Clustering methods for occupancy prediction in smart home control

Vazquez, Felix Iglesias; Kästner, Wolfgang

doi:10.1109/isie.2011.5984350

Cited by 16 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We define the context information as follow: Data(user, time, device, operation environment, Location) and use the clustering method to obtain the habit and complex habit. We choose the Fuzzy C-means as the clustering method, because it does not need to set the cluster number in advance, and it is fit for the scene changes (Vazquez and Kastner, 2011). …”

Section: Habit Learningmentioning

confidence: 99%

Rule Generation Method in Smart Home Based on Habits

2017

Revista Tecnica De La Facultad De Ingenieria Universidad Del Zu

View full text Add to dashboard Cite

In this paper, we propose a habit-based SWRL generation and reasoning approach in smart home. Definition and recognition of habits of daily living can provide humanized smart home for assisted living application, especially for people with memory deficits. This paper presents Recognizing Habit of Daily Living (RHDL) by discovering and monitoring smart home context information. The habit and habit association of using electrical appliances are defined explicitly for the first time. The generation rules between habit/complexhabit and SWRL are designed, and the reasoning is based on the Semantic Web Rule Language (SWRL). The ontology model for the RHDL is designed and the prototype system of RHDL is implemented using protege and Jess tools.

show abstract

Section: Habit Learningmentioning

confidence: 99%

Rule Generation Method in Smart Home Based on Habits

2017

Revista Tecnica De La Facultad De Ingenieria Universidad Del Zu

View full text Add to dashboard Cite

show abstract

“…They allow a mapping from one (usually high-dimensional) space to another (usually low-dimensional) space. In previous applications, we have tested their flexibility, accuracy, local minima and variable density management capabilities in comparison with other methods [9]. XSOM [8] 1 tends to overperform SOM solutions mainly when the deployment of clustering tools is intended for pattern discovery.…”

Section: Exclusive Som (Xsom)mentioning

confidence: 99%

Behavioral Profiles for Building Energy Performance Using eXclusive SOM

Vazquez

Gaceo

Kästner

et al. 2011

Engineering Applications of Neural Networks

Self Cite

View full text Add to dashboard Cite

Abstract. The identification of user and usage profiles in the built environment is of vital importance both for energy performance analysis and smart control purposes. Clustering tools are a suitable means as they are able to discover representative patterns from a myriad of collected data. In this work, the methodology of an eXclusive Self-Organizing Map (XSOM) is proposed as an evolution of a Kohonen map with outlier rejection capabilities. As will be shown, XSOM characteristics fit perfectly with the targeted application areas.

show abstract

“…Here, the data about occupancy are obtained from long-term real databases. • The way of obtaining habit profiles is studied in [5] comparing different clustering tools in the current application. Again, real data is used for the occupancy models.…”

Section: Related Work and Previous Stepsmentioning

confidence: 99%

“…The study is performed in a simulated environment under the management of controllers based on profiles obtained through Fuzzy and XSOM algorithms (which have proven to deliver optimal results in previous tests [5]). Their performances are matched with controllers based on classic strategies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impact of user habits in smart home control

2011

Self Cite

View full text Add to dashboard Cite

Lifestyle and habits of users have a direct effect on the energy performance of dwellings and facilities. Hence, in the built environment, advanced control strategies must adapt to user behaviors trying to keep a commitment between energy consumption and comfort requirements. In previous works, the suitability of predictive control based on occupancy profiles for the optimization of HVAC systems has been shown. Resting upon this basis, the present work performs a sensitivity analysis for control strategies based on usage profiles, where the input under variation is the level of habit-regularity of users. Therefore, different hypothetical user models are created and tested. The results of this analysis provide a better understanding of how user behavior affects the energy and comfort performance in dwellings under smart control and paves the way for enhanced controller design.

show abstract

Clustering methods for occupancy prediction in smart home control

Cited by 16 publications

References 8 publications

Rule Generation Method in Smart Home Based on Habits

Rule Generation Method in Smart Home Based on Habits

Behavioral Profiles for Building Energy Performance Using eXclusive SOM

Impact of user habits in smart home control

Contact Info

Product

Resources

About