Physiological Signal-Based Real-Time Emotion Recognition Based on Exploiting Mutual Information with Physiologically Common Features

Round 1

Reviewer 1 Report

This paper proposed a real-time emotion recognition system using photoplethysmography (PPG) and electromyography (EMG) physiological signals through the extraction of physiological common features using a complex-valued convolutional neural network (CVCNN). The proposed approach consists of three stages: single-pulse extraction, a physiological coherence feature module, and a physiological common feature module. Through comparison with other methods, the authors demonstrate that their proposed method outperforms other methods in terms of accuracy and recognition interval.

1)    The overall writing has some formatting issues, like wording and spacing. I suggest the authors check the grammar and avoid any typos. More importantly, the writing needs improvement for readers to understand more easily.

2)    The method part is lack of details. More detailed descriptions are needed to explain the whole model.

3)    The results are not quite sufficient. More discussions on the result part are needed. Moreover, I would suggest the authors discuss using graph transformer model in the proposed framework, which helps expand the scope of the study.

I suggest the authors check the grammar and avoid any typos. More importantly, the writing needs improvement for readers to understand more easily.

Author Response

Please refer to the attached file.

Author Response File: Author Response.pdf

Reviewer 2 Report

 

 

The paper presents an innovative real-time emotion recognition system that effectively utilizes photoplethysmography (PPG) and electromyography (EMG) physiological signals. By employing a complex-valued convolutional neural network (CVCNN) to extract common features, the proposed approach outperforms other methods in terms of accuracy and recognition interval. The experimental results validate the effectiveness and potential of the system, showcasing its promising contributions to the field of emotion recognition. The authors have definitely succeeded in delivering all the information related in a clear and reasonably detailed way. 

Author Response

Please refer to the attached file.

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper studies Physiological Signal-based Real-time Emotion Recognition Using Physiological Common Features via Complex-Valued Neural Network. The paper is well-written and provides valuable insights, but some concerns should be addressed:

1.      The paper's title should be revised to reflect its content and be more concise and engaging accurately. The authors should consider proposing a more suitable title that reflects the key findings of the research.

2.       Discuss the study's limitations and future research suggestions.

3.       I strongly suggest that the paper be proofread and reread meticulously again, particularly regarding the spelling and grammatical mistakes.

4.       Flowchart is beneficial; it’s also important to outline the methodology behind this new approach. However, explain more about your flowchart in Figure 1

5.      The abstract should include significant findings and be structured clearly and easily. It should briefly summarize the paper's main findings to help readers understand the research.

6.      The research problem should be clearly and concise to increase readability.

7.      The authors should provide more insightful and actionable managerial insights based on the research findings and clearly articulate the practical implications of the research for managers and organizations.

8.      The authors should clarify the connections between the forecasting and Data Augmentation methods and how each method contributes to the research. They should also provide a detailed explanation of the solution method used and its effectiveness.

9.      What is your mean by 161-162? " We needed to determine the appropriate length of deep learning model input signal to recognize emotions, and using the entire signal was not necessarily optimal. Clarify more? Please explain more and provide more information.

10.   It is necessary to include additional information for the data description in subsection 3.1.

11.   Consider a literature review part and add at least ten more references. Only 23 references are unacceptable. Please consider the following related references:

·        A Novel Pipeline Age Evaluation: Considering Overall Condition Index and Neural Network Based on Measured Data. Machine Learning and Knowledge Extraction. 2023 Feb 20;5(1):252-68.

·        Human emotion recognition from EEG-based brain–computer interface using machine learning: a comprehensive review. Neural Computing and Applications. 2022 Aug;34(15):12527-57.

·        EEG feature fusion for motor imagery: A new robust framework towards stroke patients rehabilitation. Computers in biology and medicine. 2021 Oct 1;137:104799.

·        Study on a real-time BEAM system for diagnosis assistance based on a system on chips design. Sensors. 2013 May 16;13(5):6552-77.

 

·        A novel machine learning approach combined with optimization models for eco-efficiency evaluation. Applied Sciences. 2020 Jul 28;10(15):5210.

Extensive editing of the English language required

Author Response

Please refer to the attached file.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

No more concerns regarding this manuscript.

No more concerns regarding this manuscript.

Reviewer 3 Report

The authors answered all my comments.

Minor editing of the English language required