Prediction of CO2 in Public Buildings DOI Creative Commons
Ekaterina Dudkina, Emanuele Crisostomi, Alessandro Franco

et al.

Energies, Journal Year: 2023, Volume and Issue: 16(22), P. 7582 - 7582

Published: Nov. 14, 2023

Heritage from the COVID-19 period (in terms of massive utilization mechanical ventilation systems), global warming, and increasing electricity prices are new challenging factors in building energy management, hindering desired path towards improved efficiency reduced consumption. The solution to improve smartness today’s automation control systems is equip them with increased intelligence take prompt appropriate actions avoid unnecessary consumption, while maintaining a level air quality. In this manuscript, we evaluate ability machine-learning-based algorithms predict CO2 levels, which classic indicators used We show that these provide accurate forecasts (more particular than those provided by physics-based models). These could be conveniently embedded systems. Our findings validated using real data measured university classrooms during teaching activities.

Language: Английский

Improve carbon dioxide emission prediction in the Asia and Oceania (OECD): nature-inspired optimisation algorithms versus conventional machine learning DOI Creative Commons
Loke Kok Foong, Vojtěch Blažek, Lukáš Prokop

et al.

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2024, Volume and Issue: 18(1)

Published: Aug. 23, 2024

This paper investigates the application of three nature-inspired optimisation algorithms – SHO, MFO, and GOA combined with four machine learning methods Gaussian Processes, Linear Regression, MLP, Random Forest to enhance carbon dioxide emission prediction in OECD Asia Oceania region. The study uses historical emissions data, socioeconomic indicators such as GDP, population density, energy consumption, urbanisation rates, environmental temperature, precipitation, forest cover. Through comprehensive experimentation, evaluates performance each combination, revealing varying effectiveness levels. MFO-MLP combination achieved highest accuracy R2 values 0.9996 0.9995 RMSE 11.7065 12.8890 for training testing datasets, respectively. GOA-MLP configuration 0.9994 0.99934 15.01306 14.59333. SHO-MLP while effective, showed lower 0.9915 0.9946 55.4516 41.575. findings suggest hybrid techniques can significantly compared conventional methods. research provides valuable insights policymakers stakeholders, indicating that optimised models support more informed effective policy-making sustainability efforts Future should explore additional ensemble improve robustness accuracy. These offer a robust tool forecast accurately, aiding developing targeted strategies reduce footprints achieve climate goals.

Language: Английский

Citations

5
Axial Capacity of FRP-Reinforced Concrete Columns: Computational Intelligence-Based Prognosis for Sustainable Structures DOI Creative Commons
Harish Chandra Arora, Sourav Kumar, Denise‐Penelope N. Kontoni

et al.

Buildings, Journal Year: 2022, Volume and Issue: 12(12), P. 2137 - 2137

Published: Dec. 5, 2022

Due to the corrosion problem in reinforced concrete structures, use of fiber-reinforced polymer (FRP) bars may be preferred place traditional reinforcing steel. FRP are used constructions boost strength structural elements and retain their longevity. In this study, axial load carrying capacity (ALCC) FRP-reinforced columns has been evaluated using analytical, as well machine learning, models. A total fourteen popular analytical models one proposed learning-based model were estimate ALCC columns. The learning is based on an artificial neural network (ANN) method. performance ANN, models, assessed six different indices. R-value developed ANN 0.9758, followed by NS value 0.9513. It found that mean absolute percentage error best-fitted 328.71% higher than model, root-mean-square 211.97% model. data demonstrate performs better other quick easy-to-use

Language: Английский

Citations

20
Computational Intelligence-Based Structural Health Monitoring of Corroded and Eccentrically Loaded Reinforced Concrete Columns DOI Creative Commons
Somain Sharma, Harish Chandra Arora, Aman Kumar

et al.

Shock and Vibration, Journal Year: 2023, Volume and Issue: 2023, P. 1 - 21

Published: Feb. 21, 2023

Corrosion of embedded steel reinforcement is the prime influencing factor that deteriorates structural performance and reduces serviceability reinforced concrete (RC) structures, especially during earthquakes. In elements, RC columns play a vital role in transferring superstructure’s load to substructure. The deterioration can affect structures’ overall performance. Hence, it becomes essential estimate remaining life deteriorated columns. literature, only limited analytical models are available calculate corroded eccentrically loaded As number dependent parameters increases, assessing residual elements providing practically applicable suitable model become very complex. Machine learning (ML)-based prediction beneficial dealing with such complex databases. this article, an ML-based artificial neural network (ANN), Gaussian process regression (GPR), support vector machine (SVM) algorithms have been applied strength ML accessed using commonly used indices, namely, coefficient determination (R2), root mean square error (RMSE), absolute (MAE), percentage (MAPE), a-20 index, Nash–Sutcliffe (NS). results proposed ANN compared existing identify suitability best model. Based on analysis, precision GPR SVM lower than processed revealed R2 value for training, testing, validation datasets 0.9908, 0.9757, 0.9855, respectively. MAPE, MAE, RMSE, NS, index all 8.31%, 48.35 kN, 72.53 0.9886, 0.8978, terms 225.77% higher sensitivity analysis demonstrates compressive plays most significant load-carrying capacity reliable, accurate, fast, cost effective. This also be as health-monitoring tool detect early damages

Language: Английский

Citations

11
Indoor Air Quality in Urban India: Current Status, Research Gap, and the Way Forward DOI
Alok Thakur, Sameer Patel

Environmental Science & Technology Letters, Journal Year: 2023, Volume and Issue: 10(12), P. 1146 - 1158

Published: Nov. 9, 2023

Given that people spend most of their time indoors in developed nations, personal exposure occurring indoor spaces dominates cumulative exposure. Therefore, the total mortality burden air pollution is primarily attributed to (IAP). Owing rapid urbanization, India too have similar activity patterns. However, IAP research urban-Indian built environments still nascent relative countries. This article comparatively reviews on measurement, modeling, and mitigation countries India. While studies nations deployed state-of-the-art instrumentation for comprehensive characterization, are severely limited quantity scope. The lack measurements has restricted robust follow-up modeling mitigation. Fundamental sources, transport, transformation, fate pollutants urban nearly nonexistent. Such critical designing operating shield occupants from sources outdoor pollution, which severe Limited due resource restrictions remain a bottleneck Shifting focus policymakers public ambient

Language: Английский

Citations

11
Theoretical Simulation of Natural Air Exchange and Indoor Air Quality with an Example of a Green Wall Introduction DOI Creative Commons
Viktor Mileikovskyi,

Tetiana Tkachenko,

Lavr Kotelkov

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104336 - 104336

Published: Feb. 1, 2025

Language: Английский

Citations

0
Smart Office Automation using Multi-Dimensional Attention Spiking Neural Network for Face Recognition in Internet of Things DOI
Harish Kumar,

Anuradha Taluja,

I. Kala

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 112967 - 112967

Published: March 1, 2025

Language: Английский

Citations

0
Internet-of-Things-Based CO2 Monitoring and Forecasting System for Indoor Air Quality Management DOI Creative Commons

M. J. Marquez-Zepeda,

Ildeberto Santos‐Ruiz, Esvan-Jesús Pérez-Pérez

et al.

Mathematical and Computational Applications, Journal Year: 2025, Volume and Issue: 30(2), P. 36 - 36

Published: March 28, 2025

This study presents a low-cost and scalable CO2 monitoring system that leverages NDIR sensors Long Short-Term Memory (LSTM) neural network to predict indoor concentrations over both short- long-term horizons. The proposed aims anticipate air quality deterioration in shared spaces, enabling proactive ventilation strategies. Various LSTM configurations were evaluated, optimizing the number of layers, neurons per layer, input delays enhance forecasting accuracy. optimal model consisted two layers with 128 each time window 10 previous observations. achieved an RMSE approximately 57 ppm for 8 h forecast classroom setting. Experimental results demonstrate reliability approach prediction its potential impact on management.

Language: Английский

Citations

0
Comparing classic regression with credit scorecard model for predicting sick building syndrome risk: A machine learning perspective in environmental assessment DOI
Mohammad Reza Hosseini, Hatam Godini, Reza Fouladi Fard

et al.

Building and Environment, Journal Year: 2024, Volume and Issue: 253, P. 111351 - 111351

Published: Feb. 28, 2024

Language: Английский

Citations

3
Event-Specific Transmission Forecasting of SARS-CoV-2 in a Mixed-Mode Ventilated Office Room Using an ANN DOI Open Access
Nishant Raj Kapoor, Ashok Kumar, Anuj Kumar

et al.

International Journal of Environmental Research and Public Health, Journal Year: 2022, Volume and Issue: 19(24), P. 16862 - 16862

Published: Dec. 15, 2022

The emerging novel variants and re-merging old of SARS-CoV-2 make it critical to study the transmission probability in mixed-mode ventilated office environments. Artificial neural network (ANN) curve fitting (CF) models were created forecast R-Event. R-Event is defined as anticipated number new infections that develop particular events occurring over course time any space. In spring summer 2022, real-time data for an environment collected India a space composite climate. performances proposed CF ANN compared with respect traditional statistical indicators, such correlation coefficient, RMSE, MAE, MAPE, NS index, a20-index, order determine merit two approaches. Thirteen input features, namely indoor temperature (TIn), relative humidity (RHIn), area opening (AO), occupants (O), per person (AP), volume (VP), CO2 concentration (CO2), air quality index (AQI), outer wind speed (WS), outdoor (TOut), (RHOut), fan (FS), conditioning (AC), selected target. main objective was relationship between level R-Event, ultimately producing model forecasting building coefficients this case 0.7439 0.9999, respectively. This demonstrates more accurate prediction than model. results show reliable significantly values offices.

Language: Английский

Citations

15
A Novel Coupled Optimization Prediction Model for Air Quality DOI Creative Commons
Q. Shao, Jiahao Chen, Tao Jiang

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 69667 - 69685

Published: Jan. 1, 2023

PM2.5 is a significant pollutant that negatively affects atmospheric environmental sustainability, and accurate prediction of its concentration crucial. Most existing models face challenges such as inadequate data feature capture, dismissal influential factors, subjective model parameter tuning. To address these issues, this paper introduces novel coupled air quality optimization based on Variational Mode Decomposition (VMD), the Informer time series algorithm, Extreme Gradient Boosting (XGBoost), Dung Beetle Optimization Algorithm (DBO). The coupling approach screens features using Spearman coefficient method, optimizes VMD with DBO, decomposes data, classifies various according to approximate entropy. algorithm DBO-optimized XGBoost process different separately, then superimpose reconstruct predicted values obtain results. Using in Nanjing an example, new achieves superior performance (R-squared=0.961, RMSE=1.988, MAE=1.624). Compared WANNs highest accuracy recent relevant studies, our demonstrates 2.96% increase R-squared, 21.89% decrease RMSE, 20.05% MAE. This comparison illustrates proposed DBO-VMD-Informer-XGBoost effectively addresses limitations offers increased accuracy. By employing advanced DBO for innovatively combining VMD, Informer, XGBoost, presents high potential anticipated have broader applications.

Language: Английский

Citations

9