Kohonen network-based adaptation of non sequential data for use in convolutional neural networks
Authors:
- Michał Bereta
Abstract
Convolutional neural networks have become one of the most powerful computing tools of artificial intelligence in recent years. They are especially suitable for the analysis of images and other data that have an inherent sequence structure, such as time series data. In the case of data in the form of vectors of features, the order of which does not matter, the use of convolutional neural networks is not justified. This paper presents a new method of representing non-sequential data as images that can be analyzed by a convolutional network. The well-known Kohonen network was used for this purpose. After training on non-sequential data, each example is represented by so-called U-image that can be used as input to a convolutional layer. A hybrid approach was also presented, where the neural network uses two types of input signals, both U-image representation and the original features. The results of the proposed method on traditional machine learning databases as well as on a difficult classification problem originating from the analysis of measurement data from experiments in particle physics are presented.
- Record ID
- CUTc0b808915a5c4150bdd971f357f958a5
- Publication categories
- ;
- Author
- Journal series
- Sensors, ISSN , e-ISSN 1424-8220, Biweekly
- Issue year
- 2021
- Vol
- 21
- No
- 21
- Pages
- [1-23]
- Article number
- 7221
- Other elements of collation
- schem.; tab.; wykr.; Bibliografia (na s.) - 22-23; Bibliografia (liczba pozycji) - 19; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 21, Iss. 21, Spec. Iss.
- Substantive notes
- Special Issue: Computational Intelligence in Data Fusion and Image Analysis
- Na publikacji błędny numer artykułu: 17221
- Keywords in English
- kohonen network, convolutional neural network, multiple input neural networks
- DOI
- DOI:10.3390/s21217221 Opening in a new tab
- URL
- https://www.mdpi.com/1424-8220/21/21/7221 Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 100
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUTc0b808915a5c4150bdd971f357f958a5/
- URN
urn:pkr-prod:CUTc0b808915a5c4150bdd971f357f958a5
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.