A new version of ResearchHub is available.Try it now
Healthy Research Rewards
ResearchHub is incentivizing healthy research behavior. At this time, first authors of open access papers are eligible for rewards. Visit the publications tab to view your eligible publications.
Got it
VC
Vincenzo Cascioli
Author with expertise in High-Energy Astrophysics and Particle Acceleration Studies
Achievements
Cited Author
Open Access Advocate
Key Stats
Upvotes received:
0
Publications:
6
(100% Open Access)
Cited by:
3,146
h-index:
13
/
i10-index:
13
Reputation
Biology
< 1%
Chemistry
< 1%
Economics
< 1%
Show more
How is this calculated?
Publications
0

Comparative Analysis of Force-Sensitive Resistors and Triaxial Accelerometers for Sitting Posture Classification

Zhuofu Liu et al.Dec 2, 2024
Sedentary behaviors, including poor postures, are significantly detrimental to health, particularly for individuals losing motion ability. This study presents a posture detection system utilizing four force-sensitive resistors (FSRs) and two triaxial accelerometers selected after rigorous assessment for consistency and linearity. We compared various machine learning algorithms based on classification accuracy and computational efficiency. The k-nearest neighbor (KNN) algorithm demonstrated superior performance over Decision Tree, Discriminant Analysis, Naive Bayes, and Support Vector Machine (SVM). Further analysis of KNN hyperparameters revealed that the city block metric with K = 3 yielded optimal classification results. Triaxial accelerometers exhibited higher accuracy in both training (99.4%) and testing (99.0%) phases compared to FSRs (96.6% and 95.4%, respectively), with slightly reduced processing times (0.83 s vs. 0.85 s for training; 0.51 s vs. 0.54 s for testing). These findings suggest that, apart from being cost-effective and compact, triaxial accelerometers are more effective than FSRs for posture detection.