Improving Deep Representations by Incorporating Domain Knowledge and Modularization for Synthetic Aperture Radar and Physiological Data
- Project Research
- 1-5 Chapters
- Abstract : Available
- Table of Content: Available
- Reference Style: APA
- Recommended for : Student Researchers
- NGN 3000
Abstract
Machine Learning (ML) using Artificial Neural Networks (ANNs), referred to as Deep Learning (DL), is a very popular and powerful method of statistical inference. A primary advantage of deep-learning has been the automatic learning of informative features (that encodes the data referred to as deep-representations henceforth) based on gradient-descent optimization of an objective function. While DL is applicable to problem domains where hand-crafted features are not readily available, its performance is critically dependent on other factors like dataset size and model architecture. Despite recent advances in the field, the question of how to modify the DL framework to incorporate domain knowledge or to disentangle factors of variation warrants more research. Until recently, most popular works in the DL literature have primarily employed inductive-bias of architectures (e.g., translational invariance in convolutional neural-nets) and relied on the availability of large labeled datasets for improved representation learning. Unfortunately, curating such large datasets is costly and not practical for many application areas. In this dissertation, we study methods to improve learned representations by incorporating domain knowledge into the learning process and through disentangling factors of variation. First, we present a sparse-modeling based data augmentation method for tomographic images and use it to incorporate domain knowledge of Synthetic Aperture ii Radar (SAR) target phenomenology into deep representations. We validate the improvements in learned representations by using them for a benchmark classification problem of Automatic Target Recognition (ATR) where we establish new state-of-theart on subsampled datasets. Second, we propose a DL-based hierarchical modeling strategy for a physiological signal generation process which in turn can be used for data augmentation. Based on the physiology of cardiovascular system function, we propose a modularized hierarchical generative model and then impose explicit regularizing constraints on each module using multi-objective loss functions. This generative model, called CardioGen, is evaluated by its ability to augment real data while training DL based models. The proposed approach showed performance improvements. Third, we propose a hierarchical deep-generative model for SAR imagery that jointly captures the underlying structure of multiple resolutions of SAR images. We utilize this model, called MrSARP, to super-resolve lower resolution magnitude images to a higher resolution. We evaluate the model’s performance using the three standard error metrics used for evaluating super-resolution performance on simulated data. Fourth, we propose a framework for learning a sufficient statistic of the data for a given downstream inference task. We design and train a DL model that encodes the Photoplethysmography (PPG) signal to a sufficient statistic and decodes it back to a task-specific PPG-like signal assuming it will be used for a fixed RR-tachogram prediction task. Compression and privacy-preservation can be a useful side-benefit of having such a downstream task. The learned deep representations of PPG data are validated using tachogram prediction error as well as its performance on the sub-task of stress estimation. i
Related Project Materials
THE INFLUENCE OF INFORMATION SYSTEMS ON BUSINESS INNOVATION
THE INFLUENCE OF INFORMATION SYSTEMS ON BUSINESS INNOVATION
Abstract: This study aimed to investi...
EXTRACTION AND STABILIZATION OF ALOE VERA GEL FROM THE PLANT
-
INTRODUCTION
Aloe vera (Aloe barbadensis miller) is a perennial plant of
EFFECT OF WORKING CAPITAL MANAGEMENT ON FINANCIAL PERFORMANCE ON MANUFACTURING FIRMS
ABSTRACT
In this research work titled “Effect of working capital management on financial performa...
THE EFFECT OF GRAPHICS ON THE PRINT MEDIA
Abstract
The study examined the Effect of Graphics on the Print Media using Osun Defender newspaper as a case study. How...
FAMILY INSTABILITY IMPLICATION FOR CHILD UPBRINGING
Abstract
The topic of this study is the cause of family instability and its effects on children in Umuchiatu Obe, Nkanu...
THE ROLE OF ELECTRONIC BANKING IN DEVELOPMENT OF BANKING INDUSTRIES IN NIGERIA. (A CASE STUDY OF GUARANTY TRUST BANK PLC OGUI ROAD, ENUGU)
ABSTRACT
The primary aim of this project tilted role of electronic banking in the development of banking industries in N...
THE IMPACT OF THE MASS MEDIA ON RURAL DEVELOPMENT
ABSTRACT
The broad objective of this study is to examine the impact of the mass media on rural...
THE EFFECT OF TEACHERS’ STRESS ON STUDENTS’ ACADEMIC PERFORMANCE IN SOME SELECTED SCHOOLS
ABSTRACT
The study examined the influence of teachers’ stress on the academic performance of students in selec...
ASSESSMENT ON THE EFFECT OF EMPLOYER-EMPLOYEE OFFICE RELATIONSHIP ON THE PRODUCTIVITY OF AN ORGANIZATION.
ABSTRACT
This study was carried out to examine the effect of employer-employee office relationship on t...
IMMUNOCYTOCHEMICAL AND MOLECULAR ANALYSIS OF LIQUID-BASED CERVICAL CYTOLOGY SPECIMENS IN AHMADU BELLO UNIVERSITY TEACHING HOSPITAL ZARIA, NORTHERN NIGERIA
ABSTRACT
Cervical cancer is a common and important public health problem for adult women in developing countries. Many industrialized cou...
