Databases and Information Systems Commons^™

Online Learning With Nonlinear Models, Doyen Sahoo

Dissertations and Theses Collection (Open Access)

Recent years have witnessed the success of two broad categories of machine learning algorithms: (i) Online Learning; and (ii) Learning with nonlinear models. Typical machine learning algorithms assume that the entire data is available prior to the training task. This is often not the case in the real world, where data often arrives sequentially in a stream, or is too large to be stored in memory. To address these challenges, Online Learning techniques evolved as a promising solution to having highly scalable and efficient learning methodologies which could learn from data arriving sequentially. Next, as the real world data exhibited …

Policy Analytics For Environmental Sustainability: Household Hazardous Waste And Water Impacts Of Carbon Pollution Standards, Kustini

Dissertations and Theses Collection (Open Access)

Policy analytics are essential in supporting more informed policy-making in environmental management. This dissertation employs a fusion of machine methods and explanatory empiricism that involves data analytics, math programming, optimization, econometrics, geospatial and spatiotemporal analysis, and other approaches for assessing and evaluating current and future environmental policies.
Essay 1 discusses household informedness and its impact on the collection and recycling of household hazardous waste (HHW). Household informedness is the degree to which households have the necessary information to make utility-maximizing decisions about the handling of their waste. Such informedness seems to be influenced by HHW public education and environmental quality …

Who Are Your Users? Comparing Media Professionals' Preconception Of Users To Data-Driven Personas, Lene Nielsen, Soon-Gyu Jung, Jisun An, Joni Salminen, Haewoon Kwak, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

One of the reasons for using personas is to align user understandings across project teams and sites. As part of a larger persona study, at Al Jazeera English (AJE), we conducted 16 qualitative interviews with media producers, the end users of persona descriptions. We asked the participants about their understanding of a typical AJE media consumer, and the variety of answers shows that the understandings are not aligned and are built on a mix of own experiences, own self, assumptions, and data given by the company. The answers are sometimes aligned with the data-driven personas and sometimes not. The end …

Enterprise Social Media Use And Impact On Performance: The Role Of Workplace Integration And Positive Emotions, Murad Moqbel, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Organizations struggle to find ways to improve employees’ performance. To date, little research has empirically examined the relationship between enterprise social media use and knowledge workers’ performance. Using social capital theory and the broaden-and-build theory of positive emotions as our theoretical framework, we investigate the relationship between enterprise social media use and knowledge workers’ performance. We tested our research model by collecting data from employees working for a large information technology firm in the Midwestern United States and analyzing the data using a structural equation modeling approach. The results suggest that enterprise social media use can increase workplace integration, which …

Analyzing The E-Learning Video Environment Requirements Of Generation Z Students Using Echo360 Platform, Swapna Gottipati, Venky Shankararaman

Research Collection School Of Computing and Information Systems

As with any other generational cohort,Generation Z students have their own unique characteristics that influencetheir approach to learning process. They are the future workforce and severalefforts are undertaken by Government and education institutes to consider thecharacteristics of Gen-Z in developing the curriculum and teaching environmentsuitable for these students. E-learning plays a key role in students learningprocess and has been widely adopted by many education institutions. Inparticular, videos play a major role in the learning process of Gen-Zstudents. The purpose of this paper isto focus the on requirements of Gen-Z students and to provide suggestions forhow to create a e-learning video …

D-Watch: Embracing “Bad” Multipaths For Device-Free Localization With Cots Rfid Devices, Ju Wang, Jie Xiong, Hongbo Jiang, Xiaojiang Chen, Dingyi Fang

Research Collection School Of Computing and Information Systems

Device-free localization, which does not require any device attached to the target, is playing a critical role in many applications, such as intrusion detection, elderly monitoring and so on. This paper introduces D-Watch, a device-free system built on the top of low cost commodity-off-the-shelf RFID hardware. Unlike previous works which consider multipaths detrimental, D-Watch leverages the ''bad'' multipaths to provide a decimeter-level localization accuracy without offline training. D-Watch harnesses the angle-of-arrival information from the RFID tags' backscatter signals. The key intuition is that whenever a target blocks a signal's propagation path, the signal power experiences a drop which can be …

Leveraging Auxiliary Tasks For Document-Level Cross-Domain Sentiment Classification, Jianfei Yu, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper, we study domain adaptationwith a state-of-the-art hierarchicalneural network for document-level sentimentclassification. We first design a newauxiliary task based on sentiment scoresof domain-independent words. We thenpropose two neural network architecturesto respectively induce document embeddingsand sentence embeddings that workwell for different domains. When thesedocument and sentence embeddings areused for sentiment classification, we findthat with both pseudo and external sentimentlexicons, our proposed methods canperform similarly to or better than severalhighly competitive domain adaptationmethods on a benchmark dataset of productreviews.

Btci: A New Framework For Identifying Congestion Cascades Using Bus Trajectory Data, Meng-Fen Chiang, Ee Peng Lim, Wang-Chien Lee, Agus Trisnajaya Kwee

Research Collection School Of Computing and Information Systems

The knowledge of traffic health status is essential to the general public and urban traffic management. To identify congestion cascades, an important phenomenon of traffic health, we propose a Bus Trajectory based Congestion Identification (BTCI) framework that explores the anomalous traffic health status and structure properties of congestion cascades using bus trajectory data. BTCI consists of two main steps, congested segment extraction and congestion cascades identification. The former constructs path speed models from historical vehicle transitions and design a non-parametric Kernel Density Estimation (KDE) function to derive a measure of congestion score. The latter aggregates congested segments (i.e., those with …

Inferring Social Media Users’ Demographics From Profile Pictures: A Face++ Analysis On Twitter Users, Soon-Gyo Jung, Jisun An, Haewoon Kwak, Joni Salminen, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

In this research, we evaluate the applicability of using facial recognition of social media account profile pictures to infer the demographic attributes of gender, race, and age of the account owners leveraging a commercial and well-known image service, specifically Face++. Our goal is to determine the feasibility of this approach for actual system implementation. Using a dataset of approximately 10,000 Twitter profile pictures, we use Face++ to classify this set of images for gender, race, and age. We determine that about 30% of these profile pictures contain identifiable images of people using the current state-of-the-art automated means. We then employ …

A Novel Density Peak Clustering Algorithm Based On Squared Residual Error, Milan Parmar, Di Wang, Ah-Hwee Tan, Chunyan Miao, Jianhua Jiang, You Zhou

Research Collection School Of Computing and Information Systems

The density peak clustering (DPC) algorithm is designed to quickly identify intricate-shaped clusters with high dimensionality by finding high-density peaks in a non-iterative manner and using only one threshold parameter. However, DPC has certain limitations in processing low-density data points because it only takes the global data density distribution into account. As such, DPC may confine in forming low-density data clusters, or in other words, DPC may fail in detecting anomalies and borderline points. In this paper, we analyze the limitations of DPC and propose a novel density peak clustering algorithm to better handle low-density clustering tasks. Specifically, our algorithm …

Robust Human Activity Recognition Using Lesser Number Of Wearable Sensors, Di Wang, Edwin Candinegara, Junhui Hou, Ah-Hwee Tan, Chunyan Miao

Research Collection School Of Computing and Information Systems

In recent years, research on the recognition of human physical activities solely using wearable sensors has received more and more attention. Compared to other types of sensory devices such as surveillance cameras, wearable sensors are preferred in most activity recognition applications mainly due to their non-intrusiveness and pervasiveness. However, many existing activity recognition applications or experiments using wearable sensors were conducted in the confined laboratory settings using specifically developed gadgets. These gadgets may be useful for a small group of people in certain specific scenarios, but probably will not gain their popularity because they introduce additional costs and they are …

Using Data Analytics For Discovering Library Resource Insights: Case From Singapore Management University, Ning Lu, Rui Song, Dina Li Gwek Heng, Swapna Gottipati, Aaron Tay

Research Collection School Of Computing and Information Systems

Library resources are critical in supporting teaching, research and learning processes. Several universities have employed online platforms and infrastructure for enabling the online services to students, faculty and staff. To provide efficient services by understanding and predicting user needs libraries are looking into the area of data analytics. Library analytics in Singapore Management University is the project committed to provide an interface for data-intensive project collaboration, while supporting one of the library’s key pillars on its commitment to collaborate on initiatives with SMU Communities and external groups. In this paper, we study the transaction logs for user behavior analysis that …

The Graph Database: Jack Of All Trades Or Just Not Sql?, George F. Hurlburt, Maria R. Lee, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

This special issue of IT Professional focuses on the graph database. The graph database, a relatively new phenomenon, is well suited to the burgeoning information era in which we are increasingly becoming immersed. Here, the guest editors briefly explain how a graph database works, its relation to the relational database management system (RDBMS), and its quantitative and qualitative pros and cons, including how graph databases can be harnessed in a hybrid environment. They also survey the excellent articles submitted for this special issue.

Multi-Step Tokenization Of Automated Clearing House Payment Transactions, Privin Alexander

USF Tampa Graduate Theses and Dissertations

Since its beginnings in 1974, the Automated Clearing House (ACH) network has grown into one of the largest, safest, and most efficient payment systems in the world. An ACH transaction is an electronic funds transfer between bank accounts using a batch processing system.

Currently, the ACH Network moves almost $43 trillion and 25 billion electronic financial transactions each year. With the increasing movement toward an electronic, interconnected and mobile infrastructure, it is critical that electronic payments work safely and efficiently for all users. ACH transactions carry sensitive data, such as a consumer's name, account number, tax identification number, account holder …

Constructing A Clinical Research Data Management System, Michael C. Quintero

USF Tampa Graduate Theses and Dissertations

Clinical study data is usually collected without knowing what kind of data is going to be collected in advance. In addition, all of the possible data points that can apply to a patient in any given clinical study is almost always a superset of the data points that are actually recorded for a given patient. As a result of this, clinical data resembles a set of sparse data with an evolving data schema. To help researchers at the Moffitt Cancer Center better manage clinical data, a tool was developed called GURU that uses the Entity Attribute Value model to handle …

A Study On The Practical Use Of Operations Research And Vessels Big Data In Benefit Of Efficient Ports Utilization In Panama, Gabriel Fuentes Lezcano

World Maritime University Dissertations

No abstract provided.

Uncovering User-Triggered Privacy Leaks In Mobile Applications And Their Utility In Privacy Protection, Joo Keng Joseph Chan

Dissertations and Theses Collection

Mobile applications are increasingly popular, and help mobile users in many aspects of their lifestyle. Applications have access to a wealth of information about the user through powerful developer APIs. It is known that most applications, even popular and highly regarded ones, utilize and leak privacy data to the network. It is also common for applications to over-access privacy data that does not fit the functionality profile of the application. Although there are available privacy detection tools, they might not provide sufficient context to help users better understand the privacy behaviours of their applications. In this dissertation, I present the …

Semvis: Semantic Visualization For Interactive Topical Analysis, Le Van Minh Tuan, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Exploratory analysis of a text corpus is an important task that can be aided by informative visualization. One spatially-oriented form of document visualization is a scatterplot, whereby every document is associated with a coordinate, and relationships among documents can be perceived through their spatial distances. Semantic visualization further infuses the visualization space with latent semantics, by incorporating a topic model that has a representation in the visualization space, allowing users to also perceive relationships between documents and topics spatially. We illustrate how a semantic visualization system called SemVis could be used to navigate a text corpus interactively and topically via …

Large Scale Kernel Methods For Online Auc Maximization, Yi Ding, Chenghao Liu, Peilin Zhao, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Learning to optimize AUC performance for classifying label imbalanced data in online scenarios has been extensively studied in recent years. Most of the existing work has attempted to address the problem directly in the original feature space, which may not suitable for non-linearly separable datasets. To solve this issue, some kernel-based learning methods are proposed for non-linearly separable datasets. However, such kernel approaches have been shown to be inefficient and failed to scale well on large scale datasets in practice. Taking this cue, in this work, we explore the use of scalable kernel-based learning techniques as surrogates to existing approaches: …

Guest Editor's Introduction To The Special Issue On Source Code Analysis And Manipulation (Scam 2015), Foutse Khomh, David Lo, Michael W. Godfrey

Research Collection School Of Computing and Information Systems

We are happy to introduce you to this special issue that presents selected papers from the 15th IEEE International Working Conference on Source Code Analysis and Manipulation (SCAM 2015). SCAM is a leading conference that brings together researchers and practitioners working on theory, techniques, and applications that concern analysis and/or manipulation of the source code of computer systems. While much attention in the wider software engineering community is properly directed towards other aspects of systems development and evolution, such as specification, design, and requirements engineering, it is the source code that contains the only precise description of the behavior of …

An Integrated Framework For Modeling And Predicting Spatiotemporal Phenomena In Urban Environments, Tuc Viet Le

Dissertations and Theses Collection (Open Access)

This thesis proposes a general solution framework that integrates methods in machine learning in creative ways to solve a diverse set of problems arising in urban environments. It particularly focuses on modeling spatiotemporal data for the purpose of predicting urban phenomena. Concretely, the framework is applied to solve three specific real-world problems: human mobility prediction, trac speed prediction and incident prediction. For human mobility prediction, I use visitor trajectories collected a large theme park in Singapore as a simplified microcosm of an urban area. A trajectory is an ordered sequence of attraction visits and corresponding timestamps produced by a visitor. …

Scalable Online Kernel Learning, Jing Lu

Dissertations and Theses Collection (Open Access)

One critical deficiency of traditional online kernel learning methods is their increasing and unbounded number of support vectors (SV’s), making them inefficient and non-scalable for large-scale applications. Recent studies on budget online learning have attempted to overcome this shortcoming by bounding the number of SV’s. Despite being extensively studied, budget algorithms usually suffer from several drawbacks.
First of all, although existing algorithms attempt to bound the number of SV’s at each iteration, most of them fail to bound the number of SV’s for the final averaged classifier, which is commonly used for online-to-batch conversion. To solve this problem, we propose …

Vireo @ Trecvid 2017: Video-To-Text, Ad-Hoc Video Search And Video Hyperlinking, Phuong Anh Nguyen, Qing Li, Zhi-Qi Cheng, Yi-Jie Lu, Hao Zhang, Xiao Wu, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

In this paper, we describe the systems developed for Video-to-Text (VTT), Ad-hoc Video Search (AVS) and Video Hyper-linking (LNK) tasks at TRECVID 2017 [1] and the achieved results.

Color-Sketch Simulator: A Guide For Color-Based Visual Known-Item Search, Jakub Lokoč, Anh Nguyen Phuong, Marta Vomlelová, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

In order to evaluate the effectiveness of a color-sketch retrieval system for a given multimedia database, tedious evaluations involving real users are required as users are in the center of query sketch formulation. However, without any prior knowledge about the bottlenecks of the underlying sketch-based retrieval model, the evaluations may focus on wrong settings and thus miss the desired effect. Furthermore, users have usually no clues or recommendations to draw color-sketches effectively. In this paper, we aim at a preliminary analysis to identify potential bottlenecks of a flexible color-sketch retrieval model. We present a formal framework based on position-color feature …

Modeling Check-In Behavior With Geographical Neighborhood Influence Of Venues, Thanh Nam Doan, Ee Peng Lim

Research Collection School Of Computing and Information Systems

With many users adopting location-based social networks (LBSNs) to share their daily activities, LBSNs become a gold mine for researchers to study human check-in behavior. Modeling such behavior can benefit many useful applications such as urban planning and location-aware recommender systems. Unlike previous studies [4,6,12,17] that focus on the effect of distance on users checking in venues, we consider two venue-specific effects of geographical neighborhood influence, namely, spatial homophily and neighborhood competition. The former refers to the fact that venues share more common features with their spatial neighbors, while the latter captures the rivalry of a venue and its nearby …

Predicting Indoor Crowd Density Using Column-Structured Deep Neural Network, Akihito Sudo, Teck Hou (Deng Dehao) Teng, Hoong Chuin Lau, Yoshihide Sekimoto

Research Collection School Of Computing and Information Systems

This work proposes a deep neural network approach known as the column-structured deep neural network (COL-DNN-R) for predicting crowd density in an indoor environment using historical Wi-Fi traces of individual visitors. With a structure designed to minimize feature engineering, COL-DNN accepts raw features such as crowd density, opening and closing hours and peak visitor counts for extracting features. The extracted features are used by a regression model R for predicting the crowd densities. Standard regression models such as MLP, RF and SVM can be used as R. Experiments are performed to investigate the effect of feature representation and model structure …

Leveraging Social Analytics Data For Identifying Customer Segments For Online News Media, Jansen, Bernard J, Soon-Gyo Jung, Jisun An, Haewoon Kwak, Haewoon Kwak

Research Collection School Of Computing and Information Systems

In this work, we describe a methodology for leveraging large amounts of customer interaction data with online content from major social media platforms in order to isolate meaningful customer segments. The methodology is robust in that it can rapidly identify diverse customer segments using solely online behaviors and then associate these behavioral customer segments with the related distinct demographic segments, presenting a holistic picture of the customer base of an organization. We validate our methodology via the implementation of a working system that rapidly and in near real-time processes tens of millions of online customer interactions with content posted on …

Eeg-Based Emotion Recognition Via Fast And Robust Feature Smoothing, Cheng Tang, Di Wang, Ah-Hwee Tan, Chunyan Miao

Research Collection School Of Computing and Information Systems

Electroencephalograph (EEG) signals reveal much of our brain states and have been widely used in emotion recognition. However, the recognition accuracy is hardly ideal mainly due to the following reasons: (i) the features extracted from EEG signals may not solely reflect one’s emotional patterns and their quality is easily affected by noise; and (ii) increasing feature dimension may enhance the recognition accuracy, but it often requires extra computation time. In this paper, we propose a feature smoothing method to alleviate the aforementioned problems. Specifically, we extract six statistical features from raw EEG signals and apply a simple yet cost-effective feature …

Second-Order Online Active Learning And Its Applications, Shuji Hao, Jing Lu, Peilin Zhao, Chi Zhang, Steven C. H. Hoi, Chunyan Miao

Research Collection School Of Computing and Information Systems

The goal of online active learning is to learn predictive models from a sequence of unlabeled data given limited label querybudget. Unlike conventional online learning tasks, online active learning is considerably more challenging because of two reasons.Firstly, it is difficult to design an effective query strategy to decide when is appropriate to query the label of an incoming instance givenlimited query budget. Secondly, it is also challenging to decide how to update the predictive models effectively whenever the true labelof an instance is queried. Most existing approaches for online active learning are often based on a family of first-order online …

Highly Efficient Mining Of Overlapping Clusters In Signed Weighted Networks, Tuan-Anh Hoang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

In many practical contexts, networks are weighted as their links are assigned numerical weights representing relationship strengths or intensities of inter-node interaction. Moreover, the links' weight can be positive or negative, depending on the relationship or interaction between the connected nodes. The existing methods for network clustering however are not ideal for handling very large signed weighted networks. In this paper, we present a novel method called LPOCSIN (short for "Linear Programming based Overlapping Clustering on Signed Weighted Networks") for efficient mining of overlapping clusters in signed weighted networks. Different from existing methods that rely on computationally expensive cluster cohesiveness …