Comparing ANFIS and integrating algorithm models (ICA-ANN, PSO-ANN, and GA-ANN) for prediction of energy consumption for irrigation land leveling

Alzoubi, Isham; Delavar, Mahmoud Reza; Mirzaei, Farhad; Arrabi, Babak Nadjar

doi:10.1080/12269328.2017.1372225

Cited by 11 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As opposed to ANN, the ANFIS (adaptive network-based fuzzy inference system) model was developed and employed to find an ideal scheme that best fit the experimental data in the fuzzy system. Alzoubi et al [36] also performed a similar study; they compared various integrating algorithm models like ICA-ANN, GA-ANN, PSO-ANN, and ANFIS and found that the GA-ANN method was the best among them for energy consumption predictions for irrigation land leveling, due to its low RSME and high R 2 values. A concrete accomplishment of GA-ANN and GA-ANFIS tools for optimization of process parameters for xylanase bio-bleaching of mixed hardwood pulp was observed with a 28.05% increment in reducing sugar content in compared to un-optimized conditions of 21.99 mg/g [37].…”

Section: Anfis Model For the Experimental Data Trainingmentioning

confidence: 98%

Improved Pullulan Production and Process Optimization Using Novel GA–ANN and GA–ANFIS Hybrid Statistical Tools

et al. 2020

View full text Add to dashboard Cite

Pullulan production from Aureobasidium pullulans was explored to increase yield. Non-linear hybrid mathematical tools for optimization of process variables as well as the pullulan yield were analyzed. The one variable at a time (OVAT) approach was used to optimize the maximum pullulan yield of 35.16 ± 0.29 g/L. The tools predicted maximum pullulan yields of 39.4918 g/L (genetic algorithm coupled with artificial neural network (GA–ANN)) and 36.0788 g/L (GA coupled with adaptive network based fuzzy inference system (GA–ANFIS)). The best regression value (0.94799) of the Levenberg–Marquardt (LM) algorithm for ANN and the epoch error (6.1055 × 10−5) for GA–ANFIS point towards prediction precision and potentiality of data training models. The process parameters provided by both the tools corresponding to their predicted yield were revalidated by experiments. Among the two of them GA–ANFIS results were replicated with 98.82% accuracy. Thus GA–ANFIS predicted an optimum pullulan yield of 36.0788 g/L with a substrate concentration of 49.94 g/L, incubation period of 182.39 h, temperature of 27.41 °C, pH of 6.99, and agitation speed of 190.08 rpm.

show abstract

Section: Anfis Model For the Experimental Data Trainingmentioning

confidence: 98%

Improved Pullulan Production and Process Optimization Using Novel GA–ANN and GA–ANFIS Hybrid Statistical Tools

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The newest technologies based on UAV [26] open fast procedures to collect data to support decisions on the land levelling maintenance. Also, the impact analysis of PLL could be improved, as reported by Alzoubi et al [34] that have applied the methodology of genetic algorithms to predict environmental indicators for PLL, such as labor, energy, and machinery cost, opening an innovative procedure to optimize the planning and practice of PLL. Well trained operators and carefully adjusted equipment, and informed farmers, is fundamental [12].…”

Section: Discussionmentioning

confidence: 99%

“…The plan method is the most common, with several options in the criteria of optimization and calculation of volumes and working times. The cut and fill areas and their depths and volumes can be identified and used to plan the field operation and assess costs and soil and energy impacts [34]. The study of the soil profile should evaluate the maximum cut that can be made without permanently effecting agricultural production.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Precise Land Levelling on Surface Irrigation Development. Impacts on Maize Water Productivity and Economics

Miao

Gonçalves

et al. 2021

Sustainability

View full text Add to dashboard Cite

The new technologies of surface irrigation require the adoption of effective Laser-controlled precision land levelling (PLL) to reach the high irrigation performance standards, with significant benefits on water saving, salinity control, crop productivity, and farmer’s income. This study aimed to assess the performance and the impacts of PLL on surface irrigation systems, focusing the maize crop on the irrigation districts Hetao (China) and Lower-Mondego (Portugal). The experimental study at field scale assessed the PLL and evaluated the on-farm irrigation under precise levelled fields and well management practices. PLL operators have been inquired to improve the knowledge about hiring services. The design of surface irrigation scenarios allowed to explain the effects of field size and slope on irrigation and land levelling performance. The best practice to manage the PLL maintenance is an important issue to guarantee a high effectiveness of irrigation performance. The optimization of PLL appeals the application of best soil tillage practices and the monitoring of soil surface elevations with newest information technologies. Efficient operational guidelines to support the PLL planning, schedule, and operation, well trained operators and carefully adjusted equipment, are key factors to the improvement.

show abstract

“…In this approach, raw features are transformed into latent variables by statistical learners such as principal component analysis (Varkeshi et al 2020), partial least squares regression (Putro, Saputro, and Imawan 2018), and independent component analysis (Alzoubi et al 2018), before being input into the neural network. The second approach utilizes statistical learning after neural network processing, employing neural networks for feature extraction and statistical models for discrimination (Chen et al 2018;Sun et al 2017).…”

Section: Related Workmentioning

confidence: 99%

Improving Neural Network Generalization on Data-Limited Regression with Doubly-Robust Boosting

Wang

2024

AAAI

View full text Add to dashboard Cite

Enhancing the generalization performance of neural networks given limited data availability remains a formidable challenge, due to the model selection trade-off between training error and generalization gap. To handle this challenge, we present a posterior optimization issue, specifically designed to reduce the generalization error of trained neural networks. To operationalize this concept, we propose a Doubly-Robust Boosting machine (DRBoost) which consists of a statistical learner and a zero-order optimizer. The statistical learner reduces the model capacity and thus the generalization gap; the zero-order optimizer minimizes the training error in a gradient-free manner. The two components cooperate to reduce the generalization error of a fully trained neural network in a doubly robust manner. Furthermore, the statistical learner alleviates the multicollinearity in the discriminative layer and enhances the generalization performance. The zero-order optimizer eliminates the reliance on gradient calculation and offers more flexibility in learning objective selection. Experiments demonstrate that DRBoost improves the generalization performance of various prevalent neural network backbones effectively.

show abstract

Comparing ANFIS and integrating algorithm models (ICA-ANN, PSO-ANN, and GA-ANN) for prediction of energy consumption for irrigation land leveling

Cited by 11 publications

References 30 publications

Improved Pullulan Production and Process Optimization Using Novel GA–ANN and GA–ANFIS Hybrid Statistical Tools

Improved Pullulan Production and Process Optimization Using Novel GA–ANN and GA–ANFIS Hybrid Statistical Tools

Assessment of Precise Land Levelling on Surface Irrigation Development. Impacts on Maize Water Productivity and Economics

Improving Neural Network Generalization on Data-Limited Regression with Doubly-Robust Boosting

Contact Info

Product

Resources

About