Classification of measured unsafe liquids using microwave spectroscopy system by multivariate data analysis techniques.

To identify hazardous (illegal and explosive) materials, microwave measurement (free space reflection type method) method has been tried to find best results in different frequency ranges. The main goal is to cluster some materials which are mainly preferred by passenger for aircraft travel. Therefore, the multivariate data analysis methods have been preferred to classify or distinguish the measured liquids. Thus, the abilities of used techniques have been shown to make the classification process easier and more responsive, while determining the convenient measurement method that can reflect the unique properties of the liquids. The desired success has been achieved magnificently by self-organizing maps algorithm.

[1]  N. Shinohara,et al.  Development of a wideband microwave reactor with a coaxial cable structure , 2016 .

[2]  Martin Hudlička,et al.  Development of Measurement and Extraction Technique of Complex Permittivity Using Transmission Parameter S21 for Millimeter Wave Frequencies , 2017 .

[3]  L. Dauerman,et al.  Microwave Treatment of Hazardous Wastes: Removal of Volatile and Semi-Volatile Organic Contaminants From Soil , 1992 .

[4]  Markus Ringnér,et al.  What is principal component analysis? , 2008, Nature Biotechnology.

[5]  A. Mudhoo,et al.  Microwave Irradiation Technology In Waste Sludge And Wastewater Treatment Research , 2011 .

[6]  Alexander N. Gorban,et al.  SOM: Stochastic initialization versus principal components , 2016, Inf. Sci..

[7]  Nirupam Chakraborti,et al.  Genetic algorithms in materials design and processing , 2004 .

[8]  S. Maitra,et al.  Principle Component Analysis and Partial Least Squares: Two Dimension Reduction Techniques for Regression , 2008 .

[9]  Guohua Li,et al.  Could microwave induced catalytic oxidation (MICO) process over CoFe2O4 effectively eliminate brilliant green in aqueous solution? , 2013, Journal of Hazardous Materials.

[10]  Kamel Haddadi,et al.  Geometrical Optics-Based Model for Dielectric Constant and Loss Tangent Free-Space Measurement , 2014, IEEE Transactions on Instrumentation and Measurement.

[11]  Testing of Josephson Spectrometer with Waveguide Coupling , 2014 .

[12]  Teuvo Kohonen,et al.  Essentials of the self-organizing map , 2013, Neural Networks.

[13]  D. Pham,et al.  Selection of K in K-means clustering , 2005 .

[14]  Muhammet Tahir Guneser,et al.  Development of extraction techniques for dielectric constant from free-space measured S-parameters between 50 and 170 GHz , 2017, Journal of Materials Science: Materials in Electronics.

[15]  D. Acierno,et al.  Use of microwaves for in-situ removal of pollutant compounds from solid matrices. , 2012, Journal of hazardous materials.

[16]  M. Al-harahsheh,et al.  Microwave treatment of electric arc furnace dust with PVC: dielectric characterization and pyrolysis-leaching. , 2014, Journal of hazardous materials.

[17]  Tao Zhang,et al.  Free-space reflection method for measuring moisture content and bulk density of particulate materials at microwave frequency. , 2015, The Review of scientific instruments.

[18]  J. Chen,et al.  Removal of ammonia nitrogen in wastewater by microwave radiation: a pilot-scale study. , 2009, Journal of hazardous materials.

[19]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Claire Cardie,et al.  Proceedings of the Eighteenth International Conference on Machine Learning, 2001, p. 577–584. Constrained K-means Clustering with Background Knowledge , 2022 .

[21]  Erdal Celik,et al.  Determination of cutting parameters for silicon wafer with a Diamond Wire Saw using an artificial neural network , 2017 .

[22]  P. Tsakiridis,et al.  Greek "red mud" residue: a study of microwave reductive roasting followed by magnetic separation for a metallic iron recovery process. , 2013, Journal of hazardous materials.

[23]  Huseyin Kurt,et al.  Determination of lapping parameters for silicon wafer using an artificial neural network , 2017, Journal of Materials Science: Materials in Electronics.