TSFuse: automated feature construction for multiple time series data

Brabandere, Arne De; Beéck, Tim Op De; Hendrickx, Kilian; Meert, Wannes; Davis, Jesse

doi:10.1007/s10994-021-06096-2

Cited by 10 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The features during all evaluation moments for each subject during the three types of exercise were derived from the kinematic timeseries data using a multivariate feature construction tool, TSFuse (version 1.0dev) [ 20 ]. Feature construction was performed in an unsupervised manner (meaning this was conducted without knowledge in which group each participant belonged to).…”

Section: Methodsmentioning

confidence: 99%

“…These features contain statistics such as the mean, variance, minimum and maximum of a timeseries, as well as more complex features such as Fourier coefficients and linear trend statistics. A complete overview of all implemented features is shown in [ 20 ]. After extracting the features for each trial, the features were averaged per subject per activity.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Can the Output of a Learned Classification Model Monitor a Person’s Functional Recovery Status Post-Total Knee Arthroplasty?

Emmerzaal

Brabandere

Straaten

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Osteoarthritis is a common musculoskeletal disorder. Classification models can discriminate an osteoarthritic gait pattern from that of control subjects. However, whether the output of learned models (probability of belonging to a class) is usable for monitoring a person’s functional recovery status post-total knee arthroplasty (TKA) is largely unexplored. The research question is two-fold: (I) Can a learned classification model’s output be used to monitor a person’s recovery status post-TKA? (II) Is the output related to patient-reported functioning? We constructed a logistic regression model based on (1) pre-operative IMU-data of level walking, ascending, and descending stairs and (2) 6-week post-operative data of walking, ascending-, and descending stairs. Trained models were deployed on subjects at three, six, and 12 months post-TKA. Patient-reported functioning was assessed by the KOOS-ADL section. We found that the model trained on 6-weeks post-TKA walking data showed a decrease in the probability of belonging to the TKA class over time, with moderate to strong correlations between the model’s output and patient-reported functioning. Thus, the LR-model’s output can be used as a screening tool to follow-up a person’s recovery status post-TKA. Person-specific relationships between the probabilities and patient-reported functioning show that the recovery process varies, favouring individual approaches in rehabilitation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Can the Output of a Learned Classification Model Monitor a Person’s Functional Recovery Status Post-Total Knee Arthroplasty?

Emmerzaal

Brabandere

Straaten

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the literature, three main feature engineering tasks can be distinguished [249]: feature extraction, feature synthesis (often referred to as feature construction in many literature sources (e.g., [250], [251], [252], [253]), and feature selection.…”

Section: Common Feature Engineering Tasks and Approaches For Automationmentioning

confidence: 99%

“…Typically, feature synthesis is achieved by performing manipulations on accessible features with the help of predefined transformation operations. Apart from generating new features, feature synthesis models [40], [253], [271] typically incorporate mechanisms to perform feature selection as not all artificially constructed features would be useful for the given task. However, these approaches, as discussed in this subsection, differ from feature selection methods as their main focus is in generating good features as oppose to merely selecting useful features from existing set extracted directly from input data.…”

Section: 22mentioning

confidence: 99%

Data augmentation: A comprehensive survey of modern approaches

Mumuni

2022

Array

244

View full text Add to dashboard Cite

“…For each subject and each exercise, features were derived from the kinematics, kinetics, and contact force time series using a multivariate feature construction tool, TSFuse. 29 Table 2 shows the variables of which the time series were used as input. The joint moments and joint contact forces were normalized body weight.…”

Section: Feature Constructionmentioning

confidence: 99%

Joint kinematics alone can distinguish hip or knee osteoarthritis patients from asymptomatic controls with high accuracy

Emmerzaal

Rossom

Straaten

et al. 2022

Journal Orthopaedic Research

Self Cite

View full text Add to dashboard Cite

Osteoarthritis (OA) is one of the leading musculoskeletal disabilities worldwide, and several interventions intend to change the gait pattern in OA patients to more healthy patterns. However, an accessible way to follow up the biomechanical changes in a clinical setting is still missing. Therefore, this study aims to evaluate whether we can use biomechanical data collected from a specific activity of daily living to help distinguish hip OA patients from controls and knee OA patients from controls using features that potentially could be measured in a clinical setting. To achieve this goal, we considered three different classes of statistical models with different levels of data complexity. Class 1 is kinematics based only (clinically applicable), class 2 includes joint kinetics (semi‐applicable under the condition of access to a force plate or prediction models), and class 3 uses data from advanced musculoskeletal modeling (not clinically applicable). We used a machine learning pipeline to determine which classification model was best. We found 100% classification accuracy for KneeOA‐vs‐Asymptomatic and 93.9% for HipOA‐vs‐Asymptomatic using seven features derived from the lumbar spine and hip kinematics collected during ascending stairs. These results indicate that kinematical data alone can distinguish hip or knee OA patients from asymptomatic controls. However, to enable clinical use, we need to validate if the classifier also works with sensor‐based kinematical data and whether the probabilistic outcome of the logistic regression model can be used in the follow‐up of patients with OA.

show abstract

TSFuse: automated feature construction for multiple time series data

Cited by 10 publications

References 50 publications

Can the Output of a Learned Classification Model Monitor a Person’s Functional Recovery Status Post-Total Knee Arthroplasty?

Can the Output of a Learned Classification Model Monitor a Person’s Functional Recovery Status Post-Total Knee Arthroplasty?

Data augmentation: A comprehensive survey of modern approaches

Joint kinematics alone can distinguish hip or knee osteoarthritis patients from asymptomatic controls with high accuracy

Contact Info

Product

Resources

About