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 5000
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
COINAGES IN NIGERIA ENGLISH: A SOCIOLINGUISTIC PERSPECTIVE
ABSTRACT
Nigerian English coinages have been widely investigated in different literatures ranging from studies in Socio...
THE IMPACT OF ADMINISTRATIVE SKILLS TRAINING ON ORGANIZATIONAL SUCCESS
THE IMPACT OF ADMINISTRATIVE SKILLS TRAINING ON ORGANIZATIONAL SUCCESS
Abstract: This...
A Critical Analysis of Business Process Reengineering in Improving Operational Efficiency: A Case Study of Logistics Companies in Taraba State
Background of the Study
Business Process Reengineering (BPR) involves the radical rede...
FARM POWER SOURCES AND UTILIZATION IN ENUGU STATE
BACKGROUND OF STUDY
Power is required to develop and execute the activities involved in agricultural pr...
Design and Implementation of AI-Based Automated University Clearance Systems in Kebbi State University of Science and Technology, Aliero, Kebbi State
Background of the Study
University clearance is a crucial administrative process that ensures students fulfill all the necessary requirem...
An Investigation of the Effectiveness of Competency-Based Education in Nursing Training in Nasarawa State College of Health Sciences
Background of the Study
Competency-based education (CBE) has emerged as an effective approach in nursing education, focusing on the demon...
An Examination of Nurses' Knowledge and Compliance with Cardiopulmonary Resuscitation (CPR) Protocols in Ahmadu Bello University Teaching Hospital, Zaria
Background of the Study
Cardiopulmonary resuscitation (CPR) is a critical lifesaving procedure used in emergencies to re...
The role of adult education in equipping retirees with financial planning skills in Lokoja Local Government Area, Kogi State
Background of the Study
The evolving economic landscape has necessitated the adoption of financial planning skills, especi...
THE EFFECT OF LABORATORY METHOD OF TEACHING MATHEMATICS ON THE ACHIEVEMENT OF JSS2 STUDENTS
Abstract
The study focused on the effect of the laboratory method of teaching on the achievement of J.SS II students in...
An Investigation into the Challenges of Implementing Maternal and Child Health Policies in Kwara State
Background of the Study
Maternal and child health (MCH) policies are designed to improve the health outcomes of mother...
