Classification of Selected Essential Oil from Family Zingiberaceae Using E-Nose and Discriminant Factorial Analysis (DFA) Techniques: An Initial Study

2015 ◽  
Vol 799-800 ◽  
pp. 932-936 ◽  
Author(s):  
Sahrim Lias ◽  
Nor Azah Mohamad Ali ◽  
Mailina Jamil ◽  
Azrina Aziz ◽  
Siti Humeirah Ab Ghani ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Statistical Analysis ◽  
Essential Oils ◽  
Initial Study ◽  
Factorial Analysis ◽  
Extraction Techniques ◽  
Aromatic Plant ◽  
P Values ◽  
Discriminant Factorial Analysis

Essential oils are very valuable natural resources and considered as secondary metabolites. They are produced from several parts of aromatic plant by using different type of extraction techniques. Each technique produced slightly different output oil yield and smell however they produced the same major chemicals compound markers when they are analysed using chemical analysis and profiling technique. Pure essential oils are known to have very strong odor and there are several techniques used to differentiate the volatile odor generated. In this study, Electronic Nose (E-Nose) technology is used to distinguish the smell among 8 samples selected within the same Zingiberaceae family. Their pattern recognition profiles were examined by statistical analysis using Discriminant Factorial Analysis (DFA). The result shows that the E-Nose technology combined with DFA were successfully discriminating all 8 samples within the same family with significant p-values < 0.05 across all samples and 100% recognition value.

scholarly journals Minimization of the Line Resistance Impact on Memdiode-Based Simulations of Multilayer Perceptron Arrays Applied to Pattern Recognition

2021 ◽  
Vol 11 (1) ◽  
pp. 9
Author(s):  
Fernando Leonel Aguirre ◽  
Nicolás M. Gomez ◽  
Sebastián Matías Pazos ◽  
Félix Palumbo ◽  
Jordi Suñé ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Ex Situ ◽  
Multilayer Perceptrons ◽  
Spice Simulation ◽  
Large Dataset ◽  
High Line ◽  
Calibration Algorithm ◽  
The Impact ◽  
Line Resistance

In this paper, we extend the application of the Quasi-Static Memdiode model to the realistic SPICE simulation of memristor-based single (SLPs) and multilayer perceptrons (MLPs) intended for large dataset pattern recognition. By considering ex-situ training and the classification of the hand-written characters of the MNIST database, we evaluate the degradation of the inference accuracy due to the interconnection resistances for MLPs involving up to three hidden neural layers. Two approaches to reduce the impact of the line resistance are considered and implemented in our simulations, they are the inclusion of an iterative calibration algorithm and the partitioning of the synaptic layers into smaller blocks. The obtained results indicate that MLPs are more sensitive to the line resistance effect than SLPs and that partitioning is the most effective way to minimize the impact of high line resistance values.

Essential oils and quality composts sourced by recycling vegetable residues from the aromatic plant supply chain

2021 ◽  
Vol 162 ◽  
pp. 113255 ◽  
Author(s):  
Massimo Zaccardelli ◽  
Graziana Roscigno ◽  
Catello Pane ◽  
Giuseppe Celano ◽  
Marisa Di Matteo ◽  
...  
Keyword(s):  
Supply Chain ◽  
Essential Oils ◽  
Aromatic Plant

scholarly journals Instrumental Odour Monitoring System Classification Performance Optimization by Analysis of Different Pattern-Recognition and Feature Extraction Techniques

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 114
Author(s):  
Tiziano Zarra ◽  
Mark Gino K. Galang ◽  
Florencio C. Ballesteros ◽  
Vincenzo Belgiorno ◽  
Vincenzo Naddeo
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Performance Optimization ◽  
Industrial Plant ◽  
Mathematical Treatment ◽  
Extraction Techniques ◽  
Peak Period ◽  
Linear Discriminant ◽  
Artificial Neural

Instrumental odour monitoring systems (IOMS) are intelligent electronic sensing tools for which the primary application is the generation of odour metrics that are indicators of odour as perceived by human observers. The quality of the odour sensor signal, the mathematical treatment of the acquired data, and the validation of the correlation of the odour metric are key topics to control in order to ensure a robust and reliable measurement. The research presents and discusses the use of different pattern recognition and feature extraction techniques in the elaboration and effectiveness of the odour classification monitoring model (OCMM). The effect of the rise, intermediate, and peak period from the original response curve, in collaboration with Linear Discriminant Analysis (LDA) and Artificial Neural Networks (ANN) as a pattern recognition algorithm, were investigated. Laboratory analyses were performed with real odour samples collected in a complex industrial plant, using an advanced smart IOMS. The results demonstrate the influence of the choice of method on the quality of the OCMM produced. The peak period in combination with the Artificial Neural Network (ANN) highlighted the best combination on the basis of high classification rates. The paper provides information to develop a solution to optimize the performance of IOMS.

Sign in / Sign up

Export Citation Format

Share Document