Feature Extraction-Based Deep Self-Organizing Map

2022 ◽  
Author(s):  
Mohamed Sakkari ◽  
Monia Hamdi ◽  
Hela Elmannai ◽  
Abeer AlGarni ◽  
Mourad Zaied
Keyword(s):  
Feature Extraction ◽  
Self Organizing Map ◽  
Self Organizing

scholarly journals Pengelompokan Berita Indonesia Berdasarkan Histogram Kata Menggunakan Self-Organizing Map

2014 ◽  
Vol 8 (1) ◽  
pp. 101
Author(s):  
Ambarwati Ambarwati ◽  
Edi Winarko
Keyword(s):  
Feature Extraction ◽  
Data Processing ◽  
System Application ◽  
Input Data ◽  
Information Resources ◽  
The Self ◽  
News Article ◽  
Self Organizing Map ◽  
Map Algorithm ◽  
Self Organizing

AbstrakBerita merupakan sumber informasi yang dinantikan oleh manusia setiap harinya. Manusia membaca berita dengan kategori yang diinginkan. Jika komputer mampu mengelompokkan berita secara otomatis maka tentunya manusia akan lebih mudah membaca berita sesuai dengan kategori yang diinginkan. Pengelompokan berita yang berupa artikel secara otomatis sangatlah menarik karena mengorganisir artikel berita secara manual membutuhkan waktu dan biaya yang tidak sedikit.Tujuan penelitian ini adalah membuat sistem aplikasi untuk pengelompokkan artikel berita dengan menggunakan algoritma Self Organizing Map. Artikel berita digunakan sebagai input data. Kemudian sistem melakukan pemrosesan data untuk dikelompokkan. Proses yang dilakukan sistem meliputi preprocessing, feature extraction, clustering dan visualize.Sistem yang dikembangkan mampu menampilkan hasil clustering dengan algoritma Self Organizing Map dan memberikan visualisasi dengan smoothed data histograms berupa island map dari artikel berita. Selain itu sistem dapat menampilkan koleksi dokumen dari lima kategori berita yang ada pada tiap tahunnya dan banyaknya kata (histogram kata) yang sering muncul pada tiap arikel berita. Pengujian dari sistem ini dengan memasukan artikel berita, kemudian sistem memprosesnya dan mampu memberikan hasil cluster dari artikel berita yang dimasukan. Kata kunci—Pengelompokkan berita Indonesia, pengelompokkan berdasar histogram kata, pengelompokan berita menggunakan SOM  Abstract News is awaited information resources by humans every day. Human reading the news with the desired category. If the computer able to news clustering with automatically, humans of course will be easier to read the news according to the desired category. News clustering in the form of news articles with automatically very interesting because it organizes news articles manually takes time and costs not a little bit.The purpose of this research is to create a system application for grouping news articles by using the Self Organizing Map algorithm. News article be used as input into the system. News articles used as input data. Then the system performs data processing until to be clustered. Processes performed by the system covers: preprocessing, feature extraction, clustering and visualize.The system developed is able to display the results clustering of the Self Organizing Map algorithm and gives visualization of the Smoothed Data Histograms in the form of island map from news articles. Additionally the system can display a word histogram and news articles from five categories news in each year. Testing of this system by entering the news articles, then the system performs data processing and gives results of a cluster from news articles that input. Keywords—Indonesia news clustering, clustering based on words histograms, news clustering using SOM

scholarly journals Feature Extraction of Structures in Sea Water Using Self-Organizing Maps and Electromagnetic Waves

2016 ◽  
Vol 16 (3) ◽  
pp. 261
Author(s):  
Murilo Teixeira Silva ◽  
Lurimar Smera Batista ◽  
Frederico Medeiros Vasconcelos De Albuquerque
Keyword(s):  
Feature Extraction ◽  
Electromagnetic Waves ◽  
Sea Water ◽  
Low Frequency ◽  
Self Organizing Map ◽  
Self Organizing Maps ◽  
Virtual Sensors ◽  
Study Region ◽  
Direct Model ◽  
Self Organizing

<pre><!--StartFragment-->The use of Self-Organizing Map (<span>SOM</span>) algorithm for feature extraction and dimensionality reduction applied to underwater object detection with Low Frequency Electromagnetic Waves is presented. Computer simulation is used to generate a direct model for the study region, and a Self Organizing Map Algorithm is used to fit the data and return a similar model, with smaller dimensionality and same characteristics. Results show that virtual sensors are created by the <span>SOM</span> algorithm with consistent predictions, filling the resolution gap of the input data. These results are useful for fastening decision making algorithms by reducing the number of inputs to a group of significant data.<!--EndFragment--></pre>

Fault Diagnosis Method for Rectifier Circuit Based on Self-Organizing Map

2013 ◽  
Vol 321-324 ◽  
pp. 1930-1933 ◽  
Author(s):  
Run Xia Shen ◽  
Yi Min Lu ◽  
Qian Qian Liang
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Self Organizing Map ◽  
Rectifier Circuit ◽  
Three Phase ◽  
Bridge Rectifier ◽  
Diagnosis Method ◽  
Fault Feature Extraction ◽  
Relevant Experiment ◽  
Self Organizing

Fault feature extraction and recognition play crucial role in fault diagnosis. In this paper, a fault diagnosis method for three-phase fully-controlled bridge rectifier circuit based on Self-Organizing Map network is proposed. The method utilized the three phase AC input current as fault detection data. Then, perform spectrum analysis with the FFT, the fault data is trained through a Self-Organizing Map network for diagnosis. Simulation and relevant experiment verifying the proposed algorithm can classify various types of power electronics device faults accurately and rapidly.

scholarly journals Performance evaluation of the self-organizing map for feature extraction

2006 ◽  
Vol 111 (C5) ◽  
Author(s):  
Yonggang Liu ◽  
Robert H. Weisberg ◽  
Christopher N. K. Mooers
Keyword(s):  
Feature Extraction ◽  
Performance Evaluation ◽  
The Self ◽  
Self Organizing Map ◽  
Self Organizing

Feature extraction of time-series process images in an aerated agitation vessel using self organizing map

2009 ◽  
Vol 73 (1-3) ◽  
pp. 60-70 ◽  
Author(s):  
Hideyuki Matsumoto ◽  
Ryuichi Masumoto ◽  
Chiaki Kuroda
Keyword(s):  
Time Series ◽  
Feature Extraction ◽  
Self Organizing Map ◽  
Self Organizing

scholarly journals An EEG Feature Extraction Method Based on Sparse Dictionary Self-Organizing Map for Event-Related Potential Recognition

Algorithms ◽  
2020 ◽  
Vol 13 (10) ◽  
pp. 259
Author(s):  
Shang Feng ◽  
Haifeng Li ◽  
Lin Ma ◽  
Zhongliang Xu
Keyword(s):  
Feature Extraction ◽  
Event Related Potential ◽  
The Self ◽  
Computer Interface ◽  
Self Organizing Map ◽  
Eeg Signal ◽  
Sparse Decomposition ◽  
Feature Extraction Method ◽  
Self Organized ◽  
Self Organizing

In the application of the brain-computer interface, feature extraction is an important part of Electroencephalography (EEG) signal classification. Using sparse modeling to extract EEG signal features is a common approach. However, the features extracted by common sparse decomposition methods are only of analytical meaning, and cannot relate to actual EEG waveforms, especially event-related potential waveforms. In this article, we propose a feature extraction method based on a self-organizing map of sparse dictionary atoms, which can aggregate event-related potential waveforms scattered inside an over-complete sparse dictionary into the code book of neurons in the self-organizing map network. Then, the cosine similarity between the EEG signal sample and the code vector is used as the classification feature. Compared with traditional feature extraction methods based on sparse decomposition, the classification features obtained by this method have more intuitive electrophysiological meaning. The experiment conducted on a public auditory event-related potential (ERP) brain-computer interface dataset showed that, after the self-organized mapping of dictionary atoms, the neurons’ code vectors in the self-organized mapping network were remarkably similar to the ERP waveform obtained after superposition and averaging. The feature extracted by the proposed method used a smaller amount of data to obtain classification accuracy comparable to the traditional method.

Sign in / Sign up

Export Citation Format

Share Document