UME: Method for Estimating User Movement Using an Acceleration Sensor

Kobayashi, Arei; Iwamoto, Takeshi; Nishiyama, S.

doi:10.1109/saint.2008.42

Cited by 4 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To highlight the problems, Table 1 shows the estimation results obtained using a previous method by Kobayashi et al [18]. The estimation method used HMM to consider time-axis changes in the power spectrum calculated from the acceleration value.…”

Section: Issues With Previous Methodsmentioning

confidence: 99%

“…Although, the experiment scale of this research is relatively large (29 users), there is room for improvement in the estimation accuracy. Kobayashi et al [18] pointed out the problem of sudden changes in vibration and times when the vibrations resembled those for other types of movement. Moreover, while their method could identify seven types of user movement using HMM, there is also room for improvement in the estimation accuracy.…”

Section: Copyright C 2011 the Institute Of Electronics Information Amentioning

confidence: 99%

“…The performance values were calculated from the averages of these test results (six sets). Table 7 shows the performance test results for the estimation accuracy of the proposed method and a previous method [18]. Here, the "proposed method" means the accelerometer-based probabilistic inference described in Sect 4.2.…”

Section: Evaluation Data Collectionmentioning

confidence: 99%

See 2 more Smart Citations

Shaka: User Movement Estimation Considering Reliability, Power Saving, and Latency Using Mobile Phone

Kobayashi

Muramatsu

Kamisaka

et al. 2011

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThis paper proposes a method for using an accelerometer, microphone, and GPS in a mobile phone to recognize the movement of the user. Past attempts at identifying the movement associated with riding on a bicycle, train, bus or car and common human movements like standing still, walking or running have had problems with poor accuracy due to factors such as sudden changes in vibration or times when the vibrations resembled those for other types of movement. Moreover, previous methods have had problems with has the problem of high power consumption because of the sensor processing load. The proposed method aims to avoid these problems by estimating the reliability of the inference result, and by combining two inference modes to decrease the power consumption. Field trials demonstrate that our method achieves 90% or better average accuracy for the seven types of movement listed above. Shaka's power saving functionality enables us to extend the battery life of a mobile phone to over 100 hours while our estimation algorithm is running in the background. Furthermore, this paper uses experimental results to show the trade-off between accuracy and latency when estimating user activity.

show abstract

Section: Issues With Previous Methodsmentioning

confidence: 99%

Section: Copyright C 2011 the Institute Of Electronics Information Amentioning

confidence: 99%

See 1 more Smart Citation

Shaka: User Movement Estimation Considering Reliability, Power Saving, and Latency Using Mobile Phone

Kobayashi

Muramatsu

Kamisaka

et al. 2011

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [1], using an acceleration sensor, a microphone and a GPS device, the user's behaviors, such as, walking, running and stationary, and the transportation mode, such as, bicycle, train and bus, are estimated with high accuracy. In [2], using only an acceleration sensor, the user's transportation mode, such as, walking, running, stationary, and on a vehicle (bus or train), are estimated.…”

Section: Related Workmentioning

confidence: 99%

Estimation of user's position and behavior based on measurements of sensor information

Tsuji

Kamioka

2009

2009 International Symposium on Autonomous Decentralized Systems

View full text Add to dashboard Cite

In this paper, we propose a user's position and behavior estimation method using sensors, such as a GPS device, an acceleration sensor, and an ultrasonic sensor, to alert important information to the user at just the right time. For exam pIe, the information obtained by the acceleration sensor can be used to estimate the user's behaviors and the position on the rail track where the train is, and the data measured by the ultrasonic sensor tells the distance to the ceiling, that is to say, the user's location, such as indoor/outdoor, on the platform, in the station premise, on the train, and in the campus building, can be detected. The evaluation result based on the field experiment proves the effectiveness of the proposed method with the accuracy of more than 90%.

show abstract