Appliance Usage Prediction for the Smart Home with an Application to Energy Demand Side Management - And Why Accuracy is not a Good Performance Metric for this Problem

Wenninger, Marc; Schmidt, Jochen; Goeller, T.

doi:10.5220/0006264401430150

Cited by 9 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This imbalance has to be dealt with. As pointed out in [67], accuracy is not an appropriate performance metric in such scenarios, as predicting the majority class will already result in relatively high scores (depending on the extent of the imbalance).…”

Section: Discussionmentioning

confidence: 99%

“…In the latter, logistic regression outperforms all other standard supervised learning classiers, including neural networks, support vector machines, decision trees and Bayesian networks. A probabilistic and markov model for appliance usage prediction is respectively used in [67] and [29]. Finally, the benets of usage proling for load shifting are illustrated in [20,61,67].…”

Section: Methods and Applicationsmentioning

confidence: 99%

“…A probabilistic and markov model for appliance usage prediction is respectively used in [67] and [29]. Finally, the benets of usage proling for load shifting are illustrated in [20,61,67].…”

Section: Methods and Applicationsmentioning

confidence: 99%

“…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%

See 3 more Smart Citations

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

Section: Discussionmentioning

confidence: 99%

Section: Methods and Applicationsmentioning

confidence: 99%

Section: Methods and Applicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Nonparametric user activity modelling and prediction

Bock

Auquilla

Nowé

et al. 2020

User Model User-Adap Inter

View full text Add to dashboard Cite

show abstract

“…Data mining tools may make this big digitalization of the healthcare environment go more smoothly. This transition with numerous smart devices generates a huge amount of data, which may be analyzed via data mining to gain a deeper understanding of people's daily life [4][5][6][7][8]. We may be able to predict human health conditions using specific smart devices based on variations in appliance usage at home.…”

Section: Introductionmentioning

confidence: 99%

innovative framework for the recognition of human activity in smart healthcare

Latchoumi¹,

Meghana²,

P³

et al. 2022

ijhs

View full text Add to dashboard Cite

Health services are one of the most difficult aspects of the massive influx of people into urban centers. With global digitization, especially in healthcare, the ability to collect, receive and present data has become a top priority. Currently, many applications in the healthcare business use Machine Learning to give individualized therapies, which will be more dynamic and efficient once personal health and predictive analytics are combined. Furthermore, machine learning-based tools aid in the treatment of patients starting at the ground level, with clinical practice diagnosis and suggestions. Massive amounts of data may be collected from smart devices in our digital age. Human activity recognition is a classification problem in which data is used to identify events performed by humans. This data is categorized and analyzed to discover patterns in the data that may be used to create future predictions. In theory, activity detection can provide significant societal benefits. Activity recognition and pattern discovery are two aspects of human activity comprehension. The first is concerned with detecting human activities accurately using a specified activity model.

show abstract