ECE 539 Final Project ANN approach to help

ECE 539 Final Project ANN approach to help manufacturing of a better car Prabhdeep Singh Virk Fall 2010

Car buying process • Read reviews, consumer reports from various news agencies. • Consider rankings provided by US News, JD Power etc. • Ask colleagues and friends for recommendation.

Good car – owner’s perspective • Exterior and interior design? • Features like acceleration, speed, fuel economy etc? • Safety features ? • Reliability ? • Overall Price ?

How to make Good car ? • Need to know what features are making it a good car. • Predict what are car consumers want and expectations? • Possible features/design responsible for high ranking. • Changes/improvements that can affect the overall ranking of car.

When expectation don’t match? • Car company loose customers due to lack of interest in their product. • Decline in sales cause catastrophic effects in terms of loosing jobs and revenue and effecting economy. • In fact failing to innovate and declining sales over past decade was two major cause of automotive industry crisis. • In this project I try to implement reverse mapping of accurately predicting the car success based on features using ANN. • Ann algorithms are proven very successful in pattern classification based problems.

Pattern Classification using ANN • Car Evaluation data from UC-Irvine data repository. • 6 Car features – Price Over all. • Buying price. • Maintenance price – Technical characteristics • • # of doors Capacity Luggage boot size Safety • 4 output classes. – – Unacceptable Acceptable Good Very good. (1210 ) ( 384 ) ( 69 ) ( 65 ) Algorithms tested: • K Nearest Neighbors • Multi-layered Precptron

K Nearest Neighbor implementation. • Tested with 1 – 15 neighbors • Increasing # of neighbors have adverse effect. # of Neighbors 1 15 Confusion Matrix 132 142 45 40 8 9 6 8 302 98 18 14 0 0 Error Rate. 28 13 1 0 0 0 40. 0463 0 0 0 0 69. 9074

Multi-layered Precptron implementation. Data Pre-processing: • Scaling input features on [-5, 5] scale. • Random train/test datasets, with fixed minimum samples(10) / class. MLP configuration: • Epochs = 1000 • Learning rate = 0. 05 • Momentum = 0. 8 • # of hidden layers = 2 • # of neurons/ hidden layer = 6 • Steepest Descent Gradient.

Results after 10 iterations: • Success Rate (%)= 90. 5093 - 95. 6019 • Mean success rate(%) = 92. 4306 • Standard Deviation(%)= 1. 4355 Resultant Confusion Matrix: 294 7 5 87 0 4 0 3 1 5 12 1 0 1 2 10

Error reflecting role of learning rate and momentum.

Conclusion • K-Nearest neighbor is ineffective due to the difference in class distribution. • MLP performed well, as long as it is trained with at least 10 samples of each class. • Feature scaling improves classification rate. • Classification rate improves with increase in neurons. • Momentum helps converging faster. • High learning rate >0. 5 case Error to oscillate. • Its possible to predict a car success ranking based on the features available.

Questions? Thank you