Physical Sciences and Mathematics Commons^™

Sparse Coding For Hyperspectral Images Using Random Dictionary And Soft Thresholding, Ender Oguslu, Khan Iftekharuddin, Jiang Li, Mark Allen Neifeld (Ed.), Amit Ashok (Ed.)

Electrical & Computer Engineering Faculty Publications

Many techniques have been recently developed for classification of hyperspectral images (HSI) including support vector machines (SVMs), neural networks and graph-based methods. To achieve good performances for the classification, a good feature representation of the HSI is essential. A great deal of feature extraction algorithms have been developed such as principal component analysis (PCA) and independent component analysis (ICA). Sparse coding has recently shown state-of-the-art performances in many applications including image classification. In this paper, we present a feature extraction method for HSI data motivated by a recently developed sparse coding based image representation technique. Sparse coding consists of a …

Scale Invariant Object Recognition Using Cortical Computational Models And A Robotic Platform, Danny Voils

Dissertations and Theses

This paper proposes an end-to-end, scale invariant, visual object recognition system, composed of computational components that mimic the cortex in the brain. The system uses a two stage process. The first stage is a filter that extracts scale invariant features from the visual field. The second stage uses inference based spacio-temporal analysis of these features to identify objects in the visual field. The proposed model combines Numenta's Hierarchical Temporal Memory (HTM), with HMAX developed by MIT's Brain and Cognitive Science Department. While these two biologically inspired paradigms are based on what is known about the visual cortex, HTM and HMAX …

Memristor-Based Reservoir Computing, Manjari S. Kulkarni

Dissertations and Theses

In today's nanoscale era, scaling down to even smaller feature sizes poses a significant challenge in the device fabrication, the circuit, and the system design and integration. On the other hand, nanoscale technology has also led to novel materials and devices with unique properties. The memristor is one such emergent nanoscale device that exhibits non-linear current-voltage characteristics and has an inherent memory property, i.e., its current state depends on the past. Both the non-linear and the memory property of memristors have the potential to enable solving spatial and temporal pattern recognition tasks in radically different ways from traditional binary transistor-based …

Model Individualization For Real-Time Operator Functional State Assessment, Guangfan Zhang, Roger Xu, Wei Wang, Aaron A. Pepe, Feng Li, Jiang Li, Frederick Mckenzie, Tom Schnell, Nick Anderson, Dean Heitkamp

Electrical & Computer Engineering Faculty Publications

Proper assessment of Operator Functional State (OFS) and appropriate workload modulation offer the potential to improve mission effectiveness and aviation safety in both overload and under-load conditions. Although a wide range of research has been devoted to building OFS assessment models, most of the models are based on group statistics and little or no research has been directed towards model individualization, i.e., tuning the group statistics based model for individual pilots. Moreover, little emphasis has been placed on monitoring whether the pilot is disengaged during low workload conditions. The primary focus of this research is to provide a real-time engagement …

Stigmergy 3.0: From Ants To Economies, Leslie Marsh, Margery Doyle

Leslie Marsh

No abstract provided.

Distinctive Neural Processes During Learning In Autism, Sarah Schipul, Diane Williams, Timothy Keller, Nancy Minshew, Marcel Just

Marcel Adam Just

No abstract provided.

Brain Activation For Language Dual-Tasking: Listening To Two People Speak At The Same Time And A Change In Network Timing, Augusto Buchweitz, Timothy Keller, Ann Meyler, Marcel Just

Marcel Adam Just

No abstract provided.

Autism As A Neural Systems Disorder: A Theory Of Frontal-Posterior Underconnectivity, Marcel Just, Timothy Keller, Vicente Malave, Rajesh Kana, Sashank Varma

Marcel Adam Just

No abstract provided.

An Fmri Investigation Of Analogical Mapping In Metaphor Comprehension: The Influence Of Context And Individual Cognitive Capacities On Processing Demands., Chantel Prat, Robert Mason, Marcel Just

Marcel Adam Just

No abstract provided.

Exploring Commonalities Across Participants In The Neural Representation Of Objects, Svetlana V. Shinkareva, Vicente L. Malave, Marcel Adam Just, Tom M. Mitchell

Marcel Adam Just

No abstract provided.

Identifying Bilingual Semantic Neural Representations Across Languages, Augusto Buchweitz, Svetlana V. Shinkareva, Robert A. Mason, Tom M. Mitchell, Marcel Adam Just

Marcel Adam Just

No abstract provided.

Efficient Method Of Visual Feature Extraction For Facial Image Detection And Retrieval, Sameem Abdul Kareem

Sameem Abdul Kareem

Due to the significant increase in the already huge collection of digital images that we have today, it has become imperative to find efficient methods for the archival and retrieval of these images. In this research, a content based human facial image detection and retrieval model is proposed for retrieving facial images of humans based on their visual content from an image database. The research proposes a technique of face segmentation based on which a new method of features extraction from the human face is devised. The capability and effectiveness of the color space models (RGB, HSV, and HSI) on …

Towards Succinctness In Mining Scenario-Based Specifications, David Lo, Shahar Maoz

David LO

Specification mining methods are used to extract candidate specifications from system execution traces. A major challenge for specification mining is succinctness. That is, in addition to the soundness, completeness, and scalable performance of the specification mining method, one is interested in producing a succinct result, which conveys a lot of information about the system under investigation but uses a short, machine and human-readable representation. In this paper we address the succinctness challenge in the context of scenario-based specification mining, whose target formalism is live sequence charts (LSC), an expressive extension of classical sequence diagrams. We do this by adapting three …

Drift Detection Using Uncertainty Distribution Divergence, Patrick Lindstrom, Brian Mac Namee, Sarah Jane Delany

Conference papers

Concept drift is believed to be prevalent inmost data gathered from naturally occurring processes andthus warrants research by the machine learning community.There are a myriad of approaches to concept drift handlingwhich have been shown to handle concept drift with varyingdegrees of success.

However, most approaches make the keyassumption that the labelled data will be available at nolabelling cost shortly after classification, an assumption whichis often violated. The high labelling cost in many domainsprovides a strong motivation to reduce the number of labelledinstances required to handle concept drift. Explicit detectionapproaches that do not require labelled instances to detectconcept drift show great …

Mobile Phone Graph Evolution: Findings, Model And Interpretation, Siyuan Liu, Lei Li, Christos Faloutsos, Lionel M. Ni

LARC Research Publications

What are the features of mobile phone graph along the time? How to model these features? What are the interpretation for the evolutional graph generation process? To answer the above challenging problems, we analyze a massive who-call-whom networks as long as a year, gathered from records of two large mobile phone communication networks both with 2 million users and 2 billion of calls. We examine the calling behavior distribution at multiple time scales (e.g. day, week, month and quarter), and find that the distribution is not only skewed with a heavy tail, but also changing at different time scales. How …

Capir: Collaborative Action Planning With Intention Recognition, Nguyen T., Hsu D., Lee W., Tze-Yun Leong, Kaelbling L., Lozano-Perez T., Grant A.

Research Collection School Of Computing and Information Systems

We apply decision theoretic techniques to construct nonplayer characters that are able to assist a human player in collaborative games. The method is based on solving Markov decision processes, which can be difficult when the game state is described by many variables. To scale to more complex games, the method allows decomposition of a game task into subtasks, each of which can be modelled by a Markov decision process. Intention recognition is used to infer the subtask that the human is currently performing, allowing the helper to assist the human in performing the correct task. Experiments show that the method …

Towards Textually Describing Complex Video Contents With Audio-Visual Concept Classifiers, Chun Chet Tan, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Automatically generating compact textual descriptions of complex video contents has wide applications. With the recent advancements in automatic audio-visual content recognition, in this paper we explore the technical feasibility of the challenging issue of precisely recounting video contents. Based on cutting-edge automatic recognition techniques, we start from classifying a variety of visual and audio concepts in video contents. According to the classification results, we apply simple rule-based methods to generate textual descriptions of video contents. Results are evaluated by conducting carefully designed user studies. We find that the state-of-the-art visual and audio concept classification, although far from perfect, is able …

Cytongrasp: Cyton Alpha Controller Via Graspit! Simulation, Nicholas Wayne Overfield

Masters Theses

This thesis addresses an expansion of the control programs for the Cyton Alpha 7D 1G arm. The original control system made use of configurable software which exploited the arm’s seven degrees of freedom and kinematic redundancy to control the arm based on desired behaviors that were configured off-line. The inclusions of the GraspIt! grasp planning simulator and toolkit enables the Cyton Alpha to be used in more proactive on-line grasping problems, as well as, presenting many additional tools for on-line learning applications. In short, GraspIt! expands what is possible with the Cyton Alpha to include many machine learning tools and …

Automating Construction And Selection Of A Neural Network Using Stochastic Optimization, Jason Lee Hurt

UNLV Theses, Dissertations, Professional Papers, and Capstones

An artificial neural network can be used to solve various statistical problems by approximating a function that provides a mapping from input to output data. No universal method exists for architecting an optimal neural network. Training one with a low error rate is often a manual process requiring the programmer to have specialized knowledge of the domain for the problem at hand.

A distributed architecture is proposed and implemented for generating a neural network capable of solving a particular problem without specialized knowledge of the problem domain. The only knowledge the application needs is a training set that the network …

Mining Software Specifications, David Lo, Siau-Cheng Khoo

David LO

No abstract provided.

Terapixel Imaging Of Cosmological Simulations, Yu Feng, Rupert Croft, Tiziana Di Matteo, Nishikanta Khandai, Randy Sargent, Illah Nourbakhsh, Paul Dille, Chris Bartley, Volker Springel, Anirban Jana, Jeffrey Gardner

Randy Sargent

The increasing size of cosmological simulations has led to the need for new visualization techniques. We focus on smoothed particle hydrodynamic (SPH) simulations run with the GADGET code and describe methods for visually accessing the entire simulation at full resolution. The simulation snapshots are rastered and processed on supercomputers into images that are ready to be accessed through a Web interface (GigaPan). This allows any scientist with a Web browser to interactively explore simulation data sets in both spatial and temporal dimensions and data sets which in their native format can be hundreds of terabytes in size or more. We …

A Pomdp Model For Guiding Taxi Cruising In A Congested Urban City, Lucas Agussurja, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We consider a partially observable Markov decision process (POMDP) model for improving a taxi agent cruising decision in a congested urban city. Using real-world data provided by a large taxi company in Singapore as a guide, we derive the state transition function of the POMDP. Specifically, we model the cruising behavior of the drivers as continuous-time Markov chains. We then apply dynamic programming algorithm for finding the optimal policy of the driver agent. Using a simulation, we show that this policy is significantly better than a greedy policy in congested road network.

A Brain-Inspired Model Of Hierarchical Planner, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Hierarchical planning is an approach of planning by composing and executing hierarchically arranged plans to solve some problems. Most symbolic-based hierarchical planners have been devised to allow the knowledge to be described expressively. However, a great challenge is to automatically seek and acquire new plans on the fly. This paper presents a novel neural-based model of hierarchical planning that can seek and acquired new plans on-line if the necessary knowledge are lacking. Inspired by findings in neuropsychology, plans can be inherently learnt, retrieved, and manipulated simultaneously rather than discretely processed like in most symbolic approaches. Using a multi-channel adaptive resonance …

Dynamic Behavior Sequencing For Hybrid Robot Architectures, Gilbert L. Peterson, Jeffrey P. Duffy, Daylond J. Hooper

Faculty Publications

Hybrid robot control architectures separate planning, coordination, and sensing and acting into separate processing layers to provide autonomous robots both deliberative and reactive functionality. This approach results in systems that perform well in goal-oriented and dynamic environments. Often, the interfaces and intents of each functional layer are tightly coupled and hand coded so any system change requires several changes in the other layers. This work presents the dynamic behavior hierarchy generation (DBHG) algorithm, which uses an abstract behavior representation to automatically build a behavior hierarchy for meeting a task goal. The generation of the behavior hierarchy occurs without knowledge of …

Classic Mosaics And Visual Correspondence Via Graph-Cut Based Energy Optimization, Yu Liu

Electronic Thesis and Dissertation Repository

Computer graphics and computer vision were traditionally two distinct research fields focusing on opposite topics. Lately, they have been increasingly borrowing ideas and tools from each other. In this thesis, we investigate two problems in computer vision and graphics that rely on the same tool, namely energy optimization with graph cuts.

In the area of computer graphics, we address the problem of generating artificial classic mosaics, still and animated. The main purpose of artificial mosaics is to help a user to create digital art. First we reformulate our previous static mosaic work in a more principled global optimization framework. Then, …

Allocating Resources In Multiagent Flowshops With Adaptive Auctions, Hoong Chuin Lau, Zhengyi Zhao, Sam Shuzhi Ge, Thong Heng Lee

Research Collection School Of Computing and Information Systems

In this paper, we consider the problem of allocating machine resources among multiple agents, each of which is responsible to solve a flowshop scheduling problem. We present an iterated combinatorial auction mechanism in which bid generation is performed within each agent, while a price adjustment procedure is performed by a centralized auctioneer. While this approach is fairly well-studied in the literature, our primary innovation is in an adaptive price adjustment procedure, utilizing variable step-size inspired by adaptive PID-control theory coupled with utility pricing inspired by classical microeconomics. We compare with the conventional price adjustment scheme proposed in Fisher (1985), and …

Influence Diagrams With Memory States: Representation And Algorithms, Xiaojian Wu, Akshat Kumar, Shlomo Zilberstein

Research Collection School Of Computing and Information Systems

Influence diagrams (IDs) offer a powerful framework for decision making under uncertainty, but their applicability has been hindered by the exponential growth of runtime and memory usage--largely due to the no-forgetting assumption. We present a novel way to maintain a limited amount of memory to inform each decision and still obtain near-optimal policies. The approach is based on augmenting the graphical model with memory states that represent key aspects of previous observations--a method that has proved useful in POMDP solvers. We also derive an efficient EM-based message-passing algorithm to compute the policy. Experimental results show that this approach produces highquality …

Improving Search Engine Results By Query Extension And Categorization, Guo Mei

Electronic Thesis and Dissertation Repository

Since its emergence, the Internet has changed the way in which information is distributed and it has strongly influenced how people communicate. Nowadays, Web search engines are widely used to locate information on the Web, and online social networks have become pervasive platforms of communication.

Retrieving relevant Web pages in response to a query is not an easy task for Web search engines due to the enormous corpus of data that the Web stores and the inherent ambiguity of search queries. We present two approaches to improve the effectiveness of Web search engines. The first approach allows us to retrieve …

Advances In Graph-Cut Optimization: Multi-Surface Models, Label Costs, And Hierarchical Costs, Andrew T. Delong

Electronic Thesis and Dissertation Repository

Computer vision is full of problems that are elegantly expressed in terms of mathematical optimization, or energy minimization. This is particularly true of "low-level" inference problems such as cleaning up noisy signals, clustering and classifying data, or estimating 3D points from images. Energies let us state each problem as a clear, precise objective function. Minimizing the correct energy would, hypothetically, yield a good solution to the corresponding problem. Unfortunately, even for low-level problems we are confronted by energies that are computationally hard—often NP-hard—to minimize. As a consequence, a rather large portion of computer vision research is dedicated to proposing …

Active Learning With Generalized Queries, Jun Du

Electronic Thesis and Dissertation Repository

We study active learning with generalized queries in the thesis.

In contrast to supervised learning, active learning can usually achieve the same predictive accuracy with much fewer labeled training examples, thus significantly reducing the labeling cost. However, previous studies of active learning mostly assume that the learner can only ask specific queries (i.e., require labels for specific examples by providing all feature values). For instance, if the task is to predict osteoarthritis based on a patient data set with 30 features, the previous active learners could only ask the specific queries as: does this patient have osteoarthritis, if ID is …