Disaster Recognition System for Risk Management in Socio-Technical Systems

Socio-technological risks have sparked a lot of interest all over the world. The subject of risk perpetrates and translates to more dynamic conceptualizations and approaches. The necessity for improvement from time to time has proved scantiness within the current establishment. This paper will explore the methodologies in modeling and inert socio-technical technique capable of addressing present-day underperformances. A cocktail of System Dynamics (SD) and Event trees (ET), Fault Trees (FT), and Artificial Neural Networks (ANN) has prospects of quenching the autonomous needs of various simple existing models. SD models are abstract in nature. Their insufficiency in narrowing risk components right down to the bone marrow leaves a lot to be desired about their implementation. However, their power is in computational speed, and given a less complex scenario, they could however suffice. Probabilistic Risk Analysis (PRA) methods lack autonomy and the models are somehow vague leaves a lot to be desired. The flexibility to expose, adjust, and prescribe is key to the core of modern-day technical-evolution. The hybrid model in context here strives for autonomy and scalability with time. This paradigm shift for propagating a sufficiently operative socio-technical risk management approach is a sure stride to exhaustively benefit from the PRA methods.