Graphics and Human Computer Interfaces Commons^™

Reducing Adaptation Latency For Multi-Concept Visual Perception In Outdoor Environments, Maggie Wigness, John G. Rogers, Luis Ernesto Navarro-Serment, Arne Suppe, Bruce A. Draper

Research Collection School Of Computing and Information Systems

Multi-concept visual classification is emerging as a common environment perception technique, with applications in autonomous mobile robot navigation. Supervised visual classifiers are typically trained with large sets of images, hand annotated by humans with region boundary outlines followed by label assignment. This annotation is time consuming, and unfortunately, a change in environment requires new or additional labeling to adapt visual perception. The time is takes for a human to label new data is what we call adaptation latency. High adaptation latency is not simply undesirable but may be infeasible for scenarios with limited labeling time and resources. In this paper, …

Landmark Detection With Surprise Saliency Using Convolutional Neural Networks, Feng Tang, Damian Lyons, Daniel Leeds

Faculty Publications

Abstract—Landmarks can be used as reference to enable people or robots to localize themselves or to navigate in their environment. Automatic definition and extraction of appropriate landmarks from the environment has proven to be a challenging task when pre-defined landmarks are not present. We propose a novel computational model of automatic landmark detection from a single image without any pre-defined landmark database. The hypothesis is that if an object looks abnormal due to its atypical scene context (what we call surprise saliency), it then may be considered as a good landmark because it is unique and easy to spot by …

Outlier-Robust Tensor Pca, Pan Zhou, Jiashi Feng

Research Collection School Of Computing and Information Systems

Low-rank tensor analysis is important for various real applications in computer vision. However, existing methods focus on recovering a low-rank tensor contaminated by Gaussian or gross sparse noise and hence cannot effectively handle outliers that are common in practical tensor data. To solve this issue, we propose an outlier-robust tensor principle component analysis (OR-TPCA) method for simultaneous low-rank tensor recovery and outlier detection. For intrinsically low-rank tensor observations with arbitrary outlier corruption, OR-TPCA is the first method that has provable performance guarantee for exactly recovering the tensor subspace and detecting outliers under mild conditions. Since tensor data are naturally high-dimensional …

Data-Driven Synthesis And Evaluation Of Syntactic Facial Expressions In American Sign Language Animation, Hernisa Kacorri

Dissertations, Theses, and Capstone Projects

Technology to automatically synthesize linguistically accurate and natural-looking animations of American Sign Language (ASL) would make it easier to add ASL content to websites and media, thereby increasing information accessibility for many people who are deaf and have low English literacy skills. State-of-art sign language animation tools focus mostly on accuracy of manual signs rather than on the facial expressions. We are investigating the synthesis of syntactic ASL facial expressions, which are grammatically required and essential to the meaning of sentences. In this thesis, we propose to: (1) explore the methodological aspects of evaluating sign language animations with facial expressions, …

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 …

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 …

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 …

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 …

An Autonomous Agent For Learning Spatiotemporal Models Of Human Daily Activities, Shan Gao, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Activities of Daily Living (ADLs) refer to activities performed by individuals on a daily basis. As ADLs are indicatives of a person’s habits, lifestyle, and well being, learning the knowledge of people’s ADL routine has great values in the healthcare and consumer domains. In this paper, we propose an autonomous agent, named Agent for Spatia-Temporal Activity Pattern Modeling (ASTAPM), being able to learn spatial and temporal patterns of human ADLs. ASTAPM utilises a self-organizing neural network model named Spatiotemporal - Adaptive Resonance Theory (ST-ART). ST-ART is capable of integrating multimodal contextual information, involving the time and space, wherein the ADL …

Efficient 3d Dental Identification Via Signed Feature Histogram And Learning Keypoint Detection, Zhiyuan Zhang, Sim Heng Ong, Xin Zhong, Kelvin W. C. Foong

Research Collection School Of Computing and Information Systems

Current methods of dental identification are mainly based on 2D dental radiographs which suffer from speed and accuracy limitations. In this paper, we present an efficient dental identification approach based on 3D dental models. We propose a novel shape descriptor, the Signed Feature Histogram (SFH), which is highly discriminative and can be easily computed to describe the local surface. Based on the SFH, a learning keypoint detection method is adopted to accurately detect the desired keypoints on both antemortem (AM) and postmortem (PM) models. For a given PM model, the optimal initial alignment to the AM model to be matched …

A Study Of Android Malware Detection Techniques And Machine Learning, Balaji Baskaran, Anca Ralescu

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

Android OS is one of the widely used mobile Operating Systems. The number of malicious applications and adwares are increasing constantly on par with the number of mobile devices. A great number of commercial signature based tools are available on the market which prevent to an extent the penetration and distribution of malicious applications. Numerous researches have been conducted which claims that traditional signature based detection system work well up to certain level and malware authors use numerous techniques to evade these tools. So given this state of affairs, there is an increasing need for an alternative, really tough malware …

Extended Pixel Representation For Image Segmentation, Deeptha Girish, Vineeta Singh, Anca Ralescu

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

We explore the use of extended pixel representation for color based image segmentation using the K-means clustering algorithm. Various extended pixel representations have been implemented in this paper and their results have been compared. By extending the representation of pixels an image is mapped to a higher dimensional space. Unlike other approaches, where data is mapped into an implicit features space of higher dimension (kernel methods), in the approach considered here, the higher dimensions are defined explicitly. Preliminary experimental results which illustrate the proposed approach are promising.

An Autonomic Computing System Based On A Rule-Based Policy Engine And Artificial Immune Systems, Rahmira Rufus, William Nick, Joseph Shelton, Albert Esterline

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

Autonomic computing systems arose from the notion that complex computing systems should have properties like those of the autonomic nervous system, which coordinates bodily functions and allows attention to be directed to more pressing needs. An autonomic system allows the system administrator to specify high-level policies, which the system maintains without administrator assistance. Policy enforcement can be done with a rule based system such as Jess (a java expert system shell). An autonomic system must be able to monitor itself, and this is often a limiting factor. We are developing an automatic system that has a policy engine and uses …

Towards The Development Of A Cyber Analysis & Advisement Tool (Caat) For Mitigating De-Anonymization Attacks, Siobahn Day, Henry Williams, Joseph Shelton, Gerry Dozier

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

We are seeing a rise in the number of Anonymous Social Networks (ASN) that claim to provide a sense of user anonymity. However, what many users of ASNs do not know that a person can be identified by their writing style.

In this paper, we provide an overview of a number of author concealment techniques, their impact on the semantic meaning of an author's original text, and introduce AuthorCAAT, an application for mitigating de-anonymization attacks. Our results show that iterative paraphrasing performs the best in terms of author concealment and performs well with respect to Latent Semantic Analysis.

Situations And Evidence For Identity Using Dempster-Shafer Theory, William Nick, Yenny Dominguez, Albert Esterline

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

We present a computational framework for identity based on Barwise and Devlin’s situation theory. We present an example with constellations of situations identifying an individual to create what we call id-situations, where id-actions are performed, along with supporting situations. We use Semantic Web standards to represent and reason about the situations in our example. We show how to represent the strength of the evidence, within the situations, as a measure of the support for judgments reached in the id-situation. To measure evidence of an identity from the supporting situations, we use the Dempster-Shafer theory of evidence. We enhance Dempster- Shafer …

Student Understanding And Engagement In A Class Employing Comps Computer Mediated Problem Solving: A First Look, Jung Hee Kim, Michael Glass, Taehee Kim, Kelvin Bryant, Angelica Willis, Ebonie Mcneil, Zachery Thomas

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

COMPS computer-mediated group discussion exercises are being added to a second-semester computer programming class. The class is a gateway for computer science and computer engineering students, where many students have difficulty succeeding well enough to proceed in their major. This paper reports on first results of surveys on student experience with the exercises. It also reports on the affective states observed in the discussions that are candidates for analysis of group functioning. As a step toward computer monitoring of the discussions, an experiment in using dialogue features to identify the gender of the participants is described.

A Tool For Staging Mixed-Initiative Dialogs, Joshua W. Buck, Saverio Perugini

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

We discuss and demonstrate a tool for prototyping dialog-based systems that, given a high-level specification of a human-computer dialog, stages the dialog for interactive use. The tool enables a dialog designer to evaluate a variety of dialogs without having to program each individual dialog, and serves as a proof-of-concept for our approach to mixed-initiative dialog modeling and implementation from a programming language-based perspective.

Keynote Talk 2: Social And Perceptual Fidelity Of Avatars And Autonomous Agents In Virtual Reality, Benjamin Kunz

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

Advances in display, computing and sensor technologies have led to a revival of interest and excitement surrounding immersive virtual reality. Here, on the cusp of the arrival of practical and affordable virtual reality technology, are open questions regarding the factors that contribute to compelling and immersive virtual worlds.

In order for virtual reality to be useful as a tool for use in training, education, communication, research, content-creation and entertainment, we must understand the degree to which the perception of the virtual environment and virtual characters resembles perception of the real world.

Relatedly, virtual reality's utility in these contexts demands evidence …

Exploring Web-Based Visual Interfaces For Searching Research Articles On Digital Library Systems, Maxwell Fowler, Chris Bellis, Chris Perry, Beomjin Kim

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

Previous studies that present information archived in digital libraries have used either document meta-data or document content. The current search mechanisms commonly return text-based results that were compiled from the meta-data without reflecting the underlying content. Visual analytics is a possible solution for improving searches by presenting a large amount of information, including document content alongside meta-data, in a limited screen space. This paper introduces a multi-tiered visual interface for searching research articles stored in Digital Library systems. The goals of this system are to allow users to find research papers about their interests in a large work space, to …

Fuzzy Algorithms: Applying Fuzzy Logic To The Golden Ratio Search To Find Solutions Faster, Stephany Coffman-Wolph

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

Applying the concept of fuzzy logic (an abstract version of Boolean logic) to well-known algorithms generates an abstract version (i.e., fuzzy algorithm) that often results in computational improvements. Precision may be reduced but counteracted by gaining computational efficiency. The trade-offs (e.g., small increase in space, loss of precision) for a variety of applications are deemed acceptable. The fuzzification of an algorithm can be accomplished using a simple three-step framework. Creating a new fuzzy algorithm goes beyond simply converting the data from raw data into fuzzy data by additionally converting the operators and concepts into their abstract equivalents. This paper demonstrates: …

The Webid Protocol Enhanced With Group Access, Biometrics, And Access Policies, Cory Sabol, William Nick, Maya Earl, Joseph Shelton, Albert Esterline

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

The WebID protocol solves the challenge of remembering usernames and passwords. We enhance this protocol in three ways. First, we give it the ability to manage groups of agents and control their access to resources on the Web. Second, we add support for biometric access control to enhance security. Finally, we add support for OWL-based policies that may be federated and result in flexible access control.

Real-Time Unsupervised Clustering, Gabriel Ferrer

MAICS: The Modern Artificial Intelligence and Cognitive Science Conference

In our research program, we are developing machine learning algorithms to enable a mobile robot to build a compact representation of its environment. This requires the processing of each new input to terminate in constant time. Existing machine learning algorithms are either incapable of meeting this constraint or deliver problematic results. In this paper, we describe a new algorithm for real-time unsupervised clustering, Bounded Self-Organizing Clustering. It executes in constant time for each input, and it produces clusterings that are significantly better than those created by the Self-Organizing Map, its closest competitor, on sensor data acquired from a physically embodied …

Front Matter: Proceedings Of The Maics 2016 Conference, University Of Dayton

Content presented at the MAICS conference

Front matter contains:

• A list of program chairs and committee members
• Foreword to the proceedings by James P. Buckley, conference chair; Saverio Perugini, general chair

Editors: Phu H. Phung, University of Dayton; Ju Shen, University of Dayton; Michael Glass, Valparaiso University

Factororacle: An Extensible Max External For Investigating Applications Of The Factor Oracle Automaton In Real-Time Music Improvisation, Adam James Wilson

Publications and Research

There are several extant software systems designed to generate music in real-time using a factor oracle automaton constructed from the musical input of a human improvisor. The impetus for the design of the factorOracle external is neither a desire to supersede these systems nor introduce novel algorithms for traversing the oracle, but rather to provide a fast, canonical interface for the automaton in Cycling74’s Max and, in future iterations, the Pure Data programming environment. Technical features of the factorOracle software are introduced here.

Oriented Object Proposals, Shengfeng He, Rynson W. H. Lau

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to generate oriented object proposals (OOPs) to reduce the detection error caused by various orientations of the object. To this end, we propose to efficiently locate object regions according to pixelwise object probability, rather than measuring the objectness from a set of sampled windows. We formulate the proposal generation problem as a generative probabilistic model such that object proposals of different shapes (i.e., sizes and orientations) can be produced by locating the local maximum likelihoods. The new approach has three main advantages. First, it helps the object detector handle objects of different …

Using Eye And Head Movements As A Control Mechanism For Tele-Operating A Ground-Based Robot And Its Payload, Kathryn C. Hicks

Computational Modeling & Simulation Engineering Theses & Dissertations

To date, eye and head tracking has been used to indicate users' attention patterns while performing a task or as an aid for disabled persons, to allow hands-free interaction with a computer. The increasing accuracy and the reduced cost of eye- and head-tracking equipment make utilizing this technology feasible for explicit control tasks, especially in cases where there is confluence between the visual task and control.

The goal of this research was to investigate the use of eye-tracking as a more natural interface for the control of a camera-equipped, remotely operated robot in tasks that require the operator to simultaneously …

Brain Machine Interface Using Emotiv Epoc To Control Robai Cyton Robotic Arm, Daniel P. Prince, Mark J. Edmonds, Andrew J. Sutter, Matthew Thomas Cusumano, Wenjie Lu, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

The initial framework for an electroencephalography (EEG) thought recognition software suite is developed, built, and tested. This suite is designed to recognize human thoughts and pair them to actions for controlling a robotic arm.

Raw EEG brain activity data is collected using an Emotiv EPOC headset. The EEG data is processed through linear discriminant analysis (LDA), where an intended action is identified. The EEG classification suite is being developed to increase the number of distinct actions that can be identified compared to the Emotiv recognition software. The EEG classifier was able to correctly distinguish between two separate physical movements.

Future …

Technology And Gambling: How It Has Changed The Game, Nicholas Hensley

Senior Seminars

No abstract provided.

Facial Expression Analysis Via Transfer Learning, Xiao Zhang

Electronic Theses and Dissertations

Automated analysis of facial expressions has remained an interesting and challenging research topic in the field of computer vision and pattern recognition due to vast applications such as human-machine interface design, social robotics, and developmental psychology. This dissertation focuses on developing and applying transfer learning algorithms - multiple kernel learning (MKL) and multi-task learning (MTL) - to resolve the problems of facial feature fusion and the exploitation of multiple facial action units (AUs) relations in designing robust facial expression recognition systems. MKL algorithms are employed to fuse multiple facial features with different kernel functions and tackle the domain adaption problem …

Metalogic Notes, Saverio Perugini

Computer Science Working Papers

A collection of notes, formulas, theorems, postulates and terminology in symbolic logic, syntactic notions, semantic notions, linkages between syntax and semantics, soundness and completeness, quantified logic, first-order theories, Goedel's First Incompleteness Theorem and more.