Databases and Information Systems Commons^™

Cross-Domain Graph Anomaly Detection Via Anomaly-Aware Contrastive Alignment, Qizhou Wang, Guansong Pang, Mahsa Salehi, Wray Buntine, Christopher Leckie

Research Collection School Of Computing and Information Systems

Cross-domain graph anomaly detection (CD-GAD) describes the problem of detecting anomalous nodes in an unlabelled target graph using auxiliary, related source graphs with labelled anomalous and normal nodes. Although it presents a promising approach to address the notoriously high false positive issue in anomaly detection, little work has been done in this line of research. There are numerous domain adaptation methods in the literature, but it is difficult to adapt them for GAD due to the unknown distributions of the anomalies and the complex node relations embedded in graph data. To this end, we introduce a novel domain adaptation approach, …

On Generalized Degree Fairness In Graph Neural Networks, Zemin Liu, Trung Kien Nguyen, Yuan Fang

Research Collection School Of Computing and Information Systems

Conventional graph neural networks (GNNs) are often confronted with fairness issues that may stem from their input, including node attributes and neighbors surrounding a node. While several recent approaches have been proposed to eliminate the bias rooted in sensitive attributes, they ignore the other key input of GNNs, namely the neighbors of a node, which can introduce bias since GNNs hinge on neighborhood structures to generate node representations. In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes. In this paper, we first define …

Contrastive Learning Approach To Word-In-Context Task For Low-Resource Languages, Pei-Chi Lo, Yang-Yin Lee, Hsien-Hao Chen, Agus Trisnajaya Kwee, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Word in context (WiC) task aims to determine whether a target word’s occurrences in two sentences share the same sense. In this paper, we propose a Contrastive Learning WiC (CLWiC) framework to improve the learning of sentence/word representations and classification of target word senses in the sentence pair when performing WiC on lowresource languages. In representation learning, CLWiC trains a pre-trained language model’s ability to cope with lowresource languages using both unsupervised and supervised contrastive learning. The WiC classifier learning further finetunes the language model with WiC classification loss under two classifier architecture options, SGBERT and WiSBERT, which use single-encoder …

Learning Relation Prototype From Unlabeled Texts For Long-Tail Relation Extraction, Yixin Cao, Jun Kuang, Ming Gao, Aoying Zhou, Yonggang Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting entity relations from texts. However, it usually suffers from the long-tail issue. The training data mainly concentrates on a few types of relations, leading to the lack of sufficient annotations for the remaining types of relations. In this paper, we propose a general approach to learn relation prototypes from unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient training data. We learn relation prototypes as an implicit factor between entities, which reflects the meanings of relations as well …

Learning Comprehensive Global Features In Person Re-Identification: Ensuring Discriminativeness Of More Local Regions, Jiali Xia, Jianqiang Huang, Shibao Zheng, Qin Zhou, Bernt Schiele, Xian-Sheng Hua, Qianru Sun

Research Collection School Of Computing and Information Systems

Person re-identification (Re-ID) aims to retrieve person images from a large gallery given a query image of a person of interest. Global information and fine-grained local features are both essential for the representation. However, global embedding learned by naive classification model tends to be trapped in the most discriminative local region, leading to poor evaluation performance. To address the issue, we propose a novel baseline network that learns strong global feature termed as Comprehensive Global Embedding (CGE), ensuring more local regions of global feature maps to be discriminative. In this work, two key modules are proposed including Non-parameterized Local Classifier …

Online Hyperparameter Optimization For Class-Incremental Learning, Yaoyao Liu, Yingying Li, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. However, none of the existing CIL models can achieve the optimal tradeoff in different data-receiving settings—where typically the training-from-half (TFH) setting needs more stability, but the training-from-scratch (TFS) needs more plasticity. To this end, we design an online learning method that can adaptively optimize the tradeoff without knowing the setting as a priori. Specifically, we first introduce the …

Real-Time Hierarchical Map Segmentation For Coordinating Multi-Robot Exploration, Tianze Luo, Zichen Chen, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Coordinating a team of autonomous agents to explore an environment can be done by partitioning the map of the environment into segments and allocating the segments as targets for the individual agents to visit. However, given an unknown environment, map segmentation must be conducted in a continuous and incremental manner. In this paper, we propose a novel real-time hierarchical map segmentation method for supporting multi-agent exploration of indoor environments, wherein clusters of regions of segments are formed hierarchically from randomly sampled points in the environment. Each cluster is then assigned with a cost-utility value based on the minimum cost possible …

Scalable And Globally Optimal Generalized L1 K-Center Clustering Via Constraint Generation In Mixed Integer Linear Programming, Aravinth Chembu, Scott Sanner, Hassan Khurram, Akshat Kumar

Research Collection School Of Computing and Information Systems

The k-center clustering algorithm, introduced over 35 years ago, is known to be robust to class imbalance prevalent in many clustering problems and has various applications such as data summarization, document clustering, and facility location determination. Unfortunately, existing k-center algorithms provide highly suboptimal solutions that can limit their practical application, reproducibility, and clustering quality. In this paper, we provide a novel scalable and globally optimal solution to a popular variant of the k-center problem known as generalized L1 k-center clustering that uses L1 distance and allows the selection of arbitrary vectors as cluster centers. We show that this clustering objective …

The Application Of Graph Technology For Improving Entity Resolution Results In The Context Of Group Membership, Md Abdus Salam Siddique

Theses and Dissertations

The main objective of Entity resolution (ER) is to find duplicate records within the same data table from the same source or different data tables from various sources. A traditional pair-wise supervised entity resolution matching depends on pre-built rules for finding matched records. On the other hand, unsupervised or semisupervised also relies on pair-wise matching. In the maximum case, group membership is left behind for consideration. In this dissertation, I have discussed the design, implementation and evaluation of a graph-based entity resolution for group membership to enhance the pair-wise matching ER system. I have designed and implemented a pipeline for …

Integrated Organizational Machine Learning For Aviation Flight Data, Michael J. Pritchard, Paul Thomas, Eric Webb, Jon Martin, Austin Walden

National Training Aircraft Symposium (NTAS)

An increased availability of data and computing power has allowed organizations to apply machine learning techniques to various fleet monitoring activities. Additionally, our ability to acquire aircraft data has increased due to the miniaturization of small form factor computing machines. Aircraft data collection processes contain many data features in the form of multivariate time-series (continuous, discrete, categorical, etc.) which can be used to train machine learning models. Yet, three major challenges still face many flight organizations 1) integration and automation of data collection frameworks, 2) data cleanup and preparation, and 3) embedded machine learning framework. Data cleanup and preparation has …

Development Of Open-Source Software 'Pystage', Victor T. Norman, Brandon Husted, Zhonglin 'Loya' Niu

Summer Research

PyStage is an open-source project that seeks to help students bridge the gap between block-based programming in Scratch and text-based programming in Python.

A New Credit Scoring Model To Reduce Potential Predatory Lending: A Design Science Approach, Anna Zakowska

CGU Theses & Dissertations

This research examines the potential impact of implementing a novel credit scoring model that integrates attributes beyond the traditional FICO model. It aims to address issues related to predatory lending and the financial exclusion affecting individuals often categorized as 'credit invisible,' 'credit unscorable,' 'unbanked,' and 'underbanked.' These individuals typically face difficulties in establishing or repairing a credit history, which poses a challenge for financial institutions in accurately evaluating their creditworthiness. This gap in the credit assessment process often opens doors to unfair lending practices. To tackle this problem, a systematically designed, built, tested, and evaluated innovative credit scoring model was …

Querying The Past: Automatic Source Attribution With Language Models, Ryan Muther, Mathew Barber, David Smith

Faculty & Staff Publications

This paper explores new methods for locating the sources used to write a text by 昀椀ne-tuning a variety of language models to rerank candidate sources. These methods promise to shed new light on traditions with complex citational practices, such as in medieval Arabic where citations are ambiguous and boundaries of quotation are poorly defined. After retrieving candidates sources using a baseline BM25 retrieval model, a variety of reranking methods are tested to see how effective they are at the task of source attribution. We conduct experiments on two datasets—English Wikipedia and medieval Arabic historical writing—and employ a variety of retrieval- …

An Empirical Assessment Of The Use Of Password Workarounds And The Cybersecurity Risk Of Data Breaches, Michael Joseph Rooney

CCAC Theses and Dissertations

Passwords have been used for a long time to grant controlled access to classified spaces, electronics, networks, and more. However, the dramatic increase in user accounts over the past few decades has exposed the realization that technological measures alone cannot ensure a high level of IS security; this leaves the end-users holding a critical role in protecting their organization and personal information. The increased use of IS as a working tool for employees increases the number of accounts and passwords required. Despite being more aware of password entropy, users still often participate in deviant password behaviors, known as ‘password workarounds’ …

Sequence Checking And Deduplication For Existing Fingerprint Databases, Tahsin Islam Sakif

Graduate Theses, Dissertations, and Problem Reports (ETD)

Biometric technology is a rapidly evolving field with applications that range from access to devices to border crossing and entry/exit processes. Large-scale applications to collect biometric data, such as border crossings result in multimodal biometric databases containing thousands of identities. However, due to human operator error, these databases often contain many instances of image labeling and classification; this is due to the lack of training and throughput pressure that comes with human error. Multiple entries from the same individual may be assigned to a different identity. Rolled fingerprints may be labeled as flat images, a face image entered into a …

Go Green With Ecosia: The Search Engine With A Sustainable Business Model, James Thibeault

Library Publications

Ecosia, a non-profit search engine, is not only a thriving business but is also directly responsible for planting over 185 million trees. Focusing on sustainability and social responsibility, Ecosia demonstrates how business models can positively impact the environment.

Knowledge Discovery On The Integrative Analysis Of Electrical And Mechanical Dyssynchrony To Improve Cardiac Resynchronization Therapy, Zhuo He

Dissertations, Master's Theses and Master's Reports

Cardiac resynchronization therapy (CRT) is a standard method of treating heart failure by coordinating the function of the left and right ventricles. However, up to 40% of CRT recipients do not experience clinical symptoms or cardiac function improvements. The main reasons for CRT non-response include: (1) suboptimal patient selection based on electrical dyssynchrony measured by electrocardiogram (ECG) in current guidelines; (2) mechanical dyssynchrony has been shown to be effective but has not been fully explored; and (3) inappropriate placement of the CRT left ventricular (LV) lead in a significant number of patients.

In terms of mechanical dyssynchrony, we utilize an …

A Geospatial Analysis Of Crime Hotspots, Campus Safety Measures, And The Campus Community’S Perceived Safety At Murray State University, Rachel Stuckey

Murray State Theses and Dissertations

Murray State University (Murray State) is in far Western Kentucky. Murray State prides itself on being a safe campus for prospective students. In this study spatial analysis was used to analyze the relationship among crime hotspots, campus safety measures, and students’ perception of safety on campus the campus of Murray State. A survey was distributed to students to determine the areas of the campus where students feel safe and unsafe. Geographical Information Systems (GIS) were used to determine the location of crime hotspots over eight years (2014-2022) to measure the spatial relationship between logged crime hotspots and perceived safe and …

Dual-View Preference Learning For Adaptive Recommendation, Zhongzhou Liu, Yuan Fang, Min Wu

Research Collection School Of Computing and Information Systems

While recommendation systems have been widely deployed, most existing approaches only capture user preferences in the , i.e., the user's general interest across all kinds of items. However, in real-world scenarios, user preferences could vary with items of different natures, which we call the . Both views are crucial for fully personalized recommendation, where an underpinning macro-view governs a multitude of finer-grained preferences in the micro-view. To model the dual views, in this paper, we propose a novel model called Dual-View Adaptive Recommendation (DVAR). In DVAR, we formulate the micro-view based on item categories, and further integrate it with the …

Dashboard Design Mining And Recommendation, Yanna Lin, Haotian Li, Aoyu Wu, Yong Wang, Huamin Qu

Research Collection School Of Computing and Information Systems

Dashboards, which comprise multiple views on a single display, help analyze and communicate multiple perspectives of data simultaneously. However, creating effective and elegant dashboards is challenging since it requires careful and logical arrangement and coordination of multiple visualizations. To solve the problem, we propose a data-driven approach for mining design rules from dashboards and automating dashboard organization. Specifically, we focus on two prominent aspects of the organization: , which describes the position, size, and layout of each view in the display space; and, which indicates the interaction between pairwise views. We build a new dataset containing 854 dashboards crawled online, …

Fridge Tracker And Recipe Provider : Fridgechamp, Matt Dudek

Williams Honors College, Honors Research Projects

FridgeChamp is a website to allow people to track their fridge/pantry contents while providing them recipes they can make with said ingredients. Currently there are few ingredient trackers and recipe matchers that exist as websites, and of those many lack simplistic recipes that a home chef would use. In addition to lacking some recipes, many tracker/recipe apps do not have a function to remove from your stock what a recipe requires, making you tediously update the stock every time you cook/use something.

High Performance Distributed File System Based On Blockchain, Ajinkya Rajguru

Master's Projects

Distributed filesystem architectures use commodity hardware to store data on a large scale with maximum consistency and availability. Blockchain makes it possible to store information that can never be tampered with and incentivizes a traditional decentralized storage system. This project aimed to implement a decentralized filesystem that leverages the blockchain to keep a record of all the transactions on it. A conventional filesystem viz. GFS [1] or HDFS [2] uses designated servers owned by their organization to store the data and are governed by a master service. This project aimed at removing a single point of failure and makes use …

Romeo And Juliet Word Cloud, Ml Tlachac

Center for Teaching Excellence (CTE)

PowerPoint presented at the Annual Spring Teaching Summit: Teaching and Learning Demos produced by the Center for Teaching Excellence.

Campus Safety Data Gathering, Classification, And Ranking Based On Clery-Act Reports, Walaa F. Abo Elenin

College of Graduate Studies: Theses & Dissertations

Most existing campus safety rankings are based on criminal incident history with minimal or no consideration of campus security conditions and standard safety measures. Campus safety information published by universities/colleges is usually conceptual/qualitative and not quantitative and are based-on criminal records of these campuses. Thus, no explicit and trusted ranking method for these campuses considers the level of compliance with the standard safety measures. A quantitative safety measure is important to compare different campuses easily and to learn about specific campus safety conditions.

In this thesis, we utilize Clery-Act reports of campuses to automatically analyze their safety conditions and generate …

Graph Deep Learning Based Hashtag Recommender For Reels On Social Media, Sriya Balineni

Master's Projects

Many businesses, including Facebook, Netflix, and YouTube, rely heavily on a recommendation system. Recommendation systems are algorithms that attempt to provide consumers with relevant suggestions for items such as movies, videos, or reels (microvideos) to watch, hashtags for their posts, songs to listen to, and products to purchase. In many businesses, recommender systems are essential because they can generate enormous amounts of revenue and make the platform stand out when compared to others. Reels are a feature of the social media platforms that enable users to create and share videos of up to sixty seconds in length. Individuals, businesses, and …

Wikipedia Web Table Interpretation, Keyword-Based Search, And Ranking, Kartikee Dabir

Master's Projects

Information retrieval and data interpretation on the web, for the purpose of gaining knowledgeable insights, has been a widely researched topic from the onset of the world wide web or what is today popularly known as the internet. Web tables are structured tabular data present amidst unstructured, heterogenous data on the web. This makes web tables a rich source of information for a variety of tasks like data analysis, data interpretation, and information retrieval pertaining to extracting knowledge from information present on the web. Wikipedia tables which are a subset of web tables hold a huge amount of useful data, …

Robust Cache System For Web Search Engine Yioop, Rushikesh Padia

Master's Projects

Caches are the most effective mechanism utilized by web search engines to optimize the performance of search queries. Search engines employ caching at multiple levels to improve its performance, for example, caching posting list and caching result set. Caching query results reduces overhead of processing frequent queries and thus saves a lot of time and computing power. Yioop is an open-source web search engine which utilizes result cache to optimize searches. The current implementation utilizes a single dynamic cache based on Marker’s algorithm. The goal of the project is to improve the performance of cache in Yioop. To choose a …

Nosql Databases In Kubernetes, Parth Sandip Mehta

Master's Projects

With the increasing popularity of deploying applications in containers, Kubernetes (K8s) has become one of the most accepted container orchestration systems. Kubernetes helps maintain containers smoothly and simplifies DevOps with powerful automations. It was originally developed as a tool to manage stateless microservices that run seamlessly in containers. The ephemeral nature of pods, the smallest deployable unit, in Kubernetes was well-aligned with stateless applications since destroying and recreating pods didn’t impact applications. There was a need to provision solutions around stateful workloads like databases so as to take advantage of K8s. This project explores this need, the challenges associated and …

Knowledge-Sharing Practice As A Tool In Organizational Development In Nigerian Higher Educational Institutions, Emmanuel Ajiri Ojo

Walden Dissertations and Doctoral Studies

AbstractUnderstanding knowledge management is key to understanding organizational development and innovations. Inadequate knowledge-sharing practices in Nigerian educational institutions has impeded innovation and management development. The purpose of this qualitative modified Delphi study was to seek consensus among administrators from Nigerian educational institutions and scholars from Nigerian universities regarding knowledge-sharing practices that nourish innovation in Nigerian higher educational institutions. The organizational development framework was used to guide the study. Data collection included a nonprobability purposive sampling of 25 participants and three rounds of surveys administered online. A consensus was reached on eight factors after coding and thematic analysis: setting knowledge-sharing expectations, …

Secure Strategies For Internet Of Things Implementation In Warehouse Environments, Oladapo Opegbemi

Walden Dissertations and Doctoral Studies

The internet of things (IoT) in warehouse environments may present security issues and challenges. These issues and challenges may impact information technology (IT) leadership in warehouse environments because a lack of security strategy adoption may lead to increased network breaches. Grounded in the technology acceptance model, the purpose of this quantitative correlational study was to examine the relationship between IT leaderships’ perceived ease-of-use, perceived usefulness of IoT devices, and their intent to adopt security strategies for IoT implementation in warehouse environments. Data were collected from IT leaders in North Texas warehouse environments using a peer-reviewed adoption survey from PsycTESTS.org. The …