Prediction of Complex Stock Market Data Using an Improved Hybrid EMD-LSTM Model

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(3), P. 1429 - 1429

Published: Jan. 21, 2023

Because of the complexity, nonlinearity, and volatility, stock market forecasting is either highly difficult or yields very unsatisfactory outcomes when utilizing traditional time series machine learning techniques. To cope with this problem improve complex market’s prediction accuracy, we propose a new hybrid novel method that based on version EMD deep technique known as long-short memory (LSTM) network. The precision proposed ensemble evaluated using KSE-100 index Pakistan Stock Exchange. Using uses Akima spline interpolation instead cubic interpolation, noisy data are first divided into multiple components technically intrinsic mode functions (IMFs) varying from high to low frequency single monotone residue. correlated sub-components then used build LSTM By comparing model other models such support vector (SVM), Random Forest, Decision Tree, its performance thoroughly evaluated. Three alternative statistical metrics, namely root means square error (RMSE), mean absolute (MAE) percentage (MAPE), compare aforementioned empirical results show suggested Akima-EMD-LSTM beats all taken consideration for study therefore recommended an effective non-stationary nonlinear financial data.

Language: Английский

---

Novel Design of Double Slope Solar Distiller with Prismatic Absorber Basin, Linen Wicks, and Dual Parallel Spraying Nozzles: Experimental Investigation and Energic–Exergic-Economic Analyses

Water, Journal Year: 2023, Volume and Issue: 15(3), P. 610 - 610

Published: Feb. 3, 2023

Increasing the evaporation zone inside solar distiller (SD) is a pivotal method for augmenting its freshwater production. Hence, in this work, newly designed prismatic absorber basin covered by linen wicks was utilized instead of conventional flat to increase surface area vaporization double-slope (DSSD). Meanwhile, further enhancement modified DSSD performance, dual parallel spraying nozzles are incorporated underneath glass cover as saltwater feed supply minimize thickness film on wick, which enhances heating process wick and, consequently, and condensation processes improved. Two double slope distillers, namely with (DSSD-WPB&DPSN) traditional (TDSSD), made tested outdoor summer conditions Tanta, Egypt (31° E 30.5° N). A comparative energic–exergic-economic analysis two proposed stills also conducted, terms cumulative distillation yield, daily energy efficiency, exergy cost per liter distilled yield. The present results show that yield DSSD-WPB&DPSN 8.20 kg/m2·day, higher than TDSSD 49.64%. Furthermore, efficiencies were increased 48.51% 118.10%, respectively, relative TDSSD. Additionally, life assessment reveals decreased 11.13% compared

Language: Английский

---

Innovative solar distillation system with prismatic absorber basin: Experimental analysis and LSTM machine learning modeling coupled with great wall construction algorithm

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: 186, P. 1120 - 1133

Published: April 18, 2024

Language: Английский

---

Enhancement and prediction of a stepped solar still productivity integrated with paraffin wax enriched with nano-additives

Case Studies in Thermal Engineering, Journal Year: 2023, Volume and Issue: 49, P. 103215 - 103215

Published: June 29, 2023

The present study deals with the emhancement of thermophysical properties paraffin wax using Silver nanoparticles and to feasibility its application in a stepped solar still through an experimental approach. Along experimentation, yield, temperature water are predicted machine learning such as melting temperature, latent heat, thermal conductivity stability different concentrations (1 2%) investigated compared that without nanoadditives. was enhanced by about 35.71% 78.57% nano-additives 1% 2%, respectively. Three SS namely, wax, doped Ag nanoparticles, fabricated tested for climatic conditions Coimbatore, India. From results fresh generation, it is identified nanocomposite PCM nanoadditives 75.65% 114.81% respectively, while any energy storage. In order estimate amount can be produced each three stills, single adaptive neuro-fuzzy inference system (ANFIS) hybrid system-particle swarm optimizer (PSO) were used models. According statistical assessment, ANFIS-PSO model had greater level accuracy than standalone ANFIS. very high determination coefficient ranged between 0.981 0.995 which indicates capability predict yield stills.

Language: Английский

---

Productivity prediction of a spherical distiller using a machine learning model and triangulation topology aggregation optimizer

Desalination, Journal Year: 2024, Volume and Issue: 585, P. 117744 - 117744

Published: May 18, 2024

Language: Английский

---

Performance prediction of aluminum and polycarbonate solar stills with air cavity using an optimized neural network model by golden jackal optimizer

Case Studies in Thermal Engineering, Journal Year: 2023, Volume and Issue: 47, P. 103055 - 103055

Published: May 20, 2023

Solar stills (SS) are simple eco-friendly desalination devices that exploit solar energy to obtain freshwater from seawater. In this study, a hybrid artificial intelligence model is proposed predict the thermal behavior of two designs SSs. Two SSs with basin and absorber plate made aluminum for first SS (ALSS)and polycarbonate second (PCSS) were established tested. Both have modified an air cavity. The was composed optimized Artificial Neural Network (ANN) by Golden Jackal Optimizer (GJO). To prove capability performance, it compared conventional ANN as well other models Genetic Algorithm (GA) or Particle Swarm (PSO). results showed ANN-GJO had better accuracy than ANN, ANN-GA, ANN-PSO overall heat transfer coefficient, efficiency, exergy distillate output. Moreover, ALSS performance PCSS regarding water productivity, efficiency. average efficiency 2.30%, 42.40%, 3.44%, 48.80%, respectively. maximum output 3.40 l/m2/day 3.80 l/m2/day,

Language: Английский

---

Optimization of an oil recovery process from oily sludge using a combined technique of froth flotation and centrifugal treatment

Journal of Cleaner Production, Journal Year: 2023, Volume and Issue: 400, P. 136752 - 136752

Published: March 9, 2023

Language: Английский

---

Kerf characteristics during CO2 laser cutting of polymeric materials: Experimental investigation and machine learning-based prediction

Engineering Science and Technology an International Journal, Journal Year: 2023, Volume and Issue: 46, P. 101519 - 101519

Published: Sept. 1, 2023

This study uses advanced machine learning approaches to predict the kerf open deviation (KOD) when a CO2 laser is used cut polymeric materials. Four materials, namely polyethylene (PE), polymethyl methacrylate (PMMA), polypropylene (PP), and polyvinyl chloride (PVC), were under same conditions. The process control factors power of beam (80–140 W) cutting speed (1–6 mm/s), while sheet thickness, standoff distance, gas pressure kept constant during experiments. KOD between upper lower opens was response. predicted using three models, conventional artificial neural network (ANN), hybrid network–humpback whale optimizer (HWO-ANN), network–particle swarm (PSO-ANN). Experimental data for all materials employed train test models. model outperformed other models root-mean-square error experimental 0.349–0.627 µm, 0.085–0.242 0.023–0.079 µm network, model, respectively.

Language: Английский

---

Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 86, P. 690 - 703

Published: Dec. 28, 2023

Membrane desalination (MD) is an efficient process for desalinating saltwater, combining the uniqueness of both thermal and separation distillation configurations. In this context, optimization strategies sizing methodologies are developed from balance system's energy demand. Therefore, robust prediction modeling thermodynamic behavior freshwater production crucial optimal design MD systems. This study presents a new advanced machine-learning model to obtain permeate flux tubular direct contact membrane unit. The was established by optimizing long-short-term memory (LSTM) election-based algorithm (EBOA). inputs were temperatures feed flow, rate salinity flow. optimized compared with other LSTM models sine–cosine (SCA), artificial ecosystem optimizer (AEO), grey wolf (GWO). All trained, tested, evaluated using different accuracy measures. LSTM-EBOA outperformed in predicting based on had highest coefficient determination 0.998 0.988 lowest root mean square error 1.272 4.180 training test, respectively. It can be recommended that paper provide useful pathway parameters selection performance systems makes optimally designed rates without costly experiments.

Language: Английский

---

Compressive strength prediction of concrete blended with carbon nanotubes using gene expression programming and random forest: hyper-tuning and optimization

Journal of Materials Research and Technology, Journal Year: 2023, Volume and Issue: 24, P. 7198 - 7218

Published: May 1, 2023

The strength of carbon nanotubes (CNTs) and cement composites is dependent on multiple variables. In addition, CNTs added to a cement-based matrix can boost its strength. However, the information related characteristics limited scarce. Their incorporation may substantially enhance mechanical durability properties cementitious mixtures. Despite challenges such as high cost workability problems. Therefore, proper consumption these materials must be used attain desired qualities. principal plan this investigation create predictive framework by utilizing machine-learning algorithms. Gene expression programming (GEP), random forest algorithm (RFA) employed estimate compressive concrete mixed with CNTs. GEP an individual approach, RFA ensemble method depict most influential model. outcomes two models are assessed employing external K-fold cross-validation, comparison done. A comprehensive database established comprising 282 data points for CS blended model then calibrated using six inputs, including curing time (CT), water-to-cement ratio (W/C), fine aggregate (FA), nanotube content (CNTs), (CC), coarse (CA). predicted results validated k-fold performance metrics, mean absolute error (MAE), root squared (RSE), correlation coefficient (R2), square (RMSE), relative (RRMSE). result shows that RF regression nth estimator robust accuracy showing minimal errors analyzed models. Likewise, depicts higher R2 = 0.96, validation demonstrate low errors. Moreover, excels in terms prediction through empirical equation. Shapley analysis (SHAP) performed check distribution parameters output. reveals time, cement, water binder have substantial influence CNT based composite.

Language: Английский

---