scholarly journals Prediction of Viscosity Values of Nanofluids at Different pH Values by Alternating Decision Tree and Multilayer Perceptron Methods

2019 ◽  
Vol 9 (7) ◽  
pp. 1288 ◽  
Author(s):  
Ahmet Demirpolat ◽  
Mehmet Das
Keyword(s):  
Decision Tree ◽  
Ethylene Glycol ◽  
Mean Square Error ◽  
Computational Intelligence ◽  
Multilayer Perceptron ◽  
Predictive Models ◽  
Mean Square ◽  
Ph Values ◽  
Alternating Decision Tree ◽  
Computational Intelligence Methods

Due to the poor thermal properties of conventional thermal fluids such as water, oil and ethylene glycol, small solid particles are added to these fluids to enhance heat transfer. Since the viscosity change determines the rheological behavior of a liquid, it is very important to examine the parameters affecting the viscosity. Since the experimental viscosity measurement is expensive and time-consuming, it is more practical to estimate this parameter. In this study, CuO (copper oxide) nanoparticles were produced and then Scanning Electron Microscope (SEM) images analyses of the produced particles were made. Nanofluids were obtained by using pure water, ethanol and ethylene glycol materials together with the produced nanoparticles and the viscosity values were calculated by experimental setups at different density and temperatures. For the viscosity values of nanofluids, predictive models were created by using different computational intelligence methods. Mean square error (MSE), root mean square error (RMSE) and mean absolute percentage error (MAPE) error analyses were used to determine the accuracy of the predictive models. The multilayer perceptron method, which has the least error value in computational methods, was chosen as the best predicting method. The multilayer perceptron method, with an average accuracy of 51%, performed better than the alternating decision tree method. As a result, the viscosity increased with the increase in the pH of the nanofluids produced by adding CuO nanoparticles and decreased with the increase in the temperature of the nanofluids. The importance of this study is to create a predictive model using computational intelligence methods for viscosity values calculated with different pH values.

scholarly journals Prediksi Harga Beras Menggunakan Metode Multilayer Perceptron (MLP) dan Long Short Term Memory (LSTM)

2020 ◽  
Vol 12 (1) ◽  
pp. 35-41
Author(s):  
Steven Sen ◽  
Dedy Sugiarto ◽  
Abdul Rochman
Keyword(s):  
Deep Learning ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Multilayer Perceptron ◽  
Short Term Memory ◽  
Mean Square ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Hidden Layer

Beras adalah salah satu komoditas utama di masyarakat Indonesia. Masalah utama dengan beras secara nasional adalah inflasi harga beras. Oleh karena itu, penelitian ini memprediksi harga beras menggunakan arsitektur jaringan saraf tiruan Multilayer Perceptron (MLP) dan deep learning : Long Short Term Memory (LSTM) untuk mengantisipasi masalah ini. Data yang digunakan dalam penelitian ini adalah data riil harga beras selama 2016 - 2019 yang diperoleh dari PT. Food Station. Total dataset adalah 1307 dengan distribusi 1123 sebagai data train dan 184 sebagai data uji. Hasil akhir yang diperoleh dalam penelitian ini adalah LSTM lebih unggul dari MLP, dengan nilai Root Mean Square Error (RMSE) data train : 0,49, dan nilai loss RMSE dari data tes adalah 0,27. Model LSTM paling optimal dari 3 tes dilakukan, yaitu jumlah hidden layer = 16 dan epochs = 150 kali.

Reinforced XGBoost machine learning model for sustainable intelligent agrarian applications

2020 ◽  
Vol 39 (5) ◽  
pp. 7605-7620 ◽  
Author(s):  
Dhivya Elavarasan ◽  
Durai Raj Vincent
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Mean Square Error ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
The Other ◽  
Gradient Boosting ◽  
Model Assessment ◽  
Mean Square ◽  
Extreme Gradient Boosting

The development in science and technical intelligence has incited to represent an extensive amount ofdata from various fields of agriculture. Therefore an objective rises up for the examination of the available data and integrating with processes like crop enhancement, yield prediction, examination of plant infections etc. Machine learning has up surged with tremendous processing techniques to perceive new contingencies in the multi-disciplinary agrarian advancements. In this pa- per a novel hybrid regression algorithm, reinforced extreme gradient boosting is proposed which displays essentially improved execution over traditional machine learning algorithms like artificial neural networks, deep Q-Network, gradient boosting, ran- dom forest and decision tree. Extreme gradient boosting constructs new models, which are essentially, decision trees learning from the mistakes of their predecessors by optimizing the gradient descent loss function. The proposed hybrid model performs reinforcement learning at every node during the node splitting process of the decision tree construction. This leads to effective utilizationofthesamplesbyselectingtheappropriatesplitattributeforenhancedperformance. Model’sperformanceisevaluated by means of Mean Square Error, Root Mean Square Error, Mean Absolute Error, and Coefficient of Determination. To assure a fair assessment of the results, the model assessment is performed on both training and test dataset. The regression diagnostic plots from residuals and the results obtained evidently delineates the fact that proposed hybrid approach performs better with reduced error measure and improved accuracy of 94.15% over the other machine learning algorithms. Also the performance of probability density function for the proposed model delineates that, it can preserve the actual distributional characteristics of the original crop yield data more approximately when compared to the other experimented machine learning models.

scholarly journals Analysis of Multi layer Perceptron Network

2013 ◽  
Vol 7 (2) ◽  
pp. 600-606
Author(s):  
Jatinder Kaur ◽  
Dr. Mandeep Singh ◽  
Pardeep Singh Bains ◽  
Gagandeep Singh
Keyword(s):  
Neural Network ◽  
Mean Square Error ◽  
Multilayer Perceptron ◽  
Function Approximation ◽  
Back Propagation ◽  
Feedforward Neural Network ◽  
Mean Square ◽  
Multi Layer Perceptron ◽  
Back Propagation Algorithm ◽  
Propagation Algorithm

In this paper, we introduce the multilayer Perceptron (feedforward) neural network (MLPs) and used it for a function approximation. For the training of MLP, we have used back propagation algorithm principle. The main purpose of this paper lies in changing the number of hidden layers of MLP for achieving minimum value of mean square error.

scholarly journals Prediction of Compressive Strength of Fly Ash Based Concrete Using Individual and Ensemble Algorithm

Materials ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 794 ◽  
Author(s):  
Ayaz Ahmad ◽  
Furqan Farooq ◽  
Pawel Niewiadomski ◽  
Krzysztof Ostrowski ◽  
Arslan Akbar ◽  
...  
Keyword(s):  
Fly Ash ◽  
Decision Tree ◽  
Mean Square Error ◽  
Gene Expression Programming ◽  
Model Performance ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Mean Square ◽  
Learning Techniques ◽  
Moderate Bias

Machine learning techniques are widely used algorithms for predicting the mechanical properties of concrete. This study is based on the comparison of algorithms between individuals and ensemble approaches, such as bagging. Optimization for bagging is done by making 20 sub-models to depict the accurate one. Variables like cement content, fine and coarse aggregate, water, binder-to-water ratio, fly-ash, and superplasticizer are used for modeling. Model performance is evaluated by various statistical indicators like mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). Individual algorithms show a moderate bias result. However, the ensemble model gives a better result with R2 = 0.911 compared to the decision tree (DT) and gene expression programming (GEP). K-fold cross-validation confirms the model’s accuracy and is done by R2, MAE, MSE, and RMSE. Statistical checks reveal that the decision tree with ensemble provides 25%, 121%, and 49% enhancement for errors like MAE, MSE, and RMSE between the target and outcome response.

The Bordeaux Automatic Meridian Circle

1978 ◽  
Vol 48 ◽  
pp. 227-228
Author(s):  
Y. Requième
Keyword(s):  
Mean Square Error ◽  
Mean Square ◽  
Meridian Circle ◽  
The Mean ◽  
Full Automation

In spite of important delays in the initial planning, the full automation of the Bordeaux meridian circle is progressing well and will be ready for regular observations by the middle of the next year. It is expected that the mean square error for one observation will be about ±0.”10 in the two coordinates for declinations up to 87°.

Investigation of Accuracy of a Calibrated Estimator of a Ratio by Modelling

2005 ◽  
Vol 10 (4) ◽  
pp. 333-342
Author(s):  
V. Chadyšas ◽  
D. Krapavickaitė
Keyword(s):  
Mean Square Error ◽  
Taylor Series ◽  
Random Sampling ◽  
Finite Population ◽  
Taylor Series Expansion ◽  
Simple Random Sampling ◽  
Population Parameter ◽  
Mean Square ◽  
Parameter Ratio ◽  
Using Data

Estimator of finite population parameter – ratio of totals of two variables – is investigated by modelling in the case of simple random sampling. Traditional estimator of the ratio is compared with the calibrated estimator of the ratio introduced by Plikusas [1]. The Taylor series expansion of the estimators are used for the expressions of approximate biases and approximate variances [2]. Some estimator of bias is introduced in this paper. Using data of artificial population the accuracy of two estimators of the ratio is compared by modelling. Dependence of the estimates of mean square error of the estimators of the ratio on the correlation coefficient of variables which are used in the numerator and denominator, is also shown in the modelling.

Performance analysis of global local mean square error criterion of stochastic linearization for nonlinear oscillator

2019 ◽  
Author(s):  
Nguyen Cao Thang ◽  
Luu Xuan Hung
Keyword(s):  
Performance Analysis ◽  
Mean Square Error ◽  
Nonlinear Oscillators ◽  
Degree Of Freedom ◽  
Equivalent Linearization ◽  
Mean Square ◽  
Error Criterion ◽  
Stochastic Linearization ◽  
Local Mean ◽  
Mean Square Error Criterion

The paper presents a performance analysis of global-local mean square error criterion of stochastic linearization for some nonlinear oscillators. This criterion of stochastic linearization for nonlinear oscillators bases on dual conception to the local mean square error criterion (LOMSEC). The algorithm is generally built to multi degree of freedom (MDOF) nonlinear oscillators. Then, the performance analysis is carried out for two applications which comprise a rolling ship oscillation and two degree of freedom one. The improvement on accuracy of the proposed criterion has been shown in comparison with the conventional Gaussian equivalent linearization (GEL).

Detection of Biomedical Images by Using Bio-inspired Artificial Intelligent

2020 ◽  
Vol 38 (2A) ◽  
pp. 255-264
Author(s):  
Hanan A. R. Akkar ◽  
Sameem A. Salman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Average Rate ◽  
Mean Square ◽  
Performance Measurements ◽  
Artificial Intelligent ◽  
Average Mean Square Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Computer vision and image processing are extremely necessary for medical pictures analysis. During this paper, a method of Bio-inspired Artificial Intelligent (AI) optimization supported by an artificial neural network (ANN) has been widely used to detect pictures of skin carcinoma. A Moth Flame Optimization (MFO) is utilized to educate the artificial neural network (ANN). A different feature is an extract to train the classifier. The comparison has been formed with the projected sample and two Artificial Intelligent optimizations, primarily based on classifier especially with, ANN-ACO (ANN training with Ant Colony Optimization (ACO)) and ANN-PSO (training ANN with Particle Swarm Optimization (PSO)). The results were assessed using a variety of overall performance measurements to measure indicators such as Average Rate of Detection (ARD), Average Mean Square error (AMSTR) obtained from training, Average Mean Square error (AMSTE) obtained for testing the trained network, the Average Effective Processing Time (AEPT) in seconds, and the Average Effective Iteration Number (AEIN). Experimental results clearly show the superiority of the proposed (ANN-MFO) model with different features.

Performance enhancement of Echo Cancellation Using a Combination of Partial Update ( PU) Methods and New Variable Length LMS (NVLLMS) Algorithm

2018 ◽  
Vol 24 (5) ◽  
pp. 66
Author(s):  
Thamer M. Jamel ◽  
Faez Fawzi Hammood
Keyword(s):  
Mean Square Error ◽  
Return Loss ◽  
Performance Enhancement ◽  
Variable Length ◽  
Echo Cancellation ◽  
Convergence Time ◽  
Length Variation ◽  
Mean Square ◽  
Step Size ◽  
Echo Return Loss Enhancement

In this paper, several combination algorithms between Partial Update LMS (PU LMS) methods and previously proposed algorithm (New Variable Length LMS (NVLLMS)) have been developed. Then, the new sets of proposed algorithms were applied to an Acoustic Echo Cancellation system (AEC) in order to decrease the filter coefficients, decrease the convergence time, and enhance its performance in terms of Mean Square Error (MSE) and Echo Return Loss Enhancement (ERLE). These proposed algorithms will use the Echo Return Loss Enhancement (ERLE) to control the operation of filter's coefficient length variation. In addition, the time-varying step size is used.The total number of coefficients required was reduced by about 18% , 10% , 6%, and 16% using Periodic, Sequential, Stochastic, and M-max PU NVLLMS algorithms respectively, compared to that used by a full update method which  is very important, especially in the application of mobile communication since the power consumption must be considered. In addition, the average ERLE and average Mean Square Error (MSE) for M-max PU NVLLMS are better than other proposed algorithms.  

Sign in / Sign up

Export Citation Format

Share Document