consuming more or less energy (e.g., walking and running versus sitting) [ 8 , 9 ]. In this context, continuously performed basic activities such as walking and running can be detected with a single sensor, while detection in situations involving transitional activities such as sitting down on a chair, which are not repeated more frequently, is improved by using multiple sensor elements [ 10 ]. For the latter, sensor data fusion can thus provide a significant improvement in recognition accuracy.…”