Back-propagation Multilayer Perceptron Neural Network Research Articles

Song’s & Non-Song’s Pattern Classification Using Neural Network

The problem of pattern classification between musical or non-musical song audio snippets and non-songs is the main subject of this paper. The machine learning approach accomplishes the goal of automatically interpreting recordings to see if they are songs or not. There are two types of songs: musical and non-musical. This is due to the possibility that it could be difficult to discern between non-musical songs and non-song patterns. Thus, it is necessary to have such systems that differentiate between non-song patterns and songs, whether or not they are melodic. The extraction and selection of characteristics have made advantage of the preprocessing phases. The features that were obtained were pitch, intensity, length (duration), tempo, and sample rate. The Back-propagation Multi-layer Perceptron Neural Network model is used for both dataset testing and model training. This technique will distinguish between a musical or non-musical song and a non-musical piece (such conversation and speech). Training data for the dataset included recordings of speeches and dialogues in Hindi and Urdu for non-song audio files, as well as audio of various male and female singers from Pakistan and India for song audio files in Hindi and Urdu. When the classifier was evaluated using a range of audio samples, 90% of its classifications for songs and non-songs were accurate.

Non-technical losses in an electrical distribution system. Energy efficiency as a continuous process

This work analyzes the problem of non-technical losses in a low-voltage electrical power distribution system with an artificial intelligence model. The problem focuses on the use of a backpropagation multilayer perceptron neural network, which will quantitatively determine these losses from the manipulation of the current profile and the voltage drop expressed as percentages of their nominal values. These two magnitudes considered, will allow obtaining from the identification of patterns with large variations a technical assessment or quantification to approach the analysis from a different perspective, differing in the methodological determination of non-technical losses currently considered as a percentage of total losses. The results obtained will allow to form a basis for the correct determination of the non-supplied energy, its influence on distribution costs and energy efficiency for the future insertion of distributed generation.

Biomechanical Study and Prediction of Lower Extremity Joint Movements Using Bayesian Regularization-Based Backpropagation Neural Network

Abstract This work aims to estimate the lower-limb joint angles in the sagittal plane using Microsoft Kinect-based experimental setup and apply an efficient machine learning technique for predicting the same based on kinematic, spatiotemporal, and biological parameters. Ten healthy participants from 19 to 50 years (33 ± 11.24 years) were asked to walk in front of the Kinect camera. Based on the skeleton image, the biomechanical hip, knee, and ankle joint angles of the lower-limb were measured using ni-labview. Thereafter, two Bayesian regularization-based backpropagation multilayer perceptron neural network models were designed to predict the joint angles in the stance and swing phase. The joint angles of two individuals, as a testing dataset, were predicted and compared with the experimental results. The test correlation coefficient for predicted joint angles has shown a promising effect of the proposed neural network models. Finally, a qualitative comparison was presented between the joint angles of healthy people and unhealthy people of similar age groups.

What Factors Influence Online Product Sales? Online Reviews, Review System Curation, Online Promotional Marketing and Seller Guarantees Analysis

This paper proposes an SFNN (a sales factor model using a neural network), which uses a back-propagation multilayer perceptron neural network and weight matrix operation, to study the mechanism of the influencing factors of online product sales in the e-commerce platform. To achieve this objective, this study analyzes the factors and relative strength of online product sales based on four aspects: online reviews, review system curation, online promotional marketing, and seller guarantees. The empirical analysis of the SFNN model based on the data of Taobao.com shows whether the 14 factors, in relation to the four aspects, have any impact on product sales. In addition, the findings indicate that the number of sentiment words greatly affects product sales. Other factors affecting online product sales significantly include the review volume, the number of uploaded pictures, the negative review rate, the discount rate, 7+day returns and money-back guarantees, and the freight insurance. This study examines the interactions among the various factors affecting product sales on the e-commerce platform and provides management inspiration for e-commerce enterprises to manipulate online reviews, undertake effective promotion and fulfill after-sales promises.

Design and implementation of Legendre‐based neural network controller in grid‐connected PV systems

This study presents the development of Legendre-based functional neural network algorithm for shunt compensation in photovoltaic (PV)-based grid-connected system. The controller is developed for improving power quality (PQ) and the compensator is controlled to work in current control mode. It injects the requisite compensating current depending on the nature of the load current. The compensator is also interfaced with PV source and the controller design incorporates its contribution too. Some of the PQ problems studied include curtailment of harmonics, providing necessary reactive power, power factor improvement and so on. Results under distorted grid, varying solar irradiation and variety of loads have been presented. The proposed algorithm is designed using non-linear functional Legendre expansion of load current and has not been used for compensation or PQ problem alleviation till date. Both simulation and experimental results verify that the proposed algorithm performs far better than the adaptive popular backpropagation multilayer perceptron neural network, recurrent neural network and non-adaptive conventional synchronous reference frame theory based techniques.

Fault diagnosis of rolling element bearing based on artificial neural network

This paper proposes the expert system for accurate fault detection of bearing. The study is based upon advanced signal processing method as wavelet transform and artificial intelligence technique as artificial neural network (ANN) and K-nearest neighbor (KNN), for fault classification of bearing. An adaptive algorithm based on wavelet transform is used to extract the fault classifying features of the bearing from time domain signal. These features have been used as inputs to proposed ANN models and the same features have also been used for KNN. Dedicated experimental setup was used to perform the test upon the bearing. Single data set for four fault conditions of bearing is collected to train ANN and KNN. The processed and normalized data was trained by using backpropagation multilayer perceptron neural network. The results obtained from ANN are compared with KNN, ANN results proved to be highly effective for classification of multiple faults.

A novel artificial intelligence approach based on Multi-layer Perceptron Neural Network and Biogeography-based Optimization for predicting coefficient of consolidation of soil

Coefficient of consolidation (Cv) is a measure of compressibility of soil. This coefficient is an important parameter which is used in the design of foundation of civil engineering structures and also in the slope stability analysis. In this study, the main objective is to propose a hybrid machine learning approach named MLP-BBO for the prediction of the coefficient of consolidation of soft soil. This method is based on Multi-layer Perceptron Neural Network (MLP) and Biogeography-based Optimization (BBO). For this, a total number of 164 soil samples were collected from the Tan Vu–Lach Huyen highway project and Ha Noi–Hai Phong highway project sites. In the modeling, input parameters used include clay (%), moisture content (%), liquid limit (%), plastic limit (%), plasticity index (%), and liquidity index (%). To validate performance of the models, standard methods such as Root-Mean-Square Error (RMSE), Mean Absolute Error (MAE), and correlation coefficient (r) were used. For the comparison of performance of the models, popular machine learning methods were used namely Backpropagation Multi-layer Perceptron Neural Networks (Bp-MLP Neural Nets), Radial Basis Functions Neural Networks (RBF-Neural Nets), Gaussian Process (GP), M5 Tree, and Support Vector Regression (SVR). Results of the model study indicate that the proposed method MLP-BBO has the highest predictive capability (RMSE = 0.397, MAE = 0.302 and r = 0.827), followed by the SVR (RMSE = 0.403, MAE = 0.299 and r = 0.819), the Bp-MLP Neural Nets (RMSE = 0.478, MAE = 0.398 and r = 0.805), the RBF-Neural Nets (RMSE = 0.412, MAE = 0.281 and r = 0.804), the GP (RMSE = 0.440, MAE = 0.301 and r = 0.777), and the M5 Tree (RMSE = 0.494, MAE = 0.322 and r = 0.728), in the prediction of Cv, respectively. Therefore, it can be concluded that though performance of all applied models is good in the prediction of the coefficient of consolidation of soil but performance of the MLP-BBO is the best.

Predicting the helpfulness of online reviews using multilayer perceptron neural networks

With the great development of e-commerce, users can create and publish a wealth of product information through electronic communities. It is difficult, however, for manufacturers to discover the best reviews and to determine the true underlying quality of a product due to the sheer volume of reviews available for a single product. The goal of this paper is to develop models for predicting the helpfulness of reviews, providing a tool that finds the most helpful reviews of a given product. This study intends to propose HPNN (a helpfulness prediction model using a neural network), which uses a back-propagation multilayer perceptron neural network (BPN) model to predict the level of review helpfulness using the determinants of product data, the review characteristics, and the textual characteristics of reviews. The prediction accuracy of HPNN was better than that of a linear regression analysis in terms of the mean-squared error. HPNN can suggest better determinants which have a greater effect on the degree of helpfulness. The results of this study will identify helpful online reviews and will effectively assist in the design of review sites.

Non-parametric modelling of a rectangular flexible plate structure

This research investigates the performance of dynamic modelling using non-parametric techniques for identification of a flexible structure system for development of active vibration control. In this paper, the implementation details are described and the experimental studies conducted in this research are analysed. The input–output data of the system were first acquired through the experimental studies using National Instruments (NI) data acquisition system. A sinusoidal force was applied to excite the flexible plate and the dynamic response of the system was then investigated. Non-parametric modelling of the system were developed using several artificial intelligent methodologies namely Adaptive Elman Neural Networks (ENN), Backpropagation Multi-layer Perceptron Neural Networks (MLPNN) and Adaptive Neuro-Fuzzy Inference System (ANFIS). The performance of all these methodologies were compared and discussed. Finally, validation and verification of the obtained model was conducted using One Step Ahead (OSA) prediction, mean squared error (MSE) and correlation tests. The prediction ability of the model was further observed with unseen data. The results verified that the MLPNN converge to an optimum solution faster and the dynamic model obtained described the flexible plate structure very well. The non-parametric models of the flexible plate structure thus developed and validated will be used as the representation of the transfer function of the system in subsequent investigations for the development of active vibration control strategies for vibration suppression in flexible structures.

Gases concentration estimation using heuristics and bio-inspired optimization models for experimental chemical electronic nose

By virtue of an electronic nose, detection and concentration estimation of harmful gases indoor become feasible by using a multi-sensor system. The estimation accuracy in actual application is constantly aspired by manufactures and researchers. This paper analyzes the application of different bio-inspired and heuristic techniques to the problem of concentration estimation in experimental electronic nose application. In this paper, seven different particle swarm optimization models are considered including six models used before in numerical function optimization, and a novel hybrid model of particle swarm optimization and adaptive genetic algorithm, for optimizing back-propagation multilayer perceptron neural network. We describe the performance of a particle swarm optimization technique, an adaptive genetic strategy and a back-propagation artificial neural network approach to perform concentration estimation of chemical gases and improve the intelligence of an E-nose.

A comparison of four methods for non-linear data modelling

This paper reports results from practical experiments with four different data modelling methods evaluated on five different real or simulated modelling problems. The methods are: partial least squares regression (PLS), back-propagation multilayer perceptron neural networks (MLP), radial basis function neural networks (RBF), and an adaptive B-spline modelling algorithm (ASMOD). The last four methods have the capability of identifying and representing general non-linear dependencies in the data without a priori specifying which specific non-linear dependencies to look for, whereas PLS needs active interaction by the data analyst to identify non-linear dependencies. The real-world modelling problems are: identifying the dynamic actuator characteristics of a hydraulic industrial robot manipulator, modelling carbon consumption as a function of other process variables in a metallurgic industrial process, and estimating water content in fish food products based on NIR spectrometry. In addition the methods have been applied for modelling data generated from a simulation of a chemical catalytic reactor, and to identify a 10-dimensional synthetic function from small samples of noisy data. Quantitative comparisons are made of the prediction accuracy in separate test data sets, and qualitative comparisons are made for some important performance characteristics, such as computation time and simplicity of use.