Physical Sciences and Mathematics Commons^™

Two Sides Of The Same Coin: Exploiting The Impact Of Identifiers In Neural Code Comprehension, Shuzheng Gao, Cuiyun Gao, Chaozheng Wang, Jun Sun, David Lo, Yue Yu

Research Collection School Of Computing and Information Systems

Previous studies have demonstrated that neural code comprehension models are vulnerable to identifier naming. By renaming as few as one identifier in the source code, the models would output completely irrelevant results, indicating that identifiers can be misleading for model prediction. However, identifiers are not completely detrimental to code comprehension, since the semantics of identifier names can be related to the program semantics. Well exploiting the two opposite impacts of identifiers is essential for enhancing the robustness and accuracy of neural code comprehension, and still remains under-explored. In this work, we propose to model the impact of identifiers from a …

Fine-Grained Commit-Level Vulnerability Type Prediction By Cwe Tree Structure, Shengyi Pan, Lingfeng Bao, Xin Xia, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

Identifying security patches via code commits to allow early warnings and timely fixes for Open Source Software (OSS) has received increasing attention. However, the existing detection methods can only identify the presence of a patch (i.e., a binary classification) but fail to pinpoint the vulnerability type. In this work, we take the first step to categorize the security patches into fine-grained vulnerability types. Specifically, we use the Common Weakness Enumeration (CWE) as the label and perform fine-grained classification using categories at the third level of the CWE tree. We first formulate the task as a Hierarchical Multi-label Classification (HMC) problem, …

A Study Of Variable-Role-Based Feature Enrichment In Neural Models Of Code, Aftab. Hussain, Md. Rafiqul Islam. Rabin, Bowen. Xu, David Lo, Mohammad Amin. Alipour

Research Collection School Of Computing and Information Systems

Although deep neural models substantially reduce the overhead of feature engineering, the features readily available in the inputs might significantly impact training cost and the performance of the models. In this paper, we explore the impact of an unsuperivsed feature enrichment approach based on variable roles on the performance of neural models of code. The notion of variable roles (as introduced in the works of Sajaniemi et al. [1], [2]) has been found to help students' abilities in programming. In this paper, we investigate if this notion would improve the performance of neural models of code. To the best of …

Semparser: A Semantic Parser For Log Analytics, Yintong Huo, Yuxin Su, Cheryl Lee, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Logs, being run-time information automatically generated by software, record system events and activities with their timestamps. Before obtaining more insights into the run-time status of the software, a fundamental step of log analysis, called log parsing, is employed to extract structured templates and parameters from the semi-structured raw log messages. However, current log parsers are all syntax-based and regard each message as a character string, ignoring the semantic information included in parameters and templates.Thus, we propose the first semantic-based parser SemParser to unlock the critical bottleneck of mining semantics from log messages. It contains two steps, an end-to-end semantics miner …

On-Device Deep Multi-Task Inference Via Multi-Task Zipping, Xiaoxi He, Xu Wang, Zimu Zhou, Jiahang Wu, Zheng Yang, Lothar Thiele

Research Collection School Of Computing and Information Systems

Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks locally on-device. Yet the complexity of these deep models needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory. Previous studies squeeze the redundancy within a single model. In this work, we aim to reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to automatically merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme …

Repeated Low-Level Blast Exposure Alters Urinary And Serum Metabolites, Austin Sigler, Jiandong Wu, Annalise Pfaff, Olajide Adetunji, Paul Ki-Souk Nam, Donald James, Casey Burton, Honglan Shi

Chemistry Faculty Research & Creative Works

Repeated exposure to low-level blast overpressures can produce biological changes and clinical sequelae that resemble mild traumatic brain injury (TBI). While recent efforts have revealed several protein biomarkers for axonal injury during repetitive blast exposure, this study aims to explore potential small molecule biomarkers of brain injury during repeated blast exposure. This study evaluated a panel of ten small molecule metabolites involved in neurotransmission, oxidative stress, and energy metabolism in the urine and serum of military personnel (n = 27) conducting breacher training with repeated exposure to low-level blasts. The metabolites were analyzed using HPLC—tandem mass spectrometry, and the Wilcoxon …

Detection Of Acetaminophen In Groundwater By Laccase-Based Amperometric Biosensors Using Mos2 Modified Carbon Paper Electrodes, Marcela Herrera-Domínguez, Koun Lim, Iris Aguilar-Hernández, Alejandra García-García, Shelley D. Minteer, Nancy Ornelas-Soto, Raúl Garcia-Morales

Chemistry Faculty Research & Creative Works

The use of enzyme-Based biosensors for the detection and quantification of analytes of interest such as contaminants of emerging concern, including over-the-counter medication, provides an attractive alternative compared to more established techniques. However, their direct application to real environmental matrices is still under investigation due to the various drawbacks in their implementation. Here, we report the development of bioelectrodes using laccase enzymes immobilized onto carbon paper electrodes modified with nanostructured molybdenum disulfide (MoS2). the laccase enzymes were two isoforms (LacI and LacII) produced and purified from the fungus Pycnoporus sanguineus CS43 that is native to Mexico. a commercial purified enzyme …

Dual Crosslinked Poly(Acrylamide-Co-N-Vinylpyrrolidone) Microspheres With Re-Crosslinking Ability For Fossil Energy Recovery, Jingyang Pu, Baojun Bai, Jiaming Geng, Na Zhang, Thomas Schuman

Chemical and Biochemical Engineering Faculty Research & Creative Works

Microspheres have been proposed to be applied in controlling wastewater production for mature oilfields and migrating leakage for gas and nuclear waste storage. However, it remains challenging for stacked microspheres to maintain strong blocking ability in micron-sized small pores or fractures. in this study, a novel microsphere was developed with comprehensive properties including high deformability and long re-crosslinking time upon tunable swelling ratio for the applications. a dual covalent and physical crosslinking strategy was used to develop novel microspheres reinforced by a hydrogen bond (H-bond, between pyrrole ring and amide group) and coordination bond (between chromium acetate (CrAc) and carboxyl …

Inferring The Compositions And Interior Structures Of Small Planets, David R. Rice

UNLV Theses, Dissertations, Professional Papers, and Capstones

Although there are now over 10,000 confirmed and candidate extrasolar planets, accurate masses and radii have been determined for around 200 planets of less than 10 Earth-masses. This number will grow exponentially over the next decade as extreme precision radial velocity spectrographs see first light. The densities of small planets hint at a diverse range of compositions for terrestrial worlds from super-Mercuries to super-Ganymedes. Uncertainty in density is as low as 3% in the Trappist-1 system. To determine composition from observed parameters, the community uses a variety of interior structure models. Underlying these models are multiple computational techniques, numerous experimental …

Fake News Detection Using Narrative Content And Discourse, Hongmin Kim

Boise State University Theses and Dissertations

With the growth of modern technology, we are living in a world where anyone can share news with the tap of a finger. The simplified process of news sharing has brought an inundation of information on the Internet, along with a vast amount of fake news. Researchers have been working to understand the characteristics of fake news, in order to accurately identify them through automated text analysis.

In this thesis, we propose the Narrative Content and Narrative Discourse features brought from the ideas by van Laer et al., Berger et al., and Aleti et al. We performed various experiments including …

Remote Sensing To Advance Understanding Of Snow-Vegetation Relationships And Quantify Snow Depth And Snow Water Equivalent, Ahmad Hojatimalekshah

Boise State University Theses and Dissertations

Snowpack is an important source of freshwater in mountainous regions. Understanding the role of different controls on snow properties (depth, distribution, and snow water equivalent (SWE)) and processes (accumulation and ablation) is important to predict available freshwater. Snow processes vary with respect to the predominant local controls in different landscapes. In many mountainous landscapes, controls on snow properties and processes are highly correlated with vegetation properties. In this dissertation, to elucidate the relationships between snow and vegetation, I use terrestrial laser scanning to explore how forest canopy structure affects snow depth distribution. In addition, I examine different vegetation metrics to …

Verifying Data Provenance During Workflow Execution For Scientific Reproducibility, Rizbanul Hasan

Boise State University Theses and Dissertations

Reproducibility is essential in scientific research to ensure that any findings or conclusions are accurate. The reproducibility crisis around scientific studies and experiments is a significant concern. Several strategies and technologies have been introduced to share and exchange research data. However, very few address scientific reproducibility issues when interacting with vast amounts of data that may be manually altered during workflow execution.

This research focuses on verifying data provenance using the principles of blockchain. This technique stores the hashes of research data in a database along with user information. It allows the workflow to verify the data against the hashes …

Interactive Effects Of Fungal Community Structure And Soil Moisture On Wyoming Big Sagebrush Performance, Arden Marlene Engel

Boise State University Theses and Dissertations

Large swathes of the North American sagebrush steppe have been converted to grazing and agricultural use. Remaining fragmented areas are threatened by invasive annual grasses and associated perpetuation of increased fire frequency, with efforts to restore sagebrush after fire largely unsuccessful. Lack of success may be due, in part, to poor interactions between sagebrush seed sourced from distant locations and unfamiliar soil fungi.

A greenhouse experiment was designed to evaluate effects of soil fungal community composition on sagebrush reestablishment by answering: (1) How does inoculation with ‘coevolved’ versus ‘foreign’ fungal inoculum impact sagebrush fitness? (2) How does moisture availability modify …

High-Performance Domain-Specific Library For Hydrologic Data Processing, Kalyan Bhetwal

Boise State University Theses and Dissertations

Hydrologists must process many gigabytes of data for hydrologic simulations, which takes time and resources degrading performance. The performance issues are caused mainly by domain scientists’ preference for using Python, which trades performance for productivity. In my thesis, I demonstrate that using the static compilation technique to compile Python to generate C code along with several optimizations reduces time and resources for hydrologic data processing. I developed a Domain Specific Library (DSL) which is a subset of Python and compiles to Sparse Polyhedral Framework - Intermediate Representation (SPF-IR), which allows opportunities for optimizations like read reduction fusion which are not …

Exploring The Capability Of A Self-Supervised Conditional Image Generator For Image-To-Image Translation Without Labeled Data: A Case Study In Mobile User Interface Design, Hailee Kiesecker

Boise State University Theses and Dissertations

This research investigates the effectiveness of a conditional image generator trained on a restricted number of unlabeled images for image-to-image translation in computer vision. While previous research has focused on using labeled data for image labeling in conditional image generation, this study proposes an original framework that utilizes self-supervised classification on generated images. The proposed approach, which combines Conditional GAN and Semantic Clustering, showed promising results. However, this study has several limitations, including a limited dataset and the need for significant computational power to generate a single UI design. Further research is needed to optimize the performance of the proposed …

Anomaly Detection Using Graph Neural Network, Bishal Lakha

Boise State University Theses and Dissertations

Detecting malicious behavior is becoming increasingly crucial as the internet becomes more prevalent. This problem can be formulated as an anomaly detection task on provenance data, where attacks are detectable as anomalies in the behavior of the system. The availability of system-level data in comparison to network data is quite limited and so is the research carried out on system-level logs. However, monitoring the operating system's processes during program execution and identifying anomalous behavior in system calls can be beneficial since it can provide broad coverage and generality, as a variety of malicious applications could be identified. Furthermore, logs like …

Sparse Format Conversion And Code Synthesis, Tobi Goodness Popoola

Boise State University Theses and Dissertations

Sparse computations are important in scientific computing. Many scientific applications compute on sparse data. Data is said to be sparse if it has a relatively small number of non-zeros. Sparse formats use auxiliary arrays to store non-zeros, as a result, the contents of auxiliary arrays are not known until run-time. The Inspector/Executor (I/E) paradigm uses run-time information for compiler optimizations. An inspector computes information at run-time to drive transformations. The executor---a compile-time transformation of the original code--- uses information computed by the inspector. The sparse polyhedral framework (SPF) encompasses a series of tools to support I/E run-time transformations. This work …

Portable Sparse Polyhedral Framework Code Generation Using Multi Level Intermediate Representation, Aaron St. George

Boise State University Theses and Dissertations

The Sparse Polyhedral Framework (SPF) provides vital support to scientific applications, but is limited in portability. SPF extends the Polyhedral Model to non-affine codes. Scientific applications need the optimizations SPF enables, but current SPF tools don't support GPUs or other heterogeneous hardware targets. As clock speeds continue to stagnate, scientific applications need the performance enhancements enabled by both SPF and newer heterogeneous hardware.

The MLIR (Multi-Level Intermediate Representation) ecosystem offers a large, extensible, and cooperating set of intermediate representations (called dialects). A typical compiler has one main intermediate representation, whereas an MLIR based compiler will have many. Because of this …

Severity Measures For Assessing Error In Automatic Speech Recognition, Ryan Whetten

Boise State University Theses and Dissertations

A common metric for evaluating Automatic Speech Recognition (ASR) is Word Error Rate (WER) which solely takes into account discrepancies at the word-level. Although WER is useful, it is not guaranteed to correlate well with intelligibility or performance on downstream tasks that make use of ASR. Meaningful assess- ment of ASR mistakes becomes even more important in high-stake scenarios such as health-care. I propose 2 general measures to evaluate the quality or severity of mistakes made by ASR systems, one based on sentiment analysis and another based on text embeddings. Both have the potential to overcome the limitations of WER. …

More Than Meets The Eye: In-Store Retail Experiences With Augmented Reality Smart Glasses, Pauline Pfeifer, Tim Hilken, Jonas Heller, Saifeddin Alimamy, Roberta Di Palma

All Works

Augmented reality smart glasses (ARSGs) promise to enhance consumer experiences and decision-making when deployed as in-store retail technologies. However, research to date has not studied in-store use cases; instead, it has focused primarily on consumers' potential adoption of these devices for everyday use. Nor have prior studies compared ARSG uses with the now-common use of AR on touchscreen devices. The current research addresses these knowledge gaps by examining whether ARSGs outperform AR on touchscreen devices in the context of in-store retail experiences. Testing with an actual retail application (n = 308) shows that ARSGs are superior to AR on touchscreen …

Different Approaches To Overcome Antibiotic Resistance, Samantha Biaesch

Chemistry

In the recent years, there has been a growing demand for the development of antibiotic treatments as bacterial infections have acquired defense mechanisms to commonly used antibiotics, such as penicillin. During the growth of bacterial cells, resistant mutants are able to survive antibiotic treatment and continue proliferation. Thus, creating a resistant bacterial cell population that can no longer be targeted through antibiotic treatment. Due to the recent need of new approaches, there has been an explosion of research in developing techniques that combat bacterial resistance. Both bacteriophage-RNA aptamer binding and modifications in bacterial tRNA show potential to be exploited for …

Time Varied Self-Reliance Aerial Ground Traffic Monitoring System With Pre-Recognition Collision Avoidance, Seungheyon Lee, Sooeon Lee, Yumin Choi, Jalel Ben-Othman, Lynda Mokdad, Hyunbum Kim

All Works

In this letter, we introduce a time varied self-reliance aerial ground traffic monitoring system which provides pre-recognition collision avoidance among mobile robots and smart UAVs for virtual emotion security. Then, with ILP (Integer Linear Programming), we make a formal definition of the problem whose objective is to minimize a total spent time by smart UAVs (Unmanned Aerial Vehicles) and mobile robots without conflicts on condition that the demanded number of self-reliance security barriers are formed. To solve the defined problem, we develop two approaches, time-differentiated pre-stop movement and approximated equal segments movement. Then, those schemes are implemented through expanded experiments …

An Overview Of Serial Depletions Of Global Marine Fisheries 1950 To 2019, Alison Follmer

Biological Sciences Undergraduate Honors Theses

Overfishing is a global issue that poses a significant risk to the entire ocean ecosystem in diminishing biodiversity and ecosystem function. This thesis examined the pattern and pace of fisheries depletions due to commercial fishing during the past 70 years. The Food and Agriculture Organization of the United Nations (FAO) Division of Fisheries and Aquaculture maintains a database of global hauls of marine taxa (reported in metric tonnes) from 1950 – 2019. These data were queried to determine the total number and sequence of fisheries depletions documented by the historic record. Analysis of this database showed progressive, linearly-increasing exploitation of …

Evaluating Snow And Ice Cover In Tierra Del Fuego, Argentina, Zoe Pitman

Geosciences Undergraduate Honors Theses

Evaluating changes in snow and ice cover is an important field for studying climate change and its impacts. This evaluation is commonly done using remote sensing because of its ability to evaluate large areas. The purpose of this study is to determine the reliability of one remote sensing technology, the Moderate Resolution Imaging Spectroradiometer (MODIS), by comparing it to in-situ snow and climate data from the weather station at the Austral Center for Scientific Research (CADIC). Data was converted from daily to monthly averages and was sorted into a series of graphs to compare the two data sets. Correlations were …

Modeling User Behavior For Cyber Security With Formal Methods And Agent Based Simulation, Hamdah Albalawi

Theses and Dissertations

Despite society’s positive outlook, technology poses real cyber security threats. Technology’s benefits can sometimes make it difficult to believe that potential threats lurk behind every device and platform. As cybercrime rises, we have come to rely increasingly on flawed devices and services. As cyberattacks become more prevalent, security professionals are committed to developing more robust and dependable security solutions. In cyber security, human error is regarded as the weakest link since all technical security solutions are vulnerable to human error. Among other human characteristics, risk-taking, logical decision-making, extraversion, and gender can significantly affect cyber security. However, there still is the …

Soil Water Use Efficiency Under Integrated Soil Management Practices In The Drylands Of Kenya, Nathan O. Oduor, Monicah Mucheru-Muna, Jayne Njeri Mugwe, Isaya Sijali, George Nyabuga, Daniel Njiru Mugendi

Graduate School of Media and Communications

Soil moisture scarcity and soil fertility decline in the drylands contribute to declining crop productivity. The possible synergistic effects of integrating soil & water conservation, and soil fertility management practices on soil moisture, and hence water use efficiency (WUE) in the drylands of Tharaka-Nithi County in Kenya was assessed. The experiment was laid in a three by three split plot arrangement, with four replications, for four cropping seasons. Minimum tillagewith mulch, tied ridges, and conventional tillage formed the main plot factors. The sub-plot factors included animal manure plus fertilizer at 120, 60, and 30 N kg ha−1. There was significant …

Quantum Chemistry–Machine Learning Approach For Predicting Properties Of Lewis Acid–Lewis Base Adducts, Hieu Huynh, Thomas J. Kelly, Linh Vu, Tung Hoang, Phuc An Nguyen, Tu C. Le, Emily Jarvis, Hung Phan

Chemistry and Biochemistry Faculty Works

Synthetic design allowing predictive control of charge transfer and other optoelectronic properties of Lewis acid adducts remains elusive. This challenge must be addressed through complementary methods combining experimental with computational insights from first principles. Ab initio calculations for optoelectronic properties can be computationally expensive and less straightforward than those sufficient for simple ground-state properties, especially for adducts of large conjugated molecules and Lewis acids. In this contribution, we show that machine learning (ML) can accurately predict density functional theory (DFT)-calculated charge transfer and even properties associated with excited states of adducts from readily obtained molecular descriptors. Seven ML models, built …

Quantitative Analysis Of The Proteomic Selectivity Of Acidic Reductive Alkylation Of Peptides, Connor Jewell

Honors Scholar Theses

Proteome quantification is a complicated process which takes on many methods, usually involving peptide derivatization and complex mass spectral analysis. Scores of techniques have been utilized to address issues of incomplete quantification. The implementation of IPTL labeling, or isobaric peptide terminal labeling, is a recent addition to the literature, which exploits the supposedly selective labeling of N-termini of tryptic peptides from the C-termini of lysine residues due to differences in basicity. This method has been shown to improve quantitation by reducing spectral complexity and provide more accurate and reproducible results on peptide abundance. Investigations into the selectivity of terminal derivatization …

Modeling Accuracy Matters: Aligning Molecular Dynamics With 2d Nmr Derived Noe Restraints, Milan Patel

Honors Scholar Theses

Among structural biology techniques, Nuclear Magnetic Resonance (NMR) provides a holistic view of structure that is close to protein structure in situ. Namely, NMR imaging allows for the solution state of the protein to be observed, derived from Nuclear Overhauser Effect restraints (NOEs). NOEs are a distance range in which hydrogen pairs are observed to stay within range of, and therefore experimental data which computational models can be compared against. To that end, we investigated the effects of adding the NOE restraints as distance restraints in Molecular Dynamics (MD) simulations on the 24 residue HP24stab derived villin headpiece subdomain to …

Staircase Arrangements Of Pillars With Distinct Heights, Andrea L. Simmons

Mathematics, Statistics, and Computer Science Honors Projects

We study the family A_n of sequences (a₁, a₂, ..., a_n) where 0 ≤ a_k ≤ k and nonzero entries are distinct. We show that these sequences are in bijection with the set partitions of [n + 1]. These sequences have a natural poset structure, and we analyze the maximal chains within this poset. Finally, we explore various subfamilies of A_n, including sequences whose largest entry is k and sequences missing the value k.