Using Wavelet Transformation for Prediction CO2 in Smart Home Care Within IoT for Monitor Activities of Daily Living

Vaňuš, Jan; Krestanova, Alice; Kubíček, Jan; Gorjani, Ojan Majidzadeh; Penhaker, Marek; Oczka, David

doi:10.1007/978-3-030-28374-2_43

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Measured values of nonelectrical and electrical quantities in real time using implemented KNX technology in SH (presence of persons, power consumption, temperature, relative humidity, or CO 2 concentration) need to be preprocessed and adjusted for subsequent calculations using appropriate mathematical methods (classification [10,11], recognition [12][13][14], and prediction [15]) (the prediction was performed by the ANN-based on the scaled conjugate gradient (SCG), experimental results verified high method accuracy > 90%), [16] (the prediction was performed by the ANN Bayesian regulation method (BRM) with LMS AF additive noise canceling, best accuracy was better than 95%) [17] (the prediction was performed by decision tree regression method with the accuracy of 46.25 ppm). An important area of the described chain is the suppression of additive noise from the measured and calculated waveforms of monitored quantities [18,19]. The disadvantage of using an LMS adaptive filter in an additive noise suppression application is the slow startup of the filtering process in the initial phase, depending on the step size parameter set and the adaptive filter order.…”

Section: Related Workmentioning

confidence: 99%

Wavelet-Based Filtration Procedure for Denoising the Predicted CO2 Waveforms in Smart Home within the Internet of Things

Vaňuš

Fiedorova

Kubíček

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

The operating cost minimization of smart homes can be achieved with the optimization of the management of the building’s technical functions by determination of the current occupancy status of the individual monitored spaces of a smart home. To respect the privacy of the smart home residents, indirect methods (without using cameras and microphones) are possible for occupancy recognition of space in smart homes. This article describes a newly proposed indirect method to increase the accuracy of the occupancy recognition of monitored spaces of smart homes. The proposed procedure uses the prediction of the course of CO2 concentration from operationally measured quantities (temperature indoor and relative humidity indoor) using artificial neural networks with a multilayer perceptron algorithm. The mathematical wavelet transformation method is used for additive noise canceling from the predicted course of the CO2 concentration signal with an objective increase accuracy of the prediction. The calculated accuracy of CO2 concentration waveform prediction in the additive noise-canceling application was higher than 98% in selected experiments.

show abstract