1-3 of 3 results
-
ERAU Industrial Math Project: OneSky Optimization
PI Mihhail Berezovski
CO-I Jose Gachancipa Parga
CO-I Timothy Mitchell
CO-I Ian Young
CO-I Ian Mungovan
OneSky Flight supports the technology needs of five established private jet brands: Flexjet, Sentient Jet, SkyJet, PrivateFly, and Sirio. One key function required by these businesses is fleet optimization. The ultimate goal for the OneSky Optimization project is to create a new optimizer that works across all of the OneSky brands.
This is the exercise of matching available aircraft with trips that need to be flown for customers. There are many possible conditions, stipulations, and goals in fleet optimization depending on the business. For instance, Flexjet is a fractional ownership brand that has its own fleet of aircraft that is used to meet owner needs. However, Sentient is a charter broker brand that does not own any aircraft, and instead, works with various operators’ aircraft to meet customer needs. In working with Embry-Riddle Aeronautical University, we hope to develop our own optimization algorithms and solvers to eliminate the need for the mathematical engine, CPLEX, which is currently being used.
One strategy that has been used for this type of problem is to create a set of ten to twenty optimization algorithms, develop heuristics that take care of constraints, utilize machine learning to train the algorithms based on historical data, and create criteria for identifying the best solution from the set of results.Categories: Undergraduate
-
ERAU Industrial Math Project: Characterizing Seismic Events through Advanced Data Analytics
PI Mihhail Berezovski
CO-I Lawrence Acchione
CO-I Nathaniel Arzola Lilly
CO-I Dhairya Chokshi
CO-I Jessica Haselwood
CO-I Paige Rasmussen
CO-I Nikolaus Rentzke
The Signal Processing and Applied Mathematics research group at the Nevada National Security Site, is seeking to collaborate with students at Embry-Riddle Aeronautical University to develop advanced data analytics methods for characterizing seismic events in the southwest United States as near-field earthquakes, far-field earthquakes, or non-natural seismic events, using publicly available seismic data.
One way of monitoring whether other countries are engaging in explosives-driven testing of weapons is to measure seismicity from the events, but this is only interesting if we can correctly characterize a seismic event as an:
- earthquake,
- industrial explosives event (mining, construction, etc.),
- or an explosives test.
The first step is to simply be able to distinguish between natural and non-natural seismic events. Since the Nevada National Security Site engages in explosives-driven tests - and is in an area of active earthquake activity - it is a natural test bed for developing data analytics approaches to classifying signals as natural or non-natural. Being a "test bed" means that, in addition to the measured signals, we have some ground truth information, meaning we know when earthquakes and explosives tests actually happen.
Larger-scale experiments, like the North Korean nuclear tests, can be seen at much larger distances, so even in Nevada we can measure seismic signals from nuclear tests. Figure shows a seismic measurement in Nevada from North Korea's September 2017 nuclear test.
Primary Goal: Develop analytics methods for differentiating near- field, small earthquakes in Nevada and southern California, from far- field, large earthquakes around the world, from non-natural seismic events.
One of the primary challenges in analyzing seismic data is that the data is collected 24 hours per day, 7 days a week, but actual seismic anomalies - either natural or not - occur relatively rarely.
Thus a first step in the analytics is to develop a technique for combing through the data to find anything that looks like an anomaly. The second task will be to classify the anomalies.Categories: Undergraduate
-
NREUP: Predictive Analytics for Dynamic Pricing in Private Aviation
PI Mihhail Berezovski
CO-I Mariah Marin
CO-I Camryn Wills
CO-I Mafalda Soares
OneSky Flight supports the technology needs of four established private jet brands; Flexjet, Sentient Jet, PrivateFly, and Sirio. One key function required by these businesses is trip pricing. This is the exercise of determining the appropriate price for a trip, considering many factors. Today, this process is manual. The ultimate goal of this project is to create a dynamic pricing tool that generates an appropriate price for trips in the US and EU. There is a large part of this project that needs to be addressed: Event Calendar. The Event Calendar includes a factor for each day of the year. These factors are based on the events/holidays that happen throughout the year and their impact on the demand for days on and surrounding the events/holidays. Support for this project is provided by the National Research Experience for Undergraduates Program (NREUP) of the Mathematical Association of America funded by the NSF Grant #1950644.
OneSky Flight supports the technology needs of four established private jet brands; Flexjet, Sentient Jet, PrivateFly, and Sirio. One key function required by these businesses is trip pricing. This is the exercise of determining the appropriate price for a trip, considering many factors. Today, this process is manual. The ultimate goal of this project is to create a dynamic pricing tool that generates an appropriate price for trips in the US and EU. There is a large part of this project that needs to be addressed: Event Calendar. The Event Calendar includes a factor for each day of the year. These factors are based on the events/holidays that happen throughout the year and their impact on the demand for days on and surrounding the events/holidays.
In order to build the list of possible events that affect the intensity of flights extended data analysis was performed. Along with processing 3 years of raw flight data (~8,000,000 single flights), students did independent research on theory behind dynamic pricing. Team determined the patterns in raw data and identify anomalies as possible event, mapping them and sorting them in holidays, sport events, extreme weather events, etc. based on open sources, also recognized the local and global patterns before identification. The corresponding quantitatively model for model of dynamic pricing algorithm was developed. It is the hierarchical model with primary and secondary factors: considering normal weekly traffic, seasonal increments, and day of the week of a selected event. With given three years of flight history, model was build using any two years and validated using third on: the prediction of demand for third year was modeled and compared with third year actual data.
Support for this project is provided by the National Research Experience for Undergraduates Program (NREUP) of the Mathematical Association of America funded by the NSF Grant #1950644.
Categories: Undergraduate
1-3 of 3 results