A unifying methodology for the evaluation of neural network models on novelty detection tasks

Barreto, Guilherme A.; Frota, Rewbenio A.

doi:10.1007/s10044-011-0265-3

Cited by 9 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Successively because neural networks do not need data recycling as in the statistic methods for detecting new events (Markou and Singh, 2003b). In several applications, the supervised learning neural networks most used for ND in a multi-class approach are MLP and RBF (Markou and Singh, 2003b; Barreto and Frota, 2012). Markou and Singh (2006) search in a model for ND with the image sequence analysis using neural networks.…”

Section: Annmentioning

confidence: 99%

“…MLP networks are successfully applied to solve complex problems using the backpropagation algorithm. The use of the Gaussian activation function for the MLP network forces the receptive field of neurons to be more selective, being activated only for a restricted region of the input space, optimizing the performance of the network for ND (Barreto and Frota, 2012;Vasconcelos and Fairhurst, 1995). The parameterization of the GMLP network with only a single hidden layer also improves its ability for ND, so that this technique allows to detect arbitrarily complex class limits (Hodge and Austin, 2004).…”

Section: Mlpmentioning

confidence: 99%

See 1 more Smart Citation

Novelty Detection Applied in Recognition of Facial Expressions

Bove

Cerqueira

Filho

2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

Esta pesquisa investiga a capacidade das redes Perceptron de Múltiplas Camadas (MLP) e Função de Base Radial (RBF) na tarefa de Detecção de Novidade (DN) no reconhecimento de expressões faciais usando recursos de vídeo. O conjunto de dados de vídeo utilizado é produzido por atores profissionais em estúdio com estados afetivos básicos do rosto humano. Os algoritmos Viola-Jones, Kanade-Lucas-Tomasi (KLT) e Análise de Componentes Principais (PCA) são usados na fase de pré-processamento para extrair atributos da face. Os resultados avaliam o desempenho das redes MLP e RBF na tarefa DN, usando novas expressões faciais compatíveis com as utilizadas na fase de treinamento e também examinam a capacidade das redes em DN usando as faces de atores nunca antes vistos pelas redes. Neste processo, as redes MLP e RBF têm uma precisão de 98% para tarefa de classificação, 68% e 98% para DN com dados semelhantes aos dados da fase de treinamento e 100% para DN com dados totalmente novos. Assim, este trabalho reúne métodos e técnicas aplicadas na DN utilizando Redes Neurais Artificiais (RNA), visando a produção de sistemas interativos de cognição no campo da computação afetiva, baseados em técnicas de Inteligência Artificial (IA) e Visão Computacional.

show abstract

Section: Annmentioning

confidence: 99%

Section: Mlpmentioning

confidence: 99%

Novelty Detection Applied in Recognition of Facial Expressions

Bove

Cerqueira

Filho

2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

show abstract

“…One output layer with nonlinear neurons and one or more intermediate layers composed of neurons that represent the network activation function is the composition of a MLP network [4,6,21,50]. The signal is always forward propagated, layer-by-layer.…”

Section: Multilayer Perceptronmentioning

confidence: 99%

Embedded real-time speed limit sign recognition using image processing and machine learning techniques

Gomes

Rebouças

Neto

et al. 2016

Neural Comput & Applic

View full text Add to dashboard Cite

The number of traffic accidents in Brazil has reached alarming levels and is currently one of the leading causes of death in the country. With the number of vehicles on the roads increasing rapidly, these problems will tend to worsen. Consequently, huge investments in resources to increase road safety will be required. The vertical R-19 system for optical character recognition of regulatory traffic signs (maximum speed limits) according to Brazilian Standards developed in this work uses a camera positioned at the front of the vehicle, facing forward. This is so that images of traffic signs can be captured, enabling the use of image processing and analysis techniques for sign detection. This paper proposes the detection and recognition of speed limit signs based on a cascade of boosted classifiers working with haar-like features. The recognition of the sign detected is achieved based on the optimum-path forest classifier (OPF), support vector machines (SVM), multilayer perceptron, k-nearest neighbor (kNN), extreme learning machine, least mean squares, and least squares machine learning techniques. The SVM, OPF and kNN classifiers had average accuracies higher than 99.5 %; the OPF classifier with a linear kernel took an average time of 87 ls to recognize a sign, while kNN took 11,721 ls and SVM 12,595 ls. This sign detection approach found and recognized successfully 11,320 road signs from a set of 12,520 images, leading to an overall accuracy of 90.41 %. Analyzing the system globally recognition accuracy was 89.19 %, as 11,167 road signs from a database with 12,520 signs were correctly recognized. The processing speed of the embedded system varied between 20 and 30 frames per second. Therefore, based on these results, the proposed system can be considered a promising tool with high commercial potential.

show abstract

“…It is well known that soft computing techniques could be modified into detectors in both static and dynamic applications and their performance mainly depends on the quality of training datasets. To be specific, as one of the pioneer algorithms, ANN has been proved useful and reported in [1][2][3][4][5][6][7][8][9]. Bishop first presented the topic of ANN based novelty detection [1].…”

Section: Introductionmentioning

confidence: 99%

Uncertainty Reduced Novelty Detection Approach Applied to Rotating Machinery for Condition Monitoring

Xiong

2015

Shock and Vibration

View full text Add to dashboard Cite

Novelty detection has been developed into a state-of-the-art technique to detect abnormal behavior and trigger alarm for in-field machine maintenance. With built-up models of normality, it has been widely applied to several situations with normal supervising dataset such as shaft rotating speed and component temperature available meanwhile in the absence of fault information. However, the research about vibration transmission based novelty detection remains unnoticed until recently. In this paper, vibration transmission measurement on rotor is performed; based on extreme value distributions, thresholds for novelty detection are calculated. In order to further decrease the false alarm rate, both measurement and segmentation uncertainty are considered, as they may affect threshold value and detection correctness heavily. Feasible reduction strategies are proposed and discussed. It is found that the associated multifractal coefficient and Kullback-Leibler Divergence operate well in the uncertainty reduction process. As shown by in situ applications to abnormal rotor with pedestal looseness, it is demonstrated that the abnormal states are detected. The higher specificity value proves the effectiveness of proposed uncertainty reduction method. This paper shows novel achievements of uncertainty reduced novelty detection applied to vibration signal in dynamical system and also sheds lights on its utilization in the field of health monitoring of rotating machinery.

show abstract

A unifying methodology for the evaluation of neural network models on novelty detection tasks

Cited by 9 publications

References 41 publications

Novelty Detection Applied in Recognition of Facial Expressions

Novelty Detection Applied in Recognition of Facial Expressions

Embedded real-time speed limit sign recognition using image processing and machine learning techniques

Uncertainty Reduced Novelty Detection Approach Applied to Rotating Machinery for Condition Monitoring

Contact Info

Product

Resources

About