Feedforward Neural Network Technique Research Articles

Power Increase due to Marine Biofouling: a Grey-box Model Approach

This paper proposes a grey-box modelling approach to predict marine biofouling growth and its effects on ship performance. The approach combines empirical or experimental-based white-box models with data-driven black-box models. First, a white-box model is built to predict ship resistance considering a bare hull. This prediction is based on calm water resistance, wind, waves, and temperature differences. Subsequently, marine biofouling growth is predicted using an experimental model that estimates the level of roughness on the ship hull. Finally, a deep extreme learning machine is used as a black-box model, employing a feedforward neural network technique. To test the approach, a superyacht case study was selected as a category of vessel heavily exposed to fouling. The study used a 2-year dataset obtained through a collaboration with Feadship. Results showed that the black-box approach outperforms the white-box approach in predictive capabilities. However, when the knowledge encapsulated in the white-box model is included in the grey-box approach, the model shows the highest prediction accuracy achieved by leveraging less historical data. This study demonstrates the potential of the proposed grey-box approach to accurately predict marine biofouling growth and its effects on ship performance, which can benefit ship operators and designers in improving operational efficiency and reducing maintenance costs.

Using machine learning to improve Q-matrix validation.

The Q-matrix, which specifies the relationship between items and attributes, is a crucial component of cognitive diagnostic models (CDMs). A precisely specified Q-matrix allows for valid cognitive diagnostic assessments. In practice, a Q-matrix is usually developed by domain experts, and noted as being subjective and potentially containing misspecifications which can decrease the classification accuracy of examinees. To overcome this, some promising validation methods have been proposed, such as the general discrimination index (GDI) method and the Hull method. In this article, we propose four new methods for Q-matrix validation based on random forest and feed-forward neural network techniques. Proportion of variance accounted for (PVAF) and coefficient of determination (i.e., the McFadden pseudo-R2) are used as input features for developing the machine learning models. Two simulation studies are carried out to examine the feasibility of the proposed methods. Finally, a sub-dataset of the PISA 2000 reading assessment is analyzed as illustration.

Development of Power Transformer Health Index Assessment Using Feedforward Neural Network

The role of a power transformer is to convert the electrical power level and send it to the consumer, making it an essential component of a power system. In addition, transformer asset management is essential for monitoring the functioning of transformers in the system to prevent failure and anticipating the health state of transformers, using a technique known as the health index (HI). However, the calculation and computation to determine the transformer HI based on a scoring and ranking technique is complex and required expert validation. Therefore, this paper presents a transformer HI prediction using a feedforward neural network (FFNN) to improve the existing complex scoring and ranking technique. Levenberg–Marquardt (LM), Bayesian Regularized (BR), and Scaled Conjugate Gradient (SCG) are the FFNN training techniques presented in this study to forecast the transformer HI. To validate the techniques, the HI values generated by different FFNN techniques were compared to the scoring and ranking system. Then, the performance of the proposed ANN was evaluated using the correlation coefficient and mean square error (MSE). As a result, the transformer HI was successfully predicted by employing three FFNN techniques, namely the LM, BR, and SCG techniques, which were able to determine whether the transformer's condition is very good, good, fair, or poor. In conclusion, the ANN suggested in this study has also been validated with the ranking and scoring approach, which provides high similarity score in comparison to the transformer health index.

Deep learning Feedforward Neural Network in predicting model of Environmental risk factors in the Sohar region

AQI (Air Quality Index) is the standard degree that guides us to measure air pollution levels such as PM2.5, O3, NO2, and SO2 to show the state of air quality. Polluted gas causes much damage and problems to people, plants, and the environment because of its negative impact. Data mining successfully examines an enormous cluster of data to recognize associations, determine relations between variables, and predict future values. In this paper, an experimental study was performed on analyzing the previous dataset of (PM2.5 and O3) for accurately predicting AQI using deep learning Feedforward Neural network techniques. The deep learning (Feedforward Neural Network (FFNN) predicting models are employed to evaluate based on R, R², MSE, MAE, and RMSE criteria using historical data from (the Ministry of Environment-Oman). Different epochs and a different number of hidden layers are deployed to improve and boost performance. In FFNN, the epochs number increase by 50,100 and 500 while the hidden layer utilized to 1,5 and 10. This optimization technique exceeds the performance from R=0.892 to R=0.992 in predicting the level of (PM2.5) and the (O3) from R=0.864 to R=0.999. The results show that the Sohar Region in a safe level of AQI.

Investigation of Performance of Electric Load Power Forecasting in Multiple Time Horizons With New Architecture Realized in Multivariate Linear Regression and Feed-Forward Neural Network Techniques

A new multiple parallel input and parallel output architecture-based models are developed for forecasting electric load power consumption. Attention was paid toward the improvement of the accuracy of forecasting using this new architecture built-in by us, as compared to others in the latest literature. The models have an ability to forecast daily load profiles with a lead time of one to seven days. Both multivariate linear regression and feed-forward neural network techniques have been chosen for comparative performance study and analysis. The real-time data used for this research work were collected from Tata Power Delhi Distribution Limited, Delhi, India. Based on the performance criteria provided in the literature, each model is analyzed and the results are presented for two different lead times, i.e., day-ahead and week-ahead only.

Evaluation of dielectric strength of SiR/TiO 2 composites using feed‐forward neural network

Among the recently insulating materials broadly utilized in high voltage outdoor insulation, silicone rubber (SiR) has gotten the foremost consideration. Actually, SiR is becoming an efficient countermeasure to insulator contamination issues. To enhance different properties of polymeric materials, micro- and nanofillers have been used for dielectric applications. In this study, micron-sized titanium dioxide (TiO2) and nano-sized TiO2 fillers were added to the SiR matrix to improve electrical and mechanical properties. Dielectric strength, tensile strength, and elongation at break tests were monitored. Also, a scanning electron microscope was carried out. The samples were prepared by mixing micro-TiO2 into SiR with the content of 0, 10, 20, 30, and 40 wt% and also mixing nano-TiO2 into SiR with the content of 0, 1, 3, 5, and 7 wt%. A feed-forward neural network technique was used to estimate the dielectric strength in different conditions and different percentages of fillers. Adding nano TiO2 filler enhances the electrical and mechanical properties of SiR composites. SiR with 5 wt% nano TiO2 showed the best improvement in electrical and mechanical properties.

Diagnosis of Type II Diabetes Based on Feed forward Neural Network Techniques

Diabetes is a disease caused by an increase in blood glucose levels due to insulin secretion deficiency (type I diabetes) or impaired insulin activity (type II diabetes). More than 90% of people with this condition are diagnosed with type II diabetes. Due to the sharply prevalence of type 2 diabetes in recent years, the prognosis and early diagnosis of the disease have become even more important. In this study, a model for diagnosis of type II diabetes was developed using Artificial Neural Network (ANN) method. The execution of the Frequent Pattern Growth algorithm on medical data is difficult. Association rule-based classification is an interesting area focused that can be utilized for early diagnosis. The discretization phase is necessary to transform numerical characteristics. Pima Indians Diabetes Data Set is taken as an input. The execution time, a number of rules generation and the detection of outlier percentage are analyzed. The CFP-growth algorithm utilizes for finding frequent patterns where constructing the Minimum Item Support (MIS)-tree, CFP-array and producing frequent patterns from the MIS-tree. From the set of frequent itemsets found, create all the association rules that have confidence exceeding the minimum confidence. In this study, we aim to build a model that helps Physicians in predicting Diabetes early and accurately. Data were collected from the PIMA Indian data set. Consisted of 768 samples (268 diabetic and 500 non-diabetics). Levenberg-Marquardt back-propagation algorithm was used to train the network, and the accuracy of the prediction of whether a person is diabetics or not was 88.8%.

Hybrid Feature Extraction Approach for Handwritten Character Classification Using Feed-forward Neural Network Techniques

Hybrid Feature Extraction Approach for Handwritten Character Classification Using Feed-forward Neural Network Techniques

MODELLING MASONRY CREW PRODUCTIVITY USING TWO ARTIFICIAL NEURAL NETWORK TECHNIQUES

Artificial neural networks have been effectively used in various civil engineering fields, including construction management and labour productivity. In this study, the performance of the feed forward neural network (FFNN) was compared with radial basis neural network (RBNN) in modelling the productivity of masonry crews. A variety of input factors were incorporated and analysed. Mean absolute percentage error (MAPE) and correlation coefficient (R) were used to evaluate model performance. Research results indicated that the neural computing techniques could be successfully employed in modelling crew productivity. It was also found that successful models could be developed with different combinations of input factors, and several of the models which excluded one or more input factors turned out to be better than the baseline models. Based on the MAPE values obtained for the models, the RBNN technique was found to be better than the FFNN technique, although both slightly overestimated the masons’ productivity.

Application of Feed-Forward Neural Networks for Classifying Acoustics Levels in Vehicle Cabin

Vehicle acoustical comfort and vibration in a passenger car cabin are the main factors that attract a buyer in car purchase. Numerous studies have been carried out by automotive researchers to identify and classify the acoustics level in the vehicle cabin. The objective is to form a special benchmark for acoustics level that may be referred for any acoustics improvement purpose. This study is focused on the sound quality change over the engine speed [rp to recognize the noise pattern experienced in the vehicle cabin. Since it is difficult for a passenger to express, and to evaluate the noise experienced or heard in a numerical scale, a neural network optimization approach is used to classify the acoustics levels into groups of noise annoyance levels. A feed forward neural network technique is applied for classification algorithm, where it can be divided into two phases: Learning Phase and Classification Phase. The developed model is able to classify the acoustics level into numerical scales which are meaningful for evaluation purposes.

Sizing of Energy Storage for Microgrids

This paper presents a new method based on the cost-benefit analysis for optimal sizing of an energy storage system in a microgrid (MG). The unit commitment problem with spinning reserve for MG is considered in this method. Time series and feed-forward neural network techniques are used for forecasting the wind speed and solar radiations respectively and the forecasting errors are also considered in this paper. Two mathematical models have been built for both the islanded and grid-connected modes of MGs. The main problem is formulated as a mixed linear integer problem (MLIP), which is solved in AMPL (A Modeling Language for Mathematical Programming). The effectiveness of the approach is validated by case studies where the optimal system energy storage ratings for the islanded and grid-connected MGs are determined. Quantitative results show that the optimal size of BESS exists and differs for both the grid-connected and islanded MGs in this paper.

Economic Time Series Forecasting: Box-Jenkins Methodology, Signal Processing and Neural Network Approach

This paper is devoted to the presentation of methods of economic time series analysis and modelling using the Box-Jenkins methodology, the signal processing approach and the feedforward neural network technique. Some results of our research on time series modelling with emphasis on potential improving forecast accuracy are presented here. The assessment of the particular models has been made using the root mean square error.

A viscosity equation of state for R134a through a multi-layer feedforward neural network technique

A multi-layer feedforward neural network (MLFN) technique is adopted for developing a viscosity equation η= η( ρ, T) for R134a. The results obtained are very promising, with an average absolute deviation (AAD) of 0.63% for the currently available 571 primary data points, and are a significant improvement over those of a corresponding conventional equation in the literature. The method requires a high accuracy equation of state for the fluid in order to convert the experimental P, T into the independent variables ρ, T, but such an equation may not be available for the target fluid. Aiming at overcoming this difficulty, a viscosity implicit equation of state in the form T= T( η, P), avoiding the density variable, is developed for the liquid surface. The attained accuracy level is equivalent to that of the former equation. The proposed technique, being completely correlative and non theoretically founded, is also a powerful tool for experimental data screening.

Improving the odds in discriminating "drug-like" from "non drug-like" compounds.

We have used a feed-forward neural network technique to classify chemical compounds into potentially "drug-like" and "non drug-like" candidates. The neural network was trained to distinguish between a set of "drug-like" and "non drug-like" chemical compounds taken from the MACCS-II Drug Data Report (MDDR) and the Available Chemicals Directory (ACD). The 2D atom types (of the full atomic representation) were assigned and applied as descriptors to encode numerically each compound. There are four main conclusions: First the method performs well, correctly assigning 88% of the compounds in both MDDR and ACD. Improved discrimination was achieved by a more critical selection of training sets. Second, the method gives much better prediction performance than the widely used "Rule of Five", which accepts as many as 74% of the ACD compounds but only 66% of those in MDDR, resulting in a correlation coefficient which is effectively zero, compared to a value of 0.63 for the neural network prediction. Third, based on a standard Tanimoto similarity search the selection of drug-like compounds in the evaluation set is not biased toward compounds similar to those in the training set. Fourth, the trained neural network was applied to evaluate the drug-likeness of 136 GABA uptake inhibitors with impressive results. The implications of applying a neural network to characterize chemical compounds are discussed.