Physical Sciences and Mathematics Commons^™

A Survey Of Schema Matching Research, Roger Blake

College of Management Working Papers and Reports

Schema matching is the process of developing semantic matches between two or more schemas. The purpose of schema matching is generally either to merge two or more databases, or to enable queries on multiple, heterogeneous databases to be formulated on a single schema (Doan and Halevy 2005). This paper develops a taxonomy of schema matching approaches, classifying them as being based on a combination schema matching technique and the type of data used by those techniques. Schema matching techniques are categorized as being based on rules, learning, or ontology, and the type of data used is categorized as being based …

Overview Of The Imageclef 2007 Object Retrieval Task, Thomas Deselaers, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

We describe the object retrieval task of ImageCLEF 2007, give an overview of the methods of the participating groups, and present and discuss the results. The task was based on the widely used PASCAL object recognition data to train object recognition methods and on the IAPR TC-12 benchmark dataset from which images of objects of the ten different classes bicycles, buses, cars, motorbikes, cats, cows, dogs, horses, sheep, and persons had to be retrieved. Seven international groups participated using a wide variety of methods. The results of the evaluation show that the task was very challenging and that different methods …

Evolutionary Combinatorial Optimization For Recursive Supervised Learning With Clustering, Kiruthika Ramanathan, Sheng Uei Guan

Research Collection School Of Computing and Information Systems

The idea of using a team of weak learners to learn a dataset is a successful one in literature. In this paper, we explore a recursive incremental approach to ensemble learning. In this paper, patterns are clustered according to the output space of the problem, i.e., natural clusters are formed based on patterns belonging to each class. A combinatorial optimization problem is therefore formed, which is solved using evolutionary algorithms. The evolutionary algorithms identify the "easy" and the "difficult" clusters in the system. The removal of the easy patterns then gives way to the focused learning of the more complicated …

Who’S Creating?, M. Thulasidas

Research Collection School Of Computing and Information Systems

We don’t read to retain information or knowledge any more. We search, scan, locate keywords, browse and bookmark. The Internet is doing to our reading habits what the calculator did to our arithmetic abilities. Knowledge is not cheap, although our easy access to it through the Internet may indicate otherwise. When we all become users of information, our knowledge will stop at its current level because nobody will be creating it any more.

Cross-Language And Cross-Media Image Retrieval: An Empirical Study At Imageclef2007, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

This paper summarizes our empirical study of cross-language and cross-media image retrieval at the CLEF image retrieval track (ImageCLEF2007). In this year, we participated in the ImageCLEF photo retrieval task, in which the goal of the retrieval task is to search natural photos by some query with both textual and visual information. In this paper, we study the empirical evaluations of our solutions for the image retrieval tasks in three aspects. First of all, we study the application of language models and smoothing strategies for text-based image retrieval, particularly addressing the short text query issue. Secondly, we study the cross-media …

Column Heterogeneity As A Measure Of Data Quality, Bing Tian Dai, Nick Koudas, Beng Chin Ooi, Divesh Srivastava, Suresh Venkatasubramanian

Research Collection School Of Computing and Information Systems

Data quality is a serious concern in every data management application, and a variety of quality measures have been proposed, including accuracy, freshness and completeness, to capture the common sources of data quality degradation. We identify and focus attention on a novel measure, column heterogeneity, that seeks to quantify the data quality problems that can arise when merging data from different sources. We identify desiderata that a column heterogeneity measure should intuitively satisfy, and discuss a promising direction of research to quantify database column heterogeneity based on using a novel combination of cluster entropy and soft clustering. Finally, we present …

Ntu: Solution For The Object Retrieval Task Of The Imageclef2007, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Object retrieval is an interdisciplinary research problem between object recognition and content-based image retrieval (CBIR). It is commonly expected that object retrieval can be solved more effectively with the joint maximization of CBIR and object recognition techniques. We study a typical CBIR solution with application to the object retrieval tasks [26,27]. We expect that the empirical study in this work will serve as a baseline for future research when using CBIR techniques for object recognition.

Mobile Information Communication Technology For Crisis Management : Understanding User Behavior, Response And Training, Elizabeth Avery Gomez

Dissertations

SMS text-messaging is an interoperable communication vehicle known to be dependable for mass media alert notifications in crisis management. SMS text-messaging also offers potential as one viable two-way communication alternative for field responders in crisis response. Both continuously changing mobile information communication technologies and the importance of precise information exchange constitute a need for communication protocol training and practice. This study introduces a technology-mediated training technique based on speech act and communicative action theories. These theories are used to inform the design of a baseline measure for task performance improvement and to suggest a model to predict communication readiness. Because …

Designing Multimodal Interaction For The Visually Impaired, Xiaoyu Chen

Dissertations

Although multimodal computer input is believed to have advantages over unimodal input, little has been done to understand how to design a multimodal input mechanism to facilitate visually impaired users' information access.

This research investigates sighted and visually impaired users' multimodal interaction choices when given an interaction grammar that supports speech and touch input modalities. It investigates whether task type, working memory load, or prevalence of errors in a given modality impact a user's choice. Theories in human memory and attention are used to explain the users' speech and touch input coordination.

Among the abundant findings from this research, the …

Sensor Data Management, Cory Andrew Henson

Kno.e.sis Publications

No abstract provided.

Research On Multi-Agent-Based Shipping Information System, Kai Wang

World Maritime University Dissertations

No abstract provided.

The Influence Of Online Word Of Mouth On Product Sales In Retail E-Commerce: An Empirical Investigation, Alanah Davis, Deepak Khazanchi

Information Systems and Quantitative Analysis Faculty Proceedings & Presentations

The ability to exchange opinions and experiences online is known as online word of mouth (WOM). Due to the high acceptance of consumers and their apparent reliance on online WOM it is important for organizations to understand how it works and what kind of impact it has on product sales. Using the well-established notions of volume and valence to describe online WOM, we empirically evaluate the hypothesized relationship between online WOM in a retail e-commerce site and actual product sales. Our analysis of the data shows that there is a significant change in the number of products sold following the …

An Information Technology Therapy Approach To Micro-Enterprise Adoption Of Icts, Peter Wolcott, Sajda Qureshi, Mehruz Kamal

Information Systems and Quantitative Analysis Faculty Proceedings & Presentations

The advent of Information and Communication Technologies (ICTs) has opened up new opportunities for micro-enterprises to improve their businesses. However the challenges to using ICTs are impeding these businesses from growing into the drivers for development that they can be. This suggests that a potentially important driver of development needs to be supported. This paper investigates the adoption of ICTs in eight micro-enterprises in an underserved community of Omaha, Nebraska. Following an action research study, this research provides insight into the key challenges and opportunities facing micro-enterprises in their use of ICTs to create value for their businesses. Its contribution …

Csi Revisited: The Science Of Forensic Dna Analysis, Michael L. Raymer

Kno.e.sis Publications

No abstract provided.

Relationship Web: Spinning The Semantic Web From Trailblazing To Complex Hypothesis Evaluation, Amit P. Sheth

Kno.e.sis Publications

No abstract provided.

Trailblazing, Complex Hypothesis Evaluation, Abductive Reasoning And Semantic Web - Exploring Possible Synergy, Amit P. Sheth

Kno.e.sis Publications

No abstract provided.

Space Adaptation: Privacy-Preserving Multiparty Collaborative Mining With Geometric Perturbation, Keke Chen, Ling Liu

Kno.e.sis Publications

The service-oriented infrastructure has become popular for collaboratively mining data distributed over organizations [3], where the participants are the data providers who submit their perturbed datasets to the designated data mining service provider (the data miner) for mining commonly interested models.

Mapping Better Business Strategies With Gis, Tin Seong Kam

Research Collection School Of Computing and Information Systems

The value of location as a business measure is fast becoming an important consideration for organisations. GIS (Geographical Information Systems), with its capability to manage, display, analyse business information spatially, is emerging as a powerful location intelligence tool. In the US, Starbucks, Blockbuster, Hyundai, and thousands of other businesses use census data and GIS software to help them understand what types of people buy their products and services, and how to better market to these consumers. For example, McDonald’s in Japan uses a GIS system to overlay demographic information on maps to help identify promising new store sites. Singapore Management …

Cost-Time Sensitive Decision Tree With Missing Values, Shichao Zhang, Xiaofeng Zhu, Jilian Zhang, Chengqi Zhang

Research Collection School Of Computing and Information Systems

Cost-sensitive decision tree learning is very important and popular in machine learning and data mining community. There are many literatures focusing on misclassification cost and test cost at present. In real world application, however, the issue of time-sensitive should be considered in cost-sensitive learning. In this paper, we regard the cost of time-sensitive in cost-sensitive learning as waiting cost (referred to WC), a novelty splitting criterion is proposed for constructing cost-time sensitive (denoted as CTS) decision tree for maximal decrease the intangible cost. And then, a hybrid test strategy that combines the sequential test with the batch test strategies is …

Are You Too Smart For Your Own Good?, M. Thulasidas

Research Collection School Of Computing and Information Systems

Knowledge can be a bad thing, if others are taking credit for it. TECHNICAL knowledge is not always a good thing for you in the modern workplace.

Semantic Web: Promising Technologies And Current Applications In Health Care & Life Sciences, Amit P. Sheth

Kno.e.sis Publications

No abstract provided.

Quo Vadis, Cs? – On The (Non)-Impact Of Conceptual Structures On The Semantic Web, Sebastian Rudolph, Markus Krotzsch, Pascal Hitzler

Computer Science and Engineering Faculty Publications

Conceptual Structures is a field of research which shares abstract concepts and interests with recent work on knowledge representation for the Semantic Web. However, while the latter is an area of research and development which is rapidly expanding in recent years, the former fails to participate in these developments on a large scale. In this paper, we attempt to stimulate the Conceptual Structures community to catch the Semantic Web train.

A Semantic Framework For Identifying Events In A Service Oriented Architecture, Karthik Gomadam, Ajith Harshana Ranabahu, Lakshmish Ramaswamy, Amit P. Sheth, Kunal Verma

Kno.e.sis Publications

We propose a semantic framework for automatically identifying events as a step towards developing an adaptive middleware for Service Oriented Architecture (SOA). Current related research focuses on adapting to events that violate certain non-functional objectives of the service requestor. Given the large of number of events that can happen during the execution of a service, identifying events that can impact the non-functional objectives of a service request is a key challenge. To address this problem we propose an approach that allows service requestors to create semantically rich service requirement descriptions, called semantic templates. We propose a formal model for expressing …

Semantics To Energize The Full Services Spectrum: Ontological Approach To Better Exploit Services At Technical And Business Levels, Amit P. Sheth

Kno.e.sis Publications

Services are pervasive in today’s economic landscape, and services- based architectures are being rapidly adopted as IT infrastructure. The need to take a broader perspective of services to include people and organizational descriptions as opposed to technical interface descriptions has already been recognized as part of an overall vision of services science [46, 100]. This article describes the Semantic Services Science (3S) model, which seeks to demonstrate the essential benefits of semantics in view of the broader vision of services science by using service descriptions that capture technical, human, organizational, and business value aspects. We assert that ontology-based semantic modeling …

Efficient Computation Of Iceberg Cubes By Bounding Aggregate Functions, Xiuzhen Zhang, Pauline Lienhua Chou, Guozhu Dong

Kno.e.sis Publications

The iceberg cubing problem is to compute the multidimensional group-by partitions that satisfy given aggregation constraints. Pruning unproductive computation for iceberg cubing when nonantimonotone constraints are present is a great challenge because the aggregate functions do not increase or decrease monotonically along the subset relationship between partitions. In this paper, we propose a novel bound prune cubing (BP-Cubing) approach for iceberg cubing with nonantimonotone aggregation constraints. Given a cube over n dimensions, an aggregate for any group-by partition can be computed from aggregates for the most specific n--dimensional partitions (MSPs). The largest and smallest aggregate values computed this way become …

An Empirical Study On Large-Scale Content-Based Image Retrieval, Yuk Man Wong, Steven C. H. Hoi, Michael R. Lyu

Research Collection School Of Computing and Information Systems

One key challenge in content-based image retrieval (CBIR) is to develop a fast solution for indexing high-dimensional image contents, which is crucial to building large-scale CBIR systems. In this paper, we propose a scalable content-based image retrieval scheme using locality-sensitive hashing (LSH), and conduct extensive evaluations on a large image testbed of a half million images. To the best of our knowledge, there is less comprehensive study on large-scale CBIR evaluation with a half million images. Our empirical results show that our proposed solution is able to scale for hundreds of thousands of images, which is promising for building Web-scale …

Discovering And Exploiting Causal Dependencies For Robust Mobile Context-Aware Recommenders, Ghim-Eng Yap, Ah-Hwee Tan, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Acquisition of context poses unique challenges to mobile context-aware recommender systems. The limited resources in these systems make minimizing their context acquisition a practical need, and the uncertainty in the mobile environment makes missing and erroneous context inputs a major concern. In this paper, we propose an approach based on Bayesian networks (BNs) for building recommender systems that minimize context acquisition. Our learning approach iteratively trims the BN-based context model until it contains only the minimal set of context parameters that are important to a user. In addition, we show that a two-tiered context model can effectively capture the causal …

Near-Duplicate Keyframe Retrieval With Visual Keywords And Semantic Context, Xiao Wu, Wan-Lei Zhao, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Near-duplicate keyframes (NDK) play a unique role in large-scale video search, news topic detection and tracking. In this paper, we propose a novel NDK retrieval approach by exploring both visual and textual cues from the visual vocabulary and semantic context respectively. The vocabulary, which provides entries for visual keywords, is formed by the clustering of local keypoints. The semantic context is inferred from the speech transcript surrounding a keyframe. We experiment the usefulness of visual keywords and semantic context, separately and jointly, using cosine similarity and language models. By linearly fusing both modalities, performance improvement is reported compared with the …

Appraisal - Who Needs It?, M. Thulasidas

Research Collection School Of Computing and Information Systems

WE GO through this ordeal every year when our boss- es appraise our performance. Our career progression, bonus and salary depend on it. So, we spend sleepless nights agonising over it.

Learning Causal Models For Noisy Biological Data Mining: An Application To Ovarian Cancer Detection, Ghim-Eng Yap, Ah-Hwee Tan, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Undetected errors in the expression measurements from highthroughput DNA microarrays and protein spectroscopy could seriously affect the diagnostic reliability in disease detection. In addition to a high resilience against such errors, diagnostic models need to be more comprehensible so that a deeper understanding of the causal interactions among biological entities like genes and proteins may be possible. In this paper, we introduce a robust knowledge discovery approach that addresses these challenges. First, the causal interactions among the genes and proteins in the noisy expression data are discovered automatically through Bayesian network learning. Then, the diagnosis of a disease based on …