This paper presents a new application of the Particle Swarm Optimization (PSO) algorithm to optimize Mel Frequency Cepstrum Coefficients (MFCC) parameters, in order to extract an optimal feature set for diagnosis of hypothyroidism in infants using Multi-Layer Perceptrons (MLP) neural network. MFCC features is influenced by the number of filter banks (f(b)) and the number of coefficients (n(c)) used. These parameters are critical in representation of the features as they affect the resolution and dimensionality of the features. In this paper, the PSO algorithm was used to optimize the values of f(b) and n(c). The MFCC features based on the PSO optimization were extracted from healthy and unhealthy infant cry signals and used to train MLP in the classification of hypothyroid infant cries. The results indicate that the PSO algorithm could determine the optimum combination of f(b) and n(c) that produce the best classification accuracy of the MLP.
In this paper, the SERS analysis technique for extracting principal components of non-structural protein 1 from its spectra is examined. The non-structural protein 1 is found a major role in the replication process of virus of flaviviridae, the cause for many viral diseases. SERS is a technique that can provide fingerprint spectral information of even a single molecule. However, the Raman spectra from SERS complicate the feature extraction process with redundant features. Principal Component Analysis is a signal processing technique, useful for filtering for the significant features while filtering off the redundant ones with minimal loss of information. Here, PCA adopting a 3-steps approach, i.e. Eigenvalue-One-Criterion, Scree test and Cumulative Percent Variance, is used to select significant principal components of NS1 from Raman spectra. It is found that principal components of NS1 from its spectra of [900x10] from SERS is found being trimmed to [9x10] by Scree test supplemented by EOC and [2x10] by CPV, with a corresponding reduction of 99% and 99.8% from the original spectral array. However, since the spectra of biological samples in actual is noisier, selection by the former of first nine components is found appropriate. So far, SERS analysis technique for detection of salivary NS1 has yet to be reported.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.