Bio-feedback controlled Electrical Muscle Stimulation (EMS) in combination with Machine Learning (ML) algorithms is a promising method for optimizing rehabilitation therapies. This study explores the integration of machine learning techniques and bio-feedback to improve the personalization and effectiveness of EMS interventions. The focus of the research is on optimizing stimulation parameters, providing real-time adaptation, and enhancing patient engagement. Electromyography (EMG) sensors are used to acquire and process muscle response data. The data is analyzed and individualized stimulation parameters are determined using machine learning algorithms, ensuring optimal muscle activation and avoiding overstimulation. By continuously monitoring EMG signals and adjusting stimulation parameters based on patient-specific responses, real-time bio-feedback is achieved. The findings indicate that bio-feedback controlled EMS with ML has the potential to enhance rehabilitation outcomes. Increased muscle activation, strength gains, and functional enhancements are the result of personalized stimulation parameters. Real-time adaptation assures the safety and efficiency of stimulation by adjusting stimulation parameters in response to changes in muscle activity. This research highlights the revolutionary effect of bio-feedback controlled EMS with ML in rehabilitation therapy. By refining stimulation parameters, providing real-time adaptation, and enhancing patient engagement, this approach provides patients with a personalized and an effective treatment option. To fully exploit the potential of this technology, additional research, validation, and clinical integration efforts are advised.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Integration of Machine Learning and Electrical Muscle Stimulation: Bio-feedback Controlled Electrical Muscle Stimulation


    Beteiligte:
    Ghosn, Karim (Autor:in)

    Erscheinungsdatum :

    2023-01-01


    Anmerkungen:

    URN:NBN:fi:amk-2023060722386


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Closed loop electrical muscle stimulation in spinal cord injured rehabilitation

    Métrailler, P. / Brodard, R. / Clavel, R. et al. | BASE | 2006

    Freier Zugriff

    Muscle Oxygen Saturation Correlates with Muscle Mechanomyography During Prolonged Electrical Stimulation-Evoked Wrist Extension Exercise

    Mohamad Saadon, Nurul Salwani / Hamzaid, Nur Azah / Hasnan, Nazirah et al. | Springer Verlag | 2019




    Chronic effects of low-frequency low-intensity electrical stimulation of stretched human muscle

    Shenkman, B. S. / Lyubaeva, E. V. / Popov, D. V. et al. | British Library Conference Proceedings | 2007