Digital Commons Network^™

Hardware Acceleration Of Inference Computing: The Numenta Htm Algorithm, Dan Hammerstrom

Systems Science Friday Noon Seminar Series

In this presentation I will describe the latest version of the Numenta HTM Cortical Learning Algorithm and why it is interesting for doing research into radical new computer architectures. Then I will discuss the hardware acceleration research we are doing, and briefly look at some preliminary applications development.

Trust Networks: Interpersonal, Social, And Sensor, Krishnaprasad Thirunarayan, Pramod Anantharam

Kno.e.sis Publications

Trust relationships occur naturally in many diverse contexts such as ecommerce, interpersonal interactions, social networks, sensor web, etc. As agents providing content and services become increasingly removed from the agents that consume them, the issue of robust trust inference and update become critical. Unfortunately, there is neither a universal notion of trust that is applicable to all domains nor a clear explication of its semantics or computation in many situations. In this beginner's level tutorial, we motivate the trust problem, explain the relevant concepts, summarize research in modeling trust and gleaning trustworthiness, and discuss challenges confronting us in this process.

Novel Application Of Neutrosophic Logic In Classifiers Evaluated Under Region-Based Image Categorization System, Wen Ju

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Neutrosophic logic is a relatively new logic that is a generalization of fuzzy logic. In this dissertation, for the first time, neutrosophic logic is applied to the field of classifiers where a support vector machine (SVM) is adopted as the example to validate the feasibility and effectiveness of neutrosophic logic. The proposed neutrosophic set is integrated into a reformulated SVM, and the performance of the achieved classifier N-SVM is evaluated under an image categorization system. Image categorization is an important yet challenging research topic in computer vision. In this dissertation, images are first segmented by a hierarchical two-stage self organizing …

Narrative Analysis And Computational Model To Predict Interestingness Of Narratives, Laxman Thapa

Theses and Dissertations - UTB/UTPA

In this research, I present results demonstrating the classification of the specially generated narratives by a machine agent by listening to human subject describing the same sets of the events. These classifications are based on human ratings of interestingness for many different recountings of the same stories. The classification is performed on various features selected after analyzing the different possible feature that affect on the interestingness of narratives. The features were extracted from the surface text as well as from annotations of how each narration relates to the content of the known story. I present the annotation process and resulting …

Real-Time Fundamental Frequency Estimation Algorithm For Disconnected Speech, Thomas Skjei

Theses and Dissertations

A new algorithm is presented for real-time fundamental frequency estimation of speech signals. This method extends and alters the YIN algorithm, which uses the autocorrelation-based difference function, by adding features to reduce latency, correct predictable errors, and make it structurally appropriate for real-time processing scenarios. The algorithm is shown to reduce the error rate of its predecessor while demonstrating latencies sufficient for real-time processing. The results indicate that the algorithm can be realized as a real-time estimator of spoken pitch and pitch variation, which has applications including diagnosis and biofeedback-based therapy of many speech disorders.

A Bottom-Up Design And Implementation For Ambiguity-Compatible Natural Language Sentence Parsing, Elise Thrasher

Computer Science Honors Theses

Although many theory-focused computer science textbooks give a brief outline of a context-free grammar model of natural language, the approach is often vague and, in reality, greatly simplifies the English language’s grammatical complexities. When applied to commonly-seen sentences, these sentence parsing models often fall short. In this paper, I detail my process of creating a programmable natural language context-free grammar that is able to parse (i.e. diagram) many common sentence forms, as well as the research which influenced the design of this project. In order to create a grammar that recognized the intricacies of the English language, I also incorporated …

Privacy Analysis Of User Association Logs In A Large-Scale Wireless Lan, Keren Tan, Guanhua Yan, Jihwang Yeo, David Kotz

Dartmouth Scholarship

User association logs collected from a large-scale wireless LAN record where and when a user has used the network. Such information plays an important role in wireless network research. One concern of sharing these data with other researchers, however, is that the logs pose potential privacy risks for the network users. Today, the common practice in sanitizing these data before releasing them to the public is to anonymize users' sensitive information, such as their devices' MAC addresses and their exact association locations. In this work, we aim to study whether such sanitization measures are sufficient to protect user privacy. By …

Voice Commands To Control Recording Sessions, J. Marty Goddard

Electrical Engineering and Computer Science - Technical Reports

In this report, the music recording workflow is described, with support for voice commands. Natural command grammars are proposed, allowing the user to name items, and issue commands on items identified by name. Recognition accuracy is examined within the contexts of single-phrase commands, and of versatile command grammars which enable the referring to items by name.

Holistic Network Defense: Fusing Host And Network Features For Attack Classification, Jenny W. Ji

Theses and Dissertations

This work presents a hybrid network-host monitoring strategy, which fuses data from both the network and the host to recognize malware infections. This work focuses on three categories: Normal, Scanning, and Infected. The network-host sensor fusion is accomplished by extracting 248 features from network traffic using the Fullstats Network Feature generator and from the host using text mining, looking at the frequency of the 500 most common strings and analyzing them as word vectors. Improvements to detection performance are made by synergistically fusing network features obtained from IP packet flows and host features, obtained from text mining port, processor, logon …

An Approach To Nearest Neighboring Search For Multi-Dimensional Data, Yong Shi, Li Zhang, Lei Zhu

Faculty Articles

Finding nearest neighbors in large multi-dimensional data has always been one of the research interests in data mining field. In this paper, we present our continuous research on similarity search problems. Previously we have worked on exploring the meaning of K nearest neighbors from a new perspective in PanKNN [20]. It redefines the distances between data points and a given query point Q, efficiently and effectively selecting data points which are closest to Q. It can be applied in various data mining fields. A large amount of real data sets have irrelevant or obstacle information which greatly affects the effectiveness …

Programming Language Fragmentation And Developer Productivity: An Empirical Study, Jonathan L. Krein

Theses and Dissertations

In an effort to increase both the quality of software applications and the efficiency with which applications can be written, developers often incorporate multiple programming languages into software projects. Although language specialization arguably introduces benefits, the total impact of the resulting language fragmentation (working concurrently in multiple programming languages) on developer performance is unclear. For instance, developers may solve problems more efficiently when they have multiple language paradigms at their disposal. However, the overhead of maintaining efficiency in more than one language may outweigh those benefits. This thesis represents a first step toward understanding the relationship between language fragmentation and …

Using Hotspots As A Novel Method For Accessing Key Events In A Large Multi-Modal Corpus, Catherine Oertel, Celine De Looze, Brian Vaughan, Emer Gilmartin, Petra Wagner

Conference papers

n 2009 we created the D64 corpus, a multi-modal corpus which consists of roughly eight hours of natural, non-directed spontaneous interaction in an informal setting. Five participants feature in the recordings and their conversations were captured by microphones (room, body mounted and head mounted), video cameras and a motion capture system. The large amount of video, audio and motion capture material made it necessary to structure and make available the corpus in such a way that it is easy to browse and query for various types of data that we term primary, secondary and tertiary. While users are able to …

Punctuated Anytime Learning And The Xpilot-Ai Combat Environment, Phillip Fritzsche

Computer Science Honors Papers

In this paper, research is presented on an application of Punctuated Anytime Learning with Fitness Biasing, a type of computational intelligence and evolutionary learning, for real-­time learning of autonomous agents controllers in the space combat game Xpilot. Punctuated Anytime Learning was originally developed as a means of effective learning in the field of evolutionary robotics. An analysis was performed on the game environment to determine optimal environmental settings for use during learning, and Fitness Biasing is employed using this information to learn intelligent behavior for a video game agent controller in real-­time. Xpilot-­AI, an Xpilot add-­on designed for testing learning …

Parsing Combinatory Categorial Grammar With Answer Set Programming: Preliminary Report, Yuliya Lierler, Peter Schüller

Computer Science Faculty Proceedings & Presentations

Combinatory categorial grammar (CCG) is a grammar formalism used for natural language parsing. CCG assigns structured lexical categories to words and uses a small set of combinatory rules to combine these categories to parse a sentence. In this work we propose and implement a new approach to CCG parsing that relies on a prominent knowledge representation formalism, answer set programming (ASP) — a declarative programming paradigm. We formulate the task of CCG parsing as a planning problem and use an ASP computational tool to compute solutions that correspond to valid parses. Compared to other approaches, there is no need to …

Spatial Interactions Between Humans And Assistive Agents, Franz J. Kurfess, Greg Flanagan, Mehul Bhatt

Computer Science and Software Engineering

While computers assist humans with tasks such as navigation that involve spatial aspects, agents that can interact in a meaningful way in this context are still in their infancy. One core issue is the mismatch in the representation of spatial information a computer-based system is likely to use, and the one a human is likely to use. Computers are better suited for quantitative schemes such as maps or diagrams that rely on measurable distances between entities. Humans frequently use higher-level, domain-specific conceptual representations such as buildings, rooms, or streets for orientation purposes. Combined with the person-centric world view that we …

Contextual Ontology Alignment Of Lod With An Upper Ontology: A Case Study With Proton, Prateek Jain, Peter Z. Yeh, Kunal Verma, Reymonrod G. Vasquez, Mariana Darnorva, Pascal Hitzler, Amit P. Sheth

Kno.e.sis Publications

The Linked Open Data (LOD) is a major milestone towards realizing the Semantic Web vision, and can enable applications such as robust Question Answering (QA) systems that can answer queries requiring multiple, disparate information sources. However, realizing these applications requires relationships at both the schema and instance level, but currently the LOD only provides relationships for the latter. To address this limitation, we present a solution for automatically finding schema-level links between two LOD ontologies – in the sense of ontology alignment. Our solution, called BLOOMS+, extends our previous solution (i.e. BLOOMS) in two significant ways. BLOOMS+ 1) uses a …

Moving Towards Adaptive Search In Digital Libraries, Udo Kruschwitz, M-Dyaa Albakour, Jinzhong Niu, Johannes Leveling, Nikolaos Nanas, Yunhyong Kim, Dawei Song, Maria Fasli, Anne De Roeck

Publications and Research

Information retrieval has become very popular over the last decade with the advent of the Web. Nevertheless, searching on the Web is very different to searching on smaller, often more structured collections such as digital libraries, local Web sites and intranets. One way of helping the searcher locating the right information for a specific information need is by providing well-structured domain knowledge to assist query modification and navigation. There are two challenges: acquiring the domain knowledge and adapting it automatically to the specific interests of the user community. We will outline how a domain model can be automatically acquired using …

Enhancing Bag-Of-Words Models By Efficient Semantics-Preserving Metric Learning, Lei Wu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

The authors present an online semantics preserving, metric learning technique for improving the bag-of-words model and addressing the semantic-gap issue. This article investigates the challenge of reducing the semantic gap for building BoW models for image representation; propose a novel OSPML algorithm for enhancing BoW by minimizing the semantic loss, which is efficient and scalable for enhancing BoW models for large-scale applications; apply the proposed technique for large-scale image annotation and object recognition; and compare it to the state of the art.

A Cultural Analysis Of Information Technology Offshore Outsourcing: An Exercise In Multi-Sited Ethnography Of Virtual Work, Tara Eaton

Wayne State University Dissertations

This study is an exploration of how ethnography and anthropological analysis can provide new understanding of transnational, multi-sited research phenomena. Research focused on the work activities of one American client organization and its Indian IT service provider situated in the global virtual field of Information Technology (IT) offshore outsourcing. The Principal Investigator adapted and applied an ethnographic approach for her fieldwork in order to understand the norms, beliefs, and values about work, as well as the relationship between cultural differences and virtual communication. Dissertation findings offer new insight for anthropological discussions of globalization as well as suggest further development of …

Citizen Sensor Data Mining, Social Media Analytics And Development Centric Web Applications, Meenakshi Nagarajan, Amit P. Sheth, Selvam Velmuru

Kno.e.sis Publications

With the rapid rise in the popularity of social media (500M+ Facebook users, 100M+ twitter users), and near ubiquitous mobile access (4.1 billion actively-used mobile phones), the sharing of observations and opinions has become common-place (nearly 100M tweets a day, 1.8 trillion SMSs in US last year). This has given us an unprecedented access to the pulse of a populace and the ability to perform analytics on social data to support a variety of socially intelligent applications -- be it towards targeted online content delivery, crisis management, organizing revolutions or promoting social development in underdeveloped and developing countries. This tutorial …

A Unified Framework Fro Managing Provenance Information In Translational Research, Satya S. Sahoo, Vinh Nguyen, Olivier Bodenreider, Priti Parikh, Todd Minning, Amit P. Sheth

Kno.e.sis Publications

Background

A critical aspect of the NIH Translational Research roadmap, which seeks to accelerate the delivery of "bench-side" discoveries to patient's "bedside," is the management of the provenance metadata that keeps track of the origin and history of data resources as they traverse the path from the bench to the bedside and back. A comprehensive provenance framework is essential for researchers to verify the quality of data, reproduce scientific results published in peer-reviewed literature, validate scientific process, and associate trust value with data and results. Traditional approaches to provenance management have focused on only partial sections of the translational research …

Semi-Automatic Management Of Knowledge Bases Using Formal Ontologies, Andreas Textor

Theses

This thesis presents an approach that deals with the ever-growing amount of data in knowledge bases, especially concerning knowledge interoperability and formal representation of domain knowledge. There arc multiple issues that must be addressed with current systems. A multitude of different formats, sources and tools exist in a domain, and it is desirable to develop their use further towards a standardised environment. Such an environment should support both the representation and processing of data from this domain, and the connection to other domains, where necessary. In order to manage large amounts of data, it should be possible to perform whatever …

A Low-Budget Tagger For Old Czech, Jirka Hana, Anna Feldman, Katsiaryna Aharodnik

Department of Computer Science Faculty Scholarship and Creative Works

The paper describes a tagger for Old Czech (1200-1500 AD), a fusional language with rich morphology. The practical restrictions (no native speakers, limited corpora and lexicons, limited funding) make Old Czech an ideal candidate for a resource-light crosslingual method that we have been developing (e.g. Hana et al., 2004; Feldman and Hana, 2010). We use a traditional supervised tagger. However, instead of spending years of effort to create a large annotated corpus of Old Czech, we approximate it by a corpus of Modern Czech. We perform a series of simple transformations to make a modern text look more like a …

Privacy Analysis Of User Association Logs In A Large-Scale Wireless Lan, Keren Tan, Guanhua Yan, Jihwang Yeo, David Kotz

Computer Science Technical Reports

User association logs collected from a large-scale wireless LAN record where and when a user has used the network. Such information plays an important role in wireless network research. One concern of sharing these data with other researchers, however, is that the logs pose potential privacy risks for the network users. Today, the common practice in sanitizing these data before releasing them to the public is to anonymize users' sensitive information, such as their devices' MAC addresses and their exact association locations. In this work, we demonstrate that such sanitization measures are insufficient to protect user privacy because the differences …

Automatic Knowledge Extraction For Filling In Biography Forms From Turkish Texts, İlknur Pehli̇van, Zeynep Orhan

Turkish Journal of Electrical Engineering and Computer Sciences

This study presents a method for building an automatic knowledge extraction system for filling in biography forms from Turkish texts. Several biographies are analyzed in order to choose the set of biography categories to be studied. The fields of the biography form to be created are also defined based on this analysis. Information extraction techniques are used for implementation. A separate testing platform is designed to evaluate the accuracy of the extracted data. Results of the testing platform have shown this study to be a promising process to be further developed especially for creating forms in the Turkish language.

An Effective Real Coded Ga Based Fuzzy Controller For Speed Control Of A Bldc Motor Without Speed Sensor, Ömer Aydoğdu, Ramazan Akkaya

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, an effective Real Coded Genetic Algorithm (GA) based optimal fuzzy controller is proposed. The fuzzy controller is used for sensorless speed control of a Brushless DC (BLDC) motor in DSP based application system. The advantages of adopting a real coded GA for the design and optimization of fuzzy controllers, which have a great deal of design and optimization parameters, are analyzed. Having accomplished optimization of developed fuzzy control system, a multi-objective performance index has been defined and it has been used as an objective function to be minimized in the real coded GA. Thus, the system can …

A Fuzzy Rule-Based System For Predicting The Live Weight Of Holstein Cows Whose Body Dimensions Were Determined By Image Analysis, Şaki̇r Taşdemi̇r, Abdullah Ürkmez, Şeref İnal

Turkish Journal of Electrical Engineering and Computer Sciences

The aim of this study was to determine the body measurement of Holstein cows through image analysis (IA) and to estimate their live weight (LW) by means of a fuzzy rule-based model using the body measurements. For this purpose, a photography environment was established at a dairy cattle farm where a large number of cows were kept. First, digital photographs of each animal were synchronously taken from different directions with Canon EOS 400D cameras. At the same time, body dimensions, namely wither height (WH), hip height (HH), body length (BL), and hip width (HW), of the cows were manually measured …

Vibrations Control Of Light Rail Transportation Vehicle Via Pid Type Fuzzy Controller Using Parameters Adaptive Method, Muzaffer Meti̇n, Rahmi̇ Güçlü

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, a conventional PID type fuzzy controller and parameter adaptive fuzzy controller are designed to control vibrations actively of a light rail transport vehicle which modeled as 6 degree-of-freedom system and compared performances of these two controllers. Rail vehicle model consists of a passenger seat and its suspension system, vehicle body, bogie, primary and secondary suspensions and wheels. The similarity between mathematical model and real system is shown by comparing uncontrolled simulation results and vibration measurements. For carrying a comfortable travel, rail vehicle body and passenger seat vibrations are minimized by adding a controller between rail vehicle body …

Longitudinal Evaluation Of A Learning System For Teaching Geographical Information System Within The Context Of A Geotechnical Problem, Aparna Sukhavasi

Masters Theses

"A learning system, to train civil engineering students to apply Geographical Information Systems (GIS) in geotechnical problems, was evaluated over a period of 5 years, hence longitudinal. The system was tested with a series of iterations consisting of usability tests and subsequent modification, which were followed by a series of applied evaluations within the context of class lab sessions. The principal goals of this evaluation were to determine the overall effectiveness of the system and the factors that affected student learning. The first evaluation was conducted in 2004; and included a control group that played a "game" related to the …

Trends In Phishing Attacks: Suggestions For Future Research, Ryan M. Schuetzler

Information Systems and Quantitative Analysis Faculty Proceedings & Presentations

Deception in computer-mediated communication is a widespread phenomenon. Cyber criminals are exploiting technological mediums to communicate with potential targets as these channels reduce both the deception cues and the risk of detection itself. A prevalent deception-based attack in computer-mediated communication is phishing. Prior phishing research has addressed the “bait” and “hook” components of phishing attacks, the human-computer interaction that takes place as users judge the veracity of phishing emails and websites, and the development of technologies that can aid users in identifying and rejecting these attacks. Despite the extant research on this topic, phishing attacks continue to be successful as …