Introducing AILA: A farmer's aide, your artificial flying botanist
An Asian country, the Philippines, is mainly agricultural, with agricultural lands accounting for roughly one-third of its total land area, particularly about 30 million hectares (ha). In the last 15 years, agriculture has contributed approximately 20% to the country’s gross domestic product (GDP), 24% to total export earnings, and 46% to full employment [Bureau of Agricultural Statistics, 2003]. In 2003, agriculture accounted for 19.6% of the GDP, while in 2004, the country’s population was estimated to be around 85 million, with about 32.15 million (39%) relying on agriculture and agriculture-related industries [National Statistics Office, 2000; Population Resources Bureau, 2004]. Agriculture employs approximately 21.7 million (67.3%) of the 31.3 million poor Filipinos (Sana, 2004). Because of the high population growth rate (about 2.3 percent per year), it is estimated that by 2025, 5.24 million hectares of frontier lands will be converted to meet the population’s needs [NSO, 2000; Environmental Management Bureau, Department of Environment and Natural Resources, 2004]. Rice and corn, in particular, continue to be the most critical contributors to agriculture’s gross value added and have become significant sources of growth. However, the primary export earners are bananas, pineapples, coconuts, sugar, and mangoes (BAS, 2004).
In the Philippines, increased agricultural production has always been a top priority for environmental protection. The improper use of modern farm techniques, deforestation, conversion of prime agricultural lands, cultivation of marginal upland areas, and depletion of fishery resources have contributed to increased environmental concern for the agricultural resource base since the 1990s. The country’s poultry and livestock industries have been impacted by changing food demands. Demand for meat and meat products rises as people’s incomes rise, and poultry and livestock farming expands. Protein sources, such as meat, milk, eggs, manure, draft power for land preparation and transportation of farm inputs and products, and an income-savings scheme for small farmers are provided by livestock and poultry. Aside from this, poultry and swine farm wastes can contaminate water systems, posing a health risk.
However, alongside increased poultry and livestock production, there are accompanying environmental issues that must be addressed. Increasing livestock production, such as cattle, carabao, swine, goats, and horses may contribute to the conversion of forest lands to grazing lands, worsening soil degradation. As a result, the Philippines is revitalizing two of its main sectors: the agricultural and fishery sectors, in response to the constant pressures of a high population growth rate and intense competition in the global market. Two million hectares of agribusiness land are to be developed as a source of livelihood and generate additional employment under the Philippine Medium Term Development Plan for 2004-2010 (NEDA, 2004). However, as the country accelerates its efforts to cope with globalization initiatives and ensure food security for its citizens, it will inevitably face environmental impacts that threaten agricultural production bases. Therefore, the Philippine agricultural sector’s primary concerns are:
1. Increased production to meet the growing population’s food needs (or food security),
2. Job creation to meet the government’s 10-point plan, and
3. Improved global competitiveness.
However, the country must also deal with threats to its cropland and fishery resources as it works toward these objectives. One of the threats that will be aimed to be solved by our project is detecting plant diseases through the aid of a modernized technology – robots.
Plant diseases caused by infectious pathogens have significantly impacted human society and nature throughout history, causing damage to food production, economic development, ecological resilience, and natural landscapes. Several people have already perished due to the Irish famine, which was due to the pathogen Phytophthora infestans, and the Bengali famine caused by the rice brown spot pathogen Bipolaris oryzae, commonly known as Breda de Haan or Shoemaker. On the other hand, the chestnut blight is caused by Cryphonectria parasitica or Murrill Barr, and Ophiostoma novo-ulmi causes Dutch elm disease. Pandemics of plant diseases wiped out a large portion of primary and secondary forestry in North America and Europe, resulting in ecological disaster. In addition, many plant pathogens produce mycotoxins, which can harm humans and animals directly or indirectly. Plant diseases can affect the entire crop production chain. They continue to be one of the greatest threats to society’s long-term development, resulting in annual yield losses of 13–22%, or billions of dollars in economic costs in staples such as rice, wheat, maize, and potato, as well as additional fees for education and the development of management strategies. These biological and economic losses account for at least a portion of the world’s estimated 800 million people suffering from hunger or malnutrition. Moreover, plant diseases result from intricate interactions between plants, pathogens, and the environment. Humans have developed a variety of approaches to manipulate the interaction to create a system that favors host plant growth and development but is suboptimal for pathogen establishment, reproduction, and transmission. These control approaches can be agronomic (e.g., crop diversification and field hygiene), regulative (e.g., quarantine and eradication), genetic (e.g., disease resistance and tolerance), physical (e.g., soil solarization and flooding), and chemical (e.g., pesticides and host-immunity inducer) and can be used individually or in combination, depending on the crop, pathogen, geographic location, technology availability, regulation policy, and other factors. The Philippine agricultural sector, in general, has embraced the tenets of modern or conventional farming practices to meet the urgent needs of a growing population while addressing the problems spawned by increasing poverty, fiscal deficits, and globalization realities. Diagnostics of plant diseases and nutrient deficiencies, irrigation management, and pesticide and fertilizer use management must all be part of crop management from the early stage through the mature harvest stage. Plant disease infection is one of agriculture’s most serious problems. As a result, quality and quantity of agricultural products suffer. Therefore, one of the modern agricultural practices is the integration of Artificial Intelligence to create a modern and friendly plant disease detection robot. This robot will serve as a solution in combatting plant diseases, specifically in the Philippines. It will also aid the farmers in determining the correct condition of their plants, which would allow them to yield more plants per year and increase their productivity and sales. Thus, this robot will comprise modern technological tools, such as cameras, sensors, and digital screens, as their main features. Specifically, two cameras will be integrated into the robot, one for sensor-detector of the disease and the other for data information presentation.
The population is rapidly growing, and with it comes increased demand for food and employment. Agriculture has undergone a revolution as a result of AI. This technology has protected crop yields from various factors such as climate change, population growth, labor issues, and food security concerns. Agriculture uses artificial intelligence for irrigation, weeding, and spraying with the help of sensors and other devices embedded in robots and drones. AI in agriculture not only assists farmers in automating their farming operations but also shifts to careful cultivation for higher crop yield and quality while using fewer resources. In agriculture, AI aids farmers in increasing efficiency, reducing harmful environmental impacts, and controlling and managing any unwelcome natural condition. Most agriculture start-ups are adopting AI-enabled approaches to improve agricultural production efficiency. Approaches based on artificial intelligence could detect diseases or climate changes sooner and respond more intelligently. Using AI in agriculture, farmers can better understand data insights such as temperature, precipitation, wind speed, and solar radiation. Data analysis of historical values allows for a more accurate comparison of desired outcomes. The best part about implementing AI in agriculture is that it won’t take away human farmers’ jobs; instead, it will improve their processes. Agro-based businesses have benefited from AI technology, which has helped them run more efficiently. Weather forecasting and disease or pest identification can both benefit from applications such as automated machine adjustments. AI is the optimal solution for improving crop management practices and solving problems that farmers face, such as climate change, pest infestations, and weed infestations that reduce yields. However, even though the number of remote sensing technologies is growing, there are still significant problems with their availability and visibility on the ground when crops are in essential growth stages. Therefore, there is a need to produce innovations that would mitigate farm issues regarding agriculture.
FIELD OF ARTIFICIAL INTELLIGENCE IN AGRICULTURAL SECTOR
Artificial Intelligence is a burgeoning revolution in agriculture. Crop production has increased, as has the quality of real-time monitoring, harvesting, processing, and marketing.
1. Development based on the Internet of Things (IoT)
The Internet of Things (IoT) is a platform that will impact a wide range of sectors and industries, including health, manufacturing, communications, energy, and agriculture. In agriculture, IoT is used to provide farmers with decision-making tools and automation technologies that seamlessly integrate products, knowledge, and services for improved efficiency, quality, and profit.
2. Insight generation based on images
Drone-based images can aid crop monitoring, field scanning, and other tasks. Farmers can combine them with PC vision technology and the Internet of Things (IoT) to ensure that activities are completed quickly. Farmers may experience ongoing climate alarms as a result of these feeds.
3. The detection of disease
The leaf images of the plant are segmented into surface areas such as background, diseased spot, and non-diseased area of the leaf using image sensing and analysis. After that, the infected or diseased area is harvested and sent to a laboratory for further analysis.
4. System of Experts
Expert systems are needed for the transfer of technical information in agriculture. It can be determined by identifying problems in the traditional technology transfer system and demonstrating that professional systems can assist in overcoming those problems and are likely to improve.
5. Field Management
During the cultivation period, real-time estimations can be achieved by building a map and identifying areas where the crops require necessary resources, such as water, fertilizer, and pesticides, using high-detail images from drone and copter systems.
The agriculture robot supports the farmer in increasing the crop’s efficiency and reduces the need for manual labor. In the upcoming generations, we can expect that these agricultural robots will do the tilling, sowing, harvesting and many other farms work individually. Indeed, these agricultural robots will deal with even the weeding and control of pests and diseases.
7. Automation techniques in irrigation and enabling farmers
AI accomplished machines alert of historical climate outline, soil quality, and crops to be grown can automate irrigation and enhance the whole yield. Nearly 70% of the world’s freshwater resource is utilized for irrigation; such automation can benefit farmers in managing their water problems.
8. Crop health monitoring
Remote sensing (RS) techniques, hyperspectral imaging, and 3D laser scanning are crucial to constructing crop metrics over thousands of acres of cultivable land.
APPLICATION OF AI TECHNIQUES IN AGRICULTURAL SECTOR
1. Image Processing
Image processing is a method used to measure the affected area of disease and find differences in the color of the affected area. The detection of infection by using image processing is essential. A robot in agriculture can detect the leaf disease-using image processing.
2. Machine Learning
Machine learning AI Applications have been successfully made in the present world to diagnose diseases. Machine learning algorithms are fast and accurate in detecting any diseases. AI in agriculture increases the recognition rate and the accuracy of the results by using machine learning and deep learning algorithm and detect plant diseases.
3. Deep Learning
A plant disease identification model based on deep learning can overcome the complexity of the environment and improve identification accuracy.
4. Expert System
Expert Systems in agriculture would take the form of Integrated crop management and decision aids and would encompass irrigation, nutritional disorders and fertilization, weed control, cultivation, and herbicidal.
AI TECHNIQUES USED FOR DETECTION OF DISEASES IN AGRICULTURE
A. Image Processing
Figure 1. Basic Flowchart of Disease Detection and Classification
(a) Image Acquisition
Images of the infected leaves are obtained. This database has different plant diseases, and the photos are stored in JPEG format.
(b) Image Pre-processing
Image pre-processing is used to erase noise from the image or other object exclusion, different pre-processing techniques. Image scaling is used to convert an original image into thumbnails because the pixel size of the original image is significant, and it requires more time for the overall procedure; hence after converting the image into thumbnails, the pixel size will get the decrease, and it will require less time.
(c) Image segmentation
Image segmentation is one of the widely used methods to distinguish pixels of an image well in a targeted app. It distributes an image into numerous discrete states such that the pixels have remarkable similarity in each area and high dissimilarity between areas.
(d) Feature Extraction
Feature Extraction is an essential part of disease detection, and it plays a critical role in identifying an object. Feature extraction is utilized in several applications in image processing. Colour, texture edges, and morphology are the features that are used in disease detection.
(e) Detection and classification of plant diseases
The final stages are detecting the disorders and with the help of detections, we can classify the plants with the disease matched with the given dataset.
Since a bit of background about Artificial Intelligence was already discussed in the previous sections, we now move on to the project proposal that we will be conducting. The students of BSCS 1 and BSIT 1 from the University of San Agustin Iloilo developed a modern robot named AILA. This flying plant robot diagnoses the status of plants using its two cameras. AILA is a current operating system designed to assist farmers in their daily tasks. The robot is accompanied by a controller having an interactive design to be convenient for the farmers to use. The farmers can obtain information and view the data about their farms. AILA has been developed for inspecting the presence of pests and diseases in a plant using a LiDAR and Thermal Imaging Sensor, designed in such a way that it can use images of plant leaves and effectively detect the conditions of the crops, so the robot is used to assess diseases of a plant for which the two cameras are placed on the robot itself. It provides a portable and dependable platform for automatically surveying farmland, detecting plant diseases, and providing appropriate treatments.
AILA can fly over fields of crops and operate diagnostics into the rows of plants in the areas. It is made up of various hardware and modules for its systematic functioning. Like most drones, AILA’s exterior body is created with carbon fiber composites, a material often used for manufactured products such as golf clubs, hockey sticks, and tennis rackets. Carbon fiber composites are now used in practically all UAV structures. This is in contrast to piloted flight, where aluminum and titanium, and carbon fiber composites make up a substantial portion of the structure. All aircraft systems must be as light as possible. The more lightweight the design, the more economical it is to function, the more extensive the range it can cover, and the longer it can stay aloft. UAVs require sensors, cameras, and electronics because they fly unmanned. Reduced construction weight helps it carry more sensors, payload, and stay in the air for longer. When AILA is operational, it roughly maintains one meter above your crops, and it can hover closer if necessary (e.g., when scanning your plants and making an assessment). When AILA is finished scanning its surroundings, it is smart enough to stay a safe distance away from your plants so it won’t accidentally damage them as it flies by. Its AI can learn to avoid these accidents and save you the trouble of taking care of a torn stem and a broken drone. It knows what area it has already been to by marking it on its three-dimensional map. Scanned areas will appear green and unexplored ones will appear red. The map is visible on your phone while using the AILA app. specifically, its features include:
· Camera – smartphones alike, the camera does not only serve one purpose but multiple. The camera will be working together with the LiDAR sensor. The camera will be equipped with a high-class imaging sensor to measure accurate data. AILA has a front-facing camera to capture high-resolution images to measure accurate data. Assisting the camera in capturing correct data is the LiDar and Thermal Imaging Sensor. The LiDar is a laser-based technology that measures ranges by using the light that it pulses. It can capture three-dimensional information about its surroundings. Next to the camera are a pair of thermal imaging sensors. These cameras’ imaging sensors respond to wavelengths in the infrared area of the electromagnetic spectrum. Because the infrared spectrum is not visible to the naked eye, thermal infrared imaging is also known as “non-visible” imaging.
· Humidity and temperature sensor – built as small and as accurate as possible. This sensor will indicate the temperature and humidity of the dynamic surroundings.
· Narrow screen – it will serve as the front indicator of the drone with additional “on/off” floating pixeled text. With the help of AILA’s sensors, it can create a three-dimensional map of its surroundings in conjunction with its camera. It can scan up to 25 square meters every 10 seconds, just enough time to recreate the area and store the information in its database. One of AILA’s sensors is a humidity sensor, detecting if your plant needs some watering and informing you about it.
· Drone Controller – Will have specific indications and control only over the drone.
· Leaf design power button – cellphones alike, this power button is designed to be sealed from the elements. The controller will require the user to press gently. It will glow and send a notification on the smartphone that the drone is ready.
· Battery Indicator – the drone will have an entire charged lifespan of 50 minutes. Dots have been programmed to dim and start after a 10 minutes mark. Blinking light will show in the last 5 minutes of operation, and the drone will begin to drop altitude and stop operating once it reaches the ground.
· LiDAR and Thermal Imaging Sensor: – LiDAR sensor is based on laser technology. The sensor works by rapidly firing lasers onto the area and will automatically be measured. Thus, gives high accuracy. Thermal imaging sensor, Thermal imaging of leaves is important in assessing a plant’s responses to heat load and water deprivation.
· Smartphone – Controller will require a smartphone to be attached with a specific type C or Lightning connector.
AILA can be connected to a mobile device once installed the AILA app. It can send you any necessary updates or inform you of harmful microorganisms that threaten your plants when connected. The great thing about AILA’s integrated database is that it can easily recognize any dangerous plant diseases when they show up, even without being connected to the wifi or a mobile device. AILA can use its cameras and sensors to identify symptoms of plant diseases, compare and contrast them to its database, and accurately diagnose your plant’s health, allowing you to take the most appropriate action to rescue your plant correctly. Its assessment of your plant’s current state goes through multiple evaluations within its database, so it is safe to say that whatever it concludes is reliable.
Figure 2. FULL FUNCTION OF AILA
WHAT DISEASES CAN AILA IDENTIFY?
Diagnosing a plant with the naked eye can be tricky and sometimes impossible. Your plant might end up with a dangerous disease like a virus, and you wouldn’t be able to do anything until it is too late. With AILA, you don’t have to worry about it. AILA’s advanced scanning technology can help determine whatever factors intend to harm your crops. There are three leading causes of plant diseases: fungi, bacteria, and viruses.
Bacterial illnesses are classified into four groups based on the level of plant tissue damage and the symptoms they cause, which include vascular wilt, necrosis, soft rot, and tumors. The invasion of the plant’s vascular system by bacteria causes vascular wilt. Water and nutrients cannot travel (translocate) through the xylem of the host plant because of the following multiplication and obstruction. Bacterial wilt of sweet corn, alfalfa, tobacco, tomato, cucurbits (e.g., squash, pumpkin, and cucumber), and black rot of crucifers are only a few examples of how the aerial plant structure can droop, wilt, or die. Toxins secreted by pathogens can cause necrosis (poison). Leaf spots, stem blights, and cankers are just a few symptoms. Pathogens that cause soft rot diseases are fungi. Soft rots are widespread in fleshy plants like potatoes, carrots, eggplant, squash, and tomatoes. Bacteria induce tumor illnesses by causing uncontrolled proliferation of plant cells, resulting in enormous structures. Most germs cause only one significant symptom, while a few cause various symptoms. In general, determining if a plant is infected with a bacterial pathogen is not straightforward; however, identifying the pathogenic agent at the species level necessitates the isolation and characterization of the pathogen using a variety of laboratory procedures. For a bacteria to cause illness in a plant, it must first penetrate and grow in the plant tissue. Bacterial pathogens invade plants through wounds caused by harsh weather, humans, tools and machinery, insects, nematodes, and natural openings like stomata, lenticels, hydathodes, nectar-producing glands, and leaf scars.
Fungi are the most common pathogens in plants, and they cause a broad spectrum of significant plant diseases. Fungi are responsible for the majority of vegetable illnesses. They harm plants by destroying cells and stressing them. Infected seed, soil, agricultural debris, neighboring crops, and weeds are all sources of fungal diseases. Wind and water splashes propagate fungi and the movement of infected soil, animals, people, machinery, tools, seedlings, and other plant material. They penetrate plants by stomata and wounds caused by pruning, harvesting, hail, insects, various illnesses, and mechanical damage. Foliar diseases are caused by fungus. Downy mildews, Powdery mildews, and White blister is three of the most common foliar diseases. Other fungi that cause soilborne illnesses include Clubroot, Pythium species, Fusarium species, Rhizoctonia species, Sclerotinia, and Sclerotium species. Fungal infections can affect a wide variety of plants. Anthracnose, Botrytis rots, Downy mildews, Fusarium rots, Powdery mildews, Rusts, Rhizoctonia deteriorates, Sclerotinia spoils and Sclerotium rots are among these diseases.
Physical evidence of the pathogen is a marker of plant disease. Fungal fruiting structures, for example, are a symptom of infection. You’re staring at the parasitic fungal disease organism when you see powdery mildew on a lilac leaf (Microsphaera alni). Gummosis, a bacterial exudate from stone fruit cankers, is caused by bacterial abscesses. Although the spot is made up of plant tissue and is a symptom, the thick, liquid exudate is mainly made up of bacteria and is a marker of the disease.
Virus particles are so tiny that they can only be spotted using an electron microscope. Most plant viruses are rod-shaped or isometric in shape (polyhedral). TMV, PVY, and CMV are examples of short rigid rod-shaped, long flexuous rod-shaped, and isometric viruses, respectively. Viruses have an inner nucleic acid core (either ribonucleic acid [RNA] or deoxyribonucleic acid [DNA]) that is covered by a protein shell (referred to as the capsid). In most human and animal viruses, the capsid is further encased by a membrane that allows the passing of the virus through the cell membrane. Plant viruses require a wound for their initial entry into a plant cell since a rigid cell wall borders their cell membrane. Plant wounds can occur spontaneously, such as when lateral roots branch out. Agronomic or horticultural methods, or other mechanical ways; fungal, nematode, or parasite plant infections; or insects may cause them. The organism that causes the wound can sometimes carry and transmit the virus. Vectors are organisms that transfer infections. Plant viruses propagate primarily by mechanical transfer and insect vector transmission. Human participation in propagating plants through budding, grafting, or cuttings is one of the most common ways viral infections reproduce.
Plant virologists, for example, use grafting and budding techniques to transfer and identify viruses in their research. Depending on the plant species and the type of virus, the seedling offspring of a virus-infected plant are usually, but not always virus-free. Insect transmission is one of the most common ways for viruses to spread in the field. The most prevalent and commercially essential vectors of plant viruses are insects in the order Homoptera, such as aphids, planthoppers, leafhoppers, whiteflies, and mealy bugs, which have piercing-sucking mouthparts. Plant viruses can also be spread by pollen grains or seeds. Agriculture has had its fair share of ups and downs over the years. From mismanaged field crops to declining income of farmers. We hope that AILA can help solve those issues by making growing crops easier. Imagine a field being attended to by dozens of automated drones, scanning and making assessments of rows upon rows of crops, and people don’t have to do it themselves. This won’t result in farmers losing their jobs, of course. AILA is merely there to provide a diagnosis and monitor your plants, making plant care time-efficient
Mosaic is a plant disease caused by different viral strains. Mosaic infections can affect various economically significant crops, including tobacco, cassava, beet, cucumber, and alfalfa. Tulip mosaic virus “breaks” tulip and lily blossoms, generating gorgeous and colorful streaks; this rare, distinctive impact fueled some of the 17th century’s Tulip Mania. Mosaic symptoms vary, but uneven leaf mottling is a common symptom (light and dark green or yellow patches or streaks). Veins may be lighter than usual or bordered with dark green or yellow, and leaves are commonly stunted, curled, or puckered. Plants are frequently dwarfed, having less fruit and blooms than typical and being malformed and stunted. Mosaic symptoms are sometimes misdiagnosed as nutrient insufficiency or herbicide harm, especially at temperatures exceeding 27 °C (81 °F). Aphids and other insects, mites, fungus, nematodes, and touch propagate the causative viruses; pollen and seeds can also transport the infection. Due to the mosaic’s symptoms, AILA can quickly identify this disease and advice you on what measures to take.
In this generation, where technology continues to prosper and advance, we mustn’t turn a blind eye toward our green friends. As human civilization thrives, they sadly decline in return. Agriculture’s scope has been widened by the development of the agricultural food industry and integrated supply chains as a result of globalization, technological and corporate advancements, and environmental effects. Furthermore, recent global financial crises have revealed flaws in the implementation and long-term viability of current growth models and agricultural policies. As a result, new structural solutions are required. Aside from these concerns, modern growth theory views technological advancement as the driving force behind economic growth. It is frequently stated that the use of technology will significantly contribute to rural development and poverty reduction. Science, technology, and engineering advancements are key tools for achieving these goals and bringing about the changes mentioned above. The use of technology in global economies is a determining factor in competition, and it has an impact on agriculture. As a result, technology has a significant impact not only on agricultural growth and employment, but also on rural development and poverty reduction. Furthermore, there have been major questions about how to produce agricultural products that are both sustainable and environmentally friendly.
Eco-friendly innovation, in particular, stimulates not only production but also efficient use of natural resources, making it a key tool in social and economic development. Innovations now enable higher value in unprocessed raw material within a chain; processing, packaging, storage, delivery, and distribution of food after production; and food safety as a result of changing economic, political, and ecological conditions around the world. As a result, the use of technology in agriculture accelerates growth and development while ensuring efficient production. Through rural development, the ultimate impact of technology use and innovation can be achieved in reducing poverty. Increasing agricultural productivity, as well as boosting farmer income, which is a major industry goal, as well as reducing poverty and developing rural areas, are not unattainable objectives. For innovation, especially the use of technology, a mental framework must be developed. Farmers, as users, must have a clear understanding of how the development and implementation of innovation will contribute to agriculture. The goal should not be limited to a specific percentage of the budget or specific figures to be met. Science’s contributions to society must be recognized as one of the most important preconditions for agricultural production to continue.In agricultural industry and food chain, revenue growth among small farmers as well as corporate companies will translate into significant increases in social welfare. To increase productivity and reduce poverty in rural areas, detailed and comprehensive analyses and plans are required. When it comes to the efficient use of natural resources, food security, and the effects of climate change, immediate action is required.
Therefore, this is the main reason behind the students of BSCS 1-A and BSIT 1-A creation of the innovative product, AILA, that serves prevent agricultural issues, particularly plant diseases. The students can use their constantly growing technology to keep the plants safe and protected from external threats. AILA brings about a lot of excellent outcomes in the agricultural sector since the protection of crops from various diseases is an essential factor, especially in a country like the Philippines, where farmers are the backbone of food production, and the agriculture industry is one of the major sectors. With the increase in population and demand for food supply, performing agricultural tasks is necessary. Due to the increased need to feed the global population, agricultural robots are becoming commonplace for farmers. In addition, AILA would not only serve to be a sensor-detector for plant diseases but it will also provide opportunity for the farmers to produce a large yield of crops or plants per year. It would also not cost them much money since AILA will be created as an affordable robot as much as possible. Through this, we aim to provide a permanent service to our farmers, who serves to be the foundation of our economic growth.
Borines, L., Nunez, J., Borines, R., and Canete, F. (2017, November). Inventory and incidence of plant diseases affecting vegetables in selected areas in the Visayas and Mindanao. https://www.researchgate.net/publication/337896098_Inventory_and_inciden\e_of_plant_diseases_affecting_vegetables_in_selected_areas_in_the_Visayas_and_Mindanao
De la Cruz, R. (2019). Philippines: Challenges, Opportunities, and Constraints in Agricultural Biotechnology. https://cgspace.cgiar.org/bitstream/handle/10947/5582/Delacruz.pdf
De la Cruz, J., and Jansen, K. (2017, November 7). Panama disease and contract farming in the Philippines: Towards a political ecology of risk. https://onlinelibrary.wiley.com/doi/full/10.1111/joac.12226
Grace, K., Navarro, M., and Mercado, S. (2017, April). Seventeen Years of Media Reportage of Modern Biotechnology in the Philippines. https://www.cabi.org/GARA/FullTextPDF/2017/20173165150.pdf
Isleib, J. (2012, December 19). Signs and symptoms of plant disease: Is it fungal, viral or bacterial? https://www.canr.msu.edu/news/signs_and_symptoms_of_plant_disease_is_it_fungal_viral_or_bacterial
Jeger, M., Beresford, R., Bock, C., Brown, N., Fox, A., and Newton, A. (2021). Global challenges facing plant pathology: multidisciplinary approaches to meet the food security and environmental challenges in the mid-twenty-frst century. https://cabiagbio.biomedcentral.com/track/pdf/10.1186/s43170-021-00042-x.pdf
Moniflor, M., Vellema, S., and Digal, L. (2019). Coordination as Management Response to the Spread of a Global Plant Disease: A Case Study in a Major Philippine Banana Production Area. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6728417/
Nilay Ganatra and Atul Patel, “A Survey on Diseases Detection and Classification of Agriculture Products using Image Processing and Machine Learning”, International Journal of Computer Applications (0975 – 8887) Volume 180 –No.13, January 2018
Ngozi Clara Eli-Chukwu, “Applications of Artificial Intelligence in Agriculture: A Review”, Engineering, Technology & Applied Science Research Vol. 9, No. 4, 2019, 4377-4383
Paras M. Khandelwal and Himanshu Chavhan, “Artificial Intelligence in Agriculture: An Emerging Era of Research”, September 2019
Rajkumar Murugesan, S. K. Sudarsanam, Malathi. G, V. Vijayakumar, Neelanarayanan. V, Venugopal. R, D. Rekha, Sumit Saha, Rahul Bajaj, Atishi Miral, Malolan V, “Artificial Intelligence and Agriculture 5. 0”, International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-8 Issue-2, July 2019
Shima Ramesh, Niveditha M, Pooja R, Prasad Bhat N, Shashank N, “Plant Disease Detection Using Machine Learning”, April 2018
Mukesh Kumar Tripathi and Dr. Dhananjay D. Maktedar, “Recent Machine Learning Based Approaches for Disease Detection and Classification of Agricultural Products”
NOAA (2021, February 26) What is Lidar? https://oceanservice.noaa.gov/facts/lidar.html#:~:text=Lidar%2C%20which%20stands%20for%20Light,variable%20distances)%20to%20the%20Earth.