Posts

Showing posts from May, 2023

WEEK 11: FYP WORKSHOP & DATA COLLECTING AND ANALYSIS

Image
Date: 22 - 26 May 2023 Content: In week 11, I had the opportunity to participate in an online FYP workshop conducted through Microsoft Teams, which focused on Technical Paper Preparation. The workshop provided value insights into the formatting and content requirements of technical paper, as well as tips and tricks for effective presentation of research findings. This knowledge will be useful for my technical paper. Furthermore, during week 11, I dedicated my time to data collection for my Final Year Project. I gathered a comprehensive dataset consisting of 1400 images. I also got 180 dataset for length and weight value for Red Tilapia Fish provided by the Fisheries Research Institute Glami Lemi, Through my analysis, I calculated the parameters 'a' and 'b' for the Length-Weigh Relationship. The resulting calculations error rate of 1.8% indicates the high level of accuracy was achieved. Conclusion: In conclusion, week 11 marked significant progress in my Final Year Proj...

WEEK 10: GET MATERIAL/COMPONENTS FOR FYP & VISIT FRI

Image
Date: 15 - 19 May 2023 Content: During week 10, I focused on acquiring essential materials and components needed for my Final Year Project (FYP) such as an aquarium, water pump, camera, and other necessary equipment. In addition on May 18th, I had the opportunity to visit the Fisheries Research Institute Glami Lemi, Jelebu, Negeri Sembilan, Malaysia. At there, I presented my updated progress regarding my final year project. The institute generously provided fish for a demonstration day, allowing me to conduct experiments and collect data. They also supplied me with materials like anti chlorine to maintain water quality and fish food to ensure the well-being of the fish throughout the project. Conclusion: Overall, week 10 was dedicated to procuring the necessary materials for my FYP. The visit to the Fisheries Research Institute was a valuable opportunity for me. With these resources in place, I am well-prepared to move forward with my project, conducting experiments and collecting dat...

WEEK 9: LENGTH-WEIGHT RELATIONSHIP

Date: 8 - 12 May 2023 Content: In my Final Year Project (FYP), one of the objectives is to estimate the weight of fish based on their length. Thanks to Dr. Haslawati Baharuddin, one of the researchers at Fisheries Research Institute Malaysia, she suggested that to uses and implementing Length-Weight Relationship to my project. In week 9, I started delved into the Length-Weight Relationship, which is represented by the formula W = a * L ^ b, where weight (W) of a fish based on its length (L), with 'a' and 'b' being parameters specific to the fish species. I also explored the application of Length-Weight Relationship in fisheries management and analyzed it strengths and limitations to ensure that this formula suitable for my project. Conclusion: Overall, week 9 was focused on understanding the Length-Weight Relationship and its relevance in fisheries management. Through my learning, I explored the formula factors influencing the relationship between weight and length of ...

WEEK 8: TRY DIFFERENT OBJECT DETECTION METHOD & LEARN DEEP LEARNING FOR COMPUTER VISION

Image
Date: 1 - 5 May 2023 Content: In week 8, I was focused on expanding my knowledge of deep learning for computer vision and finding a suitable alternative for object detection in my Final Year Project (FYP). I learned machine learning basics, classification metrics, neural networks, gradient descent, Keras, MNIST dataset and convolutional neural networks.  In this week 8, I encountered some challenges with the 'Detecto' library, as its detection speed did not meet the real-time requirements of my project. As a result, I explored new method on object detection called 'Yolov5' known for its speed to detecting object and I utilized 'Roboflow' annotation tool to support the training process. Conclusion: Overall, week 8 involved a deep dive into deep learning for computer vision. Furthermore, I made an important decision to shift from 'Detecto' to 'Yolov5' object detection method due to its improved speed. Appendix: Figure below shows the output for fi...