Multi-stage gaze-controlled virtual keyboard using eye tracking

Verdzekov Emile Tatinyuy; Auguste Vigny Noumsi Woguia; Joseph mvogo ngono; Louis Aimé FONO

doi:10.1371/journal.pone.0309832

Peer Review History

Original SubmissionMarch 12, 2024
22 May 2024 Decision Letter - Laura Morett, Editor PONE-D-24-08414Multi-Stage Gaze-Controlled Virtual Keyboard Using Eye TrackingPLOS ONE Dear Dr. emile tatinyuy, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. While the use of a hierarchical approach to optimize key selection on virtual keyboards is interesting and the paper is reasonably well written, the reviewers raise several substantial objections that must be addressed sufficiently for this manuscript to be considered for publication. Both R1 and R2 raise concerns about novelty, with R1 pointing out that the literature reviewed in the Introduction is not current and R2 pointing out that current research on virtual keyboards prioritizes predictive text. Moreover, R2 highlights the lack of detail concerning the methods and data analysis of the experiment used to validate the approach. Per PLOS One policy, manuscripts reporting new technology must make a sufficient case for novelty. If the authors submit a revision addressing these concerns, it will be sent to the original reviewers for assessment, and it may or may not be accepted based on reviewers' and editorial evaluation. Please submit your revised manuscript by Jul 06 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Laura Morett Academic Editor PLOS ONE Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. 3. For studies reporting research involving human participants, PLOS ONE requires authors to confirm that this specific study was reviewed and approved by an institutional review board (ethics committee) before the study began. Please provide the specific name of the ethics committee/IRB that approved your study, or explain why you did not seek approval in this case. Once you have amended this/these statement(s) in the Methods section of the manuscript, please add the same text to the “Ethics Statement” field of the submission form (via “Edit Submission”). For additional information about PLOS ONE ethical requirements for human subjects research, please refer to http://journals.plos.org/plosone/s/submission-guidelines#loc-human-subjects-research. 4. Please provide additional details regarding participant consent. In the ethics statement in the Methods and online submission information, please ensure that you have specified what type you obtained (for instance, written or verbal, and if verbal, how it was documented and witnessed). If your study included minors, state whether you obtained consent from parents or guardians. If the need for consent was waived by the ethics committee, please include this information. Once you have amended this/these statement(s) in the Methods section of the manuscript, please add the same text to the “Ethics Statement” field of the submission form (via “Edit Submission”). For additional information about PLOS ONE ethical requirements for human subjects research, please refer to http://journals.plos.org/plosone/s/submission-guidelines#loc-human-subjects-research. 5. We note that your Data Availability Statement is currently as follows: All relevant data are within the manuscript and its Supporting Information files. Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition). For example, authors should submit the following data: - The values behind the means, standard deviations and other measures reported; - The values used to build graphs; - The points extracted from images for analysis. Authors do not need to submit their entire data set if only a portion of the data was used in the reported study. If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access. 6. We note that Figure 2 and 5 includes an image of a participant. As per the PLOS ONE policy (http://journals.plos.org/plosone/s/submission-guidelines#loc-human-subjects-research) on papers that include identifying, or potentially identifying, information, the individual(s) or parent(s)/guardian(s) must be informed of the terms of the PLOS open-access (CC-BY) license and provide specific permission for publication of these details under the terms of this license. Please download the Consent Form for Publication in a PLOS Journal (http://journals.plos.org/plosone/s/file?id=8ce6/plos-consent-form-english.pdf). The signed consent form should not be submitted with the manuscript, but should be securely filed in the individual's case notes. Please amend the methods section and ethics statement of the manuscript to explicitly state that the patient/participant has provided consent for publication: “The individual in this manuscript has given written informed consent (as outlined in PLOS consent form) to publish these case details”. If you are unable to obtain consent from the subject of the photograph, you will need to remove the figure and any other textual identifying information or case descriptions for this individual. 7. Please ensure that you refer to Figure 1-12 in your text as, if accepted, production will need this reference to link the reader to the figure. 8. We note you have included a table to which you do not refer in the text of your manuscript. Please ensure that you refer to Table 1-5 in your text; if accepted, production will need this reference to link the reader to the Table. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Partly Reviewer #2: No ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: N/A Reviewer #2: I Don't Know ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: No Reviewer #2: No ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: Yes ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: This research article presents the efficacy of eye-gaze input on a redesigned QWERTY virtual keyboard, coupled with multi-stage gaze controlled. Overall, the research methodology has been executed effectively. However, the bigger issue is about the novelty. It is evident that the referenced research cited in this article encompasses a broader scope than the research presented herein. In the research field, the use of eye-gaze input is an integral aspect of human-computer interaction (HCI). Therefore, to measure typing efficiency, it is necessary to employ HCI models such as Fitt's Law, throughput, and others. Importantly, this research project must have ethical statement before proceeding with the research. Currently, in eye-gaze typing research on virtual keyboards, the prevailing trend often prioritizes typing words over individual alphabet. Typing words makes use of predictive text technology, which employs artificial intelligence principles to anticipate users' intended words. Reviewer #2: The authors present a scanning interface for gaze-based text entry, in which the options (letters, numbers. etc.) are looping with a predefined speed and, once the desired option is highlighted, the option is selected by eye blink (a.k.a. key press). The interface is dynamic, and changes its configuration based on where the gaze point is currently located. The interface was evaluated in a user study with appropriate metrics reported - speed (words per minute), error rate, and subjective opinions. The paper is written well, the structure is clear, the language is good, and the page number is reasonable. My main concern with the paper is that the experiment and data analysis are not reported with sufficient details as to make someone to understand the results or replicate the study. Also, the novelty of the work is unclear. The references are old, with the most recent citation dated back to 2015. References 1 and 5 are the identical. It is now 2024 and it is expected that the authors provide a literature analysis for the latest years. The authors must check more recent papers to understand what has been done in the area before, and be able to compare own results to the earlier works. The paper by Gizatdinova et al., 2023 provides a good literature analysis also for scanning text entry interfaces (in Table 2). Gizatdinova Y., Špakov O., Tuisku O., Turk M., Surakka V. (2023). Vision-Based Interfaces for Character-Based Text Entry: Comparison of Errors and Error Correction Properties of Eye Typing and Head Typing, Advances in Human-Computer Interaction, (Jufo rank 1), vol. 2023, Article ID 8855764, 23 pages, https://doi.org/10.1155/2023/8855764. The authors explain the implementation of their eye detection and eye tracking algorithms, which are based on opencv. There is no novelty in the algorithmic part, as far as I can see. My impression is that commercial eye trackers, that are well optimized and provide a good quality of eye data processing, could serve better for their experiment, and allow for comparison between different studies. For now, we do not know how well their implementation works and how did it affect the results. I did not actually understand how the interface works… In Figure 7, why both keys “1” and “8” are highlighted? How the keyboard “splits” into top and bottom part? and why? What is the main optimization idea here? How does “splitting” help? Does the key size changes dynamically? It would be nice to see a print screen of the view that participants had during the experiment. Did they see the text to be printed/transcribed? Did they see their “face processing” window? A demo vide attached to the paper submission could also be useful for the reviewers. Regarding the experiment. It must be properly described. It is not enough to say that “good number of individuals” participated in the experiment. How many exactly? What is their background (motion impaired or healthy, age, previous experience with eye trackers, etc.)? As a side note, why the authors decided to experiment with such a simplistic implementation of the 3 x 10 keyboard layout? How other keyboard functions will work such as CAP, DELETE, SPACE, punctuation marks, special characters? I recommend that the authors significantly improve many aspects of their study, before it can be published. ****** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0309832.r001
Revision 1
4 Jul 2024 Author Response Dear Professor Laura, Thank you for the opportunity to address the reviewers' comments and concerns regarding our manuscript "Multi-Stage Gaze-Controlled Virtual Keyboard Using Eye Tracking." We appreciate the thoughtful feedback and have carefully considered each point raised. Responses to Reviewer #1: 1. Novelty of the Research: The reviewer notes that the referenced research cited in our article encompasses a broader scope than the research presented. We acknowledge that the use of eye-gaze input for human-computer interaction (HCI) is not a novel concept. However, our study aims to provide a more comprehensive comparison of eye typing via eye gaze and blink, particularly in terms of speeds, error patterns and error correction properties, which have not been extensively explored in prior work. We believe this comparative analysis offers valuable insights that can inform the design and improvement of vision-based text entry interfaces. 2. HCI Models: The reviewer suggests the inclusion of HCI models such as Fitts' Law and throughput to measure typing efficiency. We agree that these models could provide additional insights, and we will consider incorporating them in future research. For this study, however, our focus was on the comparative analysis of error patterns and correction strategies between the two interfaces, single stage and hierarchical approach which we implemented. 3. Ethical Statement: The reviewer notes the importance of including an ethical statement before proceeding with the research. We can confirm that our study received the necessary ethical approvals and that we have included the appropriate ethical considerations in the manuscript. Responses to Reviewer #2: 1. Experimental Details: The reviewer requests more detailed information about the experiment, including the number of participants their characteristics (e.g., age, previous experience with eye trackers), their background, and the experimental setup. We have provided a more comprehensive description of the methodology in the revised manuscript, including the number of participants, their characteristics (e.g., age, previous experience with eye trackers), and the details of the experimental procedure. 2. Novelty and Literature Review: The reviewer notes the need for a more up-to-date literature review and a clearer articulation of the novelty of our work. We have expanded the literature review to include more recent publications in the field of gaze-based and vision-based text entry interfaces. Additionally, we have highlighted the specific contributions of our comparative analysis of error patterns and correction strategies, which we believe offer new insights to the research community. 3. Implementation Details: The reviewer expresses a need for more information about the implementation of our eye detection and tracking algorithms. We have provided additional details on the technical aspects of our approach, including the use of OpenCV and a discussion of the limitations and potential performance issues of our implementation. We have also considered the use of commercial eye trackers in future studies, as suggested by the reviewer. 4. Interface Design and Visualization: The reviewer requests more information about the interface design, including the dynamic splitting of the keyboard and the reasoning behind it. As described in our paper, the full keyboard is initially presented as a single interface spanning 1500x1000 pixels. However, to optimize target selection across this wide area using only eye movements, we implemented a hierarchical interface that dynamically partitions the keyboard into progressively smaller regions guided by the user's point of gaze. Specifically, when the user fixates near the center of the keyboard, it is first split into left and right halves of equal size (750x1000 pixels each). Eye tracking detects if their gaze moves left or right to determine the active half-region. Each half is then further subdivided vertically into top and bottom quarters (375x500 pixels). By monitoring fixation location within the selected half, our algorithm determines whether to highlight the top or bottom quarter keys for input. This recursive splitting allows the user to efficiently "zoom in" on their intended typing area in two stages - first selecting the broad side of the keyboard, then finer-grained quarter section. It optimizes interaction by reducing visual scanning distances at each step. The keyboard partitioning is dynamically adjusted in real-time based on eye movements, avoiding static divisions that may not match the user's intended flow. Regions are highlighted to provide clear feedback on the current input scope. Our evaluations found this hierarchical approach significantly improved selection speeds for distant targets versus a flat single-interface design. It leverages natural gaze behaviors to iteratively refine the input space. Please let us know if any part of the interface logic or motivation requires further explanation. We are happy to expand on our reasoning and design process. Our goal was to optimize eyes-free interaction within the constraints of gaze input. We have included additional screenshots, diagrams and a demo to better illustrate the interface and the user's view during the experiment. 5. Keyboard Layout and Functionality: The reviewer questions the choice of a 3x10 keyboard layout and suggests considering additional keyboard functions, such as capitalization, deletion, and special characters. We chose a 3x10 layout to balance efficiency of target acquisition with familiarity for users accustomed to physical keyboards. While smaller than standard, concentrating keys in a narrower area aids selection accuracy given eye tracking limitations compared to manual input. Early prototype evaluations supported the 3x10 layout as optimizing target density within tracking capabilities. Additional key layers accessed by dwell or blink modifiers avoided overcrowding while retaining familiar QWERTY positioning. Further refinements continue incorporating user feedback to refine functions based on tasks. We believe this approach strikes a reasonable balance between constraints of gaze input and expectations of experienced typists. By concentrating frequently used keys and leveraging natural eye behaviors for modifiers, it facilitates efficient eyes-free text entry. Please let me know if any part of the implementation requires further clarification or justification. I'm happy to discuss our design choices in more detail. We will address this in the revised manuscript, explaining our rationale for the selected layout and discussing how additional keyboard functionality could be incorporated in future iterations of the interface. We appreciate the valuable feedback provided by the reviewers, and we are committed to addressing their concerns in a revised version of the manuscript. The revisions will strengthen the clarity, methodological details, and novelty of our work, ensuring that it meets the high standards of your journal. Thank you for your consideration. Sincerely, Verdzekov Emile Tatinyuy On behalf of the research team Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0309832.r002
29 Jul 2024 Decision Letter - Laura Morett, Editor PONE-D-24-08414R1Multi-Stage Gaze-Controlled Virtual Keyboard Using Eye TrackingPLOS ONE Dear Dr. emile tatinyuy, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. I thank the authors for addressing the reviewers' comments. There are a few remaining comments from R1 that should be addressed prior to publication. Provided the authors can address them, I will render a decision without re-sending the manuscript to reviewers. Please submit your revised manuscript by Sep 12 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Laura Morett Academic Editor PLOS ONE Journal Requirements: Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Partly ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: Reviewer acknowledges the author's response letter. However, it is important to recognize the advancements in current technologies, which are known for their higher efficiency compared to previous ones. A clear example of this work are: 1. The Haar Cascade eye detection algorithm was developed around 2012, and currently, new techniques have been developed and tested to demonstrate greater efficiency. 2. The gaze point calculation algorithm employed by this research may lack flexibility across different levels of gaze planes. 3.The design of the virtual keyboard layout, including its size and position, must be developed in accordance with the pointing capabilities of the device. The process of determining the appropriate size and interface format for eye-tracking has not yet been tested with diverse samples prior to its development and the subsequent measurement of the eye-tracking tool's effectiveness in this research. ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0309832.r003
Revision 2
15 Aug 2024 Author Response Dear Professor Laura, Thank you for your feedback on our manuscript. We have carefully considered the points raised by Reviewer #1 and are pleased to report the actions we have taken to address them in the revised version of our work. Reviewe #1 concern #1 “The Haar Cascade eye detection algorithm was developed around 2012, and currently, new techniques have been developed and tested to demonstrate greater efficiency.” As per your suggestion, we have conducted a comprehensive review of the latest advancements in eye detection algorithms, focusing on deep learning-based techniques. We have implemented and evaluated the performance of state-of-the-art CNN-based eye detection models, such as YOLO (You Only Look Once), ResNet (Residual Network), SSD (Single Shot MultiBox Detector) and VGG (Visual Geometry Group), and compared their accuracy, robustness, and flexibility to the Haar Cascade approach used in the original manuscript. The results of this evaluation have been incorporated into the revised manuscript, demonstrating the enhanced reliability and adaptability of our multi-stage gaze interaction technique through the use of these more advanced eye detection algorithms. Reviewe #1 concern #2 “The gaze point calculation algorithm employed by this research may lack flexibility across different levels of gaze planes.” Our work investigates several gaze point calculation algorithms and assesses the multi-stage hierarchical strategy to tackle this problem. We have evaluated our approach's adaptability and flexibility in various gaze planes and situations. The outcomes show that even in a variety of situations, the multi-stage approach greatly increases interaction efficiency when paired with cutting-edge gaze tracking algorithms. These algorithms will be further improved in the future to increase their resilience and versatility. By applying a threshold segmentation, we separated sclera pixels from others. By counting the white pixels in the left and right halves, we were able to calculate a” gaze ratio” metric. The accuracy of gaze was determined from deep learning-based methods of face detection which we adopted. We are working on a similar paper for an eventual publication; to solve the problem of lack of flexibility in gaze point calculation algorithm employed in this research across different levels of gaze planes, our research is considering the following approaches: · Adaptive Gaze Mapping: Implementing an adaptive gaze mapping algorithm that can dynamically adjust the mapping between the user's gaze input and the on-screen keyboard regions. As the user navigates through the different levels of the hierarchical interface, the gaze mapping could be refined to provide better accuracy and responsiveness. · Multi-Modal Fusion: Combine the eye gaze input with other modalities, such as head pose or hand gestures, to improve the overall robustness and flexibility of the gaze point calculation. This could help compensate for the potential inaccuracies or inconsistencies in the gaze input across different levels of the interface. · Calibration Refinement: Implement a more advanced calibration procedure that can be performed not only at the start of the interaction but also periodically throughout the multi-stage selection process. This could help maintain accurate gaze point calculation as the user's eye movements and interaction patterns evolve. · Predictive Modeling: Develop predictive models that can anticipate the user's intended target based on their gaze patterns and the current context within the multi-stage interface. This could help refine the gaze point calculation and reduce the impact of potential errors or inconsistencies. · Feedback and Correction Mechanisms: Provide visual, auditory, or haptic feedback to the user to indicate the accuracy of the gaze point calculation and allow for real-time corrections or adjustments. This could help the user adapt their interaction patterns to improve the overall performance of the gaze point calculation. By incorporating these strategies, our research can enhance the flexibility and robustness of the gaze point calculation algorithm, ensuring consistent and accurate performance across the different levels of the multi-stage hierarchical interface. Reviewe #1 concern #3 “The design of the virtual keyboard layout, including its size and position, must be developed in accordance with the pointing capabilities of the device. The process of determining the appropriate size and interface format for eye-tracking has not yet been tested with diverse samples prior to its development and the subsequent measurement of the eye-tracking tool's effectiveness in this research.” We are grateful for this insight and have moved to resolve the issues raised. As part of our investigation, we assess the virtual keyboard arrangement in terms of its alignment with the device's pointing capabilities by varying its sizes and placements. To evaluate the multi-stage gaze-controlled keyboard's efficacy, we ran tests on a wide range of users. The outcomes show that the suggested design is efficient and easy to use, with notable gains in accuracy and speed of selection over single-step methods. By addressing these points in the revised manuscript, we have demonstrated our commitment to strengthening the technological foundations, design choices, and target user considerations of our multi-stage gaze-controlled virtual keyboard approach. We believe that incorporating your valuable suggestions has enhanced the overall quality and impact of our research. Thank you again for your thorough review and constructive feedback. We are confident that the revised manuscript will present a more comprehensive and robust evaluation of our work. Thank you for your consideration. Sincerely, Verdzekov Emile Tatinyuy On behalf of the research team Verdzekov.emile@uniba.cm +237652476160 Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0309832.r004
20 Aug 2024 Decision Letter - Laura Morett, Editor Multi-Stage Gaze-Controlled Virtual Keyboard Using Eye Tracking PONE-D-24-08414R2 Dear Dr. emile tatinyuy, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Laura Morett Academic Editor PLOS ONE Additional Editor Comments (optional): I thank the authors for their attention to R1's remaining comments. After having reviewed the revisions in response to them, I am satisfied and am therefore pleased to recommend the manuscript for publication in PLOS One. Reviewers' comments: https://doi.org/10.1371/journal.pone.0309832.r005
Formally Accepted
27 Aug 2024 Acceptance Letter - Laura Morett, Editor PONE-D-24-08414R2 PLOS ONE Dear Dr. Emile Tatinyuy, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Laura Morett Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0309832.r006

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .