scholarly journals IMPLEMENTASI ARTIFICIAL NEURAL NETWORK PADA FIELD PROGRAMMABLE GATE ARRAY (FPGA) DALAM SISTEM IDENTIFIKASI ODOR

Respati ◽  
2017 ◽  
Vol 10 (28) ◽  
Author(s):  
Dini Fakta Sari ◽  
Muhammad Rivai ◽  
Totok Mujiono
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Field Programmable Gate Array ◽  
Back Propagation ◽  
Lookup Table ◽  
Multi Layer Perceptron ◽  
Field Programmable ◽  
Artificial Neural ◽  
Gate Array

ABSTRAKPenggunaan Field Programmable Gate Array (FPGA) untuk implementasi artificial neural network memberikan fleksibilitas dalam sistem pemrograman. Implementasi digital pada artificial neural network menggunakan FPGA dan menggunakan fungsi aktivasi nonlinier. VHDL digunakan untuk mengimplementasikan artificial neural network pada FPGA Xilinx XC3S500E-FG320 dengan perangkat lunak Xilinx ISE Webpack 8.2i. Kecepatan operasi FPGA Xilinx XC3S500E-FG320 dapat ditingkatkan dengan menggunakan metode lookup table (LUT). Jumlah LUT yang digunakan untuk perancangan artificial neural network dengan 3 neuron pada lapisan input, 4 neuron pada lapisan output dengan 1 neuron pada lapisan tersembunyi adalah sebesar 1407 LUT, untuk 5 neuron pada lapisan tersembunyi sebesar 4549 LUT, untuk 10 neuron pada lapisan tersembunyi sebesar 6378 LUT dan untuk 15 neuron pada lapisan tersembunyi sebesar 10084 LUT. Sistem dentifikasi odor, dilengkapi dengan sensor resonator kuarsa, pengkondisi sinyal, FPGA dan display. Model Multi Layer Perceptron (MLP) dengan metode pembelajaran Back Propagation (BP) yang digunakan untuk klasifikasi odor. Artificial neural network terdiri dari 3 neuron pada lapisan input, 10 neuron pada lapisan tersembunyi dan 4 neuron pada lapisan output yang diimplementasikan pada FPGA. Tingkat keberhasilan artificial neural network untuk identifikasi amoniak sebesar 93%, untuk pertamax sebesar 90%, untuk alkohol sebesar 92% dan untuk minyak tanah sebesar 85%.Kata kunci : Odor, sistem identifikasi odor, Artificial neural network, dan FPGA.

Speckle Noise Filtering Using Back-Propagation Multi-Layer Perceptron Network in Synthetic Aperture Radar Image

2020 ◽  
pp. 489-510
Author(s):  
Khwairakpam Amitab ◽  
Debdatta Kandar ◽  
Arnab K. Maji
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Synthetic Aperture Radar ◽  
Back Propagation ◽  
Speckle Noise ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Multi Layer Perceptron ◽  
Sar Images ◽  
Artificial Neural

Synthetic Aperture Radar (SAR) are imaging Radar, it uses electromagnetic radiation to illuminate the scanned surface and produce high resolution images in all-weather condition, day and night. Interference of signals causes noise and degrades the quality of the image, it causes serious difficulty in analyzing the images. Speckle is multiplicative noise that inherently exist in SAR images. Artificial Neural Network (ANN) have the capability of learning and is gaining popularity in SAR image processing. Multi-Layer Perceptron (MLP) is a feed forward artificial neural network model that consists of an input layer, several hidden layers, and an output layer. We have simulated MLP with two hidden layer in Matlab. Speckle noises were added to the target SAR image and applied MLP for speckle noise reduction. It is found that speckle noise in SAR images can be reduced by using MLP. We have considered Log-sigmoid, Tan-Sigmoid and Linear Transfer Function for the hidden layers. The MLP network are trained using Gradient descent with momentum back propagation, Resilient back propagation and Levenberg-Marquardt back propagation and comparatively evaluated the performance.

scholarly journals Artificial Neural Network (ANN) based Object Recognition Using Multiple Feature Sets

2011 ◽  
pp. 32-36
Author(s):  
Manami Barthakur ◽  
Tapashi Thakuria ◽  
Kandarpa Kumar Sarma
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Back Propagation ◽  
Principal Component ◽  
Multi Layer Perceptron ◽  
Multiple Features ◽  
Error Back Propagation ◽  
Multiple Feature ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In this work, a simplified Artificial Neural Network (ANN) based approach for recognition of various objects is explored using multiple features. The objective is to configure and train an ANN to be capable of recognizing an object using a feature set formed by Principal Component Analysis (PCA), Frequency Domain and Discrete Cosine Transform (DCT) components. The idea is to use these varied components to form a unique hybrid feature set so as to capture relevant details of objects for recognition using a ANN which for the work is a Multi Layer Perceptron (MLP) trained with (error) Back Propagation learning.

Speckle Noise Filtering Using Back-Propagation Multi-Layer Perceptron Network in Synthetic Aperture Radar Image

2016 ◽  
pp. 280-301
Author(s):  
Khwairakpam Amitab ◽  
Debdatta Kandar ◽  
Arnab K. Maji
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Synthetic Aperture Radar ◽  
Back Propagation ◽  
Speckle Noise ◽  
Synthetic Aperture ◽  
Sar Image ◽  
Multi Layer Perceptron ◽  
Sar Images ◽  
Artificial Neural

Synthetic Aperture Radar (SAR) are imaging Radar, it uses electromagnetic radiation to illuminate the scanned surface and produce high resolution images in all-weather condition, day and night. Interference of signals causes noise and degrades the quality of the image, it causes serious difficulty in analyzing the images. Speckle is multiplicative noise that inherently exist in SAR images. Artificial Neural Network (ANN) have the capability of learning and is gaining popularity in SAR image processing. Multi-Layer Perceptron (MLP) is a feed forward artificial neural network model that consists of an input layer, several hidden layers, and an output layer. We have simulated MLP with two hidden layer in Matlab. Speckle noises were added to the target SAR image and applied MLP for speckle noise reduction. It is found that speckle noise in SAR images can be reduced by using MLP. We have considered Log-sigmoid, Tan-Sigmoid and Linear Transfer Function for the hidden layers. The MLP network are trained using Gradient descent with momentum back propagation, Resilient back propagation and Levenberg-Marquardt back propagation and comparatively evaluated the performance.

Sign in / Sign up

Export Citation Format

Share Document