Digital Commons Network^™

Beyond Search: Event-Driven Summarization For Web Videos, Richard Hong, Jinhui Tang, Hung-Khoon Tan, Chong-Wah Ngo, Shuicheng Yan, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The explosive growth of Web videos brings out the challenge of how to efficiently browse hundreds or even thousands of videos at a glance. Given an event-driven query, social media Web sites usually return a large number of videos that are diverse and noisy in a ranking list. Exploring such results will be time-consuming and thus degrades user experience. This article presents a novel scheme that is able to summarize the content of video search results by mining and threading "key" shots, such that users can get an overview of main content of these videos at a glance. The proposed …

Enabling Gpu Acceleration With Messaging Middleware, Randall E. Duran, Li Zhang, Tom Hayhurst

Research Collection School Of Computing and Information Systems

Graphics processing units (GPUs) offer great potential for accelerating processing for a wide range of scientific and business applications. However, complexities associated with using GPU technology have limited its use in applications. This paper reviews earlier approaches improving GPU accessibility, and explores how integration with middleware messaging technologies can further improve the accessibility and usability of GPU-enabled platforms. The results of a proof-of-concept integration between an open-source messaging middleware platform and a general-purpose GPU platform using the CUDA framework are presented. Additional applications of this technique are identified and discussed as potential areas for further research.

Exploring Tweets Normalization And Query Time Sensitivity For Twitter Search, Zhongyu Wei, Wei Gao, Lanjun Zhou, Binyang Li, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

This paper presents our work for the Realtime Adhoc Task of TREC 2011 Microblog Track. Microblog texts like tweets are generally characterized by the inclusion of a large proportion of irregular expressions, such as ill-formed words, which can lead to significant mismatch between query terms and tweets. In addition, Twitter queries are distinguished from Web queries with many unique characteristics, one of which reflects the clearly distinct temporal aspects of Twitter search behavior. In this study, we deal with the first problem by normalizing tweet texts and the second by capturing the temporal characteristics of topic. We divided topics into …

Consistent Community Identification In Complex Networks, Haewoon Kwak, Young-Ho Eom, Yoonchan Choi, Hawoong Jeong

Research Collection School Of Computing and Information Systems

We have found that known community identification algorithms produce inconsistent communities when the node ordering changes at input. We use the pairwise membership probability and consistency to quantify the level of consistency across multiple runs of an algorithm. Based on these two metrics, we address the consistency problem without compromising the modularity. The key insight of the algorithm is to use pairwise membership probabilities as link weights. It offers a new tool in the study of community structures and their evolutions.

Coping With Distance: An Empirical Study Of Communication On The Jazz Platform, Renuka Sindhgatta, Bikram Sengupta, Subhajit Datta

Research Collection School Of Computing and Information Systems

Global software development - which is characterized by teams separated by physical distance and/or time-zone differences - has traditionally posed significant communication challenges. Often these have caused delays in completing tasks, or created misalignment across sites leading to re-work. In recent years, however, a new breed of development environments with rich collaboration features have emerged to facilitate cross-site work in distributed projects. In this paper we revisit the question "does distance matter?" in the context of IBM Jazz Platform -- a state-of-the-art collaborative development environment. We study the ecosystem of a large distributed team of around 300 members across 35 …

Software Process Evaluation: A Machine Learning Approach, Ning Chen, Steven C. H. Hoi, Xiaokui Xiao

Research Collection School Of Computing and Information Systems

Software process evaluation is essential to improve software development and the quality of software products in an organization. Conventional approaches based on manual qualitative evaluations (e.g., artifacts inspection) are deficient in the sense that (i) they are time-consuming, (ii) they suffer from the authority constraints, and (iii) they are often subjective. To overcome these limitations, this paper presents a novel semi-automated approach to software process evaluation using machine learning techniques. In particular, we formulate the problem as a sequence classification task, which is solved by applying machine learning algorithms. Based on the framework, we define a new quantitative indicator to …

A Pomdp Model For Guiding Taxi Cruising In A Congested Urban City, Lucas Agussurja, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We consider a partially observable Markov decision process (POMDP) model for improving a taxi agent cruising decision in a congested urban city. Using real-world data provided by a large taxi company in Singapore as a guide, we derive the state transition function of the POMDP. Specifically, we model the cruising behavior of the drivers as continuous-time Markov chains. We then apply dynamic programming algorithm for finding the optimal policy of the driver agent. Using a simulation, we show that this policy is significantly better than a greedy policy in congested road network.

Finding Relevant Answers In Software Forums, Swapna Gottopati, David Lo, Jing Jiang

Research Collection School Of Computing and Information Systems

Online software forums provide a huge amount of valuable content. Developers and users often ask questions and receive answers from such forums. The availability of a vast amount of thread discussions in forums provides ample opportunities for knowledge acquisition and summarization. For a given search query, current search engines use traditional information retrieval approach to extract webpages containing relevant keywords. However, in software forums, often there are many threads containing similar keywords where each thread could contain a lot of posts as many as 1,000 or more. Manually finding relevant answers from these long threads is a painstaking task to …

Profit-Maximizing Firm Investments In Customer Information Security, Yong Yick Lee, Robert J. Kauffman, Ryan Sougstad

Research Collection School Of Computing and Information Systems

When a customer interacts with a firm, extensive personal information often is gathered without the individual's knowledge. Significant risks are associated with handling this kind of information. Providing protection may reduce the risk of the loss and misuse of private information, but it imposes some costs on both the firm and its customers. Nevertheless, customer information security breaches still may occur. They have several distinguishing characteristics: (1) typically it is hard to quantify monetary damages related to them; (2) customer information security breaches may be caused by intentional attacks, as well as through unintentional organizational and customer behaviors; and (3) …

Price Points And Price Rigidity, Daniel Levy, Dongwon Lee, Haipeng (Allen) Lee, Robert J. Kauffman, Mark Bergen

Research Collection School Of Computing and Information Systems

We study the link between price points and price rigidity using two data sets: weekly scanner data and Internet data. We find that ‘‘9’’ is the most frequent ending for the penny, dime, dollar, and ten-dollar digits; the most common price changes are those that keep the price endings at ‘‘9’’; 9-ending prices are less likely to change than non-9-ending prices; and the average size of price change is larger for 9-ending than non-9- ending prices. We conclude that 9-ending contributes to price rigidity from penny to dollar digits and across a wide range of product categories, retail formats, and …

Pat 3: An Extensible Architecture For Building Multi-Domain Model Checkers, Yang Liu, Jun Sun, Jin Song Dong

Research Collection School Of Computing and Information Systems

Model checking is emerging as an effective software verification method. Although it is desirable to have a dedicated model checker for each application domain, implementing one is rather challenging. In this work, we develop an extensible and integrated architecture in PAT3 (PAT version 3.*) to support the development of model checkers for wide range application domains. PAT3 adopts a layered design with an intermediate representation layer (IRL), which separates modeling languages from model checking algorithms so that the algorithms can be shared by different languages. IRL contains several common semantic models to support wide application domains, and builds both explicit …

Applying Time-Bound Hierarchical Key Assignment In Wireless Sensor Networks, Wentao Zhu, Robert H. Deng, Jianying Zhou, Feng Bao

Research Collection School Of Computing and Information Systems

Access privileges in distributed systems can be effectively organized as a partial-order hierarchy that consists of distinct security classes, and are often designated with certain temporal restrictions. The time-bound hierarchical key assignment problem is to assign distinct cryptographic keys to distinct security classes according to their privileges so that users from a higher class can use their class key to derive the keys of lower classes, and these keys are time-variant with respect to sequentially allocated temporal units called time slots. In this paper, we explore applications of time-bound hierarchical key assignment in a wireless sensor network environment where there …

Managing Successive Generation Product Diffusion In The Presence Of Strategic Consumers, Zhiling Guo

Research Collection School Of Computing and Information Systems

Frequent new product release and technological uncertainty about the release time pose significant challenges for firms to manage successive generation of products. On the one hand, strategic consumers may delay their purchase decision and substitute the earlier generation with the newer generation product. On the other hand, the firm must fully anticipate consumer reactions and take into account the effect of their strategic behavior on product pricing and successive generation product diffusion. This paper proposes a prediction market to forecast new product release. We show that the market information aggregation mechanism can improve forecast accuracy of new product launch. Better …

A Brain-Inspired Model Of Hierarchical Planner, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Hierarchical planning is an approach of planning by composing and executing hierarchically arranged plans to solve some problems. Most symbolic-based hierarchical planners have been devised to allow the knowledge to be described expressively. However, a great challenge is to automatically seek and acquire new plans on the fly. This paper presents a novel neural-based model of hierarchical planning that can seek and acquired new plans on-line if the necessary knowledge are lacking. Inspired by findings in neuropsychology, plans can be inherently learnt, retrieved, and manipulated simultaneously rather than discretely processed like in most symbolic approaches. Using a multi-channel adaptive resonance …

Are There Contagion Effects In Information Technology And Business Process Outsourcing?, Arti Mann, Robert J. Kauffman, Kunsoo Han, Barrie R. Nault

Research Collection School Of Computing and Information Systems

We model the diffusion of IT outsourcing using announcements about IT outsourcing deals. We estimate a lognormal diffusion curve to test whether IT outsourcing follows a pure diffusion process or there are contagion effects involved. The methodology permits us to study the consequences of outsourcing events, especially mega-deals with IT contract amounts that exceed US$1 billion. Mega-deals act, we theorize, as precipitating events that create a strong basis for contagion effects and are likely to affect decision-making by other firms in an industry. Then, we evaluate the role of different communication channels in the diffusion process of IT outsourcing by …

Learning Human Emotion Patterns For Modeling Virtual Humans, Shu Feng, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Emotion modeling is a crucial part in modeling virtual humans. Although various emotion models have been proposed, most of them focus on designing specific appraisal rules. As there is no unified framework for emotional appraisal, the appraisal variables have to be defined beforehand and evaluated in a subjective way. In this paper, we propose an emotion model based on machine learning methods by taking the following position: an emotion model should mirror actual human emotion in the real world and connect tightly with human inner states, such as drives, motivations and personalities. Specifically, a self-organizing neural model called Emotional Appraisal …

An Efficient Algorithm For Learning Event-Recording Automata, Shang-Wei Lin, Étienne André, Jin Song Dong, Jun Sun, Yang Liu

Research Collection School Of Computing and Information Systems

In inference of untimed regular languages, given an unknown language to be inferred, an automaton is constructed to accept the unknown language from answers to a set of membership queries each of which asks whether a string is contained in the unknown language. One of the most well-known regular inference algorithms is the L* algorithm, proposed by Angluin in 1987, which can learn a minimal deterministic finite automaton (DFA) to accept the unknown language. In this work, we propose an efficient polynomial time learning algorithm, TL*, for timed regular language accepted by event-recording automata. Given an unknown timed regular language, …

Prts: An Approach For Model Checking Probabilistic Real-Time Hierarchical Systems, Jun Sun, Yang Liu, Songzheng Song, Jin Song Dong, Xiaohong Li

Research Collection School Of Computing and Information Systems

Model Checking real-life systems is always difficult since such systems usually have quantitative timing factors and work in unreliable environment. The combination of real-time and probability in hierarchical systems presents a unique challenge to system modeling and analysis. In this work, we develop an automated approach for verifying probabilistic, real-time, hierarchical systems. Firstly, a modeling language called PRTS is defined, which combines data structures, real-time and probability. Next, a zone-based method is used to build a finite-state abstraction of PRTS models so that probabilistic model checking could be used to calculate the probability of a system satisfying certain property. We …

Differencing Labeled Transition Systems, Zhenchang Xing, Jun Sun, Yang Liu, Jin Song Dong

Research Collection School Of Computing and Information Systems

Concurrent programs often use Labeled Transition Systems (LTSs) as their operational semantic models, which provide the basis for automatic system analysis and verification. System behaviors (generated from the operational semantics) evolve as programs evolve for fixing bugs or implementing new user requirements. Even when a program remains unchanged, its LTS models explored by a model checker or analyzer may be different due to the application of different exploration methods. In this paper, we introduce a novel approach (named SpecDiff) to computing the differences between two LTSs, representing the evolving behaviors of a concurrent program. SpecDiff considers LTSs as Typed Attributed …

Cooperative Reinforcement Learning In Topology-Based Multi-Agent Systems, Dan Xiao, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Topology-based multi-agent systems (TMAS), wherein agents interact with one another according to their spatial relationship in a network, are well suited for problems with topological constraints. In a TMAS system, however, each agent may have a different state space, which can be rather large. Consequently, traditional approaches to multi-agent cooperative learning may not be able to scale up with the complexity of the network topology. In this paper, we propose a cooperative learning strategy, under which autonomous agents are assembled in a binary tree formation (BTF). By constraining the interaction between agents, we effectively unify the state space of individual …

Strategic Responses To Standardization: Embrace, Extend Or Extinguish?, C. Jason Woodard, Joel West

Research Collection School Of Computing and Information Systems

Prior research on technology standardization has focused on two common patterns: processes in which product developers and other stakeholders cooperate to achieve a consensus outcome, and “standards wars” in which competing technologies vie for dominance in the market. This study examines Microsoft's responses to 12 software technologies in the period between 1990 and 2005. Despite the company's reputed tendency to pursue a strategy dubbed “embrace, extend, and extinguish,” a content analysis of news articles from the same period reveals surprising diversity in Microsoft's responses at the product level.

We classify these responses using a typology that treats “embrace” and “extend” …

Virality Modeling And Analysis, Tuan Anh Hoang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Virality is a virus-like behavior that allows a piece of information to widely and quickly diffuse within the network of adopters through word of mouth. It is about how easy users propagate information to their friends and friends of friends by means of diffusion. While virality of information has several interesting applications, there are much research to be conducted on virality. These areas of research include understanding the mechanism of virality, modeling the virality both qualitatively and quantitatively, and applying virality to applications such as marketing, event detection, and others. In this paper, we survey existing works on quantitative models …

A Survey Of Information Diffusion Models And Relevant Problems, Minh Duc Luu, Tuan Anh Hoang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

There has been tremendous interest in diffusion of innovations or information in a social system. Nowadays, social networks (offline as well as online) are considered as important medium for diffusion and large amount of research has been conducted to understand the dynamics of diffusion in social networks. In this work, we review some of the models proposed for diffusion in social networks. We also highlight the major features of these models by dividing the surveyed models into two categories: non-network and network diffusion models. The former refers to user communities without any knowledge about the user relationship network and the …

A Survey Of Techniques And Challenges In Underwater Localization, Hwee-Pink Tan, Roee Diamant, Winston K. G. Seah, Marc Waldmeyer

Research Collection School Of Computing and Information Systems

Underwater Wireless Sensor Networks (UWSNs) are expected to support a variety of civilian and military applications. Sensed data can only be interpreted meaningfully when referenced to the location of the sensor, making localization an important problem. While global positioning system (GPS) receivers are commonly used in terrestrial WSNs to achieve this, this is infeasible in UWSNs as GPS signals do not propagate through water. Acoustic communications is the most promising mode of communication underwater. However, underwater acoustic channels are characterized by harsh physical layer conditions with low bandwidth, high propagation delay and high bit error rate. Moreover, the variable speed …

Collaborative Online Learning Of User Generated Content, Guangxia Li, Kuiyu Chang, Steven C. H. Hoi, Wenting Liu, Ramesh Jain

Research Collection School Of Computing and Information Systems

We study the problem of online classification of user generated content, with the goal of efficiently learning to categorize content generated by individual user. This problem is challenging due to several reasons. First, the huge amount of user generated content demands a highly efficient and scalable classification solution. Second, the categories are typically highly imbalanced, i.e., the number of samples from a particular useful class could be far and few between compared to some others (majority class). In some applications like spam detection, identification of the minority class often has significantly greater value than that of the majority class. Last …

Efficient Evaluation Of Continuous Text Seach Queries, Kyriakos Mouratidis, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Consider a text filtering server that monitors a stream of incoming documents for a set of users, who register their interests in the form of continuous text search queries. The task of the server is to constantly maintain for each query a ranked result list, comprising the recent documents (drawn from a sliding window) with the highest similarity to the query. Such a system underlies many text monitoring applications that need to cope with heavy document traffic, such as news and email monitoring.In this paper, we propose the first solution for processing continuous text queries efficiently. Our objective is to …

Recommending People In Developers' Collaboration Network, Didi Surian, Nian Liu, David Lo, Hanghang Tong, Ee Peng Lim, Christos Faloutsos

Research Collection School Of Computing and Information Systems

Many software developments involve collaborations of developers across the globe. This is true for both open-source and closed-source development efforts. Developers collaborate on different projects of various types. As with any other teamwork endeavors, finding compatibility among members in a development team is helpful towards the realization of the team’s goal. Compatible members tend to share similar programming style and naming strategy, communicate well with one another, etc. However, finding the right person to work with is not an easy task. In this work, we extract information available from Sourceforge.Net, the largest database of open source software, and build developer …

Concern Localization Using Information Retrieval: An Empirical Study On Linux Kernel, Shaowei Wang, David Lo, Zhenchang Xing, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Many software maintenance activities need to find code units (functions, files, etc.) that implement a certain concern (features, bugs, etc.). To facilitate such activities, many approaches have been proposed to automatically link code units with concerns described in natural languages, which are termed as concern localization and often employ Information Retrieval (IR) techniques. There has not been a study that evaluates and compares the effectiveness of latest IR techniques on a large dataset. This study fills this gap by investigating ten IR techniques, some of which are new and have not been used for concern localization, on a Linux kernel …

Code Search Via Topic-Enriched Dependence Graph Matching, Shaowei Wang, David Lo, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Source code contains textual, structural, and semantic information, which can all be leveraged for effective search. Some studies have proposed semantic code search where users can specify query topics in a natural language. Other studies can search through system dependence graphs. In this paper, we propose a semantic dependence search engine that integrates both kinds of techniques and can retrieve code snippets based on expressive user queries describing both topics and dependencies. Users can specify their search targets in a free form format describing desired topics (i.e., high-level semantic or functionality of the target code); a specialized graph query language …

Mining Direct Antagonistic Communities In Explicit Trust Networks, David Lo, Didi Surian, Zhang Kuan, Ee Peng Lim

Research Collection School Of Computing and Information Systems

There has been a recent increase of interest in analyzing trust and friendship networks to gain insights about relationship dynamics among users. Many sites such as Epinions, Facebook, and other social networking sites allow users to declare trusts or friendships between different members of the community. In this work, we are interested in extracting direct antagonistic communities (DACs) within a rich trust network involving trusts and distrusts. Each DAC is formed by two subcommunities with trust relationships among members of each sub-community but distrust relationships across the sub-communities. We develop an efficient algorithm that could analyze large trust networks leveraging …