scholarly journals Artificial neural network analysis of teachers’ performance against thermal comfort

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hamdan Alzahrani ◽  
Mohammed Arif ◽  
Amit Kaushik ◽  
Jack Goulding ◽  
David Heesom
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Saudi Arabia ◽  
Relative Humidity ◽  
Thermal Comfort ◽  
Teacher Performance ◽  
Thermal Parameters ◽  
Optimal Temperature ◽  
Content Type ◽  
The Impact

PurposeThe impact of thermal comfort in educational buildings continues to be of major importance in both the design and construction phases. Given this, it is also equally important to understand and appreciate the impact of design decisions on post-occupancy performance, particularly on staff and students. This study aims to present the effect of IEQ on teachers’ performance. This study would provide thermal environment requirements to BIM-led school refurbishment projects.Design/methodology/approachThis paper presents a detailed investigation into the direct impact of thermal parameters (temperature, relative humidity and ventilation rates) on teacher performance. In doing so, the research methodological approach combines explicit mixed-methods using questionnaire surveys and physical measurements of thermal parameters to identify correlation and inference. This was conducted through a single case study using a technical college based in Saudi Arabia.FindingsFindings from this work were used to develop a model using an artificial neural network (ANN) to establish causal relationships. Research findings indicate an optimal temperature range between 23 and 25°C, with a 65% relative humidity and 0.4 m/s ventilation rate. This ratio delivered optimum results for both comfort and performance.Originality/valueThis paper presents a unique investigation into the effect of thermal comfort on teacher performance in Saudi Arabia using ANN to conduct data analysis that produced indoor environmental quality optimal temperature and relative humidity range.

Impact of COVID-19 pandemic virus on G8 countries’ financial indices based on artificial neural network

2021 ◽  
Vol 14 (1) ◽  
pp. 89-103
Author(s):  
Hazem Al-Najjar ◽  
Nadia Al-Rousan ◽  
Dania Al-Najjar ◽  
Hamzeh F. Assous ◽  
Dana Al-Najjar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Interest Rate ◽  
Performance Metrics ◽  
Pearson Correlation ◽  
Content Type ◽  
Stock Indices ◽  
Pandemic Virus ◽  
Artificial Neural ◽  
The Impact

Purpose The COVID-19 pandemic virus has affected the largest economies around the world, especially Group 8 and Group 20. The increasing numbers of confirmed and deceased cases of the COVID-19 pandemic worldwide are causing instability in stock indices every day. These changes resulted in the G8 suffering major losses due to the spread of the pandemic. This paper aims to study the impact of COVID-19 events using country lockdown announcement on the most important stock indices in G8 by using seven lockdown variables. To find the impact of the COVID-19 virus on G8, a correlation analysis and an artificial neural network model are adopted. Design/methodology/approach In this study, a Pearson correlation is used to study the strength of lockdown variables on international indices, where neural network is used to build a prediction model that can estimate the movement of stock markets independently. The neural network used two performance metrics including R2 and mean square error (MSE). Findings The results of stock indices prediction showed that R2 values of all G8 are between 0.979 and 0.990, where MSE values are between 54 and 604. The results showed that the COVID-19 events had a strong negative impact on stock movement, with the lowest point on the March of all G8 indices. Besides, the US lockdown and interest rate changes are the most affected by the G8 stock trading, followed by Germany, France and the UK. Originality/value The study has used artificial intelligent neural network to study the impact of US lockdown, decrease the interest rate in the USA and the announce of lockdown in different G8 countries.

scholarly journals Artificial Neural Network for the Thermal Comfort Index Prediction: Development of a New Simplified Algorithm

Energies ◽  
2020 ◽  
Vol 13 (17) ◽  
pp. 4500
Author(s):  
Domenico Palladino ◽  
Iole Nardi ◽  
Cinzia Buratti
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Relative Humidity ◽  
Thermal Comfort ◽  
Air Temperature ◽  
Thermal Conditions ◽  
Feed Forward Neural Network ◽  
Clothing Insulation ◽  
Artificial Neural ◽  
Simplified Algorithm

A simplified algorithm using an artificial neural network (ANN, a feed-forward neural network) for the assessment of the predicted mean vote (PMV) index in summertime was developed, using solely three input variables (namely the indoor air temperature, relative humidity, and clothing insulation), whilst low air speed (<0.1 m/s), a minimal variation of radiant temperature (25.1 °C ± 2 °C) and steady metabolism (1.2 Met) were considered. Sensitivity analysis to the number of variables and to the number of neurons were performed. The developed ANN was then compared with three proven methods used for thermal comfort prediction: (i) the International Standard; (ii) the Rohles model; (iii) the modified Rohles model. Finally, another network able to predict the indoor thermal conditions was considered: the combined calculation of the two networks was tested for the PMV prediction. The proposed algorithm allows one to better approximate the PMV index than the other models (mean error of ANN predominantly in ±0.10–±0.20 range). The accuracy of the network in PMV prediction increases when air temperature and relative humidity values fall into 21–28 °C and 30–75% ranges. When the PMV is predicted by using the combined calculation (i.e., by using the two networks), the same order of magnitude of error was found, confirming the reliability of the networks. The developed ANN could be considered as an alternative method for the simplified prediction of PMV; moreover, the new simplified algorithm can be useful in buildings’ design phase, i.e., in those cases where experimental data are not available.

scholarly journals Artificial neural network, predictor variables and sensitivity threshold for DNA methylation-based age prediction using blood samples

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Zhonghui Thong ◽  
Jolena Ying Ying Tan ◽  
Eileen Shuzhen Loo ◽  
Yu Wei Phua ◽  
Xavier Liang Shun Chan ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Regression Model ◽  
Sensitivity Threshold ◽  
Ann Model ◽  
Blood Samples ◽  
Ann Models ◽  
Artificial Neural ◽  
The Impact ◽  
Age Prediction

AbstractRegression models are often used to predict age of an individual based on methylation patterns. Artificial neural network (ANN) however was recently shown to be more accurate for age prediction. Additionally, the impact of ethnicity and sex on our previous regression model have not been studied. Furthermore, there is currently no age prediction study investigating the lower limit of input DNA at the bisulfite treatment stage prior to pyrosequencing. Herein, we evaluated both regression and ANN models, and the impact of ethnicity and sex on age prediction for 333 local blood samples using three loci on the pyrosequencing platform. Subsequently, we trained a one locus-based ANN model to reduce the amount of DNA used. We demonstrated that the ANN model has a higher accuracy of age prediction than the regression model. Additionally, we showed that ethnicity did not affect age prediction among local Chinese, Malays and Indians. Although the predicted age of males were marginally overestimated, sex did not impact the accuracy of age prediction. Lastly, we present a one locus, dual CpG model using 25 ng of input DNA that is sufficient for forensic age prediction. In conclusion, the two ANN models validated would be useful for age prediction to provide forensic intelligence leads.

Design Range of Indoor Relative Humidity in Radiant Cooling Environment

2011 ◽  
Vol 243-249 ◽  
pp. 4905-4908
Author(s):  
Xue Min Sui ◽  
Xu Zhang ◽  
Guang Hui Han
Keyword(s):  
Relative Humidity ◽  
Thermal Comfort ◽  
Mean Radiant Temperature ◽  
Design Standards ◽  
Human Thermal Comfort ◽  
Radiant Cooling ◽  
Climate Parameter ◽  
Radiant Temperature ◽  
Thermal Comfort Model ◽  
The Impact

Relative humidity is an important micro-climate parameter in radiant cooling environment. Based on the human thermal comfort model, this paper studied the effect on PMV index of relative humidity, and studied the relationship of low mean radiant temperature and relative humidity, drew the appropriate design range of indoor relative humidity for radiant cooling systems.The results show that high relative humidity can compensate for the impact on thermal comfort of low mean radiant temperature, on the premise of achieving the same thermal comfort requirements. However, because of the limited compensation range of relative humidity, together with the constraints for it due to anti-condensation of radiant terminal devices, the design range of relative humidity should not be improved, and it can still use the traditional air-conditioning design standards.

Prognosis of water levels in a moor groundwater system influenced by hydrology and water extraction using an artificial neural network 

2021 ◽  
Author(s):  
Sascha Flaig ◽  
Timothy Praditia ◽  
Alexander Kissinger ◽  
Ulrich Lang ◽  
Sergey Oladyshkin ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Squared Error ◽  
Meteorological Data ◽  
Water Levels ◽  
Typical Structure ◽  
Water Abstraction ◽  
Physical Knowledge ◽  
Artificial Neural ◽  
The Impact

&lt;p&gt;In order to prevent possible negative impacts of water abstraction in an ecologically sensitive moor south of Munich (Germany), a &amp;#8220;predictive control&amp;#8221; scheme is in place. We design an artificial neural network (ANN) to provide predictions of moor water levels and to separate hydrological from anthropogenic effects. As the moor is a dynamic system, we adopt the &amp;#8222;Long short-term memory&amp;#8220; architecture.&lt;/p&gt;&lt;p&gt;To find the best LSTM setup, we train, test and compare LSTMs with two different structures: (1) the non-recurrent one-to-one structure, where the series of inputs are accumulated and fed into the LSTM; and (2) the recurrent many-to-many structure, where inputs gradually enter the LSTM (including LSTM forecasts from previous forecast time steps). The outputs of our LSTMs then feed into a readout layer that converts the hidden states into water level predictions. We hypothesize that the recurrent structure is the better structure because it better resembles the typical structure of differential equations for dynamic systems, as they would usually be used for hydro(geo)logical systems. We evaluate the comparison with the mean squared error as test metric, and conclude that the recurrent many-to-many LSTM performs better for the analyzed complex situations. It also produces plausible predictions with reasonable accuracy for seven days prediction horizon.&lt;/p&gt;&lt;p&gt;Furthermore, we analyze the impact of preprocessing meteorological data to evapotranspiration data using typical ETA models. Inserting knowledge into the LSTM in the form of ETA models (rather than implicitly having the LSTM learn the ETA relations) leads to superior prediction results. This finding aligns well with current ideas on physically-inspired machine learning.&lt;/p&gt;&lt;p&gt;As an additional validation step, we investigate whether our ANN is able to correctly identify both anthropogenic and natural influences and their interaction. To this end, we investigate two comparable pumping events under different meteorological conditions. Results indicate that all individual and combined influences of input parameters on water levels can be represented well. The neural networks recognize correctly that the predominant precipitation and lower evapotranspiration during one pumping event leads to a lower decrease of the hydrograph.&lt;/p&gt;&lt;p&gt;To further demonstrate the capability of the trained neural network, scenarios of pumping events are created and simulated.&lt;/p&gt;&lt;p&gt;In conclusion, we show that more robust and accurate predictions of moor water levels can be obtained if available physical knowledge of the modeled system is used to design and train the neural network. The artificial neural network can be a useful instrument to assess the impact of water abstraction by quantifying the anthropogenic influence.&lt;/p&gt;

Dynamic prediction of Indian stock market: an artificial neural network approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Himanshu Goel ◽  
Narinder Pal Singh
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Stock Market ◽  
Institutional Investors ◽  
Time Series Data ◽  
Gradient Algorithm ◽  
Series Data ◽  
Content Type ◽  
Artificial Neural ◽  
Indian Stock Market

Purpose Artificial neural network (ANN) is a powerful technique to forecast the time series data such as the stock market. Therefore, this study aims to predict the Indian stock market closing price using ANNs. Design/methodology/approach The input variables identified from the literature are some macroeconomic variables and a global stock market factor. The study uses an ANN with Scaled Conjugate Gradient Algorithm (SCG) to forecast the Bombay Stock Exchange (BSE) Sensex. Findings The empirical findings reveal that the ANN model is able to achieve 93% accuracy in predicting the BSE Sensex closing prices. Moreover, the results indicate that the Morgan Stanley Capital International world index is the most important variable and the index of industrial production is the least important in predicting Sensex. Research limitations/implications The findings of the study have implications for the investors of all categories such as foreign institutional investors, domestic institutional investors and investment houses. Originality/value The novelty of this study lies in the fact that there are hardly any studies that use ANN to forecast the Indian stock market using macroeconomic indicators.

The impact of board composition and ownership structure on dividend payout policy: evidence from Saudi Arabia

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Helmi A. Boshnak
Keyword(s):  
Saudi Arabia ◽  
Ownership Structure ◽  
Dividend Policy ◽  
Payout Policy ◽  
Board Composition ◽  
Dividend Payout ◽  
Content Type ◽  
Listed Firms ◽  
Propensity To Pay ◽  
The Impact

PurposeThis study examines the impact of board composition and ownership structure variables on dividend payout policy in Saudi Arabian firms. In particular, it aims to determine the effect of board size, independence and meeting frequency, in addition to chief executive officer (CEO) duality, and state, institutional, managerial, family, and foreign ownership on both the propensity to pay dividends and dividend per share for Saudi-listed firms over the period 2016–2019.Design/methodology/approachThe paper captures dividend policy with two measures, propensity to pay dividends and dividend per share, and employs a range of regression methods (logistic, probit, ordinary least squares (OLS) and random effects regressions) along with a two-stage least squares (2SLS) model for robustness to account for heteroscedasticity, serial correlation and endogeneity issues. The data set is a large panel of 280 Saudi-listed firms over the period 2016 to 2019.FindingsThe results underline the importance of board composition and the ownership structure in explaining variations in dividend policy across Saudi firms. More specifically, there is a positive relationship between the propensity to pay dividends and board-meeting frequency, institutional ownership, firm profitability and firm age, while the degree of board independence, firm size and leverage exhibit a negative relation. Further, dividend per share is positively related to board meeting frequency, institutional ownership, foreign ownership, firm profitability and age, while it is negatively related to CEO duality, managerial ownership, and firm leverage. There is no evidence that family ownership exerts an impact on dividend payout policy in Saudi firms. The findings of this study support agency, signalling, substitute and outcome theories of dividend policy.Research limitations/implicationsThis study offers an important insight into the board characteristic and ownership structure drivers of dividend policy in the context of an emerging market. Moreover, the study has important implications for firms, managers, investors, policymakers, and regulators in Saudi Arabia.Originality/valueThis paper contributes to the existing literature by providing evidence on four board and five ownership characteristic drivers of dividend policy in Saudi Arabia as an emerging stock market, thereby improving on less comprehensive previous studies. The study recommends that investors consider board composition and ownership structure characteristics of firms as key drivers of dividend policy when making stock investment decisions to inform them about the propensity of investee firms to pay dividends and maintain a given dividend policy.

Improving the electromagnetic compatibility of electronic products by using response surface methodology and artificial neural network

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ching-Hsiang Chen ◽  
Chien-Yi Huang ◽  
Yan-Ci Huang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Response Surface Methodology ◽  
Response Surface ◽  
Electromagnetic Compatibility ◽  
Heat Dissipation ◽  
Optimal Parameter ◽  
Content Type ◽  
Early Stages ◽  
Artificial Neural

Purpose The purpose of this study is to use the Taguchi Method for parametric design in the early stages of product development. electromagnetic compatibility (EMC) issues can be considered in the early stages of product design to reduce counter-measure components, product cost and labor consumption increases due to a number of design changes in the R&D cycle and to accelerate the R&D process. Design/methodology/approach The three EMC characteristics, including radiated emission, conducted emission and fast transient impulse immunity of power, are considered response values; control factors are determined with respect to the relevant parameters for printed circuit board and mechanical design of the product and peripheral devices used in conjunction with the product are considered as noise factors. The optimal parameter set is determined by using the principal component gray relational analysis in conjunction with both response surface methodology and artificial neural network. Findings Market specifications and cost of components are considered to propose an optimal parameter design set with the number of grounded screw holes being 14, the size of the shell heat dissipation holes being 3 mm and the arrangement angle of shell heat dissipation holes being 45 degrees, to dispose of 390 O filters on the noise source. Originality/value The optimal parameter set can improve EMC effectively to accommodate the design specifications required by customers and pass test regulations.

Sign in / Sign up

Export Citation Format

Share Document