Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
Pattern Recognition Using Neural Networks
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Pattern Recognition Using Neural Networks

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 14071

Special Issue Editor

Prof. Dr. Michele Calì

E-Mail Website
Guest Editor
Department of Electrical, Electronics and Computer Engineering (DIEEI), University of Catania, 95124 Catania, Italy
Interests: industrial technical drawing; computer-assisted drawing; exercises of automotive constructions; geometric modeling of machines
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

It is known that pattern recognition is a process of finding regularities and similarities in data (images, texts, videos, numbers, etc.) perceived from the real world with sensors. These similarities can be found based on statistical analysis, historical data, or the already gained knowledge by the machine itself. Among the different approaches for pattern recognition, such as backpropagation, high-order nets, time-delay neural networks, and recurrent nets, neural networks offer undisputed advantages. The main advantages are their adaptive learning, self-organization, and fault tolerance capabilities. One of the best neural model used for pattern recognition is the feed-forward network. Feed-forward means that there is no feedback to the input. Similar to the way that human beings learn from mistakes, neural networks could also learn from their mistakes by giving feedback to the input patterns. This kind of feedback would be used to reconstruct the input patterns and make them free from error, thus increasing the performance of the neural networks. The complexity of constructing the network can be avoided using backpropagation algorithms. During this supervised phase, the network compares its actual output produced with what it was meant to produce—the desired output. This means that the network works backward, going from the output unit to the input units to adjust the weight of its connections between the units until the difference between the actual and desired outcome produces the lowest possible error. Local minima are one of the main problems associated with backpropagation algorithms. In addition, neural networks have issues associated with hyper-parameters such as learning rate, architecture selection, feature representation, modularity, and scaling. Despite these problems, the application of neural networks has spread everywhere.

The Special Issue is proposed as a cross-disciplinary and sector issue, with the aim of contributing to an increase in the level of knowledge in the context of pattern recognition using neural networks. In particular, researchers are solicited to present investigations of new neural models and novelties introduced by recent approaches to the following topics:

- Image processing, segmentation, and analysis;

- Computer vision;

- Seismic analysis;

- Radar signal classification;

- Speech recognition;

- Fingerprint identification;

- Medical diagnosis;

- Stock market analysis.

Dr. Michele Calì
Guest Editor

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. Sensors 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 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 vision
  • Seismic analysis
  • Radar signal classification
  • Speech recognition
  • Fingerprint identification
  • Medical diagnosis
  • Stock market analysis

Published Papers (6 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

17 pages, 5069 KiB  
Article
An Advanced Rider-Cornering-Assistance System for PTW Vehicles Developed Using ML KNN Method
by Fakhreddine Jalti, Bekkay Hajji, Alberto Acri and Michele Calì
Sensors 2023, 23(3), 1540; https://doi.org/10.3390/s23031540 - 31 Jan 2023
Cited by 1 | Viewed by 1667
Abstract
The dynamic behavior of a Powered Two-Wheeler (PTW) is much more complicated than that of a car, which is due to the strong coupling between the longitudinal and lateral dynamics produced by the large roll angles. This makes the analysis of the dynamics, [...] Read more.
The dynamic behavior of a Powered Two-Wheeler (PTW) is much more complicated than that of a car, which is due to the strong coupling between the longitudinal and lateral dynamics produced by the large roll angles. This makes the analysis of the dynamics, and therefore the design and synthesis of the controller, particularly complex and difficult. In relation to assistance in dangerous situations, several recent manuscripts have suggested devices with limitations of cornering velocity by proposing restrictive models. However, these models can lead to repulsion by the users of PTW vehicles, significantly limiting vehicle performance. In the present work, the authors developed an Advanced Rider-cornering Assistance System (ARAS) based on the skills learned by riders running across curvilinear trajectories using Artificial Intelligence (AI) and Neural Network (NN) techniques. New algorithms that allow the value of velocity to be estimated by prediction accuracy of up to 99.06% were developed using the K-Nearest Neighbor (KNN) Machine Learning (ML) technique. Full article
(This article belongs to the Special Issue Pattern Recognition Using Neural Networks)
►▼ Show Figures

Figure 1

15 pages, 19479 KiB  
Article
Deep Multi-Scale Features Fusion for Effective Violence Detection and Control Charts Visualization
by Nadia Mumtaz, Naveed Ejaz, Suliman Aladhadh, Shabana Habib and Mi Young Lee
Sensors 2022, 22(23), 9383; https://doi.org/10.3390/s22239383 - 01 Dec 2022
Cited by 7 | Viewed by 2304
Abstract
The study of automated video surveillance systems study using computer vision techniques is a hot research topic and has been deployed in many real-world CCTV environments. The main focus of the current systems is higher accuracy, while the assistance of surveillance experts in [...] Read more.
The study of automated video surveillance systems study using computer vision techniques is a hot research topic and has been deployed in many real-world CCTV environments. The main focus of the current systems is higher accuracy, while the assistance of surveillance experts in effective data analysis and instant decision making using efficient computer vision algorithms need researchers’ attentions. In this research, to the best of our knowledge, we are the first to introduce a process control technique: control charts for surveillance video data analysis. The control charts concept is merged with a novel deep learning-based violence detection framework. Different from the existing methods, the proposed technique considers the importance of spatial information, as well as temporal representations of the input video data, to detect human violence. The spatial information are fused with the temporal dimension of the deep learning model using a multi-scale strategy to ensure that the temporal information are properly assisted by the spatial representations at multi-levels. The proposed frameworks’ results are kept in the history-maintaining module of the control charts to validate the level of risks involved in the live input surveillance video. The detailed experimental results over the existing datasets and the real-world video data demonstrate that the proposed approach is a prominent solution towards automated surveillance with the pre- and post-analyses of violent events. Full article
(This article belongs to the Special Issue Pattern Recognition Using Neural Networks)
►▼ Show Figures

Figure 1

13 pages, 4674 KiB  
Article
Multilayer Plasmonic Nanostructures for Improved Sensing Activities Using a FEM and Neurocomputing-Based Approach
by Grazia Lo Sciuto, Christian Napoli, Paweł Kowol, Giacomo Capizzi, Rafał Brociek, Agata Wajda and Damian Słota
Sensors 2022, 22(19), 7486; https://doi.org/10.3390/s22197486 - 02 Oct 2022
Viewed by 1372
Abstract
In order to obtain optimized elementary devices (photovoltaic modules, power transistors for energy efficiency, high-efficiency sensors) it is necessary to increase the energy conversion efficiency of these devices. A very effective approach to achieving this goal is to increase the absorption of incident [...] Read more.
In order to obtain optimized elementary devices (photovoltaic modules, power transistors for energy efficiency, high-efficiency sensors) it is necessary to increase the energy conversion efficiency of these devices. A very effective approach to achieving this goal is to increase the absorption of incident radiation. A promising strategy to increase this absorption is to use very thin regions of active material and trap photons near these surfaces. The most effective and cost-effective method of achieving such optical entrapment is the Raman scattering from excited nanoparticles at the plasmonic resonance. The field of plasmonics is the study of the exploitation of appropriate layers of metal nanoparticles to increase the intensity of radiation in the semiconductor by means of near-field effects produced by nanoparticles. In this paper, we focus on the use of metal nanoparticles as plasmonic nanosensors with extremely high sensitivity, even reaching single-molecule detection. The study conducted in this paper was used to optimize the performance of a prototype of a plasmonic photovoltaic cell made at the Institute for Microelectronics and Microsystems IMM of Catania, Italy. This prototype was based on a multilayer structure composed of the following layers: glass, AZO, metal and dielectric. In order to obtain good results, it is necessary to use geometries that orthogonalize the absorption of light, allowing better transport of the photocarriers—and therefore greater efficiency—or the use of less pure materials. For this reason, this study is focused on optimizing the geometries of these multilayer plasmonic structures. More specifically, in this paper, by means of a neurocomputing procedure and an electromagnetic fields analysis performed by the finite elements method (FEM), we established the relationship between the thicknesses of Aluminum-doped Zinc oxide (AZO), metal, dielectric and their main properties, characterizing the plasmonic propagation phenomena as the optimal wavelengths values at the main interfaces AZO/METAL and METAL/DIELECTRIC. Full article
(This article belongs to the Special Issue Pattern Recognition Using Neural Networks)
►▼ Show Figures

Figure 1

18 pages, 8371 KiB  
Article
Workshop Safety Helmet Wearing Detection Model Based on SCM-YOLO
by Bin Zhang, Chuan-Feng Sun, Shu-Qi Fang, Ye-Hai Zhao and Song Su
Sensors 2022, 22(17), 6702; https://doi.org/10.3390/s22176702 - 05 Sep 2022
Cited by 11 | Viewed by 2768
Abstract
In order to overcome the problems of object detection in complex scenes based on the YOLOv4-tiny algorithm, such as insufficient feature extraction, low accuracy, and low recall rate, an improved YOLOv4-tiny safety helmet-wearing detection algorithm SCM-YOLO is proposed. Firstly, the Spatial Pyramid Pooling [...] Read more.
In order to overcome the problems of object detection in complex scenes based on the YOLOv4-tiny algorithm, such as insufficient feature extraction, low accuracy, and low recall rate, an improved YOLOv4-tiny safety helmet-wearing detection algorithm SCM-YOLO is proposed. Firstly, the Spatial Pyramid Pooling (SPP) structure is added after the backbone network of the YOLOv4-tiny model to improve its adaptability of different scale features and increase its effective features extraction capability. Secondly, Convolutional Block Attention Module (CBAM), Mish activation function, K-Means++ clustering algorithm, label smoothing, and Mosaic data enhancement are introduced to improve the detection accuracy of small objects while ensuring the detection speed. After a large number of experiments, the proposed SCM-YOLO algorithm achieves a mAP of 93.19%, which is 4.76% higher than the YOLOv4-tiny algorithm. Its inference speed reaches 22.9FPS (GeForce GTX 1050Ti), which meets the needs of the real-time and accurate detection of safety helmets in complex scenes. Full article
(This article belongs to the Special Issue Pattern Recognition Using Neural Networks)
►▼ Show Figures

Figure 1

17 pages, 2723 KiB  
Article
WildGait: Learning Gait Representations from Raw Surveillance Streams
by Adrian Cosma and Ion Emilian Radoi
Sensors 2021, 21(24), 8387; https://doi.org/10.3390/s21248387 - 15 Dec 2021
Cited by 7 | Viewed by 2018
Abstract
The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person [...] Read more.
The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition require cooperative gait scenarios, in which a single person is walking multiple times in a straight line in front of a camera. We address the challenges of real-world scenarios in which camera feeds capture multiple people, who in most cases pass in front of the camera only once. We address privacy concerns by using only motion information of walking individuals, with no identifiable appearance-based information. As such, we propose a self-supervised learning framework, WildGait, which consists of pre-training a Spatio-Temporal Graph Convolutional Network on a large number of automatically annotated skeleton sequences obtained from raw, real-world surveillance streams to learn useful gait signatures. We collected and compiled the largest pretraining dataset to date of anonymized walking skeletons called Uncooperative Wild Gait, containing over 38k tracklets of anonymized walking 2D skeletons. We make the dataset available to the research community. Our results surpass the current state-of-the-art pose-based gait recognition solutions. Our proposed method is reliable in training gait recognition methods in unconstrained environments, especially in settings with scarce amounts of annotated data. Full article
(This article belongs to the Special Issue Pattern Recognition Using Neural Networks)
►▼ Show Figures

Figure 1

21 pages, 6833 KiB  
Communication
Neural Network Analysis for Microplastic Segmentation
by Gwanghee Lee and Kyoungson Jhang
Sensors 2021, 21(21), 7030; https://doi.org/10.3390/s21217030 - 23 Oct 2021
Cited by 7 | Viewed by 2370
Abstract
It is necessary to locate microplastic particles mixed with beach sand to be able to separate them. This paper illustrates a kernel weight histogram-based analytical process to determine an appropriate neural network to perform tiny object segmentation on photos of sand with a [...] Read more.
It is necessary to locate microplastic particles mixed with beach sand to be able to separate them. This paper illustrates a kernel weight histogram-based analytical process to determine an appropriate neural network to perform tiny object segmentation on photos of sand with a few microplastic particles. U-net and MultiResUNet are explored as target networks. However, based on our observation of kernel weight histograms, visualized using TensorBoard, the initial encoder stages of U-net and MultiResUNet are useful for capturing small features, whereas the later encoder stages are not useful for capturing small features. Therefore, we derived reduced versions of U-net and MultiResUNet, such as Half U-net, Half MultiResUNet, and Quarter MultiResUNet. From the experiment, we observed that Half MultiResUNet displayed the best average recall-weighted F1 score (40%) and recall-weighted mIoU (26%) and Quarter MultiResUNet the second best average recall-weighted F1 score and recall-weighted mIoU for our microplastic dataset. They also require 1/5 or less floating point operations and 1/50 or a smaller number of parameters over U-net and MultiResUNet. Full article
(This article belongs to the Special Issue Pattern Recognition Using Neural Networks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop