Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition
Всесторонний обзор применения искусственных нейронных сетей для распознавания образов
2019-01-01
SCID: 54.1/66yfzus6
Discuss with AI
artificial neural networksconvolutional neural networks (CNN)object classificationpattern recognitionperformance evaluation metrics
Figures from the paper
Abstract (AI)
The era of artificial neural network (ANN) began with a simplified application in many fields and remarkable success in pattern recognition (PR) even in manufacturing industries. Although significant progress achieved and surveyed in addressing ANN application to PR challenges, nevertheless, some problems are yet to be resolved like whimsical orientation (the unknown path that cannot be accurately calculated due to its directional position). Other problem includes; object classification, location, scaling, neurons behavior analysis in hidden layers, rule, and template matching. Also, the lack of extant literature on the issues associated with ANN application to PR seems to slow down research focus and progress in the field. Hence, there is a need for state-of-the-art in neural networks application to PR to urgently address the above-highlights problems for more successes. The study furnishes readers with a clearer understanding of the current, and new trend in ANN models that effectively addresses PR challenges to enable research focus and topics. Similarly, the comprehensive review reveals the diverse areas of the success of ANN models and their application to PR. In evaluating the performance of ANN models, some statistical indicators for measuring the performance of the ANN model in many studies were adopted. Such as the use of mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), and variance of absolute percentage error (VAPE). The result shows that the current ANN models such as GAN, SAE, DBN, RBM, RNN, RBFN, PNN, CNN, SLP, MLP, MLNN, Reservoir computing, and Transformer models are performing excellently in their application to PR tasks. Therefore, the study recommends the research focus on current models and the development of new models concurrently for more successes in the field.
Key Findings
1
GAN, SAE, DBN, RBM, RNN, RBFN, PNN, CNN, SLP, MLP, MLNN, reservoir computing, and Transformer models are reported to perform excellently on pattern-recognition tasks; the review recommends developing current and new models concurrently.
2
Performance evaluation across reviewed studies commonly uses MAPE, MAE, RMSE, and VAPE statistical indicators.
3
Persistent pattern-recognition challenges include unknown orientation, object classification and localization, scale variation, hidden-layer neuron behavior, rule matching, and template matching.
4
The review identifies limited literature addressing these challenges as a factor slowing focused research and progress in ANN-based pattern recognition.
5
The review surveys artificial neural network applications in pattern recognition across diverse fields, including manufacturing, and reports substantial progress.
Research Object
Artificial neural network (ANN) models applied to pattern recognition tasks
Research Subject
the capabilities, performance, and unresolved challenges of ANN models in pattern-recognition tasks, including classification, localization, scaling, orientation handling, hidden-layer neuron behavior, and rule/template matching
Publication Details
Publication Date
2019-01-01
Journal
Publisher
ISSN
Cited by
808
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
Artificial neural networks: a tutorial1996
Convolutional neural networks: an overview and application in radiology2018
Machine Learning in Agriculture: A Review2018
Transformer-XL: Attentive Language Models beyond a Fixed-Length Context2019
A comprehensive review on automation in agriculture using artificial intelligence2019
Survey on Computer Vision for UAVs: Current Developments and Trends2017
Qualitative Spatial Reasoning over Questions (Short Paper)2022