Research

Open AccessArticle

A New Correlation Coefficient Based on T-Spherical Fuzzy Information with Its Applications in Medical Diagnosis and Pattern Recognition

by

,

,

and

Symmetry 2022, 14(11), 2317; https://doi.org/10.3390/sym14112317 - 04 Nov 2022

Viewed by 506

Abstract

The T-Spherical fuzzy set (TSFS) is the most generalized form among the introduced fuzzy frameworks. It obtains maximum information from real-life phenomena due to its maximum range. Consequently, TSFS is a very useful structure for dealing with information uncertainties, especially when human opinion [...] Read more.

The T-Spherical fuzzy set (TSFS) is the most generalized form among the introduced fuzzy frameworks. It obtains maximum information from real-life phenomena due to its maximum range. Consequently, TSFS is a very useful structure for dealing with information uncertainties, especially when human opinion is involved. The correlation coefficient (CC) is a valuable tool, possessing symmetry, to determine the similarity degree between objects under uncertainties. This research aims to develop a new CC for TSFS to overcome the drawbacks of existing methods. The proposed CCs are generalized, flexible, and can handle uncertain situations where information has more than one aspect. In addition, the proposed CCs provide decision-makers independence in establishing their opinion. Based on some remarks, the usefulness of the new CC is reviewed, and its generalizability is evaluated. Moreover, the developed new CC is applied to pattern recognition for investment decisions and medical diagnosis of real-life problems to observe their effectiveness and applicability. Finally, the validity of the presented CC is tested by comparing it with the results of the previously developed CC. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Open AccessArticle

Weakly Supervised Object Detection with Symmetry Context

by

Xinyu Gu

,

Qian Zhang

and

Zheng Lu

Symmetry 2022, 14(9), 1832; https://doi.org/10.3390/sym14091832 - 04 Sep 2022

Viewed by 768

Abstract

Recently, weakly supervised object detection (WSOD) with image-level annotation has attracted great attention in the field of computer vision. The problem is often formulated as multiple instance learning in the existing studies, which are often trapped by discriminative object parts and fail to [...] Read more.

Recently, weakly supervised object detection (WSOD) with image-level annotation has attracted great attention in the field of computer vision. The problem is often formulated as multiple instance learning in the existing studies, which are often trapped by discriminative object parts and fail to localize the object boundary precisely. In this work, we alleviate this problem by exploiting contextual information that may potentially increase object localization accuracy. Specifically, we propose novel context proposal mining strategies and a Symmetry Context Module to leverage surrounding contextual information of precomputed region proposals. Both naive and Gaussian-based context proposal mining methods are adopted to yield informative context proposals symmetrically surrounding region proposals. Then mined context proposals are fed into our Symmetry Context Module to encourage the model to select proposals that contain the whole object, rather than the most discriminative object parts. Experimental results show that the mean Average Precision (mAP) of the proposed method achieves

52.4 %

on the PASCAL VOC 2007 dataset, outperforming the state-of-the-art methods and demonstrating its effectiveness for weakly supervised object detection. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Open AccessArticle

Identify Patterns in Online Bin Packing Problem: An Adaptive Pattern-Based Algorithm

by

,

,

,

,

and

Symmetry 2022, 14(7), 1301; https://doi.org/10.3390/sym14071301 - 23 Jun 2022

Cited by 1 | Viewed by 1398

Abstract

Bin packing is a typical optimization problem with many real-world application scenarios. In the online bin packing problem, a sequence of items is revealed one at a time, and each item must be packed into a bin immediately after its arrival. Inspired by [...] Read more.

Bin packing is a typical optimization problem with many real-world application scenarios. In the online bin packing problem, a sequence of items is revealed one at a time, and each item must be packed into a bin immediately after its arrival. Inspired by duality in optimization, we proposed pattern-based adaptive heuristics for the online bin packing problem. The idea is to predict the distribution of items based on packed items, and to apply this information in packing future arrival items in order to handle uncertainty in online bin packing. A pattern in bin packing is a combination of items that can be packed into a single bin. Patterns selected according to past items are adopted and periodically updated in scheduling future items in the algorithm. Symmetry in patterns and the stability of patterns in the online bin packing problem are discussed. We have implemented the algorithm and compared it with the Best-Fit in a series of experiments with various distribution of items to show its effectiveness. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Open AccessArticle

Visual Inspection Method for Metal Rolls Based on Multi-Scale Spatial Location Feature

by

,

,

,

,

and

Symmetry 2022, 14(7), 1291; https://doi.org/10.3390/sym14071291 - 22 Jun 2022

Viewed by 667

Abstract

Metal rolls in a non-ferrous-metal manufacturing workshop manifest the characteristics of symmetry, multiple scales and mutual covering, which poses great challenges for metal roll detection. To solve this problem, firstly, an efficient attention mechanism algorithm named ECLAM (efficient capture location attendant model) is [...] Read more.

Metal rolls in a non-ferrous-metal manufacturing workshop manifest the characteristics of symmetry, multiple scales and mutual covering, which poses great challenges for metal roll detection. To solve this problem, firstly, an efficient attention mechanism algorithm named ECLAM (efficient capture location attendant model) is proposed for capturing spatial position features efficiently, to obtain complete location information for metal rolls in a complex environment. ECLAM can improve the ability to extract the spatial features of backbone networks and reduce the influence of the non-critical background. In addition, in order to give feature maps a larger receptive field and improve the weight of location information in multi-scale feature maps, a nonlinear feature fusion module named LFFM (location feature fusion module) is used to fuse two adjacent feature images. Finally, a multi-scale object detection network named L-MSNet (location-based multi-scale object detection network) based on the combination of ECLAM and LFFM is proposed and used to accurately detect multi-scale metal rolls. In the experiments, multi-scale metal roll images are collected from an actual non-ferrous-metal manufacturing workshop. On this basis, a pixel-level image dataset is constructed. Comparative experiments show that, compared with other object detection methods, L-MSNet can detect multi-scale metal rolls more accurately. The average accuracy is improved by 2% to 5%, and the average accuracy of small and medium-sized objects is also significantly improved by 3% to 6%. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Open AccessArticle

An Efficient Asymmetric Nonlinear Activation Function for Deep Neural Networks

by

,

,

,

and

Symmetry 2022, 14(5), 1027; https://doi.org/10.3390/sym14051027 - 17 May 2022

Cited by 4 | Viewed by 1113

Abstract

As a key step to endow the neural network with nonlinear factors, the activation function is crucial to the performance of the network. This paper proposes an Efficient Asymmetric Nonlinear Activation Function (EANAF) for deep neural networks. Compared with existing activation functions, the [...] Read more.

As a key step to endow the neural network with nonlinear factors, the activation function is crucial to the performance of the network. This paper proposes an Efficient Asymmetric Nonlinear Activation Function (EANAF) for deep neural networks. Compared with existing activation functions, the proposed EANAF requires less computational effort, and it is self-regularized, asymmetric and non-monotonic. These desired characteristics facilitate the outstanding performance of the proposed EANAF. To demonstrate the effectiveness of this function in the field of object detection, the proposed activation function is compared with several state-of-the-art activation functions on the typical backbone networks such as ResNet and DSPDarkNet. The experimental results demonstrate the superior performance of the proposed EANAF. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Open AccessArticle

Using Machine Learning to Profile Asymmetry between Spiral Galaxies with Opposite Spin Directions

by

Lior Shamir

Symmetry 2022, 14(5), 934; https://doi.org/10.3390/sym14050934 - 04 May 2022

Viewed by 723

Abstract

Spiral galaxies can spin clockwise or counterclockwise, and the spin direction of a spiral galaxy is a clear visual characteristic. Since in a sufficiently large universe the Universe is expected to be symmetric, the spin direction of a galaxy is merely the perception [...] Read more.

Spiral galaxies can spin clockwise or counterclockwise, and the spin direction of a spiral galaxy is a clear visual characteristic. Since in a sufficiently large universe the Universe is expected to be symmetric, the spin direction of a galaxy is merely the perception of the observer, and therefore, galaxies that spin clockwise are expected to have the same characteristics of galaxies spinning counterclockwise. Here, machine learning is applied to study the possible morphological differences between galaxies that spin in opposite directions. The dataset used in this study is a dataset of 77,840 spiral galaxies classified by their spin direction, as well as a smaller dataset of galaxies classified manually. A machine learning algorithm was applied to classify between images of clockwise galaxies and counterclockwise galaxies. The results show that the classifier was able to predict the spin direction of the galaxy by its image in accuracy higher than mere chance, even when the images in one of the classes were mirrored to create a dataset with consistent spin directions. That suggests that galaxies that seem to spin clockwise to an Earth-based observer are not necessarily fully symmetric to galaxies that spin counterclockwise; while further research is required, these results are aligned with previous observations of differences between galaxies based on their spin directions. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Open AccessArticle

Symmetrically Stacked Long Short-Term Memory Networks for Fall Event Recognition Using Compact Convolutional Neural Networks-Based Tracker

by

Nur Ayuni Mohamed

,

Mohd Asyraf Zulkifley

,

Nor Azwan Mohamed Kamari

and

Zulaikha Kadim

Symmetry 2022, 14(2), 293; https://doi.org/10.3390/sym14020293 - 01 Feb 2022

Cited by 3 | Viewed by 770

Abstract

In recent years, the advancement of pattern recognition algorithms, specifically the deep learning-related techniques, have propelled a tremendous amount of researches in fall event recognition systems. It is important to detect a fall incident as early as possible, whereby a slight delay in [...] Read more.

In recent years, the advancement of pattern recognition algorithms, specifically the deep learning-related techniques, have propelled a tremendous amount of researches in fall event recognition systems. It is important to detect a fall incident as early as possible, whereby a slight delay in providing immediate assistance can cause severe unrecoverable injuries. One of the main challenges in fall event recognition is the imbalanced training data between fall and no-fall events, where a real-life fall incident is a sporadic event that occurs infrequently. Most of the recent techniques produce a lot of false alarms, as it is hard to train them to cover a wide range of fall situations. Hence, this paper aims to detect the exact fall frame in a video sequence, as such it will not be dependent on the whole clip of the video sequence. Our proposed approach consists of a two-stage module where the first stage employs a compact convolutional neural network tracker to generate the object trajectory information. Features of interest will be sampled from the generated trajectory paths, which will be fed as the input to the second stage. The next stage network then models the temporal dependencies of the trajectory information using symmetrical Long Short-Term Memory (LSTM) architecture. This two-stage module is a novel approach as most of the techniques rely on the detection module rather than the tracking module. The simulation experiments were tested using Fall Detection Dataset (FDD). The proposed approach obtains an expected average overlap of 0.167, which is the best performance compared to Multi-Domain Network (MDNET) and Tree-structured Convolutional Neural Network (TCNN) trackers. Furthermore, the proposed 3-layers of stacked LSTM architecture also performs the best compared to the vanilla recurrent neural network and single-layer LSTM. This approach can be further improved if the tracker model is firstly pre-tuned in offline mode with respect to a specific type of object of interest, rather than a general object. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Open AccessArticle

Social Bots Detection via Fusing BERT and Graph Convolutional Networks

by

,

,

,

and

Symmetry 2022, 14(1), 30; https://doi.org/10.3390/sym14010030 - 27 Dec 2021

Cited by 6 | Viewed by 2610

Abstract

The online social media ecosystem is becoming more and more confused because of more and more fake information and the social media of malicious users’ fake content; at the same time, unspeakable pain has been brought to mankind. Social robot detection uses supervised [...] Read more.

The online social media ecosystem is becoming more and more confused because of more and more fake information and the social media of malicious users’ fake content; at the same time, unspeakable pain has been brought to mankind. Social robot detection uses supervised classification based on artificial feature extraction. However, user privacy is also involved in using these methods, and the hidden feature information is also ignored, such as semi-supervised algorithms with low utilization rates and graph features. In this work, we symmetrically combine BERT and GCN (Graph Convolutional Network, GCN) and propose a novel model that combines large scale pretraining and transductive learning for social robot detection, BGSRD. BGSRD constructs a heterogeneous graph over the dataset and represents Twitter as nodes using BERT representations. Corpus learning via text graph convolution network is a single text graph, which is mainly built for corpus-based on word co-occurrence and document word relationship. BERT and GCN modules can be jointly trained in BGSRD to achieve the best of merit, training data and unlabeled test data can spread label influence through graph convolution and can be carried out in the large-scale pre-training of massive raw data and the transduction learning of joint learning representation. The experiment shows that a better performance can also be achieved by BGSRD on a wide range of social robot detection datasets. Full article

(This article belongs to the Special Issue Symmetry in Pattern Recognition)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Special Issue "Symmetry in Pattern Recognition"

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI