Computer Sciences Commons^™

Improving Treatment Of Local Liver Ablation Therapy With Deep Learning And Biomechanical Modeling, Brian Anderson, Kristy Brock, Laurence Court, Carlos Eduardo Cardenas, Erik Cressman, Ankit Patel

Dissertations and Theses (Open Access)

In the United States, colorectal cancer is the third most diagnosed cancer, and 60-70% of patients will develop liver metastasis. While surgical liver resection of metastasis is the standard of care for treatment with curative intent, it is only avai lable to about 20% of patients. For patients who are not surgical candidates, local percutaneous ablation therapy (PTA) has been shown to have a similar 5-year overall survival rate. However, PTA can be a challenging procedure, largely due to spatial uncertainties in the localization of the ablation probe, and in measuring the delivered ablation margin.

For this work, we hypothesized …

Unveiling The Mystery Of Api Evolution In Deep Learning Frameworks: A Case Study Of Tensorflow 2, Zejun Zhang, Yanming Yang, Xin Xia, David Lo, Xiaoxue Ren, John C. Grundy

Research Collection School Of Computing and Information Systems

API developers have been working hard to evolve APIs to provide more simple, powerful, and robust API libraries. Although API evolution has been studied for multiple domains, such as Web and Android development, API evolution for deep learning frameworks has not yet been studied. It is not very clear how and why APIs evolve in deep learning frameworks, and yet these are being more and more heavily used in industry. To fill this gap, we conduct a large-scale and in-depth study on the API evolution of Tensorflow 2, which is currently the most popular deep learning framework. We first extract …

Robot: Robustness-Oriented Testing For Deep Learning Systems, Jingyi Wang, Jialuo Chen, Youcheng Sun, Xingjun Ma, Dongxia Wang, Jun Sun, Peng Cheng

Research Collection School Of Computing and Information Systems

Recently, there has been a significant growth of interest in applying software engineering techniques for the quality assurance of deep learning (DL) systems. One popular direction is deep learning testing, where adversarial examples (a.k.a. bugs) of DL systems are found either by fuzzing or guided search with the help of certain testing metrics. However, recent studies have revealed that the commonly used neuron coverage metrics by existing DL testing approaches are not correlated to model robustness. It is also not an effective measurement on the confidence of the model robustness after testing. In this work, we address this gap by …

Defect Detection In Atomic Resolution Transmission Electron Microscopy Images Using Machine Learning, Philip Cho, Aihua W. Wood, Krishnamurthy Mahalingam, Kurt Eyink

Faculty Publications

Point defects play a fundamental role in the discovery of new materials due to their strong influence on material properties and behavior. At present, imaging techniques based on transmission electron microscopy (TEM) are widely employed for characterizing point defects in materials. However, current methods for defect detection predominantly involve visual inspection of TEM images, which is laborious and poses difficulties in materials where defect related contrast is weak or ambiguous. Recent efforts to develop machine learning methods for the detection of point defects in TEM images have focused on supervised methods that require labeled training data that is generated via …

The Whole Is Greater Than Its Parts: Ensembling Improves Protein Contact Prediction, Wendy M. Billings, Connor J. Morris, Dennis Della Corte

Faculty Publications

The prediction of amino acid contacts from protein sequence is an important problem, as protein contacts are a vital step towards the prediction of folded protein structures. We propose that a powerful concept from deep learning, called ensembling, can increase the accuracy of protein contact predictions by combining the outputs of different neural network models. We show that ensembling the predictions made by different groups at the recent Critical Assessment of Protein Structure Prediction (CASP13) outperforms all individual groups. Further, we show that contacts derived from the distance predictions of three additional deep neural networks—AlphaFold, trRosetta, and ProSPr—can be substantially …

Bibliometric Analysis Of Named Entity Recognition For Chemoinformatics And Biomedical Information Extraction Of Ovarian Cancer, Vijayshri Khedkar, Charlotte Fernandes, Devshi Desai, Mansi R, Gurunath Chavan Dr, Sonali Tidke Dr., M. Karthikeyan Dr.

Library Philosophy and Practice (e-journal)

With the massive amount of data that has been generated in the form of unstructured text documents, Biomedical Named Entity Recognition (BioNER) is becoming increasingly important in the field of biomedical research. Since currently there does not exist any automatic archiving of the obtained results, a lot of this information remains hidden in the textual details and is not easily accessible for further analysis. Hence, text mining methods and natural language processing techniques are used for the extraction of information from such publications.Named entity recognition, is a subtask that comes under information extraction that focuses on finding and categorizing specific …

Breaking Neural Reasoning Architectures With Metamorphic Relation-Based Adversarial Examples, Alvin Chan, Lei Ma, Felix Juefei-Xu, Yew-Soon Ong, Xiaofei Xie, Minhui Xue, Yang Liu

Research Collection School Of Computing and Information Systems

The ability to read, reason, and infer lies at the heart of neural reasoning architectures. After all, the ability to perform logical reasoning over language remains a coveted goal of Artificial Intelligence. To this end, models such as the Turing-complete differentiable neural computer (DNC) boast of real logical reasoning capabilities, along with the ability to reason beyond simple surface-level matching. In this brief, we propose the first probe into DNC's logical reasoning capabilities with a focus on text-based question answering (QA). More concretely, we propose a conceptually simple but effective adversarial attack based on metamorphic relations. Our proposed adversarial attack …

Deep Learning Based Models For Classification From Natural Language Processing To Computer Vision, Xianshan Qu

Theses and Dissertations

With the availability of large scale data sets, researchers in many different areas such as natural language processing, computer vision, recommender systems have started making use of deep learning models and have achieved great progress in recent years. In this dissertation, we study three important classification problems based on deep learning models.

First, with the fast growth of e-commerce, more people choose to purchase products online and browse reviews before making decisions. It is essential to build a model to identify helpful reviews automatically. Our work is inspired by the observation that a customer's expectation of a review can be …

Detecting The Intent Of Email Using Embeddings, Deep Learning And Transfer Learning, Zaid Alibadi

Theses and Dissertations

Throughout the years' several strategies and tools were proposed and developed to help the users cope with the problem of email overload, but each of these solutions had its own limitations and, in some cases, contribute to further problems. One major theme that encapsulates many of these solutions is automatically classifying emails into predefined categories (ex: Finance, Sport, Promotion, etc.) then move/tag the incoming email to that particular category. In general, these solutions have two main limitations: 1) they need to adapt to changing user’s behavior. 2) they require handcrafted features engineering which in turn need a lot of time, …

Automatic Detection Of Vehicles In Satellite Images For Economic Monitoring, Cole Hill

USF Tampa Graduate Theses and Dissertations

With the growing supply of satellites capturing images of the planet, governments andinvestors are looking for ways in which these new images may be used to determine which businesses are struggling and thriving. Recent works have shown that parking lot fill rates can provide valuable information about businesses’ earnings, however, the task of manually annotating the number of vehicles in a parking lot is expensive and time-consuming. Systems which can automate this process are therefore valuable as they are faster and cheaper than human labor. In this thesis, the problem of detection of small objects in large low-resolution images is …

Hybrid Deep Learning Architecture To Forecast Maximum Load Duration Using Time-Of-Use Pricing Plans, Jinseok Kim, Babar Shah, Ki Il Kim

All Works

Load forecasting has received crucial research attention to reduce peak load and contribute to the stability of power grid using machine learning or deep learning models. Especially, we need the adequate model to forecast the maximum load duration based on time-of-use, which is the electricity usage fare policy in order to achieve the goals such as peak load reduction in a power grid. However, the existing single machine learning or deep learning forecasting cannot easily avoid overfitting. Moreover, a majority of the ensemble or hybrid models do not achieve optimal results for forecasting the maximum load duration based on time-of-use. …

Network Traffic Anomaly Detection Method For Imbalanced Data, Shuqin Dong, Bin Zhang

Journal of System Simulation

Abstract: Aiming at the poor detection performances caused by the low feature extraction accuracy of rare traffic attacks from scarce samples, a network traffic anomaly detection method for imbalanced data is proposed. A traffic anomaly detection model is designed, in which the traffic features in different feature spaces are learned by alternating activation functions, architectures, corrupted rates and dropout rates of stacked denoising autoencoder (SDA), and the low accuracy in extracting features of rare traffic attacks in a single space is solved. A batch normalization algorithm is designed, and the Adam algorithm is adopted to train parameters of …

On-Device Deep Learning Inference For System-On-Chip (Soc) Architectures, Tom Springer, Elia Eiroa-Lledo, Elizabeth Stevens, Erik Linstead

Engineering Faculty Articles and Research

As machine learning becomes ubiquitous, the need to deploy models on real-time, embedded systems will become increasingly critical. This is especially true for deep learning solutions, whose large models pose interesting challenges for target architectures at the “edge” that are resource-constrained. The realization of machine learning, and deep learning, is being driven by the availability of specialized hardware, such as system-on-chip solutions, which provide some alleviation of constraints. Equally important, however, are the operating systems that run on this hardware, and specifically the ability to leverage commercial real-time operating systems which, unlike general purpose operating systems such as Linux, can …

Wider Vision: Enriching Convolutional Neural Networks Via Alignment To External Knowledge Bases, Xuehao Liu, Sarah Jane Delany, Susan Mckeever

Conference papers

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of hidden feature map activations is limited by the discriminative knowledge gleaned during training. The aim of our work is to explain and expand CNNs models via the mirroring or alignment of the network to an external knowledge base. This will allow us to give a semantic context or label for each visual feature. Using the resultant aligned embedding space, we can match CNN feature activations to nodes …

Wg2An: Synthetic Wound Image Generation Using Generative Adversarial Network, Salih Sarp, Murat Kuzlu, Emmanuel Wilson, Ozgur Guler

Engineering Technology Faculty Publications

In part due to its ability to mimic any data distribution, Generative Adversarial Network (GAN) algorithms have been successfully applied to many applications, such as data augmentation, text-to-image translation, image-to-image translation, and image inpainting. Learning from data without crafting loss functions for each application provides broader applicability of the GAN algorithm. Medical image synthesis is also another field that the GAN algorithm has great potential to assist clinician training. This paper proposes a synthetic wound image generation model based on GAN architecture to increase the quality of clinical training. The proposed model is trained on chronic wound datasets with various …

Unsupervised Clustering Of Rf-Fingerprinting Features Derived From Deep Learning Based Recognition Models, Christian T. Potts

Theses and Dissertations

RF-Fingerprinting is focus of machine learning research which aims to characterize wireless communication devices based on their physical hardware characteristics. It is a promising avenue for improving wireless communication security in the PHY layer. The bulk of research presented to date in this field is focused on the development of features and classifiers using both traditional supervised machine learning models as well as deep learning. This research aims to expand on existing RF-Fingerprinting work by approaching the problem through the lens of an unsupervised clustering problem. To that end this research proposes a deep learning model and training methodology to …

Privacy-Preserving Federated Deep Learning With Irregular Users, Guowen Xu, Hongwei Li, Yun Zhang, Shengmin Xu, Jianting Ning, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated deep learning has been widely used in various fields. To protect data privacy, many privacy-preserving approaches have also been designed and implemented in various scenarios. However, existing works rarely consider a fundamental issue that the data shared by certain users (called irregular users) may be of low quality. Obviously, in a federated training process, data shared by many irregular users may impair the training accuracy, or worse, lead to the uselessness of the final model. In this paper, we propose PPFDL, a Privacy-Preserving Federated Deep Learning framework with irregular users. In specific, we design a novel solution to reduce …

Addressing Artificial Intelligence Bias In Retinal Diagnostics, Philippe Burlina, Neil Joshi, William Paul, Katia D Pacheco, Neil M Bressler

Faculty, Staff and Students Publications

PURPOSE: This study evaluated generative methods to potentially mitigate artificial intelligence (AI) bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance or domain generalization, which occurs when deep learning systems (DLSs) face concepts at test/inference time they were not initially trained on.

METHODS: The public domain Kaggle EyePACS dataset (88,692 fundi and 44,346 individuals, originally diverse for ethnicity) was modified by adding clinician-annotated labels and constructing an artificial scenario of data imbalance and domain generalization by disallowing training (but not testing) exemplars for images of retinas with DR warranting referral (DR-referable) from darker-skin individuals, who presumably have greater …

An Exploratory Study On The Introduction And Removal Of Different Types Of Technical Debt In Deep Learning Frameworks, Jiakun Liu, Qiao Huang, Xin Xia, Emad Shihab, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

To complete tasks faster, developers often have to sacrifice the quality of the software. Such compromised practice results in the increasing burden to developers in future development. The metaphor, technical debt, describes such practice. Prior research has illustrated the negative impact of technical debt, and many researchers investigated how developers deal with a certain type of technical debt. However, few studies focused on the removal of different types of technical debt in practice. To fill this gap, we use the introduction and removal of different types of self-admitted technical debt (i.e., SATD) in 7 deep learning frameworks as an example. …

Deep Learning For Multi-Tissue Cancer Classification Of Gene Expressions, Tarek Khorshed

Theses and Dissertations

We contribute in saving the lives of cancer patients through early detection and diagnosis, since one of the major challenges in cancer treatment is that patients are diagnosed at very late stages when appropriate medical interventions become less effective and full curative treatment is no longer achievable. Cancer classification using gene expressions is extremely challenging given the complexity and high dimensionality of the data. Current classification methods typically rely on samples collected from a single tissue type and perform a prerequisite of gene feature selection to avoid processing the full set of genes. These methods fall short in taking advantage …

Deep Learning For Task-Based Image Quality Assessment In Medical Imaging, Weimin Zhou

McKelvey School of Engineering Graduate Student Theses & Dissertations

It has been advocated to use objective measures of image quality (IQ) for assessing and optimizing medical imaging systems. Objective measures of IQ quantify the performance of an observer at a specific diagnostic task. Binary signal detection tasks and joint signal detection and localization (detection-localization) tasks are commonly considered in medical imaging. When optimizing imaging systems for binary signal detection tasks, the performance of the Bayesian Ideal Observer (IO) has been advocated for use as a figure-of-merit (FOM). The IO maximizes the observer performance that is summarized by the receiver operating characteristic (ROC) curve. When signal detection-localization tasks are considered, …

Multi-Modal Classification Using Images And Text, Stuart J. Miller, Justin Howard, Paul Adams, Mel Schwan, Robert Slater

SMU Data Science Review

This paper proposes a method for the integration of natural language understanding in image classification to improve classification accuracy by making use of associated metadata. Traditionally, only image features have been used in the classification process; however, metadata accompanies images from many sources. This study implemented a multi-modal image classification model that combines convolutional methods with natural language understanding of descriptions, titles, and tags to improve image classification. The novelty of this approach was to learn from additional external features associated with the images using natural language understanding with transfer learning. It was found that the combination of ResNet-50 image …

A Computational Approach Within Medical Research, Ryan Christopher Hogan

Theses and Dissertations

Within the context of medical image diagnosis, we explore novel computational models to facilitate the detection of two medical conditions that burden our society. In particular, this research focuses on the use of deep learning models for the detection of Alzheimer’s Disease in Magnetic Resonance images (MRI) scans, as well as the detection of heart arrhythmias from electrocardiogram (ECG) recordings. We propose a novel architecture that depends on the 3D-CNN model to classify between MRI scans of cognitively healthy individuals and AD patients. Moreover, we explore the use of LSTM deep learning models to detect abnormal heart arrhythmias that present …

Evaluating The Performance Of Transformer Architecture Over Attention Architecture On Image Captioning, Deepti Balasubramaniam

Dissertations

Over the last few decades computer vision and Natural Language processing has shown tremendous improvement in different tasks such as image captioning, video captioning, machine translation etc using deep learning models. However, there were not much researches related to image captioning based on transformers and how it outperforms other models that were implemented for image captioning. In this study will be designing a simple encoder-decoder model, attention model and transformer model for image captioning using Flickr8K dataset where will be discussing about the hyperparameters of the model, type of pre-trained model used and how long the model has been trained. …

Adaptive Two-Stage Edge-Centric Architecture For Deeply-Learned Embedded Real-Time Target Classification In Aerospace Sense-And-Avoidance Applications, Nicholas A. Speranza

Browse all Theses and Dissertations

With the growing number of Unmanned Aircraft Systems, current network-centric architectures present limitations in meeting real-time and time-critical requirements. Current methods utilizing centralized off-platform processing have inherent energy inefficiencies, scalability challenges, performance concerns, and cyber vulnerabilities. In this dissertation, an adaptive, two-stage, energy-efficient, edge-centric architecture is proposed to address these limitations. A novel, edge-centric Sense-and-Avoidance architecture framework is presented, and a corresponding prototype is developed using commercial hardware to validate the proposed architecture. Instead of a network-centric approach, processing is distributed at the logical edge of the sensors, and organized as Detection and Classification Subsystems. Classical machine vision algorithms are …

Utilizing Resonant Scattering Signal Characteristics Via Deep Learning For Improvedclassification Of Complex Targets, Tuğçe Toprak, Mustafa Alper Selver, Mustafa Seçmen, Emi̇ne Yeşi̇m Zoral

Turkish Journal of Electrical Engineering and Computer Sciences

Object classification using late-time resonant scattering electromagnetic signals is a significant problem found in different areas of application. Due to their unique properties, spherical objects play an essential role in this field both as a challenging target and a resource of analytical late-time resonant scattering electromagnetic signals. Although many studies focus on their detailed analysis, the challenges associated with target classification by resonant late-time resonant scattering electromagnetic signals from multilayer spheres have not been investigated in detail. Moreover, existing studies made the simplifying assumption that the objects having (one or more) layers constitute equal permeability values at the core and …

Reliable And Interpretable Machine Learning For Modeling Physical And Cyber Systems, Daniel L. Marino Lizarazo

Theses and Dissertations

Over the past decade, Machine Learning (ML) research has predominantly focused on building extremely complex models in order to improve predictive performance. The idea was that performance can be improved by adding complexity to the models. This approach proved to be successful in creating models that can approximate highly complex relationships while taking advantage of large datasets. However, this approach led to extremely complex black-box models that lack reliability and are difficult to interpret. By lack of reliability, we specifically refer to the lack of consistent (unpredictable) behavior in situations outside the training data. Lack of interpretability refers to the …

Deep Learning Techniques Of Losses In Data Transmitted In Wirelesssensor Networks, Mevlüt Ersoy, Beki̇r Aksoy

Turkish Journal of Electrical Engineering and Computer Sciences

Wireless sensor network (WSN) systems are frequently used today as a result of rapid technological developments. Wireless sensor networks, which form the basis of the Internet of Things (IoT), have a wide range of use in theworld from education to health, and from military applications to home applications. It enables the data obtained fromthe sensors to be transferred between nodes with the help of end-to-end wireless protocols. In parallel with the increasingnumber of nodes in WSN, data tra?ic density also increases. Due to the limitations of the WSN network, lost packetrates also increase with increasing data tra?ic. In this study, …

Image Source Identification Using Convolutional Neural Networks In Iot Environment, Yan Wang, Qindong Sun, Dongzhu Rong, Shancang Li, Li Da Xu

Information Technology & Decision Sciences Faculty Publications

Digital image forensics is a key branch of digital forensics that based on forensic analysis of image authenticity and image content. The advances in new techniques, such as smart devices, Internet of Things (IoT), artificial images, and social networks, make forensic image analysis play an increasing role in a wide range of criminal case investigation. This work focuses on image source identification by analysing both the fingerprints of digital devices and images in IoT environment. A new convolutional neural network (CNN) method is proposed to identify the source devices that token an image in social IoT environment. The experimental results …

Neural Relation Extraction: A Review, Mehmet Aydar, Özge Bozal, Furkan Özbay

Turkish Journal of Electrical Engineering and Computer Sciences

Neural relation extraction discovers semantic relations between entities from unstructured text using deeplearning methods. In this study, we make a clear categorization of the existing relation extraction methods in termsof data expressiveness and data supervision, and present a comprehensive and comparative review. We describe theevaluation methodologies and the datasets used for model assessment. We explicitly state the common challenges inrelation extraction task and point out the potential of the pretrained models to solve them. Accordingly, we investigateadditional research directions and improvement ideas in this field.