Complete Material Cost #3,000
Order for Complete Material now
ABSTRACT
Predicting the age of fish is very necessary and much needed since all fish does not grow at the same rate. This work predicts the age of fish using artificial neural network. The prediction was based on the water temperature and the length of the fish. MATLAB 2017 was used to implement the artificial neural network. Testing and validation showed an efficiency of 90%. The research work will inevitably promote productive management in the fishery and agricultural sector of the economy.
TABLE OF CONTENTS
COVER PAGE
TITLE PAGE – – – – – – – – – i
DECLARATION – – – – – – – – – ii
CERTIFICATION – – – – – – – – – iii
DEDICATION – – – – – – – – – iv
ACKNOWLEDGEMENTS – – – – – – – v
ABSTRACT – – – – – – – – – vi
LIST OF FIGURES – – – – – – – – vii
TABLE OF CONTENTS – – – – – – – – ix
CHAPTER ONE
INTRODUCTION
1.1 BACKGROUND OF THE STUDY – – – – – 1
1.2 STATEMENT OF PROBLEM – – – – – – 2
1.3 AIM AND OBJECTIVES OF THE STUDY – – – – 3
1.4 SIGNIFICANS OF THE STUDY – – – – – 3
1.5 DEFINITION OF TERMS – – – – – – 4
CHAPTER TWO
LITERATURE REVIEW
2.1 FISHERY – – – – – – – – – 6
2.2 TYPES OF FISHERIES – – – – – – – 6
2.2.1 INLAND OR FRESH WATER FISHERIES – – – – 6
2.2.2 MARINE FISHERIES – – – – – – – 7
2.3 ECONOMIC IMPORTANCE OF FISHERY – – – 7
2.4 FISH AGE PREDICTION – – – – – – 9
2.5 AGING STRUCTURES AND TECHNIQUES – – – 10
2.6 THE ARTIFICIAL NEURAL NETWORK (ANN) – – – 13
2.6.1 TYPES OF NEURAL NETWORK – – – – – 13
2.6.2 ADVANTAGES OF ARTIFICIAL NEURAL NETWORKS – 15
2.6.3 DISADVANTAGES OF ARTIFICAL NEURAL NETWORK – 16
2.7 ARTIFICIAL NEURAL NETWORK AND FISH AGE
PREDICTION 17
2.8 FISHERY AND MACHINE LEARNING – – – – 18
CHAPTER THREE
SYSTEM ANALYSIS AND DESIGN
3.1 METHODOLOGY OF THE STUDY – – – – – 20
3.2 SYSTEM ANALYSIS – – – – – – – 20
3.3 ANALYSIS OF THE EXISTING SYSTEM – – – – 22
3.4 ANALYSIS OF THE PROPOSED SYSTEM – – – 22
3.5 SYSTEM DESIGN – – – – – – – 23
CHAPTER FOUR
SYSTEM IMPLEMENTATION
4.1 REASON FOR CHOICE OF LANGUAGE – – – – 26
4.2 DOCUMENTATION – – – – – – – 26
4.3 HARDWARE SPECIFICATION – – – – – 27
4.4 SOFTWARE SPECIFICATION – – – – – 27
4.5 SOURCE CODES – – – – – – – – 27
4.6 SAMPLE OUTPUTS – – – – – – – 28
4.7 DISCUSSION OF RESULT AND FINDINGS – – – 28
CHAPTER FIVE
SUMMARY, CONCLUSION AND RECOMMENDATION
5.1 SUMMARY – – – – – – – – 29
5.2 CONCLUSION – – – – – – – – 29
5.3 RECOMMENDATIONS – – – – – – – 30
REFERENCES – – – – – – – – 31
APPENDIX A – – – – – – – – 32
APPENDIX B – – – – – – – – 40
CHAPTER ONE
INTRODUCTION
1.1 BACKGROUND OF THE STUDY
Knowledge of fish and fish age characteristics is necessary for stock assessments and to develop management or conservation plans. Size is generally associated with age however variations can occur in size at a particular age for most fish species.
Artificial Neural Networks (ANN) unlike other computer networks are algorithms which can be used as tool to perform non-linear statistical modeling and provide a new alternative to logistic regression. The artificial neural network are flexible and non-linear models which can be used in medical and agricultural research as a tool for decision making.
Inspired by the central nervous system of humans and animals, smaller processing units (called neurons) are connected together to form a complex network which is capable of learning and adapting. This has been substantially helped by the development in computing hardware allowing us to train very large complex networks in reasonable time.
Recent developments in the area of neural network appear to be simulations and prediction in which the network uses a certain data to train the network such that errors are near zero level. The network compared to other networks have appeared to be very capable learners and readily evolving, it can create is own organization or representation of the information it receives it during learning time as knowledge of its domain are distributed across the network rather than explicitly.
The network made up of multiple processors enables faster processing and computation of solutions/results by taking in multiple unique inputs and producing one output with values modified to produce the correct and most accurate values.
1.2 STATEMENT OF PROBLEM
Fishery as a form of agriculture has derailed greatly in Nigeria amongst other West African countries from recent research. Many at times the variance in sizes and species of fishes has brought about different controversies about the maturity of fishes. These controversies have been that some fishes even though mature can still have small structures and frames leaving farmers to question the management of their enterprises and adequate measures are not properly carried out to correct this error in which fishes may die or a resultant regression in the product output of the enterprise. From research the following problems were discovered:
- The maturity of fishes was mostly guessed based on the size of fishes.
- The manual classification and estimation remained a difficult task and even experienced examiners can give inaccurate age estimation.
1.3 AIM AND OBJECTIVES OF THE STUDY
This research work is generally aimed at using statistical learning techniques (ANN) to improve and automate the process of fish age prediction.
The objectives are:
- To determine the neural network architecture for the system
- Train the Neural Network
- Demonstrate the prediction exercise by running the program
- Implement the Neural Network
1.4 SIGNIFICANCE OF THE STUDY
This research work holds its believe in the efficacy of neural network as it is being applied in the agricultural field of fishery.
The gains of this research work are as follows:
- Enhancement in the general production output of fishes
- The research will benefit fish farmers, corporate bodies into fishery and government at large.
- The research is a thought-provoking subject and will therefore open new avenues for research and create new ideas for organization, farmers to improve in their field of expertise.
- The research is of more significance to the students in the department of computer science, school of applied sciences Ken Saro-Wiwa Polytechnic, sine it serves as a partial fulfillment of the requirement for the award of National Diploma (ND) in the department of computers science.
1.5 DEFINITION OF TERMS
Architecture: The structure and design of a system or product. It is the process and the product of planning, designing and constructing structures.
Algorithm: A precise step-by-step plan for a computational procedure that begins with an impute value and yields on output value in a finite number of steps. It is a set of rules to be followed in calculate or other problem solving operations, especially by a computer.
Artificial neural network: ANN is an interconnected group of nodes, akin to the vast network of neurons in a brain. An ANN is a computational model based on the structure and functions of biological neural networks.
Fishery: Fishery is an entity engaged in raising or harvesting fish which is determined by some authority. It is the catching, processing and marketing of fish. It can also be a fishing company, a place where fish are caught and processed.
Neural network: Highly interconnected network of information processing elements that mimics the connectivity and functionality of the human brain.
Prediction: A forecast or prognosis of what will happen in the future.
Complete Material Cost #3,000
Order for Complete Material now