Abstract
Wellbeing is often affected by health-related conditions. Among them are nutrition-related health conditions, which can significantly decrease the quality of life. We envision a system that monitors the kitchen activities of patients and that based on the detected eating behaviour could provide clinicians with indicators for improving a patient’s health. To be successful, such system has to reason about the person’s actions and goals. To address this problem, we introduce a symbolic behaviour recognition approach, called Computational Causal Behaviour Models (CCBM). CCBM combines symbolic representation of person’s behaviour with probabilistic inference to reason about one’s actions, the type of meal being prepared, and its potential health impact. To evaluate the approach, we use a cooking dataset of unscripted kitchen activities, which contains data from various sensors in a real kitchen. The results show that the approach is able to reason about the person’s cooking actions. It is also able to recognise the goal in terms of type of prepared meal and whether it is healthy. Furthermore, we compare CCBM to state-of-the-art approaches such as Hidden Markov Models (HMM) and decision trees (DT). The results show that our approach performs comparable to the HMM and DT when used for activity recognition. It outperformed the HMM for goal recognition of the type of meal with median accuracy of 1 compared to median accuracy of 0.12 when applying the HMM. Our approach also outperformed the HMM for recognising whether a meal is healthy with a median accuracy of 1 compared to median accuracy of 0.5 with the HMM.
Highlights
Introduction and MotivationOne aspect of having a healthy lifespan is the type and way in which we consume food [1].Following an unhealthy diet can cause nutrition-related diseases, which in turn can reduce the quality of life
The previous section introduces the concept of behaviour recognition and illustrates that Computational State Space Models (CSSMs) provide a convenient approach by bridging the gap between activity recognition and plan recognition
The results show that the Computational Causal Behaviour Models (CCBM) models did not significantly improve the performance for activity recognition and that the observation model had the largest effect on the accuracy
Summary
One aspect of having a healthy lifespan is the type and way in which we consume food [1]. In difference to data-driven methods, which need large amounts of training data and are only able to learn cases similar to those in the data, knowledge-based approaches can reason beyond the observations due to their underlying symbolic structure This symbolic representation defines all possible behaviours and the associated effects on the environment. In attempt to cope with these challenges, there are works that propose the combination of symbolic structure and probabilistic inference (e.g., [9,10,11]) This type of approaches are known, among other, as Computational State Space Models (CSSMs) [12]. The models have been applied on simplified problems that do not extensively address the complications caused by behaviour complexity and variability observed in real settings Another core challenge is the recognition of one’s high-level behaviour from low level sensor observations [13]. The work concludes with a discussion and outline of future work in Sections 6 and 7, respectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
