Using neural network for credit card fraud detection

This paper describes four neural networks multilayer perceptron (MLP) network, Elman network, NARXSP network and radial basis function (RBF) network. Neural networks are applied for identification and control of DC servo motor and benchmark nonlinear system. Number of epochs required and time taken to train the controller are shown in the form of bar plots for four neural networks. Levenberg-Marquardt algorithm is used for training the controller using neural network toolbox in MATLAB. Each neural network controller is run ten times. Their performances are compared for each run in terms of number of epochs required and time taken to train each controller for tracking a reference trajectory.

This paper presents the classification of various types of bifurcations in the voltage stability analysis of electrical power system based on ANN (Artificial Neural Networks) techniques. The bifurcations being analysed are saddle-node bifurcation and Hopf bifurcation. The bifurcations are carried out by simulating the IEEE 14 bus model under healthy and faulty conditions in PSAT toolbox. The model is created by carrying out the analysis of the data obtained from bifurcations using neural network toolbox in MATLAB.

As the nose landing gear of the aircraft has a complex structure which needs to be tough enough to withstand heavy loads during the aircraft landing. Special attention should be paid to its strength issue. This paper designs experiments to test its strength reliability. First, select the most convenient and feasible experimental device. Then, demonstrate a strength analysis of the experimental device to ensure that it meets the requirements of the experiment. In the condition that experiments are feasible, a series of experiments are carried out, including the static experiments of one-way force and fatigue experiments of triaxial forces. Use the neural network toolbox in MATLAB to analyze the mapping relationship between the load and the strain based on the experimental data. The calculated values are in good agreement with the experimental data.

Today large and mid-size companies have more complex operations which involve different types of risk and are difficult to identify the risk. To extract these risks and analyze it scientifically, a professional risk assessment tool namely ANN is most appropriate and flexible network technology. This paper briefly presents Artificial Neural Networks (ANNs), universal and highly flexible functions, approximations for any data as an application to assess risk in cement industries for instance HOLCIM CEMENT BANGLADESH LIMITED has been selected to assess risks. To assess the risks a threelayer feed forward architecture of 10 risk factors which are independent and their strength of relationship was used as relative weight of input variables. Six neurons of hidden layer and two neurons of output layer with back propagation algorithm were designed using Neural Network Toolbox of MATLAB. The input data normalized to the range 0–0.9 and initial weights were randomly selected. The algorithm propagates the weights backwards and then controls the weights. The factors were inputted to a MATLAB-based application program and the numbers of iterations were set 9000. After implementation the overall process the adjustment weights were trained and by using adjusted weights actual output was found 0.63 in which predicted value was 0.66with 95.45% prediction success, the results very promising.

During the last years, neural networks have become a very important method in the field of medical diagnostic. In this work, a technique is proposed that involves training a Multi-Layer Perceptron with back-propagation learning algorithm, in order to recognize three classes of asthma severity, through the results of breathing tests. The breathing test parameters and the diagnosis of physicians for 200 cases of children- patients, aged 10-12 years from Alexandroupolis Hospital in Greece, are used in the supervised training method to update the network parameters. This method was implemented to diagnose three asthma cases according to their severity: mild, moderate and severe asthma. Results obtained by using Neural Network Toolbox of Matlab, show that the proposed ANN can be used in asthma diagnosis with 98% success. This research work improves the asthma diagnosis accuracy with higher consistency in order to specify the seriousness of the condition of a patient and the appropriate course of medical treatment.

College Students’ mental health is an important part of higher education, so the current research and prediction of College Students’ mental health are of great significance to better solve the problem of College Students’ mental health. Taking a local university as an example, the data from 2011 to 2019 are selected and analyzed. The normalized data processing method is used to assign weights to 11 kinds of factors that affect the health of college students. The training samples of a neural network are selected, and the structural characteristics of the neural network and the artificial neural network toolbox of MATLAB are used to establish the BP based model the mathematical model of the prediction system of College Students’ mental health based on neural network. The results show that the error between the predicted value and the measured value is only 0.88%. On this basis, this paper uses the model to predict the weight of the influencing factors of the mental health status of college students in a local university in 2020 and analyzes the causes of the prediction results, to provide the basis for the current mental health education of college students.

Artificial neural network based modelling of desiccant wheel

In this study, a neural network model was developed and tested to predict the characteristics of a possible industrial wood processing based on electromagnetic technologies. The application presented in this paper is a drying process for a half-finished oak blanks exposed in a radiofrequency electromagnetic field. To develop the model of this process, MATLAB's Neural network toolbox was used. The drying process was simulated with the help of FEM-BEM.3D-RFmove _term_masa software and the simulation results were used then for the training of the proposed neural network. The trained neural network is effective to provide the process characteristics with good accuracy.

This paper presents an Artificial Neural Network (ANN) design for a chaotic generator, and the training performances for a three layer ANN architecture with different number of hidden neurons. Chaotic systems can be synchronized and used for secure communication. Chaotic systems such as Lorenz attractor, Rossler attractor and Chen's system are generally implemented directly based on their definitions represented by a unique group of ordinary differential equations (ODEs). An feed forward ANN can be trained using the output values of a chaotic system. The training process is carried out on a computer and the weights are generated for all neurons in an ANN architecture. These weights are then used for a trained ANN architecture model to generate the expected output for the target chaotic system. The complexity of the ANN architecture defines the implementation cost and speed. Therefore it is beneficial to use less number of hidden neurons to achieve the target training performance. Lorenz attractor has its significance in studying chaotic systems and is used as the design subject in this paper. The 3-layer ANN has one input, one hidden and one output layer. The ANN architecture with 1 to 16 hidden neurons is designed and trained respectively using MATLAB Neural Network Toolbox with three training algorithms: Levenberg-Marquardt, Scaled Conjugate Gradient algorithm and Bayesian Regulation. The optimized ANN architecture can be used to improve the efficiency of the fixed-point implementation on an Field Programmable Gates Array (FPGA) device.

Use of machine learning tool to elucidate and characterize the growth mechanism of an in-situ fluid bed melt granulation

All kinds of modified BP algorithms in the MATLAB's neural networks toolbox are discussed in the optimization techniques and compared with speed and memory. Different problem types applied to those algorithms are proposed.

This paper presents a novel and straightforward way of classifying discrete and surface-mount electronic components found on electronic prototypes using transfer learning and deep convolutional neural networks (DCNN). The goal of this study is to precisely classify images of electronic components into six classes: resistor, capacitor, inductor, transformer, diode, or integrated circuit. Each class of electronic components has over 100 images which are augmented and preprocessed to match the input layer requirements of the deep learning models used. The dataset was divided into a ratio of 70:30, where 70% was used for training and 30% was used for testing and validation. Transfer Learning (TL) was done using three pre-trained deep learning models that are available on MATLAB's Neural Network Toolbox: Inception-v3, GoogleNet, and Resnet101. Using this approach provides faster deployment and only requires fewer lines of coding compared to typical deep learning classification methods which make use of Python, Tensorflow, and Keras. The results of the experiment showed that Inception-v3 has the highest validation accuracy of 94.64% in classifying electronic components.

Prediction of temperature decreasing on a green roof by using artificial neural network

Glass and carbon fiber-reinforced plastics have become increasingly popular in engineering applications as relatively new materials, and it is expected that this trend will continue. E-glass laminates have become more common in aviation components such as wings, fuselages, and stabilizers as stronger, more durable, and tougher resins such as epoxies have evolved. A sudden breakdown of an engineering component like aircraft usually results in a significant financial loss, as well as posing a risk to human life. Vibration-based detection is one type of global damage identification method. Changes in physical qualities like damping, mass, and stiffness bring noticeable changes in the modal parameters in vibration-based damage detection approaches. This chapter demonstrates how vibration-based analysis can be used to forecast the severity and position of delamination in composites. The position and area of delamination in composite beams are determined using a supervised feed-forward multilayer back-propagation artificial neural network (ANN) in the MATLAB neural network toolbox.

Multiphase flow simulations are essential methods for providing information such as the evolution of phase fraction (gas, liquid and solid), velocities, pressure, temperature and flow regimes at every time during a process. Dynamic flow simulations also help reservoir, drilling, and production engineers to develop a proper well design. DamBreak problem is one of the most well-known problems in computational fluid dynamics (CFD); it is a dynamic hydraulic phenomena and the numerical simulation requires sophisticated mathematical modeling. OpenFOAM, is used to run CFD simulations in this thesis.;One of the main issues in CFD is that the simulations are time-consuming. In this work, will use artificial intelligence (AI) to predict the behavior of the system at each time-step of the process at a lower run time. DamBreak problem is defined base on a two-dimensional rectangular tank with a barrier at the bottom, the liquid column (water in this study) at the left side of the tank behind the wall. As soon as the wall collapse, the water will pour down, resulting in complicated fluid dynamics. The main data-set, generated by OpenFOAM flow simulations, is used for building the smart proxy model (SPM), using the network toolbox in MATLAB. Neural network (NN) is applied with feed-forward back propagation method and the training algorithm is Levenberg Marquardt.;Results indicate that the smart proxy can run 3 seconds of the DamBreak process, which takes 8 hours of computational time with 4 processors when is done by using OpenFOAM, takes less than 2 minutes using the developed SPM on one processor. SPM is also capable of predicting the CFD results in non-cascading condition and up to around 40 time-steps in cascading condition with acceptable error (less than %10).