Enhancing the K-Means Algorithm through a Genetic Algorithm Based on Survey and Social Media Tourism Objectives for Tourism Path Recommendations

Round 1

Reviewer 1 Report

This manuscript addresses a timely topic and makes a relevant contribution to the field. However, some major revisions are needed before it can be published. Throughout the manuscript, there are several template or editing mistakes. Therefore, I recommend a professional round of language editing especially for format before the paper is published. I mentioned some examples for the author to check, but there are more issues that they need to check.

In Abstract line 16: Machine Learning (ML) it is recommended to be 

capitalized. and also some other words in the same format throughout the paper.

K-means should be written in the same format. Check line 19.

What does GA stand for in line 21? Genetic Algorithm was not even

mentioned GA in the title!

Check keywords to be written in the same format. If the first word is capitalized all of the rest should be the same.

While citing the references there must be a space after the word same as in lines 55 or 56, but in many cases, there is no space for example lines 51, 60, and 106. There are more similar issues throughout the paper.

Editing issues again in case of space(before Majid) and word capitalized

format in line 151. 

The title of tables 1 and 8 is written in lowercase while the other tables are different! The word low in Table 2 is written in lowercase while other words are written in uppercase.

Check the formatting issues in lines 244-248.

Plagiarism or citing issues found in lines 255-256 and 278-279!!

It is strongly recommended to use different tools to draw a better figure. Check figure 3. Please follow a format for captions throughout the paper and check again that all are written in the same format.

Author Response

Comment 1:  This manuscript addresses a timely topic and makes a relevant contribution to the field. However, some major revisions are needed before it can be published. Throughout the manuscript, there are several template or editing mistakes. Therefore, I recommend a professional round of language editing especially for format before the paper is published. I mentioned some examples for the author to check, but there are more issues that they need to check.

Answer 1: We carefully considered your comments and revised our paper accordingly, we have carefully revised and reread the paper and removed typos as suggested, and we make professional round of language editing especially and paper was polished by Cambridge Proofreading & Editing web site.

Comment 2:  In Abstract line 16: Machine Learning (ML) it is recommended to be capitalized. And also some other words in the same format throughout the paper. K-means should be written in the same format. Check line 19.

Answer 2: Thank you for your comments on our paper. According to your comment, we have changed the lowercase letters in words similar to Machine Learning (ML) to capitalized letters, and we have applied this change throughout the paper.

Comment 3:  What does GA stand for in line 21? Genetic Algorithm was not even mentioned GA in the title!

Answer 3: Thank you for your comments on our paper. According to your comment, GA stands for Genetic Algorithm (GA) and we have modified it in abstract.

Comment 4:  Check keywords to be written in the same format. If the first word is capitalized all of the rest should be the same.

Answer 4: Thank you for your comments on our paper. According to your comment, we have written the keywords in the same format.

Comment 5:  While citing the references there must be a space after the word same as in lines 55 or 56, but in many cases, there is no space for example lines 51, 60, and 106. There are more similar issues throughout the paper.

Answer 5: Thank you for your comments on our paper. Based on your feedback, we have added a space after each word before the references in the entire paper.

Comment 6:  Editing issues again in case of space (before Majid) and word capitalized format in line 151.

Answer 6: Thank you for your comments on our paper. According to your comment, we corrected the mistake of space.

Comment 7:  The title of tables 1 and 8 is written in lowercase while the other tables are different! The word low in Table 2 is written in lowercase while other words are written in uppercase.

Answer 7: Thank you for your comments on our paper. According to your comment, we corrected the lowercase in table 1and table 8 and we corrected table 2.

Comment 8:  Check the formatting issues in lines 244-248.

Answer 8: Thank you for your comments on our paper. According to your comment, we check the formatting issues in line 244-248.

Comment 9:  Plagiarism or citing issues found in lines 255-256 and 278-279!!

Answer 9: Thank you for your comments on our paper. According to your comment, we check the plagiarism and citing line 255-256 “In general, the K-means algorithm is a machine learning tool that may be useful in a wide range of applications, such as clustering, anomaly detection, image compression, recommendation systems, and tourism path planning” and removed the lines 278-279.

Comment 10:  It is strongly recommended to use different tools to draw a better figure. Check figure 3. Please follow a format for captions throughout the paper and check again that all are written in the same format.

Answer 10: Thank you for your comments on our paper. According to your comment, we have removed Figure 3 from the previous manuscript and replaced it with a new one. The new figure is clear.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Authors, 

Thanks for this paper. This paper is interesting by presenting a new approach to enhance k-means algorithm based on survey and social media tourism data for tourism path recommendations. However important the issue is, the literature on the contribution of social media and the reasoning of the applied social media tools such as Wechat and Whatsapp should be clarified otherwise it seems to be the applied case is limited.

In addition, the conclusion part should be evaluated in more detail on how this method contributes to science and tourism development.

Author Response

Comment 1:  Thanks for this paper. This paper is interesting by presenting a new approach to enhance k-means algorithm based on survey and social media tourism data for tourism path recommendations. However important the issue is, the literature on the contribution of social media and the reasoning of the applied social media tools such as Wechat and Whatsapp should be clarified otherwise it seems to be the applied case is limited.

Answer 1: Thank you for your comments on our paper. According to your comment, we would like to emphasize that effective planning of tourist paths involves three fundamental processes: gathering tourism objectives from social media, refining the K-means algorithm, and predicting tourist paths. Our previous studies have been built upon these essential processes. In addition to our existing research, we have incorporated a substantial body of literature highlighting the significance of utilizing social media platforms for tourism development. Below, we present a revised overview of the related works:

1.1. Related work

Tourism objectives are collected from various sources, including governmental and international institutions, geographical surveys, and popular social media platforms such as Facebook, WhatsApp, WeChat, and Twitter. In order to address the static objectives of tourism planning, three main processes must be carried out: collecting tourism data, classifying tourism data, and employing optimization algorithms to determine the optimal route. In the following sections, we conduct a thorough analysis of studies related to the formulation of tourism objectives, highlighting key findings and methodologies.

         Hu et al. [23] presented a method for deriving tourist movement patterns from Twitter data, involving a three-step process of cleaning geo-tagged tweets to identify those authored by tourists. However, this method's reliance solely on Twitter data may limit its ability to represent comprehensive tourist activity from other sources or platforms. In a separate study by Riaz and Sherani. [24] Overcame this limitation by focusing on the factors influencing information sharing on multiple social media platforms, particularly the adoption of Facebook and WeChat. Hashimy, and T.S. [25] explore the opportunities and challenges of using social media platforms such as WhatsApp and Facebook for tourism development in Afghanistan. These include increased visibility, user-generated content, direct communication, influencer marketing, and destination marketing. However, the paper also highlights challenges that must be addressed, such as ensuring tourist safety and the need for infrastructure development. Sakas et al. [26] consider multiple objectives, including transportation type and tourist preferences, collected from various social media platforms. These objectives collectively describe the tourist destination, falling under the category of internal objectives. However, this approach overlooks external objectives associated with interactions between tourist destinations. Addressing the challenge of integrating both internal and external objectives within a unified approach is essential for the advancement of this field.

  A novel approach developed by Kim et al. [27] focused on developing a deep learning model and an image feature vector clustering technique to automate the categorization of traveler images by tourism destinations. However, the paper has limitations, primarily focusing on spatial data and omitting information about the characteristics and features of tourist destinations. The study by Bouabdallaoui et al. [28] introduces an innovative clustering architecture that integrates GA and K-means, coupled with a hybrid topic discovery approach incorporating Latent Dirichlet Allocation (LDA) and Bidirectional Encoder Representations from Transformers (BERT). The primary objective of this novel method is to predict and analyze the most significant topics related to touristic shopping destinations in Morocco. However, a significant limitation in this paper is the lack of attention to determining the values for k and the initial seeds. This limitation stems from the paper's reliance on the random selection of both the number of groups (k) and the initial seeds, raising concerns regarding the robustness and reproducibility of the results.

   Yafeng et al. [29] presented a new approach based on the GA to develop 47 tourism areas in Chongqing City, China. While this paper provides an intriguing approach for applying the GA to optimize tourism path planning, which could assist tour operators and planners in developing more effective, fun, and easy tourist trips, it is essential to note that the scope of this study is centered on enhancing the planning of tourist routes specifically for 47 scenic areas in Chongqing, China. As a result, the general applicability of the findings to different contexts or regions may be limited. Moreover, this research solely employed the GA to identify the optimal tourism path, without delving into the diverse objectives of tourism or the various tourism data sources available, such as social media platforms. Patcharin et al. [30], introduces a method for recognizing aircraft trajectories through statistical analysis clustering. It employs K-means clustering and Gaussian Mixture clustering to group unstructured trajectories observed over Suvarnabhumi International Airport. Therefore, the applicability of these findings to other regions, such as tourist destinations, may be limited. Additionally, it's worth mentioning that the K algorithm used in this approach isn't optimized, which affects the algorithm's execution time. Majid et al. [31] proposed the development of urban tourism and branding for spatial modeling. The author used a novel hybrid modeling approach combining K-mean, fuzzy logic, and an artificial neural network (ANN) to assess urban tourism potential (AUTP). While this modeling provides valuable information for developing future strategies for urban tourism, the paper does not consider tourism data sources, such as data from social media platforms, and it also overlooks various tourism objectives. Mehrdad et al. [31] discuss the use of unsupervised clustering methods as data-driven models for mapping of mineral prospective (MPM). A hybrid data-driven clustering model that combines K-means clustering algorithm with harmony search (HS) and artificial bee colony (ABC) metaheuristic optimization algorithms. This hybrid model can be used for the selection of optimum cluster centroids for highlighting favorable targets in the prospecting stage of mineral explorations.

 In conclusion, many papers have addressed the extraction and prediction of tourist paths based on social media platforms. However, the aforementioned papers lack a precise definition of survey and social media data in the context of tourism and its unique characteristics. They primarily analyze data from a single social media platform, without comparing the suitability of various platforms for tourism research. Additionally, these papers do not introduce novel methods for analyzing social media data in the tourism domain. Furthermore, the implementation of algorithms to organize and categorize spatial and attribute data of tourist destinations can be time-consuming.

Comment 2:  In addition, the conclusion part should be evaluated in more detail on how this method contributes to science and tourism development.

Answer 2: Thank you for your comments on our paper. According to your comment, we have we carefully followed your point and added a paragraph conclusion section and evaluate how our approach contributes to tourism development. “Tourism objectives derived from social media can offer new opportunities for decision support in recommending tourism paths. In this paper, we propose an innovative approach to optimize and classify tourism objectives for recommending the optimal tourism path, using K-means algorithm and GA. We also integrate various tools for this domain, demonstrating the applicability of an improved K-means algorithm and GA for developing tourism path planning. Additionally, utilized GIS for the implementation and visualization of efficient social media tourism objectives and to display the optimal routes. Our approach is organized as follows: First, the tourism objectives were collected from surveys and social media platforms. Second, GA was used to enhance the K-means algorithm with a new parameter for clustering tourism objectives. Finally, a comparison and combination were performed with the algorithms currently used in the GIS environment.’’

Author Response File: Author Response.pdf

Reviewer 3 Report

Dear Authors,

your paper is interesting given the subject matter. However, in my opinion, your text is not very clear and its formal treatment is rather poor. The following are some important shortcomings that detract from the quality of your paper:

- Tab. 2 - why do you have some examples of Questionnaire Results in text and some are numbers? (EN vs. TD as an example);

- Tab. 4 and Tab. 5 (I suppose) are very poorly worded. But there in no information what P1...P6 are. As far I understand, there are some tourist destinations, there is no information on how you selected them, where  their are located etc. If you use Tab. 7 for it, it might be better to move this table beferore tab. 2. How did you evaluate tourist preferences (maybe Tab. 4) and costs between destinations (maybe tab. 5). Are the costs in some currency or some ratio?

- Figure 2 - the diagram is very simple, but where is there  some information about the decision what is the best solution and some threshold for end of cycle?

- Figure 3 - the figure is cut and therefore unclear

- Figure 4. - the quality of the map is very poor. If the map in uppper right corner is choroplet map, where is any information about used scale of values used or legend. Even any graticule is missing in this map. There are no annotations (labels) in both maps, the fonts used are not appropriate, etc.

- Figure 5 - the quality of this map is also very poor. The map location information on the top right is missing. I assume this is the State of Readsea in Sudan. If so, why does the map have a different projection than the left map in Figure 4? There are 4 tourist sites in the left map, but there are 7 in Tab 7. Where is the rest?

- Due to very bad explanation of the previous text the results are inconclusive.

In conclusion, I recommend to improve not only the text of the submission but also the research.

Author Response

Comment 1:  Tab. 2 - why do you have some examples of Questionnaire Results in text and some are numbers? (EN vs. TD as an example)

Answer 1: Thank you for your comments on our paper. According to your comment, Tab. 2 was derived from the questionnaire distributed on social media sites. It is observed that the questionnaire design was influenced by Tabl1. In Tab. 1, the variable 'TD' represents the size of the tourist site and is not categorized into labels such as high, very high, medium, etc. Consequently, a numerical representation was chosen due to the impracticality of describing it in written form. This approach is also applied to 'TS' and 'TI' for consistency. As for the remaining objectives, we have found that describing them in writing is easily understandable for the individuals conducting the survey and completing the questionnaire.

Comment 2:  Tab. 4 and Tab. 5 (I suppose) are very poorly worded. But there in no information what P1...P6 are. As far I understand, there are some tourist destinations, there is no information on how you selected them, where there are located etc. If you use Tab. 7 for it, it might be better to move this table beferore tab. 2. How did you evaluate tourist preferences (maybe Tab. 4) and costs between destinations (maybe tab. 5). Are the costs in some currency or some ratio?

Answer 2: Thank you for your comments on our paper. According to your comment, We have renumbered Tab. 7 as Tab. 3 to clarify the meaning of P1, P2,... P6. These destinations were selected based on tourist demand and the aesthetic views available there, categorizing them as points of interest (POI). Tourist preferences indicate the extent to which tourists evaluate tourism destinations on the TripAdvisor website. Ratings range from 1 to 5, where 5 means very good, 4 means good, 3 means average, 2 means weak, and 1 means very weak. Tab. 4 displays tourist preferences according to the TripAdvisor website. Distances between tourist destinations are measured in kilometres in Tab. 5, and travel costs between destinations are measured in Sudanese pounds (SDG) in Tab. 6.

Comment 3:  Figure 2 - the diagram is very simple, but where is there some information about the decision what is the best solution and some threshold for end of cycle?

Answer 3: Thank you for your comments on our paper. According to your comment, we have removed Figure 2 from the previous manuscript and replaced it with a new one. The updated figure now includes a decision on what constitutes the best solution and incorporates some threshold criteria for the end of the cycle.

Comment 4:  Figure 3 - the figure is cut and therefore unclear

Answer 4: Thank you for your comments on our paper. According to your comment, we have removed Figure 3 from the previous manuscript and replaced it with a new one. The new figure is clear.

Comment 5:  Figure 4. - the quality of the map is very poor. If the map in uppper right corner is choroplet map, where is any information about used scale of values used or legend. Even any graticule is missing in this map. There are no annotations (labels) in both maps, the fonts used are not appropriate, etc

Answer 5: Thank you for your comments on our paper. According to your comment, we have redraw the map based on your feedback. The map in the upper right corner serves as an illustrative map indicating the location of the Red Sea State in Sudan. We have added a coordinate grid, state names, and a longitudinal scale to enhance clarity. The main map in Figure 4 depicts the position of the city of Port Sudan within the Red Sea State. Figure 5 provides a detailed view of the distribution of tourist destinations in the city of Port Sudan. Please refer to the manuscript for further details.

Comment 6:  Figure 5 - the quality of this map is also very poor. The map location information on the top right is missing. I assume this is the State of Readsea in Sudan. If so, why does the map have a different projection than the left map in Figure 4? There are 4 tourist sites in the left map, but there are 7 in Tab 7. Where is the rest?

Answer 6: Thank you for your comments on our paper. According to your comment, we have redrawn the map based on your feedback, we added the information on the top right map，we used the same projection as the map in Figure. 4, and the number of tourist destinations is 6, which is identical to the number of destinations in Tab. 3.

Comment 7:  Due to very bad explanation of the previous text the results are inconclusive.

Answer 7: Thank you for your comments on our paper. According to your comment, we have improved the figures and tables and increased the explanation of the scientific method, thus improving the results and the way they are presented, which led to more discussion. You can see the manuscript.

Comment 8:  In conclusion, I recommend to improve not only the text of the submission but also the research.

Answer 8: Thank you for your comments on our paper. According to your comment, we improved the research and editing the English language, I think now the manuscript is more clearly. 

Author Response File: Author Response.pdf

Reviewer 4 Report

While the paper is scientifically sound and presents a novel approach, it would benefit from a more in-depth discussion of its potential limitations and broader implications in the field of tourism and data science. The application of the enhanced algorithm to a specific region (Red Sea State, Sudan) provides valuable insights but also raises questions about its generalizability to other contexts. Additionally, a more detailed discussion on the scalability of the approach and its adaptability to different types of tourism data would enhance the paper's contribution to the field.

I suggest that the authors consider citing the significant work of Tenemaza et al. (2020), titled "Improving Itinerary Recommendations for Tourists Through Metaheuristic Algorithms: An Optimization Proposal." The incorporation of this reference is relevant for a few reasons.

Shared Aspects between the Two Works:

1. Utilization of K-means Algorithm and Genetic Algorithm: Both papers employ the K-means algorithm for data clustering and a Genetic Algorithm for optimization in tourism itinerary planning. This similarity in methodology underscores the relevance of Tenemaza et al.'s work in providing context and comparison for the proposed methods.
2. Focus on Optimizing Tourist Itineraries: Each study is centered around applying advanced algorithms to enhance the tourist experience through optimized itinerary planning. The shared end goal provides a strong rationale for referencing each other's work.
3. Adoption of Metaheuristic Approaches: Both papers utilize metaheuristic algorithms to address the complexities involved in itinerary planning, a critical aspect of tourism technology.

Unique Contributions of the Reviewed Paper:

1. Emphasis on Social Media Data: The first paper specifically focuses on leveraging social media data for tourism recommendations, a unique approach that complements the broader methodology in Tenemaza et al.'s work.
2. Enhancement of Traditional Algorithms: The paper provides an innovative enhancement to the traditional K-means algorithm using GA, particularly for social media and tourism data. This specialized focus is a significant contribution to the field.

Author Response

Comment 1:  While the paper is scientifically sound and presents a novel approach, it would benefit from a more in-depth discussion of its potential limitations and broader implications in the field of tourism and data science. The application of the enhanced algorithm to a specific region (Red Sea State, Sudan) provides valuable insights but also raises questions about its generalizability to other contexts. Additionally, a more detailed discussion on the scalability of the approach and its adaptability to different types of tourism data would enhance the paper's contribution to the field.

Answer 1: Thank you for your comments on our paper. According to your comment, we have added a paragraph to the discussion section to illustrate the possibility of applying this approach to other tourist areas (In this study, we have made significant enhancements to the K-means algorithm. These enhancements, specifically improve the methods used to determine the number of groups (K) and the selection of initial seeds. We achieved these improvements by utilizing an enhanced GA and optimizing its parameters. We applied this improved GA to predict optimal tourist paths. This prediction is based on tourism objectives derived from social media platforms, taking into account factors such as popular destinations and peak travel times. Although our approach was specifically implemented in the Port Sudan region of the Red Sea State in Sudan, it has the potential to be applied to other regions as well. The suitability of other regions for this approach would depend on factors such as the variety of tourist targets, population characteristics, and the prevalence of relevant social media platforms. However, for accurate and effective implementation, it is essential to conduct a comprehensive study of the region’s specific tourist objectives, population characteristics, and relevant social networking sites.)

Comment 2:  I suggest that the authors consider citing the significant work of Tenemaza et al. (2020), titled "Improving Itinerary Recommendations for Tourists Through Metaheuristic Algorithms: An Optimization Proposal."

Answer 2: Thank you for your comments on our paper. According to your comment, we citing the paper above in our paper [1].

Reference

1. Tenemaza, M., S. Luján-Mora, A. De Antonio, and J. Ramirez, Improving itinerary recommendations for tourists through metaheuristic algorithms: an optimization proposal. IEEE Access, 2020. 8: p. 79003-79023.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The article "Enhancing K-means Algorithm through Genetic Algorithm Based on Survey and Social Media Tourism Objectives for Tourism Path Recommendations" by Mohamed A. Damos et al. presents a novel approach to optimize tourist path planning using machine learning. It focuses on improving the k-means algorithm by integrating the Genetic Algorithm (GA). This enhancement is applied to social media and survey data related to tourism, aiming to select optimal tourism paths efficiently.

The authors revised the manuscript and provided satisfactory replies to the previous comments. However, there are still some minor errors that need to be addressed before acceptance of the manuscript for batter readability and improvement of the paper. Some of them are listed below.

1.      The abbreviation should be defined properly at the first occurrence, few improper definitions Include.

·         Page 4. latent Dirichlet allocation (LDA)

·         Page 5.

o   artificial neural network (ANN) to assess urban tourism potential (AUTP)

o   harmony search (HS) and artificial

o   bee colony (ABC)

o   point of interesting (POI)

2.      Similarly, the capitalization of words should be consistent for the captions of tables, algorithms and figures, some issue include;

o   Page 8. Tab. 3 Tourism Destinations in Port Sudan city

o   Page 10. Figure 2. GA operations

o   Page 12. Tab. 7 Parameter settings of GA

o   Page 12. Figure 3. Framework of Recommended Tourism Path Enhancing the K-means algorithm though GA

o   Page 13. Algorithm 1: Pseudo code of enhance K-means by GA

o   Page 15. Tab. 8 Results of Internal Tourism Objectives Groups of Visitors Using the Enhance K- means algorithm.

o   Page 16. Figure 5. Groups of the internal tourism objectives based of enhancing the k-means algorithm.

o   Page 17. Tab.9 EN objective matrix

o   Page 17. Tab.10 Optimal tourism paths 17

3.      Furthermore, section 2.4. k-means algorithm on Page 10 needs to be rearranged and algorithm steps should be separated from the definition for batter understanding.

Author Response

The article "Enhancing K-means Algorithm through Genetic Algorithm Based on Survey and Social Media Tourism Objectives for Tourism Path Recommendations" by Mohamed A. Damos et al. presents a novel approach to optimize tourist path planning using machine learning. It focuses on improving the k-means algorithm by integrating the Genetic Algorithm (GA). This enhancement is applied to social media and survey data related to tourism, aiming to select optimal tourism paths efficiently.

       The authors revised the manuscript and provided satisfactory replies to the previous comments. However, there are still some minor errors that need to be addressed before acceptance of the manuscript for batter readability and improvement of the paper. Some of them are listed below.

Comment 1:  The abbreviation should be defined properly at the first occurrence, few improper definitions Include.

 Page 4. latent Dirichlet allocation (LDA)

 Page 5.   artificial neural network (ANN) to assess urban tourism potential (AUTP),  harmony search (HS) and artificial bee colony (ABC),  point of interesting (POI)

Answer 1 : Thank you for your feedback concerning our manuscript, we carefully considered your comments and revised our paper accordingly. We have properly defined the abbreviation at the first occurrence. You can review the manuscript for details.

Comment 2:  Similarly, the capitalization of words should be consistent for the captions of tables,   algorithms and figures, some issue include;

 Page 8. Tab. 3 Tourism Destinations in Port Sudan city

       Page 10. Figure 2. GA operations

 Page 12. Tab. 7 Parameter settings of GA

 Page 12. Figure 3. Framework of Recommended Tourism Path Enhancing the K-means algorithm though GA

 Page 13. Algorithm 1: Pseudo code of enhance K-means by GA

 Page 15. Tab. 8 Results of Internal Tourism Objectives Groups of Visitors Using the Enhance K- means algorithm.

 Page 16. Figure 5. Groups of the internal tourism objectives based of enhancing the k-means algorithm.

 Page 17. Tab.9 EN objective matrix

 Page 17. Tab.10 Optimal tourism paths

 Answer 1: Thank you for your comments. We have changed the lowercase letters to uppercase letters in the “Figures” and “Tables” mentioned above. You can look at the paper.

 Comment 3:  Furthermore, section 2.4. k-means algorithm on Page 10 needs to be rearranged and algorithm steps should be separated from the definition for batter understanding.

 Answer 3: Thank you for your comment, we rearranged the section 2.4 according your comment.

Reviewer 3 Report

Dear authors,

thank you for your correction. You repaired many of text and tables, but formatting of tables 3 to 6 left - not readable. Maybe it is caused by export to pdf, but check it, please.

Author Response

Comment 1:  thank you for your correction. You repaired many of text and tables, but formatting of tables 3 to 6 left - not readable. Maybe it is caused by export to pdf, but check it, please.

Answer 1: Thank you for your comment, we have modified Tables 3-6 according to your comments and have corrected the issue of lack of clarity when converting to PDF format.