Gun Lee

Gun Lee

Senior Research Fellow

Dr. Gun Lee is a Senior Research Fellow investigating interaction and visualization methods for sharing virtual experiences in Augmented Reality (AR) and immersive 3D environments. Recently, using AR and wearable interfaces to improve remote collaborative experience has been one of his main research themes. Extending this research into sharing richer communication cues and scaling up to a larger group of participants are the next steps he is working on.

Before joining the Empathic Computing Lab, he was a Research Scientist at the Human Interface Technology Laboratory New Zealand (HIT Lab NZ, University of Canterbury), leading mobile and wearable AR research projects. Previously, he also worked at the Electronics and Telecommunications Institute (ETRI, Korea) as a researcher where he developed VR and AR technology for industrial applications, including immersive 3D visualization systems and virtual training systems.

Dr. Lee received his B.S. degree in Computer Science from Kyungpook National University (Korea), and received his Masters and Ph.D. degrees in Computer Science and Engineering at POSTECH (Korea), investigating immersive authoring method for creating VR and AR contents using 3D user interfaces.

Personal website: http://gun-a-lee.appspot.com

Projects

  • SharedSphere

    SharedSphere is a Mixed Reality based remote collaboration system which not only allows sharing a live captured immersive 360 panorama, but also supports enriched two-way communication and collaboration through sharing non-verbal communication cues, such as view awareness cues, drawn annotation, and hand gestures.

  • Augmented Mirrors

    Mirrors are physical displays that show our real world in reflection. While physical mirrors simply show what is in the real world scene, with help of digital technology, we can also alter the reality reflected in the mirror. The Augmented Mirrors project aims at exploring visualisation interaction techniques for exploiting mirrors as Augmented Reality (AR) displays. The project especially focuses on using user interface agents for guiding user interaction with Augmented Mirrors.

  • Mini-Me

    Mini-Me is an adaptive avatar for enhancing Mixed Reality (MR) remote collaboration between a local Augmented Reality (AR) user and a remote Virtual Reality (VR) user. The Mini-Me avatar represents the VR user’s gaze direction and body gestures while it transforms in size and orientation to stay within the AR user’s field of view. We tested Mini-Me in two collaborative scenarios: an asymmetric remote expert in VR assisting a local worker in AR, and a symmetric collaboration in urban planning. We found that the presence of the Mini-Me significantly improved Social Presence and the overall experience of MR collaboration.

  • Pinpointing

    Head and eye movement can be leveraged to improve the user’s interaction repertoire for wearable displays. Head movements are deliberate and accurate, and provide the current state-of-the-art pointing technique. Eye gaze can potentially be faster and more ergonomic, but suffers from low accuracy due to calibration errors and drift of wearable eye-tracking sensors. This work investigates precise, multimodal selection techniques using head motion and eye gaze. A comparison of speed and pointing accuracy reveals the relative merits of each method, including the achievable target size for robust selection. We demonstrate and discuss example applications for augmented reality, including compact menus with deep structure, and a proof-of-concept method for on-line correction of calibration drift.

  • Empathy Glasses

    We have been developing a remote collaboration system with Empathy Glasses, a head worn display designed to create a stronger feeling of empathy between remote collaborators. To do this, we combined a head- mounted see-through display with a facial expression recognition system, a heart rate sensor, and an eye tracker. The goal is to enable a remote person to see and hear from another person's perspective and to understand how they are feeling. In this way, the system shares non-verbal cues that could help increase empathy between remote collaborators.

Publications

  • Mixed Reality Collaboration through Sharing a Live Panorama
    Gun A. Lee, Theophilus Teo, Seungwon Kim, Mark Billinghurst

    Gun A. Lee, Theophilus Teo, Seungwon Kim, and Mark Billinghurst. 2017. Mixed reality collaboration through sharing a live panorama. In SIGGRAPH Asia 2017 Mobile Graphics & Interactive Applications (SA '17). ACM, New York, NY, USA, Article 14, 4 pages. http://doi.acm.org/10.1145/3132787.3139203

    @inproceedings{Lee:2017:MRC:3132787.3139203,
    author = {Lee, Gun A. and Teo, Theophilus and Kim, Seungwon and Billinghurst, Mark},
    title = {Mixed Reality Collaboration Through Sharing a Live Panorama},
    booktitle = {SIGGRAPH Asia 2017 Mobile Graphics \& Interactive Applications},
    series = {SA '17},
    year = {2017},
    isbn = {978-1-4503-5410-3},
    location = {Bangkok, Thailand},
    pages = {14:1--14:4},
    articleno = {14},
    numpages = {4},
    url = {http://doi.acm.org/10.1145/3132787.3139203},
    doi = {10.1145/3132787.3139203},
    acmid = {3139203},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {panorama, remote collaboration, shared experience},
    }
    One of the popular features on modern social networking platforms is sharing live 360 panorama video. This research investigates on how to further improve shared live panorama based collaborative experiences by applying Mixed Reality (MR) technology. SharedSphere is a wearable MR remote collaboration system. In addition to sharing a live captured immersive panorama, SharedSphere enriches the collaboration through overlaying MR visualisation of non-verbal communication cues (e.g., view awareness and gestures cues). User feedback collected through a preliminary user study indicated that sharing of live 360 panorama video was beneficial by providing a more immersive experience and supporting view independence. Users also felt that the view awareness cues were helpful for understanding the remote collaborator’s focus.
  • Mini-Me: An Adaptive Avatar for Mixed Reality Remote Collaboration
    Thammathip Piumsomboon, Gun A Lee, Jonathon D Hart, Barrett Ens, Robert W Lindeman, Bruce H Thomas, Mark Billinghurst

    Thammathip Piumsomboon, Gun A. Lee, Jonathon D. Hart, Barrett Ens, Robert W. Lindeman, Bruce H. Thomas, and Mark Billinghurst. 2018. Mini-Me: An Adaptive Avatar for Mixed Reality Remote Collaboration. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI '18). ACM, New York, NY, USA, Paper 46, 13 pages. DOI: https://doi.org/10.1145/3173574.3173620

    @inproceedings{Piumsomboon:2018:MAA:3173574.3173620,
    author = {Piumsomboon, Thammathip and Lee, Gun A. and Hart, Jonathon D. and Ens, Barrett and Lindeman, Robert W. and Thomas, Bruce H. and Billinghurst, Mark},
    title = {Mini-Me: An Adaptive Avatar for Mixed Reality Remote Collaboration},
    booktitle = {Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems},
    series = {CHI '18},
    year = {2018},
    isbn = {978-1-4503-5620-6},
    location = {Montreal QC, Canada},
    pages = {46:1--46:13},
    articleno = {46},
    numpages = {13},
    url = {http://doi.acm.org/10.1145/3173574.3173620},
    doi = {10.1145/3173574.3173620},
    acmid = {3173620},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {augmented reality, avatar, awareness, gaze, gesture, mixed reality, redirected, remote collaboration, remote embodiment, virtual reality},
    }
    [download]
    We present Mini-Me, an adaptive avatar for enhancing Mixed Reality (MR) remote collaboration between a local Augmented Reality (AR) user and a remote Virtual Reality (VR) user. The Mini-Me avatar represents the VR user's gaze direction and body gestures while it transforms in size and orientation to stay within the AR user's field of view. A user study was conducted to evaluate Mini-Me in two collaborative scenarios: an asymmetric remote expert in VR assisting a local worker in AR, and a symmetric collaboration in urban planning. We found that the presence of the Mini-Me significantly improved Social Presence and the overall experience of MR collaboration.
  • Pinpointing: Precise Head-and Eye-Based Target Selection for Augmented Reality
    Mikko Kytö, Barrett Ens, Thammathip Piumsomboon, Gun A Lee, Mark Billinghurst

    Mikko Kytö, Barrett Ens, Thammathip Piumsomboon, Gun A. Lee, and Mark Billinghurst. 2018. Pinpointing: Precise Head- and Eye-Based Target Selection for Augmented Reality. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI '18). ACM, New York, NY, USA, Paper 81, 14 pages. DOI: https://doi.org/10.1145/3173574.3173655

    @inproceedings{Kyto:2018:PPH:3173574.3173655,
    author = {Kyt\"{o}, Mikko and Ens, Barrett and Piumsomboon, Thammathip and Lee, Gun A. and Billinghurst, Mark},
    title = {Pinpointing: Precise Head- and Eye-Based Target Selection for Augmented Reality},
    booktitle = {Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems},
    series = {CHI '18},
    year = {2018},
    isbn = {978-1-4503-5620-6},
    location = {Montreal QC, Canada},
    pages = {81:1--81:14},
    articleno = {81},
    numpages = {14},
    url = {http://doi.acm.org/10.1145/3173574.3173655},
    doi = {10.1145/3173574.3173655},
    acmid = {3173655},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {augmented reality, eye tracking, gaze interaction, head-worn display, refinement techniques, target selection},
    }
    Head and eye movement can be leveraged to improve the user's interaction repertoire for wearable displays. Head movements are deliberate and accurate, and provide the current state-of-the-art pointing technique. Eye gaze can potentially be faster and more ergonomic, but suffers from low accuracy due to calibration errors and drift of wearable eye-tracking sensors. This work investigates precise, multimodal selection techniques using head motion and eye gaze. A comparison of speed and pointing accuracy reveals the relative merits of each method, including the achievable target size for robust selection. We demonstrate and discuss example applications for augmented reality, including compact menus with deep structure, and a proof-of-concept method for on-line correction of calibration drift.
  • Snow Dome: A Multi-Scale Interaction in Mixed Reality Remote Collaboration
    Thammathip Piumsomboon, Gun A Lee, Mark Billinghurst

    Thammathip Piumsomboon, Gun A. Lee, and Mark Billinghurst. 2018. Snow Dome: A Multi-Scale Interaction in Mixed Reality Remote Collaboration. In Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems (CHI EA '18). ACM, New York, NY, USA, Paper D115, 4 pages. DOI: https://doi.org/10.1145/3170427.3186495

    @inproceedings{Piumsomboon:2018:SDM:3170427.3186495,
    author = {Piumsomboon, Thammathip and Lee, Gun A. and Billinghurst, Mark},
    title = {Snow Dome: A Multi-Scale Interaction in Mixed Reality Remote Collaboration},
    booktitle = {Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems},
    series = {CHI EA '18},
    year = {2018},
    isbn = {978-1-4503-5621-3},
    location = {Montreal QC, Canada},
    pages = {D115:1--D115:4},
    articleno = {D115},
    numpages = {4},
    url = {http://doi.acm.org/10.1145/3170427.3186495},
    doi = {10.1145/3170427.3186495},
    acmid = {3186495},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {augmented reality, avatar, mixed reality, multiple, remote collaboration, remote embodiment, scale, virtual reality},
    }
    We present Snow Dome, a Mixed Reality (MR) remote collaboration application that supports a multi-scale interaction for a Virtual Reality (VR) user. We share a local Augmented Reality (AR) user's reconstructed space with a remote VR user who has an ability to scale themselves up into a giant or down into a miniature for different perspectives and interaction at that scale within the shared space.
  • Filtering Shared Social Data in AR
    Alaeddin Nassani, Huidong Bai, Gun Lee, Mark Billinghurst, Tobias Langlotz, Robert W Lindeman

    Alaeddin Nassani, Huidong Bai, Gun Lee, Mark Billinghurst, Tobias Langlotz, and Robert W. Lindeman. 2018. Filtering Shared Social Data in AR. In Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems (CHI EA '18). ACM, New York, NY, USA, Paper LBW100, 6 pages. DOI: https://doi.org/10.1145/3170427.3188609

    @inproceedings{Nassani:2018:FSS:3170427.3188609,
    author = {Nassani, Alaeddin and Bai, Huidong and Lee, Gun and Billinghurst, Mark and Langlotz, Tobias and Lindeman, Robert W.},
    title = {Filtering Shared Social Data in AR},
    booktitle = {Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems},
    series = {CHI EA '18},
    year = {2018},
    isbn = {978-1-4503-5621-3},
    location = {Montreal QC, Canada},
    pages = {LBW100:1--LBW100:6},
    articleno = {LBW100},
    numpages = {6},
    url = {http://doi.acm.org/10.1145/3170427.3188609},
    doi = {10.1145/3170427.3188609},
    acmid = {3188609},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {360 panoramas, augmented reality, live video stream, sharing social experiences, virtual avatars},
    }
    We describe a method and a prototype implementation for filtering shared social data (eg, 360 video) in a wearable Augmented Reality (eg, HoloLens) application. The data filtering is based on user-viewer relationships. For example, when sharing a 360 video, if the user has an intimate relationship with the viewer, then full fidelity (ie the 360 video) of the user's environment is visible. But if the two are strangers then only a snapshot image is shared. By varying the fidelity of the shared content, the viewer is able to focus more on the data shared by their close relations and differentiate this from other content. Also, the approach enables the sharing-user to have more control over the fidelity of the content shared with their contacts for privacy.
  • The Effect of Collaboration Styles and View Independence on Video-Mediated Remote Collaboration
    Seungwon Kim, Mark Billinghurst, Gun Lee

    Kim, S., Billinghurst, M., & Lee, G. (2018). The Effect of Collaboration Styles and View Independence on Video-Mediated Remote Collaboration. Computer Supported Cooperative Work (CSCW), 1-39.

    @Article{Kim2018,
    author="Kim, Seungwon
    and Billinghurst, Mark
    and Lee, Gun",
    title="The Effect of Collaboration Styles and View Independence on Video-Mediated Remote Collaboration",
    journal="Computer Supported Cooperative Work (CSCW)",
    year="2018",
    month="Jun",
    day="02",
    abstract="This paper investigates how different collaboration styles and view independence affect remote collaboration. Our remote collaboration system shares a live video of a local user's real-world task space with a remote user. The remote user can have an independent view or a dependent view of a shared real-world object manipulation task and can draw virtual annotations onto the real-world objects as a visual communication cue. With the system, we investigated two different collaboration styles; (1) remote expert collaboration where a remote user has the solution and gives instructions to a local partner and (2) mutual collaboration where neither user has a solution but both remote and local users share ideas and discuss ways to solve the real-world task. In the user study, the remote expert collaboration showed a number of benefits over the mutual collaboration. With the remote expert collaboration, participants had better communication from the remote user to the local user, more aligned focus between participants, and the remote participants' feeling of enjoyment and togetherness. However, the benefits were not always apparent at the local participants' end, especially with measures of enjoyment and togetherness. The independent view also had several benefits over the dependent view, such as allowing remote participants to freely navigate around the workspace while having a wider fully zoomed-out view. The benefits of the independent view were more prominent in the mutual collaboration than in the remote expert collaboration, especially in enabling the remote participants to see the workspace.",
    issn="1573-7551",
    doi="10.1007/s10606-018-9324-2",
    url="https://doi.org/10.1007/s10606-018-9324-2"
    }
    This paper investigates how different collaboration styles and view independence affect remote collaboration. Our remote collaboration system shares a live video of a local user’s real-world task space with a remote user. The remote user can have an independent view or a dependent view of a shared real-world object manipulation task and can draw virtual annotations onto the real-world objects as a visual communication cue. With the system, we investigated two different collaboration styles; (1) remote expert collaboration where a remote user has the solution and gives instructions to a local partner and (2) mutual collaboration where neither user has a solution but both remote and local users share ideas and discuss ways to solve the real-world task. In the user study, the remote expert collaboration showed a number of benefits over the mutual collaboration. With the remote expert collaboration, participants had better communication from the remote user to the local user, more aligned focus between participants, and the remote participants’ feeling of enjoyment and togetherness. However, the benefits were not always apparent at the local participants’ end, especially with measures of enjoyment and togetherness. The independent view also had several benefits over the dependent view, such as allowing remote participants to freely navigate around the workspace while having a wider fully zoomed-out view. The benefits of the independent view were more prominent in the mutual collaboration than in the remote expert collaboration, especially in enabling the remote participants to see the workspace.
  • User Interface Agents for Guiding Interaction with Augmented Virtual Mirrors
    Gun Lee, Omprakash Rudhru, Hye Sun Park, Ho Won Kim, and Mark Billinghurst

    Gun Lee, Omprakash Rudhru, Hye Sun Park, Ho Won Kim, and Mark Billinghurst. User Interface Agents for Guiding Interaction with Augmented Virtual Mirrors. In Proceedings of ICAT-EGVE 2017 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments, 109-116. http://dx.doi.org/10.2312/egve.20171347

    @inproceedings {egve.20171347,
    booktitle = {ICAT-EGVE 2017 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments},
    editor = {Robert W. Lindeman and Gerd Bruder and Daisuke Iwai},
    title = {{User Interface Agents for Guiding Interaction with Augmented Virtual Mirrors}},
    author = {Lee, Gun A. and Rudhru, Omprakash and Park, Hye Sun and Kim, Ho Won and Billinghurst, Mark},
    year = {2017},
    publisher = {The Eurographics Association},
    ISSN = {1727-530X},
    ISBN = {978-3-03868-038-3},
    DOI = {10.2312/egve.20171347}
    }
    This research investigates using user interface (UI) agents for guiding gesture based interaction with Augmented Virtual Mirrors. Compared to prior work in gesture interaction, where graphical symbols are used for guiding user interaction, we propose using UI agents. We explore two approaches for using UI agents: 1) using a UI agent as a delayed cursor and 2) using a UI agent as an interactive button. We conducted two user studies to evaluate the proposed designs. The results from the user studies show that UI agents are effective for guiding user interactions in a similar way as a traditional graphical user interface providing visual cues, while they are useful in emotionally engaging with users.
  • Improving Collaboration in Augmented Video Conference using Mutually Shared Gaze
    Gun Lee, Seungwon Kim, Youngho Lee, Arindam Dey, Thammathip Piumsomboon, Mitchell Norman and Mark Billinghurst

    Gun Lee, Seungwon Kim, Youngho Lee, Arindam Dey, Thammathip Piumsomboon, Mitchell Norman and Mark Billinghurst. 2017. Improving Collaboration in Augmented Video Conference using Mutually Shared Gaze. In Proceedings of ICAT-EGVE 2017 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments, pp. 197-204. http://dx.doi.org/10.2312/egve.20171359

    @inproceedings {egve.20171359,
    booktitle = {ICAT-EGVE 2017 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments},
    editor = {Robert W. Lindeman and Gerd Bruder and Daisuke Iwai},
    title = {{Improving Collaboration in Augmented Video Conference using Mutually Shared Gaze}},
    author = {Lee, Gun A. and Kim, Seungwon and Lee, Youngho and Dey, Arindam and Piumsomboon, Thammathip and Norman, Mitchell and Billinghurst, Mark},
    year = {2017},
    publisher = {The Eurographics Association},
    ISSN = {1727-530X},
    ISBN = {978-3-03868-038-3},
    DOI = {10.2312/egve.20171359}
    }
    To improve remote collaboration in video conferencing systems, researchers have been investigating augmenting visual cues onto a shared live video stream. In such systems, a person wearing a head-mounted display (HMD) and camera can share her view of the surrounding real-world with a remote collaborator to receive assistance on a real-world task. While this concept of augmented video conferencing (AVC) has been actively investigated, there has been little research on how sharing gaze cues might affect the collaboration in video conferencing. This paper investigates how sharing gaze in both directions between a local worker and remote helper in an AVC system affects the collaboration and communication. Using a prototype AVC system that shares the eye gaze of both users, we conducted a user study that compares four conditions with different combinations of eye gaze sharing between the two users. The results showed that sharing each other’s gaze significantly improved collaboration and communication.
  • Exploring Natural Eye-Gaze-Based Interaction for Immersive Virtual Reality
    Thammathip Piumsomboon, Gun Lee, Robert W. Lindeman and Mark Billinghurst

    Thammathip Piumsomboon, Gun Lee, Robert W. Lindeman and Mark Billinghurst. 2017. Exploring Natural Eye-Gaze-Based Interaction for Immersive Virtual Reality. In 2017 IEEE Symposium on 3D User Interfaces (3DUI), pp. 36-39. https://doi.org/10.1109/3DUI.2017.7893315

    @INPROCEEDINGS{7893315,
    author={T. Piumsomboon and G. Lee and R. W. Lindeman and M. Billinghurst},
    booktitle={2017 IEEE Symposium on 3D User Interfaces (3DUI)},
    title={Exploring natural eye-gaze-based interaction for immersive virtual reality},
    year={2017},
    volume={},
    number={},
    pages={36-39},
    keywords={gaze tracking;gesture recognition;helmet mounted displays;virtual reality;Duo-Reticles;Nod and Roll;Radial Pursuit;cluttered-object selection;eye tracking technology;eye-gaze selection;head-gesture-based interaction;head-mounted display;immersive virtual reality;inertial reticles;natural eye movements;natural eye-gaze-based interaction;smooth pursuit;vestibulo-ocular reflex;Electronic mail;Erbium;Gaze tracking;Painting;Portable computers;Resists;Two dimensional displays;H.5.2 [Information Interfaces and Presentation]: User Interfaces—Interaction styles},
    doi={10.1109/3DUI.2017.7893315},
    ISSN={},
    month={March},}
    Eye tracking technology in a head-mounted display has undergone rapid advancement in recent years, making it possible for researchers to explore new interaction techniques using natural eye movements. This paper explores three novel eye-gaze-based interaction techniques: (1) Duo-Reticles, eye-gaze selection based on eye-gaze and inertial reticles, (2) Radial Pursuit, cluttered-object selection that takes advantage of smooth pursuit, and (3) Nod and Roll, head-gesture-based interaction based on the vestibulo-ocular reflex. In an initial user study, we compare each technique against a baseline condition in a scenario that demonstrates its strengths and weaknesses.
  • Do You See What I See? The Effect of Gaze Tracking on Task Space Remote Collaboration
    Kunal Gupta, Gun A. Lee and Mark Billinghurst

    Kunal Gupta, Gun A. Lee and Mark Billinghurst. 2016. Do You See What I See? The Effect of Gaze Tracking on Task Space Remote Collaboration. IEEE Transactions on Visualization and Computer Graphics Vol.22, No.11, pp.2413-2422. https://doi.org/10.1109/TVCG.2016.2593778

    @ARTICLE{7523400,
    author={K. Gupta and G. A. Lee and M. Billinghurst},
    journal={IEEE Transactions on Visualization and Computer Graphics},
    title={Do You See What I See? The Effect of Gaze Tracking on Task Space Remote Collaboration},
    year={2016},
    volume={22},
    number={11},
    pages={2413-2422},
    keywords={cameras;gaze tracking;helmet mounted displays;eye-tracking camera;gaze tracking;head-mounted camera;head-mounted display;remote collaboration;task space remote collaboration;virtual gaze information;virtual pointer;wearable interface;Cameras;Collaboration;Computers;Gaze tracking;Head;Prototypes;Teleconferencing;Computer conferencing;Computer-supported collaborative work;teleconferencing;videoconferencing},
    doi={10.1109/TVCG.2016.2593778},
    ISSN={1077-2626},
    month={Nov},}
    We present results from research exploring the effect of sharing virtual gaze and pointing cues in a wearable interface for remote collaboration. A local worker wears a Head-mounted Camera, Eye-tracking camera and a Head-Mounted Display and shares video and virtual gaze information with a remote helper. The remote helper can provide feedback using a virtual pointer on the live video view. The prototype system was evaluated with a formal user study. Comparing four conditions, (1) NONE (no cue), (2) POINTER, (3) EYE-TRACKER and (4) BOTH (both pointer and eye-tracker cues), we observed that the task completion performance was best in the BOTH condition with a significant difference of POINTER and EYETRACKER individually. The use of eye-tracking and a pointer also significantly improved the co-presence felt between the users. We discuss the implications of this research and the limitations of the developed system that could be improved in further work.