Real-Time Facial Emotion Detection for Therapeutic Psychiatric Interventions

Although the proposed system presents positive results, several directions are possible where the research can be taken further. The out-of-province clinical validation of the performed work which is conducted on pilot studies in a real therapeutic setting is one of the primary directions of further practice. Such considerations would support the analysis of the feasible usefulness of the ILU and VNT systems to the reducing work load of clinician, emotional sensitivity and support of the intervention measures.   It is also possible to optimize the model that will be used in the lightweight and resource-constrained devices, so optimization of the model can be considered in the future studies. The research into the efficient deep learning structures such as MobileNetV3 or EfficientNet versions could be applied to provide real-time detection of emotions during non-GPU, mobile, and embedded clinical devices as well.   The other extension that is significant is the time dynamics and multimodal information. The time-dependent patterns of perseverance of emotions, and integration of complementary cues, e.g.of physiological or behavioral manifestation, may lead to improved differentiation between short- and long-term emotion. Finally, there should also be provisions of ethical and privacy issues prior to carrying out a mass deployment. A future way forward would be to review the safe data handling protocol, the anonymity in data handling and compliance with health care regulatory framework to make sure that the facial emotion recognition technology will be utilized in a responsible and trust-worthy way in the clinical practice.

  [1]      Dada EG, Bassi JS, Chiroma H, Abdulhamid SM, Adetunmbi AO, Ajibuwa OE.Machine learning for email spam filtering: review, approaches and open research problems. Heliyon 2019;5(6):e01802. https://doi.org/10.1016/j.heliyon.2019. e01802. [3]   Hegazy O, Soliman OS, Salam MA. A machine learning model for stock market prediction. Int J Comput Sci Telecommun 2014;4(12):16–23. [4]      Beckmann JS, Lew D. Reconciling evidence-based medicine and precision medicine in the era of big data: challenges and opportunities. Genome Med 2016;8(1):134–9.   [5]   Weber GM, Mandl KD, Kohane IS. Finding the missing link for big biomedical data. Jama 2014;311(24):2479–80.   [6]   Loconsole C, Chiaradia D, Bevilacqua V, Frisoli A. Real-time emotion recognition: an improved hybrid approach for classification performance. Intelligent Computing Theory 2014:320–31.   [7]    Huang X, Kortelainen J, Zhao G, Li X, Moilanen A, Sepp€anen T, Pietik€ainen M.Multi-modal emotion analysis from facial expressions and electroencephalogram. Comput Vis Image Understand 2016;147:114–24. https://doi.org/10.1016/j. cviu.2015.09.015. [8] Raheel A, Majid M, Anwar SM. Facial expression recognition based on electroencephalography. In: 2019 2nd international conference on computing, mathematics and engineering technologies (iCoMET), Sukkur, Pakistan; 2019. p. 1–5.   [9]  Vassilis S, Herrmann Jürgen. Where do machine learning and human-computer interaction meet?. 1997.   [10]  Keltiner D, Ekrman P. In: Lewis M, Haviland Jones JM, editors. Facial expression of emotion, hand book of emotions. New York: Gilford Press; 2000. p. 236–49. [11]   Ekman P. Darwin and facial expression: a century of research in review. United State Of America: Academic Press Ishk; 2006. p. 1973. [12]   Ekman P, Friesen WV. Constants across cultures in the face and emotion. J Pers Soc Psychol 1971;17(2):124.   [13]    Ekman P. Darwin and facial expression: a century of research in review. United State Of America: Academic Press Ishk; 2006. p. 1973. [14]     Ekman P, Friesen WV, Ancoli S. Facial signs of emotional experience. J Pers Soc Psychol 1980;39:1123–34. [15]     Ekman P, Friesen WV, Ancoli S. Facial signs of emotional experience. J Pers Soc Psychol 1980;39:1123–34.