Forecasting sustainable water production in convex tubular solar stills using gradient boosting analysis

Desalination and Water Treatment, Год журнала: 2024, Номер 318, С. 100344 - 100344

Опубликована: Апрель 1, 2024

Water scarcity is an important global issue that necessitates the development of sufficient and sustainable desalination technologies. This study forecasts productivity two solar distillation technologies, namely conventional tubular still (TSS) convex (CTSS). The research objectives included assessing distillate yield both stills investigating application advanced gradient boosting machine learning (ML) technique for forecasting production. Compared to TSS, CTSS demonstrated a calculated increase in which indicates its potential as effective water technology. correlation analysis revealed TSS exhibited 10 significant correlations while 4 correlations. model exceptional predictive precision stills. R-squared (R2) was 0.86, Root Mean Squared Error (RMSE) 58.2%, Coefficient Variation (CVRMSE) 29.3%. In contrast, displayed impressive performance metrics, including R2 value 0.99, RMSE 1.2%, CVRMSE 4%. Valuable insights were provided enhancement stills, addition highlighting ML techniques accurately predicting productivity.

Язык: Английский

---

Enhancing building sustainability through aerodynamic shading devices: an integrated design methodology using finite element analysis and optimized neural networks

Asian Journal of Civil Engineering, Год журнала: 2024, Номер 25(5), С. 4281 - 4294

Опубликована: Апрель 20, 2024

Язык: Английский

---

Evaluating electrical power yield of photovoltaic solar cells with k-Nearest neighbors: A machine learning statistical analysis approach

e-Prime - Advances in Electrical Engineering Electronics and Energy, Год журнала: 2024, Номер 9, С. 100674 - 100674

Опубликована: Июль 4, 2024

The increasing demand for sustainable and renewable energy solutions reflects the critical importance of advancing photovoltaic (PV) technology its operational efficiency. In response, this study introduces a novel application k-Nearest Neighbor (k-NN) algorithm to assess reliability applicability solar panel simulation data which aimed classify current states partial shading, open, short circuit conditions, alongside regression-based analysis predicting specific operating parameters. research, published dataset that involved various PV module configurations under different environmental conditions was tested evaluated. k-NN technique applied both status predict performance metrics modules. diagnosis model demonstrated an accuracy 99.2 % F1 score %, indicating high degree in identifying Concurrently, regression exhibited Root Mean Square Error (RMSE) 0.036 R2 value unity showcased effectiveness parameters based on data. concluded results are further enriching simulation-based generation be endorsed implemented before jumping into real experimental applications, addition highlighting potential machine learning cells productivity statistical analysis.

Язык: Английский

---

UAV propeller fault diagnosis using deep learning of non-traditional χ2-selected Taguchi method-tested Lempel–Ziv complexity and Teager–Kaiser energy features

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Авг. 10, 2024

Fault detection and isolation in unmanned aerial vehicle (UAV) propellers are critical for operational safety efficiency. Most existing fault diagnosis techniques rely basically on traditional statistical-based methods that necessitate better approaches. This study explores the application of untraditional feature extraction methodologies, namely Permutation Entropy (PE), Lempel-Ziv Complexity (LZC), Teager-Kaiser Energy Operator (TKEO), PADRE dataset, which encapsulates various rotor configurations. The extracted features were subjected to a Chi-Square (χ

Язык: Английский

---

Innovative Machine Learning Approaches for Complexity in Economic Forecasting and SME Growth: A Comprehensive Review

Journal of Economy and Technology, Год журнала: 2025, Номер unknown

Опубликована: Янв. 1, 2025

Язык: Английский

---

Machine learning-driven power prediction in continuous extrusion of pure titanium for enhanced structural resilience under extreme loading

Discover Materials, Год журнала: 2025, Номер 5(1)

Опубликована: Янв. 11, 2025

Abstract The increasing demand for advanced materials capable of withstanding extreme loading conditions, such as those encountered during impact or blast events, underscores the need innovative approaches in material processing. This study focuses on leveraging machine learning (ML) to enhance predictive accuracy continuous extrusion CP-Titanium Grade 2, a vital structural resilience critical applications. Specifically, an Artificial Neural Network (ANN) model optimized using Stochastic Gradient Descent (SGD) was introduced forecast power requirements with high precision. analysis utilized published dataset that comprises theoretical, numerical, and experimental calculations robust foundation validation comparison. A visualization highlighted influence process parameters, feedstock temperature wheel velocity, performance align thematic focus resilient design. ANN-SGD achieved RMSE 0.9954 CVRMSE 11.53% which demonstrated significant improvements prediction compared traditional approaches. By achieving superior alignment results, validated its efficacy reliable efficient tool understanding optimizing complex manufacturing processes. research emphasizes potential ML revolutionize processing conditions contribute broader goals sustainable manufacturing.

Язык: Английский

---

Response to letter to the Editor from Y. Takefuji on “Beyond principal component analysis: Enhancing feature reduction in electronic noses through robust statistical methods”

Trends in Food Science & Technology, Год журнала: 2025, Номер unknown, С. 104918 - 104918

Опубликована: Фев. 1, 2025

Язык: Английский

---

Analyzing traffic accident trends and correlations in Iraq: An investigative statistical approach

AIP conference proceedings, Год журнала: 2025, Номер 3303, С. 040002 - 040002

Опубликована: Янв. 1, 2025

Язык: Английский

---

Leak detection and localization in water distribution systems using advanced feature analysis and an Artificial Neural Network

Desalination and Water Treatment, Год журнала: 2024, Номер 320, С. 100685 - 100685

Опубликована: Авг. 3, 2024

This study capitalizes on a dataset, originally including 280 sensory measurements from laboratory-scale water distribution system, to advance the concept of leakage diagnosis and localization. The test rig are formulated in two configurations, namely looped branched layouts. paper processed time-domain data accelerometers dynamic pressure sensors into advanced statistical features of: Autocorrelation Coefficient (Au-C), Signal Energy (Sig-E), detect localize leakage. By Employment these features, research developed an expert system Artificial Neural Network (ANN) model designed with optimal parameters, neurons, hidden layers classify presence pinpoint location leaks within rig. effectiveness current approach is quantitatively evaluated using F1-scores accuracy metrics. A robust capability for both detecting localizing under varying conditions was established highest F1-score 86.5 % 86.2 %, respectively. findings underscore potential integrating Intelligence (AI) enhancing reliability dependability management systems. contributes broader application AI managing resources infrastructure resilience its support improve whereabouts.

Язык: Английский

---

Optimizing water resources for sustainable desalination: The integration of expert systems and solar energy in experimental applications

Desalination and Water Treatment, Год журнала: 2024, Номер 320, С. 100683 - 100683

Опубликована: Авг. 3, 2024

The integration of renewable energy sources with multi-energy systems present challenges and opportunities to enhance sustainability. Among these, solar stills have emerged as a solution for water desalination. With the advent expert system technologies, avenues are opened improving operational efficiency distillers. This paper presents an innovative approach utilizing correlation analysis, ReliefF feature selection, k-Nearest Neighbor (kNN) algorithm forecasting cumulative distillate output double slope still. analysis is based on 6-cases-based dataset, which includes variations in relative different operational-environmental conditions. Key features that significantly impact overall performance were identified manage distiller productivity. findings reveal maximum was 1610 ML/m2.day due incorporating reflective materials phase change (PCM) enhancing distillation rates. kNN model evaluated its R2, RMSE, CVRMSE, best models achieving scores 0.995, 0.0033, 0.1666, respectively. These metrics underscore effectiveness proposed machine learning predicting output, thereby enabling informed management processes. Combining technologies computational intelligence holds significant promise sustainable environmental management, study presented.

Язык: Английский

---