Unsupervised learning for human activity recognition using smartphone sensors

Kwon, Yongjin; Kang, Kyuchang; Bae, Changseok

doi:10.1016/j.eswa.2014.04.037

Cited by 187 publications

(137 citation statements)

References 34 publications

Supporting

Mentioning

137

Contrasting

Order By: Relevance

“…However, stand activity could be accurately recognized. (Ronao & Cho, 2014) Accelerometer, Gyroscope 91.76% (Bayat et al, 2014) Accelerometer 91.15% (Kwon et al, 2014) Accelerometer, Gyroscope >90% Our Approach Accelerometer, Gravity Sensor 95%…”

Section: Accuracymentioning

confidence: 99%

A Simple Hierarchical Activity Recognition System using a Gravity Sensor and Accelerometer on a Smartphone

Dwiyantoro

Nugraha²,

Choi

2016

IJTech

View full text Add to dashboard Cite

The routine daily activities that tend to be sedentary and repetitive may cause severe health problems. This issue has encouraged researchers to design a system to detect and record people activities in real time and thus encourage them to do more physical exercise. By utilizing sensors embedded in a smartphone, many research studies have been conducted to try to recognize user activity. The most common sensors used for this purpose are accelerometers and gyroscopes; however, we found out that a gravity sensor has significant potential to be utilized as well. In this paper, we propose a novel method to recognize activities using the combination of an accelerometer and gravity sensor. We design a simple hierarchical system with the purpose of developing a more energy efficient application to be implemented in smartphones. We achieved an average of 95% for the activity recognition accuracy, and we also succeed at proving that our work is more energy efficient compared to other works.

show abstract

Section: Accuracymentioning

confidence: 99%

A Simple Hierarchical Activity Recognition System using a Gravity Sensor and Accelerometer on a Smartphone

Dwiyantoro

Nugraha²,

Choi

2016

IJTech

View full text Add to dashboard Cite

show abstract

“…Kwapisz [10] compares three learning algorithms: logistic regression, J48, and multilayer perceptron. Not only supervised but also, unsupervised algorithms have been studied [11]. In many works [12], complex algorithms, like the Random Forest, have demonstrated a very good performance compared to simple classification algorithms.…”

Section: Introductionmentioning

confidence: 99%

Feature extraction for robust physical activity recognition

Zhu

San-Segundo

Pardo

2017

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

IntroductionWith information obtained from sensors, computer based system can make more intelligent actions by adapting their behavior to the context conditions. These days, thanks to the development of multi-sensor networks, related research areas have increased rapidly. Among those areas, Human Activity Recognition (HAR) based on wearable sensors (accelerometer, gyroscope, magnetometer, etc.) has recently received lots of attention due to its large number of promising applications. One of the most interesting HAR applications is ubiquitous identification of physical activity. As we know, over-weighting is a general human problem as a result of a physical inactivity habit. A Lancet publication [1] estimates that physical inactivity causes 9% of all premature deaths worldwide. By monitoring physical activity, we can help people to learn the calories they consumed or gained during the day in a much more precise way and Abstract This paper presents the development of a Human Activity Recognition (HAR) system that uses a network of nine inertial measurement units situated in different body parts. Every unit provides 3D (3-dimension) acceleration, 3D angular velocity, 3D magnetic field orientation, and 4D quaternions. This system identifies 33 different physical activities (walking, running, cycling, lateral elevation of arms, etc.). The system is composed of two main modules: a feature extractor for obtaining the most relevant characteristics from the inertial signals every second, and a machine learning algorithm for classifying between the different activities. This paper focuses on the feature extractor module, evaluating several types of features and proposing different normalization approaches. This paper also analyses the performance of every sensor included in the inertial measurement units. The main experiments have been done using a public available dataset named REALDISP Activity Recognition dataset. This dataset includes recordings from 17 subjects performing 33 different activities in three different scenarios. Final results demonstrate that the proposed HAR system significantly improves the classification accuracy compared to previous works on this dataset. For the best configuration, the system accuracy is 99.1%. This system has been also evaluated with the OPPORTUNITY dataset obtaining competitive results.

show abstract

“…For these reasons, we need to find a new approach of human activity recognition without training model processing for new persons. [7] In this paper, we aim to overcome the limitations of existing physical-activity recognition system and intend to develop a novel method that is capable of recognizing a set of daily physical activities using only a single triaxial accelerometer. This method uses the max amplitude and its frequency, 1-D decomposition energy of triaxial accelerometer signals as features of activities.…”

Section: Introductionmentioning

confidence: 99%

An Activity Recognition Algorithm Based on Energy Expenditure Model

Zheng¹

2015

Advances in Computer Science Research

View full text Add to dashboard Cite

Abstract. Human activity recognition via triaxial accelerometers can provide valuable information to evaluate functional abilities. In this paper, we present an accelerometer sensor-based approach for human activity recognition. Our proposed recognition method uses a model of Activity Energy Expenditure to recognize six activities. The classifier utilizes Fast Fourier transform (FFT) and Discrete Wavelet Transform (DWT) algorithms to get energy expenditures of different activities. Every activity is recognized by the max amplitude and its frequency, 1-D decomposition energy of triaxial accelerometer signals. This activity recognition method can recognize six activities with an average accuracy of 90% using only a single triaxial.

show abstract

Unsupervised learning for human activity recognition using smartphone sensors

Cited by 187 publications

References 34 publications

A Simple Hierarchical Activity Recognition System using a Gravity Sensor and Accelerometer on a Smartphone

A Simple Hierarchical Activity Recognition System using a Gravity Sensor and Accelerometer on a Smartphone

Feature extraction for robust physical activity recognition

An Activity Recognition Algorithm Based on Energy Expenditure Model

Contact Info

Product

Resources

About