Current Search: time series analysis (x)
View All Items
(1 - 10 of 10)
- Title
- Leaning Robust Sequence Features via Dynamic Temporal Pattern Discovery.
- Creator
-
Hu, Hao, Wang, Liqiang, Zhang, Shaojie, Liu, Fei, Qi, GuoJun, Zhou, Qun, University of Central Florida
- Abstract / Description
-
As a major type of data, time series possess invaluable latent knowledge for describing the real world and human society. In order to improve the ability of intelligent systems for understanding the world and people, it is critical to design sophisticated machine learning algorithms for extracting robust time series features from such latent knowledge. Motivated by the successful applications of deep learning in computer vision, more and more machine learning researchers put their attentions...
Show moreAs a major type of data, time series possess invaluable latent knowledge for describing the real world and human society. In order to improve the ability of intelligent systems for understanding the world and people, it is critical to design sophisticated machine learning algorithms for extracting robust time series features from such latent knowledge. Motivated by the successful applications of deep learning in computer vision, more and more machine learning researchers put their attentions on the topic of applying deep learning techniques to time series data. However, directly employing current deep models in most time series domains could be problematic. A major reason is that temporal pattern types that current deep models are aiming at are very limited, which cannot meet the requirement of modeling different underlying patterns of data coming from various sources. In this study we address this problem by designing different network structures explicitly based on specific domain knowledge such that we can extract features via most salient temporal patterns. More specifically, we mainly focus on two types of temporal patterns: order patterns and frequency patterns. For order patterns, which are usually related to brain and human activities, we design a hashing-based neural network layer to globally encode the ordinal pattern information into the resultant features. It is further generalized into a specially designed Recurrent Neural Networks (RNN) cell which can learn order patterns in an online fashion. On the other hand, we believe audio-related data such as music and speech can benefit from modeling frequency patterns. Thus, we do so by developing two types of RNN cells. The first type tries to directly learn the long-term dependencies on frequency domain rather than time domain. The second one aims to dynamically filter out the ``noise" frequencies based on temporal contexts. By proposing various deep models based on different domain knowledge and evaluating them on extensive time series tasks, we hope this work can provide inspirations for others and increase the community's interests on the problem of applying deep learning techniques to more time series tasks.
Show less - Date Issued
- 2019
- Identifier
- CFE0007470, ucf:52679
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007470
- Title
- Managing IO Resource for Co-running Data Intensive Applications in Virtual Clusters.
- Creator
-
Huang, Dan, Wang, Jun, Zhou, Qun, Sun, Wei, Zhang, Shaojie, Wang, Liqiang, University of Central Florida
- Abstract / Description
-
Today Big Data computer platforms employ resource management systems such as Yarn, Torque, Mesos, and Google Borg to enable sharing the physical computing among many users or applications. Given virtualization and resource management systems, users are able to launch their applications on the same node with low mutual interference and management overhead on CPU and memory. However, there are still challenges to be addressed before these systems can be fully adopted to manage the IO resources...
Show moreToday Big Data computer platforms employ resource management systems such as Yarn, Torque, Mesos, and Google Borg to enable sharing the physical computing among many users or applications. Given virtualization and resource management systems, users are able to launch their applications on the same node with low mutual interference and management overhead on CPU and memory. However, there are still challenges to be addressed before these systems can be fully adopted to manage the IO resources in Big Data File Systems (BDFS) and shared network facilities. In this study, we mainly study on three IO management problems systematically, in terms of the proportional sharing of block IO in container-based virtualization, the network IO contention in MPI-based HPC applications and the data migration overhead in HPC workflows. To improve the proportional sharing, we develop a prototype system called BDFS-Container, by containerizing BDFS at Linux block IO level. Central to BDFS-Container, we propose and design a proactive IOPS throttling based mechanism named IOPS Regulator, which improves proportional IO sharing under the BDFS IO pattern by 74.4% on an average. In the aspect of network IO resource management, we exploit using virtual switches to facilitate network traffic manipulation and reduce mutual interference on the network for in-situ applications. In order to dynamically allocate the network bandwidth when it is needed, we adopt SARIMA-based techniques to analyze and predict MPI traffic issued from simulations. Third, to solve the data migration problem in small-medium sized HPC clusters, we propose to construct a sided IO path, named as SideIO, to explicitly direct analysis data to BDFS that co-locates computation with data. By experimenting with two real-world scientific workflows, SideIO completely avoids the most expensive data movement overhead and achieves up to 3x speedups compared with current solutions.
Show less - Date Issued
- 2018
- Identifier
- CFE0007195, ucf:52268
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007195
- Title
- Leader Psychology and Civil War Behavior.
- Creator
-
Smith, Gary, Schafer, Mark, Kang, Kyungkook, Powell, Jonathan, Walker, Stephen, University of Central Florida
- Abstract / Description
-
How do the psychological characteristics of world leaders affect civil wars? Multiple studies have investigated how the personalities and beliefs of world leaders affect foreign policy preferences and outcomes. However, this research has yet to be applied to the intrastate context, which is problematic, given the growing importance of civil wars in the conflict-studies literature. This dissertation project utilizes at-a-distance profiling methods to investigate how leaders and their...
Show moreHow do the psychological characteristics of world leaders affect civil wars? Multiple studies have investigated how the personalities and beliefs of world leaders affect foreign policy preferences and outcomes. However, this research has yet to be applied to the intrastate context, which is problematic, given the growing importance of civil wars in the conflict-studies literature. This dissertation project utilizes at-a-distance profiling methods to investigate how leaders and their psychological characteristics can affect the likelihood, severity, and duration of civil conflicts. The findings of this research provide further support for the general hypothesis that leaders can, and often do, matter when trying to explain policy outcomes. More importantly, the findings demonstrate that leaders can influence the likelihood of civil war onset, the severity of civil wars, and their duration. Additionally, this project investigates the effect that civil war severity has on the psychological characteristics of leaders. Contrary to some previous research, however, the findings here indicate that leaders' psychology may not be sensitive to civil conflict severity.
Show less - Date Issued
- 2018
- Identifier
- CFE0007375, ucf:52089
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007375
- Title
- A STUDY OF EQUATORIAL IONOPSHERIC VARIABILITY USING SIGNAL PROCESSING TECHNIQUES.
- Creator
-
wang, xiaoni, Eastes, Richard, University of Central Florida
- Abstract / Description
-
The dependence of equatorial ionosphere on solar irradiances and geomagnetic activity are studied in this dissertation using signal processing techniques. The statistical time series, digital signal processing and wavelet methods are applied to study the ionospheric variations. The ionospheric data used are the Total Electron Content (TEC) and the critical frequency of the F2 layer (foF2). Solar irradiance data are from recent satellites, the Student Nitric Oxide Explorer (SNOE) satellite and...
Show moreThe dependence of equatorial ionosphere on solar irradiances and geomagnetic activity are studied in this dissertation using signal processing techniques. The statistical time series, digital signal processing and wavelet methods are applied to study the ionospheric variations. The ionospheric data used are the Total Electron Content (TEC) and the critical frequency of the F2 layer (foF2). Solar irradiance data are from recent satellites, the Student Nitric Oxide Explorer (SNOE) satellite and the Thermosphere Ionosphere Mesosphere Energetics Dynamics (TIMED) satellite. The Disturbance Storm-Time (Dst) index is used as a proxy of geomagnetic activity in the equatorial region. The results are summarized as follows. (1) In the short-term variations < 27-days, the previous three days solar irradiances have significant correlation with the present day ionospheric data using TEC, which may contribute 18% of the total variations in the TEC. The 3-day delay between solar irradiances and TEC suggests the effects of neutral densities on the ionosphere. The correlations between solar irradiances and TEC are significantly higher than those using the F10.7 flux, a conventional proxy for short wavelength band of solar irradiances. (2) For variations < 27 days, solar soft X-rays show similar or higher correlations with the ionosphere electron densities than the Extreme Ultraviolet (EUV). The correlations between solar irradiances and foF2 decrease from morning (0.5) to the afternoon (0.1). (3) Geomagnetic activity plays an important role in the ionosphere in short-term variations < 10 days. The average correlation between TEC and Dst is 0.4 at 2-3, 3-5, 5-9 and 9-11 day scales, which is higher than those between foF2 and Dst. The correlations between TEC and Dst increase from morning to afternoon. The moderate/quiet geomagnetic activity plays a distinct role in these short-term variations of the ionosphere (~0.3 correlation).
Show less - Date Issued
- 2007
- Identifier
- CFE0001602, ucf:47188
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001602
- Title
- AN IMPACT EVALUATION OF U.S. ARMS EXPORT CONTROLS ON THE U.S. DEFENSE INDUSTRIAL BASE: AN INTERRUPTED TIME-SERIES ANALYSIS.
- Creator
-
Condron, Aaron, Sweo, Robert, University of Central Florida
- Abstract / Description
-
The United States Defense Industrial Base (USDIB) is an essential industry to both the economic prosperity of the US and its strategic control over many advanced military systems and technologies. The USDIB, which encompasses the industries of aerospace and defense, is a volatile industry - prone to many internal and external factors that cause demand to ebb and flow widely year over year. Among the factors that influence the volume of systems the USDIB delivers to its international customers...
Show moreThe United States Defense Industrial Base (USDIB) is an essential industry to both the economic prosperity of the US and its strategic control over many advanced military systems and technologies. The USDIB, which encompasses the industries of aerospace and defense, is a volatile industry - prone to many internal and external factors that cause demand to ebb and flow widely year over year. Among the factors that influence the volume of systems the USDIB delivers to its international customers are the arms export controls of the US. These controls impose a divergence from the historical US foreign policy of furthering an open exchange of ideas and liberalized trade. These controls, imposed by the Departments of Commerce, Defense, and State rigidly control all international presence of the Industry. The overlapping controls create an inability to conform to rapidly changing realpolitiks, leaving these controls in an archaic state. This, in turn, imposes a great deal of anxiety and expense upon managers within and outside of the USDIB. Using autoregressive integrated moving average time-series analyses, this paper confirms that the implementation of or amendment to broad arms export controls correlates to significant and near immediate declines in USDIB export volumes. In the context of the US's share of world arms exports, these controls impose up to a 20% decline in export volume.
Show less - Date Issued
- 2011
- Identifier
- CFH0004064, ucf:44785
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004064
- Title
- INVESTIGATION OF DAMAGE DETECTION METHODOLOGIES FOR STRUCTURAL HEALTH MONITORING.
- Creator
-
Gul, Mustafa, Catbas, F. Necati, University of Central Florida
- Abstract / Description
-
Structural Health Monitoring (SHM) is employed to track and evaluate damage and deterioration during regular operation as well as after extreme events for aerospace, mechanical and civil structures. A complete SHM system incorporates performance metrics, sensing, signal processing, data analysis, transmission and management for decision-making purposes. Damage detection in the context of SHM can be successful by employing a collection of robust and practical damage detection methodologies...
Show moreStructural Health Monitoring (SHM) is employed to track and evaluate damage and deterioration during regular operation as well as after extreme events for aerospace, mechanical and civil structures. A complete SHM system incorporates performance metrics, sensing, signal processing, data analysis, transmission and management for decision-making purposes. Damage detection in the context of SHM can be successful by employing a collection of robust and practical damage detection methodologies that can be used to identify, locate and quantify damage or, in general terms, changes in observable behavior. In this study, different damage detection methods are investigated for global condition assessment of structures. First, different parametric and non-parametric approaches are re-visited and further improved for damage detection using vibration data. Modal flexibility, modal curvature and un-scaled flexibility based on the dynamic properties that are obtained using Complex Mode Indicator Function (CMIF) are used as parametric damage features. Second, statistical pattern recognition approaches using time series modeling in conjunction with outlier detection are investigated as a non-parametric damage detection technique. Third, a novel methodology using ARX models (Auto-Regressive models with eXogenous output) is proposed for damage identification. By using this new methodology, it is shown that damage can be detected, located and quantified without the need of external loading information. Next, laboratory studies are conducted on different test structures with a number of different damage scenarios for the evaluation of the techniques in a comparative fashion. Finally, application of the methodologies to real life data is also presented along with the capabilities and limitations of each approach in light of analysis results of the laboratory and real life data.
Show less - Date Issued
- 2009
- Identifier
- CFE0002830, ucf:48069
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002830
- Title
- Data-Driven Modeling and Optimization of Building Energy Consumption.
- Creator
-
Grover, Divas, Pourmohammadi Fallah, Yaser, Vosoughi, Azadeh, Zhou, Qun, University of Central Florida
- Abstract / Description
-
Sustainability and reducing energy consumption are targets for building operations. The installation of smart sensors and Building Automation Systems (BAS) makes it possible to study facility operations under different circumstances. These technologies generate large amounts of data. That data can be scrapped and used for the analysis. In this thesis, we focus on the process of data-driven modeling and decision making from scraping the data to simulate the building and optimizing the...
Show moreSustainability and reducing energy consumption are targets for building operations. The installation of smart sensors and Building Automation Systems (BAS) makes it possible to study facility operations under different circumstances. These technologies generate large amounts of data. That data can be scrapped and used for the analysis. In this thesis, we focus on the process of data-driven modeling and decision making from scraping the data to simulate the building and optimizing the operation. The City of Orlando has similar goals of sustainability and reduction of energy consumption so, they provided us access to their BAS for the data and study the operation of its facilities. The data scraped from the City's BAS serves can be used to develop statistical/machine learning methods for decision making. We selected a mid-size pilot building to apply these techniques. The process begins with the collection of data from BAS. An Application Programming Interface (API) is developed to login to the servers and scrape data for all data points and store it on the local machine. Then data is cleaned to analyze and model. The dataset contains various data points ranging from indoor and outdoor temperature to fan speed inside the Air Handling Unit (AHU) which are operated by Variable Frequency Drive (VFD). This whole dataset is a time series and is handled accordingly. The cleaned dataset is analyzed to find different patterns and investigate relations between different data points. The analysis helps us in choosing parameters for models that are developed in the next step. Different statistical models are developed to simulate building and equipment behavior. Finally, the models along with the data are used to optimize the building Operation with the equipment constraints to make decisions for building operation which leads to a reduction in energy consumption while maintaining temperature and pressure inside the building.
Show less - Date Issued
- 2019
- Identifier
- CFE0007810, ucf:52335
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007810
- Title
- COUNTER-TERRORISM: WHEN DO STATES ADOPT NEW ANTI-TERROR LEGISLATION?.
- Creator
-
Clesca, Princelee, Dolan, Thomas, University of Central Florida
- Abstract / Description
-
The intent of this thesis is to research the anti-terror legislation of 15 countries and the history of terrorist incidents within those countries. Both the anti-terror legislation and the history of terrorist incidents will be researched within the time period of 1980 to 2009, a 30 year span. This thesis will seek to establish a relationship between the occurrence of terrorist events and when states change their anti-terror legislation. Legislation enacted can vary greatly. Common changes in...
Show moreThe intent of this thesis is to research the anti-terror legislation of 15 countries and the history of terrorist incidents within those countries. Both the anti-terror legislation and the history of terrorist incidents will be researched within the time period of 1980 to 2009, a 30 year span. This thesis will seek to establish a relationship between the occurrence of terrorist events and when states change their anti-terror legislation. Legislation enacted can vary greatly. Common changes in legislation seek to undercut the financing of terrorist organizations, criminalize behaviors, or empower state surveillance capabilities. A quantitative analysis will be performed to establish a relationship between terrorist attacks and legislative changes. A qualitative discussion will follow to analyze specific anti-terror legislation passed by states in response to terrorist events.
Show less - Date Issued
- 2015
- Identifier
- CFH0004851, ucf:45451
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004851
- Title
- Learning Dynamic Network Models for Complex Social Systems.
- Creator
-
Hajibagheri, Alireza, Sukthankar, Gita, Turgut, Damla, Chatterjee, Mainak, Lakkaraju, Kiran, University of Central Florida
- Abstract / Description
-
Human societies are inherently complex and highly dynamic, resulting in rapidly changing social networks, containing multiple types of dyadic interactions. Analyzing these time-varying multiplex networks with approaches developed for static, single layer networks often produces poor results. To address this problem, our approach is to explicitly learn the dynamics of these complex networks. This dissertation focuses on five problems: 1) learning link formation rates; 2) predicting changes in...
Show moreHuman societies are inherently complex and highly dynamic, resulting in rapidly changing social networks, containing multiple types of dyadic interactions. Analyzing these time-varying multiplex networks with approaches developed for static, single layer networks often produces poor results. To address this problem, our approach is to explicitly learn the dynamics of these complex networks. This dissertation focuses on five problems: 1) learning link formation rates; 2) predicting changes in community membership; 3) using time series to predict changes in network structure; 4) modeling coevolution patterns across network layers and 5) extracting information from negative layers of a multiplex network.To study these problems, we created a rich dataset extracted from observing social interactions in the massively multiplayer online game Travian. Most online social media platforms are optimized to support a limited range of social interactions, primarily focusing on communication and information sharing. In contrast, relations in massively-multiplayer online games (MMOGs) are often formed during the course of gameplay and evolve as the game progresses. To analyze the players' behavior, we constructed multiplex networks with link types for raid, communication, and trading.The contributions of this dissertation include 1) extensive experiments on the dynamics of networks formed from diverse social processes; 2) new game theoretic models for community detection in dynamic networks; 3) supervised and unsupervised methods for link prediction in multiplex coevolving networks for both positive and negative links. We demonstrate that our holistic approach for modeling network dynamics in coevolving, multiplex networks outperforms factored methods that separately consider temporal and cross-layer patterns.
Show less - Date Issued
- 2017
- Identifier
- CFE0006598, ucf:51306
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006598
- Title
- Constructing and Validating an Integrative Economic Model of Health Care Systems and Health Care Markets: A Comparative Analysis of OECD Countries.
- Creator
-
Helligso, Jesse, Wan, Thomas, Liu, Albert Xinliang, King, Christian, Hamann, Kerstin, University of Central Florida
- Abstract / Description
-
This dissertation argues that there are three basic types of health care systems used in industrial nations: free market (private insurance and provision), universal (public insurance and private provision), and socialized (public insurance and provision). It examines the role of market forces (supply and demand) within the health care systems and their effects on health outcomes by constructing an integrative model of health care markets and policies that is lacking within the scientific and...
Show moreThis dissertation argues that there are three basic types of health care systems used in industrial nations: free market (private insurance and provision), universal (public insurance and private provision), and socialized (public insurance and provision). It examines the role of market forces (supply and demand) within the health care systems and their effects on health outcomes by constructing an integrative model of health care markets and policies that is lacking within the scientific and academic literature. The results show that, free market systems have decreased access to care, good quality of care, and are economically inefficient resulting in 2.7 years of life expectancy lost and wasted expenditures (expenditures that do not increase life expectancy) of $3474 per capita ($1.12 trillion per year in the U.S.). Socialized systems are the most economically efficient systems but have decreased access to care compared to universal systems, increased access to care compared to free market systems and have the lowest quality of care of all three systems resulting in 3 months of life expectancy lost per capita and a saving of $335 per capita. Universal systems perform better than either of the other 2 systems based on quality and access to care. The models show that health insurance is a Giffen Good; a good that defies the law of demand. This study is the first fully demonstrated case of a Giffen good. This investigation shows how the theoretically informed integrative model behaves as predicted and influences health outcomes contingent upon the system type. To test and substantiate this integrative model, regression analysis, Time-Series-Cross-Section analysis, and structural equation modeling were performed using longitudinal data provided and standardized by the Organization for Economic Cooperation and Development (OECD). The results demonstrate that universal health care systems are superior to the other two systems.
Show less - Date Issued
- 2018
- Identifier
- CFE0007335, ucf:52114
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007335
