Development of artificial neural network models for predicting thermal comfort evaluation in urban parks in summer and winter

2019 ◽  
Vol 164 ◽  
pp. 106364 ◽  
Author(s):  
Sin Yi Chan ◽  
Chi Kwan Chau
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Thermal Comfort ◽  
Network Models ◽  
Urban Parks ◽  
Neural Network Models ◽  
Comfort Evaluation ◽  
Artificial Neural ◽  
Artificial Neural Network Models

Development of artificial neural network models for thermal comfort evaluation in outdoor urban spaces

2020 ◽  
Author(s):  
Eun Sub Kim ◽  
Dong Kun Lee
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Thermal Comfort ◽  
Urban Areas ◽  
Network Models ◽  
Temperate Climate ◽  
Neural Network Models ◽  
Comfort Evaluation ◽  
Artificial Neural ◽  
Artificial Neural Network Models

<p>This study has formulated artificial neural network models to predict thermal comfort evaluation in outdoor urban areas in Seoul for summer. The artificial neural network models were considerably improved by including preceptions of microclimate, perception of environmental features(e.g urban spatial characteristics and visual stimuli, etc) and personal traits as additional predictor variables. Thermal comfort in outdoor environments has been repeatedly shown to be influenced also by human perceptions and preferences. Despite numerous attempts at refining these thermal comfort, there still have been large discrepancies between the results predicted by the theoretical models and the actual thermal comfort evaluation votes. indeed Thermal comfort model using microclimatic factors including air temperature, air velocity, solar radiation and relative humidity as predictor variables could explain only 7–42% of thermal comfort evaluation votes.</p><p>Accordingly, this study aims to formulate models to predict thermal comfort evaluation in outdoor urban areas for summer in Korea, which is located in temperate climate zone. ANN models were formulated to portray intricate interrelationships among a multitude of personal traits, urban residents’ environmental perception, microclimatic and spatial perception and physiological factors. The prediction performances of the formulated ANN models were compared with those of the commonly used thermal comfort models(PMV, PET). Also, this study aims to identify important factors that influence thermal comfort evaluation in outdoor urban areas. In addition, it is intended to compare whether the important factors and the magnitude of their contributions are different in urban spatial environment. The findings should provide valuable insights for informing urban planning designers on formulating effective strategies to improve the thermal environments in outdoor urban areas in the temperate climate zone.</p>

scholarly journals A comparative study of human thermal comfort conditions in two mountainous regions in Greece during summer

2013 ◽  
Vol 12 (4) ◽  
pp. 401-408 ◽  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Thermal Comfort ◽  
Ground Surface ◽  
Network Models ◽  
Neural Network Models ◽  
Mountainous Regions ◽  
Human Thermal Comfort ◽  
Artificial Neural ◽  
Artificial Neural Network Models

Human thermal comfort conditions were determined in two mountainous regions of Greece, Gerania mountains (MG) in east continental Greece, and mountainous Nafpaktia (MN) in west continental Greece. Both regions are unexploited with considerable tourist potential. Four sites in each study region were selected on the basis of different altitude. Air temperature and humidity, 1.5 m above ground surface, were recorded simultaneously every 15 minutes by sensors with dataloggers in selected sites between 23 June and 28 August 2007. Data of the above parameters were used for the calculation of the thermohygrometric index from which thermal comfort conditions were evaluated. Also, an artificial neural network model, was applied for the THI values evaluation at the highest examined altitudes based on the respective values of the lowest examined altitudes in both MG and MN. Results showed that from 09:00 to 20:00 h, MN was found to be more suitable, in relation to MG, for tourist and recreation activities at altitudes of 1338 m. At lower altitudes, both study regions could be proposed in an equal basis for the above activities during summer. Also, for the same period, thermal comfort conditions at the highest examined altitudes of MN and MG can accurately be predicted using artificial neural network models on the basis of those at lowest examined altitudes. From 21:00 to 08:00 h, MN can be considered clearly as a better tourist destination than MG.

Automatic Electrocardiographic Analysis Using Artificial Neural Network Models

2011 ◽  
Vol 403-408 ◽  
pp. 3587-3593
Author(s):  
T.V.K. Hanumantha Rao ◽  
Saurabh Mishra ◽  
Sudhir Kumar Singh
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Radial Basis Function ◽  
Basis Function ◽  
Network Models ◽  
Neural Network Models ◽  
Radial Basis ◽  
Artificial Neural ◽  
Artificial Neural Network Models ◽  
Self Organizing

In this paper, the artificial neural network method was used for Electrocardiogram (ECG) pattern analysis. The analysis of the ECG can benefit from the wide availability of computing technology as far as features and performances as well. This paper presents some results achieved by carrying out the classification tasks by integrating the most common features of ECG analysis. Four types of ECG patterns were chosen from the MIT-BIH database to be recognized, including normal sinus rhythm, long term atrial fibrillation, sudden cardiac death and congestive heart failure. The R-R interval features were performed as the characteristic representation of the original ECG signals to be fed into the neural network models. Two types of artificial neural network models, SOM (Self- Organizing maps) and RBF (Radial Basis Function) networks were separately trained and tested for ECG pattern recognition and experimental results of the different models have been compared. The trade-off between the time consuming training of artificial neural networks and their performance is also explored. The Radial Basis Function network exhibited the best performance and reached an overall accuracy of 93% and the Kohonen Self- Organizing map network reached an overall accuracy of 87.5%.

Sign in / Sign up

Export Citation Format

Share Document