A linear model based on Kalman filter for improving neural network classification performance

Abstract

a b s t r a c tNeural network has been applied in several classification problems such as in medical diagnosis, handwriting recognition, and product inspection, with a good classification performance. The performance of a neural network is characterized by the neural network's structure, transfer function, and learning algorithm. However, a neural network classifier tends to be weak if it uses an inappropriate structure. The neural network's structure depends on the complexity of the relationship between the input and the output. There are no exact rules that can be used to determine the neural network's structure. Therefore, studies in improving neural network classification performance without changing the neural network's structure is a challenging issue. This paper proposes a method to improve neural network classification performance by constructing a linear model based on the Kalman filter as a post processing. The linear model transforms the predicted output of the neural network to a value close to the desired output by using the linear combination of the object features and the predicted output. This simple transformation will reduce the error of neural network and improve classification performance. The Kalman filter iteration is used to estimate the parameters of the linear model. Five datasets from various domains with various characteristics, such as attribute types, the number of attributes, the number of samples, and the number of classes, were used for empirical validation. The validation results show that the linear model based on the Kalman filter can improve the performance of the original neural network.

Hybrid Neural Network and Linear Model for Natural Produce Recognition Using Computer Vision

“…Details of LMKF parameter estimation can be found in [15]. All features were normalized into interval [ 1,1] − before being used in the training of the NN and in the parameter estimation of LMKF in order to minimize bias and reduce training time [19].…”

“…A hybrid neural network (NN) and linear model based on a Kalman filter (LMKF), called NN-LMKF [15], was used to classify the produce. The structure of the NN used in this study consisted of an input layer containing 16 neurons that correspond to the object features, a hidden layer, and an output layer containing 10 neurons that correspond to the object class.…”

“…The complexity of this structure depends on the number of input features and the number of output classes. If a neural network classifier uses an inappropriate structure then it tends to be a weak classifier [15]. Several methods have been proposed to increase classification performance of neural networks.…”

“…Several methods have been proposed to increase classification performance of neural networks. One of them is by using a linear model based on a Kalman filter [15]. The model was used to adjust the predicated output of a neural network such that the classification performance was increased.…”

Computer vision system for egg volume prediction using backpropagation neural network

“…Although the system used many features and used combination of LDA, PCA, and ANN to estimate volume, the system achieved only 73%in terms of the correlation ANN is a nonlinear model that mimics the biological nervous system. It has been widely used to solve various classification and prediction problems [5]. The performance of ANN is strongly related with input features and its structure [6].…”