Databases and Information Systems Commons^™

Artificial Intelligence - I: Adaptive Automated Teller Machines - Part Ii, Ghulam Mujtaba, Tariq Mahmood

International Conference on Information and Communication Technologies

Nowadays, the banking sector is increasingly relying on Automated Teller Machines (ATMs) in order to provide services to its customers. Although thousands of ATMs exist across many banks and different locations, the GUI and content of a typical ATM interface remains, more or less, the same. For instance, any ATM provides typical options for withdrawal, electronic funds transfer, viewing of mini-statements etc. However, such a static interface might not be suitable for all ATM customers, e.g., some users might not prefer to view all the options when they access the ATM, or to view specific withdrawal amounts less than, say, …

Artificial Intelligence – I: Adaptive Automated Teller Machines — Part I, Ghulam Mujtaba, Tariq Mahmood

International Conference on Information and Communication Technologies

During the past few years, the banking sector has started providing a variety of services to its customers. One of the most significant of such services has been the introduction of the Automated Teller Machines (ATMs) for providing online support to bank customers. The use of ATMs has reached its zenith in every developed country, and thousands of ATM transactions are occurring on a daily basis. In order to increase the customers' satisfaction and to provide them with more user-friendly ATM interfaces, it becomes important to mine the ATM transactions to discover useful patterns about the customers' interacting behaviors. In …

Evaluating And Implementing Web Scale Discovery Services: Part Two, Jason Vaughan, Tamera Hanken

Library Faculty Presentations

Part Four: Quick Tour of the Current Marketplace:

• "The Big 5"
• Similarities and differences

Part Five: It's Not All Sliced Bread:

• Shortcomings of web scale discovery

Part Six: Implementation (pre launch steps):

• Selecting and preparing implementation staff
• Preparing and communicating process/decisions with all staff
• Working with the vendor (roles, expectations, timeline)
• Workflow changes and implications (technical services)

Part Seven: Specific implementation tasks, issues, and considerations:

• Record loading and mapping (catalog content)
• Harvesting and mapping digital/local content
• Working with central index data (internal & external content)
• Web integration and customization
• Assessment and continuous improvement

Citizen Sensing: Opportunities And Challenges In Mining Social Signals And Perceptions, Amit P. Sheth

Kno.e.sis Publications

Millions of persons have become 'citizens' of an Internet- or Web-enabled social community. Web 2.0 fostered the open environment and applications for tagging, blogging, wikis, and social networking sites that have made information consumption, production, and sharing so incredibly easy. An interconnected network of people who actively observe, report, collect, analyze, and disseminate information via text, audio, or video messages, increasingly through pervasively connected mobile devices, has led to what we term citizen sensing. In this talk, we review recent progress in supporting collective intelligence through intelligent processing of citizen sensing. Key issues we cover in this talk are: - …

Evaluating And Implementing Web Scale Discovery Services: Part One, Jason Vaughan, Tamera Hanken

Library Faculty Presentations

Preface: Before Web Scale Discovery

• A very brief overview

Part 1: What is Web Scale Discovery

• Content
• Technology

Part 2: Why is Web Scale Discovery important?

• What’s the need?
• How is it different from earlier attempts at broad discovery?

Part 3: A Framework for Evaluating Web Scale Discovery Services

• What we did at UNLV
• Other options

Comparison Of Clustered Rdf Data Stores, Venkata Patchigolla

Purdue Polytechnic Masters Theses

Storing data in RDF format helps in simpler data interchange among different researchers compared to present approaches. There has been tremendous increase in the applications that use RDF data. The nature of RDF data is such that it tends to increase explosively. This makes it necessary to consider the time for retrieval and scalability of data while selecting a suitable RDF data store for developing applications. The research concentrates on comparing BigOWLIM. Bigdata, 4store and Virtuoso RDF stores on basis of their scalability and performance of storing and retrieving cancer proteomics and mass spectrometry data using SPARQL queries. In this …

Local Closed World Semantics: Keep It Simple, Stupid!, Adila Krishnadhi, Kunal Sengupta, Pascal Hitzler

Computer Science and Engineering Faculty Publications

A combination of open and closed-world reasoning (usually called local closed world reasoning) is a desirable capability of knowledge representation formalisms for Semantic Web applications. However, none of the proposals made to date for extending description logics with local closed world capabilities has had any significant impact on applications. We believe that one of the key reasons for this is that current proposals fail to provide approaches which are intuitively accessible for application developers at the same time are applicable, as extensions, to expressive description logics as SROIQ, which underlies the Web Ontology Language OWL.

In this paper, we propose …

Web Wisdom: An Essay On How Web 2.0 And Semantic Web Can Foster A Global Knowledge Society, Christopher Thomas, Amit P. Sheth

Kno.e.sis Publications

Admittedly this is a presumptuous title that should never be used when reporting on individual research advances. Wisdom is just not a scientific concept. In this case, though, we are reporting on recent developments on the web that lead us to believe that the web is on the way to providing a platform for not only information acquisition and business transactions but also for large scale knowledge development and decision support. It is likely that by now every web user has participated in some sort of social function or knowledge accumulating function on the web, many times without even being …

Automatic Content Generation For Video Self Modeling, Ju Shen, Anusha Raghunathan, Sen-Ching S. Cheung, Ravi R. Patel

Computer Science Faculty Publications

Video self modeling (VSM) is a behavioral intervention technique in which a learner models a target behavior by watching a video of him or herself. Its effectiveness in rehabilitation and education has been repeatedly demonstrated but technical challenges remain in creating video contents that depict previously unseen behaviors. In this paper, we propose a novel system that re-renders new talking-head sequences suitable to be used for VSM treatment of patients with voice disorder. After the raw footage is captured, a new speech track is either synthesized using text-to-speech or selected based on voice similarity from a database of clean speeches. …

A Hybrid Agent Architecture Integrating Desire, Intention And Reinforcement Learning, Ah-Hwee Tan, Yew-Soon Ong, Akejariyawong Tapanuj

Research Collection School Of Computing and Information Systems

This paper presents a hybrid agent architecture that integrates the behaviours of BDI agents, specifically desire and intention, with a neural network based reinforcement learner known as Temporal DifferenceFusion Architecture for Learning and COgNition (TD-FALCON). With the explicit maintenance of goals, the agent performs reinforcement learning with the awareness of its objectives instead of relying on external reinforcement signals. More importantly, the intention module equips the hybrid architecture with deliberative planning capabilities, enabling the agent to purposefully maintain an agenda of actions to perform and reducing the need of constantly sensing the environment. Through reinforcement learning, plans can also be …

Mining Weakly Labeled Web Facial Images For Search-Based Face Annotation, Dayang Wang, Steven C. H. Hoi, Ying He

Research Collection School Of Computing and Information Systems

In this paper, we investigate a search-based face annotation framework by mining weakly labeled facial images that are freely available on the internet. A key component of such a search-based annotation paradigm is to build a database of facial images with accurate labels. This is however challenging since facial images on the WWW are often noisy and incomplete. To improve the label quality of raw web facial images, we propose an effective Unsupervised Label Refinement (ULR) approach for refining the labels of web facial images by exploring machine learning techniques. We develop effective optimization algorithms to solve the large-scale learning …

Online Auc Maximization, Peilin Zhao, Steven C. H. Hoi, Rong Jin, Tianbo Yang

Research Collection School Of Computing and Information Systems

Most studies of online learning measure the performance of a learner by classification accuracy, which is inappropriate for applications where the data are unevenly distributed among different classes. We address this limitation by developing online learning algorithm for maximizing Area Under the ROC curve (AUC), a metric that is widely used for measuring the classification performance for imbalanced data distributions. The key challenge of online AUC maximization is that it needs to optimize the pairwise loss between two instances from different classes. This is in contrast to the classical setup of online learning where the overall loss is a sum …

Heuristic Algorithms For Balanced Multi-Way Number Partitioning, Jilian Zhang, Kyriakos Mouratidis, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Balanced multi-way number partitioning (BMNP) seeks to split a collection of numbers into subsets with (roughly) the same cardinality and subset sum. The problem is NP-hard, and there are several exact and approximate algorithms for it. However, existing exact algorithms solve only the simpler, balanced two-way number partitioning variant, whereas the most effective approximate algorithm, BLDM, may produce widely varying subset sums. In this paper, we introduce the LRM algorithm that lowers the expected spread in subset sums to one third that of BLDM for uniformly distributed numbers and odd subset cardinalities. We also propose Meld, a novel strategy for …

Generating Aspect-Oriented Multi-Document Summarization With Event-Aspect Model, Peng Li, Yinglin Wang, Wei Gao, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper, we propose a novel approach to automatic generation of aspect-oriented summaries from multiple documents. We first develop an event-aspect LDA model to cluster sentences into aspects. We then use extended LexRank algorithm to rank the sentences in each cluster. We use Integer Linear Programming for sentence selection. Key features of our method include automatic grouping of semantically related sentences and sentence ranking based on extension of random walk model. Also, we implement a new sentence compression algorithm which use dependency tree instead of parser tree. We compare our method with four baseline methods. Quantitative evaluation based on …

Relevant Knowledge Helps In Choosing Right Teacher: Active Query Selection For Ranking Adaptation, Peng Cai, Wei Gao, Kam-Fai Wong, Aoying Zhou

Research Collection School Of Computing and Information Systems

Learning to adapt in a new setting is a common challenge to our knowledge and capability. New life would be easier if we actively pursued supervision from the right mentor chosen with our relevant but limited prior knowledge. This variant principle of active learning seems intuitively useful to many domain adaptation problems. In this paper, we substantiate its power for advancing automatic ranking adaptation, which is important in web search since it's prohibitive to gather enough labeled data for every search domain for fully training domain-specific rankers. For the cost-effectiveness, it is expected that only those most informative instances in …

Linking Entities To A Knowledge Base With Query Expansion, Swapna Gottipati, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper we present a novel approach to entity linking based on a statistical language model-based information retrieval with query expansion. We use both local contexts and global world knowledge to expand query language models. We place a strong emphasis on named entities in the local contexts and explore a positional language model to weigh them differently based on their distances to the query. Our experiments on the TAC-KBP 2010 data show that incorporating such contextual information indeed aids in disambiguating the named entities and consistently improves the entity linking performance. Compared with the official results from KBP 2010 …

Effects Of Mentoring On Player Performance In Massively Multiplayer Online Role-Playing Games (Mmorpgs), Kyong Jin Shim, Kuo-Wei Hsu, Jaideep Srivastava

Research Collection School Of Computing and Information Systems

Massively Multiplayer Online Role-Playing Games (MMORPGs) have become increasingly popular and have communities comprising millions of subscribers. With their increasing popularity, researchers are realizing that video games can be a means to fully observe an entire isolated universe. In this study, we examine and report our findings on the effects of mentoring activities on player performance in Ever Quest II, a popular MMORPG developed by Sony Online Entertainment.

Parallel Learning To Rank For Information Retrieval, Shuaiqiang Wang, Byron J. Gao, Ke Wang, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Learning to rank represents a category of effective ranking methods for information retrieval. While the primary concern of existing research has been accuracy, learning efficiency is becoming an important issue due to the unprecedented availability of large-scale training data and the need for continuous update of ranking functions. In this paper, we investigate parallel learning to rank, targeting simultaneous improvement in accuracy and efficiency.

Unsupervised Information Extraction With Distributional Prior Knowledge, Cane Wing-Ki Leung, Jing Jiang, Kian Ming A. Chai, Hai Leong Chieu, Loo-Nin Teow

Research Collection School Of Computing and Information Systems

We address the task of automatic discovery of information extraction template from a given text collection. Our approach clusters candidate slot fillers to identify meaningful template slots. We propose a generative model that incorporates distributional prior knowledge to help distribute candidates in a document into appropriate slots. Empirical results suggest that the proposed prior can bring substantial improvements to our task as compared to a K-means baseline and a Gaussian mixture model baseline. Specifically, the proposed prior has shown to be effective when coupled with discriminative features of the candidates.

Generating Aspect-Oriented Multi-Document Summarization With Event-Aspect Model, Peng Li, Yinglin Wang, Wei Gao, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper, we propose a novel approach to automatic generation of aspect-oriented summaries from multiple documents. We first develop an event-aspect LDA model to cluster sentences into aspects. We then use extended LexRank algorithm to rank the sentences in each cluster. We use Integer Linear Programming for sentence selection. Key features of our method include automatic grouping of semantically related sentences and sentence ranking based on extension of random walk model. Also, we implement a new sentence compression algorithm which use dependency tree instead of parser tree. We compare our method with four baseline methods. Quantitative evaluation based on …