Data Storage Systems Commons^™

On The Pooling Of Positive Examples With Ontology For Visual Concept Learning, Shiai Zhu, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

A common obstacle in effective learning of visual concept classifiers is the scarcity of positive training examples due to expensive labeling cost. This paper explores the sampling of weakly tagged web images for concept learning without human assistance. In particular, ontology knowledge is incorporated for semantic pooling of positive examples from ontologically neighboring concepts. This effectively widens the coverage of the positive samples with visually more diversified content, which is important for learning a good concept classifier. We experiment with two learning strategies: aggregate and incremental. The former strategy re-trains a new classifier by combining existing and newly collected examples, …

Active Learning For Text Classification, Rong Hu

Doctoral

Text classification approaches are used extensively to solve real-world challenges. The success or failure of text classification systems hangs on the datasets used to train them, without a good dataset it is impossible to build a quality system. This thesis examines the applicability of active learning in text classification for the rapid and economical creation of labelled training data. Four main contributions are made in this thesis. First, we present two novel selection strategies to choose the most informative examples for manually labelling. One is an approach using an advanced aggregated confidence measurement instead of the direct output of classifiers …

Calibration Of Complex System Dynamics Models: A Practioner's Report, Rod Walker, Wayne Wakeland

Complex Systems Faculty Publications and Presentations

This paper is not a typical academic paper that is solidly grounded in the literature. Instead, this paper reports practitioner’s experiences in rebuilding and calibrating a very large system dynamics model. A prior version of this model had been in use for over 10 years in an ongoing executive training simulation. That model had never worked correctly in several key areas, requiring the outputs to be manually adjusted by very experienced facilitators during the course of the simulation. The present project rebuilt the system dynamics model, redesigned the parts that weren’t working, and calibrated the resulting model to match the …

Fusing Heterogeneous Modalities For Video And Image Re-Ranking, Hung-Khoon Tan, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Multimedia documents in popular image and video sharing websites such as Flickr and Youtube are heterogeneous documents with diverse ways of representations and rich user-supplied information. In this paper, we investigate how the agreement among heterogeneous modalities can be exploited to guide data fusion. The problem of fusion is cast as the simultaneous mining of agreement from different modalities and adaptation of fusion weights to construct a fused graph from these modalities. An iterative framework based on agreement-fusion optimization is thus proposed. We plug in two well-known algorithms: random walk and semi-supervised learning to this framework to illustrate the idea …

Increasing Efficiency In Boundary Security With Wireless Sensor Networks And Geospatial Information Systems Using Homology Theory, Luis Berumen^, Eric Chaidez^, Hamide Dogan*, Jose Gerardo Rosiles**

COURI Symposium Abstracts, Spring 2011

As part of an institutional investigation, we attempt to address the challenges the US customs and Border protection agency faces in the El Paso region. Our research focuses on defining a system for the surveillance application, and the use of mathematical models employed to achieve a greater efficiency of such architecture. With the use of the defined system, we apply homology theory through the algebraic process of topology, to accomplish an independent coordinate-free based system, which covers the surveillance area, with lesser quantity of sensor nodes. Our architecture makes the use of an operating system for wireless sensor networks; TinyOS, …

Freeing Space For Nasa: Incorporating A Lossless Compression Algorithm Into Nasa's Fiber Optic Strain Sensing System, Kaitlyn Fiechtner, Allen Parker

STAR Program Research Presentations

NASA’s Fiber Optic Strain Sensing (FOSS) system can gather and store up to 1,536,000 bytes (1.46 megabytes) per second. Since the FOSS system typically acquires hours—or even days—of data, the system can gather hundreds of gigabytes of data for a given test event. To store such large quantities of data more effectively, NASA is modifying a Lempel-Ziv-Oberhumer (LZO) lossless data compression program to compress data as it is being acquired in real time. After proving that the algorithm is capable of compressing the data from the FOSS system, the LZO program will be modified and incorporated into the FOSS system. …

Semi-Automatic Management Of Knowledge Bases Using Formal Ontologies, Andreas Textor

Theses

This thesis presents an approach that deals with the ever-growing amount of data in knowledge bases, especially concerning knowledge interoperability and formal representation of domain knowledge. There arc multiple issues that must be addressed with current systems. A multitude of different formats, sources and tools exist in a domain, and it is desirable to develop their use further towards a standardised environment. Such an environment should support both the representation and processing of data from this domain, and the connection to other domains, where necessary. In order to manage large amounts of data, it should be possible to perform whatever …

Parallelizing Scale Invariant Feature Transform On A Distributed Memory Cluster, Stanislav Bobovych

Inquiry: The University of Arkansas Undergraduate Research Journal

Scale Invariant Feature Transform (SIFT) is a computer vision algorithm that is widely-used to extract features from images. We explored accelerating an existing implementation of this algorithm with message passing in order to analyze large data sets. We successfully tested two approaches to data decomposition in order to parallelize SIFT on a distributed memory cluster.

Evidence Supporting Measure Of Similarity For Reducing The Complexity In Information Fusion, Florentin Smarandache, Jean Dezert, Xinde Li, Xinhan Huang

Branch Mathematics and Statistics Faculty and Staff Publications

This paper presents a new method for reducing the number of sources of evidence to combine in order to reduce the complexity of the fusion processing. Such a complexity reduction is often required in many applications where the real-time constraint and limited computing resources are of prime importance. The basic idea consists in selecting, among all sources available, only a subset of sources of evidence to combine. The selection is based on an evidence supporting measure of similarity (ESMS) criterion which is an efficient generic tool for outlier sources identification and rejection. The ESMS between two sources of evidence can …

Investigations Into Library Web Scale Discovery Services, Jason Vaughan

Library Faculty Research

Web scale discovery services for libraries provide deep discovery to a library’s local and licensed content, and represent an evolution, perhaps a revolution, for end user information discovery as pertains to library collections. This article frames the topic of Web scale discovery, and begins by illuminating Web scale discovery from an academic library’s perspective – that is, the internal perspective seeking widespread staff participation in the discovery conversation. This included the creation of a Discovery Task Force, a group which educated library staff, conducted internal staff surveys, and gathered observations from early adopters. The article next addresses the substantial research …

Development Of Visualization Facility At The Gis And Remote Sensing Core Lab, University Of Nevada, Las Vegas, Haroon Stephen, William J. Smith, Zhongwei Liu

Public Policy and Leadership Faculty Presentations

Visualization using advanced computational and graphic equipment has become a standard way of present day research. Availability of low cost and fast processing units, high resolution displays with graphic processing units, and specialized software has brought complex visualization capabilities to an office desktop. Nevertheless, when dealing with large datasets such as, global climate, geospatial, and social data the office desktop falls short and calls for a centralized visualization facility with high end computing and graphics equipment.

Visualization Facility at GIS and Remote Sensing Core Lab would be a useful and important addition to the UNLV IT infrastructure. It would provide …

Mining Event Structures From Web Videos, Xiao Wu, Yi-Jie Lu, Qiang Peng, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

The article is discussing the issues of mining event structures from Web video search results using text analysis, burst detection, and clustering as with the proliferation of social media, the volume of Web videos have grown exponentially.

Concept-Driven Multi-Modality Fusion For Video Search, Xiao-Yong Wei, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

As it is true for human perception that we gather information from different sources in natural and multi-modality forms, learning from multi-modalities has become an effective scheme for various information retrieval problems. In this paper, we propose a novel multi-modality fusion approach for video search, where the search modalities are derived from a diverse set of knowledge sources, such as text transcript from speech recognition, low-level visual features from video frames, and high-level semantic visual concepts from supervised learning. Since the effectiveness of each search modality greatly depends on specific user queries, prompt determination of the importance of a modality …

Topical Summarization Of Web Videos By Visual-Text Time-Dependent Alignment, Song Tan, Hung-Khoon Tan, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Search engines are used to return a long list of hundreds or even thousands of videos in response to a query topic. Efficient navigation of videos becomes difficult and users often need to painstakingly explore the search list for a gist of the search result. This paper addresses the challenge of topical summarization by providing a timeline-based visualization of videos through matching of heterogeneous sources. To overcome the so called sparse-text problem of web videos, auxiliary information from Google context is exploited. Google Trends is used to predict the milestone events of a topic. Meanwhile, the typical scenes of web …

Data-Driven Approaches To Community-Contributed Video Applications, Xiao Wu, Chong-Wah Ngo, Wan-Lei Zhao

Research Collection School Of Computing and Information Systems

With the prosperity of video-sharing websites such as YouTube, the amount of community-contributed video has increased dramatically. Reportedly more than 65,000 new videos were uploaded to YouTube every day in July 2006 and it's estimated that 20 hours of new videos were uploaded to the site every minute in May 2009. In addition to the huge volume of video data, the social Web provides rich contextual and social resources associated with videos. These resources include title, tags, thumbnails, related videos, and user and community information, as illustrated in Figure 1. While billions of user-generated videos accompanied with rich-media information have …

Investigating Perceptions Of A Location-Based Annotation System, Huynh Nhu Hop Quach, Khasfariyati Razikin, Dion Hoe-Lian Goh, Thi Nhu Quynh Kim, Tan Phat Pham, Yin-Leng Theng, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

We introduce MobiTOP, a Web-based system for organizing and retrieving hierarchical location-based annotations. Each annotation contains multimedia content (such as text, images, video) associated with a location, and users are able to annotate existing annotations to an arbitrary depth, in effect creating a hierarchy. An evaluation was conducted on a group of potential users to ascertain their perceptions of the usability of the application. The results were generally positive and the majority of the participants saw MobiTOP as a useful platform to share location-based information. We conclude with implications of our work and opportunities for future research.

On The Annotation Of Web Videos By Efficient Near-Duplicate Search, Wan-Lei Zhao, Xiao Wu, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

With the proliferation of Web 2.0 applications, usersupplied social tags are commonly available in social media as a means to bridge the semantic gap. On the other hand, the explosive expansion of social web makes an overwhelming number of web videos available, among which there exists a large number of near-duplicate videos. In this paper, we investigate techniques which allow effective annotation of web videos from a data-driven perspective. A novel classifier-free video annotation framework is proposed by first retrieving visual duplicates and then suggesting representative tags. The significance of this paper lies in the addressing of two timely issues …

On The Sampling Of Web Images For Learning Visual Concept Classifiers, Shiai Zhu, Gang Wang, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Visual concept learning often requires a large set of training images. In practice, nevertheless, acquiring noise-free training labels with sufficient positive examples is always expensive. A plausible solution for training data collection is by sampling the largely available user-tagged images from social media websites. With the general belief that the probability of correct tagging is higher than that of incorrect tagging, such a solution often sounds feasible, though is not without challenges. First, user-tags can be subjective and, to certain extent, are ambiguous. For instance, an image tagged with “whales” may be simply a picture about ocean museum. Learning concept …

Co-Reranking By Mutual Reinforcement For Image Search, Ting Yao, Tao Mei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Most existing reranking approaches to image search focus solely on mining “visual” cues within the initial search results. However, the visual information cannot always provide enough guidance to the reranking process. For example, different images with similar appearance may not always present the same relevant information to the query. Observing that multi-modality cues carry complementary relevant information, we propose the idea of co-reranking for image search, by jointly exploring the visual and textual information. Co-reranking couples two random walks, while reinforcing the mutual exchange and propagation of information relevancy across different modalities. The mutual reinforcement is iteratively updated to constrain …

Coherent Bag-Of Audio Words Model For Efficient Large-Scale Video Copy Detection, Yang Liu, Wan-Lei Zhao, Chong-Wah Ngo, Chang-Sheng Xu, Han-Qing Lu

Research Collection School Of Computing and Information Systems

Current content-based video copy detection approaches mostly concentrate on the visual cues and neglect the audio information. In this paper, we attempt to tackle the video copy detection task resorting to audio information, which is equivalently important as well as visual information in multimedia processing. Firstly, inspired by bag-of visual words model, a bag-of audio words (BoA) representation is proposed to characterize each audio frame. Different from naive singlebased modeling audio retrieval approaches, BoA is a highlevel model due to its perceptual and semantical property. Within the BoA model, a coherency vocabulary indexing structure is adopted to achieve more efficient …