Bayesian-knowledge driven ontologies: A framework for fusion of semantic knowledge under uncertainty and incompleteness.

The modeling of uncertain information is an open problem in ontology research and is a theoretical obstacle to creating a truly semantic web. Currently, ontologies often do not model uncertainty, so stochastic subject matter must either be normalized or rejected entirely. Because uncertainty is omnipresent in the real world, knowledge engineers are often faced with the dilemma of performing prohibitively labor-intensive research or running the risk of rejecting correct information and accepting incorrect information. It would be preferable if ontologies could explicitly model real-world uncertainty and incorporate it into reasoning. We present an ontology framework which is based on a seamless synthesis of description logic and probabilistic semantics. This synthesis is powered by a link between ontology assertions and random variables that allows for automated construction of a probability distribution suitable for inferencing. Furthermore, our approach defines how to represent stochastic, uncertain, or incomplete subject matter. Additionally, this paper describes how to fuse multiple conflicting ontologies into a single knowledge base that can be reasoned with using the methods of both description logic and probabilistic inferencing. This is accomplished by using probabilistic semantics to resolve conflicts between assertions, eliminating the need to delete potentially valid knowledge and perform consistency checks. In our framework, emergent inferences can be made from a fused ontology that were not present in any of the individual ontologies, producing novel insights in a given domain.

Telehealth's New Horizon: Providing Smart Hospital-Level Care in the Home.

During the COVID-19 pandemic, medical providers have expanded telehealth into daily practice, with many medical and behavioral health care visits provided remotely over video or through phone. The telehealth market was already facilitating home health care with increasing levels of sophistication before COVID-19. Among the emerging telehealth practices, telephysical therapy; teleneurology; telemental health; chronic care management of congestive heart failure, chronic obstructive pulmonary disease, diabetes; home hospice; home mechanical ventilation; and home dialysis are some of the most prominent. Home telehealth helps streamline hospital/clinic operations and ensure the safety of health care workers and patients. The authors recommend that we expand home telehealth to a comprehensive delivery of medical care across a distributed network of hospitals and homes, linking patients to health care workers through the Internet of Medical Things using in-home equipment, including smart medical monitoring devices to create a "medical smart home." This expanded telehealth capability will help doctors care for patients flexibly, remotely, and safely as a part of standard operations and during emergencies such as a pandemic. This model of "telehomecare" is already being implemented, as shown herein with examples. The authors envision a future in which providers and hospitals transition medical care delivery to the home just as, during the COVID-19 pandemic, students adapted to distance learning and adults transitioned to remote work from home. Many of our homes in the future may have a "smart medical suite" as well as a "smart home office."

HazBot: Development of a telemanipulator robot with haptics for emergency response.

OBJECTIVES: To design a remotely operated robot, "HazBot," for bioevent disaster response; specifically, to improve existing commercial robots' capabilities in handling fixed-facility hazmat incidents via a unique robot controller that allows the human operator to easily manipulate HazBot in disaster situations. DESIGN: The HazBot's design objectives were for a robot to approach a building, open doors, enter, and navigate the building. The robot's controlling device was designed to provide features not available in current robots: dexterous manipulation and enhanced sensory (touch) feedback via "haptic" technology. The design included a companion simulator to train operators on HazBot. RESULTS: The HazBot met its design goals to do several hazmat-related tasks in place of a human operator: to enter and navigate a building, passing debris and doors as necessary. HazBot's controller reduced the time for inexperienced users of manipulator robots to complete a door-opening task by 55 percent. HazBot overcame previous problems in operator control of robots, via its dexterous manipulation feature, its partially implemented haptic touch feedback, and via its companion simulator. CONCLUSIONS: The HazBot system demonstrates superior capability over existing robots: it is technically sophisticated, yet moderately priced; it has dexterous manipulation to make operator tasks easier, haptic feedback, and an excellent companion simulator. HazBot is optimized for hazmat cleanups; is mobile and scaleable; can serve in multiple environments and uncontrolled conditions; and is optimal for disaster situations. It could potentially be used in other disaster situations to deliver medicine to isolated patients, evaluate such patients, assess a downed fire fighter, etc.