TY - JOUR
T1 - Improving state estimation through projection post-processing for activity recognition with application to football
AU - Ciszewski, Michał
AU - Söhl, Jakob
AU - Jongbloed, Geurt
PY - 2023
Y1 - 2023
N2 - The past decade has seen an increased interest in human activity recognition based on sensor data. Most often, the sensor data come unannotated, creating the need for fast labelling methods. For assessing the quality of the labelling, an appropriate performance measure has to be chosen. Our main contribution is a novel post-processing method for activity recognition. It improves the accuracy of the classification methods by correcting for unrealistic short activities in the estimate. We also propose a new performance measure, the Locally Time-Shifted Measure (LTS measure), which addresses uncertainty in the times of state changes. The effectiveness of the post-processing method is evaluated, using the novel LTS measure, on the basis of a simulated dataset and a real application on sensor data from football. The simulation study is also used to discuss the choice of the parameters of the post-processing method and the LTS measure.
AB - The past decade has seen an increased interest in human activity recognition based on sensor data. Most often, the sensor data come unannotated, creating the need for fast labelling methods. For assessing the quality of the labelling, an appropriate performance measure has to be chosen. Our main contribution is a novel post-processing method for activity recognition. It improves the accuracy of the classification methods by correcting for unrealistic short activities in the estimate. We also propose a new performance measure, the Locally Time-Shifted Measure (LTS measure), which addresses uncertainty in the times of state changes. The effectiveness of the post-processing method is evaluated, using the novel LTS measure, on the basis of a simulated dataset and a real application on sensor data from football. The simulation study is also used to discuss the choice of the parameters of the post-processing method and the LTS measure.
KW - Activity recognition
KW - Performance measures
KW - Post-processing
KW - Wearable sensors
UR - http://www.scopus.com/inward/record.url?scp=85153477354&partnerID=8YFLogxK
U2 - 10.1007/s10260-023-00696-z
DO - 10.1007/s10260-023-00696-z
M3 - Article
AN - SCOPUS:85153477354
SN - 1618-2510
VL - 32
SP - 1509
EP - 1538
JO - Statistical Methods and Applications
JF - Statistical Methods and Applications
IS - 5
ER -