Digital Commons Network^™

A Comparative Study On Statistical And Machine Learning Forecasting Methods For An Fmcg Company, Zenah Yaser Alzubaidi

Theses

Demand forecasting has been an area of study among scholars and businessmen ever since the start of the industrial revolution and has only gained focus in recent years with the advancements in AI. Accurate forecasts are no longer a luxury, but a necessity to have for effective decisions made in planning production and marketing. Many aspects of the business depend on demand, and this is particularly true for the Fast-Moving Consumer Goods industry where the high volume and demand volatility poses a challenge for planners to generate accurate forecasts as consumer demand complexity rises. Inaccurate demand forecasts lead to multiple …

Metarec: Meta-Learning Meets Recommendation Systems, James Le

Theses

Artificial neural networks (ANNs) have recently received increasing attention as powerful modeling tools to improve the performance of recommendation systems. Meta-learning, on the other hand, is a paradigm that has re-surged in popularity within the broader machine learning community over the past several years. In this thesis, we will explore the intersection of these two domains and work on developing methods for integrating meta-learning to design more accurate and flexible recommendation systems.

In the present work, we propose a meta-learning framework for the design of collaborative filtering methods in recommendation systems, drawing from ideas, models, and solutions from modern approaches …

The Role Of Ai & Big Data In Habit Formation, Jingyu Cao

Theses

Forming habits are not easy for everyone. It requires professional methods and strong perseverance, which people usually feel hard to do by themself. However, people are eager to form good habits to have a better life.

This study aims to determine how AI & big data could help people to form habits. There are many applications on the market that already use this method to study user behavior in order to provide better service. My research has focused on how to conduct the personal plan and its effects on the action.

In this context, Marvelous is defined as the AI …

Reducing Body Contact Using Smart Mobile App And Machine Learning Soltutions, Rashed Saeed Abdulrahman Shaliya

Theses

The physical contact or the daily body interaction with people by shaking hands, using electronic and payment cards or touching objects such as devices, pens, access cards and gates, all these habits increase the proportion of spreading microbes, viruses and spread diseases among the people all over the world. This project illustrates how body contact can lead to a global disaster by spreading dangerous diseases and deadly viruses among people because of their daily dealings and routine. Analytical techniques were used to explore the relevant data and visualize how body contact increases the infection of a disease to become a …

Nature-Inspired Topology Optimization Of Recurrent Neural Networks, Abdelrahman A. Elsaid

Theses

Hand-crafting effective and efficient structures for recurrent neural networks (RNNs) is a difficult, expensive, and time-consuming process. To address this challenge, this work presents three nature-inspired (NI) algorithms for neural architecture search (NAS), introducing the subfield of nature-inspired neural architecture search (NI-NAS). These algorithms, based on ant colony optimization (ACO), progress from memory cell structure optimization, to bounded discrete-space architecture optimization, and finally to unbounded continuous-space architecture optimization. These methods were applied to real-world data sets representing challenging engineering problems, such as data from a coal-fired power plant, wind-turbine power generators, and aircraft flight data recorder (FDR) data.

Initial work …

Price Prediction And Valuation Using Data Mining In Dubai Real Estate Market, Abdulla Alhathboor

Theses

The purpose of this study is to find out the impact of data mining in predicting prices and values of real estate units in the Dubai real estate market. This market has always been one of the biggest markets in the economy of any nation worldwide and has always been considered one of the biggest indicators on the health of any economy. After the devastating crash of the world economy in 2008, many real estate projects were halted and economies are still recovering from that incident. Real estate brokers and agents found it difficult to sell any property during that …

Application Of Machine Learning Models: Stock Price Forecasting Of The Philippines' Top Six Conglomerates, Anthony Rey Llanos

Theses

The advent of digital age dramatically changed the way all aspects of commerce is conducted. From the largest multi-national conglomerates to the least small-and-medium enterprises and to the unassuming business-savvy individuals have adapted to take advantage of the benefits afforded by the resulting digital technology. Investing in, and profiting from, shares of stocks of companies listed in an organized stock exchange is one such instance. Gone are the days wherein stock investors and brokers are inseparable from their telephones to handle trades. Online platforms, powered by machine learning algorithms, have made investing in stocks not only accessible and convenient but …

Using Machine Learning Software In The Human Resource Recruiting Process For Candidates From Dubai Police Academy, Ibrahim Alkhazraji, Ali Saeed Buhaliba

Theses

Since Machine learning software explored the first recruitment software and found that utilizing technology improves their efficiency at work, speed, and makes the process easier, the use of machine learning for recruitment has become one of the major themes in human resources. In a few years, hiring top talents may lean entirely on the ability of the recruiters to automate their workflows intelligently. Over time, the function of human resource management has indeed evolved in organizations, as technology has been marveled for its greater efficiency in almost every sector. The use of Machine learning for recruiting in organizations has not …

New Methods For Deep Learning Based Real-Valued Inter-Residue Distance Prediction, Jacob Barger

Theses

Background: Much of the recent success in protein structure prediction has been a result of accurate protein contact prediction--a binary classification problem. Dozens of methods, built from various types of machine learning and deep learning algorithms, have been published over the last two decades for predicting contacts. Recently, many groups, including Google DeepMind, have demonstrated that reformulating the problem as a multi-class classification problem is a more promising direction to pursue. As an alternative approach, we recently proposed real-valued distance predictions, formulating the problem as a regression problem. The nuances of protein 3D structures make this formulation appropriate, allowing predictions …

Design Of A Comprehensive Modeling, Characterization, Rupture Risk Assessment And Visualization Pipeline For Abdominal Aortic Aneurysms, Golnaz Jalalahmadi

Theses

Abdominal aortic aneurysms (AAA) is a dilation of the abdominal aorta, typically within the infra-renal segment of the vessel that cause an expansion of at least 1.5 times the normal vessel diameter. It is becoming a leading cause of death in the United States and around the world, and consequentially, in 2009, the Society for Vascular Surgery (SVS) practice guidelines expressed the critical need to further investigate the factors associated with the risk of AAA rupture, along with potential treatment methods. For decades, the maximum diameter (Dmax) was introduced as the main parameter used to assess AAA behavior and its …

On Learning And Generalization To Solve Inverse Problem Of Electrophysiological Imaging, Sandesh Ghimire

Theses

In this dissertation, we are interested in solving a linear inverse problem: inverse electrophysiological (EP) imaging, where our objective is to computationally reconstruct personalized cardiac electrical signals based on body surface electrocardiogram (ECG) signals. EP imaging has shown promise in the diagnosis and treatment planning of cardiac dysfunctions such as atrial flutter, atrial fibrillation, ischemia, infarction and ventricular arrhythmia.

Towards this goal, we frame it as a problem of learning a function from the domain of measurements to signals. Depending upon the assumptions, we present two classes of solutions: 1) Bayesian inference in a probabilistic graphical model, 2) Learning from …

Open Set Classification For Deep Learning In Large-Scale And Continual Learning Models, Ryne Roady

Theses

Supervised classification methods often assume the train and test data distributions are the same and that all classes in the test set are present in the training set. However, deployed classifiers require the ability to recognize inputs from outside the training set as unknowns and update representations in near real-time to account for novel concepts unknown during offline training. This problem has been studied under multiple paradigms including out-of-distribution detection and open set recognition; however, for convolutional neural networks, there have been two major approaches: 1) inference methods to separate known inputs from unknown inputs and 2) feature space regularization …

Point Completion Networks And Segmentation Of 3d Mesh, Naga Durga Harish Kanamarlapudi

Theses

Deep learning has made many advancements in fields such as computer vision, natural language processing and speech processing. In autonomous driving, deep learning has made great improvements pertaining to the tasks of lane detection, steering estimation, throttle control, depth estimation, 2D and 3D object detection, object segmentation and object tracking. Understanding the 3D world is necessary for safe end-to-end self-driving. 3D point clouds provide rich 3D information, but processing point clouds is difficult since point clouds are irregular and unordered. Neural point processing methods like GraphCNN and PointNet operate on individual points for accurate classification and segmentation results. Occlusion of …

Query-Driven Global Graph Attention Model For Visual Parsing: Recognizing Handwritten And Typeset Math Formulas, Mahshad Mahdavi

Theses

We present a new visual parsing method based on standard Convolutional Neural Networks (CNNs) for handwritten and typeset mathematical formulas. The Query-Driven Global Graph Attention (QD-GGA) parser employs multi-task learning, using a single feature representation for locating, classifying, and relating symbols. QD-GGA parses formulas by first constructing a Line-Of-Sight (LOS) graph over the input primitives (e.g handwritten strokes or connected components in images). Second, class distributions for LOS nodes and edges are obtained using query-specific feature filters (i.e., attention) in a single feed-forward pass. This allows end-to-end structure learning using a joint loss over primitive node and edge class distributions. …

Smarter Simulation Placement Of Kilonova Light Curve Models For Computationally Inexpensive Surrogate Model Creation, Marko Ristic

Theses

The first detected binary neutron star merger GW170817 allowed for the simultaneous detection of gravitational and electromagnetic waves which started the era of multi-messenger astrophysics. The existence of an electromagnetic counterpart to a compact object merger allowed for a significantly deeper analysis of the merger event and much tighter resultant constraints on existing physical models of neutron stars, nuclear physics, and the Universe itself.

Multi-messenger analysis requires sophisticated source modeling. For the foreseeable future, demanding computational resource costs will result in a sparse availability of state-of-the-art neutron star merger light curve simulations. Astrophysical inference can proceed using an alternate approach …

Accessibility In User Reviews For Mobile Apps: An Automated Detection Approach, Murtaza Tamjeed

Theses

In recent years, mobile accessibility has become an important trend with the goal of allowing all users the possibility of using any app without many restrictions. Recent work demonstrated that user reviews include insights that are useful for app evolution. However, with the increase in the amount of received reviews, manually analyzing them is tedious and time-consuming, especially when searching for accessibility reviews. The goal of this thesis is to support the automated identification of accessibility in user reviews, to help practitioners in prioritizing their handling, and thus, creating more inclusive apps. Particularly, we design a model that takes as …

Exploring The Influence Of Energy Constraints On Liquid State Machines, Andrew Fountain

Theses

Biological organisms operate under severe energy constraints but are still the most powerful computational systems that we know of. In contrast, modern AI algorithms are generally implemented on power-hungry hardware resources such as GPUs, limiting their use at the edge. This work explores the application of biologically-inspired energy constraints to spiking neural networks to better understand their effects on network dynamics and learning and to gain insight into the creation of more energy-efficient AI. Energy constraints are modeled by abstracting the role of astrocytes in metabolizing glucose and regulating the activity-driven distribution of ATP molecules to “pools” of neurons and …

Antipodal Robotic Grasping Using Deep Learning, Shirin Joshi

Theses

In this work, we discuss two implementations that predict antipodal grasps for novel objects: A deep Q-learning approach and a Generative Residual Convolutional Neural Network approach. We present a deep reinforcement learning based method to solve the problem of robotic grasping using visio-motor feedback. The use of a deep learning based approach reduces the complexity caused by the use of hand-designed features. Our method uses an off-policy reinforcement learning framework to learn the grasping policy. We use the double deep Q-learning framework along with a novel Grasp-Q-Network to output grasp probabilities used to learn grasps that maximize the pick success. …

Machine-Assisted Translation By Human-In-The-Loop Crowdsourcing For Bambara, Allahsera Auguste Tapo

Theses

Language is more than a tool of conveying information; it is utilized in all aspects of our lives. Yet only a small number of languages in the 7,000 languages worldwide are highly resourced by human language technologies (HLT). Despite African languages representing over 2,000 languages, only a few African languages are highly resourced, for which there exists a considerable amount of parallel digital data.

We present a novel approach to machine translation (MT) for under-resourced languages by improving the quality of the model using a paradigm called ``humans in the Loop.''

This thesis describes the work carried out to create …

Self-Supervision Initialization For Semantic Segmentation Networks, Kenneth Alexopoulos

Theses

Convolutional neural networks excel at extracting features from signals. These features are able to be utilized for many downstream tasks. These tasks include object recognition, object detection, depth estimation, pixel level semantic segmentation, and more. These tasks can be used for applications such as autonomous driving where images captured by a camera can be used to give a detailed understanding of the scene. While these models are impressive, they can fail to generalize to new environments. This forces the cumbersome process of collecting images from multifarious environments and annotating them by hand. Annotating thousands or millions of images is both …

Integrated Framework For Data Quality And Security Evaluation On Mobile Devices, Igor Khokhlov

Theses

Data quality (DQ) is an important concept that is used in the design and employment of information, data management, decision making, and engineering systems with multiple applications already available for solving specific problems. Unfortunately, conventional approaches to DQ evaluation commonly do not pay enough attention or even ignore the security and privacy of the evaluated data. In this research, we develop a framework for the DQ evaluation of the sensor originated data acquired from smartphones, that incorporates security and privacy aspects into the DQ evaluation pipeline. The framework provides support for selecting the DQ metrics and implementing their calculus by …

Rit-Eyes: Realistic Eye Image And Video Generation For Eye Tracking Applications, Nitinraj Nair

Theses

Deep neural networks for video-based eye tracking have demonstrated resilience to noisy environments, stray reflections, and low resolution. However, to train these networks, a large number of manually annotated images are required. To alleviate the cumbersome process of manual labeling, computer graphics rendering is employed to automatically generate a large corpus of annotated eye images under various conditions. In this work, we introduce a synthetic eye image and video generation platform called RIT-Eyes that improves upon previous work by adding features such as an active deformable iris, an aspherical cornea, retinal retro-reflection, and gaze-coordinated eye-lid deformations. To demonstrate the utility …

Deep Learning For Quantitative Motion Tracking Based On Optical Coherence Tomography, Peter Abdelmalak

Theses

Optical coherence tomography (OCT) is a cross-sectional imaging modality based on low coherence light interferometry. OCT has been widely used in diagnostic ophthalmology and has found applications in other biomedical fields such as cancer detection and surgical guidance.

In the Laboratory of Biophotonics Imaging and Sensing at New Jersey Institute of Technology, we developed a unique needle OCT imager based on a single fiber probe for breast cancer imaging. The needle OCT imager with sub-millimeter diameter can be inserted into tissue for minimally invasive in situ breast imaging. OCT imaging provides spatial resolution similar to histology and has the potential …

Analysis Of Gameplay Strategies In Hearthstone: A Data Science Approach, Connor W. Watson

Theses

In recent years, games have been a popular test bed for AI research, and the presence of Collectible Card Games (CCGs) in that space is still increasing. One such CCG for both competitive/casual play and AI research is Hearthstone, a two-player adversarial game where players seeks to implement one of several gameplay strategies to defeat their opponent and decrease all of their Health points to zero. Although some open source simulators exist, some of their methodologies for simulated agents create opponents with a relatively low skill level. Using evolutionary algorithms, this thesis seeks to evolve agents with a higher skill …

Clearing The Clouds: Extracting 3d Information From Amongst The Noise, Alexander Fafard

Theses

Advancements permitting the rapid extraction of 3D point clouds from a variety of imaging modalities across the global landscape have provided a vast collection of high fidelity digital surface models. This has created a situation with unprecedented overabundance of 3D observations which greatly outstrips our current capacity to manage and infer actionable information. While years of research have removed some of the manual analysis burden for many tasks, human analysis is still a cornerstone of 3D scene exploitation. This is especially true for complex tasks which necessitate comprehension of scale, texture and contextual learning. In order to ameliorate the interpretation …

Forensic Memory Classification Using Deep Recurrent Neural Networks, Aishwarya Afzulpurkar

Theses

The goal of this project is to advance the application of machine learning frameworks and tools in the process of malware detection. Specifically, a deep neural network architecture is proposed to classify application modules as benign or malicious, using the lower level memory block patterns that make up these modules. The modules correspond to blocks of functionality within files used in kernel and OS level processes as well as user level applications. The learned model is proposed to reside in an isolated core with strict communication restrictions to achieve incorruptibility as well as efficiency, therefore providing a probabilistic memory-level view …

Ar Comic Chat, Dylan Bowald

Theses

Live speech transcription and captioning are important for the accessibility of deaf and hard of hearing individuals, especially in situations with no visible ASL translators. If live captioning is available at all, it is typically rendered in the style of closed captions on a display such as a phone screen or TV and away from the real conversation. This can potentially divide the focus of the viewer and detract from the experience. This paper proposes an investigation into an alternative, Augmented Reality driven approach to the display of these captions, using deep neural networks to compute, track and associate deep …

Identifying Performance Regression From The Commit Phase Utilizing Machine Learning Techniques, Max Mendelson

Theses

Over the lifespan of a software application, it is inevitable that changes to the source code will be made that causes unintended slowdowns in functionality. These slowdowns are referred to as performance regression. Typically projects who are particularly concerned about performance have performance testing that are run to identify if a performance regression is introduced into the code. This is difficult however due to how time consuming and resource intensive running performance tests are when trying to simulate a realistic scenario.

The study of De Oliveira et. al. (Perphecy) [4] suggests a technique to predict the likelihood that a commit …

High-Capacity Directional Graph Networks, Miguel Dominguez

Theses

Deep Neural Networks (DNN) have proven themselves to be a useful tool in many computer vision problems. One of the most popular forms of the DNN is the Convolutional Neural Network (CNN). The CNN effectively learns features on images by learning a weighted sum of local neighborhoods of pixels, creating filtered versions of the image. Point cloud analysis seems like it would benefit from this useful model. However, point clouds are much less structured than images. Many analogues to CNNs for point clouds have been proposed in the literature, but they are often much more constrained networks than the typical …

Crafting Adversarial Examples Using Particle Swarm Optimization, Rayan Mosli

Theses

Machine learning models have been found to be vulnerable to adversarial attacks that apply small perturbations to input samples to get them misclassified. Attacks that search for and apply the perturbations are performed in both white-box and black-box settings, depending on the information available to the attacker about the target. For black-box attacks, the attacker can only query the target with specially crafted inputs and observing the outputs returned by the model. These outputs are used to guide the perturbations and create adversarial examples that are then misclassified.

Current black-box attacks on API-based malware classifiers rely solely on feature insertion …