Physical Sciences and Mathematics Commons^™

Variational Autoencoder-Based Anomaly Detection In Time Series Data For Inventory Record Inaccuracy, Hali̇l Arğun, Sadetti̇n Emre Alpteki̇n

Turkish Journal of Electrical Engineering and Computer Sciences

Retail companies monitor inventory stock levels regularly and manage them based on forecasted sales to sustain their market position. Inventory accuracy, defined as the difference between the warehouse stock records and the actual inventory, is critical for preventing stockouts and shortages. The root causes of inventory inaccuracy are the employee or customer theft, product damage or spoilage, and wrong shipments. In this paper, we aim at detecting inaccurate stocks of one of Turkey's largest supermarket chain using the variational autoencoder (VAE), which is an unsupervised learning method. Based on the findings, we showed that VAE is able to model the …

Binary Text Classification Using Genetic Programming With Crossover-Based Oversampling For Imbalanced Datasets, Mona Aljero, Nazi̇fe Di̇mi̇li̇ler

Turkish Journal of Electrical Engineering and Computer Sciences

It is well known that classifiers trained using imbalanced datasets usually have a bias toward the majority class. In this context, classification models can present a high classification performance overall and for the majority class, even when the performance for the minority class is significantly lower. This paper presents a genetic programming (GP) model with a crossover-based oversampling technique for oversampling the imbalanced dataset for binary text classification. The aim of this study is to apply an oversampling technique to solve the imbalanced issue and improve the performance of the GP model that employed the proposed technique. The proposed technique …

A Robust Model For Spot Virtual Machine Bidding In The Cloud Market Using Information Gap Decision Theory (Igdt), Mona Naghdehforoushha, Mehdi Dehghan Takht Fooladi, Mohammed Hossein Rezvani, Mohammad Mehdi Gilanian Sadeghi

Turkish Journal of Electrical Engineering and Computer Sciences

The spot market is one of the most common cloud markets where cloud providers, such as Amazon EC2, rent their surplus computing resources at lower prices in the form of spot virtual machines (SVMs). In this market, which is often managed through an auction mechanism, users seek optimal bidding strategies for renting SVMs to minimize cost and risk. Uncertainty in the price of SVMs and their low availability/reliability is a challenging issue to bid on the user side. In this paper, we present a robust model for minimizing the cost of executing tasks by considering the uncertainty of the price …

A New Approach To Linear Displacement Measurements Based On Hall Effect Sensors, İsmai̇l Yari̇çi̇, Yavuz Öztürk

Turkish Journal of Electrical Engineering and Computer Sciences

Since displacement is a vital variable to be considered in many industrial applications, displacement sensing devices have been extensively studied both theoretically and experimentally. There have been also many studies on Hall effect-based displacement measurement, but for many systems linearity still remains a problem. This paper discusses different approaches to calculate the magnetic field due to a cylindrical permanent magnet and proposes a new setup geometry with 2-Hall effect sensors and a permanent magnet between them to overcome the linearity problems. Furthermore, theoretical and experimental studies of the discussed displacement sensor were presented by focusing on the linear range and …

Deep Learning-Based Technique For The Perception Of The Cervical Cancer, Aya Haraz, Hossam El-Din Moustafa, Abeer Twakol Khaleel, Ahmed H. Eltanboly

Mansoura Engineering Journal

In third-world countries, cervical cancer is the most prevalent and leading cause of death. It is affected by a variety of factors, including smoking, poor nutritional status, immunological inadequacy, and prolonged use of contraception. The Pap smear test, which is intended to prevent cervical cancer, finds preneoplastic changes in cervical epithelial cells. This study framework classified cervical cancer cells from Pap smears into five specified cell types using machine learning-based classification algorithms. The SIPaKMeD database is used in this investigation. This public dataset, which was manually cropped from 966 cluster cell images taken from Pap smear slides, has 4045 isolated …

Not Your Typical Tower Of Sauron: Solutions For Fermi Questions, September 2023, John Adam

Mathematics & Statistics Faculty Publications

The picture is of the tapering Chester Shot Tower, located in Chester, England. It was built in 1799 for the manufacture of lead shot for use in the Napoleonic Wars. Molten lead was poured through a sieve at the top of the tower, with the tiny droplets forming perfect spheres during the fall; these were then cooled in a vat of water at the base. This process was less labor-intensive than an earlier method using molds. It is the oldest of the three remaining shot towers in the UK. Using the parked van at the base, estimate (i) the height …

A Conceptual Framework For Managed Aquifer Recharge In The Columbia River Basalts Of The Lower Yakima River Basin, Bethany Kharrazi

All Master's Theses

In the Yakima River Basin in south-central Washington, increasing demands for water, overallocation of surface water, and a changing climate are leading to a loss of water storage and increasing water deficits in drought years. A warming climate has reduced snowpack in the Cascade Range, a vital reservoir for the irrigated agricultural industry which supports the basin’s economy. Managed aquifer recharge (MAR) is a sustainable and cost-effective approach for securing water supply by storing water underground for recovery during drought. Diminishing groundwater levels in regional basalt aquifers over the last several decades suggest there is significant storage available for intentional …

Does Sediment Supply Impact The Threshold For Initial Sediment Motion In Natural, Gravel Bedded Streams?, Emily Loucks

WWU Graduate School Collection

Sediment transport in river channels control channel morphology, streamflow, and benthic ecosystems. Predicting sediment transport rates through a channel is required for sediment management for stream restoration and aquatic habitat assessment. The critical Shields stress (τ*_c), is a dimensionless parameter used in sediment transport models that characterizes the river bed surface shear stress required to initiate sediment motion. The τ*_c is typically assumed constant in transport models, yet compilations of field data have shown that τ*_c can vary wildly, causing sediment transport models to over- or under-predict fluxes by an order of magnitude or more. Understanding …

Paleomagnetic Determination Of Vertical Axis Block Rotation Near The Doty Fault In Southwestern Washington, Charles Linneman

WWU Graduate School Collection

In this paper I present the results of paleomagnetically derived vertical axis rotations (VARs) of sites in two different flows of the Columbia River Basalt (CRB) – the 16 Ma Sentinel Bluffs member of the Grande Ronde flow and the 12 Ma Pomona Member of the Packsack Lookout – near the Doty fault in southwestern Washington. In two field seasons, I collected 99 cores from 14 sites, 11 in the Grande Ronde flow and three in the Pomona member flow. Of the 227 specimens that I demagnetized, 212 had well-defined magnetic directions. Positive fold and reversal tests results confirm the …

Glacial Loss And Threatened Fish: The Future Of Mount Rainier’S Cold-Water Bull Trout Habitats, Kathleen C. Ewen

WWU Graduate School Collection

Glaciers play a key ecological role in the river systems that they support. Cold-water reaches supplied by glacial ice serve as critical habitats for aquatic organisms that rely on specific thermal ranges to survive. Federally threatened Bull Trout (Salvelinus confluentus) require very cold temperatures, like those found in glacial systems, to complete their life cycles. However, glaciers are retreating due to climate change and are expected to continue diminishing throughout this century. Decreased glacial extent could result in warmer stream temperatures downstream from glaciers and, depending on the magnitude of stream temperature increase, cold-water habitats relied upon by Bull Trout …

Structural, Mutational, And Kinetic Characterization Of Ura4, An Isocytosine Deaminase, Ashlee Hoffman

WWU Graduate School Collection

Cytosine Deaminases (CD) are a class of enzymes found in prokaryotes and fungi that have been studied in the past due to their ability to deaminate the prodrug 5-fluorocytosine (5-FC) producing 5-fluorouracil (5-FU). 5-FU is a common anti-cancer drug that can inhibit DNA synthesis leading to cancer cell death. 5-fluorocytosine can interact with digestive bacteria leading to unwanted side effects for cancer patients. Isocytosine Deaminases (ICD) are enzymes that are of interest in the treatment of cancers using Gene Directed Enzyme Prodrug Therapy (GDEPT). ICDs can deaminate the prodrug 5-fluoroisocytosine (5-FIC) also producing the drug 5-FU.  5-FIC will likely not …

Evaluating Leaf Trait Variation In High Elevation Bristlecone Pine (Pinus Longaeva) Under Increasing Water Stress: Insights From Needle Length, Stomatal Density, And Cambial Growth, Audrey Salerno

WWU Graduate School Collection

Increasing aridification caused by climate change is altering growth patterns in trees. There is revived attention on how foliar traits respond to climate and the relationship of these traits to ring width. Bristlecone pine (Pinus longaeva, DK Bailey), a long-lived conifer found at high elevations in the cool and dry intermountain west of America, is used in paleoclimate reconstructions by measurement of their annually resolvable tree rings. The species also has annually datable needles retained on their branches for an average of 45 years making it the ideal subject for research on foliar trait and growth relationships under …

Quantifying Channel Change Following Post-Fire Debris Flows In A Steep, Coastal Stream, Big Sur, California, Telemak Olsen

WWU Graduate School Collection

Debris flows commonly occur following wildfire in steep landscapes, introducing large volumes of sediment to downstream fluvial systems. Fire-related sediment supply perturbations impact channel morphology, and importantly, fragile aquatic and riparian ecosystems downstream of disturbance. The Big Creek watershed drains 57 km² of steep chaparral and coast redwood forest along California’s Central Coast. Streams in the Big Creek watershed typically exhibit step-pool/cascade morphology and serve as vital spawning habitat for anadromous Steelhead Trout (Oncorhynchus mykiss). In 2020, 97% of the Big Creek watershed burned in the Dolan Wildfire. In January 2021, an atmospheric river event triggered a series of …

Msdrp: A Deep Learning Model Based On Multisource Data For Predicting Drug Response, Haochen Zhao, Xiaoyu Zhang, Qichang Zhao, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Motivation: Cancer heterogeneity drastically affects cancer therapeutic outcomes. Predicting drug response in vitro is expected to help formulate personalized therapy regimens. In recent years, several computational models based on machine learning and deep learning have been proposed to predict drug response in vitro. However, most of these methods capture drug features based on a single drug description (e.g. drug structure), without considering the relationships between drugs and biological entities (e.g. target, diseases, and side effects). Moreover, most of these methods collect features separately for drugs and cell lines but fail to consider the pairwise interactions between drugs and cell …

Progenitor Cell Isolation From Mouse Epididymal Adipose Tissue And Sequencing Library Construction, Qianglin Liu, Chaoyang Li, Yuxia Li, Leshan Wang, Xujia Zhang, Buhao Deng, Peidong Gao, Mohammad Shiri, Fozi Alkaifi, Junxing Zhao, Jacqueline M. Stephens, Constantine A. Simintiras, Joseph Francis, Jiangwen Sun, Xing Fu

Computer Science Faculty Publications

Here, we present a protocol to isolate progenitor cells from mouse epididymal visceral adipose tissue and construct bulk RNA and assay for transposase-accessible chromatin with sequencing (ATAC-seq) libraries. We describe steps for adipose tissue collection, cell isolation, and cell staining and sorting. We then detail procedures for both ATAC-seq and RNA sequencing library construction. This protocol can also be applied to other tissues and cell types directly or with minor modifications.

For complete details on the use and execution of this protocol, please refer to Liu et al. (2023).¹

*¹ Liu, Q., Li, C., Deng, B., Gao, P., …

Detecting Deceptive Dark-Pattern Web Advertisements For Blind Screen-Reader Users, Satwick Ram Kodandaram, Mohan Sunkara, Sampath Jayarathna, Vikas Ashok

Computer Science Faculty Publications

Advertisements have become commonplace on modern websites. While ads are typically designed for visual consumption, it is unclear how they affect blind users who interact with the ads using a screen reader. Existing research studies on non-visual web interaction predominantly focus on general web browsing; the specific impact of extraneous ad content on blind users' experience remains largely unexplored. To fill this gap, we conducted an interview study with 18 blind participants; we found that blind users are often deceived by ads that contextually blend in with the surrounding web page content. While ad blockers can address this problem via …

A Structure-Aware Generative Adversarial Network For Bilingual Lexicon Induction, Bocheng Han, Qian Tao, Lusi Li, Zhihao Xiong

Computer Science Faculty Publications

Bilingual lexicon induction (BLI) is the task of inducing word translations with a learned mapping function that aligns monolingual word embedding spaces in two different languages. However, most previous methods treat word embeddings as isolated entities and fail to jointly consider both the intra-space and inter-space topological relations between words. This limitation makes it challenging to align words from embedding spaces with distinct topological structures, especially when the assumption of isomorphism may not hold. To this end, we propose a novel approach called the Structure-Aware Generative Adversarial Network (SA-GAN) model to explicitly capture multiple topological structure information to achieve accurate …

Identifying The Serious Clinical Outcomes Of Adverse Reactions To Drugs By A Multi-Task Deep Learning Framework, Haochen Zhao, Peng Ni, Qichang Zhao, Xiao Liang, Di Ai, Shannon Erhardt, Jun Wang, Yaohang Li, Jiianxin Wang

Computer Science Faculty Publications

Adverse Drug Reactions (ADRs) have a direct impact on human health. As continuous pharmacovigilance and drug monitoring prove to be costly and time-consuming, computational methods have emerged as promising alternatives. However, most existing computational methods primarily focus on predicting whether or not the drug is associated with an adverse reaction and do not consider the core issue of drug benefit-risk assessment-whether the treatment outcome is serious when adverse drug reactions occur. To this end, we categorize serious clinical outcomes caused by adverse reactions to drugs into seven distinct classes and present a deep learning framework, so-called GCAP, for predicting the …

Dynamic Discounted Satisficing Based Driver Decision Prediction In Sequential Taxi Requests, Sree Pooja Akula

Masters Theses

"Ridesharing platforms rely on connecting available taxi drivers to potential passengers to maximize their revenue. However, predicting the stopping decision made by every driver, i.e., the final task performed during a given day, is crucial to achieving this goal. Unfortunately, little research has been done on predicting drivers’ stopping decisions, especially when they deviate from expected utility maximization behavior. This research proposes a Dynamic Discounted Satisficing (DDS) heuristic to model and learn the task at which human agents will stop working for that day, assuming that the human agents are taking sequential decisions based on their preference order. We apply …

Investigation Of Defect Production And Displacement Energies In Wurtzite Aluminum Nitride, Sean Anderson

Masters Theses

"Aluminum Nitride is an active element of sensors that monitor the performance and well-being of the nuclear reactors due to its piezoelectric properties. Yet, the variations of its properties under irradiation are largely unexplored. We report the results of the molecular dynamics simulations of the structural changes in AlN under irradiation via the knock-on atom technique. By creating and evolving the irradiation cascades due to energetic particle interaction with the atom of the crystalline lattice we determine the rate of the defect production as a function of the deposited energy. Further, we determine a displacement energy, a key characteristic that …

The Application Of Statistical Modeling To Identify Genetic Associations With Mild Traumatic Brain Injury Outcomes, Caroline Schott

Masters Theses

"Traumatic brain injury (TBI) is a growing health concern, with millions of TBI diagnoses in the United States each year. The vast majority of TBI diagnoses are mild traumatic brain injuries (mTBI), which can be challenging to manage due to variation in symptoms and outcomes. Most individuals with mTBI successfully recover quickly, but a small subset has a delayed recovery. Although the factors that contribute to this variation in recovery are not clearly understood, it is possible that genetic differences may play a role. Very few studies have investigated the association between single nucleotide polymorphisms (SNPs) with mTBI outcomes and …

Dfhic: A Dilated Full Convolution Model To Enhance The Resolution Of Hi-C Data, Bin Wang, Kun Liu, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Motivation: Hi-C technology has been the most widely used chromosome conformation capture(3C) experiment that measures the frequency of all paired interactions in the entire genome, which is a powerful tool for studying the 3D structure of the genome. The fineness of the constructed genome structure depends on the resolution of Hi-C data. However, due to the fact that high-resolution Hi-C data require deep sequencing and thus high experimental cost, most available Hi-C data are in low-resolution. Hence, it is essential to enhance the quality of Hi-C data by developing the effective computational methods.

Results: In this work, we propose …

Mitigating Anomalous Electricity Consumption In Smart Cities Using An Ai-Based Stacked-Generalization Technique, Arshid Ali, Laiq Khan, Nadeem Javaid, Safdar Hussain Bouk, Abdulaziz Aldegheishem, Nabil Alrahjeh

Computer Science Faculty Publications

Energy management and efficient asset utilization play an important role in the economic development of a country. The electricity produced at the power station faces two types of losses from the generation point to the end user. These losses are technical losses (TL) and non-technical losses (NTL). TLs occurs due to the use of inefficient equipment. While NTLs occur due to the anomalous consumption of electricity by the customers, which happens in many ways; energy theft being one of them. Energy theft majorly happens to cut down on the electricity bills. These losses in the smart grid (SG) are the …

The Birds And The Trees: Quantifying The Drivers Of Whitebark Pine Decline And Clark's Nutcracker Habitat Use In Glacier National Park, Vladimir Kovalenko

Graduate Student Theses, Dissertations, & Professional Papers

Whitebark pine (Pinus albicaulis), recently listed as threatened under the Endangered Species Act, is in steep decline in Glacier National Park, Montana, USA due to the non-native pathogen Cronartium ribicola, causal agent of the fatal disease white pine blister rust. A sample of the park’s population suggests that approximately 70 percent of whitebark pines have died, while 65 percent of the remaining trees are infected. Using landscape and climate variables, we show how geographic location, elevation, aspect, solar radiation, relative humidity, and snowpack interact with tree diameter to affect mortality, disease incidence, cone production, and regeneration. We also examine how …

Synthetic Aperture Radar Observations At Salar De Pajonales, Chile, Michael A. A. Mcinenly

Graduate Student Theses, Dissertations, & Professional Papers

Remotely sensed microwave radars provide the spatial and temporal coverage needed to improve our understanding of the relationship between moisture content and salt pan mineralogy and, ultimately, climate variability. Moisture content in the surface and near-surface crusts found in salt pan environments, such as salt pan, has a significant impact on the backscatter values recorded by synthetic aperture radar (SAR) systems. This is because moisture affects the dielectric constant and surface roughness of the saline surface, which in turn influences the amount of electromagnetic energy reflected back to the SAR sensor. Changes in backscatter values are attributed to seasonal and …

Evaluating The Use Of Environmental Tracers To Reduce Conceptual Model Uncertainty Of Hydrogeologic Models, Andrew Nordberg, Jon Graham, W. Payton Gardner

Graduate Student Theses, Dissertations, & Professional Papers

Environmental tracer concentrations for CFC12, SF6, and tritium are used in groundwater simulations to assess the ability of these tracers to reduce conceptual model uncertainty due to uncertainty of a site’s geologic and recharge characterization. The resulting groundwater simulations are characterized by site-specific hydrologic and geologic data, and with coordination from a field team with years of knowledge about the site. First-order (conceptual) uncertainty is directly addressed by using a stochastic modeling approach for spatial variability of the proposed subsurface configurations. Simulations of environmental tracer concentrations and water levels are used to assess six alternate conceptual models that are based …

Meta-Analysis Of Scent Detection Canines And Potential Factors Influencing Their Success Rates, Molly Marie Jaskinia

Graduate Student Theses, Dissertations, & Professional Papers

Objective: This is a meta-analysis focused on the success rates of scent detection canines and potential factors that could influence their accuracy. A series of statistical analyses were conducted to determine if certain demographic factors, such as the dog’s gender, age, and breed, have an effect on a scent dog’s accuracy during a search. Or if more circumstantial factors, like the dog’s level of experience in scent work, the type of target scent, and their handler’s awareness of the target’s location, affect the outcome of the search.

Materials and Methods: A dataset was created from 37 different articles consisting of …

2-Aminopyridyl Functionalized Scaffold As A Tool For Systematic Investigation Of B-Glucan Binding And Dectin-1 Activation, Jasper Alinea Aquino

Graduate Student Theses, Dissertations, & Professional Papers

Tuberculosis (TB) – an infectious disease caused by Mycobacterium tuberculosis (Mtb) – remains an epidemic worldwide contributing to millions of deaths each year. Vaccination is possibly the best means of addressing this global threat. In recent years, synergistic Th1 and Th17 immune responses have emerged as the key players for a vaccine-induced protection against TB. There is currently no vaccine approved for humans that elicits a Th17-mediated immune response. C-Type Lectin Receptors (CLR), specifically Dectin-1, a pattern recognition receptor (PRR) of β-1,3-glucans (β-glucans) primarily from fungi cell walls, is known to induce a Th17-mediated response. The Th17 response upon binding …

Beaver Dam Analogs (Bdas) Alter Carbon Pools, Fluxes, And Concentrations Of Intermountain Headwater Streams, Hilary Schultz

Graduate Student Theses, Dissertations, & Professional Papers

Beaver dam analogs (BDAs) have emerged as a climate adaptation and restoration strategy for water resource management in the drought-prone Western U.S., yet the focus has been on their influence on water quantity, overlooking effects on broader ecological components. By increasing water residence time and facilitating sediment retention, BDAs have the potential to influence carbon pools, fluxes, and concentrations. To examine the influence of BDAs on instream and riparian organic C and trace gases, we studied three intermountain headwater streams restored with BDAs two years after restoration during the summer of 2021. We found that there were subtle differences in …

Evaluating The Relative Influence Of Soil Water Potential, Soil Moisture, And Vapor Pressure Deficit On Semi-Arid Vegetation Dynamics, Kayla R. Jamerson

Graduate Student Theses, Dissertations, & Professional Papers

Knowledge of vegetation’s response to soil water availability and atmospheric demand is critical to understanding the impact of climate change on semi-arid ecosystems. However, limited field-based research has been conducted to assess the relative importance of these drivers and previous research has simplified the assessment of soil water availability by relying on soil volumetric water content (VWC) as a primary control on plant growth, which, as opposed to soil water potential (Ψsoil), does not account for the effects of soil texture on plant available water. To address these gaps, we compared remotely sensed indicators of vegetation response to field based …