Probabilistic neural-network structure determination for pattern classification

Mao, Kezhi; Tan, Kun; Ser, Wee

doi:10.1109/72.857781

Cited by 246 publications

(112 citation statements)

References 21 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…It is shown that the proposed PNN requires significantly fewer nodes and interconnection weights than the original model. In Mao et al (2000), a supervised PNN structure determination algorithm is introduced. This algorithm consists of two parts and runs in an iterative way: smoothing parameter computation by means of genetic algorithm and pattern layer neuron selection.…”

Section: Related Workmentioning

confidence: 99%

“…Four approaches are usually regarded: single parameter for whole PNN, single parameter for each class, separate parameter for each variable and separate parameter for each variable and class. In the research, diverse procedures have been developed to solve these tasks (Chtioui et al 1998;Specht 1992;Mao et al 2000;Georgiou et al 2008;Gorunescu et al 2005;Specht and Romsdahl 1994;Zhong et al 2007;Kusy and Zajdel 2015).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of prediction ability for reduced probabilistic neural network in data classification problems

Kusy

Kluska

2016

Soft Comput

View full text Add to dashboard Cite

One of the most important problems in probabilistic neural network (PNN) operation is the minimization of its structure. In this paper, two heuristic approaches of PNN's pattern layer reduction are applied. The first method is based on a k-means clustering procedure. In the second approach, the candidates for the network's pattern neurons are selected on the basis of a support vector machines algorithm. Modified models are compared in the classification problems with the traditional PNN, four well-known computational intelligence algorithms (single decision tree, multilayer perceptron, support vector machines, k-means algorithm) and PNN trained by the state-of-the-art procedures. Seven medical benchmark databases are investigated and one authors' own real ovarian cancer data set. Comparison is performed on the basis of the global performance indices which depend on the accuracy, sensitivity and specificity. These indices are computed using the standard tenfold cross-validation procedure. On the basis of the reported results, we show that the algorithm based on k-means clustering is a better PNN structure reduction procedure. Furthermore, this algorithm is much less timeconsuming.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Assessment of prediction ability for reduced probabilistic neural network in data classification problems

Kusy

Kluska

2016

Soft Comput

View full text Add to dashboard Cite

show abstract

“…The RBFN model (Mao et al, 2000) consists of three layers: the inputs and hidden and output layers. The input space can either be normalized or an actual representation can be used.…”

Section: Radial Basis Function Network (Rbfn)mentioning

confidence: 99%

Application of Signal Processing in Power Quality Monitoring

Moravej¹,

Pazoki²,

Abdoos³

2011

Power Quality Â€“Â Monitoring, Analysis and Enhancement

View full text Add to dashboard Cite

“…However, the differences are that the training stage of a PNN is actually to keep the training vectors in the system by assigning their value into weights connecting the neurons in the input layer to corresponding neurons in the pattern layers. Also, a smoothing parameter can be determined by either using trial and error in testing vectors (Kim et al 2005) or applying a genetic algorithm to minimise the classification errors in the training vectors (Mao et al 2000).…”

Section: Pnn Classificationmentioning

confidence: 99%

Application of probabilistic neural networks in modelling structural deterioration of stormwater pipes

Tran

Perera

et al. 2006

Urban Water Journal

View full text Add to dashboard Cite

In Australia, when stormwater systems were first introduced over 100 years ago, they were constructed independently of the sewer systems, and they are normally the responsibility of the third level of government, i.e., local government or city councils. Because of the increasing age of these stormwater systems and their worsening performance, there are serious concerns in a significant number of city councils regarding their deterioration. A study has been conducted on the structural deterioration of concrete pipes that make up the bulk of the stormwater pipe systems in these councils. In an attempt to look for a reliable deterioration model, a probabilistic neural network (PNN) model was developed using the data set supplied from participating councils. The PNN model was validated with snapshot-based sample data, which makes up the data set. The predictive performance of the PNN model was compared with a traditional parametric model using discriminant analysis on the same data set. Structural deterioration was hypothesised to be influenced by a set of explanatory factors, including pipe design and construction factors-such as pipe size, buried depth-and site factorssuch as soil type, moisture index, tree root intrusion, etc. The results show that the PNN model has a better predictive power and uses significantly more input variables (i.e., explanatory factors) than the discriminant model. More importantly, the key factors for prediction in the PNN model are difficult to interpret, suggesting that besides prediction accuracy, model interpretation is an important issue for further investigation.

show abstract

Probabilistic neural-network structure determination for pattern classification

Cited by 246 publications

References 21 publications

Assessment of prediction ability for reduced probabilistic neural network in data classification problems

Assessment of prediction ability for reduced probabilistic neural network in data classification problems

Application of Signal Processing in Power Quality Monitoring

Application of probabilistic neural networks in modelling structural deterioration of stormwater pipes

Contact Info

Product

Resources

About