ANN

Identification of flow pattern during the simultaneous flow of two immiscible liquids requires knowledge of the flow rate of each fluid as well as knowledge of other physical parameters like conduit inclination, pipe material, pipe diameter, viscosity of the oil, wetting characteristics of the pipe, design of the entry mixer, and fluid-fluid interfacial tension. This article presents an artificial neural

Chemical process control requires intelligent monitoring due to the dynamic nature of the chemical reactions and the non-linear functional relationship between the input and output variables involved. CSTR is one of the major processing unit in many chemical, pharmaceutical and petroleum industries as well as in environmental and waste management engineering. In spite of continuing advances in optimal solution techniques for optimization and control problems, many of such problems remain too complex to be solved by the known techniques. Thus, a heuristic approach is often a viable alternative. Neural Network models offer the most unified approach to building truly intelligent systems, which can provide good optimal solution for many applications. In this work we propose a hybrid (KohKal) neural network algorithm which is being used to model and solve a continuous stirred tank mixer/reactor (CSTM/R) problem which is non-linear and stochastic in nature. This hybrid algorithm is robust...

Fault detection and prediction in the semiconductor industry will enable organizations to optimize their resources and maintain a high production yield for semiconductors. However, the data generated from the sensors are producing an abundance amount of data being kept in the repository and it is difficult for process engineers to analyze and make use of the dataset to make timely and accurate fault prediction and detection. Hence, this research will focus on developing a predictive model to predict and detect faulty equipment in the semiconductor manufacturing process. The quality of the data is enhanced through various analyses, feature selection and dimensionality reduction techniques. Random Forest, Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN) will be the main algorithms used to develop the predictive models and their respective results compared to determine the best model to be used.

Face Expression Recognition is very fast growing research field in computer vision & artificial intelligence. Human Facial Expression is not just an easy and straightforward task due to several circumstances like illumination, facial occlusions, face shape/colour etc. Its applications include human-computer interfaces, human emotion analysis, and medical care and cure. The paper deals with the comparative study of neural network based approaches with its application to the facial expression recognition system.

In this paper, an intelligent control strategy for a microgrid system consisting of Photovoltaic panels, grid-connected, and li-ion battery energy storage systems proposed. The energy management based on the managing of battery charging and discharging by integration of a smart controller for DC/DC bidirectional converter. The main novelty of this solution are the integration of artificial neural network (ANN) for the estimation of the battery state of charge (SOC) and for the control of bidirectional converter. The simulation results obtained in the MATLAB/Simulink environment explain the performance and the robust of the proposed control technique.

Automatic Number Plate Recognition (ANPR) is an intelligent system which has the capability to recognize the character on vehicle number plate. Previous researches implemented ANPR system on personal computer (PC) with high resolution camera and high computational capability. On the other hand, not many researches have been conducted on the design and implementation of ANPR in smartphone platforms which has limited camera resolution and processing speed. In this paper, various steps to optimize ANPR, including pre-processing, segmentation, and optical character recognition (OCR) using artificial neural network (ANN) and template matching, were described. The proposed ANPR algorithm was based on Tesseract and Leptonica libraries. For comparison purpose, the template matching based OCR will be compared to ANN based OCR. Performance of the proposed algorithm was evaluated on the developed Malaysian number plates' image database captured by smartphone's camera. Results showed that the accuracy and processing time of the proposed algorithm using template matching was 97.5% and 1.13 seconds, respectively. On the other hand, the traditional algorithm using template matching only obtained 83.7% recognition rate with 0.98 second processing time. It shows that our proposed ANPR algorithm improved the recognition rate with negligible additional processing time.

Cancer is the most important cause of death for both men and women. The early detection of cancer can be helpful in curing the disease completely. So the requirement of techniques to detect the occurrence of cancer nodule in early stage is increasing. A disease that is commonly misdiagnosed is lung cancer. Artificial Neural Networks (ANNs) play a vital role in the medical field in solving various health problems like acute diseases and even other mild diseases. Earlier diagnosis of Lung Cancer saves enormous lives, failing which may lead to other severe problems causing sudden fatal end. Its cure rate and prognosis depends mainly on the early detection and diagnosis of the disease. This paper provides a Feed Forward Artificial Neural Network Model for early detection of lung cancer. The model consists of an input layer, a hidden layer and an output layer. The network is trained with one hidden layer and one output layer by giving twelve inputs. One of the most common forms of medica...

A neural network based software reliability model to predict the cumulative number of failures based on Feed Forward architecture is proposed in this paper. Depending upon the available software failure count data, the execution time is encoded using Exponential and Logarithmic function in order to provide the encoded value as the input to the neural network. The effect of encoding and the effect of different encoding parameter on prediction accuracy have been studied. The effect of architecture of the neural network in terms of hidden nodes has also been studied. The performance of the proposed approach has been tested using eighteen software failure data sets. Numerical results show that the proposed approach is giving acceptable results across different software projects. The performance of the approach has been compared with some statistical models and statistical models with change point considering three datasets. The comparison results show that the proposed model has a good prediction capability.

"In this paper, several soft computing approaches were employed for rainfall prediction. Two aspects were considered to improve the accuracy of rainfall prediction: (1) carrying out a data-preprocessing procedure, and (2) adopting a modular modeling method. The proposed preprocessing techniques included moving average (MA) and singular spectrum analysis (SSA). The modular models were composed of local support vectors regression (SVR) models or/and local artificial neural networks (ANN) models. In the process of rainfall forecasting, the ANN was first used to choose data-preprocessing method from MA and SSA. Modular models involved preprocessing the training data into three crisp subsets (low, medium and high levels) according to the magnitudes of the training data, and finally two SVRs were performed in the medium and high-level subsets whereas ANN or SVR was involved in training and predicting the low-level subset. For daily rainfall record, the low-level subset tended to be modeled by the ANN because it was overwhelming in the training data, which is based on the fact that the ANN is very efficient in training large-size samples due to its parallel information processing configuration. Four rainfall time series consisting of two monthly rainfalls and two daily rainfalls from different regions were utilized to evaluate modular models at 1-day, 2-day, and 3-day lead-time with the persistence method and the global ANN as benchmarks. Results showed that the MA was superior to the SSA when they were coupled with the ANN.  Comparison results indicated that modular models (referred to as ANN-SVR for daily rainfall simulations and MSVR for monthly rainfall simulations) outperformed other models. The ANN-MA also displayed considerable accuracy in rainfall forecasts compared with the benchmark.

KEYWORDS
Rainfall prediction, Moving Average, Singular spectral analysis, Fuzzy C-Means clustering, ANN, SVR, Modular model"

This paper investigates modelling of NTC thermistors using Steinhart-Hart equation for generic model generation and then parsing the same through the linearization algorithm based on Levenberg–Marquart back propagation technique with sigmoid activation function. The entire modelling and scripting of the
linearization algorithm has been accomplished in the MATLAB paradigm. The results showcase small linearity error optimal in the chebyshev norms. The reported technique has a potential for linearization of other impedance based non-linear sensors as well. Further work is in progress to integrate the algorithm
as a soft IP core in a full custom or semi-custom ASIC wherein thermistors are employed as sensors.

JOHN BARKER wrote most of the code, originally based on his 1983 paper on stochastic methods and subsequent developments.1-6 NICK ORTIZ (as an undergraduate student) wrote most of the code for MomInert. JACK PRESES (Brookhaven Nat'l Lab.) added several helpful features and helps to maintain the Windows versions. LARRY LOHR has contributed to the development of hindered rotor subroutines. ANDREA MARANZANA (University of Turin) contributed and maintains the codes for automatically generating input files for the MultiWell Suite from output files ...

Many studies have covered sorting technologies. Effective recycling based on effective sorting. Separating the different elements found in waste streams is essential for enabling the recovery of useful materials, minimizing the amount of material sent to landfill and allowing recyclable materials to find a new incarnation. In this paper we proposed waste sorting scheme based on Artificial Neural Network (ANN) with the accuracy of 92%. The aim is automate waste sorting by applying deep learning techniques to recognize the type of waste from their images. Deep learning with Back Propagation Network algorithm is used here. It separates waste into 3 main categories: Plastic, Paper and Metal using png image of the waste and implement it on a Raspberry Pi 3. The PI controls a mechanical system that guides the waste from its initial position into the corresponding container.

Machine learning is one of the aspect of artificial intelligence that allows the development of computer systems that have the ability to learn from experiences without being the need of programming it for every instance. Machine learning is dire need of today's scenario to eliminate human effort as well as come up with higher automation with less errors. This paper focuses on the review of Early Diabetes detection using machine learning techniques and detection of the frequently occurred disorders with it-mainly Diabetic retinopathy and diabetic neuropathy. The data set employed in most of the concerned literature is Pima Indian Diabetic Data Set. Early diabetes detection is significant as it helps to reduce the fatal effects of the diabetes. Various machine learning techniques like artificial neural network, principal component, decision trees, genetic algorithms, Fuzzy logic etc. have been discussed and compared. This paper first introduces the basic notions of diabetes and then describes the various techniques used to detect it. An extensive literature survey is then presented with relevant conclusion and future scopes with analysis have been discussed.

"Developing a hydrological forecasting model based on past records is crucial to effective hydropower reservoir management and scheduling. Traditionally, time series analysis and modeling is used for building mathematical models to generate hydrologic records in hydrology and water resources. Artificial intelligence (AI), as a branch of computer science, is capable of analyzing long-series and large-scale hydrological data. In recent years, it is one of front issues to apply AI technology to the hydrological forecasting modeling. In this paper, autoregressive moving-average (ARMA) models, artificial neural networks (ANNs) approaches, adaptive neural-based fuzzy inference system (ANFIS) techniques, genetic programming (GP) models and support vector machine (SVM) method are examined using the long-term observations of monthly river flow discharges. The four quantitative standard statistical performance evaluation measures, the coefficient of correlation (R), Nash-Sutcliffe efficiency coefficient (E), root mean squared error (RMSE), mean absolute percentage error (MAPE), are employed to evaluate the performances of various models developed. Two case study river sites are also provided to illustrate their respective performances. The results indicate that the best performance can be obtained by ANFIS, GP and SVM, in terms of different evaluation criteria during the training and validation phases.

Keywords: Monthly discharge time series forecasting; ARMA; ANN; ANFIS; GP; SVM"

In this paper, the author proposes a sensorless direct torque control (DTC) of an induction motor (IM) fed by seven-level NPC inverter using artificial neural networks (ANN) and fuzzy logic controller. Fuzzy PI controller is used for controlling the rotor speed and ANN applied in switching select stator voltage. The control method proposed in this paper can reduce the torque, stator flux and total harmonic distortion (THD) value of stator current, and especially improve system good dynamic performance and robustness in high and low speeds.

With the rapid development of technology in all life fields, and due to the huge daily needs for banking systems process, documents processing and other similar systems. The authentication became more required key for these systems. One of the successful system to verify the any person is the signature verification system. However, a reliable and accurate system is still needed. For this reason, the security challenge is take place via authentic signatures. However, a reliable and accurate system is still needed. For this reason, the security challenge is take place via authentic signatures. Therefore, this paper present a reliable signature verification system using proposed histogram of sparse codes (HSC) feature extraction approach and artificial neural networks (ANN) architecture for classification. The system achieved fast computing 0.09 ms and accurate verification results that is 99.7% using three different signature images datasets CEDAR, UTSig, and ICDAR.

The development of new materials shows the immense growth but the major problem, it is very difficult to machine the newly developed materials. So it is necessary to adopt some new machining methods. Electrical Discharge Machining (EDM) is a non-traditional and most popular machining method to manufacture dies, punches and press tools because of its capability to produce complicated, intricate shapes and to machine hard materials. Electrical Discharge Machining performance is generally evaluated on the basis of Overcut (OC), Material Removal Rate (MRR), Tool Wear Rate (TWR) and Surface Roughness (SR). The important EDM machining parameters affecting to the performance measures of the process are discharge current, pulse on time, pulse off time, arc gap, and duty cycle. Several approaches are proposed in the literature to solve the problems related with optimization of these parameters. It is felt that a review of the various approaches developed would help to compare their main features and their relative advantages or limitations to allow choose the most suitable approach for a particular application and also throw light on aspects that needs further attention. In view of above, this paper presents a review of Effect of Electrode Material on Overcut, MRR, TWR of Steel Material in EDM.

The ability to predict the aircraft fuel system health/operating condition and possible complications that occur during the long flight of an aircraft helps to improve the performance of the aircraft engine. Prognostics and Health Management (PHM) methodology includes fault detection, diagnosis, and prognosis. In this paper, we propose an Artificial Neural Network (ANN) based fault prognosis tool for a typical aircraft fuel system. Prognostics method using ANN's promise to provide a new approach to manage the fuel flow and fuel consumption of aircraft engine more effectively. This method identifies the presence of faults and mitigates them to maintain a proper fuel flow to the engine. Overlooking the presence of any faults in time could potentially be catastrophic which can lead to possible loss of lives and the aircraft as well. The developed tool works on the logical rules developed as per the engine's fuel consumption and quantity of fuel flow from the tanks. Here, we discuss the algorithm and the results of using ANN models to predict the health condition of the fuel system of aircraft.

Power transformer is one of the most important and expensive equipment in electrical network. The transformer oil is a very important component of power transformers. It has twin functions of cooling as well as insulation. The oil properties like viscosity, specific gravity, flash point, oxidation stability, total acid number, breakdown voltage, dissipation factor, volume resistivity and dielectric constant suffer a change with respect to time. Hence it is necessary that the oil condition be monitored regularly to predict, if possible, the remaining lifetime of the transformer oil, from time to time. Six properties such as moisture content, resistivity, tan delta, interfacial tension and flash point have been considered. The data for the six properties with respect to age, in days, has been taken from literature, whereby samples of ten working power transformers of 16 to 20 MVA installed at different substations in Punjab, India have been considered. This paper aims at developing ANN and ANFIS models for predicting the age of in-service transformer oil samples. Both the the models use the six properties as inputs and age as target. ANN (Artificial Neural Network) model uses a multi-layer feedforward network employing back propagation algorithm, and ANFIS (Adaptive Neuro Fuzzy Inference System) model is based on Sugeno model. The two models have been simulated for estimating the age of unknown transformer oil samples taken from generator transformers of Anpara Thermal Power Project in state of U.P. India. A comparative analysis of the two models has been made whereby ANFIS model has been found to yield better results than ANN model.

There are many methods of fault diagnosis of Power transformer but among all these FRA is the most suitable method for electrical and /or mechanical faults of a transformer. The concept of FRA has been successfully used as a diagnostic technique to detect the winding deformation of power transformer. In FRA measurement, the nine statistical indicators are used to detect the deviation in FRA signature. The effects of different winding parameters on FRA signature is described. The artificial neural network approach has been proposed to complement these nine indicators. ANN can be used to increase the efficiency and accuracy of diagnosis system. Neural network toolbox is used to train the multilayer feed-forward neural network. The Probabilistic neural network (PNN) approach and General Regression Neural network (GRNN) has been introduced due to its higher sensitivity and accuracy over the neural network. Neural pattern recognition toolbox is used to train the multilayer probabilistic neural network. Different practical case studies and their data are used to train and test the multilayer feed-forward neural network, probabilistic neural network and general regression neural network.Among all these AI techniques PNN gives the best accuracy result. In this work Matlab-2014 is to be used.

It has been suggested that DM may reduce survival of patients with liver cirrhosis (LC). Nevertheless only few prospective studies assessing the impact of DM on mortality of cirrhotic patients have been published, none in compensated LC. (i) to study the impact of DM on mortality and (ii) to identify predictors of death. Patients with compensated LC with and without DM were studied. Survival was analyzed by the Kaplan-Meier Method. Univariate and multivariate analysis was performed to determine independent predictors of mortality. 110 patients were included: 60 without DM and 50 with DM. Diabetic patients had significantly higher frequency of cryptogenic cirrhosis, anemia, hypoalbuminemia, and hypercreatininemia. They also had significantly higher BMI and Child-Pugh score. The 2.5-years cumulative survival was significantly lower in patients with DM (48 vs. 69%, p < 0.05). By univariate analysis: DM, female gender, serum creatinine…

In this paper, we are expounding Artificial Neural Network or ANN, its different qualities and business applications. In this paper we additionally demonstrate that "what are neural systems" and "Why they are so essential in today's Artificial knowledge?" Because various advances have been made in creating Intelligent framework, some roused by natural neural systems. ANN gives an exceptionally energizing choices and other application which can assume imperative part in today's software, Computer engineering field. There are a few Limitations likewise which are said. An Artificial Neural Network (ANN) is a data handling worldview that is motivated by the way natural sensory systems, for example, the mind, prepare data. The key component of this worldview is the novel structure of the data preparing framework. It is made out of an extensive number of exceptionally interconnected handling components (neurons) working as one to take care of particular issues. ANNs, similar to individuals, learn by illustration. An ANN is designed for a particular application, for example, design acknowledgment or information arrangement, through a learning procedure. Learning in natural frameworks includes conformity to the synaptic associations that exist between the neurons. This is valid for ANNs too. This paper gives outline of Artificial Neural Network, working and preparing of ANN. It additionally clarifies the application and points of interest of ANN.

Accurate and reliable suspended sediment load (SSL) prediction models are necessary for planning and management of water resource structures. More recently, soft computing techniques have been used in hydrological and environmental modeling. The present paper compared the accuracy of three different soft computing methods, namely, artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), coupled wavelet and neural network (WANN), and conventional sediment rating curve (SRC) approaches for estimating the daily SSL in two gauging stations in the USA. The performances of these models were measured by the coefficient of correlation (R), Nash-Sutcliffe efficiency coefficient (CE), root-mean-square error (RMSE), and mean absolute percentage error (MAPE) to choose the best fit model. Obtained results demonstrated that applied soft computing models were in good agreement with the observed SSL values, while they depicted better results than the conventional SRC method...

As compared to petroleum diesel, biodiesel is more corrosive for automotive materials. Studies on the characterization of corrosion products of fuel exposed automotive materials are scarce. Automotive fuel system and engine components are made from different ferrous and non-ferrous materials. The present study aims to investigate the corrosion products of different types of automotive materials such as copper, brass, aluminum and cast iron upon exposure to diesel and palm biodiesel. Changes in fuel properties due to exposure of different materials were also examined. Degradation of metal surface was characterized by digital camera, SEM/EDS and X-ray diffraction (XRD). Fuel properties were examined by measuring TAN (total acid number), density and viscosity. Among the metal investigated, copper is found to be least resistant in biodiesel and formed comparatively more corrosion products than other metals. Upon exposure of metals in biodiesel, TAN number crosses the limit given by standard while density and viscosity remain within the acceptable range of limit.

http://www.sciencedirect.com/science/article/pii/S0360544212001211