Biometrics and Machine Learning Group
Latest news
We are pleased to announce that Mateusz Trokielewicz defended (with honors) his doctoral dissertation entitled „Iris Recognition Methods Resistant to Biological Changes in the Eye” , supervised by prof. Czajka and prof. Pacut, on the 18th of July, 2019.
Iris scanner can distinguish dead eyeballs from living ones: MIT Technology Review reports on our recent developements in the field of presentation attack detection for cadaver irises.
We are pleased to announce that Mateusz Trokielewicz received the EAB European Biometrics Research Award 2016 for research on iris recognition reliability including template aging, influence of eye diseases and post-mortem recognition.
Is That Eyeball Dead or Alive? Adam Czajka discusses the prevention of iris sensors accepting the use of a high-resolution photo of an iris or, in a grislier scenario, an actual eyeball. For full article, please see IEEE Spectrum.
yieldPlanet
Hotels’ Management Optimizer (HMO) Pricing, Forecasting, Distribution – innovative new generation software for pricing, forecasting and revenue management in hotels
Financing
Research activity for yieldPlanet S.A., financed within the POIR 1.1.1 framework
The consortium
Project conducted by the Institute of Control and Computation Engineering, Warsaw University of Technology
Timeframe
01-05-2016 – 30-04-2018
Project description
The main objective of the project is to create a prototype of innovative software solution for dynamic pricing & price forecasting for hotel management in Poland & the world Hotel
Management Optimizer (HMO). The effect of the project will be a global product type innovation. The key problem, which will be solved by the project will be helping hotel managers in answering prominent question: what price should I charge for the room today, tomorrow and next days? The planned target solution is an innovative and unique software based on selflearning algorithms for realtime processing large data sets (weather forecasts, hotel systems inputs, reservation engines, OTA (Online Travel Agents such as booking.com) data & historical prices) using neural networks and other sophisticated methods of data processing (eg. random forests, support vector machines). It will help to forecast the behavior of prices with high accuracy & be a key tool in supporting decisionmaking and thereby increase revenues and profitability of hotels. The developed product will also allow for the direct management of pricing policies of hotels with the software (publication of price developments in a wide variety of reservation systems).
Keywords
forecasting, price, hotel, big data, algorithm