Adam Krasuski

Interactive Document Indexing Method Based on Explicit Semantic Analysis

In this article we propose a general framework incorporating semantic indexing and search of texts within scientific document repositories. In our approach, a semantic interpreter, which can be seen as a tool for automatic tagging of textual data, is interactively updated based on feedback from the users, in order to improve quality of the tags that it produces. In our experiments, we index our document corpus using the Explicit Semantic Analysis (ESA) method. In this algorithm, an external knowledge base is used to measure relatedness between words and concepts, and those assessments are utilized to assign meaningful concepts to given texts. In the paper, we explain how the weights expressing relations between particular words and concepts can be improved by interaction with users or by employment of expert knowledge. We also present some results of experiments on a document corpus acquired from the PubMed Central repository to show feasibility of our approach.

JRS’2012 Data Mining Competition: Topical Classification of Biomedical Research Papers

We summarize the JRS’2012 Data Mining Competition on “Topical Classification of Biomedical Research Papers”, held between January 2, 2012 and March 30, 2012 as an interactive on-line contest hosted on the TunedIT platform ( http://tunedit.org ). We present the scope and background of the challenge task, the evaluation procedure, the progress, and the results. We also present a scalable method for the contest data generation from biomedical research papers.

From Sensory Data to Decision Making: A Perspective on Supporting a Fire Commander

We discuss how to support commanders at the fire ground. We present a risk management framework for modelling the fire phenomena and for communicating with firefighters. We claim that appropriate derivation, selection and representation of information is the crucial aspect of decision support, as it may improve the commanders perception.

Using Domain Knowledge in Initial Stages of KDD: Optimization of Compound Object Processing

We present a set of guidelines for improving quality and efficiency in initial steps of the KDD process by utilizing various kinds of domain knowledge. We discuss how such knowledge may be used to the advantage of system developer and what kinds of improvements can be achieved. We focus on systems that incorporate creation and processing of compound data objects within the RDBMS framework. These basic considerations are illustrated with several examples of implemented database solutions.

Granular Knowledge Discovery Framework

A platform for fire & rescue incident data reporting system (IDRS) is presented as an example how the domain knowledge driven granule formation can assist in knowledge discovery and decision support. The current modeling, monitoring and reporting systems rarely take advantage of semantic background of the analyzed phenomena. We discuss how to build and tune practically meaningful models of processes by means of granules approximating their states and instances. We show how the layers of model creation should interact with lower-level layers of data preparation and transformation. We illustrate the proposed methodology by several IDRS related use cases. We also discuss the complexity of available data sources that can be utilized to make the proposed approach more useful.

Granular approach in knowledge discovery: real time blockage management in fire service

This article is focused on the recognition and prediction of blockages in the fire stations using granular computing approach. Blockage refers to the situation when all fire units are out and a new incident occurs. The core of the method is an estimation of the expected return times for the fire brigades based on the granularisation of source data. This estimation, along with some other considerations allows for evaluation of the probability of the blockage.

A framework for Dynamic Analytical Risk Management at the emergency scene. From tribal to top down in the risk management maturity model

We present a framework designed for the risk management at the emergency scene. The system that implements the framework is focused on supporting an Incident Commander during the fire and rescue actions. The system is able to assess and manage the risks with the use of sensory data, ontology modelling and reasoning techniques from AI domain. Within the framework we propose the novel approaches for perceiving and modelling the emergency scene, for reasoning, for assessing the state and the relations among the objects at the scene, for assessing the risk mitigation and for communicating the risks to the Incident Commander.

A Resemblance Based Approach for Recognition of Risks at a Fire Ground

This article focuses on a problem of a comparison between fire & rescue actions for a decision support at the fire ground. In our research, we split the actions into a set of frames which compose a timeline of a firefighting process. In our approach, the frames are represented as compound objects. We extract a set of features in order to represent these objects and we apply a comparator framework for the evaluation of similarities between the processes. The similarity constrains allow us to recognize the risks that appear during the actions. We justify our approach by showing results of a series of experiments which are based on reports describing real-life incidents.

Evaluation of a Heat Release Rate based on Massively Generated Simulations and Machine Learning Approach

We present an approach for evaluation of a heat release rate of compartment fires. The approach is based on the idea of matching the actual condition of the fire to the pre- generated CFD simulations. We use an IR image of imprint of the temperature on the ceiling as a similarity relationship between actual fire and the set of the simulations. We extract the invariants, features and similarity measures of the fires using machine learning approach. Index Terms—Inverse Fire Modelling, Artificial Intelligence, Classification, Image Processing, Fire Services

Outlier Detection by Interaction with Domain Experts

We present a method for improving the detection of outlying Fire Services reports based on domain knowledge and dialogue with Fire & Rescue domain experts. The outlying report is considered as an element which is significantly different from the remaining data. We follow the position of Professor Andrzej Skowron that effective algorithms in data mining and knowledge discovery in big data should incorporate an interaction with domain experts or/and be domain oriented. Outliers are defined and searched on the basis of domain knowledge and dialogue with experts. We face the problem of reducing high data dimensionality without loosing specificity and real complexity of reported incidents. We solve this problem by introducing a knowledge based generalization level intermediating between analyzed data and experts domain knowledge. In our approach we use the Formal Concept Analysis methods for both generation of the appropriate categories from data and as tools supporting communication with domain experts. We conducted two experiments in finding two types of outliers in which outlier detection was supported by domain experts.