Submit to Entropy Review for Entropy Propose a Special Issue

Journal Browser

Perspectives and Prospects of Computer Recognition and Machine Learning in Signal and Image Processing, Selected Papers from PRML 2022

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".

Deadline for manuscript submissions: closed (31 December 2022) | Viewed by 10389

Share This Special Issue

Special Issue Editors

Prof. Dr. Dakun Lai

E-Mail Website
Guest Editor

School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
Interests: IOTs and wearable devices; biomedical imaging and signal processing; bioelectromagnetism and medical applications; AI-based diagnosis of cardiac/neuro-electrical disorders
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Qijun Zhao

E-Mail Website
Guest Editor

College of Computer Science, Sichuan University, Chengdu 610065, China
Interests: biometrics; computer vision; 3D reconstruction; re-identification; object detection and recognition; fine-grained image classification

Special Issue Information

Dear Colleagues,

The 3rd International Conference on Pattern Recognition and Machine Learning (PRML 2022) will be held on July 15-17, 2022, in Chengdu, China. For more details, please visit the website for the event: http://www.prml.org/.

PRML is an annual conference that aims to present the latest research and achievements of scholars and experts in the field of pattern recognition and machine learning. The conference includes papers focused on application areas of biomedical engineering, computer vision, and the Internet of things.

Authors of selected papers from the conference will be invited to submit extended versions of their original papers and contributions under the conference topics, which should also add entropy and information theory methods to meet the journal's scope.

The scope includes, but is not limited to, the following:

Entropy and information theory;
Machine learning architectures and formulations;
Neural generative models, auto encoders, GANs;
Features extraction and selection;
Trends and relations recognition and analysis;
Recognition (object detection, categorization) and representation learning, deep learning;
Motion, tracking, and action and behavior recognition;
Vision applications and systems, vision for robotics and autonomous vehicles;
Biomedical signal and image processing;
Bioinformatics for healthcare engineering;
Explainable AI, fairness, accountability, privacy, transparency, and ethics in vision;
Image retrieval, segmentation, grouping, and shape;
Biometrics, face, gesture, body pose;
AI chips and their implantation of machine learning and deep learning algorithms;
Internet of things (IOT);
Smart signal conditioning algorithms for IS;
Applying machine-learning-powered sensing to industrial scenarios.

Dr. Dakun Lai
Prof. Dr. Qijun Zhao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

computer recognition
signal processing
image processing
machine learning
healthcare engineering

Published Papers (5 papers)

Download All Papers

Research

14 pages, 3308 KiB

Open AccessArticle

Recognition of Ellipsoid-like Herbaceous Tibetan Medicinal Materials Using DenseNet with Attention and ILBP-Encoded Gabor Features

by Liyuan Zhou, Hongmei Gao, Dingguo Gao and Qijun Zhao

Entropy 2023, 25(6), 847; https://doi.org/10.3390/e25060847 - 25 May 2023

Cited by 2 | Viewed by 1106

Abstract

Tibetan medicinal materials play a significant role in Tibetan culture. However, some types of Tibetan medicinal materials share similar shapes and colors, but possess different medicinal properties and functions. The incorrect use of such medicinal materials may lead to poisoning, delayed treatment, and potentially severe consequences for patients. Historically, the identification of ellipsoid-like herbaceous Tibetan medicinal materials has relied on manual identification methods, including observation, touching, tasting, and nasal smell, which heavily rely on the technicians’ accumulated experience and are prone to errors. In this paper, we propose an image-recognition method for ellipsoid-like herbaceous Tibetan medicinal materials that combines texture feature extraction and a deep-learning network. We created an image dataset consisting of 3200 images of 18 types of ellipsoid-like Tibetan medicinal materials. Due to the complex background and high similarity in the shape and color of the ellipsoid-like herbaceous Tibetan medicinal materials in the images, we conducted a multi-feature fusion experiment on the shape, color, and texture features of these materials. To leverage the importance of texture features, we utilized an improved LBP (local binary pattern) algorithm to encode the texture features extracted by the Gabor algorithm. We inputted the final features into the DenseNet network to recognize the images of the ellipsoid-like herbaceous Tibetan medicinal materials. Our approach focuses on extracting important texture information while ignoring irrelevant information such as background clutter to eliminate interference and improve recognition performance. The experimental results show that our proposed method achieved a recognition accuracy of 93.67% on the original dataset and 95.11% on the augmented dataset. In conclusion, our proposed method could aid in the identification and authentication of ellipsoid-like herbaceous Tibetan medicinal materials, reducing errors and ensuring the safe use of Tibetan medicinal materials in healthcare. Full article

(This article belongs to the Special Issue Perspectives and Prospects of Computer Recognition and Machine Learning in Signal and Image Processing, Selected Papers from PRML 2022)

► Show Figures

Figure 1

15 pages, 4306 KiB

Open AccessArticle

Super-Resolution Reconstruction of Terahertz Images Based on Residual Generative Adversarial Network with Enhanced Attention

by Zhongwei Hou, Xingzeng Cha, Hongyu An, Aiyang Zhang and Dakun Lai

Entropy 2023, 25(3), 440; https://doi.org/10.3390/e25030440 - 2 Mar 2023

Cited by 4 | Viewed by 1841

Abstract

Terahertz (THz) waves are widely used in the field of non-destructive testing (NDT). However, terahertz images have issues with limited spatial resolution and fuzzy features because of the constraints of the imaging equipment and imaging algorithms. To solve these problems, we propose a residual generative adversarial network based on enhanced attention (EA), which aims to pay more attention to the reconstruction of textures and details while not influencing the image outlines. Our method successfully recovers detailed texture information from low-resolution images, as demonstrated by experiments on the benchmark datasets Set5 and Set14. To use the network to improve the resolution of terahertz images, we create an image degradation algorithm and a database of terahertz degradation images. Finally, the real reconstruction of terahertz images confirms the effectiveness of our method. Full article

(This article belongs to the Special Issue Perspectives and Prospects of Computer Recognition and Machine Learning in Signal and Image Processing, Selected Papers from PRML 2022)

► Show Figures

Figure 1

16 pages, 8753 KiB

Open AccessArticle

GFI-Net: Global Feature Interaction Network for Monocular Depth Estimation

by Cong Zhang, Ke Xu, Yanxin Ma and Jianwei Wan

Entropy 2023, 25(3), 421; https://doi.org/10.3390/e25030421 - 26 Feb 2023

Cited by 1 | Viewed by 1043

Abstract

Monocular depth estimation techniques are used to recover the distance from the target to the camera plane in an image scene. However, there are still several problems, such as insufficient estimation accuracy, the inaccurate localization of details, and depth discontinuity in planes parallel to the camera plane. To solve these problems, we propose the Global Feature Interaction Network (GFI-Net), which aims to utilize geometric features, such as object locations and vanishing points, on a global scale. In order to capture the interactive information of the width, height, and channel of the feature graph and expand the global information in the network, we designed a global interactive attention mechanism. The global interactive attention mechanism reduces the loss of pixel information and improves the performance of depth estimation. Furthermore, the encoder uses the Transformer to reduce coding losses and improve the accuracy of depth estimation. Finally, a local–global feature fusion module is designed to improve the depth map’s representation of detailed areas. The experimental results on the NYU-Depth-v2 dataset and the KITTI dataset showed that our model achieved state-of-the-art performance with full detail recovery and depth continuation on the same plane. Full article

(This article belongs to the Special Issue Perspectives and Prospects of Computer Recognition and Machine Learning in Signal and Image Processing, Selected Papers from PRML 2022)

► Show Figures

Figure 1

20 pages, 3495 KiB

Open AccessArticle

A New Deep Learning Method with Self-Supervised Learning for Delineation of the Electrocardiogram

by Wenwen Wu, Yanqi Huang and Xiaomei Wu

Entropy 2022, 24(12), 1828; https://doi.org/10.3390/e24121828 - 15 Dec 2022

Cited by 3 | Viewed by 1701

Abstract

Heartbeat characteristic points are the main features of an electrocardiogram (ECG), which can provide important information for ECG-based cardiac diagnosis. In this manuscript, we propose a self-supervised deep learning framework with modified Densenet to detect ECG characteristic points, including the onset, peak and termination points of P-wave, QRS complex wave and T-wave. We extracted high-level features of ECG heartbeats from the QT Database (QTDB) and two other larger datasets, MIT-BIH Arrhythmia Database (MITDB) and MIT-BIH Normal Sinus Rhythm Database (NSRDB) with no human-annotated labels as pre-training. By applying different transformations to ECG signals, the task of discriminating signals before and after transformation was defined as the pretext task. Subsequently, the convolutional layer was frozen and the weights of the self-supervised network were transferred to the downstream task of characteristic point localizations on heart beats in the QT dataset. Finally, the mean ± standard deviation of the detection errors of our proposed self-supervised learning method in QTDB for detecting the onset, peak, and termination points of P-waves, the onset and termination points of QRS waves, and the peak and termination points of T-waves were −0.24 ± 10.04, −0.48 ± 11.69, −0.28 ± 10.19, −3.72 ± 8.18, −4.12 ± 13.54, −0.68 ± 20.42, and 1.34 ± 21.04. The results show that the deep learning network based on the self-supervised framework constructed in this manuscript can accurately detect the feature points of a heartbeat, laying the foundation for automatic extraction of key information related to ECG-based diagnosis. Full article

(This article belongs to the Special Issue Perspectives and Prospects of Computer Recognition and Machine Learning in Signal and Image Processing, Selected Papers from PRML 2022)

► Show Figures

Figure 1

17 pages, 731 KiB

Open AccessArticle

Financial Fraud Detection and Prediction in Listed Companies Using SMOTE and Machine Learning Algorithms

by Zhihong Zhao and Tongyuan Bai

Entropy 2022, 24(8), 1157; https://doi.org/10.3390/e24081157 - 19 Aug 2022

Cited by 5 | Viewed by 3561

Abstract

This paper proposes a new method that can identify and predict financial fraud among listed companies based on machine learning. We collected 18,060 transactions and 363 indicators of finance, including 362 financial variables and a class variable. Then, we eliminated 9 indicators which were not related to financial fraud and processed the missing values. After that, we extracted 13 indicators from 353 indicators which have a big impact on financial fraud based on multiple feature selection models and the frequency of occurrence of features in all algorithms. Then, we established five single classification models and three ensemble models for the prediction of financial fraud records of listed companies, including LR, RF, XGBOOST, SVM, and DT and ensemble models with a voting classifier. Finally, we chose the optimal single model from five machine learning algorithms and the best ensemble model among all hybrid models. In choosing the model parameter, optimal parameters were selected by using the grid search method and comparing several evaluation metrics of models. The results determined the accuracy of the optimal single model to be in a range from 97% to 99%, and that of the ensemble models as higher than 99%. This shows that the optimal ensemble model performs well and can efficiently predict and detect fraudulent activity of companies. Thus, a hybrid model which combines a logistic regression model with an XGBOOST model is the best among all models. In the future, it will not only be able to predict fraudulent behavior in company management but also reduce the burden of doing so. Full article

(This article belongs to the Special Issue Perspectives and Prospects of Computer Recognition and Machine Learning in Signal and Image Processing, Selected Papers from PRML 2022)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Perspectives and Prospects of Computer Recognition and Machine Learning in Signal and Image Processing, Selected Papers from PRML 2022

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (5 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI