ChapterPDF Available

Computer Vision and MachineLearning for Smart Farming and Agriculture Practices

Authors:
Kassim Kalinaki at Islamic University in Uganda (IUIU)
Kassim Kalinaki
Wasswa Shafik at Dig Connectivity Research Laboratory (DCRLab)
Wasswa Shafik
  • Dig Connectivity Research Laboratory (DCRLab)
Tar J. L. Gutu
Tar J. L. Gutu
Tar J. L. Gutu
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Owais Ahmed Malik at Universiti Brunei Darussalam
Owais Ahmed Malik
Download full-text PDF
Read full-text
Download citation

Abstract

The advent of cutting-edge techniques such as Computer Vision (CV) and Artificial Intelligence (AI) have sparked a revolution in the agricultural industry, with applications ranging from crop and livestock monitoring to yield optimization, crop grading and sorting, pest and disease identification, and pesticide spraying among others. By leveraging these innovative techniques, sustainable farming practices are being adopted to ensure future food security. With the help of CV, AI, and related methods, such as Machine Learning (ML) together with Deep Learning (DL), key stakeholders can gain invaluable insights into the performance of agricultural and farm initiatives, enabling them to make data-driven decisions without the need for direct interaction. This chapter presents a comprehensive overview of the requirements, techniques, applications, and future directions for smart farming and agriculture. Different vital stakeholders, researchers, and students who have a keen interest in this field would find the discussions in this chapter insightful.
Content uploaded by Wasswa Shafik
Author content
All content in this area was uploaded by Wasswa Shafik on Jun 27, 2023
Content may be subject to copyright.
79
Copyright © 2023, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
Chapter 5
DOI: 10.4018/978-1-6684-8516-3.ch005
ABSTRACT
The advent of cutting-edge techniques such as Computer Vision (CV) and Artificial Intelligence (AI)
have sparked a revolution in the agricultural industry, with applications ranging from crop and livestock
monitoring to yield optimization, crop grading and sorting, pest and disease identification, and pesti-
cide spraying among others. By leveraging these innovative techniques, sustainable farming practices
are being adopted to ensure future food security. With the help of CV, AI, and related methods, such
as Machine Learning (ML) together with Deep Learning (DL), key stakeholders can gain invaluable
insights into the performance of agricultural and farm initiatives, enabling them to make data-driven
decisions without the need for direct interaction. This chapter presents a comprehensive overview of
the requirements, techniques, applications, and future directions for smart farming and agriculture.
Different vital stakeholders, researchers, and students who have a keen interest in this field would find
the discussions in this chapter insightful.
Computer Vision and Machine
Learning for Smart Farming
and Agriculture Practices
Kassim Kalinaki
https://orcid.org/0000-0001-8630-9110
Islamic University in Uganda, Uganda
Wasswa Shafik
https://orcid.org/0000-0002-9320-3186
Ndejje University, Uganda
Tar J. L. Gutu
Soroti University, Uganda
Owais Ahmed Malik
Universiti Brunei Darussalam, Brunei
80
Computer Vision, Machine Learning for Smart Farming, Agriculture
INTRODUCTION
Agriculture, aside from technology and oil, remains a leading contributor to many nations’ GDPs and
is the world’s most established and vital industry. It has consistently been the primary provider of food
and livestock for billions of people (A. Kumar et al., 2019; Thilakarathne et al., 2022). As the global
populace continues to soar, projections estimate that by 2050, it will have reached a staggering 9.8 billion
individuals (United Nations, 2017). This consequently means that arable lands are expected to decrease
due to increased urbanization which will raise concerns as to whether the anticipated increase in the
demand for food and agricultural production will be met.
To meet such massive demand due to the increased population, a 70% increase in the current produc-
tion of agricultural foods will have to be realized by the year 2050 (Kakani et al., 2020). Achieving that
status will, however, prove to be a tough challenge due to reasons such as decreased cultivable lands,
rising food demands, labor requirements, and limited financial capital (Thilakarathne et al., 2022).
Hence, multi-stakeholder initiatives from the industry, academia, along with other research and develop-
ment entities are needed to fill up this gap by developing and implementing innovative solutions. These
solutions are aimed at increasing crop yields with minimal labor and limited cultivable lands, thereby
providing much-needed food security for the increased population.
Currently, the realm of information and communication technology, along with its related technologies
like fifth generation and beyond, CV, internet of things (IoT), Big Data, AI, Edge/Fog/cloud Computing,
and image processing (Kakani et al., 2020; Shafik et al., 2021; Yang et al., 2021), is transforming the
agricultural sector, fostering the development of innovative solutions to boost crop yields and satisfy
the needs of a burgeoning population (Uddin and Bansal, 2021). The integration of these technologies
has brought forth the emergence of “smart farming” and “precision agriculture,” novel concepts revolu-
tionizing the way we cultivate and harvest, which involve the use of advanced technologies to optimize
decision-making in farm management and enhance the efficiency and effectiveness of agricultural tasks
(Pathan et al., 2020). So, by harnessing the capabilities of these technologies, farmers can implement
sustainable practices that increase crop productivity and combat the effects of food insecurity caused
by poor planning, uneven harvesting, inadequate irrigation, low crop yields, and unpredictable weather
events such as droughts.
Recently, the field of CV has been garnering substantial interest in the realm of agriculture, owing
to its capacity to lower the expenses associated with food production through adaptable and intelligent
automation mechanisms, thereby helping farmers and other key stakeholders increase crop productiv-
ity. By allowing machines to perceive and understand the environment in a way similar to humans, CV,
combined with image acquisition through remotely configured camera sensors, holds enormous potential
for enhancing the overall performance of the farming and agricultural sector through contactless and
scalable solutions (Uddin and Bansal, 2021).
As a critical technology, AI and its related technologies, including ML and DL, are gaining traction
in the realm of smart farming and agriculture. Their adaptability, speed, automation, precision, and pre-
dictive capabilities enable them to emulate human thinking attributes, allowing farmers and other key
stakeholders to make precise and timely decisions that lead to increased crop yields in both quality and
quantity (Ayoub Shaikh et al., 2022) In contrast to traditional methods, these technologies offer several
key advantages, including decreased equipment expenses, amplified computational capabilities, and the
ability to collect and process large amounts of agricultural and farm-related data, thus enabling efficient
monitoring and timely decision-making (Raval et al., 2022).
20 more pages are available in the full version of this document, which may
be purchased using the "Add to Cart" button on the product's webpage:
www.igi-global.com/chapter/computer-vision-and-machine-learning-for-smart-
farming-and-agriculture-practices/325570?camid=4v1
Related Content
Real-Time EEG Device for Epilepsy Detection Using Wavelet Transform and Support Vector
Machine
Sharad Sarjerao Jagtap and Rajesh Kumar M. (2021). Advancing the Investigation and Treatment of Sleep
Disorders Using AI (pp. 104-135).
www.igi-global.com/chapter/real-time-eeg-device-for-epilepsy-detection-using-wavelet-
transform-and-support-vector-machine/285272?camid=4v1a
Symbol Grounding Problem
Angelo Loula and João Queiroz (2009). Encyclopedia of Artificial Intelligence (pp. 1543-1548).
www.igi-global.com/chapter/symbol-grounding-problem/10443?camid=4v1a
Building Data Warehouses Using Automation
Nayem Rahman and Dale Rutz (2015). International Journal of Intelligent Information Technologies (pp. 1-
22).
www.igi-global.com/article/building-data-warehouses-using-automation/135903?camid=4v1a
A Hybrid Portfolio Selection Model: Multi-Criteria Approach in the Indian Stock Market
Praveen Ranjan Srivastava and Prajwal Eachempati (2020). International Journal of Intelligent Information
Technologies (pp. 100-116).
www.igi-global.com/article/a-hybrid-portfolio-selection-model/257215?camid=4v1a
... Agriculture or farming has a substantial role in emissions generation, but adopting sustainable and artificial intelligence-assisted farming techniques has the potential to effectively trap carbon, mitigate water use, and mitigate pollutants (Shafik et al., 2023a(Shafik et al., , 2023bKalinaki et al., 2023). The transition toward a net-zero economy entails promoting techniques that guarantee global food security, foster climate conversion, and stimulate rural economic development by early plant disease detection and classification (Yang et al., 2021;Shafik et al., 2023aShafik et al., , 2023b. ...
... These practices encompass low-carbon farming techniques, agroforestry, and regenerative agriculture. These activities serve the dual purpose of mitigating emissions from agriculture while improving soil health, conserving water, and enhancing crop resilience (Kalinaki et al., 2023). Sustainable agriculture plays a crucial role in safeguarding food security by concurrently fostering and facilitating the growth of rural economies (Yang et al., 2021). ...
... The investigation of breakthrough clean energy technologies holds the utmost significance in pursuing a NZE. The advancement of solar panels, next-generation batteries, and green hydrogen production holds great potential in improving energy efficiency and mitigating emissions (Kalinaki et al., 2023). To enhance the pace of advancement, governmental bodies, research institutions, and enterprises must engage in collaborative endeavors to allocate financial resources and offer assistance for research and development initiatives in these domains (Salas et al., 2020). ...
Industry 4.0 Technologies’ Opportunities and Challenges for Realising Net-Zero Economy
Chapter
  • May 2024
This study investigates the intricate range of obstacles and potential benefits linked to the transition toward a net-zero economy (NZE), driven by the urgent need to tackle climate change and foster sustainable ecology. Based on an extensive review of scholarly sources, this study scrutinizes the technological, economic, and societal challenges that ought to be addressed to attain a NZE. Most outstandingly, it emphasizes the merits of environmentally sustainable practices, the potential for economic growth, and improvements in societal well-being that can arise from this transition. It further depicts selected case studies to demonstrate sustainable empirical evidence and provides policy recommendations. The paradigm is to assist governments and other stakeholders in effectively managing human-associated challenges to attain increased sustainable value maximally. Finally, this highlights the utmost significance of tackling these challenges and capitalizing on opportunities to facilitate a sustainable, net-zero future that guarantees worldwide prosperity and ecological welfare.
View
... Moreover, ML systems learn from data through a process called training. A ML algorithm processes a dataset during training to discover patterns and relationships in the feature space (Kalinaki, Shafik, Gutu, & Malik, 2023). These patterns are captured as a model, which can be used to make predictions or decisions about new, unseen data. ...
... Common tasks within unsupervised learning involve clustering and dimensionality reduction, with techniques such as K-Means Clustering, Hierarchical Clustering, Principal Component Analysis, Independent Component Analysis (ICA), and Fuzzy C-means illustrating the spectrum of methodologies. (Kalinaki, Shafik, Gutu, & Malik, 2023). Lastly, the subfield of reinforcement learning delves into the intricacies of decision-making within various environments, guiding agents to select actions that optimize cumulative rewards adeptly. ...
... Integrating ML, remote sensing technologies, and data analytics presents a robust solution for effective crop monitoring. Utilizing various remote sensors facilitated by satellites and drones allows for acquiring highly detailed images of agricultural landscapes (Kalinaki, Shafik, Gutu, & Malik, 2023). Subsequent analysis of these images through ML algorithms enables the assessment of crop health, detection of disease outbreaks, and evaluation of the influence of environmental factors. ...
Towards an Intelligent Tomorrow: Machine Learning Enabling Sustainable Development
Chapter
  • Mar 2024
Sustainable development has become a global imperative in the 21st century as societies grapple with environmental, social, and economic challenges. Machine learning (ML), a subset of artificial intelligence (AI), has emerged as a powerful tool to address these complex issues. Accordingly, this chapter explores the intersection of sustainable development and innovation, delving into the transformative potential of innovative solutions, particularly within the context of AI-powered techniques. Moreover, it examines how innovation, guided by sustainability principles, can be harnessed to address complex global challenges and help us progress towards a world where Sustainable Development Goals (SDGs) are not just aspirations but achievements. Furthermore, it explores how ML contributes to sustainable development across various domains, challenges encountered, and future directions.
View
... These different deep learning algorithms offer robust and accurate solutions for the identification of crop diseases and pests. They leverage advanced techniques in artificial intelligence and computer vision to improve the efficiency and effectiveness of pest and disease management in agriculture [8], [9] . ...
Deep Learning in Agritech: Exploring Techniques and Architectures for Plant Disease Detection
Article
Full-text available
  • Apr 2024
Disease detection in agriculture is crucial for maintaining crop health and productivity. Traditional methods of detection rely on manual observation and expert knowledge, which can be time-consuming and subjective. In recent years, deep learning techniques have emerged as a promising approach for automated disease detection. This paper investigates the performance of three state-of-the-art deep learning models, ResNet34, MobileNetv2, And Yolov8, in detecting and categorizing leaf diseases among corns. The study revealed that MobileNet2 demonstrates computational effectiveness in classifying corn leaf diseases, with a low average loss and the ability to discriminate between specific illnesses. Yolov8 is identified as a strong candidate for real-world applications due to its consistently high precision (95.73%), recall (94.81%), accuracy (96.18%), and F1 score (95.22%) across all disease categories. It excels in distinguishing between Blight and Common Rust and accurately recognizing healthy leaves. ResNet34 and MobileNetv2 also show competitive results, but Yolov8 performs better overall, particularly in terms of precision and recall. However, the choice of the optimal model depends on the specific application's demands, computational effectiveness, and the balance between recall and precision. Further investigation and refinement endeavors are recommended to augment the potential of these models and address any remaining obstacles in disease identification.
View
... With more robust social media promotions and publicity efforts, future WiA webinars are poised to build on Nancy's momentum to engage and energize even larger audiences. The 2 nd webinar was on September 19th, 2023, convened a discussion around cutting-edge remote sensing technologies being deployed to combat food insecurity [5]. Dr. Maria Luisa Buchaillot of the Fall Armyworm Monitoring and Early Warning System (FAMEWS) project [6] shared insights from FAMEWS' recent research leveraging satellite imagery to detect fall armyworm infestations and protect vulnerable smallholder farmers in Sub-Saharan Africa. ...
Career Development Activities for African Women, Students and Young Professionals in Geoscience and Remote Sensing
Preprint
Full-text available
  • Apr 2024
Created to champion African women’s involvement and leadership in geospatial careers, the Women in Africa (WiA) initiative was founded within the Inspire, Develop, Empower, and Advance (IDEA) committee of IEEE’s Geoscience and Remote Sensing Society (GRSS). By spotlighting academic, governmental, and industrial career paths through webinars and networking opportunities, WiA promotes professional growth and motivates youth to explore geosciences. Their inaugural effort brought together historically underrepresented African women and young professionals across academia, government, and industry for Career Development Webinars.
View
... With more robust social media promotions and publicity efforts, future WiA webinars are poised to build on Nancy's momentum to engage and energize even larger audiences. The 2 nd webinar was on September 19th, 2023, convened a discussion around cutting-edge remote sensing technologies being deployed to combat food insecurity [5]. Dr. Maria Luisa Buchaillot of the Fall Armyworm Monitoring and Early Warning System (FAMEWS) project [6] shared insights from FAMEWS' recent research leveraging satellite imagery to detect fall armyworm infestations and protect vulnerable smallholder farmers in Sub-Saharan Africa. ...
View
... IoFT solutions must be adaptable and customizable for different forest types, including tropical rainforests, temperate forests, and arid woodlands (Shafik et al., 2021). This requires considering factors such as varying climate patterns, soil conditions, and vegetation characteristics (Kalinaki & Shafik et al., 2023). Additionally, different ecosystems may require specific sensor types, data collection frequencies, and analysis methods (Yang et al., 2021). ...
Internet of Forestry Things (IoFT) Technologies and Applications in Forest Management
Chapter
  • Jan 2024
Forests play a crucial role in sustaining the planet and human societies, offering a wide range of benefits like climate and water cycle regulation, biodiversity conservation, and the provision of essential resources. However, forests face significant challenges, such as deforestation, forest degradation, and the impacts of climate change, jeopardizing their long-term sustainability. To tackle these pressing issues, innovative solutions are required, and the internet of things (IoT) emerges as a promising avenue. By leveraging IoT technologies in forest management, also known as the internet of forestry things (IoFT), a transformative approach to forest management can be achieved. The IoFT technology empowers real-time data collection on forest conditions, encompassing parameters like temperature, humidity, and soil moisture. Additionally, it facilitates monitoring the movement and location of various forest assets, including wildlife, carbon stock, personnel, and equipment. This chapter presents a comprehensive overview of the current state of IoFT technologies and their applications in forest management. The chapter explores the potential benefits of IoFT technology in forest management, highlighting its ability to enhance the efficiency, effectiveness, significance, and sustainability of forest ecosystems. It draws upon a collection of studies, reports, and articles to elucidate the various applications of IoFT technologies in forest management. These applications encompass monitoring forest health, predicting and detecting forest fires, and identifying illegal logging activities, among others. IoFT technologies also offer opportunities for optimizing forest operations such as harvesting and transportation while improving the safety of forest workers. However, the chapter also acknowledges the challenges and limitations associated with IoFT technologies in forest management. Concerns over data privacy, security, and interoperability are discussed, emphasizing the need for careful consideration and robust solutions to address these issues. In conclusion, the study provides recommendations for future research endeavors aimed at addressing the challenges and advancing the utilization of IoFT technologies in forest management. By doing so, the potential of IoFT technologies can be harnessed to their fullest extent, paving the way for sustainable and effective forest management practices.
View
Industry Revolution 4.0 and Beyond Abilities and Perils for Sustainable Zero Net Economy Development
Chapter
  • Jun 2024
The UN Sustainable Development Goals (SDGs) enhance health, ecology, vitality, and the global economy. This chapter carefully reviews scholarly literature to identify technological, economic, and sociological hurdles to a net-zero economy. It highlights this transformation's economic, social, and environmental benefits. This study provides empirical evidence and policy recommendations using case studies. The fundamental purpose is to aid governments and others in efficiently solving human problems for sustainable value. The need to address these challenges and seize chances to create a sustainable, net-zero future that ensures global prosperity and environmental health. Support governments and other relevant stakeholders in efficiently addressing human-related concerns to achieve optimal sustainable value. Finally, it accentuates the importance of addressing these issues and leveraging possibilities to achieve a sustainable, net-zero future that ensures global prosperity and ecological well-being.
View
Time Series Forecasting Techniques for Climate Trend Prediction
Chapter
  • May 2024
Climate change is a pressing global issue that profoundly impacts ecosystems, economies, and societies. Accurate climate trend prediction is crucial for informed decision-making and mitigation strategies. This study focuses on time series forecasting techniques as vital tools in predicting climate trends. It explores the complexities of climate time series data and the challenges associated with the data. The study explores traditional methods like Autoregressive Integrated Moving Average (ARIMA), highlighting their applicability and limitations. It also showcases the power of machine learning and statistical techniques in addressing climate data intricacies through real-world examples. In the era of technology, deep learning (DL) approaches, including recurrent neural networks, Long short-term memory (LSTM), Gated Recurrent Unit (GRU), and transformer-based models, are emerging for climate change forecasting. The study looks ahead to ongoing research and trends in climate time series forecasting, outlining challenges and promising areas for exploration.
View
A Review of Artificial Intelligence Techniques for Improved Cloud and IoT Security
Chapter
  • Apr 2024
The current surge in interconnected devices, which includes the Internet of Things (IoT) devices and the continually expanding cloud infrastructure, marks a new era of digital transformation and convenience. This transformative wave is reshaping industries, ushering in the age of smart cities, autonomous vehicles, and effortless remote collaboration. Yet, the growing complexity and reach of these technologies bring an accompanying increase in potential vulnerabilities and security risks. Thus, this study delves into the convergence of artificial intelligence (AI), cloud computing, and IoT security. It investigates how these state-of-the-art technologies can be leveraged to protect networks, data, and devices, presenting inventive solutions to address the ever-evolving threat landscape. Additionally, it sheds light on the challenges posed by AI-powered techniques and offers insights into future trends, making it a valuable resource for researchers, students, and cybersecurity professionals.
View
A Review of Big Data Analytics and Artificial Intelligence in Industry 5.0 for Smart Decision-Making
Chapter
  • Jan 2024
Globally, the industrial landscape is witnessing a significant transformation with the emergence of Industry 5.0, marking a new era characterized by seamless convergence of digital technologies, physical systems, and human expertise. This shift hinges on the dynamic interplay between big data analytics (BDA) and artificial intelligence (AI), becoming the cornerstone of intelligent decision-making in Industry 5.0. Accordingly, this study explores the profound impact of integrating BDA and AI in Industry 5.0, emphasizing the pivotal roles of data acquisition, storage, and processing. Additionally, it examines how AI improves human decision-making across various industrial sectors like manufacturing, retail, automotive, energy grid management, and healthcare, showcasing real-world case studies. Moreover, the chapter addresses the challenges associated with managing large-scale data and offers innovative solutions. It concludes by looking ahead, outlining promising areas for future research at the intersection of BDA and AI to foster well-informed decision-making in Industry 5.0.
View
A Simple Method to EstimateWeed Control Threshold by Using RGB Images from Drones
Article
Full-text available
  • Nov 2022
The estimation of the infestation level in a field and the consequent determination of the economic threshold is a basic requisite to rationalize post-emergence weeding. In this study, a simple and inexpensive procedure to determine the economic threshold based on weed cover is proposed. By using high-resolution RGB images captured by a low-cost drone, a free downloadable app for image processing and common spreadsheet software to perform the model parametrization, two different methods have been tested. The first method was based on the joint estimation of the two parameters involved in weed cover calculation, whereas the second method required the availability of further images for the separate estimation of the first parameter. The reliability of the two methods has been evaluated through the comparison with observed data and the goodness of fit in parameter calibration has been verified by calculating appropriate quality indices. The results showed an acceptable estimation of the weed cover value for the second method with respect to observed data (0.24 vs. 0.17 m2 and 0.17 vs. 0.14 m2, by processing images captured at 10 and 20 m, respectively), whereas the estimations obtained with the first method were disappointing (0.35 vs. 0.17 m2 and 0.33 vs. 0.14 m2, by processing images captured at 10 and 20 m, respectively).
View
Machine learning approach for the classification of wheat grains
Article
Full-text available
  • Feb 2023
Wheat is known to be one of the most important agricultural crops throughout the world. Due to its mass storage in warehouses, tonnes of wheat grains rotten every year that eventually affects its market price. This paper presents an end-to-end automatic system that utilizes computer vision techniques for the quality grading of wheat grains. The main purpose of this work is to determine most discriminatory features and a suitable classifier that may classify the given wheat sample into two classes ‘fresh’ and ‘rotten’. At first, shadow removal, segmentation, and separation of each grain is performed as parts of the pre-processing step. The pre-processing is followed by the features extraction step where 7 color and 16 texture handcrafted features are determined for each grain. The four binary classification models, namely, Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Multi-Layer Perceptron (MLP), and Naïve Bayes (NB) are then built using 10-fold cross validation approach. The classifiers are compared on the basis of performance metrics- accuracy, error rate, recall, specificity, precision, and F1-score. The comparative analysis depicts that based on color features, the SVM classifier outperforms other classifiers by achieving the accuracy of 93%. In contrast, based on texture features, the NB classifier achieved accuracy at 65%; highest among all classifiers. Experimental results encourage the utility of SVM classifier modelled on color features in automatic quality grading of wheat grains.
View
Embedded Design of Automatic Pesticide Spraying Robot Control System
Conference Paper
Full-text available
  • Oct 2022
In agriculture, crops need to apply pesticide spraying flow control precisely to reduce costs, protect the environment, and increase yield production. Although there have several variable control methods for spraying flow control because indirect control flow techniques and having a slow response could cause inaccuracy and mismanagement, also noted that those systems also suffer from complicated design and debugging, etc. In this paper, an embedded design of the fuzzy PID variable spraying control method is adopted. The experimental results show that the overshoot of Proportional-Integral-Derivative (PID) control is 10.76%, and the overshoot of fuzzy PID control is 7.17% which can meet the requirements of an advanced spray control flow system. For further investigation, a novel spray flow control method based on Programmable Logic Control (PLC) is proposed in this paper.
View
Plant disease detection using machine learning approaches
Article
Full-text available
  • Oct 2022
  • EXPERT SYST
Plant health care is the science of anticipating and diagnosing the advent of life‐threatening diseases in plants. The fatality rate of plants can be reduced by diagnosing them for any signs early on. The early detection of such diseases is one possibility for lowering plant mortality rates. Machine learning (ML), a type of artificial intelligence technology that allows researchers to enhance and develop without being explicitly programmed, is used in this study to build early prediction models for plant disease diagnosis. Due to the similarities of crops throughout the early phonological phases, crop classification has proved problematic. ML can be applied to a variety of tasks recognize different types of crops at low altitude platforms with the help of drones that provide high‐resolution optical imagery. The drones are employed to photograph phonological stages, and these greyscale photographs are then utilized to develop grey level co‐occurrence matrices‐based characteristics. In this article, the proposed plant disease detection models are developed using ML approaches such as random forest‐nearest neighbours, linear regression, Naive Bayes, neural networks, and support vector machine. The performance of the generated plants disease risk evaluation model is calculated using unbiased metrics such as true positive rate, true negative rate, precision, recall, and F1‐score method are all factors to consider. The results revealed that the ensemble plants disease model outperforms the other proposed and developed plant disease detection models. The proposed and developed plant disease prediction models aimed to predict disease detection in the early stages, allowing for early preventive actions and predictive maintenance.
View
Cybersafe Capabilities and Utilities for Smart Cities
Chapter
  • Mar 2023
From the beginning of the 21st century, the entire world suffers from two critical problems: the growth of the world population and the improvement of life expectancy of people owing to the development of healthcare facilities. This has ultimately led to urbanization where a lot of people migrated to cities in search of better prospects. To facilitate those migrating into these cities and with the purpose of better provision of city services, smart cities have emerged thereby connecting everything within the city with the aid of a complex set of technologies. The Internet of Things (IoT) is the fundamental building block of smart cities applied in a variety of smart city solutions, offering real-time information exchange and facilitating ubiquitous connectivity. As IoT is a novel technology that is still in its infancy age and requiring continuous internet connectivity, it paves way for never-ending cyber-attacks targeting smart city services and ultimately endangering the lives of city residents. On the other hand, the security of smart city solutions has always been neglected during the development phase which also endangers the entire city’s ecosystem resulting into cyber-attacks from multiple attack vectors. In this chapter, we are providing a brief review of security enhancement capabilities and utilities that can cope with smart cities for the purpose of improving their security against cyber-attacks and safeguarding the privacy of city dwellers.
View
Evaluation of soil heavy metal pollution based on K-means and SVM
Article
  • Jan 2023
In this paper, soil heavy metals Zn, Pb, Cd, Hg, As, and Sb were measured using a comprehensive distribution sampling in a mining area in Hunan, China. Machine learning data pre-processing techniques were used to process the raw data. Based on the evaluation criteria of the potential risk index, the number of clusters was set to 5, and K-means was used to cluster the sampled data. A convenient and effective evaluation model applied to evaluate of soil heavy metal pollution was obtained by comparing the algorithms of different kernel functions in SVM, with a correct rate of 0.9778 in the training set and 0.9556 in the test set, which has good classification and evaluation ability.
View
Application of AI Techniques and Robotics in Agriculture: A Review
Article
  • Jan 2023
The aim of the proposed work is to review the various AI techniques (fuzzy logic (FL), artificial neural network (ANN), genetic algorithm (GA), particle swarm optimization (PSO), artificial potential field (APF), simulated annealing (SA), ant colony optimization (ACO), artificial bee colony algorithm (ABC), harmony search algorithm (HS), bat algorithm (BA), cell decomposition (CD) and firefly algorithm (FA)) in agriculture, focusing on expert systems, robots developed for agriculture, sensors technology for collecting and transmitting data, in an attempt to reveal their potential impact in the field of agriculture. None of the literature highlights the application of AI techniques and robots in (Cultivation, Monitoring, and Harvesting) to understand their contribution to the agriculture sector and the simultaneous comparison of each based on its usefulness and popularity. This work investigates the comparative analysis of three essential phases of agriculture: Cultivation, Monitoring, and Harvesting, by knowing the depth of AI involved and the robots utilized. The current study presents a systematic review of more than 150 papers based on the existing automation application in agriculture from 1960 to 2021. It highlights the future research gap in making intelligent autonomous systems in agriculture. The paper concludes with tabular data and charts comparing the frequency of individual AI approaches for specific applications in the agriculture field.
View
Crop yield prediction using machine learning techniques
Article
  • Jan 2023
  • ADV ENG SOFTW
Machine Learning is a successful dynamic device for foreseeing crop yields, just as for choosing which harvests to plant and what to do about them during the developing season. Since it operates with a large amount of data produced by several variables, the farming system is highly complicated. Methods of machine learning can aid intelligent system decision-making. The following paper investigates a variety of methods for predicting crop yields using a variety of soil and environmental variables. The main purpose of this project is to make a machine learning model make predictions. By taking into account several variables, machine learning algorithms can help farmers decide which crop to grow in addition to increasing yield. Farmers can benefit from yield estimation because it allows them to minimize crop loss and obtain the best prices for their crops. A machine learning model may be descriptive or predictive, depending on the research question and study objectives.
View
View
An Optimal Hybrid Multiclass SVM for Plant Leaf Disease Detection using Spatial Fuzzy C-Means Model
Article
  • Oct 2022
  • EXPERT SYST APPL
In recent times, plant disease detection and diagnosing measures become a major concern in the agriculture field. Earlier identification of plant disease aids the farmers to take precautionary measures thereby preventing the spread of disease to other parts of plants. Based on the severity of the diseases, the plant may undergo an attack from mild to complete destruction. So, to avoid such destruction, plant diseases should be detected at the initial stage. Therefore, this paper proposes a novel hybrid random forest Multiclass SVM (HRF-MCSVM) design for plant foliar disease detection. To improve the computation accuracy, the image features are preprocessed and segmented using Spatial Fuzzy C-Means prior to the classification process. The Plant Village dataset used consists of a total of 54303 healthy and diseased leaf images. Finally, the performance metrics like accuracy, F-measure, specificity, sensitivity, and recall value were evaluated to determine the effectiveness of the system. The proposed HRF-MCSVM method is compared with a few existing techniques to determine its efficiency.
View