Dynimp: Dynamic Imputation for Wearable Sensing Data through Sensory and Temporal Relatedness

In wearable sensing applications, data is inevitable to be irregularly sampled or partially missing, which pose challenges for any downstream application. An unique aspect of wearable data is that it is time-series data and each channel can be correlated to another one, such as x, y, z axis of accel...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 3988 - 3992
Hlavní autoři: Huo, Zepeng, Ji, Taowei, Liang, Yifei, Huang, Shuai, Wang, Zhangyang, Qian, Xiaoning, Mortazavi, Bobak
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 23.05.2022
Témata:
Conferences
Data models
Deep learning
Imputation
Neural Networks
Noise reduction
Predictive models
Sensor phenomena and characterization
Signal processing
Wearable Sensing
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In wearable sensing applications, data is inevitable to be irregularly sampled or partially missing, which pose challenges for any downstream application. An unique aspect of wearable data is that it is time-series data and each channel can be correlated to another one, such as x, y, z axis of accelerometer. We argue that traditional methods have rarely made use of both times-series dynamics of the data as well as the relatedness of the features from different sensors. We propose a model, termed as DynImp, to handle different time point's missingness with nearest neighbors along feature axis and then feeding the data into a LSTM-based denoising autoen-coder which can reconstruct missingness along the time axis. We experiment the model on the extreme missingness scenario (> 50% missing rate) which has not been widely tested in wearable data. Our experiments on activity recognition show that the method can exploit the multi-modality features from related sensors and also learn from history time-series dynamics to reconstruct the data under extreme missingness.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747062