openExample('fuzzy/fuzzyedgedemo')

Just paste inside the matlab terminal

1. Obtain images gradient part: filter could be sobel operator, prewit operator. Others options: imfilter, imgradientxy, imgradient

2. Values of sx and sy (standard deviation): increasing value=decreasing sensitivity=decreasing intensity

3. Values of wa, wb,wc, ba, bb and bc: can alter the intensity of detected edge because they specify the start, peak, and the end of triangle.

source:https://media.cheggcdn.com/media%2Ff33%2Ff33813b2-0da2-47ff-884e-b1fb49e78d6b%2FphpLaPvki.png

Context: Assessing the environmental impact of construction projects to ensure sustainable development.

Variables: Air quality index, noise levels, water quality, waste generation, energy consumption, proximity to protected areas.

Potential Decision Rules: Assess the overall environmental impact based on these variables to determine whether a project can proceed or needs modifications.

2. Traffic Congestion Management System

Context: Managing traffic congestion in urban areas to improve traffic flow and reduce delays.

Variables: Traffic volume, average speed, number of accidents, weather conditions, road capacity.

Potential Decision Rules: Determine the level of congestion and suggest optimal traffic management strategies such as signal timing adjustments or route diversions.

3. Crop Yield Prediction System

Context: Predicting crop yield to help farmers plan and manage their agricultural activities more effectively.

Variables: Soil quality, weather conditions, irrigation levels, pest infestation, crop type.

Potential Decision Rules: Provide yield predictions and recommend actions to optimize crop production based on the current conditions.

4. Patient Health Monitoring System

Context: Continuous monitoring and assessment of patient health in hospitals or at home to provide timely medical intervention.

Variables: Heart rate, blood pressure, blood glucose levels, oxygen saturation, temperature.

Potential Decision Rules: Assess the overall health status and generate alerts or recommendations for medical intervention if any parameter deviates from the normal range.

5. Financial Risk Assessment for Investment Portfolios

Context: Assessing the risk of investment portfolios to help investors make informed decisions.

Variables: Market volatility, asset correlation, investment horizon, economic indicators, diversification.

Potential Decision Rules: Determine the risk level of a portfolio and suggest adjustments to mitigate risk and optimize returns.

6. Employee Performance Evaluation System

Context: Evaluating employee performance to support human resource decisions such as promotions, raises, or training needs.

Variables: Task completion rate, quality of work, teamwork, attendance, innovation.

Potential Decision Rules: Assess overall performance and provide recommendations for rewards or development based on the evaluation.

7. Energy Consumption Optimization for Smart Homes

Context: Managing and optimizing energy consumption in smart homes to reduce costs and environmental impact.

Variables: Energy usage patterns, occupancy, appliance efficiency, weather conditions, time of day.

Potential Decision Rules: Suggest optimal energy usage patterns and control strategies for appliances to minimize energy consumption while maintaining comfort.

8. Predictive Maintenance System for Industrial Equipment

Context: Predicting the maintenance needs of industrial equipment to prevent breakdowns and optimize maintenance schedules.

Variables: Vibration levels, temperature, usage hours, maintenance history, operating conditions.

Potential Decision Rules: Predict the likelihood of equipment failure and recommend maintenance actions to prevent downtime.

9. Customer Satisfaction Analysis in Retail

Context: Analyzing customer satisfaction to improve service quality and customer experience in retail.

Variables: Customer feedback scores, wait time, product availability, service quality, return rates.

Potential Decision Rules: Assess overall customer satisfaction and suggest improvements in specific areas to enhance the customer experience.

10. Smart Irrigation System for Water Conservation

Context: Managing irrigation systems to optimize water use in agriculture and landscaping.

Variables: Soil moisture levels, weather forecast, plant type, water availability, evaporation rate.

Potential Decision Rules: Determine the optimal irrigation schedule to ensure plants receive adequate water while minimizing waste.

11.Medical Diagnosis Support System for Diabetes Risk Assessment

Context: Diabetes is a chronic condition that, if not managed properly, can lead to serious health complications such as heart disease, kidney failure, and vision loss.

Variables: Ages,Body Mass, Body Mass Index (BMI), Blood Pressure, Family History, Physical Activity, Fasting Blood Sugar.

1. Carol Liew Pey Xuan (79002)

2. Leong Bee Ching (79853)

3. Lim Jing Yi (79882) - Leader

4. Melissa Lee Ee Jiet (80029)

5. Soo Siew Peng (81268)

https://www.mathworks.com/help/pdf_doc/fuzzy/fuzzy_ug.pdf (page 78)

Case Study 1:

PV generation: 0.499 (low)

Power factor: 0.743 (poor)

Aggregated apparent power: 96.4 (normal)

Output: 0.403

Case study 2:

PV generation: 0.941727 (high)

Power factor: 0.634058 (high)

Aggregated apparent power: 110.87 (high)

Output: 0.708