Physical Sciences and Mathematics Commons^™

Happy Toilet: A Social Analytics Approach To The Study Of Public Toilet Cleanliness, Eugene W. J. Choy, Winston M. K. Ho, Xiaohang Li, Ragini Verma, Li Jin Sim, Kyong Jin Shim

Research Collection School Of Computing and Information Systems

This study presents a social analytics approach to the study of public toilet cleanliness in Singapore. From popular social media platforms, our system automatically gathers and analyzes relevant public posts that mention about toilet cleanliness in highly frequented locations across the Singapore island - from busy shopping malls to food 'hawker' centers.

A Unified Variance-Reduced Accelerated Gradient Method For Convex Optimization, Guanghui Lan, Zhize Li, Yi Zhou

Research Collection School Of Computing and Information Systems

We propose a novel randomized incremental gradient algorithm, namely, VAriance-Reduced Accelerated Gradient (Varag), for finite-sum optimization. Equipped with a unified step-size policy that adjusts itself to the value of the conditional number, Varag exhibits the unified optimal rates of convergence for solving smooth convex finite-sum problems directly regardless of their strong convexity. Moreover, Varag is the first accelerated randomized incremental gradient method that benefits from the strong convexity of the data-fidelity term to achieve the optimal linear convergence. It also establishes an optimal linear rate of convergence for solving a wide class of problems only satisfying a certain error bound …

Ssrgd: Simple Stochastic Recursive Gradient Descent For Escaping Saddle Points, Zhize Li

Research Collection School Of Computing and Information Systems

We analyze stochastic gradient algorithms for optimizing nonconvex problems. In particular, our goal is to find local minima (second-order stationary points) instead of just finding first-order stationary points which may be some bad unstable saddle points. We show that a simple perturbed version of stochastic recursive gradient descent algorithm (called SSRGD) can find an $(\epsilon,\delta)$-second-order stationary point with $\widetilde{O}(\sqrt{n}/\epsilon^2 + \sqrt{n}/\delta^4 + n/\delta^3)$ stochastic gradient complexity for nonconvex finite-sum problems. As a by-product, SSRGD finds an $\epsilon$-first-order stationary point with $O(n+\sqrt{n}/\epsilon^2)$ stochastic gradients. These results are almost optimal since Fang et al. [2018] provided a lower bound $\Omega(\sqrt{n}/\epsilon^2)$ for finding …

Clustering Models For Topic Analysis In Graduate Discussion Forums, Mallika Gokarn Nitin, Swapna Gottipati, Venky Shankararaman

Research Collection School Of Computing and Information Systems

Discussion forums provide the base content for creating a knowledge repository. It contains discussion threads related to key course topics that are debated by the students. In order to better understand the student learning experience, the instructor needs to analyse these discussion threads. This paper proposes the use of clustering models and interactive visualizations to conduct a qualitative analysis of graduate discussion forums. Our goal is to identify the sub-topics and topic evolutions in the discussion forums by applying text mining techniques. Our approach generates insights into the topic analysis in the forums and discovers the students’ cognitive understanding within …

Optimal Design And Ownership Structures Of Innovative Retail Payment Systems, Zhiling Guo, Dan Ma

Research Collection School Of Computing and Information Systems

In response to the Fintech trend, an ongoing debate in the banking industry is how to design the new-generation interbank retail payment and settlement system. We propose a two-stage analytical model that takes into account the value-risk tradeoff in the new payment system design, as well as banks’ participation incentives and adoption timing decisions. We find that, as the system base value increases, banks tend to synchronize their investment and adoption decisions. When the system base value is low and banks are heterogeneous, bank association ownership maximizes social welfare. When both the system base value and bank heterogeneity are moderate, …

The Information Disclosure Trilemma: Privacy, Attribution And Dependency, Ping Fan Ke

Research Collection School Of Computing and Information Systems

Information disclosure has been an important mechanism to increase transparency and welfare in various contexts, from rating a restaurant to whistleblowing the wrongdoing of government agencies. Yet, the author often needs to be sacrificed during information disclosure process – an anonymous disclosure will forgo the reputation and compensation whereas an identifiable disclosure will face the threat of retaliation. On the other hand, the adoption of privacy-enhancing technologies (PETs) lessens the tradeoff between privacy and attribution while introducing dependency and potential threats. This study will develop the desirable design principles and possible threats of an information disclosure system, and discuss how …

Smu Teaching Bank: Case Study Of A Multiyear Development Project Utilizing Student Resources, Alan Megargel, Terence P. C. Fan, Venky Shankararaman

Research Collection School Of Computing and Information Systems

A domain refers to a business sector such as banking, healthcare, insurance, manufacturing etc. For an IS student, it is imperative that the domain knowledge includes a comprehension and understanding of business processes, technology and data related to the chosen domain. For example, when learning the retail banking domain, an IS student must have an understanding of the transactions concerned with retail banking such as fund transfers and loan repayments. The student must also gain a strong foothold in transaction fulfilment processes, the various application services that are used, the data that is transferred, etc. Teaching domain knowledge is very …

Online Content Consumption: Social Endorsements, Observational Learning And Word-Of-Mouth, Qian Tang, Tingting Song, Liangfei Qiu, Ashish Agarwal

Research Collection School Of Computing and Information Systems

The consumption of online content can occur through observational learning (OL) whereby consumers follow previous consumers’ choices or social endorsement (SE) wherein consumers receive content sharing from their social ties. As users consume content, they also generate post-consumption word-of-mouth (WOM) signals. OL, SE and WOM together shape the diffusion of the content. This study examines the drivers of SE and the effect of SE on content consumption and post-consumption WOM. In particular, we compare SE with OL. Using a random sample of 8,945 new videos posted on YouTube, we collected a multi-platform dataset consisting of data on video consumption and …

Self-Organizing Neural Networks For Universal Learning And Multimodal Memory Encoding, Ah-Hwee Tan, Budhitama Subagdja, Di Wang, Lei Meng

Research Collection School Of Computing and Information Systems

Learning and memory are two intertwined cognitive functions of the human brain. This paper shows how a family of biologically-inspired self-organizing neural networks, known as fusion Adaptive Resonance Theory (fusion ART), may provide a viable approach to realizing the learning and memory functions. Fusion ART extends the single-channel Adaptive Resonance Theory (ART) model to learn multimodal pattern associative mappings. As a natural extension of ART, various forms of fusion ART have been developed for a myriad of learning paradigms, ranging from unsupervised learning to supervised learning, semi-supervised learning, multimodal learning, reinforcement learning, and sequence learning. In addition, fusion ART models …

Learning To Detect Pedestrians By Watching Videos, Andrew Y. Chen

Theses and Dissertations

The field of deep learning has experienced a resurgence in the recent years, particularly resulting with the advent of AlexNet. Supervised learning is currently the most common and practical machine learning method. The struggle with employing supervised learning to approach problems is that it requires training data. Sufficient training data is correlated with performance for deep learning models. The issue is that preparing the training data can be a tedious and labor intensive task, especially on a large scale. The purpose of this paper is to determine how efficient a machine can learn when trained on automatically annotated data. The …

Comparison Of Rl Algorithms For Learning To Learn Problems, Adolfo Gonzalez Iii

Theses and Dissertations

Machine learning has been applied to many different problems successfully due to the expressiveness of neural networks and simplicity of first order optimization algorithms. The latter being a vital piece needed for training large neural networks efficiently. Many of these algorithms were produced with behavior produced by experiments and intuition. An interesting question that comes to mind is that rather than observing and then designing algorithms with beneficial behaviors, can these algorithms be learned through a reinforcement learning by modeling optimization as a game. This paper explores several reinforcement learning algorithms which are applied to learn policies suited for optimization.

Detecting Phone-Related Pedestrian Behavior Using A Two-Branch Convolutional Neural Network, Humberto Saenz

Theses and Dissertations

With the wide use of smart phones, distraction has become a major safety concern to roadway users. The distracted phone-use behaviors among pedestrians, like Texting, Game Playing and Phone Calls, have caused increasing fatalities and serious injuries. With the increasing usage of driver monitor systems on intelligent vehicles, distracted driver behaviors can be efficiently detected and warned. However, the research of phone-related distracted behavior by pedestrians has not been systemically studied. It is desired to improve both the driving and pedestrian safety by automatically discovering the phone-related pedestrian distracted behaviors. In this thesis, we propose a new computer vision-based method …

Salience-Aware Adaptive Resonance Theory For Large-Scale Sparse Data Clustering, Lei Meng, Ah-Hwee Tan, Chunyan Miao

Research Collection School Of Computing and Information Systems

Sparse data is known to pose challenges to cluster analysis, as the similarity between data tends to be ill-posed in the high-dimensional Hilbert space. Solutions in the literature typically extend either k-means or spectral clustering with additional steps on representation learning and/or feature weighting. However, adding these usually introduces new parameters and increases computational cost, thus inevitably lowering the robustness of these algorithms when handling massive ill-represented data. To alleviate these issues, this paper presents a class of self-organizing neural networks, called the salience-aware adaptive resonance theory (SA-ART) model. SA-ART extends Fuzzy ART with measures for cluster-wise salient feature modeling. …

Improving Video Game Recommendations Using A Hybrid, Neural Network And Keyword Ranking Approach, Nicholas Crawford

Faculty of Applied Science and Technology - Exceptional Student Work, Applied Computing Theses

Recommendations systems are software solutions for finding high-quality and relevant content for a given user type ranging from online shoppers, to music listeners, to video game players. Traditional recommendation systems use user review data to make recommendations, but we still want recommendations to perform well for new users with no review data. Currently, one of the problems that exists in recommendations is poor recommendation accuracy when only a small amount of data exists for a user, called the cold start problem. In this research we investigate solutions for the cold start problem in video game recommendations and we propose a …

Seer: An Explainable Deep Learning Midi-Based Hybrid Song Recommender System, Khalil Damak, Olfa Nasraoui

Faculty Scholarship

State of the art music recommender systems mainly rely on either matrix factorization-based collaborative filtering approaches or deep learning architectures. Deep learning models usually use metadata for content-based filtering or predict the next user interaction by learning from temporal sequences of user actions. Despite advances in deep learning for song recommendation, none has taken advantage of the sequential nature of songs by learning sequence models that are based on content. Aside from the importance of prediction accuracy, other significant aspects are important, such as explainability and solving the cold start problem. In this work, we propose a hybrid deep learning …

Testing Isomorphism Of Graded Algebras, Peter A. Brooksbank, James B. Wilson, Eamonn A. O'Brien

Faculty Journal Articles

We present a new algorithm to decide isomorphism between finite graded algebras. For a broad class of nilpotent Lie algebras, we demonstrate that it runs in time polynomial in the order of the input algebras. We introduce heuristics that often dramatically improve the performance of the algorithm and report on an implementation in Magma.

Social Media Sentiment Analysis With A Deep Neural Network: An Enhanced Approach Using User Behavioral Information, Ahmed Sulaiman M. Alharbi

Dissertations

Sentiment analysis on social media such as Twitter has become a very important and challenging task. Due to the characteristics of such data (including tweet length, spelling errors, abbreviations, and special characters), the sentiment analysis task in such an environment requires a non-traditional approach. Moreover, social media sentiment analysis constitutes a fundamental problem with many interesting applications, such as for Business Intelligence, Medical Monitoring, and National Security. Most current social media sentiment classification methods judge the sentiment polarity primarily according to textual content and neglect other information on these platforms. In this research, we propose deep learning based frameworks that …

Scalable Algorithms And Hybrid Parallelization Strategies For Multivariate Integration With Paradapt And Cuda, Omofolakunmi Elizabeth Olagbemi

Dissertations

The evaluation of numerical integrals finds applications in fields such as High Energy Physics, Bayesian Statistics, Stochastic Geometry, Molecular Modeling and Medical Physics. The erratic behavior of some integrands due to singularities, peaks, or ridges in the integration region suggests the need for reliable algorithms and software that not only provide an estimation of the integral with a level of accuracy acceptable to the user, but also perform this task in a timely manner. We developed ParAdapt, a numerical integration software based on a classic global adaptive strategy, which employs Graphical Processing Units (GPUs) in providing integral evaluations. Specifically, ParAdapt …

Toward Self-Reconfigurable Parametric Systems: Reinforcement Learning Approach, Ting-Yu Mu

Dissertations

For the ongoing advancement of the fields of Information Technology (IT) and Computer Science, machine learning-based approaches are utilized in different ways in order to solve the problems that belong to the Nondeterministic Polynomial time (NP)-hard complexity class or to approximate the problems if there is no known efficient way to find a solution. Problems that determine the proper set of reconfigurable parameters of parametric systems to obtain the near optimal performance are typically classified as NP-hard problems with no efficient mathematical models to obtain the best solutions. This body of work aims to advance the knowledge of machine learning …

Improved Generalisation Bounds For Deep Learning Through L∞ Covering Numbers, Antoine Ledent, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

Using proof techniques involving L∞ covering numbers, we show generalisation error bounds for deep learning with two main improvements over the state of the art. First, our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating the bounds in terms of the L 2 norm of the weight matrices, while previous bounds exhibit at least a square-root dependence on the number of classes in this case. Second, we adapt the Rademacher analysis of DNNs to incorporate weight sharing—a task of fundamental theoretical importance which was previously attempted only under very …

An Empirical Study Of Sms One-Time Password Authentication In Android Apps, Siqi Ma, Runhan Feng, Juanru Li, Yang Liu, Surya Nepal, Elisa Bertino, Robert H. Deng, Zhuo Ma, Sanjay Jha

Research Collection School Of Computing and Information Systems

A great quantity of user passwords nowadays has been leaked through security breaches of user accounts. To enhance the security of the Password Authentication Protocol (PAP) in such circumstance, Android app developers often implement a complementary One-Time Password (OTP) authentication by utilizing the short message service (SMS). Unfortunately, SMS is not specially designed as a secure service and thus an SMS One-Time Password is vulnerable to many attacks. To check whether a wide variety of currently used SMS OTP authentication protocols in Android apps are properly implemented, this paper presents an empirical study against them. We first derive a set …

Objective Sleep Quality As A Predictor Of Mild Cognitive Impairment In Seniors Living Alone, Brian Chen, Hwee-Pink Tan, Irus Rawtaer, Hwee Xian Tan

Research Collection School Of Computing and Information Systems

Singapore has the fastest ageing population in the Asia Pacific region, with an estimated 82,000 seniors living with dementia. These figures are projected to increase to more than 130,000 by 2030. The challenge is to identify more community dwelling seniors with Mild Cognitive Impairment (MCI), a prodromal state, as it provides an opportunity for evidence-based early intervention to delay the onset of dementia. In this paper, we explore the use of Internet of Things (IoT) systems in detecting MCI symptoms in seniors who are living alone, and accurately grouping them into MCI positive and negative subjects. We present feature extraction …

Digitalization In Practice: The Fifth Discipline Advantage, Siu Loon Hoe

Research Collection School Of Computing and Information Systems

Purpose The purpose of this paper is to provide advice to organizations on how to become successful in the digital age. The paper revisits Peter Senge's (1990) notion of the learning organization and discusses the relevance of systems thinking and the other four disciplines, namely, personal mastery, mental models, shared vision and team learning in the context of the current digitalization megatrend. Design/methodology/approach This paper is based on content analysis of essays from international organizations, strategy experts and management scholars, and insights gained from the author's consulting experience. A comparative case study from the health and social sector is also …

An Iot-Driven Smart Cafe Solution For Human Traffic Management, Maruthi Prithivirajan, Kyong Jin Shim

Research Collection School Of Computing and Information Systems

In this study, we present an IoT-driven solution for human traffic management in a corporate cafe. Using IoT sensors, our system monitors human traffic in a physical cafe located at a large international corporation located in Singapore. The backend system analyzes the streaming data from the sensors and provides insights useful to the cafe visitors as well as the cafe manager.

A Mathematical Programming Model For The Green Mixed Fleet Vehicle Routing Problem With Realistic Energy Consumption And Partial Recharges, Vincent F. Yu, Panca Jodiwan, Aldy Gunawan, Audrey Tedja Widjaja

Research Collection School Of Computing and Information Systems

A green mixed fleet vehicle routing with realistic energy consumption and partial recharges problem (GMFVRP-REC-PR) is addressed in this paper. This problem involves a fixed number of electric vehicles and internal combustion vehicles to serve a set of customers. The realistic energy consumption which depends on several variables is utilized to calculate the electricity consumption of an electric vehicle and fuel consumption of an internal combustion vehicle. Partial recharging policy is included into the problem to represent the real life scenario. The objective of this problem is to minimize the total travelled distance and the total emission produced by internal …

Event Reconstruction In The Advanced Particle-Astrophysics Telescope, Emily Ramey

McKelvey School of Engineering Theses & Dissertations

The Advanced Particle-Astrophysics Telescope (APT) is a concept for a gamma-ray space telescope operating in the keV to MeV energy range. Due to the nature of the telescope and the physics of detection, reconstructing initial photon trajectories can be very computationally complex. This is a barrier to the real-time detection of astrophysical transient phenomena such as Gamma Ray Bursts (GRBs), and a faster reconstruction algorithm is needed in order to effectively study them. In this project, we develop such an algorithm based on Boggs & Jean (2000) and discuss the effects of certain algorithmic parameters on computational performance. For testing, …

A Transformative Concept: From Data Being Passive Objects To Data Being Active Subjects, Hans-Peter Plag, Shelley-Ann Jules-Plag

OES Faculty Publications

The exploitation of potential societal benefits of Earth observations is hampered by users having to engage in often tedious processes to discover data and extract information and knowledge. A concept is introduced for a transition from the current perception of data as passive objects (DPO) to a new perception of data as active subjects (DAS). This transition would greatly increase data usage and exploitation, and support the extraction of knowledge from data products. Enabling the data subjects to actively reach out to potential users would revolutionize data dissemination and sharing and facilitate collaboration in user communities. The three core elements …

Leveraging Defects Life-Cycle For Labeling Defective Classes, Bailey R. Vandehei

Master's Theses

Data from software repositories are a very useful asset to building dierent kinds of

models and recommender systems aimed to support software developers. Specically,

the identication of likely defect-prone les (i.e., classes in Object-Oriented systems)

helps in prioritizing, testing, and analysis activities. This work focuses on automated

methods for labeling a class in a version as defective or not. The most used methods

for automated class labeling belong to the SZZ family and fail in various circum-

stances. Thus, recent studies suggest the use of aect version (AV) as provided by

developers and available in the issue tracker such as …

Evaluating The Resiliency Of Industrial Internet Of Things Process Control Using Protocol Agnostic Attacks, Hector L. Roldan

Theses and Dissertations

Improving and defending our nation's critical infrastructure has been a challenge for quite some time. A malfunctioning or stoppage of any one of these systems could result in hazardous conditions on its supporting populace leading to widespread damage, injury, and even death. The protection of such systems has been mandated by the Office of the President of the United States of America in Presidential Policy Directive Order 21. Current research now focuses on securing and improving the management and efficiency of Industrial Control Systems (ICS). IIoT promises a solution in enhancement of efficiency in ICS. However, the presence of IIoT …

Server Assignment With Time-Varying Workloads In Mobile Edge Computing, Quynh Vo

Graduate Doctoral Dissertations

Mobile Edge Computing (MEC) has emerged as a viable technology for mobile operators to push computing resources closer to the users so that requests can be served locally without long-haul crossing of the network core, thus improving network efficiency and user experience. In MEC, commodity servers are deployed in the edge to form a distributed network of mini datacenters. A consequential task is to partition the user cells into groups, each to be served by an edge server, to maximize the offloading to the edge. The conventional setting for this problem in the literature is: (1) assume that the interaction …