Multi-layer perceptron (MLP) neural network technique for offline handwritten Gurmukhi character recognition

Singh, Gurpreet; Sachan, Manoj Kumar

doi:10.1109/iccic.2014.7238334

Cited by 46 publications

(15 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Set f (·) as the activation function and x n ∈R 1*n , w n ∈R n*1 , b∈R q*n . Thus, the forward propagation mode from the input layer to the output layer is [30]…”

Section: Mlp Model Establishmentmentioning

confidence: 99%

Prediction of I–V Characteristic Curve for Photovoltaic Modules Based on Convolutional Neural Network

Jia

et al. 2020

Sensors

View full text Add to dashboard Cite

Photovoltaic (PV) modules are exposed to the outside, which is affected by radiation, the temperature of the PV module back-surface, relative humidity, atmospheric pressure and other factors, which makes it difficult to test and analyze the performance of photovoltaic modules. Traditionally, the equivalent circuit method is used to analyze the performance of PV modules, but there are large errors. In this paper-based on machine learning methods and large amounts of photovoltaic test data-convolutional neural network (CNN) and multilayer perceptron (MLP) neural network models are established to predict the I-V curve of photovoltaic modules. Furthermore, the accuracy and the fitting degree of these methods for current-voltage (I-V) curve prediction are compared in detail. The results show that the prediction accuracy of the CNN and MLP neural network model is significantly better than that of the traditional equivalent circuit models. Compared with MLP models, the CNN model has better accuracy and fitting degree. In addition, the error distribution concentration of CNN has better robustness and the pre-test curve is smoother and has better nonlinear segment fitting effects. Thus, the CNN is superior to MLP model and the traditional equivalent circuit model in complex climate conditions. CNN is a high-confidence method to predict the performance of PV modules. from the measured current-voltage (I-V) characteristic curves is important for evaluation, modeling and diagnosis of the actual operating state of in situ PV arrays [14]. Nowadays, manufacturers of photovoltaic modules provide standard reporting condition (SRC) or standard test condition (STC) ratings of PV modules. The main test conditions of PV modules are mainly under laboratory environment, which include irradiation intensity of 1000 W/m 2 , spectral distribution in accordance with the AM1.5 spectrum and temperature of 25 ± 1 • C for the PV module. However, in the practical engineering environment (outdoor weather conditions), these conditions rarely appear at the same time. The adequacy and applicability of PV modules under STC is still a controversial issue [15]. Actually, the PV modules based on SRC are still unreasonable for the real-world weather conditions. Therefore, performance test of PV module based on STC condition needs to be improved in the outdoor weather conditions [16]. Although the outdoor characteristics of PV modules can be predicted by algebraic or numerical methods, these methods used in photovoltaic system engineering ignore some second-order effects, like wind speed, shunt resistance, parasitic capacitance, spectral effect and non-linearity under low illumination, thus the prediction error of these methods is large [17]. Based on this, many photovoltaic modeling methods have been proposed in recent years. Generally, these methods can be divided into two types: the white box model based on equivalent circuit and the black box model based on regression [18][19][20]. The equivalent circuit method is used for the prediction of photovolta...

show abstract

“…Set f (·) as the activation function and x n ∈R 1*n , w n ∈R n*1 , b∈R q*n . Thus, the forward propagation mode from the input layer to the output layer is [30]…”

Section: Mlp Model Establishmentmentioning

confidence: 99%

Prediction of I–V Characteristic Curve for Photovoltaic Modules Based on Convolutional Neural Network

Jia

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The architecture of CNN(Convolution Neural Network) is designed using multi layer feed forward network, which is tailored to minimize the sensitivity, translation, distortions and rotations of the input images [14]. Insensitivity toward nearby changes is incorporated with the system engineering by compelling arrangements of every units situated at better places to utilize indistinguishable weight vectors, in this way constraining them to distinguish a similar component on various pieces of the input [1].…”

Section: B Convolution Neural Networkmentioning

confidence: 99%

Segmentation and Identification of Bilingual Offline Handwritten Scripts (Devanagari and Roman)

2019

IJRTE

View full text Add to dashboard Cite

 Abstract: Hand written text acknowledgment field has been considered as one of the hardest issues in the digital word. The multifaceted nature dimension of this exploration zone is high due to the reasons like diverse method for writing pursued by the clients, auxiliary independences, age elements of people and so on. This paper shows a novel procedure for the recognition of handwritten scripts, for example division of words and characters. In this paper, we have used two different scripts :"Devanagari" and "Roman" scripts. For which three Convolution Neural Networks(CNN) models are applied on different types of classification: one for language classification for which we have achieved 98% accuracy, second one for Devanagari character classification for which we have achieved 89% and third one for Roman character classification for which have achieved 97% respectively.

show abstract

“…Other layers work to map inputs to outputs by performing construction of the inputs with the node's weights by applying activation function. Logistic and hyperbolic tangent sigmoid functions are the most common activation function in MLPNN [12].…”

Section: Multilayer Perceptron Neural Network (Mlpnn)mentioning

confidence: 99%

Function Approximation using Neural and Fuzzy Methods

Nama¹,

Shaker²

2016

CAE

View full text Add to dashboard Cite

This work deals with an approximation of functions which finds the underlying relationship from an available finite input-output data of the function. It is the fundamental problem in a majority of real world applications, such as signal processing, prediction, data mining and control system. In this paper five different methods are used to verify their efficiency of approximation: MLPNN, RBFNN, GRNN, FIS and ANFIS networks. The performance is compared by using the RMSE measurement as an indicator of the fitness of these models in function approximation problem. The experimental results show that the performance of all networks used in this work at the training process is more different at the checking process when the networks have been tested with unknown data points. This depends on many factors such as type of networks used to approximate the function, available training data, noise in the data and values of the required parameters for training each network (No. of layers, No. of neurons, No. of training epochs, etc.).

show abstract

Multi-layer perceptron (MLP) neural network technique for offline handwritten Gurmukhi character recognition

Cited by 46 publications

References 5 publications

Prediction of I–V Characteristic Curve for Photovoltaic Modules Based on Convolutional Neural Network

Prediction of I–V Characteristic Curve for Photovoltaic Modules Based on Convolutional Neural Network

Segmentation and Identification of Bilingual Offline Handwritten Scripts (Devanagari and Roman)

Function Approximation using Neural and Fuzzy Methods

Contact Info

Product

Resources

About