Data mining methods of healthy indoor climate coefficients for comfortable well-being

Behrens, Grit; Schlender, Klaus; Fehring, Florian

Accès libre

Data mining methods of healthy indoor climate coefficients for comfortable well-being

,

et

01 sept. 2018

Environmental Protection and Natural Resources

Édition 29 (2018): Edition 3 (Septembre 2018)

À propos de cet article

Article précédent

Article suivant

Citez

Partagez

Télécharger la couverture

Publié en ligne: 01 sept. 2018

Pages: 7 - 12

DOI: https://doi.org/10.2478/oszn-2018-0013

Mots clés
Big data, Web-based application, indoor air quality, machine learning, artificial intelligence, neural network, ventilation behaviour

© 2018 Grit Behrens, Klaus Schlender, Florian Fehring, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Network topology of measuring sensor systems.

Example of a measuring system in an apartment.

Visual display unit logging personal room climate feelings AQF.

Interpolation and normalisation within reciprocal transformations.

Comparing suitability of AIDIN-winter according to the DIN standard.

Comparing suitability of AIextended-winter according to the air feeling.

Comparing suitability of AIDIN-summer according to the DIN standard.

Comparing suitability of AIextended-summer according to the air feeling.

Overview of minima and maxima of collected measurement datasets for winter and summer season_

Features	Unit	Winter ranges		Summer ranges
STwindow	[state]	0.00	2.00	0.00	2.00
RHin	[%]	14.27	77.10	35.71	67.45
p	[hPa]	960.33	1029.31	1006.13	1015.32
Tair	[ºC]	15.89	28.66	21.48	28.93
Wout	[km/h]	0.00	11.40	0.10	2.35
Tout	[ºC]	−10.50	17.60	14.70	32.70
RHout	[%]	22.20	99.00	30.70	86.20
CO2	[ppm]	350.00	6865.00	400.00	1230.00
Theat	[ºC]	14.13	54.44	22.56	28.94
Twall	[ºC]	8.50	27.31	24.13	32.06
AQF	[state]	0.00	2.00	0.00	2.00

Ranges of sensor data as good, neutral and bad_

DIN standard ranges for winter
Features	Unit	Range good		Range neutral		Range bad
RHin	[%]	40	68	40	62	<40	>70
Tair	[ºC]	21	23	20	24	<20	>24
CO₂	[ppm]	0	1,000	1,000	2,000	2,000	>2,000
Twall	[ºC]	13	23	23	35	>13	>35
DIN standard ranges for summer
Features	Unit	Range good		Range neutral		Range bad
RHin	[%]	40	62	40	55	<40	>70
Tair	[ºC]	23.50	25.50	22	26	<22	>26
CO₂	[ppm]	0	1,000	1,000	2,000	2,000	>2,000
Twall	[ºC]	13	23	23	35	>13	>35

Langue:: Anglais

Périodicité:: 4 fois par an
Sujets de la revue:: Sciences de la vie, Écologie

RSS Feed de la revue

Data mining methods of healthy indoor climate coefficients for comfortable well-being

Publié en ligne: 01 sept. 2018

Pages: 7 - 12

DOI: https://doi.org/10.2478/oszn-2018-0013

Mots clés
Big data, Web-based application, indoor air quality, machine learning, artificial intelligence, neural network, ventilation behaviour

© 2018 Grit Behrens, Klaus Schlender, Florian Fehring, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Overview of minima and maxima of collected measurement datasets for winter and summer season_

Ranges of sensor data as good, neutral and bad_

Data mining methods of healthy indoor climate coefficients for comfortable well-being

Grit Behrens

Klaus Schlender

Florian Fehring

Publié en ligne: 01 sept. 2018

Pages: 7 - 12

DOI: https://doi.org/10.2478/oszn-2018-0013

Mots clésBig data, Web-based application, indoor air quality, machine learning, artificial intelligence, neural network, ventilation behaviour

© 2018 Grit Behrens, Klaus Schlender, Florian Fehring, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Overview of minima and maxima of collected measurement datasets for winter and summer season_

Ranges of sensor data as good, neutral and bad_

Mots clés
Big data, Web-based application, indoor air quality, machine learning, artificial intelligence, neural network, ventilation behaviour