Physical Sciences and Mathematics Commons^™

Blended Learning In The Wake Of Ict Infrastructure Deficiencies: The Case Of A Zimbabwean University, Lucia Makwasha, Sam Jnr Takavarasha, Hazel Mubango

African Conference on Information Systems and Technology

In the wake of debates between actors in the Zimbabwean higher education sector about the effectiveness of e-learning models, it is important to investigate the effectiveness of using blended learning at a time when infrastructure challenges are disrupting ICT access. This paper aims to address this quest for a deeper understanding by investigating students' perceptions of blended learning at a selected Zimbabwean university. Twelve in-depth interviews were conducted with students from a Zimbabwean university that employs blended learning under an interpretivist paradigm. Vygotsky's Zone of Proximal Development (ZPD) was used for conceptualising students' cognitive development and Engestrom's (2003) Third-generation Activity …

On Predicting Esg Ratings Using Dynamic Company Networks, Gary Ang, Zhiling Guo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Environmental, social and governance (ESG) considerations play an increasingly important role due to the growing focus on sustainability globally. Entities, such as banks and investors, utilize ESG ratings of companies issued by specialized rating agencies to evaluate ESG risks of companies. The process of assigning ESG ratings by human analysts is however laborious and time intensive. Developing methods to predict ESG ratings could alleviate such challenges, allow ESG ratings to be generated in a more timely manner, cover more companies, and be more accessible. Most works study the effects of ESG ratings on target variables such as stock prices or …

Graph-Level Anomaly Detection Via Hierarchical Memory Networks, Chaoxi Niu, Guansong Pang, Ling Chen

Research Collection School Of Computing and Information Systems

Graph-level anomaly detection aims to identify abnormal graphs that exhibit deviant structures and node attributes compared to the majority in a graph set. One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole. To tackle this challenge, we propose a novel approach called Hierarchical Memory Networks (HimNet), which learns hierarchical memory modules---node and graph memory modules---via a graph autoencoder network architecture. The node-level memory module is trained to model fine-grained, internal graph interactions among nodes for detecting locally abnormal graphs, while the …

The Devil Is In The Tails: How Long-Tailed Code Distributions Impact Large Language Models, Xin Zhou, Kisub Kim, Bowen Xu, Jiakun Liu, Donggyun Han, David Lo

Research Collection School Of Computing and Information Systems

Learning-based techniques, especially advanced Large Language Models (LLMs) for code, have gained considerable popularity in various software engineering (SE) tasks. However, most existing works focus on designing better learning-based models and pay less attention to the properties of datasets. Learning-based models, including popular LLMs for code, heavily rely on data, and the data's properties (e.g., data distribution) could significantly affect their behavior. We conducted an exploratory study on the distribution of SE data and found that such data usually follows a skewed distribution (i.e., long-tailed distribution) where a small number of classes have an extensive collection of samples, while a …

Rosas: Deep Semi-Supervised Anomaly Detection With Contamination-Resilient Continuous Supervision, Hongzuo Xu, Yijie Wang, Guansong Pang, Songlei Jian, Ning Liu, Yongjun Wang

Research Collection School Of Computing and Information Systems

Semi-supervised anomaly detection methods leverage a few anomaly examples to yield drastically improved performance compared to unsupervised models. However, they still suffer from two limitations: 1) unlabeled anomalies (i.e., anomaly contamination) may mislead the learning process when all the unlabeled data are employed as inliers for model training; 2) only discrete supervision information (such as binary or ordinal data labels) is exploited, which leads to suboptimal learning of anomaly scores that essentially take on a continuous distribution. Therefore, this paper proposes a novel semi-supervised anomaly detection method, which devises contamination-resilient continuous supervisory signals. Specifically, we propose a mass interpolation method …

Generative Model-Based Testing On Decision-Making Policies, Zhuo Li, Xiongfei Wu, Derui Zhu, Mingfei Cheng, Siyuan Chen, Fuyuan Zhang, Xiaofei Xie, Lei Ma, Jianjun Zhao

Research Collection School Of Computing and Information Systems

The reliability of decision-making policies is urgently important today as they have established the fundamentals of many critical applications, such as autonomous driving and robotics. To ensure reliability, there have been a number of research efforts on testing decision-making policies that solve Markov decision processes (MDPs). However, due to the deep neural network (DNN)-based inherit and infinite state space, developing scalable and effective testing frameworks for decision-making policies still remains open and challenging.In this paper, we present an effective testing framework for decision-making policies. The framework adopts a generative diffusion model-based test case generator that can easily adapt to different …

When Routing Meets Recommendation: Solving Dynamic Order Recommendations Problem In Peer-To-Peer Logistics Platforms, Zhiqin Zhang, Waldy Joe, Yuyang Er, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Peer-to-Peer (P2P) logistics platforms, unlike traditional last-mile logistics providers, do not have dedicated delivery resources (both vehicles and drivers). Thus, the efficiency of such operating model lies in the successful matching of demand and supply, i.e., how to match the delivery tasks with suitable drivers that will result in successful assignment and completion of the tasks. We consider a Same-Day Delivery Problem (SDDP) involving a P2P logistics platform where new orders arrive dynamically and the platform operator needs to generate a list of recommended orders to the crowdsourced drivers. We formulate this problem as a Dynamic Order Recommendations Problem (DORP). …

Understanding Multi-Homing And Switching By Platform Drivers, Xiaotong Guo, Andreas Haupt, Hai Wang, Rida Qadri, Jinhua Zhao

Research Collection School Of Computing and Information Systems

Freelance drivers in the shared mobility market frequently switch or work for multiple platforms, affecting driver labor supply. Due to the importance of driver labor supply for the shared mobility market, understanding drivers’ switching and multi-homing behavior is vital to managing service quality on – and effective regulation of – mobility platforms. However, a lack of individual-level data on driver behavior has thus far impeded a deeper understanding. This paper taxonomizes and estimates perceived switching and multi-homing frictions on mobility platforms. Based on a structural model of driver labor supply, we estimate switching and multi-homing costs in a platform duopoly …

Threshold Attribute-Based Credentials With Redactable Signature, Rui Shi, Huamin Feng, Yang Yang, Feng Yuan, Yingjiu Li, Hwee Hwa Pang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Threshold attribute-based credentials are suitable for decentralized systems such as blockchains as such systems generally assume that authenticity, confidentiality, and availability can still be guaranteed in the presence of a threshold number of dishonest or faulty nodes. Coconut (NDSS'19) was the first selective disclosure attribute-based credentials scheme supporting threshold issuance. However, it does not support threshold tracing of user identities and threshold revocation of user credentials, which is desired for internal governance such as identity management, data auditing, and accountability. The communication and computation complexities of Coconut for verifying credentials are linear in the number of each user's attributes and …

Continual Collaborative Filtering Through Gradient Alignment, Dinh Hieu Do, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

A recommender system operates in a dynamic environment where new items emerge and new users join the system, resulting in ever-growing user-item interactions over time. Existing works either assume a model trained offline on a static dataset (requiring periodic re-training with ever larger datasets); or an online learning setup that favors recency over history. As privacy-aware users could hide their histories, the loss of older information means that periodic retraining may not always be feasible, while online learning may lose sight of users' long-term preferences. In this work, we adopt a continual learning perspective to collaborative filtering, by compartmentalizing users …

Real: A Representative Error-Driven Approach For Active Learning, Cheng Chen, Yong Wang, Lizi Liao, Yueguo Chen, Xiaoyong Du

Research Collection School Of Computing and Information Systems

Given a limited labeling budget, active learning (al) aims to sample the most informative instances from an unlabeled pool to acquire labels for subsequent model training. To achieve this, al typically measures the informativeness of unlabeled instances based on uncertainty and diversity. However, it does not consider erroneous instances with their neighborhood error density, which have great potential to improve the model performance. To address this limitation, we propose Real, a novel approach to select data instances with Representative Errors for Active Learning. It identifies minority predictions as pseudo errors within a cluster and allocates an adaptive sampling budget for …

The Power Of Identity Cues In Text-Based Customer Service: Evidence From Twitter, Yang Gao, Huaxia Rui, Shujing Sun

Research Collection School Of Computing and Information Systems

Text-based customer service is emerging as an important channel through which companies can assist customers. However, the use of few identity cues may cause customers to feel limited social presence and even suspect the human identity of agents, especially in the current age of advanced algorithms. Does such a lack of social presence affect service interactions? We studied this timely question by evaluating the impact of customers’ perceived social presence on service outcomes and customers’ attitudes toward agents. Our identification strategy hinged on Southwest Airlines’ sudden requirement to include a first name in response to service requests on Twitter, which …

Models And Algorithms For Promoting Diverse And Fair Query Results, Md Mouinul Islam

Dissertations

Ensuring fairness and diversity in search results are two key concerns in compelling search and recommendation applications. This work explicitly studies these two aspects given multiple users' preferences as inputs, in an effort to create a single ranking or top-k result set that satisfies different fairness and diversity criteria. From group fairness standpoint, it adapts demographic parity like group fairness criteria and proposes new models that are suitable for ranking or producing top-k set of results. This dissertation also studies equitable exposure of individual search results in long tail data, a concept related to individual fairness. First, the dissertation focuses …

Diversification And Fairness In Top-K Ranking Algorithms, Mahsa Asadi

Dissertations

Given a user query, the typical user interfaces, such as search engines and recommender systems, only allow a small number of results to be returned to the user. Hence, figuring out what would be the top-k results is an important task in information retrieval, as it helps to ensure that the most relevant results are presented to the user. There exists an extensive body of research that studies how to score the records and return top-k to the user. Moreover, there exists an extensive set of criteria that researchers identify to present the user with top-k results, and result diversification …

Human-Ai Complex Task Planning, Sepideh Nikookar

Dissertations

The process of complex task planning is ubiquitous and arises in a variety of compelling applications. A few leading examples include designing a personalized course plan or trip plan, designing music playlists/work sessions in web applications, or even planning routes of naval assets to collaboratively discover an unknown destination. For all of these aforementioned applications, creating a plan requires satisfying a basic construct, i.e., composing a sequence of sub-tasks (or items) that optimizes several criteria and satisfies constraints. For instance, in course planning, sub-tasks or items are core and elective courses, and degree requirements capture their complex dependencies as constraints. …

Data-Driven 2d Materials Discovery For Next-Generation Electronics, Zeyu Zhang

Dissertations

The development of material discovery and design has lasted centuries in human history. After the concept of modern chemistry and material science was established, the strategy of material discovery relies on the experiments. Such a strategy becomes expensive and time-consuming with the increasing number of materials nowadays. Therefore, a novel strategy that is faster and more comprehensive is urgently needed. In this dissertation, an experiment-guided material discovery strategy is developed and explained using metal-organic frameworks (MOFs) as instances. The advent of 7r-stacked layered MOFs, which offer electrical conductivity on top of permanent porosity and high surface area, opened up new …

Public Biological Databases And The Sui Generis Database Right, Alexander Bernier, Christian Busse, Tania M. Bubela

Office of the Provost

The sui generis database right is an intellectual property right created in the European Union to stimulate investment in the curation of databases. Since its inception, communities engaged in research and development efforts have questioned its potential to incentivise database production, and posit that it stifles productive downstream uses of existing datasets. European courts have restricted the right’s ambit through a restrictive interpretation of the circumstances in which it applies, which we argue, enables downstream use of biological databases. Nonetheless, residual ambiguities about potential infringement of the right exist. The prospect of unintentional infringement can frustrate downstream innovation. These ambiguities …

On Digital Productivity Base Of Policies For Cross-Border Data Flows Between Rcep Parties And Its Influences—Taking Digital Integration Index As A Reference, Gui Huang, Ru Tao

Bulletin of Chinese Academy of Sciences (Chinese Version)

This study reviews the newest legislation and policies of Regional Comprehensive Economic Partnership (RCEP) participating countries on cross-border data flow, and then categorized them according to the ban on data transfer, local storage of data, permission-based regulation, and standards-based regulation. By referring to the indexes in the ASEAN Digital Integration Index, the subject and object factors of digital productivity in RCEP parities are sorted out, as well as the status quo of digital economy. Through the introduction of data value chain theory, the decisive impact of digital productivity factors on the policy formulation of cross-border data flow is expounded; by …

Research On Multi-Source Heterogeneous Big Data Fusion Based On Wsr, Aihua Li, Weijia Xu, Yong Shi

Bulletin of Chinese Academy of Sciences (Chinese Version)

In the era of multi-source heterogeneous big data, big data presents new features such as cross, diversity and variability. The applications of big data in a wider range of fields have new requirements for data fusion. Under this background, the connotation of data fusion is enriched and expanded. The generalized data fusion includes the fusion of data resources, the fusion of model methods, and the fusion of decision-makers' knowledge and experience. This study analyzes the characteristics of multi-source heterogeneous data fusion at three different fusion levels: data level, information level and decision level, and discusses challenges for data fusion in …

Paradigm Review Of Data Localization In India And Its Implications For China, Ying Fan

Bulletin of Chinese Academy of Sciences (Chinese Version)

Data localization is a focal point of global data governance and its impact on global data governance is no longer confined to a single country. Over the years, India has followed a unique policy framework in terms of cross-border data flows and data localization, and its insistence on data sovereignty reflects its position in the international arena. This study uses the Indian data localization paradigm as a research base to discuss the common phenomenon of disconnect between policy motivations and practical effects of data localization, and as an entry point to introduce the latest Indian research findings in this area. …

Data Heterogeneity And Its Implications For Fairness, Ghazaleh Noroozi

Electronic Thesis and Dissertation Repository

Data heterogeneity, referring to the differences in underlying generative processes that produce the data, presents challenges in analyzing and utilizing datasets for decision-making tasks. This thesis examines the impact of data heterogeneity on biases and fairness in predictive models. The research investigates the correlation between heterogeneity and protected attributes, such as race and gender, and explores the implications of such heterogeneity on biases that may arise in downstream applications.

The contributions of this thesis are fourfold. Firstly, a comprehensive definition of data heterogeneity based on differences in underlying generative processes is provided, establishing a conceptual framework for understanding and quantifying …

On Computing Optimal Repairs For Conditional Independence, Alireza Pirhadi

Electronic Thesis and Dissertation Repository

This thesis focuses on the concept of Conditional Independence (CI) and its testing, which holds immense significance across various fields, including economics, social sciences, and biomedical research. Notably, within computer science, CI has become an integral part of building probabilistic and causal models. It aids efficient inference and plays a key role in uncovering causal relationships.

The primary aim of this thesis is to broaden the scope of CI beyond its testing aspect. We introduce the pioneering problem of data repair, designed to adhere to particular CI constraints. The value and pertinence of this problem are highlighted through two contrasting …

Geospatial Wildfire Risk Prediction Using Deep Learning, Abner Alberto Benavides

Electronic Theses, Projects, and Dissertations

This report introduces a thorough analysis of wildfire prediction using satellite imagery by applying deep learning techniques. To find wildfire-prone geographical data, we use U-Net, a convolutional neural network known for its effectiveness in biomedical image segmentation. The input to the model is the Sentinel-2 multispectral images to supply a complete view of the terrain features.

We evaluated the wildfire risk prediction model’s performance using several metrics. The model showed high accuracy, with a weighted average F1 score of 0.91 and an AUC-ROC score of 0.972. These results suggest that the model is exceptionally good at predicting the location of …

Cybersecurity Safeguards: What Cybersecurity Safeguards Could Have Prevented The Intelligence/Data Breach By A Member Of The Air National Guard, Christopher Curtis Royal

Cyber Operations and Resilience Program Graduate Projects

Jack Teixeira, a 21-year-old IT specialist Air National Guard found himself on the wrong side of the US law after sharing what is considered classified and extremely sensitive information about USA's operations and role in Ukraine and Russia war. Like other previous cases of leakage of classified intelligence, the case of Teixeira raises concerns about the weaknesses and vulnerability of federal agencies' IT systems and security protocols governing accessibility to classified documents. Internal leakages of such classified documents hurt national security and can harm the country, especially when such secretive intelligence finds its way into the hands of enemies. Unauthorized …

Unsupervised Machine Learning Of Tornado-Producing Storms In The Southeastern United States, Morgan R. Steckler

Masters Theses

The east-southeastern US is uniquely affected by storm and tornado-related damages, costs, injuries, and deaths. Based on doppler radar, satellite, and modeled data, previous research sought to understand these different types of storms that produce strong tornadoes. Many approaches to storm classification are time intensive, complex, and vary significantly across the literature. The purpose of this work is to (1) explore the radar-derived data structure and spread of strong tornado-producing mesoscale storms in the east-southeastern US; (2) use K-Means unsupervised machine learning methods to elucidate clusters (storm types) and clustering attributes; and (3) assess the utility of K-Means as a …

Fintech Data Infrastructure For Esg Disclosure Compliance, Randall E. Duran, Peter Tierney

Research Collection School Of Computing and Information Systems

Regulations related to the disclosure of environmental, governance, and social (ESG) factors are evolving rapidly and are a major concern for financial compliance worldwide. Information technology has the potential to reduce the effort and cost of ESG disclosure compliance. However, comprehensive and accurate ESG data are necessary for disclosures. Currently, the availability and quality of underlying data for ESG disclosures vary widely and are often deficient. The process involved with obtaining ESG data is also often inefficient and prone to error. This paper compares the models used and the evolution of Fintech data infrastructure developed to support financial services with …

Document-Level Relation Extraction Via Separate Relation Representation And Logical Reasoning, Heyan Huang, Changsen Yuan, Qian Liu, Yixin Cao

Research Collection School Of Computing and Information Systems

Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this article, we propose a novel model, SRLR, using Separate Relation Representation and Logical Reasoning considering the indirect relation representation and complex reasoning of evidence sentence problems. Specifically, we first expand the judgment of relational facts from the entity-level to the mention-level, highlighting fine-grained information to capture the relation representation for the entity pair. Second, we propose a logical reasoning module to identify evidence sentences and conduct …

Decoding The Underlying Meaning Of Multimodal Hateful Memes, Ming Shan Hee, Wen Haw Chong, Roy Ka-Wei Lee

Research Collection School Of Computing and Information Systems

Recent studies have proposed models that yielded promising performance for the hateful meme classification task. Nevertheless, these proposed models do not generate interpretable explanations that uncover the underlying meaning and support the classification output. A major reason for the lack of explainable hateful meme methods is the absence of a hateful meme dataset that contains ground truth explanations for benchmarking or training. Intuitively, having such explanations can educate and assist content moderators in interpreting and removing flagged hateful memes. This paper address this research gap by introducing Hateful meme with Reasons Dataset (HatReD), which is a new multimodal hateful meme …

Camper: An Effective Framework For Privacy-Aware Deep Entity Resolution, Yuxiang Guo, Lu Chen, Zhengjie Zhou, Baihua Zheng, Ziquan Fang, Zhikun Zhang, Yuren Mao, Yunjun Gao

Research Collection School Of Computing and Information Systems

Entity Resolution (ER) is a fundamental problem in data preparation. Standard deep ER methods have achieved state-of-the-art efectiveness, assuming that relations from diferent organizations are centrally stored. However, due to privacy concerns, it can be difcult to centralize data in practice, rendering standard deep ER solutions inapplicable. Despite eforts to develop rule-based privacy-preserving ER methods, they often neglect subtle matching mechanisms and have poor efectiveness as a result. To bridge efectiveness and privacy, in this paper, we propose CampER, an efective framework for privacy-aware deep entity resolution. Specifcally, we frst design a training pair self-generation strategy to overcome the absence …

Multi-View Graph Contrastive Learning For Solving Vehicle Routing Problems, Yuan Jiang, Zhiguang Cao, Yaoxin Wu, Jie Zhang

Research Collection School Of Computing and Information Systems

Recently, neural heuristics based on deep learning have reported encouraging results for solving vehicle routing problems (VRPs), especially on independent and identically distributed (i.i.d.) instances, e.g. uniform. However, in the presence of a distribution shift for the testing instances, their performance becomes considerably inferior. In this paper, we propose a multi-view graph contrastive learning (MVGCL) approach to enhance the generalization across different distributions, which exploits a graph pattern learner in a self-supervised fashion to facilitate a neural heuristic equipped with an active search scheme. Specifically, our MVGCL first leverages graph contrastive learning to extract transferable patterns from VRP graphs to …