Activity logging using lightweight classification techniques in mobile devices

Martín, Henar; Bernardos, Ana M.; Iglesias, Josué; Casar, José R.

doi:10.1007/s00779-012-0515-4

Cited by 163 publications

(139 citation statements)

References 31 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…There are few studies [22,51,55,113] that are similar to our study. For example, the authors in [51] used a combination of an accelerometer and a gyroscope and claimed that the gyroscope adds no value to the overall recognition performance.…”

Section: Related Work 45supporting

confidence: 75%

“…In some studies, different sensors are combined, but their individual contribution to the overall performance and their resource consumption costs are not evaluated, such as in [55,65]. This makes it unclear if such a fusion is actually helpful.…”

Section: Discussionmentioning

confidence: 99%

“…There are very few studies that have implemented multiple classifiers for comparison purposes, and there is still room for further research. For example, two classifiers in [68,54] and three in [55] are implemented on mobile phones and are compared for their evaluation results.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Sitting is the new smoking: online complex human activity recognition with smartphones and wearables

Shoaib¹

View full text Add to dashboard Cite

Section: Related Work 45supporting

confidence: 75%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Sitting is the new smoking: online complex human activity recognition with smartphones and wearables

Shoaib¹

View full text Add to dashboard Cite

“…During the development phase of handheld devices, developers must often observe a large number of logs to understand the behavior of the device, that is, to determine occurring exceptions and to take steps to track an issue [1,2]. When the problem is repeated, logs are created to understand the root cause of the problem.…”

Section: Introductionmentioning

confidence: 99%

“…In the traditional field trial and beta user trial, the following are the steps of a return issue: (1) problems found by a tester; (2) logging in to the problem-reporting system; (3) dumping device logs; and (4) uploading device logs to provide a more convenient way to report issues and upload logs for testers. The ALAS system integrates the original Steps (2)- (4) in an application process after a problem is determined, and only a key combination is required to begin an application that can simultaneously report a problem and dump and upload logs.…”

Section: Introductionmentioning

confidence: 99%

Automatic Data Logging and Quality Analysis System for Mobile Devices

Fanjiang

2017

Mobile Information Systems

View full text Add to dashboard Cite

The testing phase of mobile device products includes two important test projects that must be completed before shipment: the field trial and the beta user trial. During the field trial, the product is certified based on its integration and stability with the local operator's system, and, during the beta user trial, the product is certified by multiple users regarding its daily use, where the goal is to detect and solve early problems. In the traditional approach used to issue returns, testers must log into a web site, fill out a problem form, and then go through a browser or FTP to upload logs; however, this is inconvenient, and problems are reported slowly. Therefore, we propose an "automatic logging analysis system" (ALAS) to construct a convenient test environment and, using a record analysis (log parser) program, automate the parsing of log files and have questions automatically sent to the database by the system. Finally, the mean time between failures (MTBF) is used to establish measurement indicators for the beta user trial.

show abstract

Human activity recognition based on transformed accelerometer data from a mobile phone

Xia

Wang

2014

Int J Communication

View full text Add to dashboard Cite

Summary Mobile phones are equipped with a rich set of sensors, such as accelerometers, magnetometers, gyroscopes, photometers, orientation sensors, and gravity sensors. These sensors can be used for human activity recognition in the ubiquitous computing domain. Most of reported studies consider acceleration signals that are collected from a known fixed device location and orientation. This paper describes how more accurate results of basic activity recognition can be achieved with transformed accelerometer data. Based on the rotation matrix (Euler Angle Conversion) derived from the orientation angles of gyroscopes and orientation sensors, we transform input signals into a reference coordinate system. The advantage of the transformation is that it allows activity classification and recognition to be carried out independent of the orientation of sensors. We consider five user activities: staying, walking, running, ascending stairs, and descending stairs, with a phone being placed in the subject's hand, or in pants pocket, or in a handbag. The results show that an overall orientation independent accuracy of 84.77% is achieved, which is a improvement of 17.26% over those classifications without input transformation. Copyright © 2014 John Wiley & Sons, Ltd.

show abstract

Activity logging using lightweight classification techniques in mobile devices

Cited by 163 publications

References 31 publications

Sitting is the new smoking: online complex human activity recognition with smartphones and wearables

Sitting is the new smoking: online complex human activity recognition with smartphones and wearables

Automatic Data Logging and Quality Analysis System for Mobile Devices

Human activity recognition based on transformed accelerometer data from a mobile phone

Contact Info

Product

Resources

About