Publication

Papers at ECAI 2014

Aleš Tavčar, Boštjan Kaluža, Marcel Kvassay, Bernhard Schneider and Matjaž Gams, “Surrogate-Agent Modelling for Improved Training“, European Conference on Artificial Intelligence 2014 Jernej Zupančič, Damjan Kužnar, Boštjan Kaluža, Matjaž Gams, “Two-Stage Negotiation Protocol for Lowering the Consumption of Convexly Priced Resources“, Worksop on Intelligent Agents and Technologies for Socially Interconnected Systems ‘

Research

Daily Living Dynamics

An analysis of daily-living behavior is an important approach to assess the wellbeing of an elderly person that lives at home alone. This study focuses on approaches to monitoring an individual in the home environment by an ambient-intelligence system in order to detect anomalies in daily-living patterns. We propose a method that is based on …

Publication

UbiComp 2013: Ensembles of Multiple Sensors for Human Energy Expenditure Estimation

Authors: H. Gjoreski, B. Kaluža, M. Gams, R. Milić, and M. Luštrek 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2013) Abstract: Monitoring human energy expenditure is important in many health and sport applications, since the energy expenditure directly reflects the level of physical activity. The actual energy expenditure is unpractical to …

News, Publication

Book: Instant Weka How-to

Author: B. Kaluža Pack Publishing, UK (ISBN : 1782163867) Data mining has become one of the hottest topics in computer science, mainly due to the vast amounts of data in diverse applications such as market basket analysis, reactive business intelligence, human genome sequence mining, speech recognition, document search, and spam detection. Instant Weka How-to shows …

Publication

JAISE: Analysis of Daily-Living Dynamics

Authors: B. Kaluža and M. Gams Journal of Ambient Intelligence and Smart Environments Abstract An analysis of daily-living behavior is an important approach to assess the wellbeing of an elderly person that lives at home alone. This paper presents an approach to monitoring an individual in the home environment by an ambient-intelligence system in order …

Research

Semi-Supervised Learning

When a classifier is deployed in a particular environment, its performance could often be improved if it were adapted to that environment. We study how to adapt the initial classifier with a small set of labeled data form the new environment. We proposed a novel adaptive-training algorithm, which uses three additional classifiers to improve the …

Publication

AAMAS 2012: Detection of Suspicious Behavior from a Sparse Set of Multiagent Interactions

Authors: B. Kaluža, G. Kaminka, M. Tambe Eleventh International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012) Abstract In many multiagent domains, no single observation event is sufficient to determine that the behavior of individuals is suspicious. Instead, suspiciousness must be inferred from a combination of multiple events, where events refer to the individual’s …