Human Activity Recognition with Smartphone Inertial Sensors Using Bidir-LSTM Networks

Yu, Shilong; Qin, Long

doi:10.1109/icmcce.2018.00052

Cited by 62 publications

(33 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After 10 repetitions, the average accuracy of the open database was 95.08%, and the mean accuracy of the database we recorded was 87.88%. [20] 93.70% LSTM-CNN [28] 95.78% Bidir-LSTM [31] 93.79% EHARS [32] 93.92% CNN-LSTM [33] 92.13% CNN-LSTM [34] 93.40% Ours 95.99%…”

Section: G K-fold Cross-validation In Both Open Dataset and Data Thimentioning

confidence: 99%

See 1 more Smart Citation

Human Daily Activity Recognition Performed Using Wearable Inertial Sensors Combined With Deep Learning Algorithms

2020

View full text Add to dashboard Cite

This study proposed a wearable device capable of recognizing six human daily activities (walking, walking upstairs, walking downstairs, sitting, standing, and lying) through a deep learning algorithm. Existing wearable devices are mainly watches or wristbands, and almost none are to be worn on the waist. Wearable devices in the forms of watches and wristbands are unfriendly to patients who are critically ill, such as patients undergoing dialysis. Patients undergoing dialysis have artificial blood vessels on their arm, and they cannot perform intense exercise. For this type of users, general hand wearable devices cannot correctly identify wearers' activities. Therefore, we proposed a waist wearable device and these types of daily life activities to assess their exercise. The hardware of the wearable device consisted of an inertial sensor, which included a microcontroller, a three-axis accelerometer, and a three-axis gyroscope. The activity recognition algorithm of the software used motion signals acquisition, signal normalization, and a feature learning method. The feature learning method was based on a 1D convolutional neural network that automatically performed feature extraction and classification from raw data. One part of the experimental data was from the dataset of the University of California (UCI), and the other part was recorded by this study. To capture the data recorded, the wearable inertial sensing device was attached to the waists of 21 experimental participants who performed six common movements in a laboratorial environment, and the subsequent records were collected to verify the validity of the proposed deep learning algorithm in relation to the inertial sensor of the wearable device. For the six common activities in the UCI dataset and the data recorded, the recognition rates in the training sample reached 98.93% and 97.19%, respectively, and the recognition rates in the testing sample were 95.99% and 93.77%, respectively.

show abstract

Section: G K-fold Cross-validation In Both Open Dataset and Data Thimentioning

confidence: 99%

“…This study used only CNN and could obtain similar or even superior accuracy. Reference [31] used bidirectional LSTM, and it took 50,000 iterations to converge. By contrast, the present study only required 600 iterations to obtain superior accuracy.…”

Section: H the Comparisons Of Several Models Of The Open Datasetmentioning

confidence: 99%

Human Daily Activity Recognition Performed Using Wearable Inertial Sensors Combined With Deep Learning Algorithms

2020

View full text Add to dashboard Cite

show abstract

“…Generally, stacked autoencoder provides compact feature representation from continuous unlabelled sensor streams to achieve robust and seamless implementation of human activity recognition system [ 34 ]. In addition to the above mentioned, deep learning methods also include Recurrent Neural Network (RNN) [ 50 , 51 ], Long Short-Term Memory (LSTM) [ 52 ], Deep Belief Networks (DBN) [ 53 ], and so on. In Table 1 , some references that utilized deep learning methods were listed.…”

Section: Related Workmentioning

confidence: 99%

Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders

Fan

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

Activity recognition has received considerable attention in many research fields, such as industrial and healthcare fields. However, many researches about activity recognition have focused on static activities and dynamic activities in current literature, while, the transitional activities, such as stand-to-sit and sit-to-stand, are more difficult to recognize than both of them. Consider that it may be important in real applications. Thus, a novel framework is proposed in this paper to recognize static activities, dynamic activities, and transitional activities by utilizing stacked denoising autoencoders (SDAE), which is able to extract features automatically as a deep learning model rather than utilize manual features extracted by conventional machine learning methods. Moreover, the resampling technique (random oversampling) is used to improve problem of unbalanced samples due to relatively short duration characteristic of transitional activity. The experiment protocol is designed to collect twelve daily activities (three types) by using wearable sensors from 10 adults in smart lab of Ulster University, the experiment results show the significant performance on transitional activity recognition and achieve the overall accuracy of 94.88% on three types of activities. The results obtained by comparing with other methods and performances on other three public datasets verify the feasibility and priority of our framework. This paper also explores the effect of multiple sensors (accelerometer and gyroscope) to determine the optimal combination for activity recognition.

show abstract

“…Dynamic time warping [23] 89.00 Handcrafted features + SVM [24] 89.00 Convolutional neural network [25] 90.89 Hidden Markov models [26] 91.76 PCA + SVM [27] 91.82 Stacked autoencoders + SVM [28] 92.16 Hierarchical continuous HMM [28] 93.18 Bidir-LSTM network [29] 93.79 A multi-layer parallel LSTM network [30] 94.34 Convolutional neural network [31] 94.79 Convolutional neural network [16] 95.31 Fully convolutional network [32] 96.32 Genetic algorithm to optimize feature vector [33] 96.38 Bidirectional LSTM network [34] 92.67 CNN [35] 94.00 Hierarchical deep learning model [36] 97.95 Our method (LDA + SVM)…”

Section: Recognition Accuracy (%)mentioning

confidence: 99%

An Activity-Aware Sampling Scheme for Mobile Phones in Activity Recognition

Chen

Huang

2020

Sensors

View full text Add to dashboard Cite

In recent years, sensors in smartphones have been widely used in applications, e.g., human activity recognition (HAR). However, the power of smartphone constrains the applications of HAR due to the computations. To combat it, energy efficiency should be considered in the applications of HAR with smartphones. In this paper, we improve energy efficiency for smartphones by adaptively controlling the sampling rate of the sensors during HAR. We collect the sensor samples, depending on the activity changing, based on the magnitude of acceleration. Besides that, we use linear discriminant analysis (LDA) to select the feature and machine learning methods for activity classification. Our method is verified on the UCI (University of California, Irvine) dataset; and it achieves an overall 56.39% of energy saving and the recognition accuracy of 99.58% during the HAR applications with smartphone.

show abstract

Human Activity Recognition with Smartphone Inertial Sensors Using Bidir-LSTM Networks

Cited by 62 publications

References 10 publications

Human Daily Activity Recognition Performed Using Wearable Inertial Sensors Combined With Deep Learning Algorithms

Human Daily Activity Recognition Performed Using Wearable Inertial Sensors Combined With Deep Learning Algorithms

Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders

An Activity-Aware Sampling Scheme for Mobile Phones in Activity Recognition

Contact Info

Product

Resources

About