Monica is the name we gave to the Integrated Distributed Autonomous Monitoring System. Monica is Hybrid’s most important objective.

Monica comprises many applications, tools and methods. Some are proprietary IP of Hybrid, some are created in collaboration with several leading R&D institutes and partners, and some were licensed from our partners.

Hybrid’s knowledge engineers and industry partners integrate the appropriate components with specific expertise and train Monica how to use its “faculties“ for predictive/diagnostic monitoring (see Virtual Clone below)

Such specialized monitoring systems are very expensive when custom designed, trained and administered. As part of a larger system, the customization is just an added cost to the basic components shared by all the customers. Monica as a service administered by Hybrid offers not only a great cost advantage, but also dependability, multiple redundancy, and leading edge R&D across the industries.

Monica is organized as multidisciplinary system with subsystems dedicated to specific industries and markets. Its holistic structure aggregates the best solutions, thus allowing serendipitous discoveries that relate them to many diverse applications.

Monica’s Unique Value Proposition is the Virtual Clone of the monitored Subject that has the ability to detect subtle changes in its Subject and react in accordance with its training, experience and acquired knowledge. Monica’s early detection and decision support gives the Subject time to undertake preventive measures and avoid the critical event.

The Virtual Clone acquires the characteristics of the Subject through observation and then introduces multi-step filtering of the incoming data. This results in evolving sense of “Self“ paralleling the real Subject, and retention of only the relevant changes observed in the Subject according to their importance. This is similar to the human memory of events: the more frequent, longer or different is the event, the longer is the memory of it.

From the technical perspective, the interesting feature of this filtering is the analysis of data in small increments, and then progressive purge of irrelevant data after deeper analysis of changes. That means smaller storage requirements and lesser amount of data being analyzed, and consequently, faster processing. The data is further filtered and sanitized, and the long-term, important “experience” is shared in the Monica’s knowledge base.