Abstract
Human activity recognition (HAR) has been a very popular field in both real practice and theoretical research. Over the years, a number of many-vs-one Long Short-Term Memory (LSTM) models have been proposed for the sensor-based HAR problem. However, how to utilize sequence outputs of them to improve the HAR performance has not been studied seriously. To solve this problem, we present a novel loss function named harmonic loss, which is utilized to improve the overall classification performance of HAR based on baseline LSTM networks. First, label replication method is presented to duplicate true labels at each sequence step in many-vs-one LSTM networks, thus each sequence step can generate a local error and a local output. Then, considering the importance of different local errors and inspired by the Ebbinghaus memory curve, the harmonic loss is proposed to give unequal weights to different local errors based on harmonic series equation. Additionally, to improve the overall classification performance of HAR, integrated methods are utilized to exploit the sequence outputs of LSTM models based on harmonic loss and ensemble learning strategy. Finally, based on the LSTM model construction and hyper-parameter setting, extensive experiments are conducted. A series of experimental results demonstrate that our harmonic loss significantly achieves higher macro-F1 and accuracy than strong baselines on two public HAR benchmarks. Compared with previous state-of-art methods, our proposed methods can achieve competitive classification performance.
Highlights
In recent years, human activity recognition (HAR) has been attracting more and more attention from both industrial and academic field [1]–[5]
2) Getting inspiration from the Ebbinghaus memory curve of humans, we present an improved loss titled harmonic loss, which computes all local errors of Long Short-Term Memory (LSTM) models by giving different weights to each local error based on the harmonic series equation
Literature [57] develops a complement objective training method (COT) to improve the accuracy of classification by introducing a complement entropy loss (CEL) based on entropy cross loss in the training, the results show that the proposed COT can improve the classification results
Summary
Human activity recognition (HAR) has been attracting more and more attention from both industrial and academic field [1]–[5]. There are many types of human activities (walking, sitting, eating and running, etc) in real life, and researchers have proposed lots of methods to. The associate editor coordinating the review of this manuscript and approving it for publication was Xin Luo. recognize these human activities, these methods can not achieve desirable overall classification results. It is important and necessary to develop advanced methods to get good recognition results of various human activities. A lot of methods have been proposed to address HAR problems, and we divided them into two main categories: traditional machine learning methods and deep learning methods. Traditional machine learning methods range from support vector machine (SVM) [9], [10], decision tree (DT) [11], random forest (RF) [12], Gaussian Mixture [13], K-nearest neighbor
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
