Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Computer Sciences (19)
- Engineering (9)
- Artificial Intelligence and Robotics (6)
- Mathematics (3)
- Applied Mathematics (2)
-
- Applied Statistics (2)
- Bioimaging and Biomedical Optics (2)
- Biomedical Engineering and Bioengineering (2)
- Data Science (2)
- Databases and Information Systems (2)
- Electrical and Computer Engineering (2)
- Statistics and Probability (2)
- Aviation (1)
- Business (1)
- Controls and Control Theory (1)
- Earth Sciences (1)
- Electrical and Electronics (1)
- Geographic Information Sciences (1)
- Geography (1)
- Geology (1)
- Health Information Technology (1)
- Human Resources Management (1)
- Longitudinal Data Analysis and Time Series (1)
- Management and Operations (1)
- Medicine and Health Sciences (1)
- Numerical Analysis and Computation (1)
- Other Electrical and Computer Engineering (1)
- Other Mathematics (1)
- Paleontology (1)
- Institution
Articles 1 - 25 of 25
Full-Text Articles in Physical Sciences and Mathematics
Deep Learning In Indus Valley Script Digitization, Deva Munikanta Reddy Atturu
Deep Learning In Indus Valley Script Digitization, Deva Munikanta Reddy Atturu
Theses and Dissertations
This research introduces ASR-net(Ancient Script Recognition), a groundbreaking system that automatically digitizes ancient Indus seals by converting them into coded text, similar to Optical Character Recognition for modern languages. ASR-net, with an 95% success rate in identifying individual symbols, aims to address the crucial need for automated techniques in deciphering the enigmatic Indus script. Initially Yolov3 is utilized to create the bounding boxes around each graphemes present in the Indus Valley Seal. In addition to that we created M-net(Mahadevan) model to encode the graphemes. Beyond digitization, the paper proposes a new research challenge called the Motif Identification Problem (MIP) related …
Variational Bias Sampling For Collaborative Filtering Recommender Systems, Prisca Stephens
Variational Bias Sampling For Collaborative Filtering Recommender Systems, Prisca Stephens
Theses and Dissertations
Advancements in digitalization has yielded enormous growth of data on online platforms, overwhelming users with multitude of options to choose from. Recommender systems narrow down these options to a few relevant ones thereby facilitating the decision-making processes for users. This study presents a framework for integrating variational bias sampling into model-based collaborative filtering techniques for recommender systems. Variational bias sampling is a novel and unique way to account for random factors that affect explicit ratings in collaborative filtering recommender systems. A Gaussian distribution is used to model all the possible random factors that could affect ratings. Sampling user and item …
Representation Learning For Generative Models With Applications To Healthcare, Astronautics, And Aviation, Van Minh Nguyen
Representation Learning For Generative Models With Applications To Healthcare, Astronautics, And Aviation, Van Minh Nguyen
Theses and Dissertations
This dissertation explores applications of representation learning and generative models to challenges in healthcare, astronautics, and aviation.
The first part investigates the use of Generative Adversarial Networks (GANs) to synthesize realistic electronic health record (EHR) data. An initial attempt at training a GAN on the MIMIC-IV dataset encountered stability and convergence issues, motivating a deeper study of 1-Lipschitz regularization techniques for Auxiliary Classifier GANs (AC-GANs). An extensive ablation study on the CIFAR-10 dataset found that Spectral Normalization is key for AC-GAN stability and performance, while Weight Clipping fails to converge without Spectral Normalization. Analysis of the training dynamics provided further …
Countnet3d: A 3d Computer Vision Approach To Infer Counts Of Occluded Objects With Quantified Uncertainty, Stephen W. Nelson
Countnet3d: A 3d Computer Vision Approach To Infer Counts Of Occluded Objects With Quantified Uncertainty, Stephen W. Nelson
Theses and Dissertations
3D scene understanding is an important problem that has experienced great progress in recent years, in large part due to the development of state-of-the-art methods for 3D object detection. However, the performance of 3D object detectors can suffer in scenarios where extreme occlusion of objects is present, or the number of object classes is large. In this paper, we study the problem of inferring 3D counts from densely packed scenes with heterogeneous objects. This problem has applications to important tasks such as inventory management or automatic crop yield estimation. We propose a novel regression-based method, CountNet3D, that uses mature 2D …
Invading The Integrity Of Deep Learning (Dl) Models Using Lsb Perturbation & Pixel Manipulation, Ashraful Tauhid
Invading The Integrity Of Deep Learning (Dl) Models Using Lsb Perturbation & Pixel Manipulation, Ashraful Tauhid
Theses and Dissertations
The use of deep learning (DL) models for solving classification and recognition-related problems are expanding at an exponential rate. However, these models are computationally expensive both in terms of time and resources. This imposes an entry barrier for low-profile businesses and scientific research projects with limited resources. Therefore, many organizations prefer to use fully outsourced trained models, cloud computing services, pre-trained models are available for download and transfer learning. This ubiquitous adoption of DL has unlocked numerous opportunities but has also brought forth potential threats to its prospects. Among the security threats, backdoor attacks and adversarial attacks have emerged as …
Extending The Convolution In Graph Neural Networks To Solve Materials Science And Node Classification Problems, Steph-Yves Mike Louis
Extending The Convolution In Graph Neural Networks To Solve Materials Science And Node Classification Problems, Steph-Yves Mike Louis
Theses and Dissertations
The usage of graph to represent one's data in machine learning has grown in popularity in both academia and the industry due to its inherent benefits. With its flexible nature and immediate translation to real life observed objects, graph representation had a considerable contribution in advancing the state-of-the-art performance of machine learning in materials.
In this dissertation proposal, we discuss how machines can learn from graph encoded data and provide excellent results through graph neural networks (GNN). Notably, we focus our adaptation of graph neural networks on three tasks: predicting crystal materials properties, nullifying the negative impact of inferior graph …
Predicting Material Structures And Properties Using Deep Learning And Machine Learning Algorithms, Yuqi Song
Predicting Material Structures And Properties Using Deep Learning And Machine Learning Algorithms, Yuqi Song
Theses and Dissertations
Discovering new materials and understanding their crystal structures and chemical properties are critical tasks in the material sciences. Although computational methodologies such as Density Functional Theory (DFT), provide a convenient means for calculating certain properties of materials or predicting crystal structures when combined with search algorithms, DFT is computationally too demanding for structure prediction and property calculation for most material families, especially for those materials with a large number of atoms. This dissertation aims to address this limitation by developing novel deep learning and machine learning algorithms for effective prediction of material crystal structures and properties. Our data-driven machine learning …
Using Deep Learning For Encrypted Traffic Analysis Of Amazon Echo, Surendra Pathak
Using Deep Learning For Encrypted Traffic Analysis Of Amazon Echo, Surendra Pathak
Theses and Dissertations
The adoption of the Amazon Echo family of devices in modern homes has become very widespread at the current time, with hundreds of millions of devices sold. Moreover, the global smart speaker market size is growing vigorously and is projected to continue to bigger. Smart speakers allow users hands-free interaction by allowing voice control, promoting human-computer interaction to greater avenues. Though smart speaker can be useful assistant, it has some serious security concerns that need to be studied. In this study, an analysis of the security and privacy concerns of smart speakers is presented along with a passive attack, namely …
Image-Based Cancer Diagnosis Using Novel Deep Neural Networks, Hosein Barzekar
Image-Based Cancer Diagnosis Using Novel Deep Neural Networks, Hosein Barzekar
Theses and Dissertations
Cancer is the major cause of death in many nations. This serious illness can only be effectivelytreated if it is diagnosed early. In contrast, biomedical imaging presents challenges to both clinical institutions and researchers. Physiological anomalies are often characterized by modest modifications in individual cells or tissues, making them difficult to detect visually. Physiological anomalies are often characterized by slight abnormalities in individual cells or tissues, making them difficult to detect visually. Traditionally, anomalies are diagnosed by radiologists and pathologists with extensive training. This procedure, however, demands the participation of professionals and incurs a substantial expense, making the classification of …
Novel Deep Neural Network For Medical Image Classification, Dm Anisuzzaman
Novel Deep Neural Network For Medical Image Classification, Dm Anisuzzaman
Theses and Dissertations
Medical image classification is an essential part of diagnosis, which with automation may benefit both physicians and patients in terms of time and cost. For automation, different Artificial intelligence (AI) methods, including Machine Learning (ML) and Deep Learning (DL), are used widely. Specifically, DL algorithms have become popular in classifying medical images due to their propensity for good performance. This thesis studies medical image classification problems using deep learning models. Four specific medical applications are considered: (1) Osteosarcoma cancer classification in histological images, (2) Burn wound classification, (3) Wound severity classification from clinical images, and (4) Wound type classification using …
An Empirical Study On Sampling Approaches For 3d Image Classification Using Deep Learning, Nicholas Michelette
An Empirical Study On Sampling Approaches For 3d Image Classification Using Deep Learning, Nicholas Michelette
Theses and Dissertations
A 3D classification method requires more training data than a 2D image classification method to achieve good performance. These training data usually come in the form of multiple 2D images (e.g., slices in a CT scan) or point clouds (e.g., 3D CAD modeling) for volumetric object representation. The amount of data required to complete this higher dimension problem comes with the cost of requiring more processing time and space. This problem can be mitigated with data size reduction (i.e., sampling). In this thesis, we empirically study and compare the classification performance and deep learning training time of PointNet utilizing uniform …
Terrestrial Perspective On The Formation, Evolution, And Detection Of Zeolites In Lacustrine Environments On Early Mars, Gayantha Roshana Loku Kodikara
Terrestrial Perspective On The Formation, Evolution, And Detection Of Zeolites In Lacustrine Environments On Early Mars, Gayantha Roshana Loku Kodikara
Theses and Dissertations
This study evaluates the possible formation and evolution mechanisms of zeolites on early Mars with possible explanations for their limited detections using Earth analogs. This study focuses on the formation of zeolites in the closed basin lakes where the largest relatively pure concentrations of natural zeolites are found on Earth. Five working hypotheses were formulated to explore the limited detection of zeolites in closed basin lakes on Mars and different styles of scientific reasoning with suitable examples were used to test the independent, converging lines of inquiry. Zeolites may not be identifiable in certain locations on Mars using orbital data …
Deep Learning Based Generative Materials Design, Yong Zhao
Deep Learning Based Generative Materials Design, Yong Zhao
Theses and Dissertations
Discovery of novel functional materials is playing an increasingly important role in many key industries such as lithium batteries for electric vehicles and cell phones. However experimental tinkering of existing materials or Density Functional Theory (DFT) based screening of known crystal structures, two of the major current materials design approaches, are both severely constrained by the limited scale (around 250,000 in ICSD database) and diversity of existing materials and the lack of a sufficient number of materials with annotated properties. How to generate a large number of physically feasible, stable, and synthesizable crystal materials and build accurate property prediction models …
Smart City Management Using Machine Learning Techniques, Mostafa Zaman
Smart City Management Using Machine Learning Techniques, Mostafa Zaman
Theses and Dissertations
In response to the growing urban population, "smart cities" are designed to improve people's quality of life by implementing cutting-edge technologies. The concept of a "smart city" refers to an effort to enhance a city's residents' economic and environmental well-being via implementing a centralized management system. With the use of sensors and actuators, smart cities can collect massive amounts of data, which can improve people's quality of life and design cities' services. Although smart cities contain vast amounts of data, only a percentage is used due to the noise and variety of the data sources. Information and communication technology (ICT) …
A Deep Recurrent Neural Network With Iterative Optimization For Inverse Image Processing Applications, Masaki Ikuta
A Deep Recurrent Neural Network With Iterative Optimization For Inverse Image Processing Applications, Masaki Ikuta
Theses and Dissertations
Many algorithms and methods have been proposed for inverse image processing applications, such as super-resolution, image de-noising, and image reconstruction, particularly with the recent surge of interest in machine learning and deep learning methods.
As for Computed Tomography (CT) image reconstruction, the most recently proposed methods are limited to image domain processing, where deep learning is used to learn the mapping between a true image data set and a noisy image data set in the image domain. While deep learning-based methods can produce higher quality images than conventional model-based algorithms, these methods have a limitation. Deep learning-based methods used in …
A Machine Learning Pipeline With Switching Algorithms To Predict Lung Cancer And Identify Top Features, Anika Tasnim
A Machine Learning Pipeline With Switching Algorithms To Predict Lung Cancer And Identify Top Features, Anika Tasnim
Theses and Dissertations
Lung cancer is the leading cause of cancer-related death around the world. Early detection is a critical factor for its effective treatment. To facilitate early-stage prediction, a Machine Learning (ML) pipeline has been built that uses inpatient admission data to train four ML models. The data is dynamically loaded into a database, cleaned, and passed through the SelectKBest selector to identify the top features influencing the prognosis, which are then fed into the pipeline and fitted to the ML models to make the forecast. Among the models used, Decision Tree provides the highest accuracy (97.09%), followed by Random Forest (94.07%). …
Medical Image Segmentation Using Machine Learning, Masoud Khani
Medical Image Segmentation Using Machine Learning, Masoud Khani
Theses and Dissertations
Image segmentation is the most crucial step in image processing and analysis. It can divide an image into meaningfully descriptive components or pathological structures. The result of the image division helps analyze images and classify objects. Therefore, getting the most accurate segmented image is essential, especially in medical images. Segmentation methods can be divided into three categories: manual, semiautomatic, and automatic. Manual is the most general and straightforward approach. Manual segmentation is not only time-consuming but also is imprecise. However, automatic image segmentation techniques, such as thresholding and edge detection, are not accurate in the presence of artifacts like noise …
Prediction Of Concurrent Hypertensive Disorders In Pregnancy And Gestational Diabetes Mellitus Using Machine Learning Techniques, Mary Ejiwale
Theses and Dissertations
Gestational diabetes mellitus and hypertensive disorders in pregnancy are serious maternal health conditions with immediate and lifelong mother-child health consequences. These obstetric pathologies have been widely investigated, but mostly in silos, while studies focusing on their simultaneous occurrence rarely exist. This is especially the case in the machine learning domain. This retrospective study sought to investigate, construct, evaluate, compare, and isolate a supervised machine learning predictive model for the binary classification of co-occurring gestational diabetes mellitus and hypertensive disorders in pregnancy in a cohort of otherwise healthy pregnant women. To accomplish the stated aims, this study analyzed an extract (n=4624, …
Deep Learning Based Sound Event Detection And Classification, Alireza Nasiri
Deep Learning Based Sound Event Detection And Classification, Alireza Nasiri
Theses and Dissertations
Hearing sense has an important role in our daily lives. During the recent years, there has been many studies to transfer this capability to the computers. In this dissertation, we design and implement deep learning based algorithms to improve the ability of the computers in recognizing the different sound events.
In the first topic, we investigate sound event detection, which identifies the time boundaries of the sound events in addition to the type of the events. For sound event detection, we propose a new method, AudioMask, to benefit from the object-detection techniques in computer vision. In this method, we convert …
Improving Space Efficiency Of Deep Neural Networks, Aliakbar Panahi
Improving Space Efficiency Of Deep Neural Networks, Aliakbar Panahi
Theses and Dissertations
Language models employ a very large number of trainable parameters. Despite being highly overparameterized, these networks often achieve good out-of-sample test performance on the original task and easily fine-tune to related tasks. Recent observations involving, for example, intrinsic dimension of the objective landscape and the lottery ticket hypothesis, indicate that often training actively involves only a small fraction of the parameter space. Thus, a question remains how large a parameter space needs to be in the first place — the evidence from recent work on model compression, parameter sharing, factorized representations, and knowledge distillation increasingly shows that models can be …
Deep Learning-Based Object Detection In Wound Images, Yash Patel
Deep Learning-Based Object Detection In Wound Images, Yash Patel
Theses and Dissertations
Developing a deep neural network for wound localization was the first step towards an efficient and fully automated wound healing system. A wound localizer was developed in this research using the YOLOv3 model, and an iOS mobile app was also created with the developed localization algorithm. The developed system can detect the wound and its surrounding tissue and isolate the portion of the localized wound for future care. This will support the segmentation and classification of wound by eliminating a lot of redundant details from photos of wound. A lighter variant of YOLOv3 called tiny-YOLOv3 is used for mobile device …
Conceptualization And Application Of Deep Learning And Applied Statistics For Flight Plan Recommendation, Nicholas C. Forrest
Conceptualization And Application Of Deep Learning And Applied Statistics For Flight Plan Recommendation, Nicholas C. Forrest
Theses and Dissertations
The Air Forces Pilot Training Next (PTN) program seeks a more efficient pilot training environment emphasizing the use of virtual reality flight simulators alongside periodic real aircraft experience. The PTN program wants to accelerate the training pace and progress in undergraduate pilot training compared to traditional undergraduate pilot training. Currently, instructor pilots spend excessive time planning and scheduling flights. This research focuses on methods to auto-generate the planning of in-flight events using hybrid filtering and deep learning techniques. The resulting approach captures temporal trends of user-specific and program-wide student performance to recommend a feasible set of graded flight events for …
Insider’S Misuse Detection: From Hidden Markov Model To Deep Learning, Ahmed Saaudi
Insider’S Misuse Detection: From Hidden Markov Model To Deep Learning, Ahmed Saaudi
Theses and Dissertations
Malicious insiders increasingly affect organizations by leaking classified data to unautho- rized entities. Detecting insiders’ misuses in computer systems is a challenging problem. In this dissertation, we propose two approaches to detect such threats: a probabilistic graph- ical model-based approach and a deep learning-based approach. We investigate the logs of computer-based activities to discover patterns of misuse. We model user’s behaviors as sequences of computer-based events.
For our probabilistic graphical model-based approach, we propose an unsupervised model for insider’s misuse detection. That is, we develop Stochastic Gradient Descent method to learn Hidden Markov Models (SGD-HMM) with the goal of analyzing …
Sequential Survival Analysis With Deep Learning, Seth William Glazier
Sequential Survival Analysis With Deep Learning, Seth William Glazier
Theses and Dissertations
Survival Analysis is the collection of statistical techniques used to model the time of occurrence, i.e. survival time, of an event of interest such as death, marriage, the lifespan of a consumer product or the onset of a disease. Traditional survival analysis methods rely on assumptions that make it difficult, if not impossible to learn complex non-linear relationships between the covariates and survival time that is inherent in many real world applications. We first demonstrate that a recurrent neural network (RNN) is better suited to model problems with non-linear dependencies in synthetic time-dependent and non-time-dependent experiments.
Deep Learning: An Exposition, Ryan Kingery
Deep Learning: An Exposition, Ryan Kingery
Theses and Dissertations
In this paper we describe and survey the field of deep learning, a type of machine learning that has seen tremendous growth and popularity over the past decade for its ability to substantially outperform other learning methods at important tasks. We focus on the problem of supervised learning with feedforward neural networks. After describing what these are we give an overview of the essential algorithms of deep learning, backpropagation and stochastic gradient descent. We then survey some of the issues that occur when applying deep learning in practice. Last, we conclude with an important application of deep learning to the …