MétaCan
Menu
Back to cohort
Record W7127295788 · doi:10.1109/ism66958.2025.00069

Comparison of Multimodal Fall Detection Strategies

2025· article· W7127295788 on OpenAlexaff
Reema Maheshbhai Gadhia, Nasim Hajari

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicContext-Aware Activity Recognition Systems
Canadian institutionsConcordia University of Edmonton
Fundersnot available
KeywordsRobustness (evolution)Deep learningWearable computerRecallSensor fusionALARMWearable technologyFalse alarm

Abstract

fetched live from OpenAlex

Falls represent a major health concern for older adults, underscoring the need for accurate and timely detection systems. Conventional wearable or observer-based methods often suffer from compliance issues, discomfort, and high false alarm rates. This work investigates multimodal fall detection by combining motion sensors, triaxial accelerometers, and RGB-D data to capture both human movement and environmental context. We evaluate deep learning architectures, focusing on CNN-LSTM models with two fusion strategies: early fusion, which integrates multimodal features before temporal modeling, and intermediate fusion, which combines modality-specific representations at a later stage. Experiments conducted on a publicly available dataset of fall and non-fall activities demonstrate that the CNN-LSTM intermediate fusion model achieves higher accuracy, precision, and recall compared to early fusion and unimodal baselines. The results highlight the robustness of multimodal deep learning with intermediate fusion, offering a promising direction for reliable real-time fall detection in smart home and eldercare environments.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.006
Threshold uncertainty score0.011

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.005
Meta-epidemiology (narrow)0.0020.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0030.001

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 head0.043
GPT teacher head0.347
Teacher spread0.304 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

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