On-body wearable device localization with a fast and memory efficient SVM-kNN using GPUs

Li, Quan-Zhe; Shin, Sae Byuk; Hong, Chung Pyo; Kim, Shin Dug

doi:10.1016/j.patrec.2017.10.005

Cited by 5 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These factors may lead to intermittent detachment, which was often reported by subjects in the study. Enhancement of form factors and localization systems [ 22 ] may be another necessary element to improve data quality.…”

Section: Discussionmentioning

confidence: 99%

Lessons from a multicenter clinical trial with an approved wearable electrocardiogram: issues and practical considerations

Huh

Jeong

Yoo

et al. 2022

Transl Clin Pharmacol

View full text Add to dashboard Cite

Although wearable electrocardiograms (ECGs) are being increasingly applied in clinical settings, validation methods have not been standardized. As an exploratory evaluation, we performed a multicenter clinical trial implementing an approved wearable patch ECG. Healthy male adults were enrolled in 2 study centers. The approved ECGs were deployed for 6 hours, and pulse rates were measured independently with conventional pulse oximetry at selected time points for correlation analyses. The transmission status of the data was evaluated by heart rates and classified into valid, invalid, and missing. A total of 55 subjects (40 in center 1 and 15 in center 2) completed the study. Overall, 77.40% of heart rates were within the valid range. Invalid and missing data accounted for 1.42% and 21.23%, respectively. There were significant differences in valid and missing data between centers. The proportion of missing data in center 1 (24.77%) was more than twice center 2 (11.77%). Heart rates measured by the wearable ECG and conventional pulse oximetry showed a poor correlation (intraclass correlation coefficient = 0.0454). In conclusion, we evaluated the multicenter feasibility of implementing wearable ECGs. The results suggest that systems to mitigate multicenter discrepancies and remove artifacts should be implemented prior to performing a clinical trial. Trial Registration ClinicalTrials.gov Identifier: NCT05182684

show abstract

Section: Discussionmentioning

confidence: 99%

Lessons from a multicenter clinical trial with an approved wearable electrocardiogram: issues and practical considerations

Huh

Jeong

Yoo

et al. 2022

Transl Clin Pharmacol

View full text Add to dashboard Cite

show abstract

“…The KNN technique is widely used in various machine learning applications. This algorithm is a supervised learning methodology and it is a nonparametric algorithm 37,38 . This is also called a lazy learner algorithm where it does not learn from the training data set immediately.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…Apart from that, this method is a simple training approach and the implementation is easy. The training of KNN model solely depends on the best suitable value of “k” and the training performance is often better when the “k” is large 37–40 . The pseudo‐code of the KNN algorithm used in this article is shown below.…”

Section: Proposed Methodologymentioning

confidence: 99%

An experimental approach to evaluate machine learning models for the estimation of load distribution on suspension bridge using FBG sensors and IoT

Mohapatra¹,

Khanna

Gupta

et al. 2020

Computational Intelligence

View full text Add to dashboard Cite

Most of the tragedies on any bridge structure have been the cause of high‐density crowd behavior as a response to trampling as well as the crushing scenario. Therefore, it is most important to monitor such unforeseen situations by sensing the load imposed on the bridge structures. This scenario may arise where crowd movement is huge on these types of bridges. Similarly, the fiber Bragg grating (FBG) is a promising technology for structural health monitoring applications. In this work, an Internet of Things based FBG optical sensing scheme is proposed to monitor real‐time strain distribution throughout the bridge structures and localization of load imposed on the structure from a central control room. A suspension bridge model is designed by referring to a real bridge scenario and these FBG sensors are deployed to validate the proposed machine learning models. In this article, the performances of two machine learning strategies are discussed for the accurate estimation of load and its position by acquiring high sensitive FBG sensors signals at a very high data rate. The algorithms include K‐nearest neighbor (KNN) and random forest (RF); which are applied on each sensing data source, and then validated using a prototype suspension bridge model integrated with three FBG sensors (1532 nm, 1538 nm, and1541 nm) on a single optical fiber cable.

show abstract

“…The nearest neighbour classifier is a popular classification approach [68,69] and used in various applications of pattern recognition. Daniel et al [70] used KNN for image retrieval task, [71] used KNN for on-body wearable device localisation, [55] for character classification, Mensink et al [72] used the KNN method for image classification and many others. There are different variants of KNN depending upon the neighbours used for classification like 1-NN when only one neighbour is considered and k-NN when k neighbours are considered.…”

Section: Classification/recognitionmentioning

confidence: 99%

Handwritten Hindi character recognition: a review

Yadav

Purwar

Mittal³

2018

IET Image Processing

View full text Add to dashboard Cite

On-body wearable device localization with a fast and memory efficient SVM-kNN using GPUs

Cited by 5 publications

References 17 publications

Lessons from a multicenter clinical trial with an approved wearable electrocardiogram: issues and practical considerations

Lessons from a multicenter clinical trial with an approved wearable electrocardiogram: issues and practical considerations

An experimental approach to evaluate machine learning models for the estimation of load distribution on suspension bridge using FBG sensors and IoT

Handwritten Hindi character recognition: a review

Contact Info

Product

Resources

About