Physical Sciences and Mathematics Commons^™

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 …

Instance-Specific Algorithm Configuration Via Unsupervised Deep Graph Clustering, Wen Song, Yi Liu, Zhiguang Cao, Yaoxin Wu, Qiqiang Li

Research Collection School Of Computing and Information Systems

Instance-specific Algorithm Configuration (AC) methods are effective in automatically generating high-quality algorithm parameters for heterogeneous NP-hard problems from multiple sources. However, existing works rely on manually designed features to describe training instances, which are simple numerical attributes and cannot fully capture structural differences. Targeting at Mixed-Integer Programming (MIP) solvers, this paper proposes a novel instances-specific AC method based on end-to-end deep graph clustering. By representing an MIP instance as a bipartite graph, a random walk algorithm is designed to extract raw features with both numerical and structural information from the instance graph. Then an auto-encoder is designed to learn dense …

Boosting Adversarial Training In Safety-Critical Systems Through Boundary Data Selection, Yifan Jia, Christopher M. Poskitt, Peixin Zhang, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay

Research Collection School Of Computing and Information Systems

AI-enabled collaborative robots are designed to be used in close collaboration with humans, thus requiring stringent safety standards and quick response times. Adversarial attacks pose a significant threat to the deep learning models of these systems, making it crucial to develop methods to improve the models' robustness against them. Adversarial training is one approach to improve their robustness: it works by augmenting the training data with adversarial examples. This, unfortunately, comes with the cost of increased computational overhead and extended training times. In this work, we balance the need for additional adversarial data with the goal of minimizing the training …

Owner-Free Distributed Symmetric Searchable Encryption Supporting Conjunctive Queries, Qiuyun Tong, Xinghua Li, Yinbin Miao, Yunwei Wang, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Symmetric Searchable Encryption (SSE), as an ideal primitive, can ensure data privacy while supporting retrieval over encrypted data. However, existing multi-user SSE schemes require the data owner to share the secret key with all query users or always be online to generate search tokens. While there are some solutions to this problem, they have at least one weakness, such as non-supporting conjunctive query, result decryption assistance of the data owner, and unauthorized access. To solve the above issues, we propose an Owner-free Distributed Symmetric searchable encryption supporting Conjunctive query (ODiSC). Specifically, we first evaluate the Learning-Parity-with-Noise weak Pseudorandom Function (LPN-wPRF) …

Spoken Language Processing And Modeling For Aviation Communications, Aaron Van De Brook

Doctoral Dissertations and Master's Theses

With recent advances in machine learning and deep learning technologies and the creation of larger aviation-specific corpora, applying natural language processing technologies, especially those based on transformer neural networks, to aviation communications is becoming increasingly feasible. Previous work has focused on machine learning applications to natural language processing, such as N-grams and word lattices. This thesis experiments with a process for pretraining transformer-based language models on aviation English corpora and compare the effectiveness and performance of language models transfer learned from pretrained checkpoints and those trained from their base weight initializations (trained from scratch). The results suggest that transformer language …

Robust Bidirectional Poly-Matching, Ween Jiann Lee, Maksim Tkachenko, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

A fundamental problem in many scenarios is to match entities across two data sources. It is frequently presumed in prior work that entities to be matched are of comparable granularity. In this work, we address one-to-many or poly-matching in the scenario where entities have varying granularity. A distinctive feature of our problem is its bidirectional nature, where the 'one' or the 'many' could come from either source arbitrarily. Moreover, to deal with diverse entity representations that give rise to noisy similarity values, we incorporate novel notions of receptivity and reclusivity into a robust matching objective. As the optimal solution to …

Underwater Image Translation Via Multi-Scale Generative Adversarial Network, Dongmei Yang, Tianzi Zhang, Boquan Li, Menghao Li, Weijing Chen, Xiaoqing Li, Xingmei Wang

Research Collection School Of Computing and Information Systems

The role that underwater image translation plays assists in generating rare images for marine applications. However, such translation tasks are still challenging due to data lacking, insufficient feature extraction ability, and the loss of content details. To address these issues, we propose a novel multi-scale image translation model based on style-independent discriminators and attention modules (SID-AM-MSITM), which learns the mapping relationship between two unpaired images for translation. We introduce Convolution Block Attention Modules (CBAM) to the generators and discriminators of SID-AM-MSITM to improve its feature extraction ability. Moreover, we construct style-independent discriminators that enable the discriminant results of SID-AM-MSITM to …

Multi-Representation Variational Autoencoder Via Iterative Latent Attention And Implicit Differentiation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Variational Autoencoder (VAE) offers a non-linear probabilistic modeling of user's preferences. While it has achieved remarkable performance at collaborative filtering, it typically samples a single vector for representing user's preferences, which may be insufficient to capture the user's diverse interests. Existing solutions extend VAE to model multiple interests of users by resorting a variant of self-attentive method, i.e., employing prototypes to group items into clusters, each capturing one topic of user's interests. Despite showing improvements, the current design could be more effective since prototypes are randomly initialized and shared across users, resulting in uninformative and non-personalized clusters.To fill the gap, …

Deep Reinforcement Learning With Explicit Context Representation, Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji

Research Collection School Of Computing and Information Systems

Though reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems, most RL algorithms lack an explicit method that would allow learning from contextual information. On the other hand, humans often use context to identify patterns and relations among elements in the environment, along with how to avoid making wrong actions. However, what may seem like an obviously wrong decision from a human perspective could take hundreds of steps for an RL agent to learn to avoid. This article proposes a framework for discrete environments called Iota explicit context representation (IECR). The framework involves representing each state …

Stprivacy: Spatio-Temporal Privacy-Preserving Action Recognition, Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification …

Ciri: Curricular Inactivation For Residue-Aware One-Shot Video Inpainting, Weiying Zheng, Cheng Xu, Xuemiao Xu, Wenxi Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

Video inpainting aims at filling in missing regions of a video. However, when dealing with dynamic scenes with camera or object movements, annotating the inpainting target becomes laborious and impractical. In this paper, we resolve the one-shot video inpainting problem in which only one annotated first frame is provided. A naive solution is to propagate the initial target to the other frames with techniques like object tracking. In this context, the main obstacles are the unreliable propagation and the partially inpainted artifacts due to the inaccurate mask. For the former problem, we propose curricular inactivation to replace the hard masking …

Deep Video Demoireing Via Compact Invertible Dyadic Decomposition, Yuhui Quan, Haoran Huang, Shengfeng He, Ruotao Xu

Research Collection School Of Computing and Information Systems

Removing moire patterns from videos recorded on screens or complex textures is known as video demoireing. It is a challenging task as both structures and textures of an image usually exhibit strong periodic patterns, which thus are easily confused with moire patterns and can be significantly erased in the removal process. By interpreting video demoireing as a multi-frame decomposition problem, we propose a compact invertible dyadic network called CIDNet that progressively decouples latent frames and the moire patterns from an input video sequence. Using a dyadic cross-scale coupling structure with coupling layers tailored for multi-scale processing, CIDNet aims at disentangling …

Visilience: An Interactive Visualization Framework For Resilience Analysis Using Control-Flow Graph, Hailong Jiang, Shaolun Ruan, Bo Fang, Yong Wang, Qiang Guan

Research Collection School Of Computing and Information Systems

Soft errors have become one of the main concerns for the resilience of HPC applications, as these errors can cause HPC applications to generate serious outcomes such as silent data corruption (SDC). Many approaches have been proposed to analyze the resilience of HPC applications. However, existing studies rarely address the challenges of analysis result perception. Specifically, resilience analysis techniques often produce a massive volume of unstructured data, making it difficult for programmers to perform resilience analysis due to non-intuitive raw data. Furthermore, different analysis models produce diverse results with multiple levels of detail, which can create obstacles to compare and …

Problems In Microservice Development: Supporting Visualisation, Oscar Manglaras, Alex Farkas, Peter Fule, Christoph Treude, Markus Wagner

Research Collection School Of Computing and Information Systems

In microservice architectures, developers can face significant problems understanding the structure of the system and how the different microservices interact. This difficulty results from the distributed nature of the system, and the abundance of inter-service communication within the architecture. We want to determine if network visualisations can address these problems given their ability to convey complex topologies. However, to identify what architectural characteristics should be visualised, and how this should be done, we must first determine the needs of microservice developers. This paper identifies and presents the impact and frequency of problems faced by a cohort of microservice developers using …

Reachability Poorman Discrete-Bidding Games, Guy Avni, Tobias Meggendorfer, Suman Sadhukhan, Josef Tkadlec, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We consider bidding games, a class of two-player zerosum graph games. The game proceeds as follows. Both players have bounded budgets. A token is placed on a vertex of a graph, in each turn the players simultaneously submit bids, and the higher bidder moves the token, where we break bidding ties in favor of Player 1. Player 1 wins the game iff the token visits a designated target vertex. Weconsider, for the first time, poorman discrete-bidding in which the granularity of the bids is restricted and the higher bid is paid to the bank. Previous work either did not impose …

Improving Semantic Document Classification Accuracy By Integrating Human-Crafted Knowledge, Zachary Weinfeld, Lubomir Stanchev

College of Engineering Summer Undergraduate Research Program

Document classification is a pivotal task in various domains, warranting the development of robust algorithms. Among these, the Bidirectional Encoder Representations from Transformers (BERT) algorithm, introduced by Google, has proven to perform well when fine-tuned for the task at hand. Leveraging transformer architecture, BERT demonstrates stellar language understanding capabilities. However, the integration of BERT with a range of techniques has shown potential for further enhancing classification accuracy. This work investigates several techniques that leverage semantic understanding to improve the performance of document classification models trained with BERT. Specifically, we explore three methods. First, we will balance corpuses afflicted by imbalanced …

On Explicit Soliton Solutions And Blow-Up For Coupled Variable Coefficient Nonlinear Schrödinger Equations, Jose Escorcia, Erwin Suazo

School of Mathematical and Statistical Sciences Faculty Publications and Presentations

This work is concerned with the study of explicit solutions for a generalized coupled nonlinear Schrödinger equations (NLS) system with variable coefficients. Indeed, we show, employing similarity transformations, the existence of Rogue wave and dark-bright soliton like-solutions for such a generalized NLS system, provided the coefficients satisfy a Riccati system. As a result of the multiparameter solution of the Riccati system, the nonlinear dynamics of the solution can be controlled. Finite-time singular solutions in the L∞ norm for the generalized coupled NLS system are presented explicitly. Finally, an n-dimensional transformation between a variable coefficient NLS coupled system and a constant …

Towards Explainable Harmful Meme Detection Through Multimodal Debate Between Large Language Models, Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma, Bo Wang, Ruichao Yang

Research Collection School Of Computing and Information Systems

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models …

Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm, Xuan Zhang, Wei Gao

Research Collection School Of Computing and Information Systems

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents …

Patrimonio Cultural, Arqueología, Medio Ambiente Y Economía: ¿Cómo Ha Afectado La Construcción Del Aeropuerto Internacional De Chinchero-Cusco A Las Comunidades Y La Tierra De Chinchero?, Sydney Berenson

Independent Study Project (ISP) Collection

La urbanización gubernamental ha sido un problema para las poblaciones indígenas, el medio ambiente y la protección del patrimonio cultural durante numerosos años en todo el Perú. Más recientemente, en la pequeña ciudad de Chinchero, ubicada a unos 30 kilómetros al noroeste de Cusco, se está construyendo un nuevo aeropuerto internacional, Aeropuerto Internacional de Chinchero-Cusco (AICC), para reemplazar el actual aeropuerto nacional de Cusco. Chinchero es un importante centro urbano que está conformado por 13 comunidades campesinas que participan en la industria agrícola de la región, además consta con una importante comunidad artesanal, ruinas arqueológicas precolombinas y una gran biodiversidad. …

Physical-Vapor-Deposited Metal Oxide Thin Films For Ph Sensing Applications: Last Decade Of Research Progress, Mohammad Nur-E-Alam, Devendra K. Maurya, Boon K. Yap, Armin Rajabi, Camellia Doroody, Hassan B. Mohamed, Mayeen U. Khandaker, Mohammad A. Islam, Sieh K. Tiong

Research outputs 2022 to 2026

In the last several decades, metal oxide thin films have attracted significant attention for the development of various existing and emerging technological applications, including pH sensors. The mandate for consistent and precise pH sensing techniques has been increasing across various fields, including environmental monitoring, biotechnology, food and agricultural industries, and medical diagnostics. Metal oxide thin films grown using physical vapor deposition (PVD) with precise control over film thickness, composition, and morphology are beneficial for pH sensing applications such as enhancing pH sensitivity and stability, quicker response, repeatability, and compatibility with miniaturization. Various PVD techniques, including sputtering, evaporation, and ion beam …

Structure-Aware Image Translation-Based Long Future Prediction For Enhancement Of Ground Robotic Vehicle Teleoperation, Md Moniruzzaman, Alexander Rassau, Douglas Chai, Syed M. S. Islam

Research outputs 2022 to 2026

Predicting future frames through image-to-image translation and using these synthetically generated frames for high-speed ground vehicle teleoperation is a new concept to address latency and enhance operational performance. In the immediate previous work, the image quality of the predicted frames was low and a lot of scene detail was lost. To preserve the structural details of objects and improve overall image quality in the predicted frames, several novel ideas are proposed herein. A filter has been designed to remove noise from dense optical flow components resulting from frame rate inconsistencies. The Pix2Pix base network has been modified and a structure-aware …

The Uses And Limitations Of Citizen Science For Monitoring The Australian Grey Nurse Shark (Carcharias Taurus) Population, Leah Corckran

Independent Study Project (ISP) Collection

iNaturalist is a citizen science photographic database, which is an underutilized resource in photographic identification research studies. Grey nurse sharks are critically endangered and there is a lack of knowledge regarding the estimated population size, longevity, and interactions with fisheries of this species off the coasts of Australia. To determine how photos submitted to iNaturalist can be used in Carcharias taurus conservation, the photographs were evaluated on a number of criteria including: location, date, visibility of spot patterns, visible sex characteristics, and visible injuries. In total, 814 photographs of grey nurse sharks were obtained from the iNaturalist database. Only 23.2% …

Organism Communities On Giant Clam Shells As Compared To The Surrounding Substrate In Reefs Around Lizard Island, Queensland, Gayatri Singla

Independent Study Project (ISP) Collection

Coral reef ecosystems are facing destruction at the hands of anthropogenic climate change. Therefore, it is essential that we move to better understand the ecosystem functions of the organisms present in reefs. One such family whose ecosystem function we are unfamiliar with are the giant clams (family Cardiidae). As unique and abundant macrofauna, they have the potential to play an important role in their environment. The goal of our study was to determine how giant clams function as settlement substrata. We conducted 151 observational surveys of epibionts residing on living giant clam shells and of the organism communities in the …

Lha, Lu, And Shipda: Religious Landscape In A Conservation Area, Luke Stumpfl

Independent Study Project (ISP) Collection

Living in a political, cultural, and geographic border region between Nepal and Tibet (People’s Republic of China), the families of Tsum Valley face many demands from their sociopolitical, religious, and economic climate. Practicing Tibetan Buddhism, the people uphold a set of rules implemented by the community with leadership from Serap Dorje Drukpa Rinpoche over 100 years ago that prohibits the intentional murder of all animals. Hailed by leaders and scholars as a haven of biodiversity conservation due to this customary-turned- municipal law, Tsum Valley also exists within Manaslu Conservation Area governed by an entity of the federal government of Nepal …

Carbon Credibility: Strategic Opportunities For Asean Regional Industrial Policy In Voluntary Carbon Markets, Bryan Jed Soh

Independent Study Project (ISP) Collection

Carbon offsets have come under increasing scrutiny due to uncertainties in real carbon abatement, transparency, and fears that it will exacerbate global inequality by allowing the global North to ‘pay to pollute’ through ethically questionable projects in the South. Following Article 2.1.C of the Paris Agreement, this paper argues that the global green transition requires private capital to be fully mobilized through voluntary carbon markets (VCMs). Given that ASEAN states face some of the world’s greatest climate risks while being a fast-growing region, this case study answers the question: how can states play a more proactive role in regulating VCMs …

A Reflection Of Change: Evolutions In International Water Law Principles Through The Lens Of Euphrates-Tigris Dispute, Maeve Sullivan

Independent Study Project (ISP) Collection

As climate change intensifies, water scarcity will increase. Coupled with a growing global population, water security is a major modern challenge. To bring stability to international watercourses, states must establish effective sharing agreements. On this matter, international water law can help. International water law captures some of the major principles and considerations that states must account for while considering issues related to water security. This paper uses primary interviews and secondary sources to identify some of the major characteristics, features, and developments in international law to develop a conceptual framework for the topic. It then moves into a case study …

Climate Change, Malnutrition, And Hiv: The Impact Of Food Insecurity On Hiv Response In Sub-Saharan Africa, Olivia Walshak

Independent Study Project (ISP) Collection

Climate change is a key driver of an unprecedented global food crisis, exacerbated by rising temperatures and the vulnerability of crop yields. Sub-Saharan Africa is particularly susceptible, and case studies demonstrate the fragility of food systems in the region, leading to severe food insecurity and famine in the face of climate shocks.

There are a variety of health implications, particularly the syndemic relationship between malnutrition and HIV. HIV interacts bidirectionally with malnutrition, creating a vicious cycle of poor clinical outcomes. Expanding access to antiretroviral therapy in Sub-Saharan Africa is hindered by rampant food insecurity, including inadequate food intake, reduced dietary …

Críticas Contrahegemónicas De La Estrategia Nacional Del Litio: Hacia El Postextractivismo, Sarah Reyes

Independent Study Project (ISP) Collection

En abril de 2023, el presidente chileno Gabriel Boric anunció su esperada Estrategia Nacional del Litio, diseñada para expandir la extracción de litio y desarrollar una cadena de valor productiva nacional a través de una estructura de asociación público-privada con mayor participación estatal. El plan ha sido objeto de diversas críticas y niveles de oposición por parte de la izquierda, comunidades indígenas y organizaciones ambientales. Basándose en la creciente literatura de ecología política y decolonial sobre la extracción de litio, junto con marcos teóricos de decrecimiento decolonial y postextractivismo, este documento sintetiza y analiza críticas de estos tres grupos (no …

Flujos De Servicios Ecosistémicos En Un Área Marina Protegida Del Atlántico Sur: Perspectivas Desde El Análisis De La Teoría De Redes, Mitch Porter

Independent Study Project (ISP) Collection

En cuestiones de gestión de áreas protegidas, los servicios ecosistémicos se tienen cada vez más en cuenta junto con la conservación de la biodiversidad. Sin embargo, las decisiones que se toman sobre la conservación de los servicios ecosistémicos no suelen incluir los posibles efectos en cascada de la pérdida de biodiversidad sobre la provisión de servicios. Los conocimientos de la teoría de redes y los estudios de robustez pueden proporcionar una metodología para evaluar la vulnerabilidad de estos servicios frente la estructura trófica de los ecosistemas que los proveen. A través de una serie de simulaciones de extinción para la …