Mitja Lustrek

ECAI Conference 2016 Conference Paper

Continuous Live Stress Monitoring with a Wristband

• Martin Gjoreski
• Hristijan Gjoreski
• Mitja Lustrek
• Matjaz Gams

In this paper we propose a method for continuous stress monitoring using data provided by a commercial wrist device equipped with common physiological sensors and an accelerometer. The method consists of three machine-learning components: a laboratory stress-detector that detects short-term stress every 2 minutes; an activity recognizer that continuously recognizes user's activity and thus provides context information; and a context-based stress detector that first aggregates the predictions of the laboratory detector, and then exploits the user's context in order to provide the final decision in a 20 minute interval. The method was trained on 21 subjects in a laboratory setting and tested on 5 subjects in a real-life setting. The accuracy on 55 days of real-life data was 92%. The method is currently being implemented as a smartphone application, which will be demonstrated at the conference.

JBHI Journal 2016 Journal Article

Estimating Energy Expenditure With Multiple Models Using Different Wearable Sensors

• Bozidara Cvetkovic
• Radoje Milic
• Mitja Lustrek

This paper presents an approach to designing a method for the estimation of human energy expenditure (EE). The approach first evaluates different sensors and their combinations. After that, multiple regression models are trained utilizing data from different sensors. The EE estimation method designed in this way was evaluated on a dataset containing a wide range of activities. It was compared against three competing state-of-the-art approaches, including the BodyMedia Fit armband, the leading consumer EE estimation device. The results show that the proposed method outperforms the competition by up to 10. 2 percentage points.

ECAI Conference 2014 Conference Paper

Multi-objective learning of hybrid classifiers

• Rok Piltaver
• Mitja Lustrek
• Jernej Zupancic
• Saso Dzeroski
• Matjaz Gams

We propose a multi-objective machine learning approach guaranteed to find the Pareto optimal set of hybrid classification models consisting of comprehensible and incomprehensible submodels. The algorithm run-times are below 1 s for typical applications despite the exponential worst-case time complexity. The user chooses the model with the best comprehensibility-accuracy trade-off from the Pareto front which enables a well informed decision or repeats finding new Pareto fronts with modified seeds. For a classification trees as the comprehensible seed, the hybrids include single black-box model, invoked in hybrid leaves. The comprehensibility of such hybrid classifiers is measured with the proportion of examples classified by the regular leaves. We propose one simple and one computationally efficient algorithm for finding the Pareto optimal hybrid trees, starting from an initial classification tree and a black-box classifier. We evaluate the proposed algorithms empirically, comparing them to the baseline solution set, showing that they often provide valuable improvements. Furthermore, we show that the efficient algorithm outperforms the NSGA-II algorithm in terms of quality of the result set and efficiency (for this optimisation problem). Finally we show that the algorithm returns hybrid classifiers that reflect the expert's knowledge on activity recognition problem well.

ECAI Conference 2014 Conference Paper

Using multiple contexts to distinguish standing from sitting with a single accelerometer

• Hristijan Gjoreski
• Simon Kozina
• Mitja Lustrek
• Matjaz Gams

Activity recognition with a single accelerometer placed on the torso is fairly common task, but distinguishing standing from sitting in this way is very difficult because the torso is oriented the same way during both activities, and the transition between the two is very hard to classify into going down or up. We propose a novel approach based on the Multiple Contexts Ensemble (MCE) algorithm which classifies the activity with an ensemble of classifiers, each of which considers the problem in the context of a single feature. The improvement stems from using multiple viewpoints, based on accelerometer data only, designed specifically to distinguish standing from sitting. This approach improves the accuracy on the two activities by 24 percentage points compared to regular machine learning.

ECAI Conference 2012 Conference Paper

Confidence: Ubiquitous Care System to Support Independent Living

• Mitja Lustrek
• Bostjan Kaluza
• Bozidara Cvetkovic
• Erik Dovgan
• Hristijan Gjoreski
• Violeta Mirchevska
• Matjaz Gams

The Confidence system aims at helping the elderly stay independent longer by detecting falls and unusual movement which may indicate a health problem. The system uses location sensors and wearable tags to determine the coordinates of the user's body parts, and an accelerometer to detect fall impact and movement. Machine learning is combined with domain knowledge in the form of rules to recognize the user's activity. The fall detection employs a similar combination of machine learning and domain knowledge. It was tested on five atypical falls and events that can be easily mistaken for a fall. We show in the paper and demo that neither sensor type can correctly recognize all of these events on its own, but the combination of both sensor types yields highly accurate fall detection. In addition, the detection of unusual movement can observe both the user's micro-movement and macro-movement. This makes it possible for the Confidence system to detect most types of threats to the user's health and well-being manifesting in his/her movement.

ECAI Conference 2008 Conference Paper

Thinking Too Much: Pathology in Pathfinding

• Mitja Lustrek
• Vadim Bulitko

ICAPS Conference 2007 Conference Paper

Dynamic Control in Path-Planning with Real-Time Heuristic Search

• Vadim Bulitko
• Yngvi Björnsson
• Mitja Lustrek
• Jonathan Schaeffer 0001
• Sverrir Sigmundarson

Real-time heuristic search methods, such as LRTA*, are used by situated agents in applications that require the amount of planning per action to be constant-bounded regardless of the problem size. LRTA* interleaves planning and execution, with a fixed search depth being used to achieve progress towards a fixed goal. Here we generalize the algorithm to allow for a dynamically changing search depth and a dynamically changing (sub-)goal. Evaluation in path-planning on video-game maps shows that the new algorithm significantly outperforms fixed-depth, fixed-goal LRTA*. The new algorithm can achieve the same quality solutions as LRTA*, but with nine times less computation, or use the same amount of computation, but produce four times better quality solutions. These extensions make real-time heuristic search a practical choice for path-planning in computer video-games.

IJCAI Conference 2005 Conference Paper

Why Minimax Works: An Alternative Explanation

• Mitja Lustrek
• Matjaz Gams
• Ivan

In game-playing programs relying on the minimax principle, deeper searches generally produce better evaluations. Theoretical analyses, however, suggest that in many cases minimaxing amplifies the noise introduced by the heuristic function used to evaluate the leaves of the game tree, leading to what is known as pathological behavior, where deeper searches produce worse evaluations. In most of the previous research, positions were evaluated as losses or wins. Dependence between the values of positions close to each other was identified as the property of realistic game trees that eliminates the pathology and explains why minimax is successful in practice. In this paper we present an alternative explanation that does not rely on value dependence. We show that if real numbers are used for position values, position values tend to be further apart at lower levels of the game tree, which leads to a larger proportion of more extreme positions, where error is less probable. Decreased probability of error in searches to greater depths is sufficient to eliminate the pathology and no additional properties of game trees are required.