Representation Learning on Time Series with Symbolic Approximation and Deep Learning
dc.contributor.advisor | Oates, Tim | |
dc.contributor.author | Wang, Zhiguang | |
dc.contributor.department | Computer Science and Electrical Engineering | |
dc.contributor.program | Computer Science | |
dc.date.accessioned | 2019-10-11T13:42:55Z | |
dc.date.available | 2019-10-11T13:42:55Z | |
dc.date.issued | 2016-01-01 | |
dc.description.abstract | Most real-world data has a temporal component, whether it is measurements of natural (weather, sound) or man-made (stock market, robotics and even speech and language) phenomena. Analysis of temporal data has been the subject of active research for decades and is still considered to be a challenge in machine learning and data mining, due to the intrinsically structured temporal correlation. In this thesis, we propose three different novel approaches to represent and model time-series. Time-Warping SAX and Pooling SAX are two extensions of the vanilla SAX approach that is used as a symbolic representation of time series. Time-Warping SAX extracts linear temporal dependencies by building a time-delay embedding vector to construct more informative SAX words. Pooling SAX applies a non-parametric weighting scheme to extract significant variables. These are data adaptive models that achieve state-of-the-art accuracy on time-series classification problems. We also propose the Gramian Angular Field (GAF) and Markov Transition Field (MTF) as two novel approaches to encode a time-series as an image. These representations not only demonstrate potential for visual inspection by humans, but when they are combined with deep learning approaches (Convolutional Networks and Denoised Auto-encoders). They achieve state-of-the-art performance compared to other modern algorithms on classification and regression/imputation problems for different type of temporal data and trajectories. GAF and MTF are non-data adaptive approaches that allow us to learn models and extract the abstract representations supported by model-based approaches. Finally, we develop a set of exponential-form based error estimator (NRAE/NAAE) with their learning approaches (Adaptive Training) to attach the non-convex optimization problems in training deep neural networks. Both in theory and practice, they are able to achieve optimality on accuracy and robustness against outliers/noise. They provide another perspectives to debunk the non-convexity of deep learning in high dimensional learning and recurrent architectures and benefit the modeling of high-dimensional temporal data. | |
dc.genre | dissertations | |
dc.identifier | doi:10.13016/m2ht3e-cbia | |
dc.identifier.other | 11511 | |
dc.identifier.uri | http://hdl.handle.net/11603/15491 | |
dc.language | en | |
dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
dc.relation.ispartof | UMBC Theses and Dissertations Collection | |
dc.relation.ispartof | UMBC Graduate School Collection | |
dc.relation.ispartof | UMBC Student Collection | |
dc.rights | This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu | |
dc.source | Original File Name: Wang_umbc_0434D_11511.pdf | |
dc.subject | Deep Learning | |
dc.subject | Non-convex Optimization | |
dc.subject | Symbolic Aggregate Approximation | |
dc.subject | Time Series | |
dc.title | Representation Learning on Time Series with Symbolic Approximation and Deep Learning | |
dc.type | Text | |
dcterms.accessRights | Distribution Rights granted to UMBC by the author. |