Fabric Defect Detection Using Activation Layer Embedded Convolutional Neural Network (open access)

Fabric Defect Detection Using Activation Layer Embedded Convolutional Neural Network

This article develops a deep-learning algorithm for an on-loom fabric defect inspection system by combining the techniques of image pre-processing, fabric motif determination, candidate defect map generation, and convolutional neural networks (CNNs).
Date: April 29, 2019
Creator: Ouyang, Wenbin; Xu, Bugao; Hou, Jue & Yuan, Xiaohui
Object Type: Article
System: The UNT Digital Library
3D-FHNet: Three-Dimensional Fusion Hierarchical Reconstruction Method for Any Number of Views (open access)

3D-FHNet: Three-Dimensional Fusion Hierarchical Reconstruction Method for Any Number of Views

Article proposes a three-dimensional fusion hierarchical reconstruction method that utilizes a multi-view feature combination method and a hierarchical prediction strategy to unify the single view and any number of multiple views 3D reconstructions.
Date: November 22, 2019
Creator: Lu, Qiang; Lu, Yiyang; Xiao, Mingjie; Yuan, Xiaohui & Jia, Wei
Object Type: Article
System: The UNT Digital Library
Attention-Based Dense Point Cloud Reconstruction From a Single Image (open access)

Attention-Based Dense Point Cloud Reconstruction From a Single Image

Article proposes a two-stage training dense point cloud generation network.
Date: September 23, 2019
Creator: Lu, Qiang; Xiao, Mingjie; Lu, Yiyang; Yuan, Xiaohui & Yu, Ye
Object Type: Article
System: The UNT Digital Library
Automated extraction of attributes from natural language attribute-based access control (ABAC) Policies (open access)

Automated extraction of attributes from natural language attribute-based access control (ABAC) Policies

Article (1) developing a practical framework to extract authorization attributes of hierarchical ABAC system from natural language artifacts, and (2) generating a set of realistic synthetic natural language access control policies (NLACPs) to evaluate the proposed framework.
Date: January 21, 2019
Creator: Alohaly, Manar; Takabi, Hassan & Blanco, Eduardo
Object Type: Article
System: The UNT Digital Library
The Application of BP Neural Networks to Analysis the National Vulnerability (open access)

The Application of BP Neural Networks to Analysis the National Vulnerability

Article uses the analytic hierarchy process (AHP) and natural breakpoint method (NBM) to implement an AHP-NBM comprehensive evaluation model to assess the national vulnerability to climate change.
Date: 2019
Creator: Zhao, Guodong; Zhang, Yuewei; Shi, Yiqi; Lan, Haiyan & Yang, Qing
Object Type: Article
System: The UNT Digital Library
A Corpus of Negations and their Underlying Positive Interpretations (open access)

A Corpus of Negations and their Underlying Positive Interpretations

Article presenting a corpus of negations and their underlying positive interpretations using negations from Simple Wikipedia, automatically generating potential positive interpretations, and collecting manual annotations that effectively rewrite the negation in positive terms. This article was presented at the Eighth Joint Conference on Lexical and Computational Semantics (SEM 2019) in Minneapolis, Minnesota, June 6-7, 2019.
Date: June 2019
Creator: Sarabi, Zahra; Killian, Erin; Blanco, Eduardo & Palmer, Alexis
Object Type: Article
System: The UNT Digital Library
Genome-Resolved Proteomic Stable Isotope Probing of Soil Microbial Communities Using 13CO2 and 13C-Methanol (open access)

Genome-Resolved Proteomic Stable Isotope Probing of Soil Microbial Communities Using 13CO2 and 13C-Methanol

Article describes experiment where proteomic sable isotope probing (SIP) was combined with targeted metagenomic binning to reconstruct metagenome-assembled genomes (MAGs) of the microorganisms producing labeled proteins. Carbon flows were tracked from 13CO2 to the rhizosphere communities of Zea mays, Triticum aestivum, and Arabidopsis thaliana.
Date: December 6, 2019
Creator: Li, Zhou; Yao, Qiuming; Guo, Xuan; Crits-Christoph, Alexander; Mayes, Melanie A.; Hervey, William Judson IV et al.
Object Type: Article
System: The UNT Digital Library
Incorporating Emoji Descriptions Improves Tweet Classification (open access)

Incorporating Emoji Descriptions Improves Tweet Classification

Article presenting a simple strategy to process emojis in Tweets: replace them with their natural language description and use pretrained word embeddings as normally done with standard words. Results show that this strategy is more effective than using pretrained emoji embeddings for tweet classification.
Date: June 2019
Creator: Singh, Abhishek K.; Blanco, Eduardo & Jin, Wei
Object Type: Article
System: The UNT Digital Library
Bayesian analysis of complex mutations in HBV, HCV, and HIV studies (open access)

Bayesian analysis of complex mutations in HBV, HCV, and HIV studies

This article provides a review of the Bayesian-inference-based methods applied to Hepatitis B Virus (HBV), Hepatitis C Virus (HCV), and Human Immunodeficiency Virus (HIV) studies with a focus on the detection of the viral mutations and various problems which are correlated to these mutations. The authors also provide a summary of the Bayesian methods' applications toward these viruses' studies, where several important and useful results have been discovered.
Date: April 4, 2019
Creator: Guo, Xuan; Liu, Bing; Feng, Shishi & Zhang, Jing
Object Type: Article
System: The UNT Digital Library
A Lightweight Three-Factor User Authentication Protocol for the Information Perception of IoT (open access)

A Lightweight Three-Factor User Authentication Protocol for the Information Perception of IoT

Article proposes a lightweight authentication protocol based on password, smart card and biometric identification that achieves mutual authentication among User, GWN and sensor node.
Date: 2019
Creator: Kou, Liang; Shi, Yiqi; Zhang, Liguo; Liu, Duo & Yang, Qing
Object Type: Article
System: The UNT Digital Library
Integrating multi-omics datasets to infer phenotype-specific driver genes, regulatory interactions and drug response (open access)

Integrating multi-omics datasets to infer phenotype-specific driver genes, regulatory interactions and drug response

Data management plan for the grant "Integrating multi-omics datasets to infer phenotype-specific driver genes, regulatory interactions and drug response." Research to develop open source integrative computational tools that perform secondary analysis of publicly available multi-omics biological, clinical and environmental exposure datasets to infer context-specific regulatory interactions and modules, and to predict disease associated genes and patient-specific drug response.
Date: 2019-08-01/2024-06-30
Creator: Bozdag, Serdar
Object Type: Text
System: The UNT Digital Library
Episode 12: Dr. Ryan Garlick transcript

Episode 12: Dr. Ryan Garlick

Interview with Dr. Ryan Garlick for the Osher Lifelong Learning Institute (OLLI) podcast. In this episode, Susan speaks with Dr. Ryan Garlick, Principal Lecturer in UNT's Department of Computer Science and Engineering. They discuss his codebreaking work, including his participation in TV programs such as National Geographic's "Hunt for the Zodiac Killer." Dr. Garlick gives an overview of the codebreaking methods that are being used to decipher the Zodiac's mysterious messages and also talks about his academic and professional background.
Date: February 28, 2019
Creator: Supak, Susan & Garlick, Ryan
Object Type: Sound
System: The UNT Digital Library