Special Issue "Algorithms for Machine Learning and Pattern Recognition Tasks"

A special issue of Algorithms (ISSN 1999-4893).

Deadline for manuscript submissions: 30 September 2021.

Special Issue Editors

Prof. Dr. Hui Yu
E-Mail Website
Guest Editor
Prof. Dr. Mounim A. El Yacoubi
E-Mail Website
Guest Editor
Telecom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France
Interests: machine learning; deep learning; pattern recognition; modeling behavioral and physiological human data; human activity and gesture recognition; handwriting and voice analysis; human mobility analysis; biometrics; human–computer interaction; detection and assessment of neurodegenerative diseases from biometric signals
Special Issues and Collections in MDPI journals
Prof. Dr. Mehdi Ammi
E-Mail Website
Guest Editor
Department of Computer Science, University of Paris 8, 93526 Saint-Denis, France
Interests: human activity recognition; modeling physiological functions; emotions recognition; affective and social interaction; human–computer interaction; pervasive and ubiquitous environments; Internet of Things; e-health
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

Pattern recognition, the automatic recognition of patterns in the input data for solving different kinds of tasks, is a mature research field with more than 50 years of active research, which has resulted in the development of real-life successful applications such as speech recognition, handwritten mail sorting, medical imaging and natural language processing.

Pattern recognition is witnessing currently a spectacular development. The reason for which is sevenfold: the breakthrough in deep and representation learning has not only led to significantly improved performance, but it has also allowed breakthroughs in new pattern recognition. Beyond the usual dichotomy of supervised learning and classification vs. unsupervised learning and data mining/knowledge discovery in databases, significant advances have been achieved in research areas, such as self-supervised learning, hybrid deep reinforcement learning, pattern mining and graph neural networks. Moreover, while pattern recognition has been associated mainly with machine learning over the last few decades, symbolic AI and expert systems have also recently attracted increasing attention, especially with the advances in neural-symbolic computing.

This Special Issue aims to gather recent advances in algorithms for pattern recognition, particularly advanced machine/deep learning, as well as symbolic, AI techniques—investigated in the context of different tasks of classification, prediction or knowledge discovery. In addition, this Special Issue seeks to bring together academics and industrials to contribute and discuss the latest research and innovations in this field.

Prof. Dr. Hui Yu
Prof. Mounim A. El Yacoubi
Prof. Dr. Mehdi Ammi
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 papers will be 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. Algorithms 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 1400 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

  • Pattern recognition;
  • Supervised and unsupervised learning;
  • Self-supervised learning, reinforcement learning;
  • Classification, clustering, prediction;
  • Data mining, knowledge discovery in databases;
  • Artificial intelligence and machine learning;
  • Deep learning, CNN, RNN (LSTM, GRU, etc.), transformer models;
  • Transfer learning;
  • Explainable and attentional models;
  • Adversarial attacks and robust models;
  • Robustness of neural networks;
  • AI fairness;
  • Computer graphics, signal processing, bioinformatics, NLP, information retrieval;
  • Bayesian models;
  • Ensemble learning;
  • Model fusion;
  • Review of recent development in trends.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Knowledge-Driven Network for Object Detection
Algorithms 2021, 14(7), 195; https://doi.org/10.3390/a14070195 - 28 Jun 2021
Viewed by 610
Abstract
Object detection is a challenging computer vision task with numerous real-world applications. In recent years, the concept of the object relationship model has become helpful for object detection and has been verified and realized in deep learning. Nonetheless, most approaches to modeling object [...] Read more.
Object detection is a challenging computer vision task with numerous real-world applications. In recent years, the concept of the object relationship model has become helpful for object detection and has been verified and realized in deep learning. Nonetheless, most approaches to modeling object relations are limited to using the anchor-based algorithms; they cannot be directly migrated to the anchor-free frameworks. The reason is that the anchor-free algorithms are used to eliminate the complex design of anchors and predict heatmaps to represent the locations of keypoints of different object categories, without considering the relationship between keypoints. Therefore, to better fuse the information between the heatmap channels, it is important to model the visual relationship between keypoints. In this paper, we present a knowledge-driven network (KDNet)—a new architecture that can aggregate and model keypoint relations to augment object features for detection. Specifically, it processes a set of keypoints simultaneously through interactions between their local and geometric features, thereby allowing the modeling of their relationship. Finally, the updated heatmaps were used to obtain the corners of the objects and determine their positions. The experimental results conducted on the RIDER dataset confirm the effectiveness of the proposed KDNet, which significantly outperformed other state-of-the-art object detection methods. Full article
(This article belongs to the Special Issue Algorithms for Machine Learning and Pattern Recognition Tasks)
Show Figures

Figure 1

Back to TopTop