Note
Application of probabilistic neural network in bacterial identification by biochemical profiles

https://doi.org/10.1016/j.mimet.2013.05.004Get rights and content

Highlights

  • We construct a Probabilistic Neural Network (PNN) in bacterial identification.

  • One taxon in our PNN can correspond to several biochemical profiles.

  • Our PNN can be constructed on classification data other than probability matrix.

Abstract

An algorithm of Probabilistic Neural Network (PNN) for bacterial identification based on the probability matrix of API 20E system as a case study is reported. The PNN shows the correct identification of all the taxa belonging to the training and test sets and possesses merits over the conventional methods.

Section snippets

Acknowledgments

This work was supported by the Science Foundation of General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China (2009IK176 and 2012IK305).

References (16)

There are more references available in the full text version of this article.

Cited by (8)

  • Small lung nodules detection based on local variance analysis and probabilistic neural network

    2018, Computer Methods and Programs in Biomedicine
    Citation Excerpt :

    PNN methodology is often used particularly in classification tasks, and it has been applied successfully in solving problems in different areas of application [16–18]. This concept for easing the classification task has also been applied in medicine, especially for detecting resistivity to antibiotics [19], as well as for diagnosing hepatitis [20] and in gaining solutions to other medical problems [21]. We restricts Σ to two global smoothing parameter σ1 and σ2, where σ1 is used in those basis functions that have centers coming from the set of true positive nodules while σ2 for the false positive ones.

  • Using an unsupervised approach of Probabilistic Neural Network (PNN) for land use classification from multitemporal satellite images

    2015, Applied Soft Computing
    Citation Excerpt :

    In addition, it is considered as an implementation of the Bayes optimal decision rule in the NN form based on nearest neighbor classifiers [36,37]. Several recent studies [4,8,38–46] used PNN for classification and showed that this method provides satisfactory results if the initial target classes are defined correctly. In this way, finding the basis function centers (classes) with their appropriate number is an important step to achieve suitable classification.

  • Mutation breeding of bacillus amyloliquefaciens HT-Q6

    2018, Fresenius Environmental Bulletin
  • Interval probabilistic neural network

    2017, Neural Computing and Applications
View all citing articles on Scopus
View full text