Deep-cARe: Projection-Based Home Care Augmented Reality System with Deep Learning for Elderly

Round 1

Reviewer 1 Report

This study proposes an AR (PAR) projection system with a deep learning module to provide auxiliary functions and ensure the safety of the elderly in everyday life situations.

Overall, i think the document is interesting and reports a valuable research, anyway it is poorly written and confused. It needs a complete and detailed linguistic review; sometimes, there are some phrases that are difficult to understand.

The abstract is not clear. Indeed, it does not provide the reader with a clear description of the proposed system and there are no results of the experiment or discussions. I suggest rewriting it and adding the missing information.

As for the document, it is not clearly organized, except from the introduction and the related work sections, which anyway need to be improved.

Indeed, there is no clear distinction between the materials and methods section, the results section and the discussion sections. The manuscript is poorly readable.

In addition:

-Some figures are not mentioned and are not explained (e.g. figure 1) in the text.

- sometimes details are missing (i.e .144-line and 152-line - what type of projector/mini-computer/?

I suggest reviewieng the entire document in detail.

Author Response

First, we would like to deeply thank you for your precious time and in-depth and valuable feedback before stating our views on your feedback. 

We were able to think more deeply about our research thanks to your feedback and have made positive changes to the paper. We will continue to accept your high-quality review and feedback.

We have stated our views on your feedback as sequentially as possible based on the received review. We have corrected typos and grammatical errors present in the paper by paying more attention to them.

We have revised the abstract by correcting typos and adding experiment content.

We have reconstructed this paper in order to achieve maximum readability for readers. 

This paper is presented concisely by dividing the whole section and eliminating repetitive sentences.

Please see the attachment about response document for your comment.

Thank you,

Author Response File: Author Response.pdf

Reviewer 2 Report

The presented solution is only preliminary ideas and experiments with some partial solutions that could be put together in future. But starting experiments are also valuable at the stage of design of complex systems. Some experiments only test partial scenarios in a laboratory without the real surroundings of the living house. In those cases, the results will be worse. There are more improvements in future. The touching of the spatial user interface on the wall is not comfortable for older people. 

Remake the part of workflow Fig. 3 (right side) to be evident that the outputs from Application box are two possible (mobile and SUI - colour in, e.g. in ping). At that moment, the line to the bottom is not evident. There is a lot of inputs, but the central application and outputs are not evident.

Some typer set errors are highlighted in the attached file.

Maybe a stronger background in technical existing solution in the area of the older people care.

Comments for author File: Comments.pdf

Author Response

First, we would like to deeply thank you for your precious time and in-depth and valuable feedback before stating our views on your feedback. 

We were able to think more deeply about our research thanks to your feedback and have made positive changes to the paper. We will continue to accept your high-quality review and feedback.

We have stated our views on your feedback as sequentially as possible based on the received review. We have corrected typos and grammatical errors present in the paper by paying more attention to them.

We have revised the abstract by correcting typos and adding experiment content.

We have reconstructed this paper in order to achieve maximum readability for readers. 

This paper is presented concisely by dividing the whole section and eliminating repetitive sentences.

Please see the attachment about response document for your comment.

Thank you,

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper aims to present a comprehensive Augmented Reality (AR) system to increase the elderly quality of life, at their own homes. Moreover, the AR system is projection-based and its operation is supported on artificial intelligence (AI). Indeed, with the increase in life expectancy and the social changes that we all are undergoing, the elderly should be a primary focus of concern and investment when considering technological development. Their well-being, quality-of-life, joy and dignity must be a priority for all of us. For that reason alone, a paper that presents research in this area is very welcome. For the same reasons it should also meet the highest standards (as should all research), as it deals with a particularly fragile part of today’s society.    

As a general appreciation, the paper needs a detailed language revision. It has many typos (e.g. line 70, “deep” should be it a capital letter, line 31, why “;” in the middle of the sentence?), “a” or “an” are incorrectly used several times and some phrases cannot be fully understood (e.g. line 24, “...owing to medical...”, line 132 “… which users occur”). This hinders the paper’s readability and the readers’ experience. Furthermore, the document is very long due to constant repetitions. The authors do not need to frequently repeat what they consider that characterizes their work or the advantages that they find when comparing to other works. It is tiresome. If Deep-cARe is an AR system, why does the title read “Augmented Reality Systems...”? Is there more than one? Please correct this. I also do not agree with the use of “deep learning” in the title. After reading the paper, the authors apply several AI platforms, but with the exception of face recognition, none of them will learn anything further that they already know. This title can lead readers to think that the proposed AR system is capable of learning during its normal operation.

One of my main concerns regarding this paper is that it undoubtedly addresses the application of (several) existent technology. Nothing more. This can be considered as a good piece of engineering, whose main features were tested in a controlled space, without any concern by those to whom it was pieced together. Where are the experiences with the full system (not only a part at a time), in real environment, with elderly? After reading the document, I cannot accept a conclusion stating that this AR system is capable of improving the elderly quality of life or anything related. It is not proven. It was not even tested.

From the Applied Sciences Journal website:

“Aims

Applied Sciences (ISSN 2076-3417) provides an advanced forum on all aspects of applied natural sciences. It publishes reviews, research papers and communications. Our aim is to encourage scientists to publish their experimental and theoretical results in as much detail as possible. There is no restriction on the length of the papers. The full experimental details must be provided so that the results can be reproduced. Electronic files and software regarding the full details of the calculation or experimental procedure, if unable to be published in a normal way, can be deposited as supplementary electronic material.”

Bold is mine. For the aforementioned reason, I do not consider this paper as a research paper. So what is it? What does this paper contribute to the state-of-the-art? To me, it is a product. I will address this later on in my review.

As for the abstract, it is clear and objective. Again, typos most be addressed.

Regarding the introduction, it seams to be clear and it states the paper’s objectives.

As for related-work, this chapter needs work. Indeed the authors make several statements are not supported by literature (e.g. lines 101 to 103, 120 to 123). It is very hard to read this section the way it is organized. I would suggested a table comparing all the works. More and relevant paper’s are also needed to strengthen this section. Lastly, from line 138 onward it reads “Therefore, it can prevent accidents by detecting abnormal conditions such as falling and tripping”. This is completely unsupported and a does not make any sense: how can the proposed system prevent accidents by detecting if an elderly as fallen? It can, if done wright, warn someone that something out of the ordinary happen.

As for chapter 3, where is the reference supporting the sentence that ends in line 148? Line 163  ha a very important sentence that is my second concern about this work. So the authors state that walking around transporting a mobile device can be tiresome for the elderly. However, they state that their proposal can be carried and placed around the elderly’s home. How much does it weight? What is the sense in that? With this proposal and to have all the home addressed, there must be almost one device per division. Where is the cost discussion? Otherwise, the authors are installing this only in the living room (for example) and the rest of the house is unprotected. This must be discussed. Please correct the typo in Figure 3: it should read Face and not “Fare”. Moreover, where is the alarmistic part o this proposal? The authors talk about it in the document but it is not here. Figure 4 is not referred in the text.

In Section 4 the authors present how they integrated existing frameworks, API or datasets in their work. Nothing new here.

When I reached section 5 I was expecting a solid system-wide test and evaluation. There is none. The authors tried their 3 solutions separately and hope for the best when they are combined. Furthermore, they state that this can be a good system for the elderly. How do they support that? I did not read about any elderly involved in this evaluation. As such, they cannot extract any conclusion regarding the elderly from their work. It may help. We do not know.

Section 6 should present an overall system test. Again, no elderly, repeated text and some applications are shown. The last one (Figure 18) demands that the elderly move to answer the phone. However, the authors stated that this system was good for the elderly because they did not need to move (they have difficulties) to use it. Please further explain this.

Conclusions are unsupported in my opinion. Sure that this apparently is an attractive application. But it needs to be tested to know if it makes sense from the elderly point of view. Moreover and as an important note, the elderly are not dumb or stupid, as sometimes portrayed in this document: they have a different set of challenges to overcome. Some care should exist when writing some of the things that I have read in this paper. Again, there are countless repetitions also in the conclusions section.

I will leave to the editor’s consideration if this journal accepts what I must consider to be a alpha product (untested). To consider as research, my opinion is that it should undergo real-life tests with the subjects that the authors intend to help.  

Author Response

First, we would like to deeply thank you for your precious time and in-depth and valuable feedback before stating our views on your feedback. 

We were able to think more deeply about our research thanks to your feedback and have made positive changes to the paper. We will continue to accept your high-quality review and feedback.

We have stated our views on your feedback as sequentially as possible based on the received review. We have corrected typos and grammatical errors present in the paper by paying more attention to them.

We have revised the abstract by correcting typos and adding experiment content.

We have reconstructed this paper in order to achieve maximum readability for readers. 

This paper is presented concisely by dividing the whole section and eliminating repetitive sentences.

Please see the attachment about response document for your comment.

Thank you,

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

This paper has still grammar and language issues, which need to be addressed. Furthermore, the document is  long due to constant repetitions. The paper needs a complete and detailed linguistic review.

I suggest adding material and methods section and the (preliminary) results section to improve the redability. Of the paper.

For example:

“3 Material and Methods

The following paragraphs describe…….

3.1 “Architecture of Pervasive Projection Deep-cARe System “….

3.1.1  Hardware configuration …..etc

4. Results

 

The abstract is more clear but there are no still results of the experiment or discussion. In addition, the conclusion should be revisited:

”In addition, several user interfaces were implemented according to the scenarios to provide simple, intuitive interactions between users and the proposed system. In this study, daily life support, the proposed system can be applied to various fields, including professional healthcare, treatments, and therapies for the elderly by integrating a PAR system and a deep learning framework.”

It is risky to discuss about the application fields and the intuitiveness of interface before testing the system with the elderly people .

. …..etc”

The figures from 16 to 20 are not mentioned in the text.

Author Response

First, we apologize for the delay in responding because we did professional grammar corrections. We have stated our views on your feedback as sequentially as possible based on the received review.

we would like to deeply thank you for your precious time and in-depth and valuable feedback before stating our views on your feedback.

We have stated our views on your feedback as sequentially as possible based on the received review. 

Please see the attachment about response document for your comment.

 

Thank you,

Author Response File: Author Response.pdf

Reviewer 2 Report

The revised text contains interesting ideas and experiments how help elderly people. There is potential for following investigations in future.

Author Response

We appreciate you for giving us the opportunity to strengthen our manuscript with your valuable comments and queries. We have worked hard to incorporate your feedback and hope that these revisions persuade you to accept our submission.

Reviewer 3 Report

However, the language quality is still a major handicap: less typos but many repetitions. Please send the document to a professional reviewer. Moreover, I still stand on both my major concerns from the first review: there are no tests with elderly people and therefore no conclusion can be drawn about the system's applicability. Design issues also stand: each division will have to be equipped with the system for this solution to work. The authors cannot have a discussion based on their solution’s practicability (testing is done later) and foregone an issue of this magnitude: is it practical? Is it cost-effective? There is no discussion about it.

Lastly, I understand the authors’ arguments about a work that is to be implemented in the near future and it seams to fit in the issue’s theme. However, this is still research. Therefore, no conclusions can be achieved in an untested work. Their conclusions section should be corrected accordingly.

In the future please provide a document version where the changes made are highlighted. This makes it extremely hard to know where the document was modified.

Author Response

First, we apologize for the delay in responding because we did professional grammar corrections. We have stated our views on your feedback as sequentially as possible based on the received review.

we would like to deeply thank you for your precious time and in-depth and valuable feedback before stating our views on your feedback.

We have stated our views on your feedback as sequentially as possible based on the received review. 

Please see the attachment about response document for your comment.

 

Thank you,

Author Response File: Author Response.pdf

Round 3

Reviewer 1 Report

I am pleased with your corrections and modifications. however, i have still some minor issues:

line 14--specify the acronym (Object Detection rate(DR))

line 24/line 528--what do you mean for scalability of care system? 

line 97--add the details about HoloLens(Microsoft..)

table 1 ---specify the acronyms ( MUI and SUI); What 's Wed?

line 147-148--why do you talk about hololens? 

line 164 and line 172--use the same terms  PAR module or Projection AR module 

line 170--replace Spatial UI with  SUI and Mobile UI with MUI ( they alreay specified above) 

 line 520--add the results in the conclusion section.

line 528- limitation of system and future work? is not clear 

Author Response

Dear reviewer,

First, we would like to deeply thank you for your precious time and in-depth and valuable feedback before stating our views on your feedback. We were able to think more deeply about our research thanks to your feedback and have made positive changes to the paper. We will continue to accept your high-quality review and feedback.

We have stated our views on your feedback as sequentially as possible based on the received review.

 

We once again fixed the typo. Added explanation for the abbreviations.

 

line 14--specify the acronym (Object Detection rate(DR)) 

: Fixed

line 24/line 528--what do you mean for scalability of care system? 

In this paper, scalability is expected that our system can be extended not only to elderly care but also to various fields. However, these words can be dangerous when the experiment is not completed. So we performed a replacement for the word.

Scalability -> possibility in the real world for elderly. 

 

line 97--add the details about HoloLens(Microsoft..)

: Added more information

table 1 ---specify the acronyms ( MUI and SUI); What 's Wed?

: Web mean is 'Monitor display AR'. We were fixed

 

line 147-148--why do you talk about hololens? 

: To talk about the cost-effectiveness of our system, we mentioned the cost of building HMD AR (HoloLens) and general Projection AR system.

 

line 164 and line 172--use the same terms  PAR module or Projection AR module 

: Fixed

line 170--replace Spatial UI with  SUI and Mobile UI with MUI ( they alreay specified above) 

: Fixed

 line 520--add the results in the conclusion section.

: Fixed

line 528- limitation of system and future work? is not clear 

: Fixed

 

Again, we appreciate you for giving us the opportunity to strengthen our manuscript with your valuable comments and queries. We have worked hard to incorporate your feedback and hope that these revisions persuade you to accept our submission.

 

Sincerely,

Yoon Jung Park,

Reviewer 3 Report

Thank you for all the work put in further improving this paper. Considering the responses given to each comment and suggestions and while maintaining my two concerns, I understand the authors’ argumentation and consider that this paper can contribute to the state-of-the-art but mainly be a starting point to future research in the area.

Author Response

Dear reviewer,

First, we would like to deeply thank you for your precious time and in-depth and valuable feedback before stating our views on your feedback. We were able to think more deeply about our research thanks to your feedback and have made positive changes to the paper. We will continue to accept your high-quality review and feedback.

We have stated our views on your feedback as sequentially as possible based on the received review.

 

We once again fixed the typo. Added explanation for the abbreviations.

We will continue to think about your opinions and concerns and develop our research.

The final goal of our current research is to apply the system for the real environment and the elderly. We are currently trying to contact senior hospitals and nursing homes for our system experiment.

We believe that it is most critical to design and build the fusion platform of the PAR technology and DL framework that allows us to immediately apply the care system for the elderly to cases in various real environments.

We are currently in the phase of designing and building the PAR+DL fusion platform as the first step of our research.

Also, we should deeply contemplate other technologies that we have to tackle down the road.

Further, in the future, we should verify that the proposed system can achieve a more effective elderly care system than traditional systems by actually providing it to the elderly before when applying the proposed system to real environments.

So, we are carry out must to verification of smooth execution possibility of applications, real-time execution, verification of scalability of the system, experiments in the future.

 

Thank you again for your valuable feedback.

We will experiment with scalability and applicability for our system.

To this end, various attempts will be made and more advanced research will be applied.

 

Thank you again,

Author Response File: Author Response.pdf