• Manmeet Kaur
• Ankush Manocha

Abstract: One of the greatest difficulties in modern societies is the improvement of healthy living. The main purpose of this paper is to support those persons who they are mentally weak also for some reasons in their daily activities. Abnormal health activity detection is a noteworthy challenge in the healthcare domain, especially for those who they are not well mentally as well. So, auspicious and dependable observation is important to alleviate the negative impacts of these exercises on their lives. This paper describes and clarifies the ideas of novel healthcare-based abnormal activity detection framework for autistic patients in view of recordings sensors like cameras or video recorders. The framework screens the position and the actions of those children perceive the exercises from the ordinary day by day exercises by an algorithm, which we plan for this framework. Our system consequently sends an alert for help to the custodians of autistic patients with the patient's present state.

Keywords: Abnormal activity detection, Alarm generation, Deep learning on Healthcare, Autistic patients

"Health-Oriented Abnormality Detection and Alert Generation (HOADAG) framework for the Custodians of Autistic Patients ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 11, page no.158-169, November 2018, Available :http://www.jetir.org/papers/JETIRDS06023.pdf

"Health-Oriented Abnormality Detection and Alert Generation (HOADAG) framework for the Custodians of Autistic Patients ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 11, page no. pp158-169, November 2018, Available at : http://www.jetir.org/papers/JETIRDS06023.pdf