Digital Commons Network^™

Prosody-Based Query-By-Example Spoken Utterance Retrieval, Steven D. Werner, Nigel G. Ward

COURI Symposium Abstracts, Summer 2012

Current spoken dialogue retrieval systems are almost entirely lexically based, using automatic transcription by imperfect speech recognition technology. Once audio is reduced to text, little more than existing text search methods are used to retrieve results. However, spoken dialogue contains rich latent prosodic information about dialogue activities - such as agreeing, arguing, deciding, planning, storytelling, showing surprise - and this extra information can often be relevant to the searchers aims. Searching for similar speech acts rather then similar words enables similar contextual results, returning points where the speaker had the same sentiment during a topic. Previous research yielded 76 dimensions …

What Kind Of #Communication Is Twitter? A Psycholinguistic Perspective On Communication In Twitter For The Purpose Of Emergency Coordination, Hemant Purohit, Andrew Hampton, Valerie L. Shalin, Amit P. Sheth, John Flach

Kno.e.sis Publications

The present research aims to detect coordinated citizen response within social media traffic to assist emergency response. We use domain-independent linguistic properties as the first step in narrowing the candidate set of messages for domain-dependent and computationally intensive analysis.

Evaluation And Assessment Of Recommenders Using Monte Carlo Simulation, Renato Costa, Luiz Fernando Capretz

Electrical and Computer Engineering Publications

There have been various definitions, representations and derivations of trust in the context of recommender systems. This article presents a recommender predictive model based on collaborative filtering techniques that incorporate a fuzzy-driven quantifier, which includes two upmost relevant social phenomena parameters to address the vagueness inherent in the assessment of trust in social networks relationships. An experimental evaluation procedure utilizing a case study is conducted to analyze the overall predictive accuracy. These results show that the proposed methodology improves the performance of classical recommender approaches. Possible extensions are then outlined.

Question Answering System Using Open Source Software, Gaurav Gangwal

Master's Projects

To get the answers of a question there are lots of search engine availbale. But the problem with the search engine is that instead of giving a straight forrward answer they usually gives the links/URL to the webpages which might have the answers. Instead of providing links Question Answering System will provide the straighforward answer to user's question. Tasks intended by the project : • Takes question as an input from the user. • Analyses the sentiment behinds the question. • Lookover the information availbale in the knowledge base related to question. • Compute the answer of the question from …

Information-Theoretic Multi-View Domain Adaptation, Pei Yang, Wei Gao, Qi Tan, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

We use multiple views for cross-domain document classification. The main idea is to strengthen the views’ consistency for target data with source training data by identifying the correlations of domain-specific features from different domains. We present an Information-theoretic Multi-view Adaptation Model (IMAM) based on a multi-way clustering scheme, where word and link clusters can draw together seemingly unrelated domain-specific features from both sides and iteratively boost the consistency between document clusterings based on word and link views. Experiments show that IMAM significantly outperforms state-of-the-art baselines.

Joint Learning For Coreference Resolution With Markov Logic, Yang Song, Jing Jiang, Xin Zhao, Sujian Li, Houfeng Wang

Research Collection School Of Computing and Information Systems

Pairwise coreference resolution models must merge pairwise coreference decisions to generate final outputs. Traditional merging methods adopt different strategies such as the best first method and enforcing the transitivity constraint, but most of these methods are used independently of the pairwise learning methods as an isolated inference procedure at the end. We propose a joint learning model which combines pairwise classification and mention clustering with Markov logic. Experimental results show that our joint learning system outperforms independent learning systems. Our system gives a better performance than all the learning-based systems from the CoNLL-2011 shared task on the same dataset. Compared …

Identifying Event-Related Bursts Via Social Media Activities, Xin Zhao, Baihan Shu, Jing Jiang, Yang Song, Hongfei Yan, Xiaoming Li

Research Collection School Of Computing and Information Systems

Activities on social media increase at a dramatic rate. When an external event happens, there is a surge in the degree of activities related to the event. These activities may be temporally correlated with one another, but they may also capture different aspects of an event and therefore exhibit different bursty patterns. In this paper, we propose to identify event-related bursts via social media activities. We study how to correlate multiple types of activities to derive a global bursty pattern. To model smoothness of one state sequence, we propose a novel function which can capture the state context. The experiments …

Finding Bursty Topics From Microblogs, Qiming Diao, Jing Jiang, Feida Zhu, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Microblogs such as Twitter reflect the general public’s reactions to major events. Bursty topics from microblogs reveal what events have attracted the most online attention. Although bursty event detection from text streams has been studied before, previous work may not be suitable for microblogs because compared with other text streams such as news articles and scientific publications, microblog posts are particularly diverse and noisy. To find topics that have bursty patterns on microblogs, we propose a topic model that simultaneousy captures two observations: (1) posts published around the same time are more likely to have the same topic, and (2) …

Identifying And Attributing Similar Traces With Greatest Common Factor Analysis, Fred Cohen

Journal of Digital Forensics, Security and Law

This paper presents an algorithm for comparing large numbers of traces to each other and identifying and presenting groups of traces with similar features. It is applied to forensic analysis in which groups of similar traces are automatically identified and presented so that attribution and other related claims may be asserted, and independently confirmed or refuted. The approach of this paper is to identify an approximate algorithm that will find a large subset of greatest common factor similar groups of arbitrary factors in far less time and space than an exact algorithm using examiner-provided selection criteria for factor definition.

The Effects Of Diagrams And Relational Complexity On User Performance In Conditional Probability Problems In A Non-Learning Context, Vincent J. Kellen

College of Computing and Digital Media Dissertations

Many disciplines in everyday life depend on improved performance in conditional probability problems. Most adults struggle with conditional probability problems and several prior studies have shown participant accuracy is less than 50%. This study examined user performance when aided with computer-generated Venn and Euler type diagrams in a non-learning context. Despite the prevalence of research into diagrams and extensive research into conditional probability problem solving, this study is one of the only studies to apply theories of working memory to predict user performance in conditional probability problems with diagrams. Following relational complexity theory, this study manipulated problem complexity in computer …

Identifying Linux Bug Fixing Patches, Yuan Tian, Julia Lawall, David Lo

Research Collection School Of Computing and Information Systems

In the evolution of an operating system there is a continuing tension between the need to develop and test new features, and the need to provide a stable and secure execution environment to users. A compromise, adopted by the developers of the Linux kernel, is to release new versions, including bug fixes and new features, frequently, while maintaining some older “longterm” versions. This strategy raises the problem of how to identify bug fixing patches that are submitted to the current version but should be applied to the longterm versions as well. The current approach is to rely on the individual …

The Intersection Between Science And Computer Science Is Almost Empty, Dick Hamlet

Systems Science Friday Noon Seminar Series

Traditionally, a science such as physics overlaps with mathematics and engineering in a way that has been astonishingly productive. The math provides precise expression for the science, which in turn supplies the engineering with the information it needs to exploit physical phenomena. Computer science naturally wishes to put itself in the center of the traditional picture as a science. Unfortunately, it won't wash. The `science' of programming is pure and simple mathematics, not science. The distinction is more than linguistic, since science and mathematics have quite distinct goals and methods. By making the wrong choice, computer science research has been …

Structural Analysis And Auditing Of Snomed Hierarchies Using Abstraction Networks, Yue Wang

Dissertations

SNOMED is one of the leading healthcare terminologies being used worldwide. Due to its sheer volume and continuing expansion, it is inevitable that errors will make their way into SNOMED. Thus, quality assurance is an important part of its maintenance cycle.

A structural approach is presented in this dissertation, aiming at developing automated techniques that can aid auditors in the discovery of terminology errors more effectively and efficiently. Large SNOMED hierarchies are partitioned, based primarily on their relationships patterns, into concept groups of more manageable sizes. Three related abstraction networks with respect to a SNOMED hierarchy, namely the area taxonomy …

The Xbox 360 And Steganography: How Criminals And Terrorists Could Be "Going Dark", Ashley Podhradsky, Rob D’Ovidio, Cindy Casey

Annual ADFSL Conference on Digital Forensics, Security and Law

Video game consoles have evolved from single-player embedded systems with rudimentary processing and graphics capabilities to multipurpose devices that provide users with parallel functionality to contemporary desktop and laptop computers. Besides offering video games with rich graphics and multiuser network play, today's gaming consoles give users the ability to communicate via email, video and text chat; transfer pictures, videos, and file;, and surf the World-Wide-Web. These communication capabilities have, unfortunately, been exploited by people to plan and commit a variety of criminal activities. In an attempt to cover the digital tracks of these unlawful undertakings, anti-forensic techniques, such as steganography, …

Update On The State Of The Science Of Digital Evidence Examination, Fred Cohen

Annual ADFSL Conference on Digital Forensics, Security and Law

This paper updates previous work on the level of consensus in foundational elements of digital evidence examination. Significant consensus is found present only after definitions are made explicit, suggesting that, while there is a scientific agreement around some of the basic notions identified, the use of a common language is lacking.

Keywords: Digital forensics examination, terminology, scientific methodology, testability, validation, classification, scientific consensus

Issues In Designing A Corpus Of Spoken Irish, Elaine Ui Dhonnchadha, Alessio Frenda, Brian Vaughan

Conference papers

This paper describes the stages involved in implementing a corpus of spoken Irish. This pilot project (consisting of approximately 140K of transcribed data) implements parts of the design of a larger corpus of spoken Irish which it is hoped will contain approximately 2 million words when complete. It hoped that such a corpus will provide material for linguistic research, lexicography, the teaching of Irish and for development of language technology for the Irish language.

Speech & Multimodal Resources: The Herme Database Of Spontaneous Multimodal Human-Robot Dialogues, Jing Guang Hang, Emer Gilmartin, Celine De Looze, Brian Vaughan, Nick Campbell

Conference papers

This paper presents methodologies and tools for language resource (LR) construction. It describes a database of interactive speech collected over a three-month period at the Science Gallery in Dublin, where visitors could take part in a conversation with a robot. The system collected samples of informal, chatty dialogue – normally difficult to capture under laboratory conditions for human-human dialogue, and particularly so for human-machine interaction. The conversations were based on a script followed by the robot consisting largely of social chat with some task-based elements. The interactions were audio-visually recorded using several cameras together with microphones. As part of the …

Trust Networks, Krishnaprasad Thirunarayan, Pramod Anantharam, Cory Andrew Henson, Amit P. Sheth

Kno.e.sis Publications

Trust relationships occur naturally in many diverse contexts such as collaborative systems, e-commerce, interpersonal interactions, social networks, semantic sensor web, etc. As collaborating agents providing content and services become increasingly removed from the agents that consume them, the issue of robust trust inference and update become critical. There is a need to find online substitutes for traditional (direct or face-to-face) cues to derive measures of trust, and create efficient and secure system for managing trust, to support decision-making. Unfortunately, there is neither a universal notion of trust that is applicable to all domains nor a clear explication of its semantics …

Improving The Effectiveness Of Machine-Assisted Annotation, Paul L. Felt

Theses and Dissertations

Annotated textual corpora are an essential language resource, facilitating manual search and discovery as well as supporting supervised Natural Language Processing (NLP) techniques designed to accomplishing a variety of useful tasks. However, manual annotation of large textual corpora can be cost-prohibitive, especially for rare and under-resourced languages. For this reason, developers of annotated corpora often attempt to reduce annotation cost by offering annotators various forms of machine assistance intended to increase annotator speed and accuracy. This thesis contributes to the field of annotated corpus development by providing tools and methodologies for empirically evaluating the effectiveness of machine assistance techniques. This …

Real-Time Face Detection And Recognition, Parker Hill, Brendan Morris

College of Engineering: Graduate Celebration Programs

The face has become a popular biometric for identification due to the wide range of features and difficulty in manipulation of the metric. In order to work towards a robust facial recognition system, this work contains a foundation for using the face as a recognition metric. First, faces are detected from still images using a Viola-Jones object detection algorithm. Then, Eigenfaces is applied to the detected faces. The system was tested on face databases as well as real-time feed from a web camera.

Designing And Implementing A Platform For Collecting Multi-Modal Data Of Human-Robot Interaction, Brian Vaughan, Jing Guang Han, Emer Kilmartin, Nick Campbell

Articles

This paper details a method of collecting video and audio recordings of people inter- acting with a simple robot interlocutor. The interaction is recorded via a number of cameras and microphones mounted on and around the robot. The system utilised a number of technologies to engage with interlocutors including OpenCV, Python, and Max MSP. Interactions over a three month period were collected at The Science Gallery in Trinity College Dublin. Visitors to the gallery freely engaged with the robot, with interactions on their behalf being spontaneous and non-scripted. The robot dialogue was a set pattern of utterances to engage interlocutors …

Outage Detection Via Real-Time Social Stream Analysis: Leveraging The Power Of Online Complaints, Eriq Augustine, Caitlin Cushing, Alex Dekhtyar, Kevin Mcentee, Kimberly Paterson, Matt Tognetti

Computer Science and Software Engineering

Over the past couple of years, Netflix has significantly expanded its online streaming offerings, which now encompass multiple delivery platforms and thousands of titles available for instant view. This paper documents the design and development of an outage detection system for the online services provided by Netflix. Unlike other internal quality control measures used at Netflix, this system uses only publicly available information: the tweets, or Twitter posts, that mention the word “Netflix,” and has been developed and deployed externally, on servers independent of the Netflix infrastructure. This paper discussed the system and provides assessment of the accuracy of its …

Mobile Technology Update To Delone And Mclean Model Of Information Success, Jason Ryberg

Regis University Student Publications (comprehensive collection)

Senior managers are challenged to measure the success of their IT systems when justifying technology investments needed to meet the organization"â„¢s mission. Due to increasing implementation of mobile technology, enterprise adoption of smartphones is no exception. Traditionally, the DeLone and McLean Information Systems (IS) Success Model has been proven as a valid framework for measuring IS success. However, it has not been updated to address the success variables related to mobile technology. Many studies on mobile technology have reviewed mobile success, but none have attempted theoretical assimilation. This thesis attempts to correct this situation by examining the DeLone and McLean …

Adaptive Radial Basis Function Neural Networks-Based Real Time Harmonics Estimation And Pwm Control For Active Power Filters, Eyad Kh Almaita

Dissertations

With the proliferation of nonlinear loads in the power system, harmonic pollution becomes a serious problem that affects the power quality in both transmission and distribution systems. Active power filters (APF) have been proven to be one of the most successful methods for mitigating harmonics problems. So far, different techniques have been used in harmonics extraction and control of APF to satisfy the fast response and the accuracy required by the APF. Neural networks techniques have been used successfully in different real-time and complex situations. This dissertation demonstrates four main tasks; (i) a novel adaptive radial basis function neural networks …

Blog Information Classification, Nishant Patel

Master's Projects

nformation Classification is the categorization of the huge amount of data in an efficient and useful way. In the current scenario data is growing exponentially due to the rise of internet rich applications. One such source of information is the blogs. Blogs are web logs maintained by their authors that contain information related to a certain topic and also contain authors view about that topic. Micro blogs, on the other hands, are variations of blogs that contain smaller data as compared to blogs. Nevertheless, it also contains rich information. In this project, Twitter, a micro blogging website has been targeted …

Knowledge Engineering In Search Engines, Yun-Chieh Lin

Master's Projects

With large amounts of information being exchanged on the Internet, search engines have become the most popular tools for helping users to search and filter this information. However, keyword-based search engines sometimes obtain information, which does not meet user’ needs. Some of them are even irrelevant to what the user queries. When the users get query results, they have to read and organize them by themselves. It is not easy for users to handle information when a search engine returns several million results. This project uses a granular computing approach to find knowledge structures of a search engine. The project …

Cloud Information Summarization With Mobile Interface, Hrishikesh Paranjape

Master's Projects

There is a large driver for making existing data accessible everywhere, not just for people who happen to be at connected computers. This project aims to design, develop, and test Information Summarization System with its mobile application, which will allow end user the quick mobile access to underlying data on the web. The mobile application allows users to search for information about topic of their interest. This application will make use of existing established search engines to summarize the information on requested topic. The computation will be done on the cloud and communication between client and server will be done …

Cross-Lingual Text Classification With Model Translation And Document Translation, Zhang Zhang

Master's Projects

Most enterprise search engines employ data mining classifiers to classify documents. Along with the economic globalization, many companies are starting to have overseas branches or divisions. Those branches are using local languages in documents and emails. When a classifier tries to categorize those documents in another language, the trained model in mono-lingual will not work. The most direct solution would be to translate those documents in other languages into one language by the machine translator. But this solution suffers from inaccuracy of the machine translation, and the over-head work is economically inefficient. Another approach is to translate the feature extracted …

Conflict Detection And Resolution For Product Line Design In A Collaborative Decision Making Environment, Xiaoqing Frank Liu, Eric Christopher Barnes, Juha Erik Savolainen

Computer Science Faculty Research & Creative Works

Ensuring that the non-functional requirements (NFRs), of a system are satisfied is an essential task in software development. However, this task is complicated by the fact that many NFRs conflict with each other from multiple perspectives. It is essential to resolve conflicts collectively in a collaborative decision-making process since stakeholders often disagree on how conflicts should be resolved. in this paper, we describe a method for dividing high-level NFR conflicts within a product line into more manageable sub-problems. Stakeholders make use of an argumentation based collaborative decision support system to determine which design alternatives provide the best trade-offs between NFRs. …

Entropy And The Complexity Of Graphs Revisited, Abbe Mowshowitz, Matthias Dehmer

Publications and Research

This paper presents a taxonomy and overview of approaches to the measurement of graph and network complexity. The taxonomy distinguishes between deterministic (e.g., Kolmogorov complexity) and probabilistic approaches with a view to placing entropy-based probabilistic measurement in context. Entropy-based measurement is the main focus of the paper. Relationships between the different entropy functions used to measure complexity are examined; and intrinsic (e.g., classical measures) and extrinsic (e.g., Körner entropy) variants of entropy-based models are discussed in some detail.