scholarly journals Improving Drought Modeling Using Hybrid Random Vector Functional Link Methods

Water ◽  
2021 ◽  
Vol 13 (23) ◽  
pp. 3379
Author(s):  
Rana Muhammad Adnan ◽  
Reham R. Mostafa ◽  
Abu Reza Md. Towfiqul Islam ◽  
Alireza Docheshmeh Gorgij ◽  
Alban Kuriqi ◽  
...  
Keyword(s):  
Random Vector ◽  
Hybrid Methods ◽  
Search Algorithm ◽  
Absolute Error ◽  
Monthly Precipitation ◽  
Drought Forecasting ◽  
Functional Link ◽  
Hunger Games ◽  
Drought Modeling ◽  
Mean Square Errors

Drought modeling is essential in water resources planning and management in mitigating its effects, especially in arid regions. Climate change highly influences the frequency and intensity of droughts. In this study, new hybrid methods, the random vector functional link (RVFL) integrated with particle swarm optimization (PSO), the genetic algorithm (GA), the grey wolf optimization (GWO), the social spider optimization (SSO), the salp swarm algorithm (SSA) and the hunger games search algorithm (HGS) were used to forecast droughts based on the standard precipitation index (SPI). Monthly precipitation data from three stations in Bangladesh were used in the applications. The accuracy of the methods was compared by forecasting four SPI indices, SPI3, SPI6, SPI9, and SPI12, using the root mean square errors (RMSE), the mean absolute error (MAE), the Nash–Sutcliffe efficiency (NSE), and the determination coefficient (R2). The HGS algorithm provided a better performance than the alternative algorithms, and it considerably improved the accuracy of the RVFL method in drought forecasting; the improvement in RMSE for the SPI3, SP6, SPI9, and SPI12 was by 6.14%, 11.89%, 14.14%, 24.5% in station 1, by 6.02%, 17.42%, 13.49%, 24.86% in station 2 and by 7.55%, 26.45%, 15.27%, 13.21% in station 3, respectively. The outcomes of the study recommend the use of a HGS-based RVFL in drought modeling.

Classification of methods for generating pseudo-CT from MRI images for MRI-alone RT

2017 ◽  
Vol 1 (3) ◽  
pp. 54
Author(s):  
BOUKELLOUZ Wafa ◽  
MOUSSAOUI Abdelouahab
Keyword(s):  
Performance Metrics ◽  
Radiation Treatment ◽  
Hybrid Methods ◽  
Dose Calculation ◽  
Absolute Error ◽  
Ct Images ◽  
General Technique ◽  
Therapy Field ◽  
The Brain

Background: Since the last decades, research have been oriented towards an MRI-alone radiation treatment planning (RTP), where MRI is used as the primary modality for imaging, delineation and dose calculation by assigning to it the needed electron density (ED) information. The idea is to create a computed tomography (CT) image or so-called pseudo-CT from MRI data. In this paper, we review and classify methods for creating pseudo-CT images from MRI data. Each class of methods is explained and a group of works in the literature is presented in detail with statistical performance. We discuss the advantages, drawbacks and limitations of each class of methods. Methods: We classified most recent works in deriving a pseudo-CT from MR images into four classes: segmentation-based, intensity-based, atlas-based and hybrid methods. We based the classification on the general technique applied in the approach. Results: Most of research focused on the brain and the pelvis regions. The mean absolute error (MAE) ranged from 80 HU to 137 HU and from 36.4 HU to 74 HU for the brain and pelvis, respectively. In addition, an interest in the Dixon MR sequence is increasing since it has the advantage of producing multiple contrast images with a single acquisition. Conclusion: Radiation therapy field is emerging towards the generalization of MRI-only RT thanks to the advances in techniques for generation of pseudo-CT images. However, a benchmark is needed to set in common performance metrics to assess the quality of the generated pseudo-CT and judge on the efficiency of a certain method.

EXPRESS: Baseline Correction Based on a Search Algorithm from Artificial Intelligence

2020 ◽  
pp. 000370282097751
Author(s):  
Xin Wang ◽  
Xia Chen
Keyword(s):  
Artificial Intelligence ◽  
Objective Function ◽  
Least Squares ◽  
Least Squares Method ◽  
Search Algorithm ◽  
Absolute Error ◽  
Search Problem ◽  
Baseline Correction ◽  
Current Spectrum ◽  
Data Points

Many spectra have a polynomial-like baseline. Iterative polynomial fitting (IPF) is one of the most popular methods for baseline correction of these spectra. However, the baseline estimated by IPF may have substantially error when the spectrum contains significantly strong peaks or have strong peaks located at the endpoints. First, IPF uses temporary baseline estimated from the current spectrum to identify peak data points. If the current spectrum contains strong peaks, then the temporary baseline substantially deviates from the true baseline. Some good baseline data points of the spectrum might be mistakenly identified as peak data points and are artificially re-assigned with a low value. Second, if a strong peak is located at the endpoint of the spectrum, then the endpoint region of the estimated baseline might have significant error due to overfitting. This study proposes a search algorithm-based baseline correction method (SA) that aims to compress sample the raw spectrum to a dataset with small number of data points and then convert the peak removal process into solving a search problem in artificial intelligence (AI) to minimize an objective function by deleting peak data points. First, the raw spectrum is smoothened out by the moving average method to reduce noise and then divided into dozens of unequally spaced sections on the basis of Chebyshev nodes. Finally, the minimal points of each section are collected to form a dataset for peak removal through search algorithm. SA selects the mean absolute error (MAE) as the objective function because of its sensitivity to overfitting and rapid calculation. The baseline correction performance of SA is compared with those of three baseline correction methods: Lieber and Mahadevan–Jansen method, adaptive iteratively reweighted penalized least squares method, and improved asymmetric least squares method. Simulated and real FTIR and Raman spectra with polynomial-like baselines are employed in the experiments. Results show that for these spectra, the baseline estimated by SA has fewer error than those by the three other methods.

Design and application of an optimally tuned PID controller for DC motor speed regulation via a novel hybrid Lévy flight distribution and Nelder–Mead algorithm

2021 ◽  
pp. 014233122110196
Author(s):  
Davut Izci
Keyword(s):  
Pid Controller ◽  
Search Algorithm ◽  
Cuckoo Search ◽  
Absolute Error ◽  
Dc Motor ◽  
Cuckoo Search Algorithm ◽  
Lévy Flight ◽  
Motor Speed ◽  
Levy Flight ◽  
Speed Regulation

This paper deals with the design of an optimally performed proportional–integral–derivative (PID) controller utilized for speed control of a direct current (DC) motor. To do so, a novel hybrid algorithm was proposed which employs a recent metaheuristic approach, named Lévy flight distribution (LFD) algorithm, and a simplex search method known as Nelder–Mead (NM) algorithm. The proposed algorithm (LFDNM) combines both LFD and NM algorithms in such a way that the good explorative behaviour of LFD and excellent local search capability of NM help to form a novel hybridized version that is well balanced in terms of exploration and exploitation. The promise of the proposed structure was observed through employment of a DC motor with PID controller. Optimum values for PID gains were obtained with the aid of an integral of time multiplied absolute error objective function. To verify the effectiveness of the proposed algorithm, comparative simulations were carried out using cuckoo search algorithm, genetic algorithm and original LFD algorithm. The system behaviour was assessed through analysing the results for statistical and non-parametric tests, transient and frequency responses, robustness, load disturbance, energy and maximum control signals. The respective evaluations showed better performance of the proposed approach. In addition, the better performance of the proposed approach was also demonstrated through experimental verification. Further evaluation to demonstrate better capability was performed by comparing the LFDNM-based PID controller with other state-of-the-art algorithms-based PID controllers with the same system parameters, which have also confirmed the superiority of the proposed approach.

Utilization of random vector functional link integrated with manta ray foraging optimization for effluent prediction of wastewater treatment plant

2021 ◽  
Vol 298 ◽  
pp. 113520
Author(s):  
Khaled Elmaadawy ◽  
Mohamed Abd Elaziz ◽  
Ammar H. Elsheikh ◽  
Ahmed Moawad ◽  
Bingchuan Liu ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Random Vector ◽  
Wastewater Treatment Plant ◽  
Treatment Plant ◽  
Functional Link ◽  
Manta Ray

scholarly journals A Power Transformer Fault Diagnosis Method Based on Random Vector Functional-Link Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Qian Wang ◽  
Shinan Wang ◽  
Rong Shi ◽  
Yong Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Network Model ◽  
Random Vector ◽  
Network Structure ◽  
Theoretical Basis ◽  
Parameter Selection ◽  
Functional Link ◽  
Transformer Fault ◽  
Hidden Nodes

The random vector functional link (RVFL) network is suitable for solving nonlinear problems from transformer fault symptoms and different fault types due to its simple structure and strong generalization ability. However, the RVFL network has a disadvantage in that the network structure, and parameters are basically determined by experiences. In this paper, we proposed a method to improve the RVFL neural network algorithm by introducing the concept of hidden node sensitivity, classify each hidden layer node, and remove nodes with low sensitivity. The simplified network structure could avoid interfering nodes and improve the global search capability. The five characteristic gases produced by transformer faults are divided into two groups. A fault diagnosis model of three layers with four classifiers was built. We also investigated the effects of the number of hidden nodes and scale factors on RVFL network learning ability. Simulation results show that the number of implicit layer nodes has a large impact on the network model when the number of input dimensions is small. The network requires a higher number of implicit layer neurons and a smaller threshold range. The size of the scale factor has significant influence on the network model with larger input dimension. This paper describes the theoretical basis for parameter selection in RVFL neural networks. The theoretical basis for the selection of the number of hidden nodes, and the scale factor is derived. The importance of parameter selection for the improvement of diagnostic accuracy is verified through simulation experiments in transformer fault diagnosis.

scholarly journals A Maximum Entropy Production Evaporation – Transpiration Product for Australia

2019 ◽  
Author(s):  
Olanrewaju Abiodun ◽  
Okke Batelaan ◽  
Huade Guan ◽  
Jingfeng Wang
Keyword(s):  
Entropy Production ◽  
Maximum Entropy ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Production Model ◽  
Model Parameters ◽  
Drought Period ◽  
Maximum Entropy Production ◽  
Millennium Drought ◽  
Mean Square Errors

Abstract. The aim of this research is to develop evaporation and transpiration products for Australia based on the maximum entropy production model (MEP). We introduce a method into the MEP algorithm of estimating the required model parameters over the entire Australia through the use of pedotransfer function, soil properties and remotely sensed soil moisture data. Our algorithm calculates the evaporation and transpiration over Australia on daily timescales at the 5 km2 resolution for 2003–2013. The MEP evapotranspiration (ET) estimates are validated using observed ET data from 20 Eddy Covariance (EC) flux towers across 8 land cover types in Australia. We also compare the MEP ET at the EC flux towers with two other ET products over Australia; MOD16 and AWRA-L products. The MEP model outperforms the MOD16 and AWRA-L across the 20 EC flux sites, with average root mean square errors (RMSE), 8.21, 9.87 and 9.22 mm/8 days respectively. The average mean absolute error (MAE) for the MEP, MOD16 and AWRA-L are 6.21, 7.29 and 6.52 mm/8 days, the average correlations are 0.64, 0.57 and 0.61, respectively. The percentage Bias of the MEP ET was within 20 % of the observed ET at 12 of the 20 EC flux sites while the MOD16 and AWRA-L ET were within 20 % of the observed ET at 4 and 10 sites respectively. Our analysis shows that evaporation and transpiration contribute 38 % and 62 %, respectively, to the total ET across the study period which includes a significant part of the “millennium drought” period (2003–2009) in Australia. The data (Abiodun et al., 2019) is available at https://doi.org/10.25901/5ce795d313db8.

Sign in / Sign up

Export Citation Format

Share Document