Special lssues

Pattern Recognition Based on Machine Learning

Submission Deadline: 31 March 2024 (closed)

Guest Editors

Prof. Dr. Jungpil SHIN, The University of Aizu, Aizuwakamatsu, Japan.
Prof. Dr. Md. Al Mehedi Hasan, Rajshahi University of Engineering and Technology, Bangladesh.

Summary

In current decades, the pattern is an abstract idea that can be found in our daily activities. Usually, pattern elements have a repeated manner that can be physically visualized or computationally recognized by specific algorithms or mathematical formulas. Any of the senses, like geometric shapes, can be observed as a pattern. In contrast, the analysis may only observe patterns in mathematics, science, or another computation field. In the digital platform, a vector or matrix can be represented the pattern's actual information or features. These pattern-based features can be easily handled or analyzed through the various applications of artificial intelligence (AI) based machine learning (ML) technologies. The ML-based technique aims to let the computer make its own critical decision by reducing human involvement with the pattern data. Pattern recognition (PR) is recognizing a pattern based on the features or statistical information extracted raced from the image, video, or sensor pattern using various machine learning algorithms. There is various application of the PR in the field of computer science and Electrical Engineering, such as computer vision, sensor data analysis, natural language processing, speech recognition, speaker identification, computer vision, sensor data analysis, natural language processing, speech recognition, multimedia document recognition (MDR), automatic medical diagnosis, robotics, bioinformatics, and so on. This Special Issue aims to provide the author's collaboration and to network among institutions or universities for promoting the research and publishing innovative and technically sound research papers that exhibit theoretical and practical contributions to PR by employing ML.


Keywords

Image and Video Processing;
Image Segmentation;
Computer Vision;
Speech Recognition;
Automated Target Recognition;
Character Recognition;
Gesture and Human Activity Recognition;
Sign Language Recognition;
Neurological Disorder Detection;
EEG Classification;
Opensim Based Gesture Recognition;
Handwriting Recognition;
Gait Analysis Methods in Rehabilitation;
Industrial Inspection;
Medical Diagnosis;
Health Informatics;
Biomedical Signal and Image Processing;
Bioinformatics;
Deep Learning (DL) for Healthcare Data;
Sensor Fusion of Biomedical Data;
Brain-Computer Interface;
Mental Disorder Detection;
Control System;
Remote Sensing;
Healthcare Application;
Machine Learning (ML), Deep Learning (DL), and The Internet of Things (IoT);
Large-Scale Dataset Analysis;
Current State-Of-The-Art and Future Trends of ML And DL.

Published Papers


  • Open Access

    ARTICLE

    RLAT: Lightweight Transformer for High-Resolution Range Profile Sequence Recognition

    Xiaodan Wang, Peng Wang, Yafei Song, Qian Xiang, Jingtai Li
    Computer Systems Science and Engineering, Vol.48, No.1, pp. 217-246, 2024, DOI:10.32604/csse.2023.039846
    (This article belongs to the Special Issue: Pattern Recognition Based on Machine Learning)
    Abstract High-resolution range profile (HRRP) automatic recognition has been widely applied to military and civilian domains. Present HRRP recognition methods have difficulty extracting deep and global information about the HRRP sequence, which performs poorly in real scenes due to the ambient noise, variant targets, and limited data. Moreover, most existing methods improve the recognition performance by stacking a large number of modules, but ignore the lightweight of methods, resulting in over-parameterization and complex computational effort, which will be challenging to meet the deployment and application on edge devices. To tackle the above problems, this paper proposes… More >

Share Link