Reinforcement learning-based AI assistant and VR play therapy game for children with Down syndrome bound to wheelchairs

Joypriyanka Mariselvam; Surendran Rajendran; Youseef Alotaibi; Joypriyanka Mariselvam; Surendran Rajendran; Youseef Alotaibi

doi:10.3934/math.2023867

AIMS Mathematics

2023, Volume 8, Issue 7: 16989-17011. doi: 10.3934/math.2023867

Previous Article Next Article

Research article

Reinforcement learning-based AI assistant and VR play therapy game for children with Down syndrome bound to wheelchairs

1.
Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, 602105, India
2.
Department of Computer Science, College of Computer and Information Systems, Umm Al-Qura University, Makkah, 21955, Saudi Arabia

Received: 17 March 2023 Revised: 28 April 2023 Accepted: 08 May 2023 Published: 16 May 2023
MSC : 68Q32, 68T40, 90C25, 92D30

Some of the most significant computational ideas in neuroscience for learning behavior in response to reward and penalty are reinforcement learning algorithms. This technique can be used to train an artificial intelligent (AI) agent to serve as a virtual assistant and a helper. The goal of this study is to determine whether combining a reinforcement learning-based Virtual AI assistant with play therapy. It can benefit wheelchair-bound youngsters with Down syndrome. This study aims to employ play therapy methods and Reinforcement Learning (RL) agents to aid children with Down syndrome and help them enhance their abilities like physical and mental skills by playing games with them. This Agent is designed to be smart enough to analyze each patient's lack of ability and provide a specific set of challenges in the game to improve that ability. Increasing the game's difficulty can help players develop these skills. The agent should be able to assess each player's skill gap and tailor the game to them accordingly. The agent's job is not to make the patient victorious but to boost their morale and skill sets in areas like physical activities, intelligence, and social interaction. The primary objective is to improve the player's physical activities such as muscle reflexes, motor controls and hand-eye coordination. Here, the study concentrates on the employment of several distinct techniques for training various models. This research focuses on comparing the reinforcement learning algorithms like the Deep Q-Learning Network, QR-DQN, A3C and PPO-Actor Critic. This study demonstrates that when compared to other reinforcement algorithms, the performance of the AI helper agent is at its highest when it is trained with PPO-Actor Critic and A3C. The goal is to see if children with Down syndrome who are wheelchair-bound can benefit by combining reinforcement learning with play therapy to increase their mobility.
- artificial intelligence,
- down syndrome,
- reinforcement learning,
- virtual AI assistant deep q-network,
- asynchronous advantage actor-critic
Citation: Joypriyanka Mariselvam, Surendran Rajendran, Youseef Alotaibi. Reinforcement learning-based AI assistant and VR play therapy game for children with Down syndrome bound to wheelchairs[J]. AIMS Mathematics, 2023, 8(7): 16989-17011. doi: 10.3934/math.2023867

Related Papers:

Abstract

Some of the most significant computational ideas in neuroscience for learning behavior in response to reward and penalty are reinforcement learning algorithms. This technique can be used to train an artificial intelligent (AI) agent to serve as a virtual assistant and a helper. The goal of this study is to determine whether combining a reinforcement learning-based Virtual AI assistant with play therapy. It can benefit wheelchair-bound youngsters with Down syndrome. This study aims to employ play therapy methods and Reinforcement Learning (RL) agents to aid children with Down syndrome and help them enhance their abilities like physical and mental skills by playing games with them. This Agent is designed to be smart enough to analyze each patient's lack of ability and provide a specific set of challenges in the game to improve that ability. Increasing the game's difficulty can help players develop these skills. The agent should be able to assess each player's skill gap and tailor the game to them accordingly. The agent's job is not to make the patient victorious but to boost their morale and skill sets in areas like physical activities, intelligence, and social interaction. The primary objective is to improve the player's physical activities such as muscle reflexes, motor controls and hand-eye coordination. Here, the study concentrates on the employment of several distinct techniques for training various models. This research focuses on comparing the reinforcement learning algorithms like the Deep Q-Learning Network, QR-DQN, A3C and PPO-Actor Critic. This study demonstrates that when compared to other reinforcement algorithms, the performance of the AI helper agent is at its highest when it is trained with PPO-Actor Critic and A3C. The goal is to see if children with Down syndrome who are wheelchair-bound can benefit by combining reinforcement learning with play therapy to increase their mobility.

References

[1]	V. Oriol, I. Babuschkin, W. M. Czarnecki, M. Mathieu, A. Dudzik, J. Chung, et al., Grandmaster level in starcraft ii using multi-agent reinforcement learning, Nature, 575 (2019), 350–54, https://doi.org/10.1038/s41586-019-1724-z
[2]	Q. Shunian, Z. Li, Z. Pang, Z. Li, Y. Tao, Multi-Agent optimal control for central chiller plants using reinforcement learning and game theory, Systems, 11 (2023), 136. https://doi.org/10.3390/systems11030136 doi: 10.3390/systems11030136
[3]	S. Konstantinos, G. K. Sidiropoulos, G. A. Papakostas, Reinforcement learning in game industry-review, prospects and challenges, Appl. Sci., 13 (2023), 2443. https://doi.org/10.3390/app13042443
[4]	L. Hyun-Kyo, J. Kim, J. Heo, Y. H. Han, Federated reinforcement learning for training control policies on multiple IoT devices, Sensors, 20 (2020). https://doi.org/10.3390/s20051359
[5]	G. Yang, Y. Cheng, C. L. P. Chen, X. Wang, Proximal policy optimization with policy feedback, IEEE T. Syst. Man Cy-S., 52 (2022), 4600–4610. https://doi.org/10.1109/TSMC.2021.3098451 doi: 10.1109/TSMC.2021.3098451
[6]	D. A. Elena, F. Vallone, M. C. Zurlo, D. Marocco, SG-ACCORD: Designing virtual agents for soft skills training in the school context, Educ. Sci., 12 (2022), 174. https://doi.org/10.3390/educsci12030174 doi: 10.3390/educsci12030174
[7]	A. Elor, S. Kurniawan, Deep reinforcement learning in immersive virtual reality exergame for agent movement guidance, IEEE 8th International Conference on Serious Games and Applications for Health (SeGAH), (2020), 1–7. https://doi.org/10.1109/SeGAH49190.2020.9201901
[8]	K. A. Ogudo, R. Surendran, O. I. Khalaf, Optimal artificial intelligence based automated skin lesion detection and classification model, Comput. Syst. Sci. Eng., 44 (2023), 693–707, https://doi.org/10.32604/csse.2023.024154 doi: 10.32604/csse.2023.024154
[9]	B. Patti, T. Becker, A. Martian, K. D. Primrose, J. Wingen, Motor control outcomes following nintendo wii use by a child with down syndrome, Pediatric Physical Therapy: The Official Publication of the Section on Pediatrics of the American Physical Therapy Association, 24 (2012), 78–84. https://doi.org/10.1097/PEP.0b013e31823e05e6 doi: 10.1097/PEP.0b013e31823e05e6
[10]	C. Mario, P. M. Castilla, D. E. Mancebo, L. Aguilar, C. G. Ferreras, V. C. Payo, Automatic assessment of prosodic quality in Down syndrome: Analysis of the impact of speaker heterogeneity, NATO Adv. Sci. Instit. Series E: Appl. Sci., 9 (2019), 1440. https://doi.org/10.3390/app9071440 doi: 10.3390/app9071440
[11]	G. F. César, D. E. Mancebo, M. C. Astorgano, L. A. Cuevas, V. F. Lucas, Engaging adolescents with down syndrome in an educational video game, Int. J. Human-Comput. Int., 33 (2017), 693–712.
[12]	M. H. Lara, A. I. Martinez-García, K. Caro, Emotion4Down: A serious video game for supporting emotional awareness of people with down syndrome. In Proceedings of the 8th Mexican Conference on Human-Computer Interaction, MexIHC '21 5. New York, NY, USA: Association for Computing Machinery, 2 (2022), 1–5. https://doi.org/10.1145/3492724.3492729
[13]	M. Isys, D. G. Trevisan, C. N. Vasconcelos, Esteban, Observed interaction in games for down syndrome children, In 2015 48th Hawaii International Conference on System Sciences, (2015) 662–671. https://doi.org/10.1109/HICSS.2015.86
[14]	C. J. Mills, D. Tracey, R. Kiddle, R. Gorkin, Evaluating a virtual reality sensory room for adults with disabilities, Sci. Rep-UK., 13 (2023), 495. https://doi.org/10.1038/s41598-022-26100-6 doi: 10.1038/s41598-022-26100-6
[15]	P. Kelsey, J. L. Sherry, Parental perspectives on video game genre preferences and motivations of children with down syndrome, J. Enabling Technol., 12 (2023), 1–9. https://doi.org/10.1108/JET-08-2017-0034 doi: 10.1108/JET-08-2017-0034
[16]	R. Pedro, F. Nicolau, M. Norte, E. Zorzal, J. Botelho, V. Machado, et al., Preclinical dental students self-assessment of an improved operative dentistry virtual reality simulator with haptic feedback, Sci. Rep-UK, 13 (2023), 2823. https://doi.org/10.1038/s41598-023-29537-5
[17]	Y. Shih-Ching, W. Hwang, T. Huang, W. Liu, Y. Chen, Y. Hung, A study for the application of body sensing in assisted rehabilitation training, International Symposium on Computer, Consumer and Control, (2012), 922–925. https://doi.org/10.1109/IS3C.2012.240
[18]	P. Giovanni, A. Coronato. A Reinforcement-Learning-Based Approach for the Planning of Safety Strategies in AAL Applications, Intelligent Environments Amsterdam, (2018), 498–505. https://doi.org/10.3233/978-1-61499-874-7-498
[19]	P. Giovanni, A. Coronato, M. Naeem, G. D. Pietro, A reinforcement learning-based approach for the risk management of e-health environments: A case study. 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS). (2018), 711–716. https://doi.org/10.1109/SITIS.2018.00114
[20]	T. Thanarajan, Y. Alotaibi, S. Rajendran, K. Nagappan, Improved wolf swarm optimization with deep-learning-based movement analysis and self-regulated human activity recognition, AIMS Math., 8 (2023), 12520–12539. https://doi.org/10.3934/math.2023629 doi: 10.3934/math.2023629
[21]	S. Haejung, T. H. Laine, Influence of avatar facial appearance on users' perceived embodiment and presence in immersive virtual reality, Electronics, (2023). https://doi.org/10.3390/electronics12030583
[22]	P. Adéla, T. Morton, F. J. A. Perez-Cueto, G. Makransky, A randomized trial testing the effectiveness of virtual reality as a tool for pro environmental dietary change, Sci. Rep-UK., 12 (2022), 14315. https://doi.org/10.1038/s41598-022-18241-5 doi: 10.1038/s41598-022-18241-5
[23]	N. Takashi, H. Sato, Y. Asa, T. Koike, K. Miyata, E. Nakagawa, et al., Achieving affective human–virtual agent communication by enabling virtual agents to imitate positive expressions, Sci. Rep-UK., 10 (2020), 5977. https://doi.org/10.1038/s41598-020-62870-7
[24]	O. J. van, F. Dignum, Agent communication for believable human-like interactions between virtual characters, Cognitive Agents for Virtual Environments, (2013). 37–54. https://doi.org/10.1007/978-3-642-36444-0_3
[25]	C. Karina, I. A. Encinas-Monroy, V. L. Amado-Sanchez, O. I. Islas-Cruz, E. A. Ahumada-Solorza, L. A. Castro, Using a gesture-based videogame to support eye-hand coordination and pre-literacy skills of children with down, 79 (2020), 1–28. https://doi.org/10.1007/s11042-020-09452-x
[26]	T. Tamilvizhi, R. Surendran, K. Anbazhagan, K. Rajkumar, Quantum behaved particle swarm Optimization-Based deep transfer learning model for sugarcane leaf disease detection and classification, Math. Probl. Eng., 2022 (2022), 3452413. https://doi.org/10.1155/2022/3452413 doi: 10.1155/2022/3452413
[27]	W. Linwan, N. A. Dodoo, T. J. Wen, L. Ke, Understanding twitter conversations about artificial intelligence in advertising based on natural language processing, Int. J. Adver., 41 (2022), 685–702. https://doi.org/10.1080/02650487.2021.1920218 doi: 10.1080/02650487.2021.1920218
[28]	M. Corrales-Astorgano, Prosody training of people with down syndrome using an educational video game, In Iber SPEECH ISCA: ISCA. 2021-37, Syndrome, Multimed. Tools Appl., 79 (2021), 34101–34128. https://doi.org/10.21437/iberspeech
[29]	E. David, M. Corrales-Astorgano, V. Cardeñoso-Payo, L. Aguilar, C. González-Ferreras, P. Martínez-Castilla, et al., PRAUTOCAL Corpus: A corpus for the study of down syndrome prosodic aspects, Lang. Resour. Eval., 56 (2022), 191–224. https://doi.org/10.1007/s10579-021-09542-8
[30]	S. S. Rawat, S. Singh, Y. Alotaibi, S. Alghamdi, G. Kumar, Infrared target-background separation based on weighted nuclear norm minimization and robust principal component analysis, Mathematics, 10 (2022), 2829. https://doi.org/10.3390/math10162829 doi: 10.3390/math10162829
[31]	R. Meenakshi, R. Ponnusamy, S. Alghamdi, O. Ibrahim Khalaf, Y. Alotaibi, Development of mobile app to support the mobility of visually impaired people, Comput. Mater. Con., 73 (2022), 3473–3495. https://doi.org/10.32604/cmc.2022.028540 doi: 10.32604/cmc.2022.028540
[32]	Y. A. Alotaibi, New Meta-Heuristics Data Clustering Algorithm Based on Tabu Search and Adaptive Search Memory. Symmetry. 14 (2022), 623. https://doi.org/10.3390/sym14030623
[33]	C. Hyunji, S. Lee. Intelligent Virtual Assistant Knows Your Life (2018). http://arXiv.org/abs/1803.00466
[34]	N. Krishnaraj, S. Rajendran, Y. Alotaibi. Trust aware multi-objective metaheuristic optimization based secure route planning technique for cluster based iiot environment, IEEE Access., 10 (2022), 112686–112694. https://doi.org/10.1109/ACCESS.2022.3211971 doi: 10.1109/ACCESS.2022.3211971
[35]	S. Rajagopal, T. Thanarajan, Y. Alotaibi, S. Alghamdi, Brain tumor: Hybrid feature extraction based on UNET and 3DCNN, Comput. Syst. Sci. Eng., 45 (2023), 2093–2109. https://doi.org/10.32604/csse.2023.032488 doi: 10.32604/csse.2023.032488
[36]	R. T. Radha, R. Surendran, A. Meshal, Penguin Search Optimization Algorithm with Multi-agent Reinforcement Learning for Disease Prediction and Recommendation Model, J. Intell. Fuzzy Sys., (2023), 1–13. https://doi.org/10.3233/JIFS-223933
[37]	S. S. Rawat, S. Alghamdi, G. Kumar, Y. Alotaibi, O. I. Khalaf, L. P. Verma, Infrared small target detection based on partial sum minimization and total variation, Mathematics, 10 (2022), 671. https://doi.org/10.3390/math10040671 doi: 10.3390/math10040671
[38]	C. Taehyeok, K. Cho, Y. Sung, Approaches that use domain-specific expertise: behavioral-cloning-based advantage actor-critic in basketball games, Sci. China, Ser. A, 11 (2023), 1110. https://doi.org/10.3390/math11051110 doi: 10.3390/math11051110
[39]	F. Jie, Y. Rao, Q. Luo, J. Xu, Solving one-dimensional cutting stock problems with the deep reinforcement learning, Sci. China, Ser. A, 11 (2023), 1028. https://doi.org/10.3390/math11041028 doi: 10.3390/math11041028

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)