Abstract: Provided includes the main body part 100 in which a number of rotors 101 controlled by the control unit 110 are installed on the outside, a number of wing bodies 200 in which the elastic member 220 is opened to both sides to absorb the impact in the event of a collision with the guide 210 placed on the outer side of the rotor 101, a parachute deployment unit 300 installed on the upper side of the main body part 100 and ejecting the parachute canopy 320 upward in an emergency situation, a lower airbag ejection unit 400 installed under the main body part 100 and inflating the lower airbag 401 downward in an emergency situation, and a landing gear unit 500 installed under the main body part 100.

Abstract: A case management tool uses a novel event forecast engine. The engine leverages a flexible and extensible data structure that combines diverse formats of claims (e.g., both medical and pharmacy) and that highlights “episodes” rather than items. The engine also makes predictions with respect to “cohorts” groups, where cohorts are defined using both static and dynamic features, the latter being features that change their values based on observation periods. Multiple definitions of cohorts are implemented, and optimal cohort definitions are estimated. The engine uses rolling time window processing to extract dynamic features in the data sets, and then one or more machine learning algorithms are applied to the extracted data. Cohort-wise machine learning models preferably learn on dynamic features, which are then put together for final predictions. A validation step is applied when outcomes are later observed. Validation results update the cohort definitions as well as the model parameters.