Professional Documents
Culture Documents
The classical results of an electrophoresis test are The main goal of our application is to replace the
like a five curves. Therefore, in this case, the specialist interpretation when an experienced
physician’s experience is very important for the good physician is not available.
interpretation of results. [2] In the next we present the result obtained using the
application for this situation.
The curve extracted from electrophoresis gel step of the test is computing of maximum values.
represents the input data for the genetic algorithm. These values are the values for albumin, gamma
After the algorithm configuration, in the main globulin, alpha globulin, etc.
window of the application, the computed curves are The original curve is the representation of normal
displayed approximating the original ones. The parameters. Figure 5 presents the superposition of
purpose of our method is the automatic drawing of the original curve and computed curves in different
five curves. If the curve is drawn exactly, the final moments of the application running.
The results can be seen in figure 6. This application is easy to use and its runtime is very short. The graphical
interfaces allow the clear visualization of process interpretation.
Corina SAVULESCU, Zdzislaw POLKOWSKI
Figure 6. The final results
V. CONCLUSIONS
In figure 6, the computed parameters: albumin, Our study indicates that the genetic algorithms can
alpha globulin, etc are presented. be successfully used and are more robust than other
methods of controlled search; they use performance
functions obtained through simple transformations of
IV. FUTURE WORK the function under evaluation. Also, genetic
Based on our research and according to Debiprasad algorithms are easy to use and can find optimal
Ghosh, genetic algorithms can be implemented in any solutions very easily.
field besides the medical one, e.g business, logistics, This application is an alternative method for
and management. This is possible as long as you can evaluation of the laboratory tests (in special
convert it as an optimization problem with a model electrophoresis tests), using a part of artificial
represented by a list of parameters, which is enabled intelligence. The main advantage of this method is the
with genetic operations like: mutation, crossover and need of minimal knowledge in the medical field. For
selection. this reason, the implementation of this approach
When you have a model, which is ready for provides an instrument easy to use, which offers the
optimization using genetic algorithm, but your design tests results quickly and clearly.
or business intuition is more accurate than the result Although the results of research and tests have
given by simulation. [4]. demonstrated the effectiveness of the use of genetic
Today, genetic algorithms have become the most algorithms, they could be further developed in a
valuable asset in advertising. Currently websites are number of ways by testing them in many other fields
gathering data about their users. Not only that users such as business, management, logistics etc.
read but what they read and also verify if they read it
in their entirety and how long it took them. On this
basis, you can appropriate whether they were REFERENCES
interested. After that all users can be grouped and [1] C. Săvulescu, I. Sima, E. Sofron, “The functional
drawn conclusions. Thanks to genetic algorithms, it is identification of systems using genetic algorithms”,
Proceedings of the 1th International Symposium on Electrical
possible to find twins. If 100 of the people who have and Electronics Engineering, pp. 82-85, ISBN 973-627-355-3,
used the service 40 have common characteristics, it Galaţi 12-13 october 2006J.
means that when other people with these [2] A.T.Andrews, – Theory, Techiniques ans Biotechnical and
characteristics are found in the network, the Clinical Applications, Oxford University Press, 1993.
probability of using the service is higher [5]. [3] Al. Ene, C. Savulescu, “Sisteme cu inteligenta artificiala”,
Indrumar de laborator, Pitesti, 1998.
Another interesting area of research concerning the
[4] [Online] Available: https://www.quora.com/How-can-I-run-
use of genetic algorithms is scheduling and planning a simulations-using-genetic-algorithms-in-non-science-fields-e-
business process. Scheduling issues where you have g-design-or-business, access date 2017-04-09.
to allocate resources to tasks collection are usually [5] [Online] Available: http://www.rp.pl/Biznes-IT/309209922-
difficult to solve due to the presence of multiple Sztuczna-inteligencja-przyszloscia-nowoczesnego-
constraints [6]. biznesu.html#ap-1, access date 2017-04-07.
[6] [Online] Available: http://zeszyty- naukowe.wwsi.edu.pl
zeszyty/zeszyt1/Algorytmy_Ewolucyjne_I_Ich_Zastosowania.
pdf, access date 2017-04-05.