Key Risk Factors for Polish State Fire Service: a Data Mining Competition at Knowledge Pit

Abstract

Abstract-In this paper we summarize AAIA'14 Data Mining Competition: Key risk factors for Polish State Fire Service which was held between February 3, 2014 and May 5, 2014 at the Knowledge Pit platform http://challenge.mimuw.edu.pl/. We describe the scope and background of this competition and we explain in details the evaluation procedure. We also briefly overview the results of this analytical challenge, showing the way in which those results can be beneficial to one of our other projects which is related to the problem of improving firefighter safety at a fire scene. Finally, we reveal some technical details regarding the architecture and functionalities of the Knowledge Pit competition platform, which we are developing in order to facilitate solving of practical problems that require advanced data analytics.

Parallel computation of information gain using Hadoop and MapReduce

“…Furthermore, we did not want to focus on significant preprocessing like discretization or transformation of values so we can easily compare our results with other research. The FedCSIS AAIA'14 data mining competition dataset [44] has exactly those properties. It is a sparse matrix with 50000 instances and 11852 numeric features, most of which are have the value 0 or 1.…”

Tagging Firefighter Activities at the Emergency Scene: Summary of AAIA’15 Data Mining Competition at Knowledge Pit

“…In the dataset there was left-handed subject and certain activities (for example throwing_hose) was performed in very distinctive way. [14]. This year's topic was related to real-time screening of firefighters' vital functions and monitoring of ongoing physical activities at the incident scene.…”

“…On the one hand, this task was very challenging due to a fact that different people tend to perform the same activities in different ways. On the other hand, automatically generated and accurate activity labels would facilitate monitoring of firefighters' safety and contribute to development of efficient command supporting systems [13], [14].…”

“…In such systems like described training data needs to be prepared beforehand and classification procedure needs to take into account power consumption on mobile processing unit and low-radio link throughput. This paper describes a data mining competition which was organized at the Knowledge Pit platform [14]. Special dataset collected during training exercises of firefighters cadets using custom-built BSN was prepared and made available publicly to encourage a research community to work on new methods and classification models in this particular application.…”

Predicting Dangerous Seismic Events: AAIA'16 Data Mining Challenge

“…The main difficulty in that task was related to the problem of, so called, concept drift [6] and the necessity of constructing robust representation of the available data [7]. This competition was hosted by the Knowledge Pit platform [8] which supports the organization of data mining competitions associated with data science-related conferences.…”