Gwo-Yun Lee

Bio: Gwo-Yun Lee is an academic researcher from Industrial Technology Research Institute. The author has contributed to research in topics: Linear discriminant analysis & Feature extraction. The author has an hindex of 3, co-authored 3 publications receiving 172 citations.

Activity recognition using one triaxial accelerometer: a neuro-fuzzy classifier with feature reduction

Abstract: This paper presents a neuro-fuzzy classifer for activity recognition using one triaxial accelerometer and feature reduction approaches. We use a triaxial accelerometer to acquire subjects' acceleration data and train the neurofuzzy classifier to distinguish different activities/movements. To construct the neuro-fuzzy classifier, a modified mapping-constrained agglomerative clustering algorithm is devised to reveal a compact data configuration from the acceleration data. In addition, we investigate two different feature reduction methods, a feature subset selection and linear discriminate analysis. These two methods are used to determine the significant feature subsets and retain the characteristics of the data distribution in the feature space for training the neuro-fuzzy classifier. Experimental results have successfully validated the effectiveness of the proposed classifier.

Online classifier construction algorithm for human activity detection using a tri-axial accelerometer

Abstract: This paper presents an online construction algorithm for constructing fuzzy basis function (FBF) classifiers that are capable of recognizing different types of human daily activities using a tri-axial accelerometer. The activity recognition is based on the acceleration data collected from a wireless tri-axial accelerometer module mounted on users' dominant wrists. Our objective is to enable users to: (1) online add new training samples to the existing classes for increasing the recognition accuracy, (2) online add additional classes to be recognized, and (3) online delete an existing class. For this objective we proposed a dynamic linear discriminant analysis (LDA) which can dynamically update the scatter matrices for online constructing FBF classifiers without storing all the training samples in memory. Our experimental results have successfully validated the integration of the FBF classifier with the proposed dynamic LDA can reduce computational burden and achieve satisfactory recognition accuracy.

A Survey on Human Activity Recognition using Wearable Sensors

Abstract: Providing accurate and opportune information on people's activities and behaviors is one of the most important tasks in pervasive computing. Innumerable applications can be visualized, for instance, in medical, security, entertainment, and tactical scenarios. Despite human activity recognition (HAR) being an active field for more than a decade, there are still key aspects that, if addressed, would constitute a significant turn in the way people interact with mobile devices. This paper surveys the state of the art in HAR based on wearable sensors. A general architecture is first presented along with a description of the main components of any HAR system. We also propose a two-level taxonomy in accordance to the learning approach (either supervised or semi-supervised) and the response time (either offline or online). Then, the principal issues and challenges are discussed, as well as the main solutions to each one of them. Twenty eight systems are qualitatively evaluated in terms of recognition performance, energy consumption, obtrusiveness, and flexibility, among others. Finally, we present some open problems and ideas that, due to their high relevance, should be addressed in future research.

Assessment of physical activity in youth

Abstract: Despite much progress with physical activity assessment, the limitations concerning the accurate measurement of physical activity are often amplified in young people due to the cognitive, physiological, and biomechanical changes that occur during natural growth as well as a more intermittent pattern of habitual physical activity in youth compared with adults. This mini-review describes and compares methods to assess habitual physical activity in youth and discusses main issues regarding the use and interpretation of data collected with these techniques. Self-report instruments and movement sensing are currently the most frequently used methods for the assessment of physical activity in epidemiological research; others include heart rate monitoring and multisensor systems. Habitual energy expenditure can be estimated from these input measures with varying degree of uncertainty. Nonlinear modeling techniques, using accelerometry perhaps in combination with physiological parameters like heart rate or temperature, have the greatest potential for increasing the prediction accuracy of habitual physical activity energy expenditure. Although multisensor systems may be more accurate, this must be balanced against feasibility, a balance that shifts with technological and scientific advances and should be considered at the beginning of every new study.

Activity Recognition Using a Single Accelerometer Placed at the Wrist or Ankle

Abstract: AB Purpose: Large physical activity surveillance projects such as the UK Biobank and NHANES are using wrist-worn accelerometer-based activity monitors that collect raw data. The goal is to increase wear time by asking subjects to wear the monitors on the wrist instead of the hip, and then to use information in the raw signal to improve activity type and intensity estimation. The purposes of this work was to obtain an algorithm to process wrist and ankle raw data and to classify behavior into four broad activity classes: ambulation, cycling, sedentary, and other activities. Methods: Participants (N = 33) wearing accelerometers on the wrist and ankle performed 26 daily activities. The accelerometer data were collected, cleaned, and preprocessed to extract features that characterize 2-, 4-, and 12.8-s data windows. Feature vectors encoding information about frequency and intensity of motion extracted from analysis of the raw signal were used with a support vector machine classifier to identify a subject's activity. Results were compared with categories classified by a human observer. Algorithms were validated using a leave-one-subject-out strategy. The computational complexity of each processing step was also evaluated. Results: With 12.8-s windows, the proposed strategy showed high classification accuracies for ankle data (95.0%) that decreased to 84.7% for wrist data. Shorter (4 s) windows only minimally decreased performances of the algorithm on the wrist to 84.2%. Conclusions: A classification algorithm using 13 features shows good classification into the four classes given the complexity of the activities in the original data set. The algorithm is computationally efficient and could be implemented in real time on mobile devices with only 4-s latency.

A Deep Learning Approach to Human Activity Recognition Based on Single Accelerometer

Abstract: In this paper, we propose an acceleration-based human activity recognition method using popular deep architecture, Convolution Neural Network (CNN). In particular, we construct a CNN model and modify the convolution kernel to adapt the characteristics of tri-axial acceleration signals. Also, for comparison, we use some widely used methods to accomplish the recognition task on the same dataset. The large dataset we constructed consists of 31688 samples from eight typical activities. The experiment results show that the CNN works well, which can reach an average accuracy of 93.8% without any feature extraction methods.

Activity recognition using hierarchical hidden markov models on a smartphone with 3D accelerometer

Abstract: As smartphone users have been increased, studies using mobile sensors on smartphone have been investigated in recent years. Activity recognition is one of the active research topics, which can be used for providing users the adaptive services with mobile devices. In this paper, an activity recognition system on a smartphone is proposed where the uncertain time-series acceleration signal is analyzed by using hierarchical hidden Markov models. In order to address the limitations on the memory storage and computational power of the mobile devices, the recognition models are designed hierarchy as actions and activities. We implemented the real-time activity recognition application on a smartphone with the Google android platform, and conducted experiments as well. Experimental results showed the feasibility of the proposed method.