Received: 18 February 2022 | Revised: 2 June 2022 | Accepted: 2 July 2022 | Published online: 4 July 2022

Journal of Computational and Cognitive Engineering

RESEARCH ARTICLE 2023, Vol. 2(2) 155–162
DOI: 10.47852/bonviewJCCE2202174

Implementation of Artificial
Intelligence in Agriculture
Shivangi Sharma1, Kirti Verma2,* and Palak Hardaha1
1
Department of Computer Science and Engineering, Lakshmi Narain College of Technology and Sciences, India
2
Department of Engineering Mathematics, Lakshmi Narain College of Technology, India

Abstract: Agriculture has a significant contribution to the economy. Agricultural automation is a major cause of concern and a relatively new
phenomenon throughout the world. The world’s population is quickly growing, resulting in increased demand for food and labor. Farmers’
customary techniques were insufficient to achieve these goals. As a result, new automated techniques were developed. These creative initiatives
met food demands while also providing work opportunities for a large number of people. Agriculture has changed as a result of artificial
intelligence (AI). This strategy has shielded agricultural production from a variety of threats such as weather, population growth, labor rights, and
food security concerns. The major issue of this is the numerous applications of AI in agriculture, such as irrigation, weeding, and spraying with
different sensors or other ways implanted in robots and drones. These technologies limit the use of water, pesticides, and herbicides, preserve soil
fertility, and help in the effective use of labor, resulting in increased output and quality. Many researchers make efforts to gain a quick overview
of the present state of automation in agriculture, including weeding systems using robots and drones. Two automated weeding strategies as well
as several soil water sensing technologies are explored. The drones are employed for the numerous methods for spraying and crop monitoring. In
this paper, we also discuss how AI should be combined with other technologies and applications of AI for solving farming challenges.
Keywords: artificial intelligence, herbicide, pesticide, automation, irrigation, machine learning, anomaly detection, computer vision, natural
language processing, conversational AI

1. Introduction the quality of their product, and assure a faster time to market for
their harvested crops owing to AI-based technological solutions
Crop varieties, irrigation, soil detection, crop scouting, (Figure 1; Abdullahi et al., 2015).
weeding, and crop establishing in the agricultural industry all Vertical farming is a type of agriculture in which food is grown on
benefit from artificial intelligence (AI)-based solutions that help top of one another rather than in horizontal rows. Growing vertically
boost efficiency in all domains and handle problems faced by frees up space, leading to a higher crop yield per sq. foot of area
many organizations. Agricultural robotics are being developed in utilized. The worldwide human population is rapidly growing, with
order to give high-value AI applications in the aforementioned 9.9 billion people estimated by 2050, and food consumption is
industry. The agriculture industry is in peril as the world expected to rise by 35% to 56%. However, everyone is leaning
population expands, but AI has the potential to give a long-term toward building their own homes and owning property, as well as
solution. Farmers can create more output with less input, improve doing large-scale undertakings. Farmers have a tendency to think of
AI as something that only applies in the digital world. They may be
Figure 1 unable to see how it can assist them in working the real land. This is
Vertical farming not because they are fearful of the unknown or conservative. Their
resistance stems from a lack of awareness of how AI tools can be
applied in the real world (Ahir et al., 2020).
Because Agri Tech vendors fail to adequately explain why their
solutions are valuable and how they should be implemented, new
technologies sometimes appear complex and unduly expensive.
This is what occurs in agriculture when AI is used. Although AI
can be beneficial, technology companies must still do a lot of work
to assist farmers in properly implementing it (Ahirwar et al., 2019).
Agriculture entails a variety of processes and phases, the majority
of which are performed manually. AI can help with the most complex
and routine jobs by supplementing existing technology. When
integrated with other technology, it can gather and evaluate massive
*Corresponding author: Kirti Verma, Department of Engineering Mathematics, data on a digital platform, determine the best course of action, and
Lakshmi Narain College of Technology, India. Email: kirtivrm3@gmail.com even initiate that action (Aitkenhead et al., 2003).

© The Author(s) 2022. Published by BON VIEW PUBLISHING PTE. LTD. This is an open access article under the CC BY License (https://creativecommons.org/
licenses/by/4.0/).

155
Journal of Computational and Cognitive Engineering Vol. 2 Iss. 2 2023

2. Using Artificial Intelligence to Tackle Farming Farmers can use AI to get real-time insights into their fields,
Problems allowing them to spot areas that require irrigation, fertilizer, or
pesticide application. In addition, novel farming techniques such as
As previously said, AI cannot exist without the use of other vertical agriculture may assist improve food output while reducing
technologies such as big data, sensors, and software. Similarly, AI is resource consumption. As a result, herbicide use is reduced, harvest
required for the proper operation of other technologies. In the case of quality is improved, earnings are increased, and significant cost
huge data, for example, the data is not especially valuable. What savings are realized (Bakker et al., 2006).
matters is how it is processed and whether or not it is useful (Al-Ali
et al., 2015). 2.4. Artificial intelligence can help with workforce
When it comes to AI recommendations based on a collection of shortages
data, the time, place, and selection criteria all play a role. To make
AI technology work, it is also critical to have excellent data Agricultural work is difficult, and labor shortages are nothing new in
engineers and data analysts. Let us take a closer look at how AI is this business. With the use of automation, farmers can address this
used in agriculture (Albaji et al., 2010). problem. Farmers can save money by using driverless tractors, smart
irrigation and fertilization systems, smart spraying, vertical farming
2.1. Big data as a tool for making well-informed software, and AI-based harvesting robots. AI-driven farm tools are
decisions faster, tougher, and more accurate than any human farm worker
(Bendig et al., 2012).
The real purpose of data collection and production is to put it to
good use. Data analytics in agriculture can result in large production 2.5. Artificial intelligence can help with workforce
gains and significant cost reductions. Farmers can acquire credible shortages
recommendations based on well-sorted real-time information on
crop needs by merging AI and big data. As a result, guesswork Agricultural work is difficult, and labor shortages are nothing new
will be eliminated, allowing for more exact farming methods such in this business. With the use of automation, farmers can address this
as irrigation, fertilization, crop protection, and harvesting (Anand problem. Farmers can save money by using driverless tractors, smart
et al., 2015). irrigation and fertilization systems, smart spraying, vertical farming
software, and AI-based harvesting robots. AI-driven farm tools are
2.2. AI helps people make smarter decisions faster, tougher, and more accurate than any human farm worker
(Bhagyalaxmi et al., 2016).
Predictive analytics has the potential to be a game changer. Farmers
can collect and process substantially more data using AI than they could 3. Farming in Future
without it, and they can do so much faster. Farmers may use AI to handle
critical difficulties including analyzing market demand, projecting Another option comes from AI technology. Due to AI, the
pricing, and deciding the best time to sow and harvest (Anthony agriculture industry is undergoing a new era of transition, that is, for
et al., 2014). everything from employing from yield and soil monitoring to
However, AI can also acquire information about soil health, make disease diagnosis and data modeling, computer vision technology
fertilizer suggestions, check the weather, and track the readiness of has a wide range of applications (Bhaskaranand & Gibson, 2011).
product. All of this helps farmers make better judgments at every Agriculture is one of the the world’s oldest professions. As the
stage of the crop-growing process (Arvind et al., 2017). world’s population rises, so does the demand to cultivate and
produce more, better crops of the highest quality. AI and deep
2.3. Artificial intelligence reduces costs learning are examples of new technology. People in rural areas will
be able to access the same tools as city dwellers to tackle agricultural
Precision agriculture, a type of farm management, can help challenges such as low productivity, language barriers, and water
farmers grow more crops with fewer resources. Precision agriculture scarcity. Because of Alexa and Siri, a voice-style smart assistant
aided by AI could be the next big thing in agriculture. Precision programmer, people who do not understand or speak English will be
farming combines the greatest soil management practices, able to communicate with them. AI, machine learning, internet-of-
variable rate technologies, and data management strategies to assist things, cloud, and blockchain are buzzwords these days. We will
farmers increase yields while reducing costs (Figure 2; Bak et al., 2003). experience an innovative shift after the web, sometimes referred to as

Figure 2
Future scope in artificial intelligence

156
Journal of Computational and Cognitive Engineering Vol. 2 Iss. 2 2023

the“FourthIndustrialRevolution,”asaresultofthemethodandacceptance To improve horticultural precision and efficiency, farmers

of these improvements. Blockchain and AI are the true capabilities of such employ AI to construct irregular forecasting models. These
new technologies. The information recorded in blockchain databases is models can forecast future climate patterns over a lengthy period
scrambled. AI and blockchain have a lot to offer in the commercial of time, helping small farmers to make more informed decisions.
realm. Many businesses are attempting to determine what these are and Because knowledge is sparse in nonindustrialized nations, small
how to implement them (Birrell et al., 1996). In this context, creating a farms need to anticipate events on a regular basis. Because small
blockchain AI business necessitates expertise and rigorous research. farmers provide 70% of the world’s harvests, it is vital to
Blockchains are excellent for storing personal data if properly prepared, maintain these smaller homesteads running and developing tiny
and they may unlock a wealth of value and ease in our lives. Intelligent yields (Bond & Grundy, 2001).
medical solutions frameworks that make appropriate judgments based
on our clinical studies and data, or Amazon and Netflix’s proposal Agriculture drone applications are as follows:
engines that suggest what we might like to purchase or watch right now
should be considered. Difficulties in farming are as follows: • Planting seeds.
• Analysis of the soil and the field.
1. Water accessibility. • Spot spraying and harvest spraying.
2. The time it takes for a rainstorm to pass. • Mapping and surveying of harvests.
3. Natural compost is readily available. • Monitoring and management of the water system.
4. Availability of transportation to transfer the produce/reap. • Ongoing livestock surveillance.
5. Production capacity is easily accessible.
The most promising new AI technologies for revolutionizing
6. Market value variety and popular produce decrease.
agriculture are as follows:
Supply chain, smart farming, autonomous transportation, and smart retail 1. Crop and soil monitoring.
are all areas where AI can be used in the agriculture industry. By 2. Observing crop maturity.
recognizing weather conditions, temperature, water consumption, and 3. Detection of insect and plant diseases.
soil, AI assists farmers in making better decisions about how to 4. Intelligent spraying.
produce and yield fruitful crops. In precision horticulture, AI 5. Automatic weeding.
frameworks are employed to improve harvest quality and precision.
Accuracy agriculture uses AI to help identify plant ailments, 4. How Artificial Intelligence (AI) Can Help
irritations, and helpless plant nutrition on ranches. Weeds may be
Agriculture
detected and targeted using simulated intelligence sensors, which can
then be used to identify which herbicides to administer in the Agriculture entails a variety of processes and phases, the
appropriate buffer zone. Pesticides and other potentially harmful majority of which are performed manually. AI can help with the
substances are kept out of our food by prohibiting their misuse most complex and routine jobs by supplementing existing
(Figure 3; Blasco et al., 2002). technology. When integrated with other technology, it can gather
and evaluate massive data on a digital platform, determine the
Figure 3 best course of action, and even initiate that action (Figure 4;
Image of drones’ Buchanan, 1989).
The following processes could benefit from combining AI with
agriculture:
AI can simplify crop selection by analyzing market demand and
assisting farmers in identifying the most profitable product.

Risk management
Forecasting and predictive analytics can help farmers
reduce errors in business processes and lower the chance of crop
failure.

Figure 4
The function of artificial intelligence (AI) in the agricultural information management cycle

157
Journal of Computational and Cognitive Engineering Vol. 2 Iss. 2 2023

Seed breeding Rather than collecting aerial image data and training computer
AI can assist develop crops that are less prone to disease and and sense of direction models to use it for insightful crop and soil
better adaptable to environmental conditions by gathering data on monitoring, we can now employ drone technology (UAVs) to capture
plant growth. aerial picture data and train computer and sense of direction models to
use it (Figures 5 and 6). An Unmanned Aerial Vehicle (UAV)
Monitoring soil health This data can be analyzed and interpreted by visual sensing
AI systems that monitor soil health can conduct chemical soil AI to:
analysis and provide precise estimations of missing nutrients.
• Keep tabs on crop health.
Protecting crops • Predict yields with accuracy.
AI can monitor the health of plants in order to detect and even • Identify crop deficiency far more quickly than humans.
predict diseases, identify and eradicate weeds, and offer appropriate
pest control. AI technologies can alert farmers to particular problem
regions, allowing them to take rapid action (Chang &
Crops that are fed Lin, 2018).
AI can help in determining the best irrigation patterns and
fertilizer application times, as well as predicting the best 6. Observing Crop Maturity
agronomic product mix.
Researchers can learn more about crop maturity by collecting
alternate years and doing timely experiments on them. They will
Harvesting
learn about the crop ripeness from time to time, but this information
It is possible to automate harvesting and even predict the ideal
may not be correct. It is like putting on a show for wheat (Figure 7).
time for it using AI.
This vision-based idea was discovered to surpass human
objective observation in properly recognizing crop (wheat) growth
5. Crop and Soil Monitoring stages, eliminating the requirement for farmers to visit the fields on
a regular basis to monitor their crop (Figure 8; Choudhary et al., 2019).
Crop vitality, production amount, and quality are all affected by Farmers used to check the ripeness of tomatoes by visiting the field
soil micronutrient and macronutrients. Human’s sight and judgment everyday and checking them with their hands to see how they were
were used to measure the quality of the soil and crop health. developing, but today they must and-check the maturity of fresh

Figure 5
Farming by water sprinkling method in a large land drip irrigation system

Figure 6
Visual sensing AI

158
Journal of Computational and Cognitive Engineering Vol. 2 Iss. 2 2023

Figure 7 builds systems that can “keep an eye” on plant condition by

Ripening of tomatoes utilizing categorization, detection, and picture segmentation
methodologies (Artificial Neural Network Based Segmentation)
(Cillis et al., 2018).
As shown in Figures 10 and 11, the insecticides can be
verified using AI method in farm to protect plants from harmful
insects.
The investigators utilized a sticky pit to capture six different
organisms of flying insects and take a picture of them in real-
time basis. They utilized YOLO object recognition for detection
and coarse counting and support vector machines (SVMs)
having worldwide features for the data and fine counting. After
that, their computer vision model correctly detected and counted
bees, flies, mosquitoes, moths, chafers, and fruit flies with
92.5% and 90.18% accuracy, respectively. Cattle Eye is a great
Figure 8 example of a farming company that prioritizes AI. Cow health
Stages of growth of wheats and activity are monitored using overhead cameras and computer
vision algorithms. This implies that a cattle farmer does not have
to be right next to the cow always to notice a problem (Costa
et al., 2012).
Alternatively, the cattle may be remotely viewed and tracked in
real time, alerting farmers as soon as an issue emerges. This can be
used to:

• Count animals, detect sickness, spot aberrant behavior, and keep

track of major events like births.
• Gather information from cameras and drones (UAVs).
• Combine with other technology to keep farmers up to date on
animal health, food and water availability, and so on.

Figure 9 8. Intelligent Spraying

Stages of ripening of tomatoes in a farm
Pesticides and fertilizer can be sprayed equally throughout a
field using UAVs equipped with computer vision AI. The
computer vision system’s accuracy allows it to spray with such
precision that collateral damage to crops or the environment is
avoided. Farmers found it easier since when they used to spray by
hand, and they sprayed differently or more or less in regions that
were harmful to them. We should not always use chemicals;
instead, we should utilize manure and cow dung, as well as
kitchen trash. Chemicals are extremely harmful to humans, so we
must consider them (Figure 12; De Oca et al., 2018).

9. Automatic Weeding
Physical weed removal not only saves the farmer time and effort,
but it also decreases the need for chemicals, making the entire
tomatoes on an industrialized level. Computers, on the other hand, have agricultural process more ecologically friendly and sustainable
made life easier in every way. Machines, for example, can check for (Figure 13; Dela Cruz et al., 2017).
waste and ripeness in factories; in the field, various AI technologies A group of scientists is striving to make this a reality by
allow farmers to assess the freshness of tomatoes without touching designing agricultural robots capable of detecting weeds and soil
them (Figure 9; Chung et al., 2016). moisture levels.

7. Hitting the Ground with Computer Vision 10. Farmers as AI Engineers: The Future of AI in
Agriculture
Farmers must collect soil samples and transport them to a
research facility for time-consuming and energy-intensive analysis. Agriculture has employed technology throughout history to
Instead, the researchers decided to investigate if picture-relevant enhance efficiency and lessen the amount of hardwork human
data from a ridiculously low easily portable scanning electron labor required in farming. People and agriculture have developed
microscope could be used to create training model to perform since the beginning of agriculture, from improved ploughs
the same thing. For monitoring insect and plant diseases, through irrigation, tractors to present AI. Another big step forward
deep learning-based image identification technology can be in this field is the expanded and more inexpensive availability of
used to identify plant pathogens and pests. This technique computer vision (Figure 14).

159
Journal of Computational and Cognitive Engineering Vol. 2 Iss. 2 2023

Figure 10
Insecticides using AI method in farm

Figure 11
Insecticides using AI method in farm

Figure 12
Researches in farm testing of insects

Figure 13
With the help of AI and drone checking for the weeds at an exact place

160
Journal of Computational and Cognitive Engineering Vol. 2 Iss. 2 2023

Figure 14
Anup Patil, a 28-year-old engineer, who quit his IT job to do farming in a village

AI has the potential to revolutionize agriculture in the twenty- analyze resource and job limitations in agriculture. Traditional
first century, given substantial changes in our climate, environment, methods required a large amount of work to get agricultural data
and global food needs by: such as plant height, soil texture, and content, which demanded
time-consuming physical testing. Quick and non-damaging high-
Improving time, labor, and resource efficiency. throughput phenol typing would be possible with the help of the
different technologies investigated, with the added benefit of
• Improving the long-term viability of the environment. flexible and favorable activity, on-demand access to information,
• Improving resource allocation’s “smartness.” and spatial goals (Doherty & Rudol, 2007).
• Providing real-time monitoring to improve the quality and health
of crops.
Conflicts of Interest
As a result, changes in the agriculture business will be necessary.
Farmers’ “field” expertise will need to be converted into AI training, The authors declare that they have no conflicts of interest to this
which will need more technological improvements. Education costs work.
a lot in the agriculture industry. Agriculture, on the other hand, is no
stranger to innovation and adaptability. Computer vision and Informed Consent
agricultural robotics are two recent examples of how farmers may
use new technology to fulfill rising global food demand and Informed consent was obtained from all individual participants
improve food security. AI’s future hope is our next generation, included in the study.
which has the power to build chemical-free agriculture. Society’s
thinking need to change as sending their children into technological References
and medical professions has promise, but we also needed to consider
agriculture. Many engineers choose the agricultural business after Abdullahi, H. S., Mahieddine, F., & Sheriff, R. E. (2015).
graduation, and with the help of AI, they are revolutionizing the Technology impact on agricultural productivity: A review of
future of agriculture, making it easier and more ecologically friendly precision agriculture using unmanned aerial vehicles. In
while still earning revenue. Wireless and Satellite Systems: 7th International
Conference, 2015, 388–400.
11. Conclusion Ahir, K., Govani, K., Gajera, R., & Shah, M. (2020). Application on
virtual reality for enhanced education learning, military
In the agricultural business, issues include a lack of suitable training and sports. Augmented Human Research, 5, 7.
irrigation systems, weeds, crop height-related difficulties with https://doi.org/10.1007/s41133-019-0025-2
plant care, and harsh weather conditions. However, with the Ahirwar, S., Swarnkar, R., Bhukya, S., & Namwade, G. (2019).
assistance of technology, performance may be enhanced, and so Application of drone in agriculture. International Journal of
these concerns can be remedied. It might be enhanced with the Current Microbiology and Applied Sciences, 8, 2500–2505.
use of AI-driven technology such as remote sensors for https://doi.org/10.20546/ijcmas.2019.801.264
measuring soil moisture content and GPS-assisted automatic Aitkenhead, M. J., McDonald, A. J. S., Dawson, J. J., Couper, G.,
watering. Farmers were concerned about whether precision Smart, R. P., Billett, M., Hope, D., & Palmer, S. (2003).
weeding techniques could compensate for the significant amount A novel method for training neural networks for
of crops lost during the weeding procedure. Not only can these time-series prediction in environmental systems. Ecological
self-driving robots increase productivity, but they also reduce the Modelling, 162, 87–95. https://doi.org/10.1016/S0304-
usage of unnecessary pesticides and herbicides. Aside from that, 3800(02)00401-5
farmers may effectively employ drones to spray pesticides and Al-Ali, A. R., Qasaimeh, M., Al-Mardini, M., Radder, S., &
herbicides on their fields, and plant monitoring is no longer a Zualkernan, I. A. (2015). ZigBee-based irrigation system for
concern. Human brain power, for example, might be utilized to home gardens. In 2015 International Conference on

161
Journal of Computational and Cognitive Engineering Vol. 2 Iss. 2 2023

Communications, Signal Processing, and Their Applications, Engineering 83(2), 149–157. https://doi.org/10.1006/bioe.
2015, 1–4. https://doi.org/10.1109/iccspa.2015.7081305 2002.0109
Albaji, M., Shahnazari, A., Behzad, M., Naseri, A., Boroomand Nasab, Bond, W., & Grundy, A. C. (2001). Non-chemical weed management
S., & Golabi, M., (2010). Comparison of different irrigation in organic farming systems. Weed Research 41(5), 383–405.
methods based on the parametric evaluation approach in https://doi.org/10.1046/j.1365-3180.2001.00246.x
Dosalegh plain: Iran. Agricultural Water Management, 97(7), Buchanan, R. A. (1989). Bush regeneration: Recovering Australian
1093–1098. https://doi.org/10.1016/j.agwat.2010.02.015 landscapes. The Open Training and Education Network,
Anand, K., Jayakumar, C., Muthu, M., & Amirneni, S. (2015). 242–246.
Automatic drip irrigation system using fuzzy logic and Chang, C. L., & Lin, K.-M. (2018). Smart agricultural machine
mobile technology. In 2015 IEEE Technological Innovation with a computer vision-based weeding and variable-rate
in ICT for Agriculture and Rural Development (TIAR), irrigation scheme. Robotics, 7(3), 38. https://doi.org/10.3390/
2015, 54–58. https://doi.org/10.1109/tiar.2015.7358531 robotics7030038
Anthony, D., Elbaum, S., Lorenz, A., & Detweiler, C. (2014). On Choudhary, S., Gaurav, V., Singh, A., & Agarwal, S. (2019).
crop height estimation with UAVs. In 2014 IEEE/RSJ Autonomous crop irrigation system using artificial
International Conference on Intelligent Robots and intelligence. International Journal of Engineering and
Systems, 2014, 4805–4812. https://doi.org/10.1109/iros. Advanced Technology, 8(5), 46–51. https://www.ijeat.org/
2014.6943245 wp-content/uploads/papers/v8i5S/E10100585S19.pdf
Arvind, G., Athira, V. G., Haripriya, H., Rani, R. A., & Aravind, S. (2017, Chung, S., Choi, M., Lee, K., Kim, Y., Hong, S., & Li, M. (2016).
April). Automated irrigation with advanced seed germination and Sensing technologies for grain crop yield monitoring systems:
pest control. In 2017 IEEE Technological Innovations in ICT for A review. Journal of Biosystems Engineering, 41(4), 408–417.
Agriculture and Rural Development (TIAR), 2017, 64–67. https:// https://doi.org/10.5307/JBE.2016.41.4.408
doi.org/10.1109/tiar.2017.8273687 Cillis, D., Pezzuolo, A., Marinello, F., & Sartori, L. (2018). Field-scale
Bak, T., & Jakobsen, H. (2004). Agricultural robotic platform with four electrical resistivity profiling mapping for delineating soil
wheel steering for weed detection. Biosystems Engineering, condition in a nitrate vulnerable zone. Applied Soil Ecology, 123,
87(2), 125–136. https://doi.org/10.1016/j.biosystemseng.2003. 780–786. https://doi.org/10.1016/j.apsoil.2017.06.025
10.009 Costa, F. G., Ueyama, J., Braun, T., Pessin, G., Osorio, F. S., &
Bakker, T., van Asselt, K., Bontsema, J., Müller, J., & van Straten, G. Vargas, P. A. (2012). The use of unmanned aerial vehicles
(2006). An autonomous weeding robot for organic farming. In and wireless sensor network in agricultural applications. In
Field and Service Robotics: Results of the 5th International 2012 IEEE International Geoscience and Remote Sensing
Conference, 2006, 579–590. Symposium, 2012, 5045–5048. https://doi.org/10.1109/igarss.
Bendig, J., Bolten, A., & Bareth, G. (2012). Introducing a low-cost 2012.6352477
mini-UAV for thermal-and multispectral-imaging. International De Oca, A. M., Arreola, L., Flores, A., Sanchez, J., & Flores, G. (2018).
Archives of the Photogrammetry, Remote Sensing and Spatial Low-cost multispectral imaging system for crop monitoring. In
Information Sciences, 39, 345–349. 2018 International Conference on Unmanned Aircraft Systems,
Bhagyalaxmi, K., Jagtap, K. K., Nikam, N. S., Nikam, K. K., & 2018, 443–451. https://doi.org/10.1109/icuas.2018.8453426.
Sutar, S. S. (2016). Agricultural robot: irrigation system, Dela Cruz, J. R., Baldovino, R. G., Bandala, A. A., & Dadios, E. P.
weeding, monitoring of field, disease detection. International (2017). Water usage optimization of smart farm automated
Journal of Innovative Research in Computer and irrigation system using artificial neural network. In 2017 5th
Communication Engineering, 4(3), 4403–4409. https://doi.org/ International Conference on Information and Communication
10.15680/IJIRCCE.2016.0403235 Technology, 2017, 1–5. https://doi.org/10.1109/icoict.2017.
Bhaskaranand, M., & Gibson, J. D. (2011, November). Low-complexity 8074668
video encoding for UAV reconnaissance and surveillance. In 2011 Doherty, P., & Rudol, P. (2007). A UAV search and rescue scenario with
Military Communications Conference, 2021, 1633–1638. human body detection and geolocalization. In AI 2007 20th
Birrell, S. J., Sudduth, K. A., & Borgelt, S. C. (1996). Comparison of Australian Joint Conference on Artificial Intelligence, 2007,
sensors and techniques for crop yield mapping. Computers and 1–13. https://doi.org/10.1007/978-3-540-76928-6_1
Electronics in Agriculture, 14(2-3), 215–233. https://doi.org/
10.1016/0168-1699(95)00049-6 How to Cite: Sharma, S., Verma, K., & Hardaha, P. (2023). Implementation of
Blasco, J., Aleixos, N., Roger, J. M., Rabatel, G., & Molto, E. (2002). Artificial Intelligence in Agriculture. Journal of Computational and Cognitive
Engineering 2(2), 155–162, https://doi.org/10.47852/bonviewJCCE2202174
Robotic weed control using machine vision. Biosystems

162