scholarly journals THE IDENTIFICATION OF COASTLINE CHANGES FROM LANDSAT 8 SATELLITE DATA USING ARTIFICIAL NEURAL NETWORKS AND K-NEAREST NEIGHBOR

2020 ◽  
Author(s):  
Mustafa Kesikoğlu ◽  
Sevim Yasemin Çiçekli ◽  
Tolga Kaynak
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Satellite Data ◽  
Nearest Neighbor ◽  
Landsat 8 ◽  
K Nearest Neighbor ◽  
Artificial Neural

scholarly journals Deteksi Citra Uang Kertas dengan Fitur RGB Menggunakan K-Nearest Neighbor

2020 ◽  
Vol 9 (2) ◽  
pp. 163-172
Author(s):  
Andhika Ryan Pratama ◽  
Muhammad Mustajib ◽  
Aryo Nugroho
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Nearest Neighbor ◽  
Feedforward Neural Network ◽  
K Nearest Neighbor ◽  
Artificial Neural

Mesin pendeteksi uang kertas menjadi salah satu objek yang diperhatikan untuk diteliti dan dikembangkan. Mesin pendeteksi uang kertas Indonesia yang ditemukan seperti di stasiun kereta api di suatu kota, terdapat kegagalan dalam mengenali nilai uang kertas tertentu. Tujuan dari penelitian ini adalah membangun model dari pengenalan nilai uang kertas menggunakan K-Nearest Neighbor (KNN) yang merupakan metode yang paling sederhana dan paling penting dalam pengenalan pola, hal ini ditunjukkan pada akurasi yang diperoleh lebih tinggi dibandingkan metode lainnya seperti Artificial Neural Networks (ANN) dan Feedforward Neural Network (FNN). Model yang diusulkan menggunakan ekstraksi fitur, terdapat beberapa fitur yang digunakan untuk pengenalan uang kertas seperti yang pernah dilakukan menggunakan ekstraksi fitur tekstur. Penelitian ini menggunakan ekstraksi fitur warna. Warna memberikan informasi yang berarti dan nilai-nilai yang penting dalam proses mendeskripsikan suatu objek. Warna yang digunakan adalah  Red, Green, Blue (RGB). Hasil disajikan pada dataset 40 gambar uang kertas yang terdiri dari pecahan 2000 rupiah keluaran lama, 2000 rupiah keluaran baru, 5000 rupiah keluaran lama, dan 5000 rupiah keluaran baru. Pendekatan yang diusulkan terlihat kinerja yang cukup baik dengan menggunakan metode KNN. Dari 16 data uji menunjukkan 15 objek uang kertas berhasil dideteksi dengan benar. Akurasi yang dihasilkan sebesar 93,7% dengan nilai K=5.

Investigating of Correlation between MODIS Satellite Data and Ground Data Related to Aerosols and Modeling Aerosols Using Neural Networks over Shiraz

2012 ◽  
Vol 260-261 ◽  
pp. 926-929
Author(s):  
Ali Reza Dehghani ◽  
Ali Akbar Safavi ◽  
Mohammad Jafar Nazemossadat ◽  
Seyed Mohammad Hessam Mohammadi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Satellite Data ◽  
Satellite Image ◽  
Frequency Bands ◽  
Input And Output ◽  
Satellite Information ◽  
Proposed Model ◽  
Artificial Neural ◽  
Band Number

This paper presents an investigation of satellite data and ground data about aerosols and then modelsthe mentioned data over Shiraz using artificial neural networks. MODIS satellite data are available on 36 various frequency bands. In this study, a good correlation between ground data and the 10 first satellite image bands is being shown. Specially, the best correlation was found in band number 8. Therefore, using neural networks and ground data along with satellite information, a model of aerosols is constructed. In the mentioned model, satellite data of band 8 and ground data are used as network input and output, respectively. The results show the effectiveness of the proposed model.

scholarly journals DETERMINATION OF RESS GENERATION USING ARTIFICIAL NEURAL NETWORKS

2020 ◽  
pp. 76-83
Author(s):  
О. Rubanenko ◽  
D. Danylchenko ◽  
V. Teptya
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Renewable Energy ◽  
Satellite Data ◽  
Electricity Generation ◽  
Renewable Energy Sources ◽  
Energy Sources ◽  
Power Stations ◽  
Photovoltaic Power ◽  
Artificial Neural

Paper considers the perspectives and potential of using renewable energy sources to decide the global warming problem. The World trend of increasing electricity generation by photovoltaic power stations according to the International Renewable Energy Agency and the trend of increasing the installed capacity of photovoltaic power stations in Ukraine, which supply the generated capacity at a "green" tariff according to the National Commission for State Regulation of Energy utilities of Ukraine. Opportunities and conditions of using artificial neural networks to defined the power generation of photovoltaic power stations on the example of the power plant "Tsekinivska-2" 4–5 turns are investigated. A platform developed by the European Commission – Photovoltaic Geographical Information System – was used to create a database for the creation and training of artificial neural networks. Regularities of change of meteorological satellite data and their influence on electricity generation of photovoltaic power stations are established. For this purpose, the software complex MATLAB was used, namely the module for the creation of artificial neural networks – Neural Networks Toolbox. The height of the sun is conditionally considered constant and its value is repeated from year to year or has a slight deviation, so it can be used as an indicator of the hour and can be considered known in advance, so determined by empirical formulas and changes only under certain astrophysical laws. Regarding the temperature at 2 m and the wind at 10 m, these meteorological data are known, as they are needed not only for forecasting the operation of renewable energy sources but also in agriculture. Therefore, data related to solar radiation are considered to be the most problematic, as this value is the most difficult to determine. Satellite data may have an error, the installation of weather stations, namely quality pyranometers is a costly procedure, but will help provide a training sample of quality data. To forecast with satisfactory accuracy, it is necessary to collect data for 1 year of operation of the weather station. The nntool and Anfis MATLAB modules were used to predict generation. But the obtained results can be used to assess the effectiveness of the photovoltaic power stations, but they are unsatisfactory for the operational balancing of the system.

A STUDY OF ULTRASONIC LIVER IMAGES CLASSIFICATION WITH ARTIFICIAL NEURAL NETWORKS BASED ON FRACTAL GEOMETRY AND MULTIRESOLUTION ANALYSIS

2004 ◽  
Vol 16 (02) ◽  
pp. 59-67 ◽  
Author(s):  
WEN-LI LEE ◽  
KAI-SHENG HSIEH ◽  
YUNG-CHANG CHEN ◽  
YING-CHENG CHEN
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Fractal Geometry ◽  
Feature Vector ◽  
Probabilistic Neural Network ◽  
Back Propagation ◽  
Attractive Alternative ◽  
K Nearest Neighbor ◽  
Artificial Neural

In this study, we evaluate the accuracy of classifiers for classification of ultrasonic liver tissues. Two different statistic classifiers and three various artificial neural networks are included: Bayes classifier, k-nearest neighbor classifier, Back-propagation neural networks, probabilistic neural network and modified probabilistic neural network. These five different classifiers were investigated to determine their ability to classify various categories of ultrasonic liver images. The investigation was performed on the basis of the same feature vector. For statistic classifiers the classification accuracy is at most 90.7% and with artificial neural networks the accuracy is at least 92%. The experimental results illustrated that artificial neural networks are an attractive alternative to conventional statistic techniques when dealing with classification task. Moreover, the feature vector based on fractal geometry and wavelet transform can provide good discriminant ability for ultrasonic liver images under study.

Sign in / Sign up

Export Citation Format

Share Document