scholarly journals Three-Dimensional Dental Analysis for Sex Estimation in the Italian Population: A Pilot Study Based on a Geometric Morphometric and Artificial Neural Network Approach

Healthcare ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 9
Author(s):  
Giorgio Oliva ◽  
Vilma Pinchi ◽  
Ilenia Bianchi ◽  
Martina Focardi ◽  
Corrado Paganelli ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Pilot Study ◽  
Partial Least Square ◽  
Least Square ◽  
Future Research ◽  
Italian Population ◽  
Neural Network Approach ◽  
Geometric Morphometric ◽  
Artificial Neural

Dental dimorphism can be used for discriminating sex in forensic contexts. Geometric morphometric analysis (GMA) allows the evaluation of the shape and size, separately, of uneven 3D objects. This study presents experiments using a novel combination of GMA and an artificial neural network (ANN) for sex classification, applied to premolars of Caucasian Italian adults (50 females and 50 males). General Procrustes superimposition (GPS) and the partial least square (PLS) method were performed, respectively, to study the shape variance between sexes and to eliminate landmark variations. The “set-aside” approach was used to assess the accuracy of the proposed neural networks. As the main findings of the pilot study, the proposed method applied to the first upper premolar correctly classified 90% of females and 73% of males of the test sample. The accuracy was 0.84 and 0.80 for the training and test samples, respectively. The sexual dimorphism resulting from GMA was low, although statistically significant. GMA combined with the ANN demonstrated better sex classification ability than previous odontometric or dental morphometric methods. Future research could overcome some limitations by considering a larger sample of subjects and other kinds of teeth and experimenting with the use of computer vision for automatic landmark positioning.

QSPR MODELLING OF STABILITY CONSTANTS OF METAL-THIOSEMICARBAZONE COMPLEXES USING MULTIVARIATE REGRESSION METHODS AND ARTIFICIAL NEURAL NETWORK

2021 ◽  
Vol 36 (06) ◽  
Author(s):  
NGUYEN MINH QUANG ◽  
TRAN NGUYEN MINH AN ◽  
NGUYEN HOANG MINH ◽  
TRAN XUAN MAU ◽  
PHAM VAN TAT
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Stability Constants ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Structure Property ◽  
Least Square Regression ◽  
Thiosemicarbazone Complexes ◽  
Artificial Neural

In this study, the stability constants of metal-thiosemicarbazone complexes, logb11 were determined by using the quantitative structure property relationship (QSPR) models. The molecular descriptors, physicochemical and quantum descriptors of complexes were generated from molecular geometric structure and semi-empirical quantum calculation PM7 and PM7/sparkle. The QSPR models were built by using the ordinary least square regression (QSPROLS), partial least square regression (QSPRPLS), primary component regression (QSPRPCR) and artificial neural network (QSPRANN). The best linear model QSPROLS (with k of 9) involves descriptors C5, xp9, electric energy, cosmo volume, N4, SsssN, cosmo area, xp10 and core-core repulsion. The QSPRPLS, QSPR PCR and QSPRANN models were developed basing on 9 varibles of the QSPROLS model. The quality of the QSPR models were validated by the statistical values; The QSPROLS: R2train = 0.944, Q2LOO = 0.903 and MSE = 1.035; The QSPRPLS: R2train = 0.929, R2CV = 0.938 and MSE = 1.115; The QSPRPCR: R2train = 0.934, R2CV = 0.9485 and MSE = 1.147. The neural network model QSPRANN with architecture I(9)-HL(12)-O(1) was presented also with the statistical values: R2train = 0.9723, and R2CV = 0.9731. The QSPR models also were evaluated externally and got good performance results with those from the experimental literature.

scholarly journals Comparison of partial least squares and artificial neural network chemometric techniques in determination of sulfamethoxazole and trimethoprim in pharmaceutical suspension by ATR–FTIR spectrometry

2011 ◽  
Vol 26 (2) ◽  
pp. 105-114 ◽  
Author(s):  
M. Khanmohammadi ◽  
N. Dallali ◽  
A. Bagheri Garmarudi ◽  
M. Zarnegar ◽  
K. Ghasemi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Partial Least Square ◽  
Least Square ◽  
Statistical Parameters ◽  
Modified Method ◽  
Ftir Spectrometry ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Partial Least Square (PLS) and Artificial Neural Network (ANN) techniques were compared during development of an analytical method for quantitative determination of sulfamethoxazole (SMX) and trimethoprim (TMP) in Co-Trimoxazole®suspension. The procedure was based on Attenuated Total Reflectance Fourier Transform Infrared (ATR–FTIR) spectrometry. The 800–2500 cm−1spectral region was selected for quantitative analysis.R2and relative error of prediction (REP) in PLS technique were (0.989, 2.128) and (0.986, 1.381) for SMX and TMP, respectively. These statistical parameters were improved using the ANN models considering the complexity of the sample and the speediness and simplicity of the method.R2and RMSEC in modified method were (0.997, 1.064) and (0.997, 0.634) for SMX and TMP, respectively.

scholarly journals Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

2019 ◽  
Vol 16 (2) ◽  
pp. 701
Author(s):  
Mohd Nazrul Effendy Mohd Idrus ◽  
Kim Seng Chia
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Latent Variables ◽  
Near Infrared ◽  
Spectroscopic Analysis ◽  
Partial Least Square ◽  
Least Square ◽  
Coefficient Of Determination ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

<p>Predictive models is crucial in near-infrared (NIR) spectroscopic analysis. Partial least square - artificial neural network (PLS-ANN) is a hybrid method that may improve the performance of prediction in NIR spectroscopic analysis. This study investigates the advantage of PLS-ANN over the well-known modelling in spectroscopy analysis that is partial least square (PLS) and artificial neural network (ANN). The results show that ANN that coupled with first order SG derivatives achieved the best prediction with root mean square error of prediction (RMSEP) of 0.3517 gd/L and coefficient of determination ( ) of 0.9849 followed by PLS-ANN with RMSEP of 0.4368 gd/L and  of 0.9787, and PLS with RMSEP of 0.4669 gd/L and  of 0.9727. This suggests that the spectrum information may unable to be totally represented by the first few latent variables of PLS and a nonlinear model is crucial to model these nonlinear information in NIR spectroscopic analysis.</p>

Sign in / Sign up

Export Citation Format

Share Document