Databases and Information Systems Commons^™

Empowering Crisis Information Extraction Through Actionability Event Schemata And Domain-Adaptive Pre-Training, Yuhao Zhang, Siaw Ling Lo, Phyo Yi Win Myint

Research Collection School Of Computing and Information Systems

One of the persistent challenges in crisis detection is inferring actionable information to support emergency response. Existing methods focus on situational awareness but often lack actionable insights. This study proposes a holistic approach to implementing an actionability extraction system on social media, including requirement gathering, selection of machine learning tasks, data preparation, and integration with existing resources, providing guidance for governments, civil services, emergency workers, and researchers on supplementing existing channels with actionable information from social media. Our solution leverages an actionability schema and domain-adaptive pre-training, improving upon the state-of-the-art model by 5.5% and 10.1% in micro and macro F1 …

Defending Federated Recommender Systems Against Untargeted Attacks: A Contribution-Aware Robust Aggregation Scheme, Ruicheng Liang, Yuanchun Jiang, Feida Zhu, Ling Cheng, Huiwen Liu

Research Collection School Of Computing and Information Systems

Federated recommender systems (FedRSs) effectively tackle the tradeoff between recommendation accuracy and privacy preservation. However, recent studies have revealed severe vulnerabilities in FedRSs, particularly against untargeted attacks seeking to undermine their overall performance. Defense methods employed in traditional recommender systems are not applicable to FedRSs, and existing robust aggregation schemes for other federated learning-based applications have proven ineffective in FedRSs. Building on the observation that malicious clients contribute negatively to the training process, we design a novel contribution-aware robust aggregation scheme to defend FedRSs against untargeted attacks, named contribution-aware Bayesian knowledge distillation aggregation (ConDA), comprising two key components for the …

Qlorax: Heuristic-Guided Fine-Tuning Of Llama-2 For Domain Adaptation In Entrepreneurship, Gaurob Saha

Theses and Dissertations

This thesis presents a study on the fine-tuning of large language models (LLMs) for domain-specific applications using limited data. We fine-tuned the LLaMA-2 (7B) model on a curated entrepreneurial dataset containing 3,545 human-written question-answer pairs, of which 3,095 were used for training and 450 were reserved for evaluation. A complete fine-tuning and evaluation pipeline was developed, which included clustering human-written answers, generating centroid-based summaries for each cluster, and evaluating the model's generated responses through cosine similarity.

Training was carried out over five epochs, with model performance evaluated after each epoch. The fine-tuned model demonstrated strong semantic alignment with human-written content, …

Digital Platform Transitions In The Finance Industry: Three Essays, Cheryll-Ann Wilson

2025

This three-paper dissertation is motivated by an emerging dichotomy in the financial sector: an increasing use of an open-source digital platform—the Python platform—in an industry that historically has been wedded to proprietary systems.

Chapter 1 is a qualitative pilot study to ascertain which factors are likely to motivate investment professionals to select Python versus other tools and/or technologies. I find that efficiency and access to industry-specific libraries—notably Pandas and NumPy—are significant motivators in their selection of Python over Excel. Chapters 2 and 3 examine the issues through a sequential, exploratory mixed methods approach.

Chapter 2—the qualitative field study—investigates how and …

Tintin: A Unified Hardware Performance Profiling Infrastructure To Uncover And Manage Uncertainty, Ao Li, Marion Sudvarg, Zihan Li, Sanjoy Baruah, Chris Gill, Ning Zhang

Computer Science Faculty Research & Creative Works

Hardware performance counters (HPCs) enable the measurement of microarchitectural events, which are crucial for tracking and predicting program behavior. High-fidelity measurement and precise attribution are essential for accurate profiling. However, existing profiling tools have fundamental challenges in both aspects. In measurement, numerous events compete for limited hardware monitoring resources; while for attribution, applications have diverse requirements, but systems provide limited support. Existing tools mitigate the former limitation through event multiplexing, but this approach introduces non-trivial errors. The latter limitation, however, remains largely unaddressed. This paper introduces Tintin, an HPC profiling infrastructure with a modular three-component design that addresses both challenges. …

Leaf-Based Varietal Categorization Of Sweetpotato (Ipomoea Batatas L. Lam.), A Potentially Healthful Vegetable, Using Image Processing And K-Means Clustering, Shahidul Islam, Md Towfiqur Rahman, Md Hamidul Rahman, Abdul Momin

Department of Agricultural and Biological Systems Engineering: Dissertations, Theses, and Student Research

Sweetpotato (Ipomoea batatas Lam) leaves contain higher concentrations of phenolic compounds, flavonoids, and carotenoids that are remarkable in health promotion. However, the nutrient content in sweetpotato leaves varies from variety to variety, and leaf shape and color are the key identifying factors for the varietal classification of sweetpotatoes. So, detecting sweetpotato leaves is essential for the in-situ identification of sweetpotato varieties and for developing intelligent agricultural systems. This study aimed to create a leaf-shape-based varietal classification technique for sweetpotato using image processing techniques coupled with a K-means clustering algorithm. 38 leaf images (RGB) of two sweetpotato cultivars were collected …

In-Season Nitrogen Mmanagement: Leveraging Data Visualization For Precision Agriculture, Chathurika Harshani Narayana

Department of Agricultural and Biological Systems Engineering: Dissertations, Theses, and Student Research

Effective nitrogen management is vital for sustainable agriculture, impacting both crop yield and environmental health. Traditional methods often use fixed application rates set before planting, which do not adapt to changing crop needs during the season. This can lead to over- or under-application, reducing efficiency and sustainability. While modern tools like sensors, satellites, and UAVs provide valuable real-time data on crop and field conditions, integrating and using this data to guide timely nitrogen decisions remains a major challenge. In-season nitrogen management offers a solution by allowing for dynamic adjustments to nitrogen applications, addressing crop needs as they arise. This approach …

Development And Application Of Computational Tools For Data-Driven Materials Science., Logan L. Lang

Graduate Theses, Dissertations, and Problem Reports (ETD)

Modern materials science generates vast amounts of data from computational simulations and experiments, creating significant challenges for data processing and analysis. This thesis addresses these challenges through the development and application of computational tools within the framework of Material Data Science (MDS). Contributions span the four pillars of MDS: Material/Molecular Data, Algorithms, Databases, and High-Throughput Processes—with a primary focus on the Algorithm, Data, Database pillars.

For the Algorithm pillar, two Python libraries were developed to streamline common analysis tasks. PyProcar simplifies the post-processing and visualization of electronic structure data (band structures, density of states, Fermi surfaces) obtained from various Density …

University Of Akron Commuter Rideshare Service (Uacrs), Nicholas Szijarto

Williams Honors College, Honors Research Projects

At the University of Akron, a large number of students commute to and from the campus. A majority of them use their own personal vehicles every day. I propose a web-based application that would benefit the University by offering ridesharing services for commuting students and faculty. This would be made with an Angular frontend, a Spring Boot Java backend, and a MySQL database. I would hope to allow this application to have users register and then input their schedules of travel, including starting point, destination, and the time of this transfer. The program could suggest groups of students to travel …

Connecting Worlds: Travelmate’S Bidding System For Personalized Travel Experiences, Suman Khadka

Williams Honors College, Honors Research Projects

TravelMate is a web platform that connects travelers with local guides through a personalized trip posting system along with real time bidding from freelancer guides. This platform utilizes Next.js for a responsive frontend, and Supabase for managing database and backend RESTful API, using PostgREST - a thin API layer on top of Postgres. This platform is ideal for anyone looking to explore new places with a freelancer guide and gain cultural insights from a local expert who understands the place deeply.

Flowing Together Or Alone: Impact Of Collaboration In The Metaverse, Fiona Fui-Hoon Nah, Brenda Eschenbrenner, Langtao Chen

Research Collection School Of Computing and Information Systems

The metaverse is the next-generation Internet (Web3) that facilitates social connections and collaborations in a virtual world environment. Given the potential of the metaverse to provide more satisfying and effective means of remote collaborations, exploring the possibility of leveraging the metaverse for these endeavors is warranted. Therefore, an important question to address is whether greater engagement occurs when tasks are completed collaboratively versus individually in the metaverse. We address this question by drawing on flow and transportation theories to hypothesize the effect of carrying out a creative task in the metaverse collaboratively versus alone on one's cognitive absorption, a contextually …

Your Cursor Reveals: On Analyzing Workers’ Browsing Behavior And Annotation Quality In Crowdsourcing Tasks, Pei-Chi Lo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

In this work, we investigate the connection between browsing behavior and task quality of crowdsourcing workers performing annotation tasks that require information judgements. Such information judgements are often required to derive ground truth answers to information retrieval queries. We explore the use of workers’ browsing behavior to directly determine their annotation result quality. We hypothesize user attention to be the main factor contributing to a worker’s annotation quality. To predict annotation quality at the task level, we model two aspects of task-specific user attention, also known as general and semantic user attentions . Both aspects of user attention can be …

Label Correlated Contrastive Learning For Medical Report Generation, Xinyao Liu, Junchang Xin, Bing Tian Dai, Qi Shen, Zhihong Huang, Zhiqiong Wang

Research Collection School Of Computing and Information Systems

Background and Objective: Automatic generation of medical reports reduces both the burden on radiologists and the possibility of errors due to the inexperience of radiologists. The model that utilizes attention mechanism and contrastive learning can generate medical reports by capturing both general and specific semantics. However, existing contrastive learning methods ignore the specificity of medical data, that is, a patient may suffer from multiple diseases at the same time. This means that the lack of fine-grained relationships for contrastive learning will lead to the problem of insufficient specificity. Methods: To address the above problem, a label correlated contrastive learning method …

Risk Spillover Effect Of China-Asean Supply Chains: Insights Of Industrial Transfer, Zeyang Bian, Yuning Zhang, Keng Siau, Yaqian Zhang, Jianjia He

Research Collection School Of Computing and Information Systems

As labour costs in China increase, labour-intensive industries are migrating to ASEAN countries, attracted by lower labour costs and market potential. This shift not only affects the economies of China and ASEAN but also reshapes the global manufacturing landscape. This paper investigates the correlation and spillover of supply chain risks using production exposure indicators derived from inter-country input-output data and the R-Vine Copula model. We assess the risk spillover of each country within the global supply chain. Our findings indicate that industrial relocation can significantly alter supply chain structures, thereby affecting the concentration and direction of risks. While China's role …

Performance Evaluation Of Newsql Databases In A Distributed Architecture, Zhiyao Zhang, Alan @ Ali Madjelisi Megargel, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

In the last decade, application architectures have evolved drastically, moving from monolithic architectures to distributed architectures where deployment has shifted from dedicated on-premises servers to the cloud. Distributed architectures and cloud computing has enabled businesses to scale their application components across different geographical locations. While it is easy to scale the application layer, scaling its database layer that relies on traditional SQL databases is challenging and often is a common source of bottlenecks when it comes to application performance. This paper evaluates the performance characteristics between two NewSQL databases solutions, MySQL NDB Cluster vs. TIBCO ActiveSpaces IMDG. Serving as an …

Llms-Based Augmentation For Domain Adaptation In Long-Tailed Food Datasets, Qing Wang, Chong-Wah Ngo, Ee-Peng Lim, Qianru Sun

Research Collection School Of Computing and Information Systems

Training a model for food recognition is challenging because the training samples, which are typically crawled from the Internet, are visually different from the pictures captured by users in the free-living environment. In addition to this domain-shift problem, the real-world food datasets tend to be long-tailed distributed and some dishes of different categories exhibit subtle variations that are difficult to distinguish visually. In this paper, we present a framework empowered with large language models (LLMs) to address these challenges in food recognition. We first leverage LLMs to parse food images to generate food titles and ingredients. Then, we project the …

Interactive Video Search With Multi-Modal Llm Video Captioning, Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Cross-modal representation learning is essential for interactive text-to-video search tasks. However, the representation learning is limited by the size and quality of video-caption pairs. To improve the search accuracy, we propose to enlarge the size of available video-caption pairs by leveraging multi-model LLM on video captioning. Specifically, we use LLM to generate video captions for a large video collection (i.e., WebVid dataset) and use the generated video-caption pairs to pre-train a text-to-video search model. Additionally, we use LLM to generate fine-grained captions for test video collections to enable text-to-caption retrieval. Furthermore, we build a semantic overview of the retrieved rank …

Dims: Distributed Index For Similarity Search In Metric Spaces, Yifan Zhu, Chengyang Luo, Tang Qian, Lu Chen, Yunjun Gao, Baihua Zheng

Research Collection School Of Computing and Information Systems

Similarity search finds objects that are similar to a given query object based on a similarity metric. As the amount and variety of data continue to grow, similarity search in metric spaces has gained significant attention. Metric spaces can accommodate any type of data and support flexible distanc e metrics, making similarity search in metric spaces beneficial for many real-world applications, such as multimedia retrieval, personalized recommendation, trajectory analytics, data mining, decision planning, and distributed servers. However, existing studies mostly focus on indexing metric spaces on a single machine, which faces efficiency and scalability limitations with increasing data volume and …

Learning To Rank Aspects And Opinions For Comparative Explanations, Trung Hoang Le, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Comparative recommendation explanations help to make sense of recommendations by comparing a recommended item along some aspects of interest with one or many items being considered. This work extends the notion of comparative explanations, by going beyond merely better/worse statements, to further incorporate aspect-level opinions for more informative comparisons. To enhance the quality of both the personalized recommendation and the explanation, we incorporate optimization objectives that preserve relative rankings of aspects and opinions, in addition to the classical rankings of overall preferences for items. We integrate the multiple ranking objectives and multi-tensor factorization together. Experiments on datasets of different domains …

An Agent-Based Computational Finance Simulation Model To Study Market Efficiency, Wei Feng, Keng Siau, Wee-Yeap Lau, Lim-Thye Goh, Haonan Chen

Research Collection School Of Computing and Information Systems

The advancement of computational modeling, data systems, and digital infrastructure has enabled the rise of agent-based computational finance (ACF). This study models interactions among heterogeneous investors. By embedding behavioral logics such as environmental, social, and governance (ESG) preferences and volatility thresholds, the model captures microstructural dynamics under different trading rules. Using ACF, the authors compare transaction plus 0 day (T+0) to transaction plus 1 day (T+1). Results show that T+0 improves price discovery, deepens liquidity, and reduces transaction costs. From a computational perspective, this research contributes to ACF by showing how policy logic and investor heterogeneity can be encoded and …