A distributed multilabel classification approach towards mining appliance usage in smart homes

Roy, Saikat; Mishra, Kakuli; Maulik, Ujjwal; Basu, Srinka

doi:10.1109/calcon.2017.8280779

Cited by 4 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples are found in a variety of application areas such as smart heating systems [2,12,17,24,33,36,38,39,41,43,53,64], which already found their way to the market (e.g. Nest, Heat Genius, Anna), appliance usage forecasting [3,4,8,20,29,51,60,67], dynamic power management [35,45,46,55], smart charging of electric vehicles [28,37] and fault detection [7,40,49,68]. Ventä [66] denes intelligence as products and systems that 1) continuously monitor their status and environment, 2) react and adapt to environmental and operational conditions, 3) maintain optimal performance in variable circumstances, also in exceptional cases and 4) actively communicate with the user, environment or with other products and systems.…”

Section: Introductionmentioning

confidence: 99%

Nonparametric user activity modelling and prediction

Bock

Auquilla

Nowé

et al. 2020

User Model User-Adap Inter

View full text Add to dashboard Cite

Modelling the occupancy of buildings, rooms or the usage of machines has many applications in varying elds, exemplied by the fairly recent emergence of smart, self-learning thermostats. Typically, the aim of such systems is to provide insight into user behaviour and incentivise energy savings or to automatically reduce consumption while maintaining user comfort. This paper presents a non-parametric user activity modelling algorithm, i.e. a Dirichlet process mixture (DPM) model, implemented by Gibbs sampling and the stick-breaking process, to infer the underlying patterns in user behaviour from the data. The technique deals with multiple activities, such as , of multiple users. Furthermore, it can also be used for modelling and predicting appliance usage (e.g. ).The algorithm is evaluated, both on cluster validity and predictive performance, using three case studies of varying complexity. The obtained results indicate that the method is able to properly assign the activity data into welldened clusters. Moreover, the high prediction accuracy demonstrates that these clusters can be exploited to anticipate future behaviour, facilitating the development of intelligent building management systems.

show abstract