Computer Sciences Commons^™

A Comprehensive Framework To Replicate Process-Level Concurrency Faults, Supat Rattanasuksun

Department of Computer Science and Engineering: Dissertations, Theses, and Student Research

Concurrency faults are one of the most damaging types of faults that can affect the dependability of today’s computer systems. Currently, concurrency faults such as process-level races, order violations, and atomicity violations represent the largest class of faults that has been reported to various Linux bug repositories. Clearly, existing approaches for testing such faults during software development processes are not adequate as these faults escape in-house testing efforts and are discovered during deployment and must be debugged.

The main reason concurrency faults are hard to test is because the conditions that allow these to occur can be difficult to replicate, …

Game-Theoretic And Machine-Learning Techniques For Cyber-Physical Security And Resilience In Smart Grid, Longfei Wei

FIU Electronic Theses and Dissertations

The smart grid is the next-generation electrical infrastructure utilizing Information and Communication Technologies (ICTs), whose architecture is evolving from a utility-centric structure to a distributed Cyber-Physical System (CPS) integrated with a large-scale of renewable energy resources. However, meeting reliability objectives in the smart grid becomes increasingly challenging owing to the high penetration of renewable resources and changing weather conditions. Moreover, the cyber-physical attack targeted at the smart grid has become a major threat because millions of electronic devices interconnected via communication networks expose unprecedented vulnerabilities, thereby increasing the potential attack surface. This dissertation is aimed at developing novel game-theoretic and …

Modeling Contemporaneous Basket Sequences With Twin Networks For Next-Item Recommendation, Duc Trong Le, Hady W. Lauw, Yuan Fang

Research Collection School Of Computing and Information Systems

Our interactions with an application frequently leave a heterogeneous and contemporaneous trail of actions and adoptions (e.g., clicks, bookmarks, purchases). Given a sequence of a particular type (e.g., purchases)-- referred to as the target sequence, we seek to predict the next item expected to appear beyond this sequence. This task is known as next-item recommendation. We hypothesize two means for improvement. First, within each time step, a user may interact with multiple items (a basket), with potential latent associations among them. Second, predicting the next item in the target sequence may be helped by also learning from another supporting sequence …

A Bayesian Latent Variable Model Of User Preferences With Item Context, Aghiles Salah, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Personalized recommendation has proven to be very promising in modeling the preference of users over items. However, most existing work in this context focuses primarily on modeling user-item interactions, which tend to be very sparse. We propose to further leverage the item-item relationships that may reflect various aspects of items that guide users’ choices. Intuitively, items that occur within the same “context” (e.g., browsed in the same session, purchased in the same basket) are likely related in some latent aspect. Therefore, accounting for the item’s context would complement the sparse user-item interactions by extending a user’s preference to other items …

Online Deep Learning: Learning Deep Neural Networks On The Fly, Doyen Sahoo, Hong Quang Pham, Jing Lu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch setting, requiring the entire training data to be made available prior to the learning task. This is not scalable for many real-world scenarios where new data arrives sequentially in a stream. We aim to address an open challenge of “Online Deep Learning” (ODL) for learning DNNs on the fly in an online setting. Unlike traditional online learning that often optimizes some convex objective function with respect to a shallow model (e.g., a linear/kernel-based hypothesis), ODL is more challenging as the optimization objective is non-convex, and regular DNN with …

Mind The Gap: Situated Spatial Language A Case-Study In Connecting Perception And Language, John D. Kelleher

Other

This abstract reviews the literature on computational models of spatial semantics and the potential of deep learning models as an useful approach to this challenge.

An Investigation Into The Effects Of Multiple Kernel Combinations On Solutions Spaces In Support Vector Machines, Paul Kelly, Luca Longo

Conference papers

The use of Multiple Kernel Learning (MKL) for Support Vector Machines (SVM) in Machine Learning tasks is a growing field of study. MKL kernels expand on traditional base kernels that are used to improve performance on non-linearly separable datasets. Multiple kernels use combinations of those base kernels to develop novel kernel shapes that allow for more diversity in the generated solution spaces. Customising these kernels to the dataset is still mostly a process of trial and error. Guidelines around what combinations to implement are lacking and usually they requires domain specific knowledge and understanding of the data. Through a brute …

A Legal Perspective On The Trials And Tribulations Of Ai: How Artificial Intelligence, The Internet Of Things, Smart Contracts, And Other Technologies Will Affect The Law, Iria Giuffrida, Fredric Lederer, Nicolas Vermeys

Faculty Publications

No abstract provided.

Machine Learning And Threat Intelligence, Jacob Vangore

Student Scholarship – Computer Science

Machine learning plays a role in a wide variety of fields. It can be used for predicting stock prices, identifying diseases, and even teaching Mario how to avoid mushrooms. This project explores the use of machine learning in realm of threat intelligence. There are many sources for professionals to keep up to date on the latest threats to software (NVD, PacketStorm, Twitter, etc.). However, it can become over cumbersome for individuals to monitor all of these sources manually. Building an automated string match system is a good first step to tackle this problem, but many false positives may be returned. …

Non-Linear Machine Learning With Active Sampling For Mox Drift Compensation, Tamara Matthews, Muhammad Iqbal, Horacio Gonzalez-Velez

Conference papers

Abstract—Metal oxide (MOX) gas detectors based on SnO2 provide low-cost solutions for real-time sensing of complex gas mixtures for indoor ambient monitoring. With high sensitivity under ideal conditions, MOX detectors may have poor longterm response accuracy due to environmental factors (humidity and temperature) along with sensor aging, leading to calibration drifts. Finding a simple and efficient solution to correct such calibration drifts has been the subject of numerous studies but remains an open problem. In this work, we present an efficient approach to MOX calibration using active and transfer sampling techniques coupled with non-linear machine learning algorithms, namely neural networks, …

Fuzziness-Based Active Learning Framework To Enhance Hyperspectral Image Classification Performance For Discriminative And Generative Classifiers, Muhammad Ahmad, Stanislav Protasov, Adil Mehmood Khan, Rasheed Hussain, Asad Masood Khattak, Wajahat Ali Khan

All Works

© 2018 Ahmad et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said problem, we propose a fuzziness-based active learning framework (FALF), in which we implement the idea of selecting optimal …

Generating Diverse And Meaningful Captions: Unsupervised Specificity Optimization For Image Captioning, Annika Lindh, Robert J. Ross, Abhijit Mahalunkar, Giancarlo Salton, John D. Kelleher

Conference papers

Image Captioning is a task that requires models to acquire a multi-modal understanding of the world and to express this understanding in natural language text. While the state-of-the-art for this task has rapidly improved in terms of n-gram metrics, these models tend to output the same generic captions for similar images. In this work, we address this limitation and train a model that generates more diverse and specific captions through an unsupervised training approach that incorporates a learning signal from an Image Retrieval model. We summarize previous results and improve the state-of-the-art on caption diversity and novelty.

We make our …

Development Of An Electronic Nose For Olfactory System Modelling Using Artificial Neural Network, Proceso L. Fernandez Jr, Mary Anne Sy Roa

Department of Information Systems & Computer Science Faculty Publications

Electronic nose (e-nose) devices have received considerable attention in the field of sensor technology because of their many potential uses such as in identification of toxic wastes, monitoring air quality, examining odors in infected wounds and in inspection of food. Notwithstanding the vast amount of literature on the usage of e-noses for specific purposes, the technology originally and ultimately aims to mimic the capability of mammals to discriminate odors from all sorts of objects. This study demonstrates the theoretical and practical feasibility of designing an e-nose towards general odor classification. A multi-sensor array hardware unit was carefully constructed for data …

Artificial Neural Network (Ann) In A Small Dataset To Determine Neutrality In The Pronunciation Of English As A Foreign Language In Filipino Call Center Agents, Proceso L. Fernandez Jr, Rey Benjamin M. Baquirin

Department of Information Systems & Computer Science Faculty Publications

Artificial Neural Networks (ANNs) have continued to be efficient models in solving classification problems. In this paper, we explore the use of an ANN with a small dataset to accurately classify whether Filipino call center agents’ pronunciations are neutral or not based on their employer’s standards. Isolated utterances of the ten most commonly used words in the call center were recorded from eleven agents creating a dataset of 110 utterances. Two learning specialists were consulted to establish ground truths and Cohen’s Kappa was computed as 0.82, validating the reliability of the dataset. The first thirteen Mel-Frequency Cepstral Coefficients (MFCCs) were …

Support Vector Machines For Image Spam Analysis, Aneri Chavda, Katerina Potika, Fabio Di Troia, Mark Stamp

Faculty Publications, Computer Science

Email is one of the most common forms of digital communication. Spam is unsolicited bulk email, while image spam consists of spam text embedded inside an image. Image spam is used as a means to evade text-based spam filters, and hence image spam poses a threat to email-based communication. In this research, we analyze image spam detection using support vector machines (SVMs), which we train on a wide variety of image features. We use a linear SVM to quantify the relative importance of the features under consideration. We also develop and analyze a realistic “challenge” dataset that illustrates the limitations …