Digital Commons Network^™

Structured Summarization Of Multi-Party Conversations, Ching-Sheng Lin

Legacy Theses & Dissertations (2009 - 2024)

Automatic summarization is the task of creating a set of short and concise sentences that capture the content of the original source material. Summaries should retain only the most relevant content of the source, while suppressing secondary and redundant information. Most existing approaches to automatic summarization have been applied to narrative documents such as news, reports, and technical documents. Relatively few techniques were proposed for summarizing meetings and other forms of interactive content.

Persuasion In Online Communication : Automation And Counteraction, Samira Shaikh Shaikh

Legacy Theses & Dissertations (2009 - 2024)

In this thesis, we studied persuasion in online communication and how to automate

Towards A Semantic-Based Information Extraction System For Matching Résumés To Job Openings, Duygu Çeli̇k

Turkish Journal of Electrical Engineering and Computer Sciences

A curriculum vitae or a résumé, in general, consists of personal details, education, work experience, qualifications, and references. The overall objective of this study was to extract such data as experience, features, and business and education information from résumés stored in human resources repositories. In this article, we propose an ontology-driven information extraction system that is planned to operate on several million free-format textual résumés to convert them to a structured and semantically enriched version for use in semantic data mining of data essential in human resources processes. The architecture and working mechanism of the system, similarity of the concept …

The Classification Of Eeg Signals Using Discretization-Based Entropy And The Adaptive Neuro-Fuzzy Inference System, Mahmut Heki̇m

Turkish Journal of Electrical Engineering and Computer Sciences

A novel feature extraction called discretization-based entropy is proposed for use in the classification of EEG signals. To this end, EEG signals are decomposed into frequency subbands using the discrete wavelet transform (DWT), the coefficients of these subbands are discretized into the desired number of intervals using the discretization method, the entropy values of the discretized subbands are calculated using the Shannon entropy method, and these are then used as the inputs of the adaptive neuro-fuzzy inference system (ANFIS). The equal width discretization (EWD) and equal frequency discretization (EFD) methods are used for the discretization. In order to evaluate their …

A Generalized Particle Swarm Optimization Using Reverse Direction Information, Emre Çomak

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, an improved particle swarm optimization (PSO) algorithm, including 4 types of new velocity updating formulae (each is equal to the traditional PSO), was introduced. This algorithm was called the reverse direction supported particle swarm optimization (RDS-PSO) algorithm. The RDS-PSO algorithm has the potential to extend the diversity and generalization of traditional PSO by regulating the reverse direction information adaptively. To implement this extension, 2 new constants were added to the velocity update equation of the traditional PSO, and these constants were regulated through 2 alternative procedures, i.e. max--min-based and cosine amplitude-based diversity-evaluating procedures. The 4 most commonly …

A New Step-Size Searching Algorithm Based On Fuzzy Logic And Neural Networks For Lms Adaptive Beamforming Systems, Walter Orozco-Tupacyupanqui, Mariko Nakano-Miyatake, Hector Perez Meana

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, a novel algorithm based on fuzzy logic and neural networks is proposed to find an approximation of the optimal step size $\mu $ for least-mean-squares (LMS) adaptive beamforming systems. A new error ensemble learning (EEL) curve is generated based on the final prediction value of the ensemble-average learning curve of the LMS adaptive algorithm. This information is classified and fed into a back propagation neural network, which automatically generates membership functions for a fuzzy inference system. An estimate of the optimal step size is obtained using a group of linguistic rules and the corresponding defuzzification method. Computer …

A New Compression Algorithm For Fast Text Search, Aydin Carus, Altan Mesut

Turkish Journal of Electrical Engineering and Computer Sciences

We propose a new compression algorithm that compresses plain texts by using a dictionary-based model and a compressed string-matching approach that can be used with the compressed texts produced by this algorithm. The compression algorithm (CAFTS) can reduce the size of the texts to approximately 41% of their original sizes. The presented compressed string matching approach (SoCAFTS), which can be used with any of the known pattern matching algorithms, is compared with a powerful compressed string matching algorithm (ETDC) and a compressed string-matching tool (Lzgrep). Although the search speed of ETDC is very good in short patterns, it can only …

Applying Metaheuristic Optimization Methods To Design Novel Adaptive Pi-Type Fuzzy Logic Controllers For Load-Frequency Control In A Large-Scale Power Grid, Thimaiphuong Dao, Yaonan Wang, Ngockhoat Nguyen

Turkish Journal of Electrical Engineering and Computer Sciences

Due to the complexity and diversity of large-scale power systems in practice, designing load-frequency control (LFC) strategies against load variations faces big challenges to ensure the stability and economy of the network. The focus of this paper is to design a novel adaptive PI-type fuzzy logic (FL)-based LFC architecture for solving the LFC problem in such an interconnected electric power grid. Applying 2 biologically inspired optimization methods, namely particle swarm optimization method and a genetic algorithm, the membership functions and rule base of a basic PI-type FL model were parameterized and optimized simultaneously and successfully. An online self-tuning method was …

Fast Measurement Of Headlamps By Means Of A Developed Fuzzy Luxmeter Based On A Fuzzy Mapping Algorithm, Mustafa Şi̇nasi̇ Ayas, İsmai̇l Hakki Altaş, Turhan Alçeli̇k

Turkish Journal of Electrical Engineering and Computer Sciences

headlamps in the dark is inferable from the results of studies. Various regulations are available in order to arrange the required illuminance values at certain positions on the road. The designed and produced headlamps have to satisfy the requirements of these regulations. Manual measurement tools, such as the luxmeter (which are based on point-by-point measurements), have traditionally been used. This traditional way has been considered inefficient in terms of awkward setup procedures, complexity, the continuous intervention of human operators, and costs. In this study, in order to overcome these problems, a new approach for measuring the illuminance values is proposed. …

An Investigation Of Intelligent Controllers Based On Fuzzy Logic And Artificial Neural Network For Power System Frequency Maintenance, Ngockhoat Nguyen, Qi Huang, Thi-Mai-Phuong Dao

Turkish Journal of Electrical Engineering and Computer Sciences

No abstract provided.

Authentication Of Uncertain Data Based On K-Means Clustering, Levent Ünver, Taflan İmre Gündem

Turkish Journal of Electrical Engineering and Computer Sciences

No abstract provided.

Wind Farm Based On Dfig Entirely Interfaced With 14-Node Distribution Network: Power Control And Voltage Regulation, Babouri Rabah, Aouchenni Ounissa, Aouzellag Djamal, Ghedamsi Kaci

Turkish Journal of Electrical Engineering and Computer Sciences

power quality problems due to the fluctuating nature of the wind and the increasing complexity of the power system. This paper describes a novel approach to voltage and power control of a radial electrical distribution network, using a wind farm. The wind farm consists of seven 75 kW induction generators (DFIG) supplying two AC/DC converters. The feed structure of the DFIG allows operating the system conversion in a wide range of speed variations. That is why it is a recommended solution, due to its capacity to increase the generator power to twice its nominal power; consequently, the system's size and …

Scalable Sentiment Analytics, Aslan Baki̇rov, Kevser Nur Çoğalmiş, Ahmet Bulut

Turkish Journal of Electrical Engineering and Computer Sciences

Spark has become a widely popular analytics framework that provides an implementation of the equally popular MapReduce programming model. Hadoop is an Apache foundation framework that can be used for processing large datasets on a cluster of computers using the MapReduce programming model. Mahout is an Apache foundation project developed for building scalable machine learning libraries, which includes built-in machine learning classifiers. In this paper, we show how to build a simple text classifier on Spark, Apache Hadoop, and Apache Mahout for extracting out sentiments from a text collection containing millions of text documents. Using a collection of 7 million …

Identifying Acquisition Devices From Recorded Speech Signals Using Wavelet-Based Features, Ömer Eski̇dere

Turkish Journal of Electrical Engineering and Computer Sciences

Speech characteristics have played a critical role in media forensics, particularly in the investigation of evidence. This study proposes two wavelet-based feature extraction methods for the identification of acquisition devices from recorded speech. These methods are discrete wavelet-based coefficients (DWBCs) and wavelet packet-based coefficients, which are mainly based on a multiresolution analysis. These features' ability to capture characteristics of acquisition devices is compared to conventional mel frequency cepstral coefficients and subband-based coefficients. In the experiments, 14 different audio acquisition devices were trained and tested using support vector machines. Experimental results showed that DWBCs can effectively be used in source audio …

Using Natural Language Processing And Qualitative Analysis To Intervene In Gang Violence: A Collaboration Between Social Work Researchers And Data Scientists, Desmond Upton Patton, Kathleen Mckeown, Owen Rambow, Jamie C. Macbeth

Computer Science: Faculty Publications

The U.S. has the highest rate of firearm-related deaths when compared to other industrialized countries. Violence particularly affects lowincome, urban neighborhoods in cities like Chicago, which saw a 40% increase in firearm violence from 2014 to 2015 to more than 3,000 shooting victims. While recent studies have found that urban, gang-involved individuals curate a unique and complex communication style within and between social media platforms, organizations focused on reducing gang violence are struggling to keep up with the growing complexity of social media platforms and the sheer volume of data they present. In this paper, describe the Digital Urban Violence …

Knowledge Extraction From Metacognitive Reading Strategies Data Using Induction Trees, Christopher Taylor, Arun D. Kulkarni, Kouider Mokhtari

Computer Science Faculty Publications and Presentations

The assessment of students’ metacognitive knowledge and skills about reading is critical in determining their ability to read academic texts and do so with comprehension. In this paper, we used induction trees to extract metacognitive knowledge about reading from a reading strategies dataset obtained from a group of 1636 undergraduate college students. Using a C4.5 algorithm, we constructed decision trees, which helped us classify participants into three groups based on their metacognitive strategy awareness levels consisting of global, problem-solving and support reading strategies. We extracted rules from these decision trees, and in order to evaluate accuracy of the extracted rules, …

Confluence Of Vision And Natural Language Processing For Cross-Media Semantic Relations Extraction, Amara Tariq

Electronic Theses and Dissertations

In this dissertation, we focus on extracting and understanding semantically meaningful relationships between data items of various modalities; especially relations between images and natural language. We explore the ideas and techniques to integrate such cross-media semantic relations for machine understanding of large heterogeneous datasets, made available through the expansion of the World Wide Web. The datasets collected from social media websites, news media outlets and blogging platforms usually contain multiple modalities of data. Intelligent systems are needed to automatically make sense out of these datasets and present them in such a way that humans can find the relevant pieces of …

Fuzzy Decision Tree-Based Inference System For Liver Disease Diagnosis, Himaja Sivaraju

Theses and Dissertations

Medical diagnosis can be challenging because of a number of factors. Uncertainty in the diagnosis process arises from inaccuracy in the measurement of patient attributes, missing attribute data and limitation in the medical expert’s ability to define cause and effect relationships when there are multiple interrelated variables. Given this situation, a decision support system, which can help doctors come up with a more reliable diagnosis, can have a lot of potential.

Decision trees are used in data mining for classification and regression. They are simple to understand and interpret as they can be visualized. But, one of the disadvantages of …

Bytewise Approximate Matching: The Good, The Bad, And The Unknown, Vikram S. Harichandran, Frank Breitinger, Ibrahim Baggili

Journal of Digital Forensics, Security and Law

Hash functions are established and well-known in digital forensics, where they are commonly used for proving integrity and file identification (i.e., hash all files on a seized device and compare the fingerprints against a reference database). However, with respect to the latter operation, an active adversary can easily overcome this approach because traditional hashes are designed to be sensitive to altering an input; output will significantly change if a single bit is flipped. Therefore, researchers developed approximate matching, which is a rather new, less prominent area but was conceived as a more robust counterpart to traditional hashing. Since the conception …

Proceedings Of The 3rd Annual Cuny Games Festival, Robert O. Duncan, Joe Bisz, Julie Cassidy, Carlos Hernandez, Kathleen Offenholley, Maura A. Smale, Deborah Sturm, Cuny Games Network

Publications and Research

Proceedings of the CUNY Games Conference, held from January 22-23, 2016, at the CUNY Graduate Center and Borough of Manhattan Community College.

Literacy and Story - Anything Can be Attempted: In-Person Simulations and Role-Plays in Educations - Game Design - STEM - Design Research - Literature and Story - Awareness: Gender and Sex - Transformative Games Initiative: Game Design as a Classroom Laboratory for Any Discipline - Narrative and Rhetoric - Design Challenges - Information Literacy and Language - Game Design for All: What’s Your Game Plan? Turn Any Idea into a Game! - Ghosts in the Machine - Game …

Implementation Of An Air Supply Unit Control Scheme For The Uc2av (Unmanned Circulation Control Aerial Vehicle), Cameron Rosen

Electronic Theses and Dissertations

The expanded prevalence of Unmanned Aerial Vehicles (UAVs) in recent years has created many opportunities to research novel applications for their use, enabled by the reduced cost, mission flexibility, and reduced risk that small-scale unmanned platforms provide in comparison to larger aircraft. Despite the versatility of unmanned aviation, limitations on payload size and weight, fuel and power capacity, and takeoff and landing infrastructure can restrict UAV applications, and have created a need for lift augmenting technologies that can reduce the impact of these limitations. Circulation Control (CC) is an active flow technique that has been proven as a method for …

In God We Trust. All Others Must Bring Data. - W. Edwards Deming Using Word Embeddings To Recognize Idioms, Jing Peng, Anna Feldman

Department of Computer Science Faculty Scholarship and Creative Works

Expressions, such as add fuel to the fire, can be interpreted literally or idiomatically depending on the context they occur in. Many Natural Language Processing applications could improve their performance if idiom recognition were improved. Our approach is based on the idea that idioms violate cohesive ties in local contexts, while literal expressions do not. We propose two approaches: 1) Compute inner product of context word vectors with the vector representing a target expression. Since literal vectors predict well local contexts, their inner product with contexts should be larger than idiomatic ones, thereby telling apart literals from idioms; and (2) …

Identifying Offensive Videos On Youtube, Rajeshwari Kandakatla

Browse all Theses and Dissertations

Harassment on social media has become a critical problem and social media content depicting harassment is becoming common place. Video-sharing websites such as YouTube contain content that may be offensive to certain community, insulting to certain religion, race etc., or make fun of disabilities. These videos can also provoke and promote altercations leading to online harassment of individuals and groups. In this thesis, we present a system that identifies offensive videos on YouTube. Our goal is to determine features that can be used to detect offensive videos efficiently and reliably. We conducted experiments using content and metadata available for each …

Cyberbullying Detection With A Pronunciation Based Convolutional Neural Network, Xiang Zhang, Jonathan Tong, Nishant Vishwamitra, Elizabeth Whittaker, Joseph P. Mazer, Robin Kowalski, Hongxin Hu, Feng Luo, Jamie C. Macbeth, Edward Dillon

Computer Science: Faculty Publications

Cyberbullying can have a deep and long lasting impact on its victims, who are often adolescents. Accurately detecting cyberbullying helps prevent it. However, the noise and errors in social media posts and messages make detecting cyberbullying very challenging. In this paper, we propose a novel pronunciation based convolutional neural network (PCNN) to address this challenge. Upon observing that the pronunciation of misspelled words in informal online conversations is often unchanged, we used the phoneme codes of the text as the features for a convolutional neural network. This procedure corrects spelling errors that did not alter the pronunciation, thereby alleviating the …

Resqu: A Framework For Automatic Evaluation Of Knowledge-Driven Automatic Summarization, Nishita Jaykumar

Browse all Theses and Dissertations

Automatic generation of summaries that capture the salient aspects of a search resultset (i.e., automatic summarization) has become an important task in biomedical research. Automatic summarization offers an avenue for overcoming the information overload problem prevalent in large online digital libraries. However, across many of the knowledge-driven approaches for automatic summarization it is not always clear which features highly impact or influence the quality of a summary. Instead, there has been considerable focus on utilizing schema knowledge to facilitate browsing and exploration of generated summaries a posteriori. Informative features should not be ignored, since they could be utilized to help …

Knowledge-Driven Implicit Information Extraction, Pathirage Dinindu Perera

Browse all Theses and Dissertations

Natural language is a powerful tool developed by humans over hundreds of thousands of years. The extensive usage, flexibility of the language, creativity of the human beings, and social, cultural, and economic changes that have taken place in daily life have added new constructs, styles, and features to the language. One such feature of the language is its ability to express ideas, opinions, and facts in an implicit manner. This is a feature that is used extensively in day to day communications in situations such as: 1) expressing sarcasm, 2) when trying to recall forgotten things, 3) when required to …

Identifying Tweets With Implicit Entity Mentions, Adarsh Koruthu Alex

Browse all Theses and Dissertations

Social networking sites like Twitter and Facebook have become a significant source of user-generated content in the past decade. Mining of this user-generated content has proved beneficial for a broad range of applications like Event Extraction, Document Retrieval, and Sentiment Analysis. Identifying entities is one of the major tasks that fuel important information for above tasks. Identification of entities is typically performed in two steps; Named Entity Recognition (NER) and Entity Linking. State of the art NER solutions focus on recognizing the entities that are mentioned explicitly in social media posts. However, entities are frequently mentioned implicitly in them. For …

Framework For Semantic Integration And Scalable Processing Of City Traffic Events, Surendra Brahma Marupudi

Browse all Theses and Dissertations

Intelligent traffic management requires analysis of a large volume of multimodal data from diverse domains. For the development of intelligent traffic applications, we need to address diversity in observations from physical sensors which give weather, traffic flow, parking information; we also need to do the same with social media, which provides live commentary of various events in a city. The extraction of relevant events and the semantic integration of numeric values from sensors, unstructured text from Twitter, and semi- structured data from city authorities is a challenging physical-cyber-social data integration problem. In order to address the challenge of both scalability …

Learning Hierarchically Decomposable Concepts With Active Over-Labeling, Yuji Mo, Stephen Scott, Doug Downey

School of Computing: Conference and Workshop Papers

Many classification tasks target high-level concepts that can be decomposed into a hierarchy of finer-grained subconcepts. For example, some string entities that are Locations are also Attractions, some Attractions are Museums, etc. Such hierarchies are common in named entity recognition (NER), document classification, and biological sequence analysis. We present a new approach for learning hierarchically decomposable concepts. The approach learns a high-level classifier (e.g., location vs. non-location) by seperately learning multiple finer-grained classifiers (e.g., museum vs. non-museum), and then combining the results. Soliciting labels at a finer level of granularity than that of the target concept is a new approach …

Evaluating Distributed Word Representations For Predicting Missing Words In Sentences, Saniya Saifee

Dissertations and Theses

In recent years, the distributed representation of words in vector space or word embeddings have become very popular as they have shown significant improvements in many statistical natural language processing (NLP) tasks as compared to traditional language models like Ngram. In this thesis, we explored various state-of-the-art methods like Latent Semantic Analysis, word2vec, and GloVe to learn the distributed representation of words. Their performance was compared based on the accuracy achieved when tasked with selecting the right missing word in the sentence, given five possible options. For this NLP task we trained each of these methods using a training corpus …