Digital Commons Network^™

Classifying Idiomatic And Literal Expressions Using Topic Models And Intensity Of Emotions, Jing Peng, Anna Feldman, Ekaterina Vylomova

Department of Computer Science Faculty Scholarship and Creative Works

We describe an algorithm for automatic classification of idiomatic and literal expressions. Our starting point is that words in a given text segment, such as a paragraph, that are highranking representatives of a common topic of discussion are less likely to be a part of an idiomatic expression. Our additional hypothesis is that contexts in which idioms occur, typically, are more affective and therefore, we incorporate a simple analysis of the intensity of the emotions expressed by the contexts. We investigate the bag of words topic representation of one to three paragraphs containing an expression that should be classified as …

An Empirical Study Of The Impact Of Idioms On Phrase Based Statistical Machine Translation Of English To Brazilian-Portuguese, Giancarlo Salton, Robert J. Ross, John D. Kelleher

Conference papers

This paper describes an experiment to evaluate the impact of idioms on Statis- tical Machine Translation (SMT) process using the language pair English/Brazilian- Portuguese. Our results show that on sen- tences containing idioms a standard SMT system achieves about half the BLEU score of the same system when applied to sentences that do not contain idioms. We also provide a short error analysis and out- line our planned work to overcome this limitation.

Optimal Fuzzy Load Frequency Controller With Simultaneous Auto-Tuned Membership Functions And Fuzzy Control Rules, Abas Ali Zamani, Ehsan Bijami, Farid Sheikholeslam, Bahram Jafrasteh

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, an auto-tuned fuzzy load frequency controller (FLFC)-based artificial bee colony (ABC) algorithm is developed to quench the deviations in the frequency and tie-line power due to load disturbances in an interconnected power system. Optimal tuning of membership functions (MFs) and fuzzy control rules is very important to improve the design performance and achieve a satisfactory level of robustness for a particular operation. In this work, to reduce the fuzzy system design effort and take large parametric uncertainties into account, a new systematic and simultaneous tuning method is developed for designing MFs and fuzzy rules. For this, the …

An Information Security Control Assessment Methodology For Organizations, Angel Rafael Otero

CCAC Theses and Dissertations

In an era where use and dependence of information systems is significantly high, the threat of incidents related to information security that could jeopardize the information held by organizations is more and more serious. Alarming facts within the literature point to inadequacies in information security practices, particularly the evaluation of information security controls in organizations. Research efforts have resulted in various methodologies developed to deal with the information security controls assessment problem. A closer look at these traditional methodologies highlights various weaknesses that can prevent an effective information security controls assessment in organizations. This dissertation develops a methodology that addresses …

Time Will Tell : Temporal Reasoning In Clinical Narratives And Beyond, Weiyi Sun

Legacy Theses & Dissertations (2009 - 2024)

Temporal reasoning in natural language refers to the extraction and understanding of time-related information conveyed in free text. A clinical narrative temporal reasoning component can enable a spectrum of medical natural language processing (NLP) applications that directly improve patient care documentation efficiency, accessibility and accountability. This dissertation contributes in three subtasks under temporal reasoning: temporal annotation, temporal expression extraction and temporal relation inferences. The temporal annotation work described in the dissertation produced one of the first publicly available clinical narratives. We published one of the first sets of temporal

A New Approach In The Evaluation Of Hospital Information Systems, Güney Gürsel, Neşe Zayi̇m, Kemal Hakan Gülkesen, Ali̇ Ari̇foğlu, Osman Saka

Turkish Journal of Electrical Engineering and Computer Sciences

Hospital information system (HIS) evaluation frameworks have largely been discussed in the literature. However, existing frameworks lack one important aspect: to what extent user expectations of HISs are met. In this study, user expectation data are collected by means of the 'expectation questionnaire'. The internal consistencies of the answers to the questionnaire are measured by Cronbach's alpha coefficient. Fuzzy logic methodologies are used to evaluate the expectation variables in the proposed evaluation framework. The evaluation variables are not represented in the results equally; they are reflected by the weights assigned by the users. Our proposed framework provides the overall degree …

Expert Doctor Verdis: Integrated Medical Expert System, Aytürk Keleş

Turkish Journal of Electrical Engineering and Computer Sciences

Innovative medical technologies are developing day by day, as there is an important need for integrated medical expert systems (ESs) that will help to effectively manage and control diagnosis and treatment processes. These systems, with new approaches, have improved the experiences and capabilities of physicians to make the diagnosis of diseases. In this work, an integrated medical ES called Expert Doctor Verdis (Ex-Dr Verdis) is developed, which combines an advanced medical information system containing various medical services supported by information technologies, with ES capabilities in a single system. This system is also one kind of decision support system. Implementation of …

The Rna Newton Polytope And Learnability Of Energy Parameters, Elmirasadat Forouzmand

Wayne State University Theses

Computational RNA secondary structure prediction has been a topic of much research interest for several decades now. Despite all the progress made in the field, even the state-of-the-art algorithms do not provide satisfying results, and the accuracy of output is limited for all the existent tools. Very complex energy models, different parameter estimation methods, and recent machine learning approaches had not been the answer for this problem. We believe that the first step to achieve results with high quality is to use the energy model with the potential for predicting accurate output. Hence, it is necessary to have a systematic …

Functional Scaffolding For Musical Composition: A New Approach In Computer-Assisted Music Composition, Amy K. Hoover

Electronic Theses and Dissertations

While it is important for systems intended to enhance musical creativity to define and explore musical ideas conceived by individual users, many limit musical freedom by focusing on maintaining musical structure, thereby impeding the user's freedom to explore his or her individual style. This dissertation presents a comprehensive body of work that introduces a new musical representation that allows users to explore a space of musical rules that are created from their own melodies. This representation, called functional scaffolding for musical composition (FSMC), exploits a simple yet powerful property of multipart compositions: The pattern of notes and rhythms in different …

Idiographic Digital Profiling: Behavioral Analysis Based On Digital Forensics, Chad M. Steel

Journal of Digital Forensics, Security and Law

Idiographic digital profiling (IDP) is the application of behavioral analysis to the field of digital forensics. Previous work in this field takes a nomothetic approach to behavioral analysis by attempting to understand the aggregate behaviors of cybercriminals. This work is the first to take an idiographic approach by examining a particular subject's digital footprints for immediate use in an ongoing investigation. IDP provides a framework for investigators to analyze digital behavioral evidence for the purposes of case planning, subject identification, lead generation, obtaining and executing warrants, and prosecuting offenders.

Table Of Contents

Journal of Digital Forensics, Security and Law

No abstract provided.

How Well Does Multiple Ocr Error Correction Generalize?, William B. Lund, Eric K. Ringger, Daniel D. Walker

Faculty Publications

As the digitization of historical documents, such as newspapers, becomes more common, the need of the archive patron for accurate digital text from those documents increases. Building on our earlier work, the contributions of this paper are: 1. in demonstrating the applicability of novel methods for correcting optical character recognition (OCR) on disparate data sets, including a new synthetic training set, 2. enhancing the correction algorithm with novel features, and 3. assessing the data requirements of the correction learning method. First, we correct errors using conditional random fields (CRF) trained on synthetic training data sets in order to demonstrate the …

Design Requirements For Generating Deceptive Content To Protect Document Repositories, Ben Whitham

Australian Information Warfare and Security Conference

For nearly 30 years, fake digital documents have been used to identify external intruders and malicious insider threats. Unfortunately, while fake files hold potential to assist in data theft detection, there is little evidence of their application outside of niche organisations and academic institutions. The barrier to wider adoption appears to be the difficulty in constructing deceptive content. The current generation of solutions principally: (1) use unrealistic random data; (2) output heavily formatted or specialised content, that is difficult to apply to other environments; (3) require users to manually build the content, which is not scalable, or (4) employ an …

Transforming Web Tables To A Relational Database, David W. Embley, George Nagy, Sharad C. Seth

School of Computing: Conference and Workshop Papers

HTML tables represent a significant fraction of web data. The often complex headers of such tables are determined accurately using their indexing property. Isolated headers are factored to extract category hierarchies. Web tables are then transformed into a canonical form and imported into a relational database. The proposed processing allows for the formulation of arbitrary SQL queries over the collection of induced relational tables.

Fuzzy Logic Approach To Henry Factor For Distributed Feedback Laser Case, Abdullah Çavuşoğlu

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, a simple approach for intelligent modeling of the Henry factor (\alpha-alpha parameter, antiguiding factor, phase-amplitude coupling factor) or the so-called linewidth enhancement factor, which is an actual analysis and design parameter for semiconductor laser diodes and optical communication systems, is proposed based on the fuzzy logic (FL) phenomenon. The proposed FL-based model easily computes the Henry factor in terms of different wavelengths and injection current levels (i.e. the inputs of the model). The experimental data belong to a distributed feedback laser, obtained from amplified spontaneous emission spectra, which is among the techniques required for the characterization of …

A Proof-Theoretic Semantic Analysis Of Dynamic Epistemic Logic, Sabine Frittella, Giuseppe Greco, Alexander Kurz, Alessandra Palmigiano, Vlasta Sikimić

Engineering Faculty Articles and Research

The present paper provides an analysis of the existing proof systems for dynamic epistemic logic from the viewpoint of proof-theoretic semantics. Dynamic epistemic logic is one of the best known members of a family of logical systems which have been successfully applied to diverse scientific disciplines, but the proof theoretic treatment of which presents many difficulties. After an illustration of the proof-theoretic semantic principles most relevant to the treatment of logical connectives, we turn to illustrating the main features of display calculi, a proof-theoretic paradigm which has been successfully employed to give a proof-theoretic semantic account of modal and substructural …

Three Essays On Social/Political Structures And Icts Use, Seungeui Ryu

Open Access Theses & Dissertations

My research identifies how social structures affect the use of the Internet and/or a mobile chat application and how the Internet impacts the political structure of a nation. In my first essay of the 3-essay Dissertation, I am designing three models based on social structure theory that are used to study the Internet and a popular mobile chat application's use by managers in South Korea, with the help of a survey instrument. In my first essay, the contribution is on i) testing a model of manager's personal behavior on Information and Communication Technology (ICT) use at the individual level involving …

Multi-Dimensional Emotion Recognition From Geometry And Color Information, Geovany A. Ramirez

Open Access Theses & Dissertations

Emotions play a fundamental role in everyday interactions among humans. Humans are adept at expressing themselves and interpreting others through a multi-modal, subtle and complex process using non-verbal cues including speech prosody, facial expression, eye gaze, body gestures, head motion, posture, and skin color changes. However, recognizing the affective state of humans is a difficult task for computers.

Automatic emotion recognition has focused on analysis of the six discrete basic emotions: happiness, sadness, surprise, fear, anger and disgust. However, humans express more complex and subtle affective states such as confusion, shame, pleasure, anxiety or depression. Therefore, a different representation based …

“Time For Some Traffic Problems”: Enhancing E-Discovery And Big Data Processing Tools With Linguistic Methods For Deception Detection, Erin S. Crabb

Journal of Digital Forensics, Security and Law

Linguistic deception theory provides methods to discover potentially deceptive texts to make them accessible to clerical review. This paper proposes the integration of these linguistic methods with traditional e-discovery techniques to identify deceptive texts within a given author’s larger body of written work, such as their sent email box. First, a set of linguistic features associated with deception are identified and a prototype classifier is constructed to analyze texts and describe the features’ distributions, while avoiding topic-specific features to improve recall of relevant documents. The tool is then applied to a portion of the Enron Email Dataset to illustrate how …

Defeasible Reasoning And Argument-Based Systems In Medical Fields: An Informal Overview, Luca Longo, Pierpaolo Dondio

Conference papers

The first aim of this article is to provide readers informally with the basic notions of defeasible and non-monotonic reasoning, logics borrowed from artificial intelligence. It then describes argumentation theory, a paradigm for implementing defeasible reasoning in practice as well as the common multilayer schema upon which argument-based models are usually built. The second aim is to describe the selection of argumentbased applications in the medical and health-care sectors. Finally, the paper will conclude with a summary of the features, which make defeasible reasoning and argumentation theory attractive, that emerge from the applications under review. The target reader is a …

Crime Pattern Detection Using Online Social Media, Raja Ashok Bolla

Masters Theses

"In this research, we show online social networks can be used to study crime detection problems. Crime is defined as an act harmful not only to the individual involved, but also to the community as a whole. It is also a forbidden act that is punishable by law. Crimes are social nuisances that place heavy financial burdens on society. Here we look at use of data mining followed by sentiment analysis on online social networks, to help detect the crime patterns. Twitter is an online social networking and microblogging service that enables users to post brief text updates, also referred …

Computing Trust As A Form Of Presumptive Reasoning, Pierpaolo Dondio, Luca Longo

Conference papers

This study describes and evaluates a novel trust model for a range of collaborative applications. The model assumes that humans routinely chose to trust their peers by relying on few recurrent presumptions, which are domain independent and that form a recognisable trust expertise. We refer to these presumptions as trust schemes, the specialised version of Walton’s argumentation schemes. Experimental evidence is provided about trust schemes efficacy with a detailed experiment over an online community of 80.000 members. Results show how proposed trust schemes are more effective in trust computation when they are combined together and when their plausibility in the …

Evaluation Of A Substitution Method For Idiom Transformation In Statistical Machine Translation, Giancarlo Salton, Robert J. Ross, John D. Kelleher

Conference papers

We evaluate a substitution based technique for improving Statistical Machine Translation performance on idiomatic multiword expressions. The method operates by performing substitution on the original idiom with its literal meaning before translation, with a second substitution step replacing literal meanings with idioms following translation. We detail our approach, outline our implementation and provide an evaluation of the method for the language pair English/Brazilian-Portuguese. Our results show improvements in translation accuracy on sentences containing either morphosyntactically constrained or unconstrained idioms. We discuss the consequences of our results and outline potential extensions to this process.

Evolving Decision Trees For The Categorization Of Software, Jasenko Hosic

Masters Theses

"Current manual techniques of static reverse engineering are inefficient at providing semantic program understanding. An automated method to categorize applications was developed in order to quickly determine pertinent characteristics. Prior work in this area has had some success, but a major strength of the approach detailed in this thesis is that it produces heuristics that can be reused for quick analysis of new data. The method relies on a genetic programming algorithm to evolve decision trees which can be used to categorize software. The terminals, or leaf nodes, within the trees each contain values based on selected features from one …

Ratings Lead You To The Product, Reviews Help You Clinch It? The Dynamics And Impact Of Online Review Sentiments On Products Sales, Nan Hu, Noi Sian Koh, Srinivas K. Reddy

Research Collection Lee Kong Chian School Of Business

It is generally assumed that ratings are a numeric representation of text sentiments and their valences are consistent. This however may not always be true. Using a panel of data on over 4000 books from Amazon.com, we develop a multiple equation model to examine the inter-relationships between ratings, sentiments, and sales. We find that ratings do not have a significant direct impact on sales but have an indirect impact through sentiments. Sentiments, however, have a direct significant impact on sales. Our findings also indicate that the two most accessible types of reviews - most helpful and most recent - play …

Understanding Human Learning Using A Multiagent Based Unified Learning Model Simulation, Vlad T. Chiriacescu

School of Computing: Dissertations, Theses, and Student Research

Within cognitive science, computational modeling based on cognitive architectures has been an important approach to addressing questions of human cognition and learning. Modeling issues such as limited expressivity in representing knowledge and lack of appropriate selection of model structure represent a challenge for existing architectures. Furthermore, latest research shows that the concepts of long-term memory, motivation and working memory are critical cognitive aspects but a unifying cognitive paradigm integrating those concepts hasn’t been previously achieved.

Derived from a synthesis of neuroscience, cognitive science, psychology, and education, the Unified Learning Model (ULM) provides this integration by merging a statistical learning mechanism …

Fuzziness And Bayesian Analysis In Engineering, Matthias Stein, Michael Beer, Vladik Kreinovich

Departmental Technical Reports (CS)

An engineering analysis requires a realistic quantification of all input information. The amount and quality of the available information dictates the uncertainty model and its associated quantification concept. For inconsistent information, a distinction between probabilistic and non-probabilistic characteristics is beneficial. In this distinction, uncertainty refers to probabilistic characteristics and non-probabilistic characteristics are summarized as imprecision. When uncertainty and imprecision occur simultaneously, the uncertainty model fuzzy randomness appears useful. In a Bayesian approach the fuzzy probabilistic model provides the opportunity to take account of imprecision in data and in prior expert knowledge. The Bayesian approach ex-tended to inconsistent information is demonstrated …

A Systems Approach To Countermeasures In Credibility Assessment Interviews, Nathan Twyman, Ryan M. Schuetzler, Jeffrey Gainer Proudfoot, Aaron Elkins

Information Systems and Quantitative Analysis Faculty Proceedings & Presentations

Countermeasures, or techniques for hiding guilt during a credibility assessment examination, have long been an important topic in cognitive psychology and criminal justice fields. With recent IS research on automated screening systems, understanding the potential for countermeasures in this new paradigm is of increasing importance. This paper reports on a large experiment examining countermeasures in an automated deception detection screening context. The effectiveness of traditional countermeasure types (mental and physical) are examined, as well as an exploratory approach of trying several countermeasures at once. The exploratory approach was tested to investigate a proposed novel systems-inspired solution to countermeasures—triangulating on deception …

Fuzzy Search Strategy Generation For Adversarial Systems Using Fuzzy Process Particle Swarm Optimization, Fuzzy Patterns, And A Hunch Factor, Stephany Coffman-Wolph

Dissertations

Adversarial game-playing situations have been studied in both game theory and artificial intelligence since the 1950s. However, developing strategies for game playing is challenging due to the large search tree size as the environment size increases. The research presented develops a centralized fuzzy search strategy to find winning strategies for adversarial situations using fuzzy logic. The aforementioned fuzzy algorithm, Fuzzy Strategy Finder (FSF), can be used to find valid strategies for any problem that can be written as a Reti-like or zero-sum game. Using several chess endgames, the FSF will be shown to have a faster runtime without a significant …

Dynamic Joint Sentiment-Topic Mode, Yulan He, Chenghua Lin, Wei Gao, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Social media data are produced continuously by a large and uncontrolled number of users. The dynamic nature of such data requires the sentiment and topic analysis model to be also dynamically updated, capturing the most recent language use of sentiments and topics in text. We propose a dynamic Joint Sentiment-Topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic-specific word distributions are generated according to the word distributions at previous epochs. We study three different …