Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations

Sun, Lin; Zhang, Daqing; Li, Bin; Guo, Bin; Li, Shijian

doi:10.1007/978-3-642-16355-5_42

Cited by 213 publications

(155 citation statements)

References 16 publications

Supporting

Mentioning

150

Contrasting

Unclassified

Order By: Relevance

“…Finally, in [32], the sensor data are collected during an entire day of normal mobile phone usage. An SVM-based classifier is used to recognize many common physical activities with the aim of obtaining a complete monitoring of the user's lifestyle.…”

Section: Related Workmentioning

confidence: 99%

Using multiple sensors for reliable markerless identification through supervised learning

Albarelli

Bergamasco

Celentano

et al. 2013

Machine Vision and Applications

View full text Add to dashboard Cite

In many interaction models involving an active surface, there is a need to identify the specific object that performs an action. This is the case, for instance, when interactive contents are selected through differently shaped physical objects, or when a two-way communication is sought as the result of a touch event. When the technological facility is based on image processing, fiducial markers become the weapon of choice in order to associate a tracked object to its identity. Such approach, however, requires a clear and unoccluded view of the marker itself, which is not always the case. We came across this kind of hurdle during the design of a very large multi-touch interactive table. In fact, the thickness of the glass and the printed surface, which were required for our system, produced both blurring and occlusion at a level such that markers were completely unreadable. To overcome these limitations we propose an identification approach based on SVM that exploits the correlation between the optical features of the blob, as seen by the camera, and the data coming from active sensors available on the physical object that interacts with the table. This way, the recognition has been cast into a classification problem that can be solved through a standard

show abstract

Section: Related Workmentioning

confidence: 99%

Using multiple sensors for reliable markerless identification through supervised learning

Albarelli

Bergamasco

Celentano

et al. 2013

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Previous works on mobile activity estimation [5] have shown that knowing the body position in which a mobile is being carried may enhance the results achieved in user activity classification. In our proposal of light classifiers, we have included the possibility of activating a first stage of body position estimation, capable of delivering information about where the user is carrying the mobile device: in the hand (texting or talking), in the front or back trouser pockets, in the shirt or jacket pockets, in a short or long strap bag, in a backpack, in an armband or in a waist case.…”

Section: IIImentioning

confidence: 99%

“…RELATED WORK Most of the works tackling with embeddable activity recognition aim at finding the best set of features and algorithms to differentiate the activity [5], but they do not analyze the impact of that computation process when the system must run inside the device. One of the works that do address this issue is the one from Lane et al [6], which have designed BeWell, an application in which the embedded accelerometer, microphone and GPS receiver are used to recognize driving, stationary, running and walking activities, analyzing the RAM and CPU load of the application, as well as its impact on power consumption.…”

Section: Introductionmentioning

confidence: 99%

Towards a fuzzy-based multi-classifier selection module for activity recognition applications

Martín

Iglesias

Cano

et al. 2012

2012 IEEE International Conference on Pervasive Computing and Communications Workshops

View full text Add to dashboard Cite

Abstract-Performing activity recognition using the information provided by the different sensors embedded in a smartphone face limitations due to the capabilities of those devices when the computations are carried out in the terminal. In this work a fuzzy inference module is implemented in order to decide which classifier is the most appropriate to be used at a specific moment regarding the application requirements and the device context characterized by its battery level, available memory and CPU load. The set of classifiers that is considered is composed of Decision Tables and Trees that have been trained using different number of sensors and features. In addition, some classifiers perform activity recognition regardless of the on-body device position and others rely on the previous recognition of that position to use a classifier that is trained with measurements gathered with the mobile placed on that specific position. The modules implemented show that an evaluation of the classifiers allows sorting them so the fuzzy inference module can choose periodically the one that best suits the device context and application requirements.

show abstract

“…When smartphones are carried by people in pockets or bags, they are moving at the pace of the human body; thus, they appear to be the ideal platforms for detecting physical activities such as sitting, walking, and running [1]. However, the study of activity recognition using an accelerometer-embedded smartphone is still very limited, and there are still many difficulties that have greatly prevented it from mass adoption thus far.…”

Section: Introductionmentioning

confidence: 99%

Activity Recognition Based on an Accelerometer in a Smartphone Using an FFT-Based New Feature and Fusion Methods

Xue

Jin

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWith the development of personal electronic equipment, the use of a smartphone with a tri-axial accelerometer to detect human physical activity is becoming popular. In this paper, we propose a new feature based on FFT for activity recognition from tri-axial acceleration signals. To improve the classification performance, two fusion methods, minimal distance optimization (MDO) and variance contribution ranking (VCR), are proposed. The new proposed feature achieves a recognition rate of 92.41%, which outperforms six traditional time-or frequency-domain features. Furthermore, the proposed fusion methods effectively improve the recognition rates. In particular, the average accuracy based on class fusion VCR (CFVCR) is 97.01%, which results in an improvement in accuracy of 4.14% compared with the results without any fusion. Experiments confirm the effectiveness of the new proposed feature and fusion methods.

show abstract

Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations

Cited by 213 publications

References 16 publications

Using multiple sensors for reliable markerless identification through supervised learning

Using multiple sensors for reliable markerless identification through supervised learning

Towards a fuzzy-based multi-classifier selection module for activity recognition applications

Activity Recognition Based on an Accelerometer in a Smartphone Using an FFT-Based New Feature and Fusion Methods

Contact Info

Product

Resources

About