GROUP ASSIGNMENT CI by Nurul Syuhadah

Group Member Name & Matric

aylingaming13 — 2024-06-21 05:54:58 UTC

Mudhiah Nur Jannah Binti Fyros (80167)

Nisa Zamnery Lurong (81955)

Fatin Nurshafiqah Binti Zulkefli (79419)

Erni Siregar Binti Mulia (79337)

Aiza Azlin Binti Kahlik (81628)

Nurul Syuhadah Binti Masturi (80909)

MatLab Task Distribution

aylingaming13 — 2024-06-21 06:05:26 UTC

PART A (20%):

Develop a fuzzy expert system using MATLAB® software.

1)Mudhiah Nur Jannah Binti Fyros (80167)

2)Aiza Azlin Binti Kahlik (81628)

3) Fatin Nurshafiqah Binti Zulkefli (79419)

PART B (10%):

Develop a Fuzzy logic image processing system to detect edges in an image.

1)Nisa Zamnery Lurong (81955)

2)Erni Siregar Binti Mulia (79337)

3)Nurul Syuhadah Binti Masturi (80909)

Report Task Distribution

aylingaming13 — 2024-06-21 06:06:27 UTC

Introduction:

Part A:

Part B: Nurul Syuhadah Binti Masturi (80909)

Conclusion:

Appendix:

Question

aylingaming13 — 2024-06-21 06:14:07 UTC

What are the advantages and limitations of using the Mamdani and Sugeno inference systems in rainfall prediction?

Question

aylingaming13 — 2024-06-21 06:15:16 UTC

How can you visualize and interpret the fuzzy logic surface plots to understand the relationship between inputs and outputs?

Question

aylingaming13 — 2024-06-21 06:15:40 UTC

What are the emerging trends in fuzzy logic research that could be applied to further improve rainfall prediction models?

Question

aylingaming13 — 2024-06-21 06:16:12 UTC

How can the results of the fuzzy logic rainfall prediction model be communicated to non-technical stakeholders?

Project Kickoff at Petary

aylingaming13 — 2024-06-21 06:25:52 UTC

Topic Selection

We agreed to focus on implementing fuzzy logic to enhance the accuracy and reliability of rainfall prediction in Malaysia. This decision was motivated by the potential benefits of fuzzy logic in handling the inherent uncertainty and imprecision of meteorological data.

Second Meeting

aylingaming13 — 2024-06-21 06:28:58 UTC

The purpose of the second meeting is to documenting the design and implementation steps ensures clarity and transparency in the development process of the fuzzy logic model.

The steps involve in here is outlining the overall structure of the fuzzy logic model and document the chosen fuzzy membership functions for each input variable.

Parameter Tuning

aylingaming13 — 2024-06-21 06:38:30 UTC

Fine-tuning the parameters of the fuzzy logic model, such as membership function shapes and rule base adjustments, to improve prediction accuracy.

Challenge: Iterative testing and validation processes are often required to optimize the model, which can be time-consuming and resource-intensive.

Model Complexity

aylingaming13 — 2024-06-21 06:39:23 UTC

Designing and implementing complex fuzzy membership functions and rules that accurately represent the non-linear relationships between weather variables and rainfall.

Challenge: Balancing model complexity with computational efficiency especially when dealing with large datasets and multiple input variables.

Part B (output)

nsyuhadah225_ — 2024-06-22 19:59:32 UTC

The image effectively demonstrates the steps involved in grayscale conversion and fuzzy edge detection, showcasing the transition from a detailed color image to a simplified grayscale representation and finally to an edge-highlighted output.