Physical Sciences and Mathematics Commons^™

Comparing Machine Learning Techniques With State-Of-The-Art Parametric Prediction Models For Predicting Soybean Traits, Susweta Ray

Department of Statistics: Dissertations, Theses, and Student Work

Soybean is a significant source of protein and oil, and also widely used as animal feed. Thus, developing lines that are superior in terms of yield, protein and oil content is important to feed the ever-growing population. As opposed to the high-cost phenotyping, genotyping is both cost and time efficient for breeders while evaluating new lines in different environments (location-year combinations) can be costly. Several Genomic prediction (GP) methods have been developed to use the marker and environment data effectively to predict the yield or other relevant phenotypic traits of crops. Our study compares a conventional GP method (GBLUP), a …

Contrastive Learning For Unsupervised Auditory Texture Models, Christina Trexler

Computer Science and Computer Engineering Undergraduate Honors Theses

Sounds with a high level of stationarity, also known as sound textures, have perceptually relevant features which can be captured by stimulus-computable models. This makes texture-like sounds, such as those made by rain, wind, and fire, an appealing test case for understanding the underlying mechanisms of auditory recognition. Previous auditory texture models typically measured statistics from auditory filter bank representations, and the statistics they used were somewhat ad-hoc, hand-engineered through a process of trial and error. Here, we investigate whether a better auditory texture representation can be obtained via contrastive learning, taking advantage of the stationarity of auditory textures to …

Neurolkh: Combining Deep Learning Model With Lin-Kernighan-Helsgaun Heuristic For Solving The Traveling Salesman Problem, Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

We present NeuroLKH, a novel algorithm that combines deep learning with the strong traditional heuristic Lin-Kernighan-Helsgaun (LKH) for solving Traveling Salesman Problem. Specifically, we train a Sparse Graph Network (SGN) with supervised learning for edge scores and unsupervised learning for node penalties, both of which are critical for improving the performance of LKH. Based on the output of SGN, NeuroLKH creates the edge candidate set and transforms edge distances to guide the searching process of LKH. Extensive experiments firmly demonstrate that, by training one model on a wide range of problem sizes, NeuroLKH significantly outperforms LKH and generalizes well to …

From Language Comprehension Towards General Ai, Binay Dahal

UNLV Theses, Dissertations, Professional Papers, and Capstones

Language comprehension or more formally, natural language understanding is one of the major undertakings in Artificial Intelligence. In this work, we explore a few of the problems in language understanding using fixed deep learning models. Specifically, first, we look into question generation. Asking questions relates to the cognitive ability of language comprehension and context understanding. For that reason, making progress in question generation is significant. We introduce a novel task called “question generation with masked target answer” and propose various models and present the baseline result for the task. Next, we extend on the question generation task and develop a …

Joint Linear And Nonlinear Computation With Data Encryption For Efficient Privacy-Preserving Deep Learning, Qiao Zhang

Electrical & Computer Engineering Theses & Dissertations

Deep Learning (DL) has shown unrivalled performance in many applications such as image classification, speech recognition, anomalous detection, and business analytics. While end users and enterprises own enormous data, DL talents and computing power are mostly gathered in technology giants having cloud servers. Thus, data owners, i.e., the clients, are motivated to outsource their data, along with computationally-intensive tasks, to the server in order to leverage the server’s abundant computation resources and DL talents for developing cost-effective DL solutions. However, trust is required between the server and the client to finish the computation tasks (e.g., conducting inference for the newly-input …

Deep Learning Predicts Ebv Status In Gastric Cancer Based On Spatial Patterns Of Lymphocyte Infiltration, Baoyi Zhang, Kevin Yao, Min Xu, Jia Wu, Chao Cheng

Computer Vision Faculty Publications

EBV infection occurs in around 10% of gastric cancer cases and represents a distinct subtype, characterized by a unique mutation profile, hypermethylation, and overexpression of PD-L1. Moreover, EBV positive gastric cancer tends to have higher immune infiltration and a better prognosis. EBV infection status in gastric cancer is most commonly determined using PCR and in situ hybridization, but such a method requires good nucleic acid preservation. Detection of EBV status with histopathology images may complement PCR and in situ hybridization as a first step of EBV infection assessment. Here, we developed a deep learning-based algorithm to directly predict EBV infection …

Deep Learning For Multiclass Classification, Predictive Modeling And Segmentation Of Disease Prone Regions In Alzheimer’S Disease, Maryamossadat Aghili

FIU Electronic Theses and Dissertations

One of the challenges facing accurate diagnosis and prognosis of Alzheimer’s Disease (AD) is identifying the subtle changes that define the early onset of the disease. This dissertation investigates three of the main challenges confronted when such subtle changes are to be identified in the most meaningful way. These are (1) the missing data challenge, (2) longitudinal modeling of disease progression, and (3) the segmentation and volumetric calculation of disease-prone brain areas in medical images. The scarcity of sufficient data compounded by the missing data challenge in many longitudinal samples exacerbates the problem as we seek statistical meaningfulness in multiclass …

Treatment Selection Using Prototyping In Latent-Space With Application To Depression Treatment, Akiva Kleinerman, Ariel Rosenfeld, David Benrimoh, Robert Fratila, Caitrin Armstrong, Joseph Mehltretter, Eliyahu Shneider, Amit Yaniv-Rosenfeld, Jordan Karp, Charles F. Reynolds, Gustavo Turecki, Adam Kapelner

Publications and Research

Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results, each of them suffers from important limitations. In this article, we propose a novel deep learning-based treatment selection approach that is shown to strike a balance between the two paradigms using latent-space prototyping. Our approach is specifically tailored for domains in which effective prototypes and sub-groups of patients are assumed to exist, but groupings relevant to the training objective are not …

System Identification Through Lipschitz Regularized Deep Neural Networks, Elisa Negrini, Giovanna Citti, Luca Capogna

Mathematics Sciences: Faculty Publications

In this paper we use neural networks to learn governing equations from data. Specifically we reconstruct the right-hand side of a system of ODEs x˙(t)=f(t,x(t)) directly from observed uniformly time-sampled data using a neural network. In contrast with other neural network-based approaches to this problem, we add a Lipschitz regularization term to our loss function. In the synthetic examples we observed empirically that this regularization results in a smoother approximating function and better generalization properties when compared with non-regularized models, both on trajectory and non-trajectory data, especially in presence of noise. In contrast with sparse regression approaches, since neural networks …

Stock Market Trend Forecasting Based On Multiple Textual Features: A Deep Learning Method, Zhenda Hu, Zhaoxia Wang, Seng-Beng Ho, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Stock market trend forecasting is a valuable and challenging research task for both industry and academia. In order to explore the influence of stock news information on the stock market trend, a textual embedding construction method is proposed to encode multiple textual features, including topic features, sentiment features, and semantic features extracted from stock news textual content. In addition, a deep learning method is designed by using financial data and multiple textual features obtained from multiple news textual embeddings for short-term stock market trend prediction. For evaluation, extensive experiments on real stock market data are conducted. The experimental results illustrate …

Patchnet: Hierarchical Deep Learning-Based Stable Patch Identification For The Linux Kernel, Thong Hoang, Julia Lawall, Yuan Tian, Richard J. Oentaryo, David Lo

Research Collection School Of Computing and Information Systems

Linux kernel stable versions serve the needs of users who value stability of the kernel over new features. The quality of such stable versions depends on the initiative of kernel developers and maintainers to propagate bug fixing patches to the stable versions. Thus, it is desirable to consider to what extent this process can be automated. A previous approach relies on words from commit messages and a small set of manually constructed code features. This approach, however, shows only moderate accuracy. In this paper, we investigate whether deep learning can provide a more accurate solution. We propose PatchNet, a hierarchical …

Multi-Object Localization In Robotic Hand, Tsing Tsow

USF Tampa Graduate Theses and Dissertations

We have developed a machine learning approach to localized objects inside a robotic hand using only images from 2D cameras. Specifically, we used deep learning method (You Only Look Once, YOLO) and Iterative closest Point (ICP) to estimate the 3D coordinates of the objects in a robotic hand. This method will also output the number of objects inside the robotic hand in addition to the coordinates of the objects. We have demonstrated the performance with simulation and obtained typical accuracy within a few pixels (couple mm) and counting accuracy of about 76%. We have also applied it to real images, …

Detection Of Dental Apical Lesions Using Cnns On Periapical Radiograph, Chun-Wei Li, Szu-Yin Lin, He-Sheng Chou, Tsung-Yi Chen, Yu-An Chen, Sheng-Yu Liu, Yu-Lin Liu, Chiung-An Chen, Yen-Cheng Huang, Shih-Lun Chen, Yi-Cheng Mao, Patricia Angela R. Abu, Wei-Yuan Chiang, Wen-Shen Lo

Department of Information Systems & Computer Science Faculty Publications

Apical lesions, the general term for chronic infectious diseases, are very common dental diseases in modern life, and are caused by various factors. The current prevailing endodontic treatment makes use of X-ray photography taken from patients where the lesion area is marked manually, which is therefore time consuming. Additionally, for some images the significant details might not be recognizable due to the different shooting angles or doses. To make the diagnosis process shorter and efficient, repetitive tasks should be performed automatically to allow the dentists to focus more on the technical and medical diagnosis, such as treatment, tooth cleaning, or …

Towards Accurate Run-Time Hardware-Assisted Stealthy Malware Detection: A Lightweight, Yet Effective Time Series Cnn-Based Approach, Hossein Sayadi, Yifeng Gao, Hosein Mohammadi Makrani, Jessica Lin, Paulo Cesar Costa, Setareh Rafatirad, Houman Homayoun

Computer Science Faculty Publications and Presentations

According to recent security analysis reports, malicious software (a.k.a. malware) is rising at an alarming rate in numbers, complexity, and harmful purposes to compromise the security of modern computer systems. Recently, malware detection based on low-level hardware features (e.g., Hardware Performance Counters (HPCs) information) has emerged as an effective alternative solution to address the complexity and performance overheads of traditional software-based detection methods. Hardware-assisted Malware Detection (HMD) techniques depend on standard Machine Learning (ML) classifiers to detect signatures of malicious applications by monitoring built-in HPC registers during execution at run-time. Prior HMD methods though effective have limited their study on …

Research On The Network Of 3d Smoke Flow Super-Resolution Data Generation, Jinlian Du, Shufei Li, Xueyun Jin

Journal of System Simulation

Abstract: Aiming at the problem of low data generation efficiency due to the high complexity of solving the N-S equation of smoke flow field, a deep learning model which can generate high-resolution smoke flow data based on low-resolution smoke flow data solved by N-S equation is explored and designed. Based on the Generative Adversarial Network, the smoke data reconstruction network based on the sub voxel convolution layer is constructed. Considering the fluidity of smoke, time loss based on advection step is introduced into the loss function to realize high-precision smoke simulation. By extending the image super-resolution quality evaluation index, the …

Deep Learning For Image Super-Resolution: A Survey, Zhihao Wang, Jian Chen, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Image Super-Resolution (SR) is an important class of image processing techniqueso enhance the resolution of images and videos in computer vision. Recent years have witnessed remarkable progress of image super-resolution using deep learning techniques. This article aims to provide a comprehensive survey on recent advances of image super-resolution using deep learning approaches. In general, we can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR. In addition, we also cover some other important issues, such as publicly available benchmark datasets and performance evaluation metrics. Finally, we conclude this survey by …

Towards More Trustworthy Deep Learning: Accurate, Resilient, And Explainable Countermeasures Against Adversarial Examples, Fei Zuo

Theses and Dissertations

Despite the great achievements made by neural networks on tasks such as image classification, they are brittle and vulnerable to adversarial example (AE) attacks, which are crafted by adding human-imperceptible perturbations to inputs in order that a neural-network-based classifier incorrectly labels them. Along with the prevalence of deep learning techniques, the threat of AEs attracts increasingly attentions since it may lead to serious consequences in some vital applications such as disease diagnosis.

To defeat attacks based on AEs, both detection and defensive techniques attract the research community’s attention. Given an input image, the detection system outputs whether it is an …

Neural Network Based Approach For Detecting Location Spoofing In Vehicular Communication, Smarth Kukreja

Electronic Theses and Dissertations

Vehicular Ad hoc Network (VANET) is an evolving subset of MANET. It's deployed on the roads, where vehicles act as mobile nodes. Active security and Intelligent Transportation System (ITS) are integral applications of VANET, which require stable and uninterrupted vehicle-to-vehicle communication technology. VANET, is a type of wireless network, due to which it is quite prone to security attacks. Extremely dynamic connections, sensitive data sharing and time-sensitivity of this network make it a vulnerable to security attacks. The messages shared between the vehicles are the basic safety message (BSM), these messages are broadcasted by each vehicle in the network to …

Traffic Sign And Light Detection Using Deep Learning For Automotive Applications, Humaira Naimi

Electronic Theses and Dissertations

Traffic sign and light detection are core components of Advanced Driver Assistance Systems (ADAS) and self-driving vehicles. The automotive industry is widely employing numerous approaches for automation through computer vision techniques. Object detection algorithms based on deep learning can be divided into two main categories, two stage and single stage detection algorithms. Two stage algorithms are designed to improve detection accuracy. While single stage algorithms are constructed to be faster, this increases their suitability for real time applications. This thesis presents a lightweight traffic sign and light detector by adapting a single stage, Single Shot Multibox Detection (SSD) algorithm by …

Computer-Aided Diagnosis Of Low Grade Endometrial Stromal Sarcoma (Lgess), Xinxin Yang, Mark Stamp

Faculty Research, Scholarly, and Creative Activity

Low grade endometrial stromal sarcoma (LGESS) accounts for about 0.2% of all uterine cancer cases. Approximately 75% of LGESS patients are initially misdiagnosed with leiomyoma, which is a type of benign tumor, also known as fibroids. In this research, uterine tissue biopsy images of potential LGESS patients are preprocessed using segmentation and stain normalization algorithms. We then apply a variety of classic machine learning and advanced deep learning models to classify tissue images as either benign or cancerous. For the classic techniques considered, the highest classification accuracy we attain is about 0.85, while our best deep learning model achieves an …

Artificial Intelligence In Cyber Security, University Of Maine Artificial Intelligence Initiative

General University of Maine Publications

UMaine AI draws top talent and leverages a distinctive set of capabilities from the University of Maine and other collaborating institutions from across Maine and beyond, while it also recruits world-class talent from across the nation and the world. It is centered at the University of Maine, leveraging the university’s strengths across disciplines, including computing and information sciences, engineering, health and life sciences, business, education, social sciences, and more.

Users’ Sentiment Analysis Toward National Digital Library Of India: A Quantitative Approach For Understanding User Perception, Ritu Sharma, Sarita Gulati, Amanpreet Kaur, Rupak Chakravarty

Library Philosophy and Practice (e-journal)

Sentiment analysis is also known as opinion mining. Sentiment analysis is contextual mining of text which identifies and extracts subjective information in textual data. It is extremely used by business, educational organizations, and social media monitoring to gain the general outlook of the wide public regarding their product and policy. The current study looks for gaining insights into user reviews on the National Digital Library of India (NDLI) mobile app (android and iOS). For this purpose, sentiment analysis will be used. It yields an average of 3.64/5 ratings based on 11,861 reviews. The dataset includes a total of 4560 user …

Learning In Convolutional Neural Networks Accelerated By Transfer Entropy, Adrian Moldovan, Angel Caţaron, Răzvan Andonie

Computer Science Faculty Scholarship

Recently, there is a growing interest in applying Transfer Entropy (TE) in quantifying the effective connectivity between artificial neurons. In a feedforward network, the TE can be used to quantify the relationships between neuron output pairs located in different layers. Our focus is on how to include the TE in the learning mechanisms of a Convolutional Neural Network (CNN) architecture. We introduce a novel training mechanism for CNN architectures which integrates the TE feedback connections. Adding the TE feedback parameter accelerates the training process, as fewer epochs are needed. On the flip side, it adds computational overhead to each epoch. …

Advancing Proper Dataset Partitioning And Classification Of Visual Search And The Vigilance Decrement Using Eeg Deep Learning Algorithms, Alexander J. Kamrud

Theses and Dissertations

Electroencephalography (EEG) classification of visual search and vigilance tasks has vast potential in its benefits. In future human-machine teaming systems, EEG could act as the tool for operator state assessment, enabling AI teammates to know when to assist the operator in these tasks, with the potential to lead to increased safety of operations, better training systems for our operators, and improved operational effectiveness. This research investigates deep learning methods which utilize EEG signals to classify the efficiency of an operator's search and to classify whether an operator is in a decrement during a vigilance type task, and investigates performing these …

Deep Learning For Weather Clustering And Forecasting, Nathaniel R. Beveridge

Theses and Dissertations

Clustering weather data is a valuable endeavor in multiple respects. The results can be used in various ways within a larger weather prediction framework or could simply serve as an analytical tool for characterizing climatic differences of a particular region of interest. This research proposes a methodology for clustering geographic locations based on the similarity in shape of their temperature time series over a long time horizon of approximately 11 months. To this end an emerging and powerful class of clustering techniques that leverages deep learning, called deep representation clustering (DRC), are utilized. Moreover, a time series specific DRC algorithm …

Automatic Fairness Testing Of Neural Classifiers Through Adversarial Sampling, Peixin Zhang, Jingyi Wang, Jun Sun, Xinyu Wang, Guoliang Dong, Xinggen Wang, Ting Dai, Jinsong Dong

Research Collection School Of Computing and Information Systems

Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e., non-discrimination). Unfortunately, discrimination might be intrinsically embedded into the models due to the discrimination in the training data. As a countermeasure, fairness testing systemically identifies discriminatory samples, which can be used to retrain the model and improve the model’s fairness. Existing fairness testing approaches however have two major limitations. Firstly, they only work well on traditional machine learning models and have poor performance (e.g., effectiveness and efficiency) on deep learning …

Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue

Dissertations

The zero-one loss function is less sensitive to outliers than convex surrogate losses such as hinge and cross-entropy. However, as a non-convex function, it has a large number of local minima, andits undifferentiable attribute makes it impossible to use backpropagation, a method widely used in training current state-of-the-art neural networks. When zero-one loss is applied to deep neural networks, the entire training process becomes challenging. On the other hand, a massive non-unique solution probably also brings different decision boundaries when optimizing zero-one loss, making it possible to fight against transferable adversarial examples, which is a common weakness in deep learning …

Towards Adversarial Robustness With 01 Lossmodels, And Novel Convolutional Neural Netsystems For Ultrasound Images, Meiyan Xie

Dissertations

This dissertation investigates adversarial robustness with 01 loss models and a novel convolutional neural net systems for vascular ultrasound images.

In the first part, the dissertation presents stochastic coordinate descent for 01 loss and its sensitivity to adversarial attacks. The study here suggests that 01 loss may be more resilient to adversarial attacks than the hinge loss and further work is required.

In the second part, this dissertation proposes sign activation network with a novel gradient-free stochastic coordinate descent algorithm and its ensembling model. The study here finds that the ensembling model gives a high minimum distortion (as measured by …

Advances In Deep Learning With Applications To Computer Vision And Astronomy, Zhihang Hu

Dissertations

Deep Learning has spanned a variety of applications in computer vision as well as computational astronomy. These two aspects obtained similar data structure, therefore, their solutions can be transferable between each other. This dissertation look into two video-related tasks in computer vision and propose a novel problem in computational astronomy.

Specifically, acquiring an in-depth understanding of videos has been a cornerstone problem in computer vision. This problem has been studied by various researchers from different perspectives, among which video prediction has attracted much attention. Video prediction aims to generate the pixels of future frames given a sequence of context frames. …

A Transformer-Based Classification System For Volcanic Seismic Signals, Cristian Bravo Roman, Cindy Mora Stock, Alexander James Hemming

Undergraduate Student Research Internships Conference

Volcanic seismic signals are a key element in volcano monitoring to assess the state of unrest and a possible eruption style and timing. Different sources such as brittle fracture (volcano-tectonic - VT) or fluid movement (long period - LP) generate signals with distinct characteristics in frequency content and shape, but site effects such as attenuation or background noise make their determination difficult to the untrained eye. In cases of unrest or an eminent eruption, the amount of data would require a fast and reliable source of pre-classification to classify and catalogue to aid in the job usually done by a …