HELPFuL: Human Emotion Label Prediction Based on Fuzzy Learning for Realizing Artificial Intelligent in IoT
Round 1
Reviewer 1 Report
Review report for the paper “HELPFuL: Human Emotion Labels Predition based on Fuzzy Learning for Realizing Artificial Intelligent in IoT”
- Significance:
. The scientific content of this paper is correct.
. The technical quality of this paper should be improved.
. The overall linguistic quality is Good.
. All symbols appearing in the formulas that do not have an explanation should be described.
. The conclusion is correctly justified but it should be better supported
by the results.
. The limits of the results obtained in this paper are not mentioned. This
point should be investigated.
- Quality of presentation:
. The abstract is clear and presents correctly the subject addressed in this paper.
. Introduction – This section should be extended to highlight the motivation of the proposed method.
. The literature review is poor. There are many extensions of fuzzy rough sets such as intuitionistic fuzzy rough set and neutrosophic rough sets. These extensions should be discussed.
. Better highlight novelty in the study. Why fuzzy rough set, why not other generalizations of fuzzy rough sets such as intuitionistic fuzzy rough set and neutrosophic rough sets. Please see the following references to support the literature review.
1. A New Intuitionistic Fuzzy Rough Set Approach for Decision Support
2. A Novel Approach to Neutrosophic Soft Rough Set under Uncertainty
3. HERO: Human Emotions Recognition for Realizing Intelligent Internet of Things
4. Deep learning approach to text analysis for human emotion detection from big data
5. A Fuzzy Modelling Approach of Emotion for Affective Computing Systems
. Section 2- should be updated. Based on LR you should add the definition of fuzzy set.
- Generally, validation and comparisons of the results is well prepared. But, more discussion on the results of the case study are needed. The authors need to discuss these values and the performance of their approach. How should we know about the quality of these solutions?
- The conclusion section should be extended. The authors need to clearly provide several solid future research directions and add results of the proposed method.
- Scientific soundness: The subject addressed in this paper is relevant.
- Interest to the readers: In my opinion, method of this paper seem to be interesting for the readership of the journal.
-
Good.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
Dear Authors,
I enjoyed reading your paper "HELPFuL: Human Emotion Labels Prediction based on Fuzzy Learning for Realizing Artificial Intelligence in IoT". Your innovative use of fuzzy learning in facial expression recognition is both novel and exciting, potentially revolutionizing the way we approach emotion recognition in AI.
Here are my comments and suggestions:
Clarity and Consistency: The abstract is generally clear and well-written, however, there are some minor inconsistencies that could be addressed. For instance, you occasionally refer to "Artificial Intelligent" instead of "Artificial Intelligence".
Emotion Ambiguity: I find your approach to handling emotion ambiguity through fuzzy learning quite interesting. However, it would be beneficial to expand on the mechanics of this process in the text, as it's not entirely clear from the abstract.
Compound Emotion Prediction: The concept of compound emotion prediction is intriguing. Could you provide some specific examples of this? How does your system handle the complexity of human emotions that may be experienced simultaneously or in rapid succession?
Application Scope: Your conclusion mentions that your method extends the application scope of AI in IoT. It would be helpful to discuss potential specific use cases to give readers a more concrete understanding of its potential impact.
Evaluation and Results: You mention that your proposed algorithm performs well on human emotion labels prediction, but I would suggest providing more details about the evaluation process, such as the datasets used, comparative methods, and precise results achieved.
Overall, this is a thought-provoking and well-researched paper that I believe could make a significant contribution to the field. Your concept of using fuzzy learning to address the challenge of predicting human emotion labels has the potential to greatly enhance the effectiveness of AI within the IoT domain.
I look forward to seeing your revisions and further development of this work.
I look forward to seeing your revisions and further development of this work.
Author Response
Please see the attachment.
Reviewer 3 Report
The manuscript introduces a method for human emotion label prediction based on fuzzy learning expression recognition. The authors show the effectiveness of the proposed approach on real-world data.
The manuscript is interesting, and I suggest acceptance for publication after some minor revisions. My comments only concern the need to expand some parts of the article to improve its readability and self-consistency.
-The authors could consider extending the bibliography to improve the auto-consistency of the manuscrièt.
-The conclusions section is too poor and needs to be extended with comments about the obtained results, future research, and the potential impact of the proposed method in real-life applications.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
The authors have made extensive corrections based on the input of the reviewer, resulting in an improved manuscript. The manuscript can be published in it is present form.
