Daily Routine Recognition with Visual Interactive Labeling by Fusing Acceleration and Audio Signals

Kuebert, Thomas; Puder, Henning; Koeppl, Heinz

doi:10.1109/isspit47144.2019.9001791

Cited by 2 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we address this gap by building a data set of multiple subjects with audio and ACC data for the HA preferred ear position and further analyze the routine data. In our previous work [15], we already showed the improved routine detection rates by combining audio and ACC features. Furthermore, we also applied our processing scheme on TU Darmstadt data set and showed a superior performance over the topic model [15].…”

Section: Related Workmentioning

confidence: 92%

“…In our previous work [15], we already showed the improved routine detection rates by combining audio and ACC features. Furthermore, we also applied our processing scheme on TU Darmstadt data set and showed a superior performance over the topic model [15]. For the offline recognition, lots of experiments with different classifiers such as decision trees or neural networks are performed for activity primitives mostly [5].…”

Section: Related Workmentioning

confidence: 92%

“…Whereas, the TU Darmstadt set contains the real life of the first author in an open setting by two ACC sensors. They focused on the daily routine during working days in office characterized by a very repetitive structure [15]. In contrast, our set contains the real life of 7 subjects and is a more realistic with unconstrained environments and activities.…”

Section: Data Setmentioning

confidence: 99%

“…Therefore, they are segmented in non-overlapping one-minute frames to balance between fast audio (seconds) and slow activity (minutes) changes [38,39]. This window length already showed a good performance in our previous work on TU Darmstadt and our former set [15]. Afterwards, the statistical quantities-mean, variance (var), and mean crossing rate-are computed for all features and frames [6].…”

Section: Featuresmentioning

confidence: 99%

See 3 more Smart Citations

Daily Routine Recognition for Hearing Aid Personalization

2021

Self Cite

View full text Add to dashboard Cite

This work focuses on daily routine recognition to personalize the hearing aid (HA) configuration for each user. So far, there is only one public data set containing the data of two acceleration sensors taken under unconstrained real-life conditions of one person. Therefore, we create a realistic and extensive data set with seven subjects and a total length of 63449 min. For the recordings, the HA streams the acceleration and audio data to a mobile phone, where the user simultaneously annotates it. This builds the grounds for our comprehensive simulations, where we train a set of classifiers in an offline and online manner to analyze the model generalization abilities across subjects for high-level activities. To achieve this, we build a feature representation, which describes the recurring daily situations and environments well. For the offline classification, the deep neural network, multi-layer perceptron (MLP), and random forest (RF) trained in a person-dependent manner show the significantly best F-measure performance of 86.6%, 87.1%, and 87.3%, respectively. We confirm that for high-level activities the person-dependent model outperforms the independent one. In our online experiments, we personalize a model that was pretrained in a person-independent manner by daily updates. Thereby, multiple incremental learners and an online RF are tested. We demonstrate that MLP and RF improve the F-measure compared to the offline baselines.

show abstract

Section: Related Workmentioning

confidence: 92%

Section: Related Workmentioning

confidence: 92%

Section: Data Setmentioning

confidence: 99%

Section: Featuresmentioning

confidence: 99%

See 2 more Smart Citations

Daily Routine Recognition for Hearing Aid Personalization

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…All this research has been applied to one public data set, which contains the acceleration data of the author Huynh over seven working days [8]. We also processed this data set with our supervised scheme and outperformed the topic model (TM) approach [9]. The major obstacle for further research on model generalization across multiple subjects is the time-consuming recording of data sets.…”

Section: Related Workmentioning

confidence: 99%

Improving Daily Routine Recognition in Hearing Aids Using Sequence Learning

2021

Self Cite

View full text Add to dashboard Cite

This work focuses on sequence learning to improve the daily routine recognition in hearing aids (HA), where the goal is to personalize the device configuration for each user. We apply the sequence methods on two large real-world data sets. One publicly available set contains the acceleration (ACC) data of one person, Huynh, over seven working days, whereas our set includes the real life of seven subjects over 104 days with ACC and audio data of a HA. For both sets, we design statistical features to represent the recurring routine behavior well. In our comprehensive simulations, we analyze several sequence classifiers learning the temporal relationships of high-level activities. The multi-layer perceptron (MLP) and random forest (RF) as an observation model for the hidden Markov model (HMM) show the best F-measure performance of 85.3% and 91.6% on our set and the Huynh set, respectively. In particular, the MLP-HMM combination strongly improves on both sets compared to the non-sequence classifier MLP by 6.7% and 10.2%. Within the segment error analysis, we show that the sequence classifiers improve the temporal prediction stability by a reduction of insertion errors. Thus, the improved sequence classification helps the user to better address his condition due to preferred HA settings.

show abstract

Daily Routine Recognition with Visual Interactive Labeling by Fusing Acceleration and Audio Signals

Cited by 2 publications

References 12 publications

Daily Routine Recognition for Hearing Aid Personalization

Daily Routine Recognition for Hearing Aid Personalization

Improving Daily Routine Recognition in Hearing Aids Using Sequence Learning

Contact Info

Product

Resources

About