CHAPTER ONE

INTRODUCTION

1. 1. Background of the Study

The threat of diseases to the world's food supply has become more significant due to the increasing number of people and the need for more sustainable agriculture. The diseases that affect orange fruits have caused significant economic and production losses in recent years. The swift detection and identification of these diseases is crucial to prevent these damages and losses (Sankaran et al., 2010).

With the growing popularity of computer science in the field of image classification, the accuracy of this process is becoming more and more important. Some factors are responsible for determining the classification accuracy of a system, these includes the number of features extracted, the type of classification algorithm used, and the quality of the images curated. Poor weather conditions can prevent the visibility of fruits images that have been curated. With image classification, it is very important that the system identifies the various features that are included in the image (Harmandeep et al., 2022).

There are several ways to detect orange fruit diseases. Some diseases have nothing to do with visible symptoms, and symptoms that appears, only appears when it is too late to act. Such cases usually require advanced analysis using a powerful microscope. In some cases, the signs are only visible in part of the electromagnetic spectrum that is invisible to the human eye (Barbedo, 2013). It has been noted most orange plant diseases cause certain symptoms in the visible spectrum. The disease can be symptomatic in different parts of the plant i.e. leaves, stems, fruits / seeds, etc. Regardless of the approach, correctly identifying the disease when it first occurs is an important step in efficient disease management. Historically, disease identification has been supported by agricultural advisory bodies or other agencies such as local plant clinics. More recently, such efforts have been further supported by taking advantage of the increasing worldwide spread of the Internet to make information available online for diagnosing diseases. Recently, the proliferation of mobile-based tools has taken advantage of historically unprecedented rapid adoption of mobile phone technology in all parts of the world. Smartphones, in particular, offer a very innovative approach to disease identification with their immense computing power, high-definition displays, and a wide range of integrated accessories such as advanced high-definition (HD) cameras. It is widely estimated that there will be 5-6 billion smartphones in the world by 2020. At the end of 2015, 69% of the world's population already had access to mobile broadband coverage, and mobile broadband penetration reached 47% in 2015, a 12-fold increase from 2007 (Harvey et al., 2017).

 This study proposes a smart agricultural product disease prediction system, taking orange fruit disease as a case study, using convolutional neural networks (CNNs), a class of deep learning algorithms specifically used for computer vision problems.

1.2 Statement of the Problem

The prediction of disease on orange fruits on the farms does not utilize all the techniques used to produce good quality oranges free from diseases. This has resulted in reduced economic profits for orange fruit farmers. Orange is an important crop grown in Nigeria and other tropical regions of the world because it is rich in vitamin C and other important nutrients. Orange fruit production has been greatly affected by diseases distorting the quality of oranges and causing economic losses for the growers. To increase the production yield of orange fruit, a Convolutional Neural Network (CNN) based approach to predict orange diseases by the use of mobile devices has been proposed, which would allow the early detection of diseases in orange fruit for quick treatment and to promote high quality orange fruit yield.

1.3     Aim and Objectives of the Study

The aim of this study is to develop a smart agricultural products disease prediction system (a case study of orange fruit) based on Convolutional Neural Network (CNN). The objectives of the study are as follows;

1. Carryout requirement analysis for the existing system.
2. Design an agricultural fruit disease prediction system using CNN algorithm.
3. Implement the designed system in objective (ii).
4. Evaluate the performance of the implemented system in objective (iii).

1.4     Significance of the Study

The study will serve as an avenue that would aid farmers and agriculturist to carry out orange fruit disease using their mobile device.

The software is also relevant in the following ways:

1. Enable easy prediction of orange fruit disease.
2. Reduce the cost of carrying out a paid farm disease inspection.
3. Reduce the time of carrying out a manual examination for orange fruit disease.

1.5     Scope of the Study

This research is limited to the prediction of orange fruit disease in orange fruits using computer vision and convolutional Neural Network on a mobile device.

1.6   Limitation of the Study

The researcher faced some limitations during the course of this research. Some of this limitations/constraint includes;

i.        Time constraint: Time factor was the major factors as the timeframe to submit the project was too short for rigorous research.

ii.       financial constraint:  Lack of adequate finance to fund the researcher as to the purchase of data to review related works online was another major setback.

1.7   Definition of Terms

AEO:             Agricultural Extension Organizations

Artificial Intelligence: It is the intelligence displayed by machines, unlike the natural intelligence shown by humans and animals.

Artificial Neural Networks: These are computer systems inspired by, but not necessarily similar to, the biological neural networks that make up animal brains. Such systems learn to perform tasks by looking at examples, usually by being programmed with any particular task or rules.

Citrus Disease:     This refers to abnormal condition in citrus that impairs its physical functions, associated with specific symptoms and signs.

Citrus: It is a tree or a genus that includes citron, lemon, lime, orange and grape fruit.

Convolutional Neural Network (CNN): Is a class of Deep Neural Networks, most commonly applied to analyzing visual imagery.

Data Argumentation:   Is use in deep learning to regularize, normalize the information on data to be trained.

Data Notation:    This is the process of labeling data to make it usable for machine learning.

Dataset: A collection of related sets of information that is composed of separate elements but can be manipulated as a unit by a computer.

Deep Learning: It is a part of broader family of machine learning model base on artificial neural networks.

Disease Detection: It is a process of determining which disease or condition explains a tree/person’s symptoms and sign. It is most often referred to as diagnosis with the medical context.

Disease Diagnosis: This can be described as the process of identifying a type of disease, condition, or injury from the signs and symptoms on the host.

Image: This refers to the optical counterpart of an object produced by an optical device (such as a lens or mirror) or an electronic device.

Machine Learning: It is the scientific study of algorithms and statistical models that computer systems use on others to perform a particular task efficiently, instead using explicit instructions based on models and inferences. It is considered a subset of artificial intelligence.

Mobile App: A mobile app or mobile application is a computer program or software application designed to run on a mobile device such as a phone-tablet or watch.

 Model: Is a description or analogy used to help visualize something that cannot be directly observed.

Multilayer Perceptron: This refers to fully connected networks, that is, each neuron in one layer is connected to all neurons in the next layer.

Orange: An orange is the fruit of various citrus fruits of the Rutaceae family. This mainly refers to citrus x sinensis, also known as sweet orange to distinguish it from the associated citrus x aurantium called bitter orange.

Pathogen:   It is a bacterium, virus, or other microorganism that can cause disease.

Perceptron: This refers to a linear classifier (binary) use in supervised learning. It helps to classify the given input data.

Pest:  Is a destructive insects or other animal that attacks crops, food, livestock etc.

Phytosanitary:   This refers to measures for the control of plant diseases especially in agricultural crops.

Pollinators: It’s an animal that transfers pollen from the stamens of flowers to the female stigma.

Software: It is a program and other operating information use by a computer system.

Tensor-Flow: Tensor flow is a free open-source data flow and differentiable programming software library for a variety of tasks. The tensor flow library is a math library that is symbolic and it is been used in machine learning applications such as neural networks.