ArticlePDF Available

Production of Disease-Free Olive Seedlings with Artificial Intelligence and Biotechnological Methods

Authors:

Abstract and Figures

It is an inevitable fact that the applications of machine learning and artificial intelligence technologies in agricultural biotechnology approaches, whose applications are increasing rapidly in almost every field, will have an important place in determining the future fate of agriculture. Applications in which artificial intelligence is adapted to biotechnological processes such as breeding, in vitro culture studies, germplasm preservation, disease-free plant production, genetic transformation, and other genetic analyzes are becoming increasingly common. In the current study is highlighted the potential benefits between artificial intelligence and agricultural technologies. As with many plant species, viral diseases have negative effects on fruit yield, life span, and quality of olive varieties, which are important in economy. Elimination of viruses from the plant with traditional methods is quite laborious, takes a lot of time, and often fails to produce successful results. However, new protocols have been developed to eliminate persistent pathogens. These protocols include techniques such as heat application (thermotherapy), chemical therapy (chemotherapy), tissue culture methods (meristem culture). When these techniques are applied alone or together, it may be possible to obtain anti-virus plants. Artificial intelligence technology will make it possible to benefit from the method to be used in the most efficient way by revealing which of these biotechnological methods can be used in the most effective and optimal conditions, and the possible advantages and disadvantages as a result of comparing with others.
Content may be subject to copyright.
RESEARCH ARTICLE
European Journal of Biology and Biotechnology
www.ejbio.org
DOI: http://dx.doi.org/10.24018/ejbio.2021.2.3.172
Vol 2 | Issue 3 | June 2021
79
I. INTRODUCTION
Machine learning and artificial intelligence, which are the
computer programming sciences for digital platforms such
as computer and smartphone to learn from data, have begun
to be common applied in in vitro-based and/or classical
plant breeding studies for evaluation of the data flow
obtained from plant observed phenotypes to DNA
sequences. Machine learning methods can be divided into
three classes: deep learning models, nonlinear and linear
algorithms and supervised models. In plant biotechnology,
there are different process for application of non-linear non-
parametric machine learning algorithms such as random
arrangement (RA), deep neural networks (DNN), artificial
neural networks (ANN), support vector machines (SVM)
and convoluted neural networks (CNN) [1]. Distorted data
sets obtained by photo viewing data or sequencing data, can
be evaluated via machine learning algorithms [2]. DNA
sequencing data can be used in machine learning models to
identify and classify displaceable elements [3]. Using
machine learning algorithms, breeders can predict multiple
dependent variables (multiple outputs) through variable
combinations of multiple inputs in a single model and
decrease the analysis required.
Olive (Olea europaea L.), originated from above
Mesopotamia and southwest of Asia including part of
Turkey's Southeastern Anatolia Region and Syria. Taking
the olive into culture started on the eastern shores of the
Mediterranean approximately 3000 BC and made it one of
the unique fruit cultivars cultivated in this area [4]. Today,
the Mediterranean area supports 98% of the world's olive oil
production with nearly 2000 culture varieties [5]. Spreading
to variable regions from origin centre where they were
cultivated, ensures olives one of the most considerable
horticultural plant species and makes the studies required for
conserving its germplasm a very significant priority.
Recently studies on mitochondrial analysis show that wild
olive species from Mediterranean basin originated from two
different locations, one in Maghreb and the other in the Near
East [6]. It is indicated that the olives cultivation began
approximately 5500 years ago, after the human migration
from the wild Mediterranean olive known as "Oleaster",
which began to spread throughout North Africa and
Southern Europe. The original development of the olive
genetic resources is based on the selection and
characterization of the best trees, which is the beginning of
the clonal genetic basis of the cultivars in addition to the
vegetative multiplication [7].
Production of Disease-Free Olive Seedlings with
Artificial Intelligence and Biotechnological Methods
S. Galatali, M. A. Balci, O. Akguller, and E. Kaya
ABSTRACT
It is an inevitable fact that the applications of machine learning and
artificial intelligence technologies in agricultural biotechnology approaches,
whose applications are increasing rapidly in almost every field, will have an
important place in determining the future fate of agriculture. Applications
in which artificial intelligence is adapted to biotechnological processes such
as breeding, in vitro culture studies, germplasm preservation, disease-free
plant production, genetic transformation, and other genetic analyzes are
becoming increasingly common. In the current study is highlighted the
potential benefits between artificial intelligence and agricultural
technologies. As with many plant species, viral diseases have negative
effects on fruit yield, life span, and quality of olive varieties, which are
important in economy. Elimination of viruses from the plant with
traditional methods is quite laborious, takes a lot of time, and often fails to
produce successful results. However, new protocols have been developed to
eliminate persistent pathogens. These protocols include techniques such as
heat application (thermotherapy), chemical therapy (chemotherapy), tissue
culture methods (meristem culture). When these techniques are applied
alone or together, it may be possible to obtain anti-virus plants. Artificial
intelligence technology will make it possible to benefit from the method to
be used in the most efficient way by revealing which of these
biotechnological methods can be used in the most effective and optimal
conditions, and the possible advantages and disadvantages as a result of
comparing with others.
Keywords: Artificial Intelligence, biotechnology, Olea europaea L.
plant viruses.
Published Online: June 13, 2021
ISSN: 2684-5199
DOI: 10.24018/ejbio.2021.2.3.172
S. Galatali
Mugla Sitki Kocman University,
Mugla, Tukey.
(e-mail: selingalatali mu.edu.tr)
M. A. Balci
Mugla Sitki Kocman University,
Mugla, Tukey.
(e-mail: mehmetalibalci mu.edu.tr)
O. Akguller
Mugla Sitki Kocman University,
Mugla, Tukey.
(e-mail: oakguller mu.edu.tr)
E. Kaya*
Mugla Sitki Kocman University,
Mugla, Tukey.
(e-mail: ergunkaya mu.edu.tr)
*Corresponding Author
@
@
@
@
RESEARCH ARTICLE
European Journal of Biology and Biotechnology
www.ejbio.org
DOI: http://dx.doi.org/10.24018/ejbio.2021.2.3.172
Vol 2 | Issue 3 | June 2021
80
As with many plant species, viral diseases have negative
effects on fruit yield, life span, and quality of olive varieties,
which are important in our country's (Turkey) economy
(Fig. 1). These negative effects, which can lead to tree
losses, may occur when the plant is infected by viruses
through insects and/or birds vectors due to reasons such as
plant injury. Types of viruses that have been detected in the
Mediterranean climate zone in which our country is located
so far and that cause infection in olive trees are Olive vein
yellowing associated potexvirus (OVYaV), Olive Latent 2
Bromovirus (OLV2), Olive latent sobemovirus 1 (OLV1),
Olive latent ringspot nepovirus (OLRV), Cucumber mosaic
cucumovirus (CMV), Tobacco mosaic tobamovirus (TMV),
Arabis mosaic nepovirus (ArMV), Strawberry latent
ringspot nepovirus (SLRSV), and Cherry leaf roll nepovirus
(CLRV) [8]-[13].
Fig. 1. Symptomatic effects of Olive vein yellowing associated potexvirus
(OVYaV) on leaf and fruit in "Memecik" olive cultivars collected from
Muğla/Köyceğiz.
Olive trees are an important carrier of viruses that cause
viral infections, and in our country, olive producers do not
pay attention to whether the olive trees from which the
cuttings are carrying viruses in their cutting works for
seedling production [14]. In this context, it is necessary to
examine the plantation of our country in terms of viral
diseases, to identify those infected with the disease and to
diagnose existing viral diseases, and thus to fight virus
diseases effectively. Since there is no chemical method that
can be used in the control of plant viral diseases, the main
goal of the fight is to prevent the spread of existing viral
diseases by using biotechnological methods to produce
virus-free and disease-free seedlings.
In addition to traditional methods such as destroying the
sources of virus infection, directly protecting, and fighting
the vectors that carry the virus from plant to plant, growing
plants resistant to virus infections, treatment with various
biotechnological methods (thermotherapy, chemotherapy) or
advanced tissue culture methods such as purification using
meristem culture. Elimination of viruses from the plant with
traditional methods is quite laborious, takes a lot of time,
and often fails to produce successful results [15]. However,
new protocols have been developed to eliminate persistent
pathogens. These protocols include techniques such as heat
application (thermotherapy), chemical therapy
(chemotherapy), tissue culture methods (meristem culture).
When these techniques are applied alone or together, it may
be possible to obtain anti-virus plants.
Meristem culture has been used for the purification of
plants from viruses since the 1930s [16], [17]. This
technique utilizes the difference in the amount of virus
particles in different plant cells. The apical end and root
meristem cells of the plant are very small due to their
continuous division characteristics. Hence the probability of
viruses being present in these cells is very low, these tissues
are highly preferred in the production of virus-free and
disease-free plants [18]. Although it cannot be stated that
these parts of the plant are completely free of viruses, the
treatment efficiency can be increased by applying different
treatment options together (i.e., in conjunction with each
other) [19].
The treatment of plant viruses with thermotherapy on one
hand is based on the fact that the virus concentration
decreases towards the top of the plant, and on the other
hand, it inhibits the reproduction and diffusion of the plant
virus due to the increase in temperature. This technique can
also be applied in conjunction with meristem culture and
chemotherapy [20]. It has been reported that this treatment
method has been used in combination with chemotherapy in
the treatment of apical parts (parts larger than the meristem)
with meristem culture since the 1960s [21], [22]. It has also
been reported that the apical portions treated in this way are
still used in virus-free plant recovery [23].
Conventionally, developed as an alternative to the
prevention and elimination of viruses and plant diseases and
often preferred in the literature, in vivo, and in vitro
thermotherapy treatments are used to eliminate several plant
viruses [24]. Postman and Mehlenbacher [25] achieved the
elimination of ApMV virus, which they determined by
ELISA method, on hazelnut varieties from different
countries by thermotherapy technique. Manganaris et al.
[26] developed an effective thermotherapy protocol for the
eradication of PNRSV and PPV from nectarines and
emphasized that this could be extended by applying it to
commercial Prunus spp. varieties.
In the cryotherapy method, the isolated meristems are
subjected to cryoprotective processes in the most
appropriate way, treated with liquid nitrogen (-196 °C), and
then transferred to the appropriate regeneration medium and
their development is observed. The basis of the
cryopreservation technique is that the transport of viral
particles to the meristematic dome is difficult due to the lack
of advanced conduction tissues in the meristems, and thus
regenerated new tissues can be virus-free. Cryotherapy
method is an up-to-date technique developed for virus
elimination from infected plants. Using the cryotherapy
method, potato (Solanum tuberosum L., Solanaceae), sweet
potato (Ipomea batatas [L.] Lam., Convolvulaceae), grape
(Vitis vinifera L.; Vitaceae), citrus fruits (Citrus spp.,
Rutaceae) and plum (Purunus spp., Rosaceae), blackberry
(Rubus idaeus L.; Rosaceae) and banana (Musa spp.,
Musaceae) have been used to eradicate different viruses
infected plants [27]-[31].
Nowadays, thanks to newly developed technologies, the
use of biotechnological methods is increasingly common in
the treatment of these and similar pathogen-based diseases,
which cause significant losses in plants. The limitation in
these applications is the different application requirements
for each plant species and even variety. Thanks to
a b
c
RESEARCH ARTICLE
European Journal of Biology and Biotechnology
www.ejbio.org
DOI: http://dx.doi.org/10.24018/ejbio.2021.2.3.172
Vol 2 | Issue 3 | June 2021
81
technologies such as machine learning and artificial
intelligence, it is possible to both save time and choose the
effective protocol. Artificial intelligence technology will
make it possible to benefit from the method to be used in the
most efficient way by revealing which of these
biotechnological methods can be used in the most effective
and optimal conditions, and the possible advantages and
disadvantages as a result of comparing with others.
II. ARTIFICIAL INTELLIGENCE, MACHINE LEARNING AND
DATA SCIENCE
Although artificial intelligence, machine learning, and
data science are heavily intertwined, they are related but
different fields. The relationship between them is shown in
Fig. 2. While artificial intelligence is concerned with giving
machines the ability to imitate human behavior, particularly
cognitive functions; machine learning can be thought of as
one of the tools of artificial intelligence and provides
machines with learning ability. your manuscript
electronically for review.
Fig. 2. Schematic representation of the relationship between artificial
intelligence, machine learning, and data science.
A. Artificial Intelligence
Every algorithm has inputs and outputs. The data are
processed with the functions specified in the algorithm and a
result is presented. Artificial intelligence, on the other hand,
should have the ability to correctly interpret external data,
learn from these data and use these capabilities to fulfill
certain goals and tasks through flexible adaptation [32]. Any
artificial intelligence optimizes its functions by analyzing
inputs that provide data, maximizing its success on the
target. Since the first introduction of artificial intelligence,
various approaches have been applied to create machines
that think. These approaches include symbolic logic, logic-
based, knowledge-based, flexible computation, and
statistical learning [33].
B. Machine Learning
Machine learning can be considered as one of the tools of
artificial intelligence as shown in Fig. 2. The results of an
experienced situation provide the ability to learn. The
schematic representation of the operation between
traditional programming algorithms and machine learning is
given in Fig. 3 [34]. A program converts input signals into
output signals using pre-determined rules and relationships
in a computer script. Machine learning algorithms use both
known input and output as training data to find a model that
converts input into output.
Fig. 3. Schematic representation of the difference in functioning in artificial
intelligence and traditional programming.
C. Data Science
Data science, also known as data mining, is a field of
study that provides resources for areas such as artificial
intelligence, machine learning and statistics. For example,
data science is the work done to collect and parse the data of
a store's customers and transform it into clean data that can
be used on artificial intelligence. It is mostly used in
conjunction with machine learning in terms of the need for
large amounts of data. Data science uses learning algorithms
such as decision trees, neural networks, k-nearest neighbors,
and k-mean clustering.
III. ARTIFICIAL INTELLIGENCE APPLICATIONS
The process of collecting and analyzing data, which is an
essential part of scientific research, gained momentum after
the 20th century with the invention of the computer and the
digitalization of data. With powerful and comprehensive
package programs used for statistical analysis, data
processing has also become easier. Artificial intelligence
applications differ positively from traditional statistical
techniques in terms of contributing to the processes such as
the method to be followed or the interpretation of the
findings [35].
RESEARCH ARTICLE
European Journal of Biology and Biotechnology
www.ejbio.org
DOI: http://dx.doi.org/10.24018/ejbio.2021.2.3.172
Vol 2 | Issue 3 | June 2021
82
A. Artificial Intelligence Applications in Basic Sciences
The main point that makes artificial intelligence
successful is the learning ability that allows it to keep up
with these changes in natural sciences. In addition to
encountering artificial intelligence studies in all sciences
dealing with nature such as mathematics, engineering,
medicine, environment, biology, astronomy, physics,
chemistry, geology, meteorology, and genetics, it is seen
that its use in daily life is increasing. The most known of
these is the face recognition feature in smartphones. By
processing the image data obtained from the phone's camera
with artificial intelligence algorithms, the user of the phone
can be identified or processes such as identifying and auto-
tagging the person you have previously tagged in a photo
can be performed [36-37]. When the same technology is
trained with different data sets, it can turn into a useful tool
in that area. For example, Golgiyaz et al. [38] conducted a
study on the estimation of the flue gas temperature with
features obtained from the flame image in a coal-fired
burner and developed a model that predicted with 97%
accuracy.
TABLE I: THE REPORTS OF SOME ARTIFICIAL NEURAL NETWORKS
STUDIES INCORPORATED IN THE AGRICULTURE
Technology and System
Purpose
References
Artificial neural
networks and expert
systems
Predicting crop nutrition
levels
[39]
Expert systems
(COMAX, COtton
Management eXpert)
Increasing the production of
cotton crop
[40]
Expert systems
(COTFLEX)
Associated the farm and Crop
databases to support
significant data relation the
cotton crop to the grower so
that it becomes easy for the
farmer to take crucial
decisions.
[41]
Expert systems
(SMARTSOY -
SOYGRO)
Generating recommendation
for soybean crop is dependent
on calculation and prediction
of the cost and damage rate to
treat the plant and gain the
yield.
[42]
Expert system
(PRITHVI, based on
fuzzy logic)
The system, designed for
explicitly of Soybeans crop.
[43]
Expert systems
(POMME)
Helping the farmers for spray
in chemicals (insecticide) on
the apple to prevent the
disturb due to atmosphere and
insects.
[44]
ANN algorithms
Estimating soil moisture in
Paddy fields
[45]
ANN algorithms
Predicting of spatial water
distribution in the subsurface
[46]
Chaudhuri et al. conducted a study on the predictability of
high-intensity earthquakes with artificial intelligence for the
Indo-Himalayan border region. The researchers who applied
a neural fuzzy logic inference system, which is a mixed
model, obtained a model with a prediction accuracy of
99.4% [46].
Greenhouse gas emissions, which are known to be
effective in global temperature increase, are increasing day
by day. It is important to make accurate predictions for the
future in determining the measures to be taken to eliminate
the negative effects it creates in our environment and to
protect the environment. Pabuccu and Bayramoglu
conducted their study, CO2 emissions for Turkey's
estimation, at 2020-2025-2030 years have used artificial
neural networks. Estimates according to respectively 740.33
million tons this year (Mt), 1039.32 Mt and 1244.13 Mt
values that will be the Turkey's Paris, he has been
committed for 2030 Climate Summit 929 Mt, they could be
out on the CO2 content. It is clear that the use of renewable
energy sources is a good alternative to reduce CO2
emissions [47]. However, feasibility studies are also
important in this regard, as in every investment. In order to
find answers to questions such as from what source, where
and to what extent the power plant where the investment
will be made, studies are carried out on artificial intelligence
models. For example, the use of artificial intelligence can be
observed in determining the control parameters of a
photovoltaic power plant [48] or calculating the wind
potential of a region [49].
IV. CONCLUSION
Image processing and artificial intelligence algorithms are
also used to detect plant diseases that cause serious
economic losses to producers. Alruwaili et al. classified
some diseases in olive leaves using deep learning techniques
in their study [50]. As a result of their study, they stated that
they achieved a general accuracy rate of 99.11%. In
addition, there are commercial examples of agricultural
machines that use artificial intelligence technology today. A
Technology company can perform the imaging and spraying
process simultaneously thanks to the withdrawable type of
equipment it produces. Herbicide can be applied to weeds
detected while on the move and drug can be applied to the
cultivated plant. In this way, it avoids unnecessary practices
and exhibits a more environmentally friendly approach.
ACKNOWLEDGMENT
The study was supported by Mugla metropolitan
municipality, Department of Agricultural Services.
REFERENCES
[1] H. Zheng, W. Li, J. Jiang, Y. Liu, T. Cheng, Y. Tian, Y. Zhu, W. Cao,
Y. Zhang and X.A. Yao. “Comparative Assessment of Different
Modeling Algorithms for Estimating Leaf Nitrogen Content in Winter
Wheat Using Multispectral Images from an Unmanned Aerial
Vehicle,” Remote Sensing, vol. 10, no. 2. pp. 2026, 2018.
[2] H. Hu, A. Scheben and D. Edwards. “Advances in Integrating
Genomics and Bioinformatics in the Plant Breeding Pipeline,”
Agriculture, vol. 8, no. 6. pp. 75, 2018.
[3] S. Orozco-Arias, G. Isaza and R. Guyot. “Retrotransposons in Plant
Genomes: Structure, Identification, and Classification through
Bioinformatics and Machine Learning,” International Journal of
Molecular Science, vol. 20, pp. 3837, 2019.
[4] D. Zohary and P. Spiegel-Roy. “Beginnings of fruit growing in the
old world,” Science, vol. 187, no. 4174. pp. 319-327, 1975.
[5] G. Bartolini and R. Petruccelli. Classification, Origin, Diffusion, and
History of the Olive, Rome, Food and Agriculture Organization of the
United Nations, 2002, pp. 43.
[6] G. Besnard and A. Berville. “On Chloroplast DNA Variations in the
Olea europaea L. Complex: Comparison of RFLP and PCR
Polymorphisms,” Theoretical and Applied Genetics, vol. 104, pp.
1157-1163, 2002.
[7] G. Besnard, P. Baradat, D. Chevalier, A. Lagmount and A. Berville.
“Genetic differentiation in the olive complex (Olea europaea)
RESEARCH ARTICLE
European Journal of Biology and Biotechnology
www.ejbio.org
DOI: http://dx.doi.org/10.24018/ejbio.2021.2.3.172
Vol 2 | Issue 3 | June 2021
83
revealed by RAPDs and RFLPs in the rRNA genes,” Genetic
Resources and Crop Evolution, vol. 48, pp. 165182, 2001.
[8] E. Pacini and M. Cresi. “Viral Particles in Developing Pollen Grains
of Olea europaea L,” Plant Diseases, vol. 57, pp. 13-29, 1978.
[9] M. Marte, M.F. Cadani, V. Savino and E. Rugini. “Strawberry Latent
Ringspot Virus AssociatedWith a New Disease of Olive in Central
Italy,” Plant Disease, vol. 70, pp. 171-172, 1986.
[10] M.A. Castellano, A.D. Eranco and G.P. Martelli. “Electron
Microscopy of Two Olive Viruses in Host Tissue,” Plant Diseases,
vol. 68, no. 12. pp. 57-12, 1987.
[11] H.E. Waterworth and R.L. Monroe. “Graft Transmission of Olive
Sickle Leaf Disorder,” Plant Diseases, vol. 59, pp. 366-367, 1988.
[12] G.P. Martelli, V. Savino, B. Di Terlizzi, L. Catalano, S. Sabanadzovic
and N. Greco. “Viruses and of olive in Apulia (Southern Italia),” Acta
Hortuculture, vol. 386, pp. 569-573, 1995.
[13] E. Triolo, A. Materazzi and S. Toni. “An Isolate of Tobacco Mosaic
Tobamovirus From Olea europaea L.,” Advances in Hortucultural
Science,” vol. 10, no. 1. pp. 39-45, 1996.
[14] O. Beler and S. Acıkgoz. “Determination of some viral diseases seen
in olive nurseries and trees in Aegean and Marmara Regions by
ELISA Test,” Journal of ADU Faculty of Agriculture, vol. 2, no.1. pp.
79 84, 2005.
[15] M. Ravelonandro, N. Minoiu and R. Scorza. “Investigations of
Potential Environmental Impacts in the Release of Transgenic
Plums,” Acta Horticulturae, vol. 657, pp. 325–329, 2004.
[16] J.H. Dodds and L.W. Roberts. “Experiments in Plant Tissue Culture,”
Cambridge University Press, USA, pp.113-121. 1986.
[17] S.A. Nehra and K.K. Kartha. 1994. “Meristem and Shoot Tip Culture:
Requirements and Applications,” In: Vasil, I., Thorpe, T.A. (Eds.),
Plant Cell and Tissue Culture, Dordrecht, Netherlands: Kluwer
Academic Publishers, pp. 37-70.
[18] B. Burun. Plant Biotechnology Department 6, Disease-Free Plant
Production, Selçuk University Press, 2001. pp. 190-210.
[19] J.L. Sherwood. “Applied Aspect of Plant Regeneration,” In: Dixon,
D. A., Gonzales, R.A., (Eds.), Plant Cell Cultur, A Ptactical
Approach, pp. 135-138. 1993.
[20] S. Spiegel, A. Stein and Y. Tam. “In vitro Thermotherapy of
Rosaceous Fruit Trees,” Acta Horticulturae, vol. 386, pp. 419–420,
1995.
[21] R. Galzy. “Confirmation de la Nature Virale du Court-Noue de la
Vigne par Desessais De Thermotherapie sur des Cultures in vitro,”
Comptes Rendus des Seances de l Academie des Sciences, vol. 253,
pp. 706-708, 1961.
[22] B. Kassanis. “Heat Therapy of Virus-Infected Plants,” Annals
Applied Biology, vol. 41, pp. 470-74, 1954.
[23] B. Krizan and E. Ondursikovsa. “Thermotherapy of Apricot
Cultivars,” Acta Horticulturea, vol. 839, pp. 269-274, 2009.
[24] E. Knapp, V. Hanzer, D. Mendonça, A. da Câmara Machado, H.
Katinger and M. Laimer de Câmara Machado. “Improved virus
detection in rosaceous fruit trees,” In vitro, Plant Cell, Tissue and
Organ Culture, vol. 52, pp. 36, 1998.
[25] J.D. Postman and S.A. Mehlenbacher. “Apple mosaic virus in
hazelnut germplasm,” Acta Horticulturae, vol. 351, pp. 601-609,
1994.
[26] G.A. Manganaris, A.S. Economou, J.N. Boubourakas and N.I. Katis.
“Elimination of PPV and PNRSV Through Thermotherapy and
Meristem-Tip Culture in Nectarine,” Cell Biology and
Morphogenesis, vol. 22, pp. 195-200, 2003.
[27] G. Faccioli and A. Colombarini. “Correlation of potato virus S and
virus M contents of potato meristem tips with the percentage of virus-
free plantlets produced in vitro,” Potato Research, vol. 39, pp. 129–
140, 1996.
[28] M. Brison, M-T. Boucaud, A. Pierronnet and F. Dosba. “Effect of
cryopreservation on the sanitary state of a cv. Prunus rootstock
experimentally contaminated with Plum Pox Potyvirus,” Plant
Science, vol. 123, pp. 189196, 1997.
[29] B. Helliot, B. Panis, Y. Poumay, R. Swenen, P. Lepoivre and E.
Frison. “Cryopreservation for the elimination of cucumber mosaic
and banana streak viruses from banana (Musa spp.),” Plant Cell
Reports, vol. 20, pp. 11171122, 2002.
[30] Q.C. Wang, M. Munir, P. Li, R. Gafny, I. Sela and E. Tanne.
“Elimination of grapevine virus A (GVA) by cryopreservation of in
vitro-grown shoot tips of Vitis vinifera L.,” Plant Science, vol. 165,
pp. 321327, 2003.
[31] R. Infante and N. Fiore. “Combined effect of thermotherapy and in
vitro shoot culture on the Grapevine leafroll associated virus 2 Red
Globe strain affecting ‘Red Globe’ vines,” Journal of Food,
Agriculture & Environment, vol. 7, no. 3-4. pp. 274 277, 2009.
[32] A. Kaplan and M. Haenlein. “Siri, Siri, in my hand: Who’s the fairest
in the land? On the interpretations, illustrations, and implications of
artificial intelligence,” Business Horizons, vol. 62, no.1. pp. 15-25,
2018.
[33] R. Hoehndorf and N. Queralt-Rosinach. “Data Science and Symbolic
AI: Synergies, Challenges and Opportunities,” Data Science, vol. 1,
pp. 2738, 2017.
[34] V. Kotu and B. Deshpande. Data Science: Concepts and Practice. 2.
Edition. Elsevier, USA. 2019.
[35] E. Brent. “Designing Social Science Research with Expert Systems,”
Anthropological Quarterly, vol. 62, no. 3. pp. 121-130, 1989.
[36] S. Chaudhuri, A.R. Chowdhury and P. Das. “Implementation of
Sugeno: ANFIS for forecasting the seismic moment of large
earthquakes over Indo-Himalayan region,” Natural Hazards, vol. 90,
no. 1. pp. 391-405, 2017.
[37] M.O. Derawi. Smartphones and Biometrics. PhD Thesis, Gjøvik
University College. Norway2012.
[38] S. Golgiyaz, M.F. Talu and C. Onat. “Prediction of Flue Gas
Temperature Using Image Processing and Machine Learning,”
European Journal of Science and Technology, vol. 16, pp. 283-291,
2019.
[39] H. Song and Y. He. Crop nutrition diagnosis expert system based on
artificial neuralnetworks, Third International Conference on
Information Technology and Applications (ICITA'05), 2005. Sydney,
NSW.
[40] H. Lemmon. “Comax: an expert system for cotton crop management,”
Science, vol. 233, no. 4759. pp. 2933, 1986.
[41] N.D. Stone and T.W. Toman. “A dynamically linked expert-database
system for decision support in Texas cotton production,” Computers
and Electronics in Agriculture, vol. 4, no. 2. pp. 139148, 1989.
[42] W.D. Batchelor, R.W. McClendon, D.B. Adams and J.W. Jones.
“Evaluation of SMARTSOY: an expert simulation system for insect
pest management,” Agricultural Systems, vol. 31, no. 1. pp. 6781,
1989.
[43] C. Prakash, A.S. Rathor and G.S.M. Thakur. “Fuzzy Based
Agriculture Expert System for Soyabean,” pp. 1–13, 2013.
[44] J. Roach, R. Virkar, C. Drake and M. Weaver. “An expert system for
helping apple growers,” Computers and Electronics in Agriculture,
vol. 2, no. 2. pp. 97108, 1987.
[45] C. Arif, M. Mizoguchi, B.I. Setiawan and R. Doi. “Estimation of soil
moisture in paddy field using Artificial Neural Networks,”
International Journal of Advanced Research in Artificial Intelligence,
vol. 1. no.1. pp. 1721, 2012.
[46] S. Chaudhuri, A.R. Chowdhury and P. Das. “Implementation of
Sugeno: ANFIS for forecasting the seismic moment of large
earthquakes over Indo-Himalayan region,” Natural Hazards, vol. 90,
no. 1. pp. 391-405, 2017.
[47] H. Pabuccu and T. Bayramoglu. “CO2 Emissions Forecast with
Neural Networks: The Case of Turkey,” Gazi University Faculty of
Economics and Administrative Sciences Journal, vol. 18, no. 3. pp.
762-778, 2016.
[48] R. Belu. “Artificial intelligence techniques for solar energy and
photovoltaic applications,” Handbook of Research on Solar Energy
Systems and Technologies, pp. 376-436, 2012.
[49] I. Ozcan. “Determination of Wind Energy Potential in Isparta
Province and Design of a Wind Farm,” Master Thesis, Süleyman
Demirel University, Isparta. 2011.
[50] M. Alruwaili, S. Alanazi, S. El-Ghany and A. Shehab. “An Efficient
Deep Learning Model for Olive Diseases Detection,” International
Journal of Advanced Computer Science and Applications, vol. 10, no.
8. pp. 486-492, 2019.
Mrs. Selin Galatali
Research Assistant in Molecular Biology and
Genetics Department (Mugla Sitki Kocman
University, Tukey). Her research interests are in the
areas of plant biotechnology and plant molecular
biology. She investigates cold stress genes of in vitro
grown plant species at transcriptional levels.
Assoc. Prof. Dr. Mehmet Ali Balci
He is working with Muğla Sıtkı Koçman University,
Faculty of Science, Department of Mathematics.
Mehmet Ali holds a joint PhD degree in Applied
Mathematics from Ege University, İzmir, Turkey. He
has successfully led several research projects for data
analysis methods on social networks and
mathematical modeling. His research interests
include graph kernel designing for data analysis,
network analysis with clustering techniques, machine
RESEARCH ARTICLE
European Journal of Biology and Biotechnology
www.ejbio.org
DOI: http://dx.doi.org/10.24018/ejbio.2021.2.3.172
Vol 2 | Issue 3 | June 2021
84
learning with deep diffusive neural networks, and mathematical modeling
of social phenomena.
Assist. Prof. Dr. Omer Akguller
He is working with Muğla Sıtkı Koçman
University, Faculty of Science, Department of
Mathematics. Ömer holds M.Sc. and PhD degrees
in Geometry from Muğla Sıtkı Koçman
University. His research interests include the
geometry of correlation networks, geometric
filtration on networks, geometry processing, and
manifold learning.
Assoc. Prof. Dr. Ergun Kaya
He earned his Ph.D. in Molecular Biology and
Genetics at Gebze Technical University, Turkey,
and served as a post-doctoral fellow in Plant
Biotechnology at Colorado State University,
National Center for Genetic Resources
Preservation (USA). His primary research
interests are plant biotechnology, plant molecular
biology.
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Worldwide, plant diseases adversely influence both the quality and quantity of crop production. Thus, the early detection of such diseases proves efficient in enhancing the crop quality and reducing the production loss. However, the detection of plant diseases either via the farmers' naked eyes or their traditional tools or even within laboratories is still an error prone and time consuming process. The current paper presents a Deep Learning (DL) model with a view to developing an efficient detector of olive diseases. The proposed model is distinguishable from others in a number of novelties. It utilizes an efficient parameterized transfer learning model, a smart data augmentation with balanced number of images in every category, and it functions in more complex environments with enlarged and enhanced dataset. In contrast to the lately developed state-of-art methods, the results show that our proposed method achieves higher measurements in terms of accuracy, precision, recall, and F 1-Measure.
Article
Full-text available
This paper presents an experimental study on the flue gas temperature estimation in small-scale nut coal-fired boiler. The flue gas temperature must be within a certain range depending on the fuel type, otherwise it causes corrosion in the boiler. Within the scope of this study, features were obtained from flame image. The flue gas temperature was estimated with these features and the SVR model. The flame image was taken with a CCD camera. At the same time, the reference flue gas temperature was taken with the flue gas analyzer. The flame image and temperature are recorded on the same computer. Flame image is converted to gray scale image and features are obtained. The intensity distribution of the flame image was used when obtaining the features. Two types of distribution were used for this process. The first is the histogram of the flame image to obtain a location independent intensity distribution. The second is to obtain a spatial intensity distribution using row and column sums. The attributes obtained from the combinations of these two type features were performed with 6 kinds of SVR models. The best results were obtained for the cubic SVR model for the feature extraction method in which the attributes obtained from both distributions were used together. In the proposed model the flue temperature (T ° C) was estimated with R = 0.97 accuracy. The results show that there is a high correlation between the flue gas temperature and the flame image.
Article
Full-text available
Unmanned aerial vehicle (UAV)-based remote sensing (RS) possesses the significant advantage of being able to efficiently collect images for precision agricultural applications. Although numerous methods have been proposed to monitor crop nitrogen (N) status in recent decades, just how to utilize an appropriate modeling algorithm to estimate crop leaf N content (LNC) remains poorly understood, especially based on UAV multispectral imagery. A comparative assessment of different modeling algorithms (i.e., simple and non-parametric modeling algorithms alongside the physical model retrieval method) for winter wheat LNC estimation is presented in this study. Experiments were conducted over two consecutive years and involved different winter wheat varieties, N rates, and planting densities. A five-band multispectral camera (i.e., 490 nm, 550 nm, 671 nm, 700 nm, and 800 nm) was mounted on a UAV to acquire canopy images across five critical growth stages. The results of this study showed that the best-performing vegetation index (VI) was the modified renormalized difference VI (RDVI), which had a determination coefficient (R2) of 0.73 and a root mean square error (RMSE) of 0.38. This method was also characterized by a high processing speed (0.03 s) for model calibration and validation. Among the 13 non-parametric modeling algorithms evaluated here, the random forest (RF) approach performed best, characterized by R2 and RMSE values of 0.79 and 0.33, respectively. This method also had the advantage of full optical spectrum utilization and enabled flexible, non-linear fitting with a fast processing speed (2.3 s). Compared to the other two methods assessed here, the use of a look up table (LUT)-based radiative transfer model (RTM) remained challenging with regard to LNC estimation because of low prediction accuracy (i.e., an R2 value of 0.62 and an RMSE value of 0.46) and slow processing speed. The RF approach is a fast and accurate technique for N estimation based on UAV multispectral imagery.
Article
Full-text available
Artificial intelligence (AI)—defined as a system's ability to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation—is a topic in nearly every boardroom and at many dinner tables. Yet, despite this prominence, AI is still a surprisingly fuzzy concept and a lot of questions surrounding it are still open. In this article, we analyze how AI is different from related concepts, such as the Internet of Things and big data, and suggest that AI is not one monolithic term but instead needs to be seen in a more nuanced way. This can either be achieved by looking at AI through the lens of evolutionary stages (artificial narrow intelligence, artificial general intelligence, and artificial super intelligence) or by focusing on different types of AI systems (analytical AI, human-inspired AI, and humanized AI). Based on this classification, we show the potential and risk of AI using a series of case studies regarding universities, corporations, and governments. Finally, we present a framework that helps organizations think about the internal and external implications of AI, which we label the Three C Model of Confidence, Change, and Control.
Article
Full-text available
Abstract : SLRV was repeatedly isolated from flowers, leaves and roots of olive cv. Ascolana tenera. All infected plants exhibited leaf narrowing and twisting, shortening of internodes, and fruit deformations. SLRV and the associated disease were both transmitted to healthy Ascolana tenera scions by grafting to naturally affected trees. Infectivity to differential hosts, serological properties and sedimentation behaviour of purified viral preparations indicate that the isolate is similar to the SLRV previously obtained from symptomless olive trees. This is the first report of a viral infection on olive associated with clear-cut symptoms.
Article
Full-text available
With the global human population growing rapidly, agricultural production must increase to meet crop demand. Improving crops through breeding is a sustainable approach to increase yield and yield stability without intensifying the use of fertilisers and pesticides. Current advances in genomics and bioinformatics provide opportunities for accelerating crop improvement. The rise of third generation sequencing technologies is helping overcome challenges in plant genome assembly caused by polyploidy and frequent repetitive elements. As a result, high-quality crop reference genomes are increasingly available, benefitting downstream analyses such as variant calling and association mapping that identify breeding targets in the genome. Machine learning also helps identify genomic regions of agronomic value by facilitating functional annotation of genomes and enabling real-time high-throughput phenotyping of agronomic traits in the glasshouse and in the field. Furthermore, crop databases that integrate the growing volume of genotype and phenotype data provide a valuable resource for breeders and an opportunity for data mining approaches to uncover novel trait-associated candidate genes. As knowledge of crop genetics expands, genomic selection and genome editing hold promise for breeding diseases-resistant and stress-tolerant crops with high yields.
Article
A tobamovirus was isolated with difficulty from olive cv. Leccino in Tuscany (central Italy). The naturally field-infected olive tree displayed severe decline symptoms, while the leaves exhibited a conspicuous vein-banding. Mechanical transmission and (DAS)-ELISA detection of this virus was facilitated or obtained, respectively, after partial purification of leaf extracts. The virus shared several properties with the type-strain of tobacco mosaic virus; dissimilarities were excluded as regards host range, electrophoretic analyses and (DAS)-ELISA tests. Based on these findings we conclude that the tobamovirus isolate from olive is a strain of tobacco mosaic virus. This seems to be the first record of a tobamovirus associated to O. europaea; our results bring to 9 the total number of viruses isolated from olive in Italy.
Article
Virus infection seriously limits stone fruit production. The most important viral pathogen is Plum pox virus (PPV). However, other viruses, such as Prune dwarf virus (PDV) and Prunus necrotic ringspot virus (PNRSV) also represent major threats. In this paper, results of in vitro treatments are compared with those of in vivo thermotherapy (i.e., treatment of plants in a peat substrate) to eliminate PPV, PDV, and PNRSV from three apricot varieties, including 'Bergeron', 'Leskora', and 'Marlen'. Therapy takes 45 days under temperature 37°C (in light) and 35°C (in dark) and photoperiod 16h (light) and 8h (dark) in both cases. Following treatment, shoot tips (3 mm long) were collected from plants and cultured in vitro. Plants originating from these shoot tips were tested by RT-PCR and ELISA following transfer to non-sterile conditions for either 6 or 12 months, respectively. No differences were detected between the two methods of treatment. However, differences in numbers of dead plants during treatment and during culture of apical segments.