Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension Features

Multiple-stream deep learning (DL) models are typically used for multiple-modality datasets, with each model extracting favorable features from its own modality dataset. Through feature fusion, multiple-stream models can generally achieve higher recognition rates. While feature engineering is indisp...

Full description

Saved in:
Bibliographic Details
Main Author: Yen-Ching Chang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Fractal and Fractional
Subjects:
Online Access:https://www.mdpi.com/2504-3110/9/4/248
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850180414611652608
author Yen-Ching Chang
author_facet Yen-Ching Chang
author_sort Yen-Ching Chang
collection DOAJ
description Multiple-stream deep learning (DL) models are typically used for multiple-modality datasets, with each model extracting favorable features from its own modality dataset. Through feature fusion, multiple-stream models can generally achieve higher recognition rates. While feature engineering is indispensable for machine learning models, it is generally omitted for DL. However, feature engineering can be regarded as an important supplement to DL, especially when using small datasets with rich characteristics. This study aims to utilize limited existing resources to improve the overall performance of the considered models. Therefore, I choose a single-modality dataset—the Chest X-Ray dataset—as my original dataset. For ease of evaluation, I take 16 pre-trained models as basic models for the development of multiple-stream models. Based on the characteristics of the Chest X-Ray dataset, three characteristic datasets are generated from the original dataset, including the Hurst exponent dataset (corresponding to a fractal dimension dataset), as inputs to the multiple-stream models. For comparison, various multiple-stream models are developed based on the same dataset. The experimental results show that, with feature engineering, the accuracy can be raised from 91.67% (one-stream) to 94.52% (two-stream), 94.73% (three-stream), and 94.79% (four-stream), while, without feature engineering, it can be increased from 91.67% to 92.35%, 93.49%, and 93.66%, respectively. In the future, the simple yet effective methodology proposed in this study can be widely applied to other datasets, in order to effectively promote the overall performance of models in scenarios characterized by limited resources.
format Article
id doaj-art-d0c09388dcb347009f8d4545b40f63a1
institution OA Journals
issn 2504-3110
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Fractal and Fractional
spelling doaj-art-d0c09388dcb347009f8d4545b40f63a12025-08-20T02:18:11ZengMDPI AGFractal and Fractional2504-31102025-04-019424810.3390/fractalfract9040248Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension FeaturesYen-Ching Chang0Department of Medical Informatics, Chung Shan Medical University, Taichung 40201, TaiwanMultiple-stream deep learning (DL) models are typically used for multiple-modality datasets, with each model extracting favorable features from its own modality dataset. Through feature fusion, multiple-stream models can generally achieve higher recognition rates. While feature engineering is indispensable for machine learning models, it is generally omitted for DL. However, feature engineering can be regarded as an important supplement to DL, especially when using small datasets with rich characteristics. This study aims to utilize limited existing resources to improve the overall performance of the considered models. Therefore, I choose a single-modality dataset—the Chest X-Ray dataset—as my original dataset. For ease of evaluation, I take 16 pre-trained models as basic models for the development of multiple-stream models. Based on the characteristics of the Chest X-Ray dataset, three characteristic datasets are generated from the original dataset, including the Hurst exponent dataset (corresponding to a fractal dimension dataset), as inputs to the multiple-stream models. For comparison, various multiple-stream models are developed based on the same dataset. The experimental results show that, with feature engineering, the accuracy can be raised from 91.67% (one-stream) to 94.52% (two-stream), 94.73% (three-stream), and 94.79% (four-stream), while, without feature engineering, it can be increased from 91.67% to 92.35%, 93.49%, and 93.66%, respectively. In the future, the simple yet effective methodology proposed in this study can be widely applied to other datasets, in order to effectively promote the overall performance of models in scenarios characterized by limited resources.https://www.mdpi.com/2504-3110/9/4/248deep learningfeature engineeringfeature fusionmultiple-stream modelsHurst exponentfractal dimension
spellingShingle Yen-Ching Chang
Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension Features
Fractal and Fractional
deep learning
feature engineering
feature fusion
multiple-stream models
Hurst exponent
fractal dimension
title Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension Features
title_full Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension Features
title_fullStr Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension Features
title_full_unstemmed Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension Features
title_short Multiple-Stream Models for a Single-Modality Dataset with Fractal Dimension Features
title_sort multiple stream models for a single modality dataset with fractal dimension features
topic deep learning
feature engineering
feature fusion
multiple-stream models
Hurst exponent
fractal dimension
url https://www.mdpi.com/2504-3110/9/4/248
work_keys_str_mv AT yenchingchang multiplestreammodelsforasinglemodalitydatasetwithfractaldimensionfeatures