Search
Now showing items 1-10 of 32
The World Trade Web: using network analysis and machine learning as tools for public policy decision-making
(2020-11-01)
The World Trade Web (WTW) contains a wealth of information that upon rigorous analysis can aid governments in public policy decision-making. In my attempt to provide this valuable input, this dissertation uses two main ...
Polymorphic Adversarial DDoS attack on IDS using GAN
(2020-12-01)
IDS are essential components in preventing malicious traffic from penetrating networks. IDS have been rapidly enhancing their detection ability using ML algorithms. As a result, attackers look for new methods to evade the ...
Achieving real-time video summarization on commodity hardware
(2018-04-01)
We present a system for automatic video summarization which is able to operate in
real-time on commodity hardware. This is achieved by performing segmentation
to divide a video into a series of small video clips, which are ...
Characterizing the potential energy surface of two dimensional and bulk materials using high dimensional neural network potentials
(2018-08-01)
Computing material properties at the ab-initio level of detail is computationally prohibitive for large systems or long timescales. As a result, such methods cannot be used to efficiently sample configuration space. Force ...
Perpetually playing physics
(2019-08-01)
Here we discuss ideas of reinforcement learning and the importance of various aspects of it. We show how reinforcement learning methods based on genetic algorithms can be used to reproduce thermodynamic cycles without prior ...
Application-specific transfer learning over edge networks
(2021-11-01)
Transfer learning uses a profound labeled set of data from the source domain to deal with a similar problem for the target domain. Transfer learning provides accurate decision- making when insufficient data samples are ...
Machine learning classifiers for critical cardiac conditions
(2016-04-01)
Cardiac diseases are one of the leading causes of death in Canada. Current methods of diagnosing cardiac conditions require a manual and visual analysis of ECG and heart rate (RR interval) data. In this thesis, novel ...
Machine learning classification techniques for non-intrusive load monitoring
(2016-10-01)
Non-intrusive load monitoring is the concept of determining the operational loads using
single-point sensing. The features contained within the electrical load’s signal are used to identify
a unique signature which is ...
Time-efficient offloading and execution of machine learning tasks between embedded systems and fog nodes
(2019-12-01)
As embedded systems become more prominent in society, it is important that the technologies that run on them must be used efficiently. One such technology is the Neural Network (NN). NN's, combined with the Internet of ...
Predicting Bitcoin: a robust model for predicting Bitcoin price directions based on network influencers
(2016-10-01)
The ability to predict financial markets has tremendous potential to limit exposure
to risk and provide better assurances of annualized gains. In this thesis, a
model for predicting the future daily price of Bitcoin is ...