This paper describes a new binocular tracking method using log polar mapping (LPM) which approximately represents the of retina into visual cortex in primate vision. Using LPM makes it possible not only to obtain both high central resolution and wide field view, but also significantly reduce processing image data. In this paper, is performed software by lookup table method. Our utilizes zero disparity filter (ZDF) for extracting target object virtual horopter estimating disparities,...

Maturity detection is very important for fruit farmhouses. In a previous study, we revealed type of odor sensor that responds to the strength fruits smell as well maturities. The data consists dead time and step response first-order lag element. We focus on element, which form rises exponentially constant value. This paper presents quick method maturity in few seconds rising signal sensor. Using neural network, performs without waiting fully reach up First, network trained sample with two...

This paper presents a machine learning approach to automatically classifying post-harvest vegetal species. Color images of species were applied convolutional neural networks (CNNs) and support vector (SVM) classifiers. We focused on okra as the target classified it into two quality types. However, our could also be other The solution consists several components, each design process its combinations are essential for classification quality. Therefore, we carefully investigated their effects...

One of the well-known and frequently used crossover operators real-coded genetic algorithms (GAs) is blend (BLX). The BLX utilizes a uniform probability distribution function in offspring production process. convergence speed not high sometimes falls to local optimum for searching solution problems. In order improve performance GA, we propose use biased functions (BPDF) with BPDF produces that are close best individuals current generation it highly likely these will offerr problem....

This paper presents a method of maturity detection the tropical fruits using smell sensor. We investigate many sensing data different and find out that are characterized as first-order lag element. The element has two parameters: gain time constant. Knowing constant is useful for detecting fruits. In this paper, we apply genetic algorithm to identify parameters data. Experiments monkey bananas guavas show good results.

In this paper, we present a study on activity functions for an MLNN (multi-layered neural network) and propose suitable function data enlargement processing.We have carefully studied the training performance of Sigmoid, ReLu, Leaky-ReLu L & exp.activity few inputs to multiple output patterns.Our MLNNs model has hidden layers with two or three four six outputs variations by BP (backpropagation) NN (neural training.We focused multi teacher signals investigate evaluate in select best good hence...

This paper presents a study on the improvement of MLNNs (multi-layer neural networks) performance by an activity function for multi logic training patterns.Our model network has L hidden layers two inputs and three, four to six output using BP (backpropagation) network.We used functions XOR (exclusive OR), OR, AND, NAND (not AND), NXOR exclusive OR) NOR as teacher signals evaluate information data enlargement in signal processing (synaptic divergence state).We specifically from which we...

In this research, we propose a method to adaptively generate AUV trajectories using neural controller that learns by applying genetic algorithm. The uses two neuro-controllers. One is learned in advance as controller. other learning at the same time redesigning new trajectory when deviates from planned during navigation. controllers are evolutionarily algorithms. navigation simulation, multi-point search problem of under tidal current environment was taken up. Numerical experiments have...

Sea Experiment on Tele-operation System of Underwater Excavator Tsukasa Kita, Taketsugu Hirabayashi, Atsushi Ueyama, Hiroshi Kinjo, Naoki Oshiro and Nobuyuki Kinjo Pages 118-125 (2020 Proceedings the 37th ISARC, Kitakyushu, Japan, ISBN 978-952-94-3634-7, ISSN 2413-5844) Abstract: We have developed a remote operation support system for underwater excavators conducted experiments. been operated by divers boarding them. Their main task is levelling rubble mounds port structures in...

Vibration control is important in mechatronics, aerospace engineering, civil engineering and other fields. Recently, active vibration rather than passive being used, reflecting modern theory. In this paper, we propose an optimal digital feedback regulator which based only on the first second-order information for a system elminating transient disturbance. The Wiener-Hopf criterion adopted scheme. Since controller constructed as finite-impulse response filter, computation require to design...