Next Article in Journal
Image-To-Image Translation Using a Cross-Domain Auto-Encoder and Decoder
Next Article in Special Issue
Optimization of Physical Activity Recognition for Real-Time Wearable Systems: Effect of Window Length, Sampling Frequency and Number of Features
Previous Article in Journal
Optimal Design Model of the Energy Systems in Iron and Steel Enterprises
Previous Article in Special Issue
Dynamic Handwriting Analysis for Neurodegenerative Disease Assessment: A Literary Review
 
 
Article
Peer-Review Record

Analogy Study of Center-Of-Pressure and Acceleration Measurement for Evaluating Human Body Balance via Segmentalized Principal Component Analysis

Appl. Sci. 2019, 9(22), 4779; https://doi.org/10.3390/app9224779
by Tian-Yau Wu 1,* and Ching-Ting Liou 2
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3:
Reviewer 4: Anonymous
Appl. Sci. 2019, 9(22), 4779; https://doi.org/10.3390/app9224779
Submission received: 6 October 2019 / Revised: 31 October 2019 / Accepted: 5 November 2019 / Published: 8 November 2019

Round 1

Reviewer 1 Report

 

The manuscript by Wu et al “Analogy study of COP and acceleration measurement for evaluating human body balance via segmentalized PCA” presents a PCA based model developed using simple acceleration measurements to predict the standard and expensive COP measurements. The problem considered here is important as currently the standard COP measurements are done via expensive equipment. The manuscript is generally well-written, analyses seem technically good and the manuscript is suitable for Applied Sciences. I have few concerns that should addressed before considering it for publication at Applied Sciences.

 

Major comments

Authors used the swaying acceleration measurements to build the PCA model to predict the correlated COP measurements. I don’t see any methodological development or new method, they simply applied or used PCA method. They considered only first PC1 (with most variance of data), did authors considered PC2 and PC3. What are the variances associated with PC1, PC2, PC3 etc. Authors should justify why only PC1 is sufficient. Authors claim that obtaining traditional COP measurements are expensive and thus they propose the cheap/inexpensive approach via measuring acceleration measurements. Authors should compare the costs involved in both approaches. Authors also briefly explain the various visual conditions why only 5 conditions selected or can they add more conditions, it is difficult to understand for a general reader.

 

Minor comments

 

Few typos are present and should be fixed. The language is good but fine tuning is needed and it will be greatly benefited if proof-read by native English speaker.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The paper is clear and simple to understand, but the scientific contribution of this paper must be improve.

This paper poses the change of a conventional COP by a simple three-dimensional accelerometer device. Probably, the normal COP have two uni-dimensional accelerometers, one in the AP direction and the other in the ML direction. This paper obtains both signals using PCA of the three-dimensional signal. This technique is used in literature and mathematically is clear. In fact, several papers use this technique in more complex problems.

The contribution of this paper can be the filter of the signal (EMD) and the use of the segmentalized PCA instead of normal PCA. The paper does not show results about the advantages of these techniques with respect to a simple PCA. Can be interesting to test the results obtained using only PCA with respect to the results obtained with segmentalized PCA and filter EMD.

Maybe, the practice contribution of this device is very interesting. But, in any cases, the scientific contribution of these techniques are not very big.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Very interesting paper, congrats to autors for great work in very sensitive area. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Equilibrium disorders are indicative of some abnormalities of the nervous system and musculoskeletal system. Such problems are becoming more common with ageing. In severe form, they are a prerequisite for falls and severe injuries. The novelty of this article is the proposed hardware implementation based on a capacitive acceleration sensor as well as the approach of segmentalized principal components analysis (sPCA) for processing the sensor data. A high degree of correlation is demonstrated between the results obtained with accelerometer and a standard stabilizer platform for monitoring the center of pressure (COP) of the body during swaying. Authors claim that the measurement system using accelerometers have the advantage of much lower price and convenient portability in comparison with COP.

The abstract is well written and provides accurate information about the main points in the article.

Critical comments, questions and proposals to the authors:

The presence of unpopular abbreviations in the title, which are explained in the main body of text, should be avoided. Several similar passages repeat in the text, which do not contribute to the clarification of the authors' theses, e.g. ln:49-51; ln:52-53; ln:75-76; ln:124-126. It is not acceptable for a basic paragraph in the text to begin with a table, the explanation of which is given below in the text. Authors claim: „In order to verify the accuracy of analogy between the acceleration measurements and the COP-based EQs ………. the data sets that include the synchronous measurements of body swaying acceleration and COP as well as the EQs evaluation were collected from Department of Physical Therapy and Assistive Technology in National Yang-Ming University”. It is unclear how many records are included, by patients with what status, what is the format of system data, and how they correlate with accelerometer signals. The cited references are not enough to present adequately the state of the art in the field of balance measurement of the human body. In the conclusion authors claim “ … the acceleration measurements of human body’s sway can be utilized to represent the human balancing ability with lower expense”. This is not quite true since the relatively inexpensive registering system (analogue part) implies a more sophisticated and expensive system for signal processing, storage and data transfer.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Authors sufficiently addressed my concerns and it is now ready for publication.

Reviewer 4 Report

The corrections made are adequate and improve the understanding of the experimental studies carried out and the results .

Back to TopTop