Enhancing Robot Feeding Efficiency for Children with Cerebral Palsy Using Facial Recognition Algorithms
DOI:
https://doi.org/10.26821/IJSHRE.13.03.2025.130303Keywords:
Facial Expression Recognition, Robotic Arm, Raspberry Pi Integration, Arduino Nano, RealTime Monitoring, Deep Learning AlgorithmsAbstract
Feeding difficulties are one of the most significant concerns of children with cerebral palsy. Their poor posture, muscle tone, and movement control make them more susceptible to choking and highly reliant on caregivers during feeding time.
Current feeding solutions include gastrostomy and nasogastric tube insertions. These have relieved a good number of symptoms but are associated with risk in the form of infection, skin irritation, and inhibited mobility for the child. Some studies have reported that as many as 35% of children with CP suffered from these complications. Thus, there is an immediate need for a safer, non-invasive feeding solution that enhances autonomy while maintaining caregiver oversight.
To solve these problems, the paper introduces a new robotic feeding assistant for children suffering from CP, FeedEase, through which facial landmarks can be detected and analyzed by using MediaPipe computer vision technology to establish, in real time, if the child’s mouth is open or closed. FeedEase is controlled by the Arduino Nano and fed by precise NEMA 17 stepper motors through DRV8825 drivers, and it dispenses food automatically only when the mouth is open, thus reducing the chances of choking significantly and thus hands-on intervention by a caregiver or caregiver. In initial simulations, FeedEase has shown impressive accuracy as pointed out during in-mouth-state detection measures exceeding 95% precision and applicable both in home care scenarios and places like institutional care.
The system is designed so that the caregivers will hardly intervene, allowing the young ones with CP to be more independent during meals. Earlier simulations performed quite well, achieving over 90% accuracy on mouth-state detection, thus making FeedEase applicable for both domestic and institutional care. This investigation adds on to the avowal nursing care by feeding efficiency via facial expression recognition, and also provides a novel way of recognizing hunger cues .Effectively, combining and involving machine learning approaches with computer vision in real time, FeedEase offers an easier and non-invasive mode of feeding, hence increasing independence, minimizing the caregiver’s burden and enhancing the quality of life for a child suffering from cerebral palsy.
References
. DRV8825 Stepper Motor Driver Module. (n.d.). indiamart.com ().
<https://www.indiamart.com/proddetail/drv8825-stepper-motor-driver-module- 2853587737888.html?mTd=1>.
. (). <https://www.indiamart.com/proddetail/4-8-kg-cm-nema17-stepper-motor- 23873626812.html?mTd=1>.
Clark, Cecilia and Nicole. Intelligent Clinical Augmentation: Developing a Novel Socially Assistive Robot for Children with Cerebral Palsy (2020).
Cunningham, Ryan. “Fully automated image-based estimation of postural point-features in children with cerebral palsy using deep learning”. Royal Society Open Science 6 (2019): 191011–191011.
Fang, Qinyuan. “RGB-D camera based 3D human mouth detection and tracking towards robotic feeding assistance”. Proceedings of the 11th PErvasive Technologies Related to Assistive Environments Conference (2018).
Martín-Ruiz, et al. “A virtual environment to improve the detection of oral-facial malfunction in children with cerebral palsy”. Sensors 16 (2016): 444–444.
Mashrur, Tanzim. “Assistive feeding robot for upper limb impairment-Testing and validation”.
International Journal of Advanced Robotic Systems 20 (2023):
–17298806231183571.
Meyer-Heim, Andreas. “Improvement of walking abilities after robotic-assisted locomotion training in children with cerebral palsy”. Archives of disease in childhood 94 (2009): 615–620.
Najafi, Mohammad. “Robotic assistance for children with cerebral palsy based on learning from tele-cooperative demonstration”. International Journal of Intelligent Robotics and Applications 1 (2017): 43–54.
Robles-Bykbaev and Vladimir. “Robotic assistant for support in speech therapy for children with cerebral palsy”. IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC) (2016).
Sakkos, Dimitrios. “Identification of abnormal movements in infants: A deep neural network for body part-based prediction of cerebral palsy”. IEEE Access 9 (2021): 94281–94292.
Wallard, Laura. “Robotic-assisted gait training improves walking abilities in diplegic children with cerebral palsy”. European journal of paediatric neurology 21 (2017): 557–564.
Zhu, Manli. “Interpreting deep learning based cerebral palsy prediction with channel attention”. 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) (2021).
