Browsing by Discipline
Now showing items 21-40 of 46
-
Exploration of contrastive learning strategies toward more robust stance detection systems
(2023)Stance Detection, in general, is the task of identifying the author’s position on controversial topics. In Natural Language Processing, Stance Detection extracts the author’s attitude from the text written toward an issue ... -
Extracting specific text from documents using machine learning algorithms
(2018)Increasing use of Portable Document Format (PDF) files has promoted research in analyzing the files' layout for text extraction purpose. For this reason, it is important to have a system in place to analyze these documents ... -
Feature learning boosts network performance
(2020)Features are an important part of machine learning. Features are often the reduced-dimensional representation of input data, feature calculation, extraction, and fusion directly affect the final result of the network. ... -
Federated learning framework and energy disaggregation techniques for residential energy management
(2023)Residential energy use is a significant part of total power usage in developed countries. To reduce overall energy use and save funds, these countries need solutions that help them keep track of how different appliances ... -
From social media to expert reports: automatically validating and extending complex conceptual models using machine learning approaches
(2019)Given the importance of developing accurate models of any complex system, the modeling process often seeks to be comprehensive by including experts and community members. While many qualitative modeling processes can ... -
Hybrid deep learning with stacked dilated causal convolutions for health forecasting using multivariate time-series data
(2022)Health forecasting using time-series data facilitates preventive medicine and healthcare interventions by predicting future health events. This thesis introduces a novel hybrid deep-learning architecture for health ... -
Identifying variables affecting students' academic performance among engineering students
(2018)An essential consideration for campus administrators and faculty members is that students complete their degree with good academic grades. Being able to predict factors affecting students performance is necessary to help ... -
Improving cataract surgery procedure using machine learning and thick data analysis
(2023)Cataract surgery is one of the most frequent and safe Surgical operations are done globally, with approximately 16 million surgeries conducted each year. The entire operation is carried out under microscopical ... -
Lightweight deep learning for monocular depth estimation
(2021)Monocular depth estimation is a challenging but significant part of computer vision with many applications in other areas of study. This estimation method aims to provide a relative depth prediction for a single input ... -
Medical workflow design and planning using Node-Red data fusion
(2021)The space of clinical planning requires a complex arrangement of information, often not capable of being captured in a singular dataset. As a result, data fusion techniques can be used to combine multiple data sources ... -
Multi-timeframe algorithmic trading bots using thick data heuristics with deep reinforcement learning
(2022)This thesis presents an augmented Artificial Intelligence (AI) algorithmic trading approach that combines Thick Data Heuristics (TDH), with Deep Reinforcement Learning (DRL), to successfully learn trading execution timing ... -
Online sequential learning with non-iterative strategy for feature extraction, classification and data augmentation
(2020)Network aims to optimize for minimizing the cost function and provide better performance. This experimental optimization procedure is widely recognized as gradient descent, which is a form of iterative learning that starts ... -
Optimization of hospital emergency department
(2021)This thesis is centered around the topic of emergency department(ED) optimization. Working in conjunction with the Thunder Bay Regional Health Sciences Centre a simulation model was developed to determine an optimal ... -
Permissioned blockchains for real world applications
(2020)Blockchain technology, even though relatively new, has evolved rapidly in the past 12 years. Bitcoin’s underlying technology - the first blockchain - was a public, permissionless, and completely decentralized network ... -
Placements of virtual network functions for effective network functions virtualization
(2019)In the future wireless networks, network function virtualization will lay the foun- dation for establishing a new resource management framework to e ciently utilize network resources. The rst part of this thesis deals ... -
Quantifying the impact of Twitter activity in political battlegrounds
(2022)It may be challenging to determine the reach of the information, how well it corresponds with the domain design, and how to utilize it as a communication medium when utilizing social media platforms, notably Twitter, to ... -
A role and attribute based encryption approach to privacy and security in cloud based health services
(2012-11-10)Cloud computing is a rapidly emerging computing paradigm which replaces static and expensive data centers, network and software infrastructure with dynamically scalable “cloud based” services offered by third party providers ... -
Semantic similarity between words and sentences using lexical database and word embeddings
(2018)Calculating the semantic similarity between sentences is a long-standing problem in the area of natural language processing. The semantic analysis field has a crucial role to play in the research related to the text ... -
Semi-supervised framework for clustering and semantic segmentation
(2021)During the past couple of decades, machine learning and deep learning methods have achieved remarkable results in many real-world applications. However, it is difficult to develop and train these artificial intelligence ... -
Surface estimation from multi-modal tactile data
(2021)The increasing popularity of Robotic applications has seen use in healthcare, surgery, and as an industrial tool. These robots are expected to be able to make physical contact with the objects in the environment which ...
