Mitja Luštrek

An agent-based approach to care in independent living

This paper presents a multi-agent system for the care of elderly people living at home on their own, with the aim to prolong their independence. The system is composed of seven groups of agents providing a reliable, robust and flexible monitoring by sensing the user in the environment, reconstructing the position and posture to create the physical awareness of the user in the environment, reacting to critical situations, calling for help in the case of an emergency, and issuing warnings if unusual behavior is detected. The system has been tested during several on-line demonstrations.

Dynamic control in real-time heuristic search

Real-time heuristic search is a challenging type of agent-centered search because the agents planning time per action is bounded by a constant independent of problem size. A common problem that imposes such restrictions is pathfinding in modern computer games where a large number of units must plan their paths simultaneously over large maps. Common search algorithms (e.g., A*, IDA*, D*, ARA*, AD*) are inherently not real-time and may lose completeness when a constant bound is imposed on per-action planning time. Real-time search algorithms retain completeness but frequently produce unacceptably suboptimal solutions. In this paper, we extend classic and modern real-time search algorithms with an automated mechanism for dynamic depth and subgoal selection. The new algorithms remain real-time and complete. On large computer game maps, they find paths within 7% of optimal while on average expanding roughly a single state per action. This is nearly a three-fold improvement in suboptimality over the existing state-of-the-art algorithms and, at the same time, a 15-fold improvement in the amount of planning per action.

How Accurately Can Your Wrist Device Recognize Daily Activities and Detect Falls

Although wearable accelerometers can successfully recognize activities and detect falls, their adoption in real life is low because users do not want to wear additional devices. A possible solution is an accelerometer inside a wrist device/smartwatch. However, wrist placement might perform poorly in terms of accuracy due to frequent random movements of the hand. In this paper we perform a thorough, large-scale evaluation of methods for activity recognition and fall detection on four datasets. On the first two we showed that the left wrist performs better compared to the dominant right one, and also better compared to the elbow and the chest, but worse compared to the ankle, knee and belt. On the third (Opportunity) dataset, our method outperformed the related work, indicating that our feature-preprocessing creates better input data. And finally, on a real-life unlabeled dataset the recognized activities captured the subject’s daily rhythm and activities. Our fall-detection method detected all of the fast falls and minimized the false positives, achieving 85% accuracy on the first dataset. Because the other datasets did not contain fall events, only false positives were evaluated, resulting in 9 for the second, 1 for the third and 15 for the real-life dataset (57 days data).

Efficient Activity Recognition and Fall Detection Using Accelerometers

Ambient assisted living (AAL) systems need to understand the user’s situation, which makes activity recognition an important component. Falls are one of the most critical problems of the elderly, so AAL systems often incorporate fall detection. We present an activity recognition (AR) and fall detection (FD) system aiming to provide robust real-time performance. It uses two wearable accelerometers, since this is probably the most mature technology for such purpose. For the AR, we developed an architecture that combines rules to recognize postures, which ensures that the behavior of the system is predictable and robust, and classifiers trained with machine learning algorithms, which provide maximum accuracy in the cases that cannot be handled by the rules. For the FD, rules are used that take into account high accelerations associated with falls and the recognized horizontal orientation (e.g., falling is often followed by lying). The system was tested on a dataset containing a wide range of activities, two different types of falls and two events easily mistaken for falls. The F-measure of the AR was 99 %, even though it was never tested on the same persons it was trained on. The F-measure of the FD was 78 % due to the difficulty of the events to be recognized and the need for real-time performance, which made it impossible to rely on the recognition of long lying after a fall.

Behavior Analysis Based on Coordinates of Body Tags

This paper describes fall detection, activity recognition and the detection of anomalous gait in the Confidence project. The project aims to prolong the independence of the elderly by detecting falls and other types of behavior indicating a health problem. The behavior will be analyzed based on the coordinates of tags worn on the body. The coordinates will be detected with radio sensors. We describe two Confidence modules. The first one classifies the users activity into one of six classes, including falling. The second one detects walking anomalies, such as limping, dizziness and hemiplegia. The walking analysis can automatically adapt to each person by using only the examples of normal walking of that person. Both modules employ machine learning: the paper focuses on the features they use and the effect of tag placement and sensor noise on the classification accuracy. Four tags were enough for activity recognition accuracy of over 93% at moderate sensor noise, while six were needed to detect walking anomalies with the accuracy of over 90%.

Context-Based Fall Detection Using Inertial and Location Sensors

Falls are some of the most common sources of injury among the elderly. A fall is particularly critical when the elderly person is injured and cannot call for help. This problem is addressed by many fall-detection systems, but they often focus on isolated falls under restricted conditions, neglecting complex, real-life situations. In this paper a combination of body-worn inertial and location sensors for fall detection is studied. A novel context-based method that exploits the information from both types of sensors is designed. The evaluation is performed on a real-life scenario, including fast falls, slow falls and fall-like situations that are difficult to distinguish from falls. All the possible combinations of six inertial and four location sensors are tested. The results show that: (i) context-based reasoning significantly improves the performance; (ii) a combination of two types of sensors in a single physical sensor enclosure seems to be the best practical solution.

Competitive Live Evaluations of Activity-Recognition Systems

Ensuring the validity and usability of activity recognition approaches requires agreement on a set of standard evaluation methods. Due to the diversity of the sensors and other hardware employed, however, designing, implementing, and accepting standard tests is a difficult task. This article presents an initiative to evaluate activity recognition systems: a living-lab evaluation established through the annual Evaluating Ambient Assisted Living Systems through Competitive Benchmarking-Activity Recognition (EvAAL-AR) competition. In the EvAAL-AR, each team brings its own activity-recognition system; all systems are evaluated live on the same activity scenario performed by an actor. The evaluation criteria attempt to capture practical usability: recognition accuracy, user acceptance, recognition delay, installation complexity, and interoperability with ambient assisted living systems. Here, the authors discuss the competition and the competing systems, focusing on the system that achieved the best recognition accuracy, and the system that was evaluated as the best overall. The authors also discuss lessons learned from the competition and ideas for future development of the competition and of the activity recognition field in general.

Context-based ensemble method for human energy expenditure estimation

Multiple Contexts Ensemble (MCE) method to estimate the human energy expenditure (EE).MCE outperforms conventional regression approaches, ensembles and BodyMedia EE device.MCE provides better accuracy than using only the activity of the user as the context.MCE is independent of the machine learning algorithm, thus any algorithm can be used. Monitoring human energy expenditure (EE) is important in many health and sports applications, since the energy expenditure directly reflects the intensity of physical activity. The actual energy expenditure is unpractical to measure; therefore, it is often estimated from the physical activity measured with accelerometers and other sensors. Previous studies have demonstrated that using a persons activity as the context in which the EE is estimated, and using multiple sensors, improves the estimation. In this study, we go a step further by proposing a context-based reasoning method that uses multiple contexts provided by multiple sensors. The proposed Multiple Contexts Ensemble (MCE) approach first extracts multiple features from the sensor data. Each feature is used as a context for which multiple regression models are built using the remaining features as training data: for each value of the context feature, a regression model is trained on a subset of the dataset with that value. When evaluating a data sample, the models corresponding to the context (feature) values in the evaluated sample are assembled into an ensemble of regression models that estimates the EE of the user. Experiments showed that the MCE method outperforms (in terms of lower root means squared error and lower mean absolute error): (i) five single-regression approaches (linear and non-linear); (ii) two ensemble approaches: Bagging and Random subspace; (iii) an approach that uses artificial neural networks trained on accelerometer-data only; and (iv) BodyMedia (a state-of-the-art commercial EE-estimation device).

Learning Biomarkers of Pluripotent Stem Cells in Mouse

Pluripotent stem cells are able to self-renew, and to differentiate into all adult cell types. Many studies report data describing these cells, and characterize them in molecular terms. Machine learning yields classifiers that can accurately identify pluripotent stem cells, but there is a lack of studies yielding minimal sets of best biomarkers (genes/features). We assembled gene expression data of pluripotent stem cells and non-pluripotent cells from the mouse. After normalization and filtering, we applied machine learning, classifying samples into pluripotent and non-pluripotent with high cross-validated accuracy. Furthermore, to identify minimal sets of best biomarkers, we used three methods: information gain, random forests and a wrapper of genetic algorithm and support vector machine (GA/SVM). We demonstrate that the GA/SVM biomarkers work best in combination with each other; pathway and enrichment analyses show that they cover the widest variety of processes implicated in pluripotency. The GA/SVM wrapper yields best biomarkers, no matter which classification method is used. The consensus best biomarker based on the three methods is Tet1, implicated in pluripotency just recently. The best biomarker based on the GA/SVM wrapper approach alone is Fam134b, possibly a missing link between pluripotency and some standard surface markers of unknown function processed by the Golgi apparatus.

Energy expenditure estimation with wearable accelerometers

This paper presents a method for human activity recognition and energy expenditure estimation with two tri-axial accelerometers. Recognizing the activity of a person and measuring his/her energy expenditure is important for the management of several diseases. In the CHIRON project we aim to monitor congestive heart failure patients using wearable sensors and a smartphone. Our method uses a classifier for activity recognition constructed with machine learning. Attention was paid to the complexity of the attributes for machine learning, resulting in the omission of the most complex attributes in order to prolong the battery life. The recognized activity serves as an input to a classifier for energy expenditure estimation, which was also constructed with machine learning. The best-performing classifier turned out to be a composite of two activity-specific classifiers and a general classifier. Its mean absolute error was 0.91 metabolic equivalents of task (MET).