Instrumentation & Measurement Magazine 23-6 - 29

A further quantitative confirmation was obtained by overlapping the maps produced in L-band and one performed by GIS
[20]. Table 1 reports the net change due to the above procedure.
The results of grasslands are obtained by external procedure
in bands different from L-one. The proposed research allows
improved applications of machine learning in the field of measurement and instrumentation.

References
[1]	 G. Andria, A. D'Orazio, A. Lay-Ekuakille, M. Moretti, P. Pieri,
F. Tralli, and M. Tropeano, "Accuracy assessment in photo
interpretation of remote sensing ERS-2/SAR Images," in Proc.
17th IEEE - IMTC2000, 2000.
[2]	 A. Lay-Ekuakille, M. Moretti, P. Pieri, F. Tralli, and M. Tropeano,
"Spectral characterization of soil by using Ers-2/Sar satellite
images," in Proc. EGS European Geophysicist Society Congress, 1999.
[3]	 "Sensor Systems." [Online]. Available: http://www.fao.org/3/
t0355e/t0355e04.htm.
[4]	 C. Huang et al., "Impact of sensor's point spread function on land
cover characterization: assessment and deconvolution," Remote
Sensing of Environment, vol. 80, no.2, pp. 203-212, 2002.
[5]	 J. Li and Z. Liu, "Self-measurements of point-spread function
for remote sensing optical imaging instruments," IEEE Trans.
Instrum. Meas., (early publication), 02 Sep. 2019.
[6]	 Z-Q. Zhao et al., "Object detection with deep learning: a review,"
IEEE Trans. Neural Networks and Learning Syst., vol. 30, no.11, pp.
3212-3232, 2019.

Fig. 11. Gaussian magnitude distribution and SAR image. (a) 1992; (b) 1996.

[7]	 "Json Encoder and Decoder." [Online]. Available: https://docs.
python.org/3/library/json.html.
[8]	 L. J. Koerner, T. A. Caswell, D. B. Allan and S. I. Campbell,

pixel. The weights are determined using the standard deviation of the gaussian law.

reproducible research," IEEE Trans. Instrum. Meas., vol. 69, no. 4,
pp. 1698-1707, Apr. 2020.

Conclusions

[9]	 N. D. Maron, L. Rokach, and A. Shmilovici, "Using the confusion

Environmental measurements, in particular land classification by means of SAR sensors, can be implemented and upped
for diverse environmental applications involving modeling
for predicting the behavior of environmental matrices [14]-
[16]. Machine learning can come to the rescue to the limits and
constraints of land classification as it is done in many other applications such as biomedical measurements [17], [18], because
there is a functional connection between land and health. In
fact, many algorithms which used the first-generation algorithms of artificial intelligence have been developed for both
lines of research. This paper illustrated findings in the field of
machine learning for environmental measurements and classification. A dedicated deep learning algorithm, based on open
computer vision in Python environment, was implemented to
classify the content of two different SAR images, from two different years, to see the evolution of land features over time. As
results, two images were yielded in L-band to see eventual increasing presence of leaves and trees. Major information has
been extracted with confirmation of reflectance, hence spectral density. A comparative analysis was done in terms of
convolution and kernel analysis by performing an intelligent
filtering to remove noise [19] due to reflection of signals on soil.
September 2020	

"A Python instrument control and data acquisition suite for

matrix for improving ensemble classifiers," in Proc. 2010 IEEE 26th
Convention of Electrical and Electronics Engineers, Nov. 2010.
[10]	J-Y. Chang and J.L. Chen, " Classifier-augmented median filters
for image restoration," IEEE Trans. Instrum. Meas., vol.53, no. 2,
pp. 351-356, 2004.
[11]	A. Tharwat, "Classification assessment methods," Applied
Computing and Informatics, in press, 2018.
[12]	S. Kim and R. Casper, "Applications of convolution in image
processing with MATLAB," University of Washington, 2013.
[Online]. Available: https://www.academia.edu/13962682/
Applications_of_Convolution_in_Image_Processing_with_
MATLAB.
[13]	"Confusion Matrix in Machine Learning," Geeks for Geeks.
[Online]. Available: https://www.geeksforgeeks.org/confusionmatrix-machine-learning/.
[14]	G. A. Giorgio, M. Ragosta, and V. Telesca, "Application of a
multivariate statistical index on series of weather measurements
at local scale," Measurement: J. Int. Meas. Confederation, vol. 112,
pp. 61-66, 2017.
[15]	M. G. Blasi, G. Liuzzi, G. Masiello, V. Telesca, and S. Venafra,
"Surface parameters from SEVIRI observations through a
kalman filter approach: application and evaluation of the

IEEE Instrumentation & Measurement Magazine	29

http://www.fao.org/3/t0355e/t0355e04.htm http://www.fao.org/3/t0355e/t0355e04.htm https://docs.python.org/3/library/json.html https://docs.python.org/3/library/json.html https://www.academia.edu/13962682/Applications_of_Convolution_in_Image_Processing_with_MATLAB https://www.academia.edu/13962682/Applications_of_Convolution_in_Image_Processing_with_MATLAB https://www.academia.edu/13962682/Applications_of_Convolution_in_Image_Processing_with_MATLAB https://www.geeksforgeeks.org/confusion-matrix-machine-learning/ https://www.geeksforgeeks.org/confusion-matrix-machine-learning/

Instrumentation & Measurement Magazine 23-6

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 23-6