Financial applications of machine learning: A literature review

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 219, P. 119640 - 119640

Published: Feb. 3, 2023

Language: Английский

---

Deep Learning and Artificial Intelligence in Sustainability: A Review of SDGs, Renewable Energy, and Environmental Health

Sustainability, Journal Year: 2023, Volume and Issue: 15(18), P. 13493 - 13493

Published: Sept. 8, 2023

Artificial intelligence (AI) and deep learning (DL) have shown tremendous potential in driving sustainability across various sectors. This paper reviews recent advancements AI DL explores their applications achieving sustainable development goals (SDGs), renewable energy, environmental health, smart building energy management. has the to contribute 134 of 169 targets all SDGs, but rapid these technologies necessitates comprehensive regulatory oversight ensure transparency, safety, ethical standards. In sector, been effectively utilized optimizing management, fault detection, power grid stability. They also demonstrated promise enhancing waste management predictive analysis photovoltaic plants. field integration facilitated complex spatial data, improving exposure modeling disease prediction. However, challenges such as explainability transparency models, scalability high dimensionality with next-generation wireless networks, ethics privacy concerns need be addressed. Future research should focus on developing scalable algorithms for processing large datasets, exploring addressing considerations. Additionally, efficiency models is crucial use technologies. By fostering responsible innovative use, can significantly a more future.

Language: Английский

---

A systematic review towards integrative energy management of smart grids and urban energy systems

Renewable and Sustainable Energy Reviews, Journal Year: 2023, Volume and Issue: 189, P. 114023 - 114023

Published: Nov. 3, 2023

Language: Английский

---

Predicting Energy Consumption in Residential Buildings Using Advanced Machine Learning Algorithms

Energies, Journal Year: 2023, Volume and Issue: 16(9), P. 3748 - 3748

Published: April 27, 2023

The share of residential building energy consumption in global has rapidly increased after the COVID-19 crisis. accurate prediction under different indoor and outdoor conditions is an essential step towards improving efficiency reducing carbon footprints sector. In this paper, a PSO-optimized random forest classification algorithm proposed to identify most important factors contributing heating consumption. A self-organizing map (SOM) approach applied for feature dimensionality reduction, ensemble model based on stacking method trained dimensionality-reduced data. results show that outperforms other models with accuracy 95.4% prediction. Finally, causal inference introduced addition Shapley Additive Explanation (SHAP) explore analyze influencing clear relationship between water pipe temperature changes, air temperature, found, compensating neglect SHAP analysis. findings research can help owners/managers make more informed decisions around selection efficient management systems save bills.

Language: Английский

---

Improving Energy Performance in Flexographic Printing Process through Lean and AI Techniques: A Case Study

Energies, Journal Year: 2023, Volume and Issue: 16(4), P. 1972 - 1972

Published: Feb. 16, 2023

Flexographic printing is a highly sought-after technique within the realm of packaging and labeling due to its versatility, cost-effectiveness, high speed, high-quality images, environmentally friendly nature. A major challenge in flexographic need optimize energy usage, which requires diligent attention resolve. This research combines lean principles machine learning improve efficiency selected machines; i.e., Miraflex F&K. By implementing 5Why root cause analysis Kaizen, study found that idle time was reduced by 30% for F&K machine, resulting savings 34.198% 38.635% per meter, respectively. Additionally, multi-linear regression model developed using range input parameters, such as production substrate density, time, working total run predict consumption job scheduling. The results exhibit efficient accurate, leading reduction costs while maintaining or even improving quality printed output. approach can also add reducing carbon footprint manufacturing process help companies meet sustainability goals.

Language: Английский

---

Comparative study of genetic programming-based algorithms for predicting the compressive strength of concrete at elevated temperature

Case Studies in Construction Materials, Journal Year: 2023, Volume and Issue: 18, P. e02199 - e02199

Published: June 6, 2023

The elevated temperature severely influences the mixed properties of concrete, causing a decrease in its strength properties. Accurate proportioning concrete components for obtaining required compressive (C-S) at temperatures is complicated and time-taking process. However, using evolutionary programming techniques such as gene expression (GEP) multi-expression (MEP) provides accurate prediction C-S. This article presents genetic programming-based models (such (MEP)) forecasting temperatures. In this regard, 207 C-S values were obtained from previous studies. model's development, was considered output parameter with nine most influential input parameters, including; Nano silica, cement, fly ash, water, temperature, silica fume, superplasticizer, sand, gravels. efficacy accuracy GEP MEP-based assessed by statistical measures mean absolute error (MAE), correlation coefficient (R2), root square (RMSE). Moreover, also evaluated external validation different criteria recommended comparing MEP models, gave higher R2 lower RMSE MAE 0.854, 5.331 MPa, 0.018 MPa respectively, indicating strong between actual anticipated outputs. Thus, GEP-based model used further sensitivity analysis, which revealed that cement influencing factor. addition, proposed simple mathematical can be easily implemented practice.

Language: Английский

---

AI-Driven Innovations in Building Energy Management Systems: A Review of Potential Applications and Energy Savings

Energies, Journal Year: 2024, Volume and Issue: 17(17), P. 4277 - 4277

Published: Aug. 27, 2024

Despite the tightening of energy performance standards for buildings in various countries and increased use efficient renewable technologies, it is clear that sector needs to change more rapidly meet Net Zero Emissions (NZE) scenario by 2050. One problems have been analyzed intensively recent years operation much than they were designed to. This problem, known as gap, found many often attributed poor management building systems. The application Artificial Intelligence (AI) Building Energy Management Systems (BEMS) has untapped potential address this problem lead sustainable buildings. paper reviews different AI-based models proposed applications with intention reduce consumption. It compares evaluated reviewed papers presenting accuracy error rates model identifies where greatest savings could be achieved, what extent. review showed offices (up 37%) when employ AI HVAC control optimization. In residential educational buildings, lower intelligence existing BEMS results smaller 23% 21%, respectively).

Language: Английский

---

Ranking building design and operation parameters for residential heating demand forecasting with machine learning

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 86, P. 108817 - 108817

Published: Feb. 19, 2024

The European Union's Energy Performance in Buildings Directive has made significant strides enhancing building energy efficiency since its inception 2002. However, approximately 75% of EU buildings still fall short energy-efficient standards. Furthermore, there is a growing momentum to extend the concept nearly zero-energy entire districts, thereby fostering Net-Zero Districts. This underscores necessity for large-scale urban modelling identify and improve underperforming transition planning. Given increasing interest black box models performance, this study aims common input variables demand literature, analyse their influence, develop heating prediction model using different algorithms: Random Forest, XGBoost, Extra Trees. Four large datasets generated from white-box simulation three Spanish cities were used training testing models. features consistently stand out as most important prediction: shape factor, infiltration rate, south equivalent surface, internal gains, regardless algorithm or climatic zone. multi-location XGBoost with an optimizer emerged best-performing model, average Mean Absolute Percentage Error value hovering around 40%. Analysis employing SHapley Additive exPlanation (SHAP) values showcases model's ability factors that drive higher demand, alongside strong predictive performance. suggests potential integration into programmes key be addressed during renovation. Additionally, results show XGBoost-based software's identifying renovation targets.

Language: Английский

---

An interpretable multi-stage forecasting framework for energy consumption and CO2 emissions for the transportation sector

Energy, Journal Year: 2023, Volume and Issue: 286, P. 129499 - 129499

Published: Nov. 6, 2023

The transportation sector is deemed one of the primary sources energy consumption and greenhouse gases throughout world. To realise design sustainable transport, it imperative to comprehend relationships evaluate interactions among a set variables, which may influence transport CO2 emissions. Unlike recent published papers, this study strives achieve balance between machine learning (ML) model accuracy interpretability using Shapley additive explanation (SHAP) method for forecasting emissions in UK's sector. end, paper proposes an interpretable multi-stage framework simultaneously maximise ML determine relationship predictions influential variables by revealing contribution each variable predictions. For sector, experimental results indicate that road carbon intensity found be most contributing both other studies, population GDP per capita are uninfluential variables. proposed assist policymakers making more informed decisions establishing accurate investment.

Language: Английский

---

Developing a multi-objective optimization model for improving building's environmental performance over the whole design process

Building and Environment, Journal Year: 2023, Volume and Issue: 246, P. 110996 - 110996

Published: Nov. 2, 2023

This study is built upon two previous articles which focus on identifying the key design variables affecting life-cycle environmental impacts in each stage of building process. research aims to investigate trade-offs between embodied and operational explore potential reduction total a by varying identified A multi-objective optimization model based BIM LCA integration has been developed find out solution with optimal option minimal impacts. Applying proposed mid-rise residential building, results showed that process lower approximately 47.6 %. Moreover, for reducing carbon emissions greater early stages, up 32.5 %, compared emission 7.5 % detailed construction stages. Furthermore, solutions aimed at addressing trade-off were stage. The provides an insight into understanding how can be optimized mitigate

Language: Английский

---