東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Unsupervised Learning of Low-Dimensi...

Farnoosh, Amirreza.

FindBook

Google Book

Amazon

博客來

Unsupervised Learning of Low-Dimensional Dynamical Representations from Spatiotemporal Data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Unsupervised Learning of Low-Dimensional Dynamical Representations from Spatiotemporal Data./
作者:	Farnoosh, Amirreza.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	146 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Artificial intelligence. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28719456
ISBN:	9798544281757

Unsupervised Learning of Low-Dimensional Dynamical Representations from Spatiotemporal Data.
Farnoosh, Amirreza.

Unsupervised Learning of Low-Dimensional Dynamical Representations from Spatiotemporal Data. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 146 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--Northeastern University, 2021.

This item must not be sold to any third party vendors.

Ever-improving sensing technologies offer a fast and accurate collection of large-scale spatiotemporal data, recorded from multimodal sensors of heterogeneous natures, in various application domains, ranging from medicine and biology to robotics and traffic control. In this dissertation, we propose frameworks for learning the underlying representation of these data in an unsupervised manner, tailored towards several emerging applications, namely indoor navigation and mapping, neuroscience hypothesis testing, time series forecasting, 3D motion segmentation, and human action recognition.As such, (1) we developed an unsupervised framework for real-time depth and view-angle estimation from an inertially augmented video recorded from an indoor scene by employing geometric-based machine learning and deep learning models. (2) We introduced a hierarchical deep generative factor analysis framework for temporal modeling of neuroimaging datasets. Our model approximates high dimensional data by a product between time-dependent weights and spatially-dependent factors which are in turn represented in terms of lower dimensional latents. This framework can be extended to perform clustering in the low dimensional temporal latent or perform factor analysis in the presence of a control signal. (3) We developed a deep switching dynamical system for dynamical modeling of multidimensional time-series data. Specifically, we employ a deep vector auto-regressive latent model switched by a chain of discrete latents to capture higher-order multimodal latent dependencies. This results in a flexible model that (i) provides a collection of potentially interpretable states abstracted from the process dynamics, and (ii) performs short- and long-term vector time series prediction in a complex multi-relational setting. (4) We developed a dynamical deep generative latent model for segmentation of 3D pose data over time that parses the meaningful intrinsic states in the dynamics of these data and enables a low-level dynamical generation and segmentation of skeletal movements. Our model encodes highly correlated skeletal data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We extended this model for human action recognition by decoding from these low-dimensional latents to the motion data and their associated action labels.

ISBN: 9798544281757Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

3D skeletal motion

Unsupervised Learning of Low-Dimensional Dynamical Representations from Spatiotemporal Data.
LDR:03696nmm a2200421 4500 001 2283872
005 20211115071707.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798544281757
035 $a (MiAaPQ)AAI28719456
035 $a AAI28719456
040 $a MiAaPQ $c MiAaPQ
100 1 $a Farnoosh, Amirreza. $3 3562940
245 1 0 $a Unsupervised Learning of Low-Dimensional Dynamical Representations from Spatiotemporal Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 146 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Ostadabbas, Sarah.
502 $a Thesis (Ph.D.)--Northeastern University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Ever-improving sensing technologies offer a fast and accurate collection of large-scale spatiotemporal data, recorded from multimodal sensors of heterogeneous natures, in various application domains, ranging from medicine and biology to robotics and traffic control. In this dissertation, we propose frameworks for learning the underlying representation of these data in an unsupervised manner, tailored towards several emerging applications, namely indoor navigation and mapping, neuroscience hypothesis testing, time series forecasting, 3D motion segmentation, and human action recognition.As such, (1) we developed an unsupervised framework for real-time depth and view-angle estimation from an inertially augmented video recorded from an indoor scene by employing geometric-based machine learning and deep learning models. (2) We introduced a hierarchical deep generative factor analysis framework for temporal modeling of neuroimaging datasets. Our model approximates high dimensional data by a product between time-dependent weights and spatially-dependent factors which are in turn represented in terms of lower dimensional latents. This framework can be extended to perform clustering in the low dimensional temporal latent or perform factor analysis in the presence of a control signal. (3) We developed a deep switching dynamical system for dynamical modeling of multidimensional time-series data. Specifically, we employ a deep vector auto-regressive latent model switched by a chain of discrete latents to capture higher-order multimodal latent dependencies. This results in a flexible model that (i) provides a collection of potentially interpretable states abstracted from the process dynamics, and (ii) performs short- and long-term vector time series prediction in a complex multi-relational setting. (4) We developed a dynamical deep generative latent model for segmentation of 3D pose data over time that parses the meaningful intrinsic states in the dynamics of these data and enables a low-level dynamical generation and segmentation of skeletal movements. Our model encodes highly correlated skeletal data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We extended this model for human action recognition by decoding from these low-dimensional latents to the motion data and their associated action labels.
590 $a School code: 0160.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Electrical engineering. $3 649834
650 4 $a Neurosciences. $3 588700
650 4 $a Bioinformatics. $3 553671
650 4 $a Biomechanics. $3 548685
653 $a 3D skeletal motion
653 $a Computational neuroscience
653 $a Deep generative Models
653 $a Indoor navigation
653 $a Switching dynamical Models
653 $a Variational inference
690 $a 0800
690 $a 0984
690 $a 0544
690 $a 0317
690 $a 0715
690 $a 0648
710 2 $a Northeastern University. $b Electrical and Computer Engineering. $3 1018491
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0160
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28719456