Engineering characteristics of nanosilica/polymer-modified bitumen and predicting their rheological properties using multilayer perceptron neural network model

To forecast solar irradiance with higher accuracy and generalization capability is challenging in the photovoltaic (PV) energy system. Meteorological parameters are highly influential in solar irradiance, leading to intermittent and randomicity. Forecasting using a single neural network model does not have sufficient generalization ability to achieve the optimal forecasting of solar irradiance. This paper proposes a novel cooperative multi-input multilayer perceptron neural network (CMMLPNN) to mitigate the issues related to generalization and meteorological effects. Authors develop a proposed forecasting neural network model based on the amalgamation of two inputs, three inputs, four inputs, five inputs, and six inputs associated multilayer perceptron neural network. In the proposed forecasting model (CMMLPNN), the authors overcome the variance based on the meteorological parameters. The amalgamation of five multi-input multilayer perceptron neural networks leads to better generalization ability. Some individual multilayer perceptron neural network-based forecasting models outperform in some situations, but cannot assure generalization ability and suffer from the meteorological weather condition. The proposed CMMLPNN (cooperative multi-input multilayer perceptron neural network) achieves better forecasting accuracy with the generalization ability. Therefore, the proposed forecasting model is superior to other neural network-based forecasting models and existing models.

Download Full-text

Detection of Lung Cancer using Multilayer Perceptron Neural Network

Medical Technologies Journal ◽

10.26415/2572-004x-vol1iss4p109 ◽

2017 ◽

Vol 1 (4) ◽

pp. 109

Author(s):

Farzad Mirzakhani

Keyword(s):

Neural Network ◽

Lung Cancer ◽

Artificial Neural Network ◽

Positive Predictive Value ◽

Negative Predictive Value ◽

Network Model ◽

Neural Network Model ◽

Multilayer Perceptron ◽

Predictive Value ◽

Artificial Neural Network Model

Introduction: Lung cancer is the most common cancer in terms of prevalence and mortality. The cancer can be detected once it is reached to a stage that is visible in the CT imaging. Eighty six percent of the patients with lung cancer because they are late understand their disease, surgery has little effect on their improvement. Therefore, the existence of an intelligent system that can detect lung cancer in the early stages is necessary. Methods: In this study, a lung cancer dataset of UCI database was used. This dataset consists of 32 samples, 57 variables and 3 classes (each class including 10, 9 and 13 samples). The data were normalized within the range 0 to 1. Then, to increase the detection speed, the dimensions of the data were reduced by using the Principal Components Analysis (PCA). Then, using a multilayer perceptron neural network, a model for classification and prediction of lung cancer was developed. Finally, the performance of the model was measured using sensitivity, specificity, positive predictive value and negative predictive value. It should be noted that all analyzes were done using Weka software. Results: After developing and evaluating an artificial neural network model, the developed model had a sensitivity of 66.7%, a 98.5% specificity, a positive predictive value of 75%, and a negative predictive value of 97.7%. Conclusion: In intelligent diagnostic systems, in addition to high accuracy of diagnosis, the speed of diagnosis and decision making is also important. Therefore, researchers increased the speed of the prediction model by reducing 57 variables to 8 variables using PCA. Also, the high sensitivity and high specificity of developed model demonstrates high power of artificial neural network model in detecting lung cancer.

Download Full-text

A Comparison of Jordanian Bankruptcy Models: Multilayer Perceptron Neural Network and Discriminant Analysis

International Business Research ◽

10.5539/ibr.v9n12p121 ◽

2016 ◽

Vol 9 (12) ◽

pp. 121

Author(s):

Yusuf Ali Al-Hroot

Keyword(s):

Neural Network ◽

Discriminant Analysis ◽

Network Model ◽

Neural Network Model ◽

Multilayer Perceptron ◽

Classification Accuracy ◽

Type I ◽

Analysis Model ◽

Prediction Rate ◽

Two Samples

<p>The main purpose of this study is to develop and compare the classification accuracy of bankruptcy prediction models using the multilayer perceptron neural network, and discriminant analysis, for the industrial sector in Jordan. The models were developed using the ten popular financial ratios found to be useful in earlier studies and expected to predict bankruptcy. The study sample was divided into two samples; the original sample (n=14) for developing the two models and a hold-out sample (n=18) for testing the prediction of models for three years prior to bankruptcy during the period from 2000 to 2014.</p><p>The results indicated that there was a difference in prediction accuracy between models in two and three years prior to failure. The results indicated that the multilayer perceptron neural network model achieved a higher overall classification accuracy rate for all three years prior to bankruptcy than the discriminant analysis model. Furthermore, the prediction rate was 94.44% two years prior to bankruptcy using multilayer perceptron neural network model and 72.22% using the discriminant analysis model. This is a significant difference of 22.22%. On the other side, the prediction rate of 83.34% three years prior to bankruptcy using multilayer perceptron neural network model and 61.11% using discriminant analysis model. We indicate there was a difference exists of 22.23%. In addition, the multilayer perceptron neural network model provides in the ﬁrst two years prior to bankruptcy the lowest percentage of type I error.</p>

Download Full-text