Feature Selection Methods for Optimal Design of Studies for Developmental Inquiry

Brick, Timothy R.; Koffer, Rachel; Gerstorf, Denis; Ram, Nilam

doi:10.1093/geronb/gbx008

Cited by 20 publications

(15 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a number of intelligent feature selection or reduction approaches that have been proposed in literature including filter methods, wrapper methods, forward selection, backward selection, embedded methods or regularization, LASSO regression, Ridge regression, matrix factorization methods such as principal component analysis (PCA), independent component analysis (ICA), etc. [ 56 ]. In most of the cases, features are transformed into a new low-dimensional feature space.…”

Section: Introductionmentioning

confidence: 99%

MEG Sensor Selection for Neural Speech Decoding

et al. 2020

View full text Add to dashboard Cite

Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in providing communication assistance to locked-in patients. Magnetoencephalography (MEG) has recently shown great potential as a non-invasive neuroimaging modality for neural speech decoding, owing in part to its spatial selectivity over other high-temporal resolution devices. Standard MEG systems have a large number of cryogenically cooled channels/sensors (200 − 300) encapsulated within a fixed liquid helium dewar, precluding their use as wearable BCI devices. Fortunately, recently developed optically pumped magnetometers (OPM) do not require cryogens, and have the potential to be wearable and movable making them more suitable for BCI applications. This design is also modular allowing for customized montages to include only the sensors necessary for a particular task. As the number of sensors bears a heavy influence on the cost, size, and weight of MEG systems, minimizing the number of sensors is critical for designing practical MEG-based BCIs in the future. In this study, we sought to identify an optimal set of MEG channels to decode imagined and spoken phrases from the MEG signals. Using a forward selection algorithm with a support vector machine classifier we found that nine optimally located MEG gradiometers provided higher decoding accuracy compared to using all channels. Additionally, the forward selection algorithm achieved similar performance to dimensionality reduction using a stacked-sparse-autoencoder. Analysis of spatial dynamics of speech decoding suggested that both left and right hemisphere sensors contribute to speech decoding. Sensors approximately located near Broca's area were found to be commonly contributing among the higher-ranked sensors across all subjects. INDEX TERMS autoencoder, brain-computer interface, forward selection algorithm, magnetoencephalography, neural speech decoding, OPM, SVM

show abstract

Section: Introductionmentioning

confidence: 99%

MEG Sensor Selection for Neural Speech Decoding

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Note that to prevent variable selection (i.e., ranking) from seeing the data used for model training (i.e., parameter tuning in this study), the training-validation dataset was divided into five disjoint subsets in this recursive selection process so that at each backward elimination parameter tuning can be conducted using four of the subsets of data while variable ranking can be performed separately based on the other subset. This suggested approach follows the principles of variable selection for study design recommended by Brick et al (2017).…”

Section: Methodsmentioning

confidence: 99%

Predictive Feature Generation and Selection Using Process Data From PISA Interactive Problem-Solving Items: An Application of Random Forests

Han

Davier

2019

Front. Psychol.

View full text Add to dashboard Cite

The Programme for International Student Assessment (PISA) introduced the measurement of problem-solving skills in the 2012 cycle. The items in this new domain employ scenario-based environments in terms of students interacting with computers. Process data collected from log files are a record of students’ interactions with the testing platform. This study suggests a two-stage approach for generating features from process data and selecting the features that predict students’ responses using a released problem-solving item—the Climate Control Task. The primary objectives of the study are (1) introducing an approach for generating features from the process data and using them to predict the response to this item, and (2) finding out which features have the most predictive value. To achieve these goals, a tree-based ensemble method, the random forest algorithm, is used to explore the association between response data and predictive features. Also, features can be ranked by importance in terms of predictive performance. This study can be considered as providing an alternative way to analyze process data having a pedagogical purpose.

show abstract

“…For example, a survey might trigger when the weighted sum B 1 ×HeartRate+B 2 ×HRV is higher than a threshold T, where B 1 , B 2 , and T have been determined by fitting a logistic regression or support vector machine. Ongoing research has begun to incorporate more advanced models, such as Bayesian sequential updating models [34], vector autoregressive models [35], and automated feature selection results [19] In brief, these models are kept relatively lightweight by using sequential updating methods whenever possible, by relying on existing OS-level functions when available (eg, for GPS), and by tuning the temporal precision of modeling whenever possible. For example, the rule set provided in Figure 2 uses a preselected set of identified geofences-that is, areas of the map that have been precomputed as spaces of interest.…”

Section: Real-time Adaptation For Responsive Assessment and Interventionmentioning

confidence: 99%

“…Participant burden can be reduced, for example, via passive sensing tools [18]. Methods also exist to balance data cost with burden, for example, by reducing survey size through feature selection [19] or by modeling adherence propensity [20]. Research is still needed to optimize the interaction between participant and technology to maximize engagement and minimize burden while ensuring data quality.…”

Section: Introductionmentioning

confidence: 99%

Low-Burden Mobile Monitoring, Intervention, and Real-Time Analysis Using the Wear-IT Framework: Example and Usability Study

Brick¹,

Mundie²,

Weaver³

et al. 2020

JMIR Form Res

Self Cite

View full text Add to dashboard Cite

Background Mobile health (mHealth) methods often rely on active input from participants, for example, in the form of self-report questionnaires delivered via web or smartphone, to measure health and behavioral indicators and deliver interventions in everyday life settings. For short-term studies or interventions, these techniques are deployed intensively, causing nontrivial participant burden. For cases where the goal is long-term maintenance, limited infrastructure exists to balance information needs with participant constraints. Yet, the increasing precision of passive sensors such as wearable physiology monitors, smartphone-based location history, and internet-of-things devices, in combination with statistical feature selection and adaptive interventions, have begun to make such things possible. Objective In this paper, we introduced Wear-IT, a smartphone app and cloud framework intended to begin addressing current limitations by allowing researchers to leverage commodity electronics and real-time decision making to optimize the amount of useful data collected while minimizing participant burden. Methods The Wear-IT framework uses real-time decision making to find more optimal tradeoffs between the utility of data collected and the burden placed on participants. Wear-IT integrates a variety of consumer-grade sensors and provides adaptive, personalized, and low-burden monitoring and intervention. Proof of concept examples are illustrated using artificial data. The results of qualitative interviews with users are provided. Results Participants provided positive feedback about the ease of use of studies conducted using the Wear-IT framework. Users expressed positivity about their overall experience with the framework and its utility for balancing burden and excitement about future studies that real-time processing will enable. Conclusions The Wear-IT framework uses a combination of passive monitoring, real-time processing, and adaptive assessment and intervention to provide a balance between high-quality data collection and low participant burden. The framework presents an opportunity to deploy adaptive assessment and intervention designs that use real-time processing and provides a platform to study and overcome the challenges of long-term mHealth intervention.

show abstract

Feature Selection Methods for Optimal Design of Studies for Developmental Inquiry

Cited by 20 publications

References 42 publications

MEG Sensor Selection for Neural Speech Decoding

MEG Sensor Selection for Neural Speech Decoding

Predictive Feature Generation and Selection Using Process Data From PISA Interactive Problem-Solving Items: An Application of Random Forests

Low-Burden Mobile Monitoring, Intervention, and Real-Time Analysis Using the Wear-IT Framework: Example and Usability Study

Contact Info

Product

Resources

About