UWindsor Together: Student Mental Health and Remote Learning Services

MSc Thesis Defense of Raj Gadhiya:"Marijuana Intoxication Detection using Convolutional Neural Network "

Monday, January 25, 2021 - 10:00 to 12:00

SCHOOL OF COMPUTER SCIENCE 

The School of Computer Science is pleased to present… 

MSc Thesis Defense by: Raj Gadhiya 

 
Date:  Monday January 25th, 2021  
Time:  10:00 am – 12:00pm 
Reminder: If interested in attending this event, contact the Graduate Secretary at csgradinfo@uwindsor.ca
 

Abstract:  

Machine learning is a broad study of computer science widely used for data analysis and algorithms that has the ability to learn and improve by experience and training. Supervised learning, Unsupervised learning, Dimensionality reduction, Deep learning, etc are the methods offered by Machine learning. These techniques are applied in fields like medical, automotive finance, and many more. In this thesis, Convolutional neural network (CNN) which is a part of deep learning techniques is applied to identify if a person is under influence of Marijuana using changes in facial features like redness of eyes caused by smoking Marijuana. CNN is a state-of-the-art method in tasks like images classification and pattern recognition. CNN’s ability to learn from training the model using image dataset is a suitable method to be used in the problem of identifying a person’s sobriety based on facial features. The proposed methodology is divided into three components which are dataset creation for training the classification model, face detection for input and using this input for making predictions if a person is under the influence of Marijuana or not. The purpose of this thesis is to train and develop a CNN model that may be helpful implementing in vehicles in future to reduce impaired driving incidents. Impaired driving is a major criminal cause of vehicle accidents in Canada.  Impaired driving is a serious problem that puts the lives of pedestrians on the road and drivers involved in impaired driving themselves in danger. This thesis represents how CNN can be useful in this situation.   
 
Keywords:  CNN, Neural Networks, Image Classification, Machine Learning, Face Detection 
 

MSc Thesis Committee:  

Internal Reader: Dr Jianguo Lu
External Reader: Dr Dan Xiao
Advisor: Dr Dan Wu
Chair: Dr. Saeed Samet

MSc Thesis Defense Announcement

5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca