Physical Sciences and Mathematics Commons^™

Mobile Big Data Analytics Using Deep Learning And Apache Spark, Mohammad Abu Alsheikh, Dusit Niyato, Shaowei Lin, Hwee-Pink Tan, Zhu Han

Research Collection School Of Computing and Information Systems

The proliferation of mobile devices, such as smartphones and Internet of Things gadgets, has resulted in the recent mobile big data era. Collecting mobile big data is unprofitable unless suitable analytics and learning methods are utilized to extract meaningful information and hidden patterns from data. This article presents an overview and brief tutorial on deep learning in mobile big data analytics and discusses a scalable learning framework over Apache Spark. Specifically, distributed deep learning is executed as an iterative MapReduce computing on many Spark workers. Each Spark worker learns a partial deep model on a partition of the overall mobile, …

Predicting Changes To Source Code, Justin James Roll

Master's Theses

Organizations typically use issue tracking systems (ITS) such as Jira to plan software releases and assign requirements to developers. Organizations typically also use source control management (SCM) repositories such as Git to track historical changes to a code-base. These ITS and SCM repositories contain valuable data that remains largely untapped. As developers churn through an organization, it becomes expensive for developers to spend time determining which software artifact must be modified to implement a requirement. In this work we created, developed, tested and evaluated a tool called Class Change Predictor, otherwise known as CCP, for predicting which class will implement …

Bridging Statistical Learning And Formal Reasoning For Cyber Attack Detection, Kexin Pei

Open Access Theses

Current cyber-infrastructures are facing increasingly stealthy attacks that implant malicious payloads under the cover of benign programs. Current attack detection approaches based on statistical learning methods may generate misleading decision boundaries when processing noisy data with such a mixture of benign and malicious behaviors. On the other hand, attack detection based on formal program analysis may lack completeness or adaptivity when modeling attack behaviors. In light of these limitations, we have developed LEAPS, an attack detection system based on supervised statistical learning to classify benign and malicious system events. Furthermore, we leverage control flow graphs inferred from the system event …

Cross-Subject Continuous Analytic Workload Profiling Using Stochastic Discrete Event Simulation, Joseph J. Giametta

Theses and Dissertations

Operator functional state (OFS) in remotely piloted aircraft (RPA) simulations is modeled using electroencephalograph (EEG) physiological data and continuous analytic workload profiles (CAWPs). A framework is proposed that provides solutions to the limitations that stem from lengthy training data collection and labeling techniques associated with generating CAWPs for multiple operators/trials. The framework focuses on the creation of scalable machine learning models using two generalization methods: 1) the stochastic generation of CAWPs and 2) the use of cross-subject physiological training data to calibrate machine learning models. Cross-subject workload models are used to infer OFS on new subjects, reducing the need to …

The Global Rock-Art Database Project Towards Machine Learning: Building A Collaborative Open Source Platform For Heritage Management From Information Structure To Information Visualization Using Australian Heritage Examples, Robert Haubt

Staff Scholarship - Australia & Dubai

This guest talk, presented at Lava Lab at the University of Hawaiʻi, explores the intersection of collaboration, data ontology, and information visualization in advancing machine learning within the Global Rock Art Database project. Drawing on insights from the project’s first four years, the talk emphasizes the critical need for cultural heritage preservation by systematically recording and structuring global rock art data in accessible and sustainable ways. This effort not only supports public education on rock art but also facilitates scholarly research.

Key discussions include advancements in data ontology using the CIDOC Conceptual Reference Model (CIDOC CRM) for semantic data management …

Privacy And Accountability In Black-Box Medicine, Roger Allan Ford, W. Nicholson Price Ii

Law Faculty Scholarship

Black-box medicine—the use of big data and sophisticated machine learning techniques for health-care applications—could be the future of personalized medicine. Black-box medicine promises to make it easier to diagnose rare diseases and conditions, identify the most promising treatments, and allocate scarce resources among different patients. But to succeed, it must overcome two separate, but related, problems: patient privacy and algorithmic accountability. Privacy is a problem because researchers need access to huge amounts of patient health information to generate useful medical predictions. And accountability is a problem because black-box algorithms must be verified by outsiders to ensure they are accurate and …

A Near-To-Far Learning Framework For Terrain Characterization Using An Aerial/Ground-Vehicle Team, Ashkan Hajjam

Electronic Theses and Dissertations

In this thesis, a novel framework for adaptive terrain characterization of untraversed far terrain in a natural outdoor setting is presented. The system learns the association between visual appearance of different terrain and the proprioceptive characteristics of that terrain in a self-supervised framework. The proprioceptive characteristics of the terrain are acquired by inertial sensors recording measurements of one second traversals that are mapped into the frequency domain and later through a clustering technique classified into discrete proprioceptive classes. Later, these labels are used as training inputs to the adaptive visual classifier. The visual classifier uses images captured by an aerial …

Greenc5: An Adaptive, Energy-Aware Collection For Green Software Development, Junya Michanan

Electronic Theses and Dissertations

Dynamic data structures in software applications have been shown to have a large impact on system performance. In this paper, we explore energy saving opportunities of interface-based dynamic data structures. Our results suggest that savings opportunities exist in the C5 Collection between 16.95% and 97.50%. We propose a prototype and architecture for creating adaptive green data structures by applying machine learning tools to build a model for predicting energy efficient data structures based on the dynamic workload. Our neural network model can classify energy efficient data structures based on features such as the number of elements, frequency of operations, interface …

Feature Selection For Movie Recommendation, Zehra Çataltepe, Mahi̇ye Uluyağmur, Esengül Tayfur

Turkish Journal of Electrical Engineering and Computer Sciences

TV users have an abundance of different movies they could choose from, and with the quantity and quality of data available both on user behavior and content, better recommenders are possible. In this paper, we evaluate and combine different content-based and collaborative recommendation methods for a Turkish movie recommendation system. Our recommendation methods can make use of user behavior, different types of content features, and other users' behavior to predict movie ratings. We gather different types of data on movies, such as the description, actors, directors, year, and genre. We use natural language processing methods to convert the Turkish movie …

A Mapreduce-Based Distributed Svm Algorithm For Binary Classification, Ferhat Özgür Çatak, Mehmet Erdal Balaban

Turkish Journal of Electrical Engineering and Computer Sciences

Although the support vector machine (SVM) algorithm has a high generalization property for classifying unseen examples after the training phase~and a small loss value, the algorithm is not suitable for real-life classification and regression problems. SVMs cannot solve hundreds of thousands of examples in a training dataset. In previous studies on distributed machine-learning algorithms, the SVM was trained in a costly and preconfigured computer environment. In this research, we present a MapReduce-based distributed parallel SVM training algorithm for binary classification problems. This work shows how to distribute optimization problems over cloud computing systems with the MapReduce technique. In the second …

Removal Of Impulse Noise In Digital Images With Na\"Ive Bayes Classifier Method, Cafer Budak, Mustafa Türk, Abdullah Toprak

Turkish Journal of Electrical Engineering and Computer Sciences

No abstract provided.

Harnessing The Power Of Text Mining For The Detection Of Abusive Content In Social Media, Hao Chen, Susan Mckeever, Sarah Jane Delany

Conference papers

Abstract The issues of cyberbullying and online harassment have gained considerable coverage in the last number of years. Social media providers need to be able to detect abusive content both accurately and efficiently in order to protect their users. Our aim is to investigate the application of core text mining techniques for the automatic detection of abusive content across a range of social media sources include blogs, forums, media-sharing, Q&A and chat - using datasets from Twitter, YouTube, MySpace, Kongregate, Formspring and Slashdot. Using supervised machine learning, we compare alternative text representations and dimension reduction approaches, including feature selection and …

Mathematical Foundations Of Sentiment Classification : A Probabilistic Approach, Syed Shahzad Raza

Legacy Theses & Dissertations (2009 - 2024)

This thesis is an introduction to the mathematical formalization of sentiment classification. It presents two popular probabilistic machine learning models to classify tweets downloaded from Twitter during the US Election Period, 2016. The thesis analyses accuracy of the two classification algorithms used. Namely, Multinomial Naïve Bayes and Bernoulli Naïve Bayes algorithms. Supervised learning approaches implemented in this thesis use approximately 600 manually labeled tweets containing information regarding the US presidential candidates. It is shown with 80% accuracy that majority of twitter users spoke in favor of Donald Trump before and after the presidential election through their tweets. We also discuss …

Vehicle Engine Classification Using Of Laser Vibrometry Feature Extraction, Chi Him Liu

Dissertations and Theses

Used as a non-invasive and remote sensor, the laser Doppler vibrometer (LDV) has been used in many different applications, such as inspection of aircrafts, bridge and structure and remote voice acquisition. However, using LDV as a vehicle surveillance device has not been feasible due to the lack of systematic investigations on its behavioral properties. In this thesis, the LDV data from different vehicles are examined and features are extracted. A tone-pitch indexing (TPI) scheme is developed to classify different vehicles by exploiting the engine’s periodic vibrations that are transferred throughout the vehicle’s body. Using the TPI with a two-layer feed-forward …

An Investigation Into Off-Link Ipv6 Host Enumeration Search Methods, Clinton Carpene

Theses: Doctorates and Masters

This research investigated search methods for enumerating networked devices on off-link 64 bit Internet Protocol version 6 (IPv6) subnetworks. IPv6 host enumeration is an emerging research area involving strategies to enable detection of networked devices on IPv6 networks. Host enumeration is an integral component in vulnerability assessments (VAs), and can be used to strengthen the security profile of a system. Recently, host enumeration has been applied to Internet-wide VAs in an effort to detect devices that are vulnerable to specific threats. These host enumeration exercises rely on the fact that the existing Internet Protocol version 4 (IPv4) can be exhaustively …

Eeg Interictal Spike Detection Using Artificial Neural Networks, Howard J. Carey Iii

Theses and Dissertations

Epilepsy is a neurological disease causing seizures in its victims and affects approximately 50 million people worldwide. Successful treatment is dependent upon correct identification of the origin of the seizures within the brain. To achieve this, electroencephalograms (EEGs) are used to measure a patient’s brainwaves. This EEG data must be manually analyzed to identify interictal spikes that emanate from the afflicted region of the brain. This process can take a neurologist more than a week and a half per patient. This thesis presents a method to extract and process the interictal spikes in a patient, and use them to reduce …

Forecasting Customer Electricity Load Demand In The Power Trading Agent Competition Using Machine Learning, Saiful Abu

Open Access Theses & Dissertations

Accurate electricity load demand forecasting is an important problem in managing the power grid for both economic and environmental reasons. The Power TAC simulation provides a platform to do research on smart grid energy generation and distribution systems. Brokers are the focus of the design task posed to developers by the system. The brokers work as self-interested entities that try to maximize profits by trading electricity across multiple markets. To be successful, a broker has to forecast the electricity demand for customers as accurately as possible so it can use this information to operate efficiently. My proposed forecasting method uses …

Mining Human Activity Using Dimensionality Reduction And Pattern Recognition, Ismail El Moudden, Mounir Ouzir, Badreddine Benyacoub, Souad El Bernoussi

Research and Infrastructure Service Enterprise (RISE) Faculty Publications

Human activity recognition (HAR) is an emerging research topic in pattern recognition, especially in computer vision. The main objective of human activity recognition is to automatically detect and analyze human activities from the information acquired from different sensors. Human activity prediction using big data remains a challengingly open problem. Several approaches have recently been developed in order to find practical ways to solve high dimensionality of data problems. The aim of this study is to attempt, using data mining techniques, to deal with HAR modeling involving a significant number of variables in order to identify relevant parameters from data and …

Using Tourmaline As An Indicator Of Provenance: Development And Application Of A Statistical Approach Using Random Forests, Erin Lael Walden

LSU Master's Theses

Tourmaline is a petrologic indicator mineral that is the major repository of boron in the earth’s crust. It forms readily when boron is present, accommodating multiple cations and anions with multiple possible substitutions for each site in the crystal structure. It is stable over a wide variety of pressures and temperatures, from near-surface P/T conditions to greater than 950 C and 7 GPa. It records information about conditions of formation, as well as pressure and temperature. Due to its resistance to chemical or physical weathering, and the negligible diffusion of elements in the crystal lattice, information about provenance is preserved. …

Novel Machine Learning Methods For Modeling Time-To-Event Data, Bhanukiran Vinzamuri

Wayne State University Dissertations

Predicting time-to-event from longitudinal data where different events occur at different time points is an extremely important problem in several domains such as healthcare, economics, social networks and seismology, to name a few. A unique challenge in this problem involves building predictive models from right censored data (also called as survival data). This is a phenomenon where instances whose event of interest are not yet observed within a given observation time window and are considered to be right censored. Effective models for predicting time-to-event labels from such right censored data with good accuracy can have a significant impact in these …

A Comparison Of Fundamental Network Formation Principles Between Offline And Online Friends On Twitter, Felicia Natali, Feida Zhu

Research Collection School Of Computing and Information Systems

We investigate the differences between how some of the fundamental principles of network formation apply among offline friends and how they apply among online friends on Twitter. We consider three fundamental principles of network formation proposed by Schaefer et al.: reciprocity, popularity, and triadic closure. Overall, we discover that these principles mainly apply to offline friends on Twitter. Based on how these principles apply to offline versus online friends, we formulate rules to predict offline friendship on Twitter. We compare our algorithm with popular machine learning algorithms and Xiewei’s random walk algorithm. Our algorithm beats the machine learning algorithms on …

A Data Science Course For Undergraduates: Thinking With Data, Benjamin Baumer

Mathematics Sciences: Faculty Publications

Data science is an emerging interdisciplinary field that combines elements of mathematics, statistics, computer science, and knowledge in a particular application domain for the purpose of extracting meaningful information from the increasingly sophisticated array of data available in many settings. These data tend to be nontraditional, in the sense that they are often live, large, complex, and/or messy. A first course in statistics at the undergraduate level typically introduces students to a variety of techniques to analyze small, neat, and clean datasets. However, whether they pursue more formal training in statistics or not, many of these students will end up …

The Performance Of Random Prototypes In Hierarchical Models Of Vision, Kendall Lee Stewart

Dissertations and Theses

I investigate properties of HMAX, a computational model of hierarchical processing in the primate visual cortex. High-level cortical neurons have been shown to respond highly to particular natural shapes, such as faces. HMAX models this property with a dictionary of natural shapes, called prototypes, that respond to the presence of those shapes. The resulting set of similarity measurements is an effective descriptor for classifying images. Curiously, prior work has shown that replacing the dictionary of natural shapes with entirely random prototypes has little impact on classification performance. This work explores that phenomenon by studying the performance of random prototypes on …

Dynamic Data Management In A Data Grid Environment, Björn Barrefors

School of Computing: Dissertations, Theses, and Student Research

A data grid is a geographically distributed set of resources providing a facility for computationally intensive analysis of large datasets to a large number of geographically distributed users. In the scientific community, data grids have become increasingly popular as scientific research is driven by large datasets. Until recently, developments in data management for data grids have focused on management of data at lower layers in the data grid architecture. With dataset sizes expected to approach exabyte scale in coming years, data management in data grids are facing a new set of challenges. In particularly, the problem of automatically placing and …

Energy Forecasting For Event Venues: Big Data And Prediction Accuracy, Katarina Grolinger, Alexandra L'Heureux, Miriam Am Capretz, Luke Seewald

Electrical and Computer Engineering Publications

Advances in sensor technologies and the proliferation of smart meters have resulted in an explosion of energy-related data sets. These Big Data have created opportunities for development of new energy services and a promise of better energy management and conservation. Sensor-based energy forecasting has been researched in the context of office buildings, schools, and residential buildings. This paper investigates sensor-based forecasting in the context of event-organizing venues, which present an especially difficult scenario due to large variations in consumption caused by the hosted events. Moreover, the significance of the data set size, specifically the impact of temporal granularity, on energy …

Evaluating The Intrinsic Similarity Between Neural Networks, Stephen Charles Ashmore

Graduate Theses and Dissertations

We present Forward Bipartite Alignment (FBA), a method that aligns the topological structures of two neural networks. Neural networks are considered to be a black box, because neural networks contain complex model surface determined by their weights that combine attributes non-linearly. Two networks that make similar predictions on training data may still generalize differently. FBA enables a diversity of applications, including visualization and canonicalization of neural networks, ensembles, and cross-over between unrelated neural networks in evolutionary optimization. We describe the FBA algorithm, and describe implementations for three applications: genetic algorithms, visualization, and ensembles. We demonstrate FBA's usefulness by comparing a …

Analyzing Repetitive Sequences With Structured Dynamic Bayesian Networks, Thomas. L. Lake

Masters Theses

Time series often feature structure that is known a priori and easily described using natural language terms such as repetitive, symmetric, seasonal, and self-similar. However, the typical conjugate priors used in Bayesian analysis do not capture such complex phenomena well. As a result of this mismatch, known structure is modeled poorly or completely ignored. Focusing on time series with repetitive structure, this thesis proposes to overcome this problem by reducing rather than in- creasing the capacity of a well know time series model, the Hidden Markov Model. Through a careful choice in the way model capacity is reduced the model …

Distributed Approach For Peptide Identification, Naga V K Abhinav Vedanbhatla

Masters Theses & Specialist Projects

A crucial step in protein identification is peptide identification. The Peptide Spectrum Match (PSM) information set is enormous. Hence, it is a time-consuming procedure to work on a single machine. PSMs are situated by a cross connection, a factual score, or a probability that the match between the trial and speculative is right and original. This procedure takes quite a while to execute. So, there is demand for enhancement of the performance to handle extensive peptide information sets. Development of appropriate distributed frameworks are expected to lessen the processing time.

The designed framework uses a peptide handling algorithm named C-Ranker, …

Learning Relative Similarity From Data Streams: Active Online Learning Approaches, Shuji Hao, Peilin Zhao, Steven C. H. Hoi, Chunyan Miao

Research Collection School Of Computing and Information Systems

Relative similarity learning, as an important learning scheme for information retrieval, aims to learn a bi-linear similarity function from a collection of labeled instance-pairs, and the learned function would assign a high similarity value for a similar instance-pair and a low value for a dissimilar pair. Existing algorithms usually assume the labels of all the pairs in data streams are always made available for learning. However, this is not always realistic in practice since the number of possible pairs is quadratic to the number of instances in the database, and manually labeling the pairs could be very costly and time …

Detecting, Modeling, And Predicting User Temporal Intention, Hany M. Salaheldeen

Computer Science Theses & Dissertations

The content of social media has grown exponentially in the recent years and its role has evolved from narrating life events to actually shaping them. Unfortunately, content posted and shared in social networks is vulnerable and prone to loss or change, rendering the context associated with it (a tweet, post, status, or others) meaningless. There is an inherent value in maintaining the consistency of such social records as in some cases they take over the task of being the first draft of history as collections of these social posts narrate the pulse of the street during historic events, protest, riots, …