Artificial Intelligence and Robotics Commons^™

Concatenative Synthesis For Novel Timbral Creation, James Eric Bilous

Master's Theses

Modern day musicians rely on a variety of instruments for musical expression. Tones produced from electronic instruments have become almost as commonplace as those produced by traditional ones as evidenced by the plethora of artists who can be found composing and performing with nothing more than a personal computer. This desire to embrace technical innovation as a means to augment performance art has created a budding field in computer science that explores the creation and manipulation of sound for artistic purposes. One facet of this new frontier concerns timbral creation, or the development of new sounds with unique characteristics that …

Supervised Learning For Multi-Domain Text Classification, Siva Charan Reddy Gangireddy

Master's Projects

Digital information available on the Internet is increasing day by day. As a result of this, the demand for tools that help people in finding and analyzing all these resources are also growing in number. Text Classification, in particular, has been very useful in managing the information. Text Classification is the process of assigning natural language text to one or more categories based on the content. It has many important applications in the real world. For example, finding the sentiment of the reviews, posted by people on restaurants, movies and other such things are all applications of Text classification. In …

Categorizing Blog Spam, Brandon Bevans

Master's Theses

The internet has matured into the focal point of our era. Its ecosystem is vast, complex, and in many regards unaccounted for. One of the most prevalent aspects of the internet is spam. Similar to the rest of the internet, spam has evolved from simply meaning ‘unwanted emails’ to a blanket term that encompasses any unsolicited or illegitimate content that appears in the wide range of media that exists on the internet.

Many forms of spam permeate the internet, and spam architects continue to develop tools and methods to avoid detection. On the other side, cyber security engineers continue to …

Multi Faceted Text Classification Using Supervised Machine Learning Models, Abhiteja Gajjala

Master's Projects

In recent year’s document management tasks (known as information retrieval) increased a lot due to availability of digital documents everywhere. The need of automatic methods for extracting document information became a prominent method for organizing information and knowledge discovery. Text Classification is one such solution, where in the natural language text is assigned to one or more predefined categories based on the content. In my research classification of text is mainly focused on sentiment label classification. The idea proposed for sentiment analysis is multi-class classification of online movie reviews. Many research papers discussed the classification of sentiment either positive or …

Dual Formulations For Optimizing Dec-Pomdp Controllers, Akshat Kumar, Hala Mostafa, Shlomo Zilberstein

Research Collection School Of Computing and Information Systems

Decentralized POMDP is an expressive model for multi-agent planning. Finite-state controllers (FSCs)---often used to represent policies for infinite-horizon problems---offer a compact, simple-to-execute policy representation. We exploit novel connections between optimizing decentralized FSCs and the dual linear program for MDPs. Consequently, we describe a dual mixed integer linear program (MIP) for optimizing deterministic FSCs. We exploit the Dec-POMDP structure to devise a compact MIP and formulate constraints that result in policies executable in partially-observable decentralized settings. We show analytically that the dual formulation can also be exploited within the expectation maximization (EM) framework to optimize stochastic FSCs. The resulting EM algorithm …

Self-Organizing Neural Network For Adaptive Operator Selection In Evolutionary Search, Teck Hou Teng, Stephanus Daniel Handoko, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Evolutionary Algorithm is a well-known meta-heuristics paradigm capable of providing high-quality solutions to computationally hard problems. As with the other meta-heuristics, its performance is often attributed to appropriate design choices such as the choice of crossover operators and some other parameters. In this chapter, we propose a continuous state Markov Decision Process model to select crossover operators based on the states during evolutionary search. We propose to find the operator selection policy efficiently using a self-organizing neural network, which is trained offline using randomly selected training samples. The trained neural network is then verified on test instances not used for …

Designing And Comparing Multiple Portfolios Of Parameter Configurations For Online Algorithm Selection, Aldy Gunawan, Hoong Chuin Lau, Mustafa Misir

Research Collection School Of Computing and Information Systems

Algorithm portfolios seek to determine an effective set of algorithms that can be used within an algorithm selection framework to solve problems. A limited number of these portfolio studies focus on generating different versions of a target algorithm using different parameter configurations. In this paper, we employ a Design of Experiments (DOE) approach to determine a promising range of values for each parameter of an algorithm. These ranges are further processed to determine a portfolio of parameter configurations, which would be used within two online Algorithm Selection approaches for solving different instances of a given combinatorial optimization problem effectively. We …

Strategic Planning For Setting Up Base Stations In Emergency Medical Systems, Supriyo Ghosh, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Emergency Medical Systems (EMSs) are an important component of public health-care services. Improving infrastructure for EMS and specifically the construction of base stations at the ”right” locations to reduce response times is the main focus of this paper. This is a computationally challenging task because of the: (a) exponentially large action space arising from having to consider combinations of potential base locations, which themselves can be significant; and (b) direct impact on the performance of the ambulance allocation problem, where we decide allocation of ambulances to bases. We present an incremental greedy approach to discover the placement of bases that …

Serendipity-Driven Celebrity Video Hyperlinking, Shujun Yang, Lei Pang, Chong-Wah Ngo, Benoit Huet

Research Collection School Of Computing and Information Systems

This demo showcases the utility of video hyperlinks with celebrities as the link anchors and their social circles as targets, aiming to help users quickly explore the aboutness of a celebrity by link traversal. Through content analysis, our system embeds hyperlinks into videos such that users can click-and-jump between celebrity faces in different videos to get-to-know their social circles. One peculiar feature is the ability of the system in providing links that maximize users' chance encounter, or serendipitous experience, beyond information need. Our system is enabled by two key components, name-face association and diversity-based ranking, for the aboutness and serendipity …

Exemplar-Driven Top-Down Saliency Detection Via Deep Association, Shengfeng He, Rynson W. H. Lau, Qingxiong Yang

Research Collection School Of Computing and Information Systems

Top-down saliency detection is a knowledge-driven search task. While some previous methods aim to learn this "knowledge" from category-specific data, others transfer existing annotations in a large dataset through appearance matching. In contrast, we propose in this paper a locateby-exemplar strategy. This approach is challenging, as we only use a few exemplars (up to 4) and the appearances among the query object and the exemplars can be very different. To address it, we design a two-stage deep model to learn the intra-class association between the exemplars and query objects. The first stage is for learning object-to-object association, and the second …

Movie Script Shot Lister, David Robert Smith

Master's Projects

The making of a motion picture almost always starts with the script, the written version of a story envisioned within the mind of its creator. The script is then broken down into shots. Each individual shot is filmed and then they are edited together to create the motion picture. The goal of the Movie Script Shot Lister thesis project is to be able to read in a script for a movie or television show, and automatically generate a shot list. While a script is text, a shot list is the blue print for how to visualize that script, so the …

Multiple Sequence Alignment With Pro Le Hidden Markov Models, Shubhangi Rakhonde

Master's Projects

The human genome consists of various patterns and sequences that are of biolog- ical signi cance. Capturing these patterns can help us in resolving various mysteries related to the genome, like how genomes evolve, how diseases occur due to genetic mutation, how viruses mutate to cause new disease and what is the cure for these diseases. All these applications are covered in the study of bioinformatics.

One of the very common tasks in bioinformatics involves simultaneous alignment of a number of biological sequences. In bioinformatics, this is widely known as Mul- tiple Sequence Alignment. Multiple sequence alignments help in grouping …

Hive - An Agent Based Modeling Framework, Roohi Bharti

Master's Projects

This thesis begins by defining agent based modeling. Agent based models are used to model the emergent behavior of complex systems with many interacting components, known as agents. Several model examples are given using NetLogo, which is a popular agent-based modeling platform. A model of concurrent computation is described that uses message passing as the only form of communication between the model’s components, which are called actors. The model is called an actor model. Actors are primitive objects of concurrency in an actor model. In particular, we describe the actor model implemented by Akka, which is Scala’s new actor library. …

Automatic Classification Of Perceived Gender From Face Images, Joseph Lemley, Sami Abdul-Wahid, Dipayan Banik

Symposium Of University Research and Creative Expression (SOURCE)

Building software that can visually and accurately perceive gender from face images is an important step in making more intelligent machines. Several approaches to this problem have been suggested in the literature. We evaluate Histogram of Oriented Gradients, Dual Tree Complex Wavelet Transform (DTCWT) Principal Component Analysis (PCA) with Support Vector Machines (SVM) and compare them to Convolutional Neural Networks for this task. We train and test our classifiers with two benchmarks containing thousands of facial images. As expected, convolutional neural networks had the best performance while the performance of DTCWT varied most depending on the dataset used

Applying Machine Learning To Predict Stock Value, Joseph Lemley, Yishui Liu, Dipayan Banik, Sadia Afroze

Symposium Of University Research and Creative Expression (SOURCE)

The purpose of this study was to compare machine learning techniques for short term stock prediction and evaluate their effectiveness. Stock value analysis is an important element of modern economies. The ability to predict future stock prices from historical price values is of tremendous interest to investors. The prediction of stock performance is still an unsolved problem with a variety of techniques being proposed. Real stock values are affected by many elements, some of which cannot be measured. In this study, we limit our analysis to stock closing prices. We use these prices to predict the future stock value using …

Detection Of Locations Of Key Points On Facial Images, Manoj Gyanani

Master's Projects

In field of computer vision research, One of the most important branch is Face recognition. It targets at finding size and location of human face on digital image, by identifying and separating faces from the surrounding objects like building, plants etc. For the purpose of developing an advanced face recognition algorithm, Detection of facial key points is the basic and very important task, basically it is about finding out the location of specific key points on facial images. This key points can be mouths, noses, left eyes, right eyes and so on.

For implementation of solution, I have used amazon …

Automatically Characterizing Product And Process Incentives In Collective Intelligence, Allen Brockhurst Lavoie

McKelvey School of Engineering Graduate Student Theses & Dissertations

Social media facilitate interaction and information dissemination among an unprecedented number of participants. Why do users contribute, and why do they contribute to a specific venue? Does the information they receive cover all relevant points of view, or is it biased? The substantial and increasing importance of online communication makes these questions more pressing, but also puts answers within reach of automated methods. I investigate scalable algorithms for understanding two classes of incentives which arise in collective intelligence processes. Product incentives exist when contributors have a stake in the information delivered to other users. I investigate product-relevant user behavior changes, …

Texture Modelling Using Convolutional Neural Networks, Leon A. Gatys, Alexander S. Ecker, Matthias Bethge

MODVIS Workshop

We introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layers of the network. We show that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit. Extending this framework to texture transfer, we introduce A Neural Algorithm of Artistic Style that …

Focusing On Selection For Fixation, John K. Tsotsos, Calden Wloka, Yulia Kotseruba

MODVIS Workshop

Building on our presentation at MODVIS 2015, we continue in our quest to discover a functional, computational, explanation of the relationship among visual attention, interpretation of visual stimuli, and eye movements, and how these produce visual behavior. Here, we focus on one component, how selection is accomplished for the next fixation. The popularity of saliency map models drives the inference that this is solved; we suggested otherwise at MODVIS 2015. Here, we provide additional empirical and theoretical arguments. We then develop arguments that a cluster of complementary, conspicuity representations drive selection, modulated by task goals and history, leading to a …

Collecting Image Cropping Dataset: A Hybrid System Of Machine And Human Intelligence, Uyen T. Mai, Feng Liu

Student Research Symposium

Image cropping is a common tool that exists in almost any image editor, yet automatic cropping is still a difficult problem in Computer Vision. Since images nowadays can be easily collected through the web, machine learning is a promising approach to solve this problem. However, an image cropping dataset is not yet available and gathering such a large-scale dataset is a non-trivial task. Although a crowdsourcing website such as Mechanical Turk seems to be a solution to this task, image cropping is a sophisticated task that is vulnerable to unreliable annotation; furthermore, collecting a large-scale high-quality dataset through crowdsourcing is …

Ant Colony Optimization For Continuous Spaces, Rachel Findley

Computer Science and Computer Engineering Undergraduate Honors Theses

Ant Colony Optimization (ACO) is an optimization algorithm designed to find semi-optimal solutions to Combinatorial Optimization Problems. The challenge of modifying this algorithm to effectively optimize over a continuous domain is one that has been tackled by several researchers. In this paper, ACO has been modified to use several variations of the algorithm for continuous spaces. An aspect of ACO which is crucial to its success when optimizing over a continuous space is choosing the appropriate object (solution component) out of an infinite set to add to the ant's path. This step is highly important in shaping good solutions. Important …

Improving Electroencephalography-Based Imagined Speech Recognition With A Simultaneous Video Data Stream, Sarah J. Stolze

Computer Science and Computer Engineering Undergraduate Honors Theses

Electroencephalography (EEG) devices offer a non-invasive mechanism for implementing imagined speech recognition, the process of estimating words or commands that a person expresses only in thought. However, existing methods can only achieve limited predictive accuracy with very small vocabularies; and therefore are not yet sufficient to enable fluid communication between humans and machines. This project proposes a new method for improving the ability of a classifying algorithm to recognize imagined speech recognition, by collecting and analyzing a large dataset of simultaneous EEG and video data streams. The results from this project suggest confirmation that complementing high-dimensional EEG data with similarly …

Inferring Intrinsic Beliefs Of Digital Images Using A Deep Autoencoder, Seok H. Lee

Computer Science and Computer Engineering Undergraduate Honors Theses

Training a system of artificial neural networks on digital images is a big challenge. Often times digital images contain a large amount of information and values for artificial neural networks to understand. In this work, the inference model is proposed in order to absolve this problem. The inference model is composed of a parameterized autoencoder that endures the loss of information caused by the rescaling of images and transition model that predicts the effect of an action on the observation. To test the inference model, the images of a moving robotic arm were given as the data set. The inference …

Two-Player Game Ai, Hunter Noble, Ashraf Aly

Celebration of Student Scholarship Poster Sessions Archive

No abstract provided.

Evaluation Of Topic Models For Content-Based Popularity Prediction On Social Microblogs, Axel Magnuson

Boise State University Theses and Dissertations

Online social networks are an increasingly central medium of communication in the 21st century. We have seen a proliferation of competing social networks which differentiate themselves by serving different niches of communication. Among these, Twitter has risen to prominence as a leader among microblogging communities, characterized by publicly visible 140-character messages called tweets. The wide visibility of Twitter messages has enabled some users to curate large followings, and has facilitated content creators who wish to reach as many viewers as possible. Researchers have since investigated many methods for predicting which messages will become popular or even go viral on Twitter. …

Efficient Algorithms For Clustering Polygonal Obstacles, Sabbir Kumar Manandhar

UNLV Theses, Dissertations, Professional Papers, and Capstones

Clustering a set of points in Euclidean space is a well-known problem having applications in pattern recognition, document image analysis, big-data analytics, and robotics. While there are a lot of research publications for clustering point objects, only a few articles have been reported for clustering a given distribution of obstacles. In this thesis we examine the development of efficient algorithms for clustering a given set of convex obstacles in the 2D plane. One of the methods presented in this work uses a Voronoi diagram to extract obstacle clusters. We also consider the implementation issues of point/obstacle clustering algorithms.

Simultaneous Optimization And Sampling Of Agent Trajectories Over A Network, Hala Mostafa, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We study the problem of optimizing the trajectories of agents moving over a network given their preferences over which nodes to visit subject to operational constraints on the network. In our running example, a theme park manager optimizes which attractions to include in a day-pass to maximize the pass’s appeal to visitors while keeping operational costs within budget. The first challenge in this combinatorial optimization problem is that it involves quantities (expected visit frequencies of each attraction) that cannot be expressed analytically, for which we use the Sample Average Approximation. The second challenge is that while sampling is typically done …

Approximate Inference Using Dc Programming For Collective Graphical Models, Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau, Daniel Sheldon

Research Collection School Of Computing and Information Systems

Collective graphical models (CGMs) provide a framework for reasoning about a population of independent and identically distributed individuals when only noisy and aggregate observations are given. Previous approaches for inference in CGMs work on a junction-tree representation, thereby highly limiting their scalability. To remedy this, we show how the Bethe entropy approximation naturally arises for the inference problem in CGMs. We reformulate the resulting optimization problem as a difference-of-convex functions program that can capture different types of CGM noise models. Using the concave-convex procedure, we then develop a scalable message-passing algorithm. Empirically, our approach is highly scalable and accurate for …

Reinforcement Learning Framework For Modeling Spatial Sequential Decisions Under Uncertainty: (Extended Abstract), Truc Viet Le, Siyuan Liu, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We consider the problem of trajectory prediction, where a trajectory is an ordered sequence of location visits and corresponding timestamps. The problem arises when an agent makes sequential decisions to visit a set of spatial locations of interest. Each location bears a stochastic utility and the agent has a limited budget to spend. Given the agent's observed partial trajectory, our goal is to predict the remaining trajectory. We propose a solution framework to the problem considering both the uncertainty of utility and the budget constraint. We use reinforcement learning (RL) to model the underlying decision processes and inverse RL to …

Robust Influence Maximization, Meghna Lowalekar, Pradeep Varakantham, Akshat Kumar

Research Collection School Of Computing and Information Systems

Influence Maximization is the problem of finding a fixed size set of nodes, which will maximize the expected number of influenced nodes in a social network. The number of influenced nodes is dependent on the influence strength of edges that can be very noisy. The noise in the influence strengths can be modeled using a random noise or adversarial noise model. It has been shown that all random processes that independently affect edges of the graph can be absorbed into the activation probabilities themselves and hence random noise can be captured within the independent cascade model. On the other hand, …