MétaCan
Menu
Back to cohort
Record W2762224430 · doi:10.1109/ihtc.2017.8058201

Benefits of automatic human action recognition in an assistive system for people with dementia

2017· article· en· W2762224430 on OpenAlexaff
Emilie Jean-Baptiste, Alex Mihailidis

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicContext-Aware Activity Recognition Systems
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsAction recognitionComputer scienceTask (project management)Action (physics)Human–computer interactionContext (archaeology)Activity recognitionRecallArtificial intelligenceTask analysisMachine learningPsychologyCognitive psychologyEngineering

Abstract

fetched live from OpenAlex

In the context of Activities of Daily Living, a human action can be defined as any interaction between an individual and his or her environment during a task (e.g., to use the soap during handwashing). When an assistive system is designed to recall users what to do during a task, one of its goals is to properly track and detect their actions in order to provide accurate guidance. This paper describes a k-Nearest Neighbor (kNN) based Action Recognition System (ARS) for use in COACH, which is an assistive technology designed for people with dementia. The kNN-based ARS is able to recognize 6 main actions related to the handwashing task. The recognition is done in real-time and uses continuous sequences of discrete hand positions output by a handtracker. The aims of this new ARS are (1) to verify the benefits of enabling automatic human action recognition in COACH, (2) to evaluate its ability to overcome the limitations experienced during previous clinical trials.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.846
Threshold uncertainty score0.767

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.002
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.082
GPT teacher head0.309
Teacher spread0.227 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations16
Published2017
Admission routes1
Has abstractyes

Explore more

Same topicContext-Aware Activity Recognition SystemsFrench-language works237,207