Improving performance in pulse radar detection using Bayesian regularization for neural network training

Kumar, Preetam; Merchant, S. N.; Desai, U.B.

doi:10.1016/j.dsp.2004.06.002

Cited by 34 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is used in about 80-90% of applications [49]. Backpropagation optimization is used for forward neural networks with hidden layers and is designed for data classification that is generally not linearly separable [50]. The learning process of backpropagation can be divided into four main parts [15]…”

Section: Backpropagation Algorithmmentioning

confidence: 99%

The design of an indirect method for the human presence monitoring in the intelligent building

Vaňuš

Machac

Martínek

et al. 2018

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

This article describes the design and verification of the indirect method of predicting the course of CO 2 concentration (ppm) from the measured temperature variables T indoor (°C) and the relative humidity rH indoor (%) and the temperature T outdoor (°C) using the Artificial Neural Network (ANN) with the Bayesian Regulation Method (BRM) for monitoring the presence of people in the individual premises in the Intelligent Administrative Building (IAB) using the PI System SW Tool (PI-Plant Information enterprise information system). The CA (Correlation Analysis), the MSE (Root Mean Squared Error) and the DTW (Dynamic Time Warping) criteria were used to verify and classify the results obtained. Within the proposed method, the LMS adaptive filter algorithm was used to remove the noise of the resulting predicted course. In order to verify the method, two long-term experiments were performed, specifically from February 1 to

show abstract

Section: Backpropagation Algorithmmentioning

confidence: 99%

The design of an indirect method for the human presence monitoring in the intelligent building

Vaňuš

Machac

Martínek

et al. 2018

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…In order to provide a meaningful visual comparison of the power plots, we replace the null in the output by the arbitrarily chosen number 10 −20 . Clearly, the SSR obtained when using our SVM is higher compared to 42.73 dB, 139.2 dB, 188.2 dB and 100 dB obtained using FFNNs respectively in [5], [12], [13] and [16]; 63.19 dB using a radial basis function neural network (RBFNN) in [9]; or other techniques such as least squares inverse filter [2]. We emphasise that except for [11]- [13], only a 0 dB target is considered in all these references.…”

Section: Simulation Resultsmentioning

confidence: 85%

A Novel Application of Support Vector Machines to Detect Targets

Padaki¹,

George

2010

2010 Second International Conference on Computational Intelligence, Modelling and Simulation

View full text Add to dashboard Cite

In this paper we develop a novel pulse radar detection scheme using Support Vector Machines (SVMs). SVMs are a powerful tool for pattern classification. Exploiting this, we design a SVM for pulse radar detection of targets embedded in noise. An adaptive pre-processing stage is included when the echoes are very weak. It is observed that the signal-to-sidelobe ratio obtained is much higher compared to neural network based pulse radar detection schemes. We further examine the noise tolerance, range resolution ability and Doppler tolerance of the new algorithm for pulse compression, and compare it with the ones available in literature.

show abstract

“…In the Bayesian framework, the weight values of the network are assumed to be random variables. According to Bayesian's rule [39], the optimization of the regularization parameters αGi, βGi, αAi, and βAi requires solving the Hessian matrix of …”

Section: Temperature Error Compensation Methods Of Rbf Neural Network mentioning

confidence: 99%

Error Modeling, Calibration, and Compensation of Inertial Measurement Unit (IMU)

Quan

Gong

Fang

et al. 2015

INS/CNS/GNSS Integrated Navigation Technology

View full text Add to dashboard Cite

Improving performance in pulse radar detection using Bayesian regularization for neural network training

Cited by 34 publications

References 8 publications

The design of an indirect method for the human presence monitoring in the intelligent building

The design of an indirect method for the human presence monitoring in the intelligent building

A Novel Application of Support Vector Machines to Detect Targets

Error Modeling, Calibration, and Compensation of Inertial Measurement Unit (IMU)

Contact Info

Product

Resources

About