Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
Recent Advances in Representation Learning
share announcement

Recent Advances in Representation Learning

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (31 December 2021) | Viewed by 14070

Special Issue Editors

Dr. Imad Rida

E-Mail
Guest Editor
Laboratoire Biomécanique et Bioingénierie UMR 7338, Université de Technologie de Compiègne, Centre de Recherches de Royallieu, CS- 20529 - 60205 Compiègne CEDEX, France
Interests: machine learning; signal processing; image processing; pattern recognition
Prof. Dr. Lunke Fei

E-Mail Website
Guest Editor
Guangdong University of Technology, Guangzhou 510006, China
Interests: biometrics; machine learning; palmprint
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Dan Istrate

E-Mail Website
Guest Editor
Le laboratoire BioMécanique et BioIngénierie UMR 7338, Université de Technologie de Compiègne, 60200 Compiègne, France
Interests: biomedical signal processing; connected objects; e-health
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The performance of any pattern recognition system heavily depends on finding a good and suitable feature representation space where observations from different classes are well separated. The main methods range from conventional hand-crafted feature design (SIFT, LBP, HoG, etc.) to dimensionally reduction techniques (PCA, LDA, FA, ISOMAP, LLE, etc.) and feature selection (wrapper, filter, embedded) in the past two decades, until the recent deep neural networks (CNN, RNN, etc.). Unfortunately, finding this proper representation is a challenging problem which different communities have taken a huge interest in, including the machine learning, data mining, and computer vision communities.

This Special Issue aims to highlight advances in machine learning and pattern recognition. Potential topics include but are not limited to the following:

  • Unsupervised, semisupervised, and supervised representation learning;
  • Dictionary and sparse representation learning;
  • Deep representation learning;
  • Subspace learning and dimensional reduction;
  • Optimization for representation learning;
  • Application of representation learning.

Dr. Imad Rida
Prof. Dr. Lunke Fei
Prof. Dr. Dan Istrate
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. Electronics is an international peer-reviewed open access semimonthly 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 2400 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

  • machine learning
  • representation learning
  • sparse learning
  • deep learning.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

22 pages, 805 KiB  
Article
Robust Latent Common Subspace Learning for Transferable Feature Representation
by Shanhua Zhan, Weijun Sun and Peipei Kang
Electronics 2022, 11(5), 810; https://doi.org/10.3390/electronics11050810 - 04 Mar 2022
Cited by 4 | Viewed by 1320
Abstract
This paper proposes a novel robust latent common subspace learning (RLCSL) method by integrating low-rank and sparse constraints into a joint learning framework. Specifically, we transform the data from source and target domains into a latent common subspace to perform the data reconstruction, [...] Read more.
This paper proposes a novel robust latent common subspace learning (RLCSL) method by integrating low-rank and sparse constraints into a joint learning framework. Specifically, we transform the data from source and target domains into a latent common subspace to perform the data reconstruction, i.e., the transformed source data is used to reconstruct the transformed target data. We impose joint low-rank and sparse constraints on the reconstruction coefficient matrix which can achieve following objectives: (1) the data from different domains can be interlaced by using the low-rank constraint; (2) the data from different domains but with the same label can be aligned together by using the sparse constraint. In this way, the new feature representation in the latent common subspace is discriminative and transferable. To learn a suitable classifier, we also integrate the classifier learning and feature representation learning into a unified objective and thus the high-level semantics label (data label) is fully used to guide the learning process of these two tasks. Experiments are conducted on diverse data sets for image, object, and document classifications, and encouraging experimental results show that the proposed method outperforms some state-of-the-arts methods. Full article
(This article belongs to the Special Issue Recent Advances in Representation Learning)
►▼ Show Figures

Figure 1

19 pages, 4669 KiB  
Article
Proactive Cross-Layer Framework Based on Classification Techniques for Handover Decision on WLAN Environments
by Josué Vicente Cervantes-Bazán, Alma Delia Cuevas-Rasgado, Luis Martín Rojas-Cárdenas, Saúl Lazcano-Salas, Farid García-Lamont, Luis Arturo Soriano, José de Jesús Rubio and Jaime Pacheco
Electronics 2022, 11(5), 712; https://doi.org/10.3390/electronics11050712 - 25 Feb 2022
Cited by 1 | Viewed by 1344
Abstract
In recent years, modern technology has been increasing, and this has grown a derivate in big challenges related to the network and application infrastructures. New devices have been providing more high functionalities to users than ever before; however, these devices depend on a [...] Read more.
In recent years, modern technology has been increasing, and this has grown a derivate in big challenges related to the network and application infrastructures. New devices have been providing more high functionalities to users than ever before; however, these devices depend on a high functionality of network in order to ensure a correct functioning ability over applications. This is essential for mobile networking systems to evolve in order to meet the future requirements of capacity, coverage, and data rate. In addition, when a network problem happens, it could be converted into somethingmore disastrous and difficult to solve. A crucial point is the network physical change and the difficulties, such as loss continuity of services and the decision to select the future network to be connected. In this article, a new framework is proposed to forecast a future network to be connected through a mobile node in WLAN environments. The proposed framework considers a decision-making process based on five classifiers and the user’s position and acceleration data in order to anticipate the network change, reaching up to 96.75% accuracy in predicting the connection of this future network. In this way, an early change of network is obtained without packet and time loss during the network change. Full article
(This article belongs to the Special Issue Recent Advances in Representation Learning)
►▼ Show Figures

Figure 1

16 pages, 1464 KiB  
Article
A Hybrid Machine Learning Model for Predicting USA NBA All-Stars
by Alberto Arteta Albert, Luis Fernando de Mingo López, Kristopher Allbright and Nuria Gómez Blas
Electronics 2022, 11(1), 97; https://doi.org/10.3390/electronics11010097 - 29 Dec 2021
Cited by 2 | Viewed by 2404
Abstract
Throughout the modern age, sports have been a very important part of human existence. As our documentation of sports has become more advanced, so have the prediction capabilities. Presently, analysts keep track of a massive amount of information about each team, player, coach, [...] Read more.
Throughout the modern age, sports have been a very important part of human existence. As our documentation of sports has become more advanced, so have the prediction capabilities. Presently, analysts keep track of a massive amount of information about each team, player, coach, and matchup. This collection has led to the development of unparalleled prediction systems with high levels of accuracy. The issue with these prediction systems is that they are proprietary and very costly to maintain. In other words, they are unusable by the average person. Sports, being one of the most heavily analyzed activities on the planet, should be accessible to everyone. In this paper, a preliminary system for using publicly available statistics and open-source methods for predicting NBA All-Stars is introduced and modified to improve the accuracy of the predictions, which reaches values close to 0.9 in raw accuracy, and higher than 0.9 in specificity. Full article
(This article belongs to the Special Issue Recent Advances in Representation Learning)
►▼ Show Figures

Figure 1

20 pages, 2454 KiB  
Article
Harnessing the Power of Sensors and Machine Learning to Design Smart Fence to Protect Farmlands
by Preetam Suman, Deepak Kumar Singh, Fahad R. Albogamy and Mohammad Shibee
Electronics 2021, 10(24), 3094; https://doi.org/10.3390/electronics10243094 - 13 Dec 2021
Cited by 1 | Viewed by 2354
Abstract
Agriculture and animals are two crucial factors for ecological balance. Human–wildlife conflict is increasing day-by-day due to crop damage and livestock depredation by wild animals, causing local farmer’s economic loss resulting in the deepening of poverty. Techniques are needed to stop the crop [...] Read more.
Agriculture and animals are two crucial factors for ecological balance. Human–wildlife conflict is increasing day-by-day due to crop damage and livestock depredation by wild animals, causing local farmer’s economic loss resulting in the deepening of poverty. Techniques are needed to stop the crop damage caused by animals. The most prominent technique used to protect crops from animals is fencing, but somehow, it is not a full-proof solution. Most fencing techniques are harmful to animals. Thousands of animals die due to the side effects of fencing techniques, such as electrocution. This paper introduces a virtual fence to solve these issues. The proposed virtual fence is invisible to everyone, because it is an optical fiber sensor cable, which is laid 12-inches-deep in soil. A laser light is used at the start of the fiber sensor cable, and a detector detects at the end of the cable. The technique is based on the reflection of light inside the fiber optic cable. The interferometric technique is used to predict the changes in the pattern of the laser light. The fiber cable sensors are connected to a microprocessor, which can predict the intrusion of any animal. The use of machine learning techniques to pattern detection makes this technique highly efficient. The machine learning algorithms developed for the identification of animals can also classify the animal. The paper proposes an economical and feasible machine-learning-based solution to save crops from animals and to save animals from dangerous fencing. The description of the complete setup of optical fiber sensors, methodology, and machine learning algorithms are covered in this paper. This concept was implemented and regressive tests were carried out. Tests were performed on the data, which were not used for training purposes. Sets of people (50 people in each set) were randomly moved into the fiber optic cable sensor in order to test the effectiveness of the detection. There have been very few instances where the algorithm has been unable to categorize the detections into different animal classes. Three datasets were tested for configuration effectiveness. The complete setup was also tested in a zoo to test the identification of elephants and tigers. The efficiency of identification is 94% for human, 80% for tiger, and 75% for elephant. Full article
(This article belongs to the Special Issue Recent Advances in Representation Learning)
►▼ Show Figures

Figure 1

12 pages, 785 KiB  
Article
BU-Net: Brain Tumor Segmentation Using Modified U-Net Architecture
by Mobeen Ur Rehman, SeungBin Cho, Jee Hong Kim and Kil To Chong
Electronics 2020, 9(12), 2203; https://doi.org/10.3390/electronics9122203 - 21 Dec 2020
Cited by 68 | Viewed by 5747
Abstract
The semantic segmentation of a brain tumor is of paramount importance for its treatment and prevention. Recently, researches have proposed various neural network-based architectures to improve the performance of segmentation of brain tumor sub-regions. Brain tumor segmentation, being a challenging area of research, [...] Read more.
The semantic segmentation of a brain tumor is of paramount importance for its treatment and prevention. Recently, researches have proposed various neural network-based architectures to improve the performance of segmentation of brain tumor sub-regions. Brain tumor segmentation, being a challenging area of research, requires improvement in its performance. This paper proposes a 2D image segmentation method, BU-Net, to contribute to brain tumor segmentation research. Residual extended skip (RES) and wide context (WC) are used along with the customized loss function in the baseline U-Net architecture. The modifications contribute by finding more diverse features, by increasing the valid receptive field. The contextual information is extracted with the aggregating features to get better segmentation performance. The proposed BU-Net was evaluated on the high-grade glioma (HGG) datasets of the BraTS2017 Challenge—the test datasets of the BraTS 2017 and 2018 Challenge datasets. Three major labels to segmented were tumor core (TC), whole tumor (WT), and enhancing core (EC). To compare the performance quantitatively, the dice score was utilized. The proposed BU-Net outperformed the existing state-of-the-art techniques. The high performing BU-Net can have a great contribution to researchers from the field of bioinformatics and medicine. Full article
(This article belongs to the Special Issue Recent Advances in Representation Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop