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
E-MARKETING AND SMALL ENTERPRISE THREATS AND OPPORTUNITIES
ABSTRACT
The growth and spread of internet with an extraordinary pace over the last few decades has resulted in its increased use for mar...
THE ROLE OF NIGERIA MONEY MARKET IN SAVINGS MOBILIZATION
ABSTRACT
This research is on an issue which is of great importance to the Nigeria economy, it is on the Nigeria money ma...
THE ROLE OF PLAY-BASED LEARNING IN EARLY CHILDHOOD SOCIALIZATION
ABSTRACT: This research explored the role of play-based learning in early...
PUBLIC PERCEPTION OF THE ROLE OF MASS MEDIA IN REPORTAGE OF RECOVERED LOOTED FUNDS
Background of the Study
It is well known that corruption has a negative influence on countries all arou...
ASESSEMENT OF THE CONTRIBUTIONS OF COMMITTEE ON APPROPRIATION OF THE 8TH ASSEMBLY ON BUDGET SCRUTINY
BACKGROUND TO THE STUDY
Budgets affect all of us. As citizens, we depend on the state to provide crucial services and i...
THE CHALLENGES FACED BY COMMERCIAL VEHICLES IN ABUJA
EXCERPT FROM THE STUDY
The Federal Road Safety Corps (FRSC, 2010) in its research monograph "Road Mirror‟ found tha...
THE INFLUENCE OF REGULATORY CHANGES ON BUSINESS STRATEGIES
ABSTRACT: THE INFLUENCE OF REGULATORY CHANGES ON BUSINESS STRATEGIES
This research aim...
EPIDEMIOLOGICAL STUDIES OF SCHISTOSOMIASIS IN JOS SOUTH LOCAL GOVERNMENT AREA, PLATEAU STATE, NIGERIA
Abstract
Schistosomiasis is a helminthic disease that affect many people all over the world causing illnesses that prevent people from fa...
AVAILABILITY AND USE OF MEDICAL INFORMATION RESOURCES BY UNDERGRADUATE STUDENTS OF FACULTY OF MEDICINE, FEDERAL UNIVERSITY OF HEALTH SCIENCES, AZARE
BSTRACT
The main purpose of this st...
NURSES' ROLE IN PREVENTION OF INFANT AND UNDER-FIVE CHILD MORTALITY IN AFRICA
ABSTRACT
The under-five mortality rate remains unacceptably high with 6.3 million children dying before their fift...
