Effective Quantization Evaluation Method of Functional Movement Screening with Improved Gaussian Mixture Model
Round 1
Reviewer 1 Report
This manuscript will need to revise a few points.
1) Authors described that In summary, we proposed an automated FMS assessment method based on an improved Gaussian mixture model in this study. First, we ~show that the improved Gaussian mixture model has better performance compared~ addition, we ~ on depth cameras. However, I could not understand this study's purpose and hypotheses in the Introduction. Please more exactly for this.
2) Are there any study limitations here?
3) Figures are not clear, so could you revise these?
I recommend revising these English after revision.
Author Response
Dear Editor, the reply to the question is placed in the following word .
Author Response File: Author Response.pdf
Reviewer 2 Report
The study " Effective quantization evaluation method of Functional Movement Screening with Improved Gaussian Mixture Model" presents an innovative method for automated assessment of functional movement based on the improved Gaussian Mixture Model (GMM). The authors focus on utilizing this method for conducting Functional Movement Screening (FMS) using Azure Kinect depth sensors.
One of the strengths of this study is the application of oversampling for minority samples, which helps address data diversity. Additionally, the manual extraction of movement features from the FMS dataset and training the Gaussian mixture model for different score categories (1 point, 2 points, 3 points) are well-described and executed. The results demonstrate that the improved GMM achieves higher scoring accuracy (Improved GMM: 0.8) compared to other models (Traditional GMM = 0.38, Adaboost.M1 = 0.7, Naïve-Bayes = 0.75). Moreover, the agreement between the scoring results of the improved GMM and expert scoring is relatively high (kappa = 0.67).
However, there are a few suggestions to consider in this work. Firstly, although the described methods of extracting movement features are well-presented, it would be beneficial to provide more details regarding the criteria for selecting these features and their quantification. Additionally, there is a lack of information regarding how the FMS assessment results are used to evaluate injury risk. Including more information on the practical application of these results in a clinical setting could enhance the study.
In conclusion, the study " Effective quantization evaluation method of Functional Movement Screening with Improved Gaussian Mixture Model" presents a promising method for automated FMS assessment based on the improved GMM. The results suggest that the proposed method can effectively perform the FMS assessment task, and the use of depth sensors holds promise for future research. However, providing additional details on the selection of movement features and the practical application of assessment results could further enrich the study.
The conclusion of a research paper is where you wrap up your ideas and leave the reader with a strong final impression. It is worth formulating more boldly conclusions divided into cognitive (despite limitations) and application. Be sure to separate: the results and postulates chapter.
Additional Suggestions:
- add research limitation
Author Response
Dear Editor, the reply to the question is placed in the following word .
Author Response File: Author Response.pdf