Browsing by Subject "Recommender System"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Computational Sleep Science: Machine Learning for the Detection, Diagnosis, and Treatment of Sleep Problems from Wearable Device Data
    (2017-12) Sathyanarayana, Aarti
    This thesis is motivated by the rapid increase in global life expectancy without the respective improvements in quality of life. I propose several novel machine learning and data mining methodologies for approaching a paramount component of quality of life, the translational science field of sleep research. Inadequate sleep negatively affects both mental and physical well-being, and exacerbates many non-communicable health problems such as diabetes, depression, cancer and obesity. Taking advantage of the ubiquitous adoption of wearable devices, I create algorithmic solutions to analyse sensor data. The goal is to improve the quality of life of wearable device users, as well as provide clinical insights and tools for sleep researchers and care-providers. Chapter 1 is the introduction. This section substantiates the timely relevance of sleep research for today's society, and its contribution towards improved global health. It covers the history of sleep science technology and identifies core computing challenges in the field. The scope of the thesis is established and an approach is articulated. Useful definitions, sleep domain terminology, and some pre-processing steps are defined. Lastly, an outline for the remainder of the thesis is included. Chapter 2 dives into my proposed methodology for widespread screening of sleep disorders. It surveys results from the application of several statistical and data mining methods. It also introduces my novel deep learning architecture optimized for the unique dimensionality and nature of wearable device data. Chapter 3 focuses on the diagnosis stage of the sleep science process. I introduce a human activity recognition algorithm called RAHAR, Robust Automated Human Activity Recognition. This algorithm is unique in a number of ways, including its objective of annotating a behavioural time series with exertion levels rather than activity type. Chapter 4 focuses on the last step of the sleep science process, therapy. I define a pipeline to identify \textit{behavioural recipes}. These \textit{recipes} are the target behaviour that a user should complete in order to have good quality sleep. This work provides the foundation for building out a dynamic real-time recommender system for wearable device users, or a clinically administered cognitive behavioural therapy program. Chapter 5 summarizes the impact of this body of work, and takes a look into next steps. This chapter concludes my thesis.
  • Thumbnail Image
    Item
    A Personalized Recommender System with Correlation Estimation
    (2018-05) Yang, Fan
    Recommender systems aim to predict users’ ratings on items and suggest certain items to users that they are most likely to be interested in. Recent years there has been a lot of interest in developing recommender systems, especially personalized recommender systems to efficiently provide personalized services and increase conversion rates in commerce. Personalized recommender systems identify every individual’s preferences through analyzing users’ behavior, and sometimes also analyzing user and item feature information. Existing recommender system methods typically ignore the correlations between ratings given by a user. However, based on our observation the correlations can be strong. We propose a new personalized recommender system method that takes into account the correlation structure of ratings by a user. General precision matrices are estimated for the ratings of each user and clustered among users by supervised clustering. Moreover, in the proposed model we utilize user and item feature information, such as the demographic information of users and genres of movies. Individual preferences are estimated and grouped over users and items to find similar individuals that are close in nature. Computationally, we designed an algorithm applying the difference of convex method and the alternating direction method of multipliers to deal with the nonconvexity of the loss function and the fusion type penalty respectively. Theoretical rate of convergence is investigated for our new method. We also show theoretically that incorporating the correlation structure gives higher asymptotic efficiency of the estimators compared to ignoring it. Both simulation studies and Movielens data indicate that our method outperforms existing competitive recommender system methods.