Digital Commons Network^™

The Promise And Perils Of Smart (City) Bots As Educational Tools, Thomas Menkhoff, Siew Ning Kan, Shaohui Foong

Research Collection Lee Kong Chian School Of Business

Written from an educator’s perspective, the paper aims to examine the increasing use of chatbot technology capable of answering user queries in various fields such as commerce, public service delivery, urban areas, higher education etc. by simulating human conversation through text messages or voice commands. We analyse why smart bots have become popular technologies in the context smart cities; shed light on different types of bots (chatbots, large language models such as ChatGPT, flying bots); and explain how we use bots as teaching tool in an introductory AI for business course. A key argument putting forward is that smart bots …

Promise And Peril Of Collaborative Code Generation Models : Balancing Effectiveness And Memorization, Zhi Chen, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

In the rapidly evolving field of machine learning, training models with datasets from various locations and organizations presents significant challenges due to privacy and legal concerns. The exploration of effective collaborative training settings, which are capable of leveraging valuable knowledge from distributed and isolated datasets, is increasingly crucial. This study investigates key factors that impact the effectiveness of collaborative training methods in code next-token prediction, as well as the correctness and utility of the generated code, showing the promise of such methods. Additionally, we evaluate the memorization of different participant training data across various collaborative training settings, including centralized, federated, …

Pvp-Ssd: Point-Voxel Fusion With Partitioned Point Cloud Sampling For Anchor-Free Single-Stage Small 3d Object Detection, Xinlin Wu, Yibin Tian, Yin Pan, Zhiyuan Zhang, Xuesong Wu, Ruisheng Wang, Zhi Zeng

Research Collection School Of Computing and Information Systems

Single-stage object detection from 3D point clouds in autonomous driving faces significant challenges, particularly in accurately detecting small objects. To address this issue, we propose a novel method called Point-Voxel dual-branch feature extraction with Partitioned point cloud sampling for anchor-free Single-Stage Detection of 3D objects (PVP-SSD). The network comprises two branches: a point branch and a voxel branch. In the point branch, a partitioned point cloud sampling strategy leverages axial features to divide the point cloud. Then, it assigns different sampling weights to various segments to enhance the sampling accuracy. Additionally, a local feature enhancement module explicitly calculates the correlation …

Data Provenance Via Differential Auditing, Xin Mu, Ming Pang, Feida Zhu

Research Collection School Of Computing and Information Systems

With the rising awareness of data assets, data governance, which is to understand where data comes from, how it is collected, and how it is used, has been assuming evergrowing importance. One critical component of data governance gaining increasing attention is auditing machine learning models to determine if specific data has been used for training. Existing auditing techniques, like shadow auditing methods, have shown feasibility under specific conditions such as having access to label information and knowledge of training protocols. However, these conditions are often not met in most real-world applications. In this paper, we introduce a practical framework for …

Hisoma: A Hierarchical Multi-Agent Model Integrating Self-Organizing Neural Networks With Multi-Agent Deep Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent deep reinforcement learning (MADRL) has shown remarkable advancements in the past decade. However, most current MADRL models focus on task-specific short-horizon problems involving a small number of agents, limiting their applicability to long-horizon planning in complex environments. Hierarchical multi-agent models offer a promising solution by organizing agents into different levels, effectively addressing tasks with varying planning horizons. However, these models often face constraints related to the number of agents or levels of hierarchies. This paper introduces HiSOMA, a novel hierarchical multi-agent model designed to handle long-horizon, multi-agent, multi-task decision-making problems. The top-level controller, FALCON, is modeled as a class …

Efficient Cascaded Multiscale Adaptive Network For Image Restoration, Yichen Zhou, Pan Zhou, Teck Khim Ng

Research Collection School Of Computing and Information Systems

Image restoration, encompassing tasks such as deblurring, denoising, and super-resolution, remains a pivotal area in computer vision. However, efficiently addressing the spatially varying artifacts of various low-quality images with local adaptiveness and handling their degradations at different scales poses significant challenges. To efficiently tackle these issues, we propose the novel Efficient Cascaded Multiscale Adaptive (ECMA) Network. ECMA employs Local Adaptive Module, LAM, which dynamically adjusts convolution kernels across local image regions to efficiently handle varying artifacts. Thus, LAM addresses the local adaptiveness challenge more efficiently than costlier mechanisms like self-attention, due to its less computationally intensive convolutions. To construct a …

Collaborative Cross-Modal Fusion With Large Language Model For Recommendation, Zhongzhou Liu, Hao Zhang, Kuicai Dong, Yuan Fang

Research Collection School Of Computing and Information Systems

Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual attributes of users and items. Recent focus on the application of large language models for recommendation (LLM4Rec) has highlighted their capability for effective semantic knowledge capture. However, these methods often overlook the collaborative signals in user behaviors. Some simply instruct-tune a language model, while others directly inject the embeddings of a CF-based model, lacking a synergistic fusion of different modalities. To address these issues, we propose a framework of Collaborative Cross-modal Fusion with Large Language Models, termed CCF-LLM, …

Calibrated One-Class Classification For Unsupervised Time Series Anomaly Detection, Hongzuo Xu, Yijie Wang, Songlei Jian, Qing Liao, Yongjun Wang, Guansong Pang

Research Collection School Of Computing and Information Systems

Time series anomaly detection is instrumental in maintaining system availability in various domains. Current work in this research line mainly focuses on learning data normality deeply and comprehensively by devising advanced neural network structures and new reconstruction/prediction learning objectives. However, their one-class learning process can be misled by latent anomalies in training data (i.e., anomaly contamination) under the unsupervised paradigm. Their learning process also lacks knowledge about the anomalies. Consequently, they often learn a biased, inaccurate normality boundary. To tackle these problems, this paper proposes calibrated one-class classification for anomaly detection, realizing contamination-tolerant, anomaly-informed learning of data normality via uncertainty …

Gradualreality: Enhancing Physical Object Interaction In Virtual Reality Via Interaction State-Aware Blending, Hyuna Seo, Juheon Yi, Rajesh Krishna Balan, Youngki Lee

Research Collection School Of Computing and Information Systems

We present GradualReality, a novel interface enabling a Cross Reality experience that includes gradual interaction with physical objects in a virtual environment and supports both presence and usability. Daily Cross Reality interaction is challenging as the user’s physical object interaction state is continuously changing over time, causing their attention to frequently shift between the virtual and physical worlds. As such, presence in the virtual environment and seamless usability for interacting with physical objects should be maintained at a high level. To address this issue, we present an Interaction State-Aware Blending approach that (i) balances immersion and interaction capability and (ii) …

D2sr: Decentralized Detection, De-Synchronization, And Recovery Of Lidar Interference, Darshana Rathnayake, Hemanth Sabbella, Meera Radhakrishnan, Archan Misra

Research Collection School Of Computing and Information Systems

We address the challenge of multi-LiDAR interference, an issue of growing importance as LiDAR sensors are embedded in a growing set of pervasive devices. We introduce a novel approach named D2SR, enabling decentralized interference detection, mitigation, and recovery without explicit coordination among nearby LiDAR devices. D2SR comprises three stages: (a) Detection, which identifies interfered frames, (b) Mitigation, which performs time-shifting of a LiDAR’s active period to reduce interference, and (c) Recovery, which corrects or reconstructs the depth values in interfered regions of a depth frame. Key contributions include a lightweight interference detection algorithm achieving an F1-score of 92%, a simple …

Large-Scale Graph Label Propagation On Gpus, Chang Ye, Yuchen Li, Bingsheng He, Zhao Li, Jianling Sun

Research Collection School Of Computing and Information Systems

Graph label propagation (LP) is a core component in many downstream applications such as fraud detection, recommendation and image segmentation. In this paper, we propose GLP, a GPU-based framework to enable efficient LP processing on large-scale graphs. By investigating the data processing pipeline in a large e-commerce platform, we have identified two key challenges on integrating GPU-accelerated LP processing to the pipeline: (1) programmability for evolving application logics; (2) demand for real-time performance. Motivated by these challenges, we offer a set of expressive APIs that data engineers can customize and deploy efficient LP algorithms on GPUs with ease. To achieve …

Motif Graph Neural Network, Xuexin Chen, Ruicui Cai, Yuan Fang, Min Wu, Zijian Li, Zhifeng Hao

Research Collection School Of Computing and Information Systems

Graphs can model complicated interactions between entities, which naturally emerge in many important applications. These applications can often be cast into standard graph learning tasks, in which a crucial step is to learn low-dimensional graph representations. Graph neural networks (GNNs) are currently the most popular model in graph embedding approaches. However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing high-order graph structures as opposed to low-order structures. To capture high-order structures, researchers have resorted to motifs and developed motif-based GNNs. However, the existing motif-based GNNs still often suffer from less discriminative power on high-order …

Foss: Towards Fine-Grained Unknown Class Detection Against The Open-Set Attack Spectrum With Variable Legitimate Traffic, Ziming Zhao, Zhaoxuan Li, Xiaofei Xie, Jiongchi Yu, Fan Zhang, Rui Zhang, Binbin Chen, Xiangyang Luo, Ming Hu, Wenrui Ma

Research Collection School Of Computing and Information Systems

Anomaly-based network intrusion detection systems (NIDSs) are essential for ensuring cybersecurity. However, the security communities realize some limitations when they put most existing proposals into practice. The challenges are mainly concerned with (i) fine-grained unknown attack detection and (ii) ever-changing legitimate traffic adaptation. To tackle these problem, we present three key design norms. The core idea is to construct a model to split the data distribution hyperplane and leverage the concept of isolation, as well as advance the incremental model update. We utilize the isolation tree as the backbone to design our model, named FOSS, to echo back three norms. …

What Is The Fallacy Of Approximation?, Matthew Hammerton, Sovan Patra

Research Collection School of Social Sciences

Many philosophers appeal to the “fallacy of approximation”, or “problem of second best”. However, despite the pervasiveness of such appeals, there has been only a single attempt to provide a systematic account of what the fallacy is. We identify the shortcomings of this account and propose a better one in its place. Our account not only captures all the contexts in which approximation-based reasoning occurs but also systematically explains the several different ways in which it can be in error.

Behavioral Factors Associated With Patients' Non-Attendance: A Retrospective Study In An Outpatient Specialty Clinic At A Women's And Children's Hospital In Singapore, Yue Tang, Houyuan Jiang, Jingui Xie, Zhichao Zheng, Chui Yee Loke, Bee Keow Goh

Research Collection Lee Kong Chian School Of Business

Background: This study aimed to identify behavioral factors that affect patient attendance in outpatient clinics, especially those related to rescheduling. Methods: A retrospective study was conducted on 20,386 appointment records for 6,252 patients in an outpatient specialty clinic at a women’s and children’s hospital in Singapore over 34 months (January 2012–October 2014). Multivariate logistic regression was used to analyze the influence of independent variables on appointment no-shows. Results: The average no-show rate of the study population was 28.87%. Patient historical behaviors were significantly associated with appointment attendance. In particular, a larger number of previous visits, more historical no-shows, more historical …

Network Effects, Word Of Mouth, And Entry Performance: A Study Of Digital Freemium Products, Noman Shaheer, Liang Chen, Jingtao Yi, Sali Li, Huiwen Su

Research Collection Lee Kong Chian School Of Business

International entry research rarely examines strategies affecting entry performance in a target country, largely due to data limitations in the traditional multinational enterprise setting. However, the emergence of digital business with trackable international performance data helps address this gap. We utilize digital freemium products as our research context to examine the effect of two major demand-side strategies associated with freemium products, network effects and word-of-mouth (WOM), on entry performance across different institutional environments. By analyzing 1,891 freemium games, we show that lower network readiness of a target country strengthens the impact of network effects on entry performance whereas higher network …

Insights From An Updated Personnel Selection Meta-Analytic Matrix: Revisiting General Mental Ability Tests’ Role In The Validity-Diversity Trade-Off, Christopher M. Berry, Filip Lievens, Charlene Zhang, Paul R. Sackett

Research Collection Lee Kong Chian School Of Business

General mental ability (GMA) tests have long been at the heart of the validity–diversity trade-off, with conventional wisdom being that reducing their weight in personnel selection can improve adverse impact, but that this results in steep costs to criterion-related validity. However, Sackett et al. (2022) revealed that the criterion-related validity of GMA tests has been considerably overestimated due to inappropriate range restriction corrections. Thus, we revisit the role of GMA tests in the validity-diversity trade-off using an updated meta-analytic correlation matrix of the relationships six selection methods (biodata, GMA tests, conscientiousness tests, structured interviews, integrity tests, and situational judgment tests) …

Physical Frictions And Digital Banking Adoption, Hyun Soo Choi, Roger Loh

Research Collection Lee Kong Chian School Of Business

The behavioral literature suggests that minor frictions can elicit desirable behavior without obvious coercion. Using closures of ATMs in a densely populated city as an instrument for small frictions to physical banking access, we find that customers affected by ATM closures increase their usage of the bank's digital platform. Other spillover effects of this adoption of financial technology include increases in point-of-sale (POS) transactions, electronic funds transfers, automatic bill payments and savings, and a reduction in cash usage. Our results show that minor frictions can help overcome the status-quo bias and facilitate significant behavior change.

Ocapo: Fine-Grained Occupancy-Aware, Empirically-Driven Pdc Control In Open-Plan, Shared Workspaces, Ravi Anuradha, Dulaj Sanjaya Weerakoon, Archan Misra

Research Collection School Of Computing and Information Systems

Passive Displacement Cooling (PDC) is a relatively recent technology gaining attention as a means of significantly reducing building energy consumption overheads, especially in tropical climates. PDC eliminates the use of mechanical fans, instead using chilled-water heat exchangers to perform convective cooling. In this paper, we identify and characterize the impact of several key parameters affecting occupant comfort in a 1000m2 open-floor area (consisting of multiple zones) of a ZEB (Zero Energy Building) deployed with PDC units and tackle the problem of setting the temperature setpoint of the PDC units to assure occupant thermal comfort and yet conserve energy. We tackle …

Transformer-Based Joint Learning Approach For Text Normalization In Vietnamese Automatic Speech Recognition Systems, The Viet Bui, Tho Chi Luong, Oanh Thi Tran

Research Collection School Of Computing and Information Systems

In this article, we investigate the task of normalizing transcribed texts in Vietnamese Automatic Speech Recognition (ASR) systems in order to improve user readability and the performance of downstream tasks. This task usually consists of two main sub-tasks: predicting and inserting punctuation (i.e., period, comma); and detecting and standardizing named entities (i.e., numbers, person names) from spoken forms to their appropriate written forms. To achieve these goals, we introduce a complete corpus including of 87,700 sentences and investigate conditional joint learning approaches which globally optimize two sub-tasks simultaneously. The experimental results are quite promising. Overall, the proposed architecture outperformed the …

Self-Supervised Learning For Time Series Analysis : Taxonomy, Progress, And Prospects, Zhang Kexin, Qingsong Wen, Chaoli Zhang, Rongyao Cai, Ming Jin, Yong Liu, James Y. Zhang, Guansong Pang, Guansong Pang, Pan Shirui

Research Collection School Of Computing and Information Systems

Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural language processing, a comprehensive survey for time series SSL is still missing. To fill this gap, we review current state-of-the-art SSL methods for time series data in this article. To this end, we first comprehensively review existing surveys related to SSL and time …

Interactive Example-Based Explanations To Improve Health Professionals’ Onboarding With Ai For Human-Ai Collaborative Decision Making, Min Hun Lee, Renee Bao Xuan Ng, Silvana Xinyi Choo, Shamala Thilarajah

Research Collection School Of Computing and Information Systems

A growing research explores the usage of AI explanations on user’s decision phases for human-AI collaborative decision-making. However, previous studies found the issues of overreliance on ‘wrong’ AI outputs. In this paper, we propose interactive example-based explanations to improve health professionals’ onboarding with AI for their better reliance on AI during AI-assisted decision-making. We implemented an AI-based decision support system that utilizes a neural network to assess the quality of post-stroke survivors’ exercises and interactive example-based explanations that systematically surface the nearest neighborhoods of a test/task sample from the training set of the AI model to assist users’ onboarding with …

Brushbuds: Toothbrushing Tracking Using Earphone Imus, Qiang Yang, Yang Liu, Jake Stuchbury-Wass, Kayla-Jade Butkow, Dong Ma, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Inadequate toothbrushing habits are a leading cause of oral health problems such as tooth decay. Many individuals are uncertain if they are brushing effectively or over-focusing on specific areas. While high-end electric toothbrushes can address these concerns, manual toothbrushes remain widely used due to their simplicity and affordability. In this paper, we introduce BrushBuds, an earphone-based toothbrushing monitoring system aimed at tracking brushing areas, which leverages the ubiquitous presence of earphones to enhance manual toothbrushing. BrushBuds utilizes Inertial Measurement Units (IMUs) in earphones to detect subtle head movements incurred by toothbrushing. By capturing distinct motion patterns specific to brushing for …

Daily Stress, Problematic Social Media Use, And Executive Functions: A Daily Diary Approach, Wee Qin Ng

Dissertations and Theses Collection (Open Access)

A growing body of research suggests that daily stress may be a risk factor for problematic social media use. However, findings concerning the relation between stress and social media use are mixed, suggesting the presence of moderators that may buffer the relation between stress and problematic social media use. Further, previous studies have relied on either cross-sectional designs or longitudinal designs that may not fully capture daily experiences of stressors and social media use. To overcome these limitations, the present study utilized a 7-day daily diary study to investigate the within-individual associations between daily stress and problematic social media use. …

Ecosystem-Oriented Development Of New Energy Vehicle Industry And Its Spillover Effects, Jianli Li

Dissertations and Theses Collection (Open Access)

The vigorous development of the manufacturing industry, along with advancements in technologies such as the Internet, has propelled the growth of China's new energy vehicle (NEV) industry, and exhibited characteristics of ecosystem-oriented development, which has brought positive impacts on both China's economic and social development. Benefiting from China's policy environment and developmental foundation, the Chinese automotive industry has achieved a leapfrog development in the field of new energy, with China ranking first in global sales and the penetration rate of NEVs continuously increasing. As power batteries and other domains continue to improve and intelligent driving technologies make constant breakthroughs, NEVs …

Understanding The Governance And Inheritance Mechanism Of Fujian Merchants From The Perspective Of Modern Economics, Feiyan Zhang

Dissertations and Theses Collection (Open Access)

Under the general background of globalization and market economy, Chinese enterprises are embracing advanced governance models around the world, and facing the challenge of effectively combining them with local culture. In the history of China, Fujian (Min) merchants formed a famous commercial group, leaving modern enterprises some precious enlightenment in its unique governance and inheritance mechanism. This research will extensively explore the governance mechanism of Fujian commercial group and assess its potentials and enlightenment for application in the system of modern enterprises. This research aims to provide theoretical and practical guidance for the development of a governance model matching with …

How Does Highly Educated Chinese Woman’S Endorsement Of Traditional Family Values Impact Her Well-Being?, Qiong Zhou

Dissertations and Theses Collection (Open Access)

With global advancements in gender equality and open-minded influence, Chinese women now have more opportunities to pursue higher education or independent work. However, there is a question of whether Chinese traditional family value still impacts Chinese women’s lives, thus affecting women's individual well-being.

Based on the results of a questionnaire survey and regression analysis of 301 highly educated Chinese women, we find that the endorsement of traditional family values by these women can indirectly affect their individual well-being through their engagement in job and family; that is, their achievements and satisfactions of job, family and self will be impacted by …

The Impact Of S2b2c Model On The Performance Of Chain Enterprises, Qingyang Zhao

Dissertations and Theses Collection (Open Access)

As the economy is highly developed today, enterprises are studying how to improve channel efficiency, customer loyalty, and supply chain stability along the value chain to ensure their competitive advantages. By observing the development of key chain-operated enterprises in China over the past 20 years, this study proposes to examine the impact of constructing an S2B2C model on corporate performance. A foundational theory has been established, and a theoretical framework has been analyzed. Following a logical order from the abstract to the concrete and from theory to practice, a combination of case studies and empirical analysis is employed to evaluate …

A Rose Or A Unicorn? Asean’S Mission Under The Spotlight, Lily Kong

Research Collection School of Social Sciences

In a commentary, SMU President Professor Lily Kong explores the question posed by political scientist Donald Emmerson in 1995 - is Southeast Asia more like a vibrant rose or an elusive unicorn? Against the backdrop of the 44th ASEAN Summit, with the theme "Connectivity and Resilience", Prof Kong highlights ASEAN's efforts in fostering regional connectivity and resilience through economic growth, cultural exchanges, and digital advancements. Despite substantial economic integration and digital connectivity, she points out that ASEAN faces challenges in creating a cohesive regional identity. The piece argues for deeper cultural engagement and a focus on shared values to build …

Evaluation Of Unplanned Reattendances To The Pediatric Emergency Department: A Five-Year Study, Liying Toh, Jin Wee Lee, Siok Hoon Ang, Sashikumar Ganapathy, Janani D/O Nadarajan, Shu-Ling Chong

Research Collection School Of Economics

Background: Unplanned reattendances (UR) are an important quality indicator in the emergency department (ED). Understanding the risk factors associated with UR can aid clinicians in optimizing the allocation of time and resources, as well as targeted counselling for this specific group of patients. In this study, we aimed to compare patient characteristics between children who attended a pediatric emergency department (ED) with unplanned reattendances (UR) and those without UR. We also aimed to study the association between healthcare delivery factors such as timing of the attendance, patient load, changeover months for rotating junior doctors, presence of supervision, and rate of …