Databases and Information Systems Commons^™

Mkboost: A Framework Of Multiple Kernel Boosting, Hao Xia, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Multiple kernel learning (MKL) is a promising family of machine learning algorithms using multiple kernel functions for various challenging data mining tasks. Conventional MKL methods often formulate the problem as an optimization task of learning the optimal combinations of both kernels and classifiers, which usually results in some forms of challenging optimization tasks that are often difficult to be solved. Different from the existing MKL methods, in this paper, we investigate a boosting framework of MKL for classification tasks, i.e., we adopt boosting to solve a variant of MKL problem, which avoids solving the complicated optimization tasks. Specifically, we present …

Gamification Of Education Using Computer Games, Fiona Fui-Hoon Nah, Venkata Telaprolu, Shashank Rallapalli, Pavani R. Venkata

Research Collection School Of Computing and Information Systems

We review the literature on gamification and identify principles of gamification and system design elements for gamifying computer educational games. Gamification of education is expected to increase learners’ engagement, which in turn increases learning achievement. We propose a gamification framework that synthesizes findings from the literature. The gamification framework is comprised of principles of gamification, system design elements for gamification, and dimensions of user engagement.

Usability Of Performance Dashboards, Usefulness Of Operational And Tactical Support, And Quality Of Strategic Support: A Research Framework, Bih-Ru Lea, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Performance dashboards are used as a strategic decision support tool in organizations. In this research, we examine the relationships between the usability of performance dashboards, the usefulness of operational and tactical support, and the quality of strategic support that they provide. We hypothesize that usability of performance dashboards will influence user perceptions of the usefulness of the operational and tactical support provided by the dashboards, which in turn influence the perceived quality of strategic support provided.

Unified Modeling Language: The Teen Years And Growing Pains, J. Erickson, Keng Siau

Research Collection School Of Computing and Information Systems

Unified Modeling Language (UML) is adopted by the Object Management Group as a standardized general-purpose modeling language for object-oriented software engineering. Despite its status as a standard, UML is still in a development stage and many studies have highlighted its weaknesses and challenges - including those related to human factor issues. Further, UML has grown considerably more complex since its inception. This paper traces the history of Unified Modeling Language (UML) from its formation to its current state and discusses the current state of the UML language. The paper first introduces UML and its various diagrams, and discusses its characteristics …

Usability Of Performance Dashboards, Usefulness Of Operational And Tactical Support, And Quality Of Strategic Support: A Research Framework, Bih-Ru Lea, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Performance dashboards are used as a strategic decision support tool in organizations. In this research, we examine the relationships between the usability of performance dashboards, the usefulness of operational and tactical support, and the quality of strategic support that they provide. We hypothesize that usability of performance dashboards will influence user perceptions of the usefulness of the operational and tactical support provided by the dashboards, which in turn influence the perceived quality of strategic support provided.

Video Concept Detection By Learning From Web Images: A Case Study On Cross Domain Learning, Shiai Zhu, Ting Yao, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Concept detection is probably the most important research problem in the area of multimedia. The need to model with sufficient and diverse training instances, however, makes the task computationally and resourcefully expensive. Meanwhile, the popularity of social media has generated massive amount of weakly tagged images which could be leveraged for concept model learning. Therefore, in this paper, we consider exploring weakly taggedWeb images to shed some light on video concept detection. Particularly, two sets of Web images downloaded from Flickr are utilized as training data for concept detection on two real-world large-scale video datasets released by TRECVID. Our experiments …

Active Learning With Expert Advice, Peilin Zhao, Steven C. H. Hoi, Jinfeng Zhuang

Research Collection School Of Computing and Information Systems

Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle can be costly or time consuming. In this paper, we address a new problem of active learning with expert advice, where the outcome of an instance is disclosed only when it is requested by the online learner. Our goal is to learn an accurate prediction model by asking the oracle the number of questions as small as possible. To address this challenge, we propose …

Real-Life Vehicle Routing With Non-Standard Constraints, Wee Leong Lee

Research Collection School Of Computing and Information Systems

Real-life vehicle routing problems comprise of a number of complexities that are not considered by the classical models found in vehicle routing literature. I present, in this paper, a two-stage sweep-based heuristic to find good solutions to a real-life Vehicle Routing Problem (VRP). The problem I shall consider, will deal with some non-standard constraints beyond those normally associated with the classical VRP. Other than considering the capacity constraints for vehicles and the time windows for deliveries, I shall introduce four additional non-standard constraints: merging of customer orders, controlling the maximum number of drop points, matching orders to vehicle types, and …

Shortlisting Top-K Assignments, Yimin Lin, Kyriakos Mouratidis

Research Collection School Of Computing and Information Systems

In this paper we identify a novel query type, the top-K assignment query (αTop-K). Consider a set of objects and a set of suppliers, where each object must be assigned to one supplier. Assume that there is a cost associated with every object-supplier pair. If we allocate each object to the server with the smallest cost (for the specific object), the derived overall assignment will have the minimum total cost. In many scenarios, however, runner-up assignments may be required too, like for example when a decision maker needs to make additional considerations, not captured by individual object-supplier costs. In this …

Reviving Dormant Ties In An Online Social Network Experiment, Ee Peng Lim, Denzil Correa, David Lo, Michael Finegold, Feida Zhu

Research Collection School Of Computing and Information Systems

Social network users connect and interact with one another to fulfil different kinds of social and information needs. When interaction ceases between two users, we say that their tie becomes dormant. While there are different underlying reasons of dormant ties, it is important to find means to revive such ties so as to maintain vibrancy in the relationships. In this work, we thus focus on designing an online experiment to evaluate the effectiveness of personalized social messages to revive dormant ties. The experiment carefully selects users with dormant ties so that no user gets mixed treatments and be affected by …

Indoor Positioning For Smartphones Using Asynchronous Ultrasound Trilateration, Viacheslav Filonenko, Charlie Cullen, James Carswell

Articles

Modern smartphones are a great platform for Location Based Services (LBS). While outdoor LBS for smartphones has proven to be very successful, indoor LBS for smartphones has not yet fully developed due to the lack of an accurate positioning technology. In this paper we present an accurate indoor positioning approach for commercial off-the-shelf (COTS) smartphones that uses the innate ability of mobile phones to produce ultrasound, combined with Time-Difference-of-Arrival (TDOA) asynchronous trilateration. We evaluate our indoor positioning approach by describing its strengths and weaknesses, and determine its absolute accuracy. This is accomplished through a range of experiments that involve variables …

Crisis Response Coordination In Online Communities, Hemant Purohit

Kno.e.sis Publications

During recent crises, citizens (sensors) are increasingly using social media to share variety of information- situation on the ground, emerging needs, donation offers, damage, etc. In such an evolving ad-hoc community, how can we extract actionable nuggets from the social media streams to aid relief efforts? This doctoral consortium presentation summarizes a framework to analyze social data and manage information to assist coordination by focusing on three important questions to answer: Whom to coordinate with, Why to coordinate and How to coordinate, with exemplary insights for needs and availability from the recent disaster events.

Based On Repeated Experience, System For Modification Of Expression And Negating Overload From Media And Optimizing Referential Efficiency, Peter R. Badovinatz, Veronika M. Megler

Computer Science Faculty Publications and Presentations

Content items are revealed to a user based on whether they have been previously reviewed by the user. A number of content items are thus received over time. The content items may be discrete content items, or may be portions of a content stream, and may be received over different media. For each content item, it is determined whether the content item was previously reviewed by a user. Where the content item was not previously reviewed, the item is revealed to the user, such as by being displayed or announced to the user. Where the content item was previously reviewed, …

Brovine: Mammary Gland Gene Database, Therin C. Irwin

Computer Science and Software Engineering

Brovine is used by the Animal Science department at Cal Poly to catalog and analyze genetic information. Brovine, or the Mammary Gland Gene Database, is a system used to store and categorize genetic information which is gathered through experimentation and through TESS, a web application that lets users search through catalogs of similar genetic information. This document describes the purpose, use, and maintenance of Brovine.

Anomaly Detection On Social Data, Hanbo Dai

Dissertations and Theses Collection (Open Access)

The advent of online social media including Facebook, Twitter, Flickr and Youtube has drawn massive attention in recent years. These online platforms generate massive data capturing the behavior of multiple types of human actors as they interact with one another and with resources such as pictures, books and videos. Unfortunately, the openness of these platforms often leaves them highly susceptible to abuse by suspicious entities such as spammers. It therefore becomes increasingly important to automatically identify these suspicious entities and eliminate their threats. We call these suspicious entities anomalies in social data, as they often hold different agenda comparing to …

Demo: Approximate Semantic Matching In The Collider Event Processing Engine, Souleiman Hasan, Kalpa Gunaratna, Yongrui Qin, Edward Curry

Kno.e.sis Publications

This demo presents a use case from the energy management domain. It builds upon previous work on approximate semantic matching of heterogeneous events and compares two semantic matching scenarios: exact and approximate. It illustrates how a large number of exact matching event subscriptions are needed to match heterogeneous power consumption events. It then demonstrates how a small number of approximate semantic matching subscriptions are needed but possibly with a lower true positives/negatives performance. The demo is delivered via the COLLIDER approximate event processing engine currently under development in DERI.

Visual Tracking Via Locality Sensitive Histograms, Shengfeng He, Qingxiong Yang, Rynson W.H. Lau, Jian Wang, Ming-Hsuan Yang

Research Collection School Of Computing and Information Systems

This paper presents a novel locality sensitive histogram algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of occurrences of each intensity value by adding ones to the corresponding bin, a locality sensitive histogram is computed at each pixel location and a floating-point value is added to the corresponding bin for each occurrence of an intensity value. The floating-point value declines exponentially with respect to the distance to the pixel location where the histogram is computed, thus every pixel is considered but those that are far away can be neglected due to the very small weights …

Preparing Detailed 3d Building Models For Google Earth Integration, Linh Truong-Hong, Thanh Thoa Pham Thi, Junjun Yin, James Carswell

Conference papers

Today's spatially aware users are becoming more interested in retrieving personalised and task relevant information, requiring detailed 3D city models linked to non-spatial attribute data. However, current implementations of 3D city models are typically LoD2 that don't include geometric or attribute details about many visible features (e.g. rooms) of a building. As such, valueadded applications developed for web-based and wireless platforms are limited to querying for available non-spatial business data at the building level only. To overcome this, geometrically accurate 3D building models are necessary to enable users to visualize, interact, and query for task specific non-spatial business data. This …

An Analysis Of Generational Caching Implemented In A Production Website, Marc E. Zych

Master's Theses

Website scaling has been an issue since the inception of the web. The demand for user generated content and personalized web pages requires the use of a database for a storage engine. Unfortunately, scaling the database to handle large amounts of traffic is still a problem many companies face. One such company is iFixit, a provider of free, publicly-editable, online repair manuals. Like many websites, iFixit uses Memcached to decrease database load and improve response time. However, the caching strategy used is a very ad hoc one and therefore can be greatly improved.

Most research regarding web application caching focuses …

A Latent Variable Model For Viewpoint Discovery From Threaded Forum Posts, Minghui Qiu, Jing Jiang

Research Collection School Of Computing and Information Systems

Threaded discussion forums provide an important social media platform. Its rich user generated content has served as an important source of public feedback. To automatically discover the viewpoints or stances on hot issues from forum threads is an important and useful task. In this paper, we propose a novel latent variable model for viewpoint discovery from threaded forum posts. Our model is a principled generative latent variable model which captures three important factors: viewpoint specific topic preference, user identity and user interactions. Evaluation results show that our model clearly outperforms a number of baseline models in terms of both clustering …

Mining User Relations From Online Discussions Using Sentiment Analysis And Probabilistic Matrix Factorization, Minghui Qiu, Liu Yang, Jing Jiang

Research Collection School Of Computing and Information Systems

Advances in sentiment analysis have enabled extraction of user relations implied in online textual exchanges such as forum posts. However, recent studies in this direction only consider direct relation extraction from text. As user interactions can be sparse in online discussions, we propose to apply collaborative filtering through probabilistic matrix factorization to generalize and improve the opinion matrices extracted from forum posts. Experiments with two tasks show that the learned latent factor representation can give good performance on a relation polarity prediction task and improve the performance of a subgroup detection task.

A Latent Variable Model For Viewpoint Discovery From Threaded Forum Posts, Minghui Qiu, Jing Jiang

Research Collection School Of Computing and Information Systems

No abstract provided.

Mining User Relations From Online Discussions Using Sentiment Analysis And Probabilistic Matrix Factorization, Minghui Qiu, Liu Yang, Jing Jiang

Research Collection School Of Computing and Information Systems

No abstract provided.

Hunts: A Trajectory Recommendation System For Effective And Efficient Hunting Of Taxi Passengers, Ye Ding, Siyuan Liu, Jiansu Pu, Lionel Ni

Research Collection School Of Computing and Information Systems

Nowadays, there are many taxis traversing around the city searching for available passengers, but their hunts of passengers are not always efficient. To the dynamics of traffic and biased passenger distributions, current offline recommendations based on place of interests may not work well. In this paper, we define a new problem, global-optimal trajectory retrieving (GOTR), as finding a connected trajectory of high profit and high probability to pick up a passenger within a given time period in real-time. To tackle this challenging problem, we present a system, called HUNTS, based on the knowledge from both historical and online GPS data …

T-Watcher: A New Visual Analytic System For Effective Traffic Surveillance, Jiansu Pu, Siyuan Liu, Ye Ding, Huamin Qu, Lionel Ni

Research Collection School Of Computing and Information Systems

Nowadays, big cities are suffering from severe traffic congestion as a result of the continuing increase in vehicles. Taxis equipped with GPS can be viewed as sensors of the traffic situation in city. However, trajectory data generated by taxi’s GPS traces are often high-dimensional and contain large spatial and temporal attributes, which pose challenges for analysts. In this paper, based on taxi trajectory data, we present an interactive visual analytics system, T-Watcher, for monitoring and analyzing complex traffic situations in big cities. Users are able to use a carefully designed interface to monitor and inspect data interactively from three levels …

Real Time Event Detection In Twitter, Xun Wang, Feida Zhu, Jing Jiang, Sujian Li

Research Collection School Of Computing and Information Systems

Event detection has been an important task for a long time. When it comes to Twitter, new problems are presented. Twitter data is a huge temporal data flow with much noise and various kinds of topics. Traditional sophisticated methods with a high computational complexity aren’t designed to handle such data flow efficiently. In this paper, we propose a mixture Gaussian model for bursty word extraction in Twitter and then employ a novel time-dependent HDP model for new topic detection. Our model can grasp new events, the location and the time an event becomes bursty promptly and accurately. Experiments show the …

A Direct Mining Approach To Efficient Constrained Graph Pattern Discovery, Feida Zhu, Zequn Zhang, Qiang Qu

Research Collection School Of Computing and Information Systems

Despite the wealth of research on frequent graph pattern mining, how to efficiently mine the complete set of those with constraints still poses a huge challenge to the existing algorithms mainly due to the inherent bottleneck in the mining paradigm. In essence, mining requests with explicitly-specified constraints cannot be handled in a way that is direct and precise. In this paper, we propose a direct mining framework to solve the problem and illustrate our ideas in the context of a particular type of constrained frequent patterns — the “skinny” patterns, which are graph patterns with a long backbone from which …

Concept Graphs: Applications To Biomedical Text Categorization And Concept Extraction, Said Bleik

Dissertations

As science advances, the underlying literature grows rapidly providing valuable knowledge mines for researchers and practitioners. The text content that makes up these knowledge collections is often unstructured and, thus, extracting relevant or novel information could be nontrivial and costly. In addition, human knowledge and expertise are being transformed into structured digital information in the form of vocabulary databases and ontologies. These knowledge bases hold substantial hierarchical and semantic relationships of common domain concepts. Consequently, automating learning tasks could be reinforced with those knowledge bases through constructing human-like representations of knowledge. This allows developing algorithms that simulate the human reasoning …

Main-Stream Media Behaviour Analysis On Twitter: A Case Study On Uk General Election, Zhongyu Wei, Yulan He, Wei Gao, Binyang Li, Lanjun Zhou, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

With the development of social media tools such as Facebook and Twitter, mainstream media organizations including newspapers and TV media have played an active role in engaging with their audience and strengthening their influence on the recently emerged platforms. In this paper, we analyze the behavior of mainstream media on Twitter and study how they exert their influence to shape public opinion during the UK's 2010 General Election. We first propose an empirical measure to quantify mainstream media bias based on sentiment analysis and show that it correlates better with the actual political bias in the UK media than the …

Hybrid Methods For Feature Selection, Iunniang Cheng

Masters Theses & Specialist Projects

Feature selection is one of the important data preprocessing steps in data mining. The feature selection problem involves finding a feature subset such that a classification model built only with this subset would have better predictive accuracy than model built with a complete set of features. In this study, we propose two hybrid methods for feature selection. The best features are selected through either the hybrid methods or existing feature selection methods. Next, the reduced dataset is used to build classification models using five classifiers. The classification accuracy was evaluated in terms of the area under the Receiver Operating Characteristic …