Evolutionary Design of Convolutional Neural Networks for Human Activity Recognition in Sensor-Rich Environments.

Alejandro Baldominos,Yago Saez,Pedro Isasi

doi:10.3390/s18041288

Abstract

Human activity recognition is a challenging problem for context-aware systems and applications. It is gaining interest due to the ubiquity of different sensor sources, wearable smart objects, ambient sensors, etc. This task is usually approached as a supervised machine learning problem, where a label is to be predicted given some input data, such as the signals retrieved from different sensors. For tackling the human activity recognition problem in sensor network environments, in this paper we propose the use of deep learning (convolutional neural networks) to perform activity recognition using the publicly available OPPORTUNITY dataset. Instead of manually choosing a suitable topology, we will let an evolutionary algorithm design the optimal topology in order to maximize the classification F1 score. After that, we will also explore the performance of committees of the models resulting from the evolutionary process. Results analysis indicates that the proposed model was able to perform activity recognition within a heterogeneous sensor network environment, achieving very high accuracies when tested with new sensor data. Based on all conducted experiments, the proposed neuroevolutionary system has proved to be able to systematically find a classification model which is capable of outperforming previous results reported in the state-of-the-art, showing that this approach is useful and improves upon previously manually-designed architectures.

Highlights

Internet of Things smart devices are currently experiencing unprecedented growth, offering a new range of services and solutions
When interpreting the phenotypes of these individuals, we can draw some interesting conclusions regarding the CNN topologies they represent. This is specially true if we remember that specific mechanisms such as niching were implemented in order to enhance the genetic diversity and consistency between different individuals in the hall-of-fame can be interpreted as a sign that those values performed well
This work deals with a well-established research challenge when working with sensor networks, which is context-aware activity recognition

Summary

Introduction

Internet of Things smart devices are currently experiencing unprecedented growth, offering a new range of services and solutions. These devices form large and heterogeneous sensor networks where context-aware systems are commonly needed for different reasons. Wireless sensor networks can be widely used to bring together and exchange environmental information from homes, buildings, vehicles, etc., where one of the most important and common challenges is performing an appropriate context identification. These context-awareness processes can be useful for many different tasks, for example providing a more customized experience and improved interaction to users. With a proper context identification, health apps could monitor users’

Methods

Results

Conclusion