Posts

Showing posts from June, 2023

WEEK 13: PRESENTATION AND DEMONSTRATION DAY

Image
Date: 5 - 9 June 2023 Content: In week 13, excitement filled the air as the much-anticipated presentation day drew near. With all the necessary preparations in place, including the printing of my project poster, the final touches were finish. The long-awaited day arrived on Wednesday, 7th June, and I was arriving early to signing up and setting up my booth. During presentation, I was being assessed by Ts. Dr. Ismail Adam, from Electronic Technology section lecture, and Dr. Haslawati Baharuddin, a representative from the Fisheries Research Institute. I delivered a detailed and comprehensive pitch, hoping to capture their interest and convey the importance of my project. The response to my presentation was positive, with Dr. Haslawati Baharuddin even engaging in a discussion about my project afterwards, indicating her interest and further validating the value of my work. Conclusion: In conclusion, week 13 was an important milestone as it marked the presentation day for my Final Year Pro...

WEEK 12: FYP WORKSHOP & MODEL TRAINING AND FINISHING MY PROJECT

Image
Date: 29 - 31 May/1 - 2 June 2023 Content: During week 12, I participated in an online FYP workshop conducted through Microsoft Teams, focusing on claim and documentation for the Final Year Project (FYP). The workshop provided valuable guidance on documenting the claim, progress report and the process of uploading related documents. This workshop equipped me with the necessary knowledge to ensure proper documentation of my FYP. Simultaneously, I dedicated time to model training using the YOLOv5 framework. Although initially achieving satisfactory results with precision and recall above 70%, I encountered an issue where the model misidentified the background as fish. To overcome this challenge, I transitioned to YOLOv8, an upgraded version of the YOLO model. The training results with YOLOv8 surpassed expectations, getting precision and recall rates exceeding 90%. With the highly accurate model, I proceeded to develop a Fish Measurement System using Computer Vision techniques, allowing ...