Human Activity Recognition Based on an Efficient Neural Architecture Search Framework Using Evolutionary Multi-Objective Surrogate-Assisted Algorithms

Abstract

Human activity recognition (HAR) is a popular and challenging research topic driven by various applications. Deep learning methods have been used to improve HAR models’ accuracy and efficiency. However, this kind of method has a lot of manually adjusted parameters, which cost researchers a lot of time to train and test. So, it is challenging to design a suitable model. In this paper, we propose HARNAS, an efficient approach for automatic architecture search for HAR. Inspired by the popular multi-objective evolutionary algorithm, which has a strong capability in solving problems with multiple conflicting objectives, we set weighted f1-score, flops, and the number of parameters as objects. Furthermore, we use a surrogate model to select models with a high score from the large candidate set. Moreover, the chosen models are added to the training set of the surrogate model, which makes the surrogate model update along the search process. Our method avoids manually designing the network structure, and the experiment results demonstrate that it can reduce 40% training costs on both time and computing resources on the OPPORTUNITY dataset and 75% on the UniMiB-SHAR dataset. Additionally, we also prove the portability of the trained surrogate model and HAR model by transferring them from the training dataset to a new dataset.

Edge-Fog-Cloud Data Analysis for eHealth-IoT

“…Some papers achieve excellent and high performance, but their results may only apply to some classes [42] because this database consists of two parts (ADL and fall) which indicates that they only worked on one aspect, which shows it's not the same dataset. Additionally, they may only consider a fixed data length, transforming it into a product matrix based on the temporal window size and the sliding step [43]. This experiment demonstrates that among the Machine Learning models, KNN is the strongest in terms of high performance and speed.…”

Adaptive Multi-Scale Difference Graph Convolution Network for Skeleton-Based Action Recognition

“…Human action recognition (HAR) has garnered increasing attention in recent years due to its diverse range of applications, including human-machine interactions [1][2][3], surveillance [4,5], and robotics [6]. Skeleton-based human action recognition has emerged as a popular choice owing to its robustness against dynamic circumstances and complex backgrounds [7][8][9][10][11][12][13][14][15][16][17].…”