scholarly journals Predicting the airborne microbial transmission via human breath particles using a gated recurrent units neural network

2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hamid Reza Tamaddon Jahromi ◽  
Igor Sazonov ◽  
Jason Jones ◽  
Alberto Coccarelli ◽  
Samuel Rolland ◽  
...  
Keyword(s):  
Neural Network ◽  
Indoor Environment ◽  
Numerical Results ◽  
Human Breath ◽  
Content Type ◽  
Operation Conditions ◽  
Gated Recurrent Units ◽  
Enclosed Space ◽  
The Impact ◽  
Ventilation Conditions

Purpose The purpose of this paper is to devise a tool based on computational fluid dynamics (CFD) and machine learning (ML), for the assessment of potential airborne microbial transmission in enclosed spaces. A gated recurrent units neural network (GRU-NN) is presented to learn and predict the behaviour of droplets expelled through breaths via particle tracking data sets. Design/methodology/approach A computational methodology is used for investigating how infectious particles that originated in one location are transported by air and spread throughout a room. High-fidelity prediction of indoor airflow is obtained by means of an in-house parallel CFD solver, which uses a one equation Spalart–Allmaras turbulence model. Several flow scenarios are considered by varying different ventilation conditions and source locations. The CFD model is used for computing the trajectories of the particles emitted by human breath. The numerical results are used for the ML training. Findings In this work, it is shown that the developed ML model, based on the GRU-NN, can accurately predict the airborne particle movement across an indoor environment for different vent operation conditions and source locations. The numerical results in this paper prove that the presented methodology is able to provide accurate predictions of the time evolution of particle distribution at different locations of the enclosed space. Originality/value This study paves the way for the development of efficient and reliable tools for predicting virus airborne movement under different ventilation conditions and different human positions within an indoor environment, potentially leading to the new design. A parametric study is carried out to evaluate the impact of system settings on time variation particles emitted by human breath within the space considered.

Spatial density and ambient scent: effects on consumer anxiety

2014 ◽  
Vol 29 (1) ◽  
pp. 76-94 ◽  
Author(s):  
Tina Poon ◽  
Bianca Grohmann
Keyword(s):  
Spatial Perception ◽  
Experimental Manipulation ◽  
Spatial Density ◽  
Laboratory Setting ◽  
Content Type ◽  
Anxiety Levels ◽  
Enclosed Space ◽  
Retail Setting ◽  
Ambient Scent ◽  
The Impact

Purpose – This replication and extension of Hirsch and Gruss examines the impact of spatial density and ambient scent on consumers' spatial perception and anxiety. The paper aims to discuss these issues. Design/methodology/approach – A 2 (spatial density: high, low)×3 (ambient scent: no scent, scent associated with spaciousness, scent associated with enclosed spaces) between-participants experimental design was implemented in a laboratory setting. A pretest determined scent selection and manipulation checks were successful. Findings – Spatial perception was influenced by spatial density, but not ambient scent. Ambient scent and spatial density interacted, such that consumers' anxiety levels significantly increased under conditions of low spatial density combined with an ambient scent associated with spaciousness, and directionally increased under conditions of high spatial density combined with ambient scent associated with enclosed space. Research limitations/implications – This research was conducted in a laboratory setting in order to increase experimental control. An exploration of the strength of the observed effects in a field (retail) setting would be insightful. Practical implications – Results of this study suggest that retailers need to consider both spatial density and choice of ambient scent carefully in order to reduce consumers' anxiety levels. Originality/value – This research is one of the few to consider the impact of spatial density and ambient scent on consumers' anxiety levels. The use of a between-participants design and the experimental manipulation of both spatial density and ambient scent results in a more rigorous test of the scent – anxiety relation observed in previous research.

Market orientation and performance: modelling a neural network

2009 ◽  
Vol 43 (3/4) ◽  
pp. 421-437 ◽  
Author(s):  
Manuela Silva ◽  
Luiz Moutinho ◽  
Arnaldo Coelho ◽  
Alzira Marques
Keyword(s):  
Neural Network ◽  
Market Orientation ◽  
Network Model ◽  
Neural Network Model ◽  
Performance Modelling ◽  
Network Modelling ◽  
Content Type ◽  
Market Intelligence ◽  
And Performance ◽  
The Impact

PurposeThis paper aims to investigate the impact of market orientation (MO) on performance using a neural network model in order to find new linkages and new explanations for this relationship.Design/methodology/approachThis investigation is based on a survey data collection from a sample of 192 Portuguese companies. A neural network model has been developed to identify the effects of each dimension of MO on each dimension of performance.FindingsRelationship among MO and performance was corroborated but MO's impact is poor and based on its first dimension, market intelligence generation.Research limitations/implicationsFurther research in this field should be conducted using other tools offered by neural network modelling.Practical implicationsManagers should give more attention to cross‐functional co‐ordination in order to improve market intelligence dissemination and responsiveness and, thus, global performance.Originality/valueThe paper presents the development of a neural network model to analyse this relationship.

Forecasting construction output: a comparison of artificial neural network and Box-Jenkins model

2016 ◽  
Vol 23 (3) ◽  
pp. 302-322 ◽  
Author(s):  
Ka Chi Lam ◽  
Olalekan Shamsideen Oshodi
Keyword(s):  
Neural Network ◽  
Construction Industry ◽  
Time Series Data ◽  
Predictive Accuracy ◽  
Moving Average ◽  
Arima Model ◽  
Series Data ◽  
Effective Response ◽  
Content Type ◽  
The Impact

Purpose – Fluctuations in construction output has an adverse effect on the construction industry and the economy due to its strong linkage. Developing reliable and accurate predictive models is vital to implementing effective response strategies to mitigate the impact of such fluctuations. The purpose of this paper is to compare the accuracy of two univariate forecast models, i.e. Box-Jenkins (autoregressive integrated moving average (ARIMA)) and Neural Network Autoregressive (NNAR). Design/methodology/approach – Four quarterly time-series data on the construction output of Hong Kong were collected (1983Q1-2014Q4). The collected data were divided into two parts. The first part was fitted to the model, while the other was used to evaluate the predictive accuracy of the developed models. Findings – The NNAR model can provide reliable and accurate forecast of total, private and “others” construction output for the medium term. In addition, the NNAR model outperforms the ARIMA model, in terms of accuracy. Research limitations/implications – The applicability of the NNAR model to the construction industry of other countries could be further explored. The main limitation of artificial intelligence models is the lack of explanatory capability. Practical implications – The NNAR model could be used as a tool for accurately predicting future patterns in construction output. This is vital for the sustained growth of the construction industry and the economy. Originality/value – This is the first study to apply the NNAR model to construction output forecasting research.

Operations-based classification of the bullwhip effect

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sachin Gupta ◽  
Anurag Saxena
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Logistic Regression ◽  
Supply Chain ◽  
Discriminant Analysis ◽  
Bullwhip Effect ◽  
Content Type ◽  
Operational Variables ◽  
Artificial Neural ◽  
The Impact

Purpose Present study deals with the most discussed rather than addressed yet still an unsolved problem of supply chain known as the bullwhip effect. Operational variables affecting the bullwhip effect are identified and their role in causing the bullwhip effect has been explored using artificial neural networks. The purpose of this study is to analyze the impact of identified operational reasons that affect the bullwhip effect and to analyze the bunch of variables that are more prominent in explaining the phenomenon of the bullwhip effect. Design/methodology/approach Ten major sectors of the Indian economy are analyzed for the bullwhip effect in the present study, and the operational variables affecting the bullwhip effect in these sectors are identified. The bullwhip metric is developed as the ratio of variance in production to the variance in the demand. The impact of identified operation variables on the bullwhip effect has been discussed using the artificial neural network technique known as multilayer perceptron. The classification is also performed using neural network, logistic regression and discriminant analysis. Findings The operation variables are found to be varying with respect to sectors. The study emphasizes that analyzing the right set of operation variables with respect to the sector is required to deal with the complex problem, the bullwhip effect. The operational variables affecting the bullwhip effect are identified. The classification result of the neural network is compared with those of the logistic regression and discriminant analysis, and it is found that the dynamism present in the bullwhip effect is better classified by neural network. Research limitations/implications The study used 11 years of observations to analyze the bullwhip effect on the basis of operational variables. The bullwhip effect is a complex phenomenon, and it is explained on the basis of an extensive set of operational variables which is not exhaustive. Further, the behavioral aspect (bullwhip because of decision-making) is not explored in the present study. Practical implications The operational aspect plays a gigantic role to explain and deal with the bullwhip effect. Strategies to mitigate the bullwhip effect must be in accordance with the operational variables impacting the sector. Originality/value The study suggests a novel approach to study the bullwhip effect in supply chain management using the application of neural networks in which operational variables are taken as predictor variables.

Using photographs and metadata to estimate house prices in South Korea

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Changro Lee ◽  
Key-Ho Park
Keyword(s):  
Neural Network ◽  
South Korea ◽  
Visual Information ◽  
House Prices ◽  
House Price ◽  
Content Type ◽  
Real Estate Valuation ◽  
Valuation Process ◽  
Price Estimation ◽  
The Impact

PurposeMost prior attempts at real estate valuation have focused on the use of metadata such as size and property age, neglecting the fact that the building workmanship in the construction of a house is also a key factor for the estimation of house prices. Building workmanship, such as exterior walls and floor tiling correspond to the visual attributes of a house, and it is difficult to capture and evaluate such attributes efficiently through classical models like regression analysis. Deep learning approach is taken in the valuation process to utilize this visual information.Design/methodology/approachThe authors propose a two-input neural network comprising a multilayer perceptron and a convolutional neural network that can utilize both metadata and the visual information from images of the front view of the house.FindingsThe authors applied the two-input neural network to Guri City in Gyeonggi Province, South Korea, as a case study and found that the accuracy of house price estimations can be improved by employing image information along with metadata.Originality/valueFew studies considered the impact of the building workmanship in the valuation process. The authors revealed that it is useful to use both photographs and metadata for enhancing the accuracy of house price estimation.

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 Modelling ozone disinfection process for creating COVID-19 secure spaces

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
HamidReza Tamaddon Jahromi ◽  
Samuel Rolland ◽  
Jason Jones ◽  
Alberto Coccarelli ◽  
Igor Sazonov ◽  
...  
Keyword(s):  
Ozone Concentration ◽  
Decay Kinetics ◽  
Content Type ◽  
Indoor Space ◽  
Disinfection Process ◽  
Computational Methodology ◽  
Enclosed Space ◽  
Ozone Disinfection ◽  
The Impact ◽  
Indoor Spaces

Purpose A novel modelling approach is proposed to study ozone distribution and destruction in indoor spaces. The level of ozone gas concentration in the air, confined within an indoor space during an ozone-based disinfection process, is analysed. The purpose of this work is to investigate how ozone is distributed in time within an enclosed space. Design/methodology/approach A computational methodology for predicting the space- and time-dependent ozone concentration within the room across the consecutive steps of the disinfection process (generation, dwelling and destruction modes) is proposed. The emission and removal of ozone from the air volume are possible by means of a generator located in the middle of the room. This model also accounts for ozone reactions and decay kinetics, and gravity effect on the air. Finding This work is validated against experimental measurements at different locations in the room during the disinfection cycle. The numerical results are in good agreement with the experimental data. This comparison proves that the presented methodology is able to provide accurate predictions of the time evolution of ozone concentration at different locations of the enclosed space. Originality/value This study introduces a novel computational methodology describing solute transport by turbulent flow for predicting the level of ozone concentration within a closed room during a COVID-19 disinfection process. A parametric study is carried out to evaluate the impact of system settings on the time variation of ozone concentration within the space considered.

A deep neural network based context-aware smart epidemic surveillance in smart cities

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Harsuminder Kaur Gill ◽  
Vivek Kumar Sehgal ◽  
Anil Kumar Verma
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Smart Cities ◽  
Geographical Area ◽  
Final Decision ◽  
Context Aware ◽  
Content Type ◽  
Data Points ◽  
Risk Areas ◽  
The Impact

PurposeEpidemics not only affect the public health but also are a threat to a nation's growth and economy as well. Early prediction of epidemic can be beneficial to take preventive measures and to reduce the impact of epidemic in an area.Design/methodology/approachA deep neural network (DNN) based context aware smart epidemic system has been proposed to prevent and monitor epidemic spread in a geographical area. Various neural networks (NNs) have been used: LSTM, RNN, BPNN to detect the level of disease, direction of spread of disease in a geographical area and marking the high-risk areas. Multiple DNNs collect and process various data points and these DNNs are decided based on type of data points. Output of one DNN is used by another DNN to reach to final prediction.FindingsThe experimental evaluation of the proposed framework achieved the accuracy of 87% for the synthetic dataset generated for Zika epidemic in Brazil in 2016.Originality/valueThe proposed framework is designed in a way that every data point is carefully processed and contributes to the final decision. These multiple DNNs will act as a single DNN for the end user.

The More Control, the Better?

2014 ◽  
Vol 26 (2) ◽  
pp. 81-91 ◽  
Author(s):  
Jeeyun Oh ◽  
Mun-Young Chung ◽  
Sangyong Han
Keyword(s):  
Mixed Design ◽  
Negative Effects ◽  
Story Structure ◽  
Content Type ◽  
High User ◽  
User Control ◽  
Rigorous Research ◽  
Control Versus ◽  
The Media ◽  
The Impact

Despite of the popularity of interactive movie trailers, rigorous research on one of the most apparent features of these interfaces – the level of user control – has been scarce. This study explored the effects of user control on users’ immersion and enjoyment of the movie trailers, moderated by the content type. We conducted a 2 (high user control versus low user control) × 2 (drama film trailer versus documentary film trailer) mixed-design factorial experiment. The results showed that the level of user control over movie trailer interfaces decreased users’ immersion when the trailer had an element of traditional story structure, such as a drama film trailer. Participants in the high user control condition answered that they were less fascinated with, absorbed in, focused on, mentally involved with, and emotionally affected by the movie trailer than participants in the low user control condition only with the drama movie trailer. The negative effects of user control on the level of immersion for the drama trailer translated into users’ enjoyment. The impact of user control over interfaces on immersion and enjoyment varies depending on the nature of the media content, which suggests a possible trade-off between the level of user control and entertainment outcomes.

Sign in / Sign up

Export Citation Format

Share Document