LEARNING TO GENERATE ARTIFICIAL FOVEA TRAJECTORIES FOR TARGET DETECTION

This paper shows how ‘static’ neural approaches to adaptive target detection can be replaced by a more efficient and more sequential alternative. The latter is inspired by the observation that biological systems employ sequential eye movements for pattern recognition. A system is described, which builds an adaptive model of the time-varying inputs of an artificial fovea controlled by an adaptive neural controller. The controller uses the adaptive model for learning the sequential generation of fovea trajectories causing the fovea to move to a target in a visual scene. The system also learns to track moving targets. No teacher provides the desired activations of ‘eye muscles’ at various times. The only goal information is the shape of the target. Since the task is a ‘reward-only-at-goal’ task, it involves a complex temporal credit assignment problem. Some implications for adaptive attentive systems in general are discussed.

Download Full-text

Time-varying Barrier Lyapunov Function Based Adaptive Neural Controller Design for Nonlinear Pure-feedback Systems with Unknown Hysteresis

International Journal of Control Automation and Systems ◽

10.1007/s12555-018-0745-y ◽

2019 ◽

Vol 17 (7) ◽

pp. 1642-1654 ◽

Cited By ~ 14

Author(s):

Li Tang ◽

Dongjuan Li

Keyword(s):

Lyapunov Function ◽

Controller Design ◽

Time Varying ◽

Feedback Systems ◽

Neural Controller ◽

Barrier Lyapunov Function ◽

Adaptive Neural Controller

Download Full-text

TRANSITION TO CONVOLUTIONAL NEURAL NETWORKS IN RADAR PROBLEMS

Informatization and communication ◽

10.34219/2078-8320-2019-10-3-96-99 ◽

2019 ◽

pp. 96-99

Author(s):

K. Maystrenko ◽

A. Budilov ◽

D. Afanasev

Keyword(s):

Neural Networks ◽

Pattern Recognition ◽

Target Detection ◽

Convolutional Neural Networks ◽

Network Topology ◽

Subject Areas ◽

The Subject ◽

Printed Materials ◽

Hardware Costs

Goal. Identify trends and prospects for the development of radar in terms of the use of convolutional neural networks for target detection. Materials and methods. Analysis of relevant printed materials related to the subject areas of radar and convolutional neural networks. Results. The transition to convolutional neural networks in the field of radar is considered. A review of papers on the use of convolutional neural networks in pattern recognition problems, in particular, in the radar problem, is carried out. Hardware costs for the implementation of convolutional neural networks are analyzed. Conclusion. The conclusion is made about the need to create a methodology for selecting a network topology depending on the parameters of the radar task.

Download Full-text

An Adaptive Neural Controller for a Robot

IFAC Proceedings Volumes ◽

10.1016/s1474-6670(17)41014-7 ◽

1998 ◽

Vol 31 (31) ◽

pp. 115-120

Author(s):

Marcelo R. Stemmer ◽

Edson R. de Pieri ◽

Fábio A. Pires Borges

Keyword(s):

Neural Controller ◽

Adaptive Neural Controller

Download Full-text

Researching a Moving Target Detection Method Based on Magnetic Flux Induction Technology

Metals ◽

10.3390/met11121967 ◽

2021 ◽

Vol 11 (12) ◽

pp. 1967

Author(s):

Chaoqun Xu ◽

Li Yang ◽

Kui Huang ◽

Yang Gao ◽

Shaohua Zhang ◽

...

Keyword(s):

Magnetic Flux ◽

Magnetic Dipole ◽

Target Detection ◽

Electromotive Force ◽

Detection Method ◽

Field Tests ◽

Moving Target ◽

Moving Targets ◽

Moving Target Detection ◽

Modern Warfare

The ocean is a very important arena in modern warfare where all marine powers deploy their military forces. Due to the complex environment of the ocean, underwater equipment has become a very threatening means of surprise attack in modern warfare. Therefore, the timely and effective detection of underwater moving targets is the key to obtaining warfare advantages and has important strategic significance for national security. In this paper, magnetic flux induction technology was studied with regard to the difficulty of detecting underwater concealed moving targets. Firstly, the characteristics of a magnetic target were analyzed and an equivalent magnetic dipole model was established. Secondly, the structure of the rectangular induction coil was designed according to the model, and the relationship between the target’s magnetism and the detection signal was deduced. The variation curves of the magnetic flux and the electromotive force induced in the coil were calculated by using the numerical simulation method, and the effects of the different motion parameters of the magnetic dipole and the size parameters of the coil on the induced electromotive force were analyzed. Finally, combined with the wavelet threshold filter, a series of field tests were carried out using ships of different materials in shallow water in order to verify the moving target detection method based on magnetic flux induction technology. The results showed that this method has an obvious response to moving targets and can effectively capture target signals, which verifies the feasibility of the magnetic flux induction detection technology.

Download Full-text

Harmonic Reduction Solution by Applying On-Line Trained Adaptive Neural Controller for Shunt Active Filter

Lecture Notes in Electrical Engineering - Proceedings of the 2nd International Conference on Intelligent Technologies and Engineering Systems (ICITES2013) ◽

10.1007/978-3-319-04573-3_144 ◽

2014 ◽

pp. 1181-1189

Author(s):

Nguyen Thi-Hoai Nam ◽

Chun-Tang Chao ◽

Chi-Jo Wang ◽

Cheng-Ting Hsu

Keyword(s):

Active Filter ◽

Neural Controller ◽

Shunt Active Filter ◽

Harmonic Reduction ◽

On Line ◽

Adaptive Neural Controller

Download Full-text

Moving targets pattern recognition based on the wavelet neural network

Journal of Electronics (China) ◽

10.1007/bf02687991 ◽

2005 ◽

Vol 22 (3) ◽

pp. 321-328

Author(s):

Guangying Ge ◽

Lili Chen ◽

Jianjian Xu

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Wavelet Neural Network ◽

Moving Targets

Download Full-text

Adaptive Neural Controller for Unknown Standalone Photovoltaic Distributed Generation Systems with Unknown Disturbances

IEEE Transactions on Sustainable Energy ◽

10.1109/tste.2021.3123184 ◽

2021 ◽

pp. 1-1

Author(s):

Meher Preetam Korukonda ◽

Ravi Prakash ◽

Suvendu Samanta ◽

Laxmidhar Behera

Keyword(s):

Distributed Generation ◽

Neural Controller ◽

Unknown Disturbances ◽

Adaptive Neural Controller

Download Full-text

Deep Convolutional Neural Network driven Neuro-Fuzzy System for Moving Target Detection Using the Radar Signals

Journal of Information & Knowledge Management ◽

10.1142/s0219649222500101 ◽

2021 ◽

Author(s):

M. Bharat Kumar ◽

P. Rajesh Kumar

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Target Detection ◽

Fuzzy System ◽

Deep Convolutional Neural Network ◽

Moving Target ◽

Moving Targets ◽

Moving Target Detection ◽

Neuro Fuzzy ◽

Deep Cnn

In radar signal processing, detecting the moving targets in a cluttered background remains a challenging task due to the moving out and entry of targets, which is highly unpredictable. In addition, detection of targets and estimation of the parameters have become a major constraint due to the lack of required information. However, the appropriate location of the targets cannot be detected using the existing techniques. To overcome such issues, this paper presents a developed Deep Convolutional Neural Network-enabled Neuro-Fuzzy System (Deep CNN-enabled Neuro-Fuzzy system) for detecting the moving targets using the radar signals. Initially, the received signal is presented to the Short-Time Fourier Transform (STFT), matched filter, radar signatures-enabled Deep Recurrent Neural Network (Deep RNN), and introduced deep CNN to locate the targets. The target location output results are integrated using the newly introduced neuro-fuzzy system to detect the moving targets effectively. The proposed deep CNN-based neuro-fuzzy system obtained effective moving target detection results by varying the number of targets, iterations, and the pulse repetition level for the metrics, like detection time, missed target rate, and MSE with the minimal values of 1.221s, 0.022, and 1,952.15.

Download Full-text