Sample Projects
Research Project @ CASCADE
Seed Project: Towards Socially Graceful Autonomous Vehicles via Data-driven Modelling and Optimization
Zhang, Wnlong; Yang, Yezhou; Ren, Yi
The current problem with autonomous vehicles stems from the unpredictability that comes with the “social norms” of humans on the road, autonomous vehicles currently lack the ability to predict the intents of other drivers, or understand how other drivers perceive their intents. As stated in the proposal, “The project will focus on the development of control mechanisms that naturally derives motions that are socially “acceptable”, the definition of which is culturally dependent.” Specifically, research will focus on two areas, lane changing and stop sign passing. Through their research, the team plans to collect driving behavioral data from the human participants using a mobile robot testbed, develop data-driven models for human drivers, and evaluate the motion planning algorithm in experiments with human participants. In turn, their research could improve the safety and efficiency of transportation systems, and increase acceptance of autonomous vehicle technologies.
Seed Project: Distributed and Low-Latency Big Data Computing Systems
Ying, Li
This project is attempting to innovate on the current state of big data computing systems that are not suitable for processing large-scale real-time sensing data from mobile devices and sensors. These applications face the problem of transferring big datasets to a data center for processing, this challenge arises from either real-time processing requirements or bandwidth constraints. As stated in the project proposal, the team aims to explore the viability of “computing-centric networking for building distributed self-organizing big data computing systems.” This new system consists of three layers, the Computing Layer, the Computing-centric Network Layer, and the Data Layer. These layers should be able to integrate heterogeneous computing platforms ranging from high-performance servers, mobile devices to energy-constrained sensors and controllers. The goal of these new architectures and algorithms is to “balance the computation and communication in big-data computing networks, regulate the computing requests to avoid overloading the system, reduce task processing delay, balance the lifetime of devices and the performance of computing, and guarantee fairness among different computing tasks.”
Seed Project: Learning complex structures under cascading disasters through heterogeneous spatiotemporal time series
Pedriellie, Giulia; Sarwats, Mohamed
This project addresses the CASCADE challenge of Data Engineering for Sustainability, Natural Resources, and Hazards, by looking at the application of electric power generation in the event of a failure. The team is aiming to collect and store data that reconstruct the underlying electric power networks with access to only partial data about the nodes behaviors. As one may have guessed, some major challenges persist when attempting to complete this task such as storing heterogeneous data, quickly retrieving information from heterogeneous places, and analyzing the information gathered from simulated models. The proposal team plans to address these challenges by using advanced analytical methods that can understand heterogeneous data to recreate the original infrastructure that created them. As an outcome of this project, the team aims to produce a software package that is able to understand electric network information from large data sets and simulations. This software package will then produce a set of possible network configurations that can produce the data. If successful, the data processing algorithms and analytics algorithm will have a significant impact on CASCADE members ability to utilize heterogeneous data sources. The produced software can also be extended and adopted by utility companies for network analysis and supporting decision making.
Seed Project: Blockchain operated safety deposit boxes for storage and item sales
Jevtic, Peter; Metel, Michael
The project proposes a physical storage space (similar to safety deposit boxes), that utilizes blockchain technology to allow the space to be controlled remotely anywhere in the world. Each locker bank will have a computer monitoring a specific blockchain (such as the Ethereum blockchain), in which each locker is controlled by a unique smart contract. The user can send messages to these contracts that the computer reads to do things such as lock the box, open and close a peephole, shut the locker, close the contract, check the contracts balance, and conduct any other action placed upon the box such as transferring ownership. The variability that comes with these lockboxes means the use cases can range from users easily storing valuable possessions overseas, to the online buying and selling of merchandise. The research gathered from this project can provide a better understanding of blockchain technology when applied to actuarial sciences, along with a proof of concept for the commercial use of this type of technology.
Collaborative Research: Planning Grant: IUCRC for Assured and SCAlable Data Engineering (CASCADE)
Candan, Kasim Selcuk; Ahn, Gail-Joo; Davulcu, Hasan
The vision of the proposed NSF I/UCRC Center for Assured and SCAlable Data Engineering (CASCADE) is to enable a fundamental shift from current ad hoc approaches to the engineering of data systems, towards a principled framework for the engineering of data systems that support reliable and timely data-driven decision making. Through synergistic industry/academy partnerships, CASCADE will enable a strategic framework that includes multi-disciplinary teams that translate technological insights obtained from fundamental research on (a) trusted and privacy-preserving data processing and analysis, (b) real-time data processing and analysis, (c) parallel and distributed data processing and analysis, and (d) high dimensional and multi-modal data processing and analysis, into new key technology elements whose different instantiations are deployed for direct impact to various critical industries including in the energy and finance sectors.
Toward new classification criteria for mild and moderate TBI by a data-inclusive cross-study analysis using FITBIR
Li, Jing; Wu, Teresa
The current method of classifying the severity of traumatic brain injuries, a leading cause of death and disability, is imprecise; patients who have very different severities of injury and post-injury symptoms are often classified into the same traumatic brain injury group. This research will use multifaceted data contained within FITBIR to discover new severity subtypes of traumatic brain injury based upon predicted patient outcomes. Provision of diagnostic criteria for new traumatic brain injury severity subtypes will assist clinicians with determining how aggressive to be with rehabilitative therapies, will allow clinicians to provide more accurate prognoses to their patients and will assist researchers with determining which patients should be considered for clinical trials of new traumatic brain injury therapies.
Commercialization of the Social Influence Algorithms for Information Operations
Shakarian, Paulo
N.A.
EAGER: Data Management Systems Support for Personalized Recommendation Applications
Sarwat, Mohamed; Candan, Kasim Selcuk
A recommender system exploits the users' opinions in order to extract a set of interesting items for each user. This project conducts research, develop requisite knowledge and build software infrastructure to support efficient, scalable, and usable data management for personalized recommendation applications. The project tackles the following system challenges to support recommendation applications: (1) Flexibility and Usability: The user should be able to declaratively define a variety of recommenders using popular recommendation algorithms that fit the application needs. The system must be able to integrate the recommendation functionality with other data attributes/sources as well as performing the recommendation functionality and other data access operations side by side. (2) Efficiency and scalability: The system is expected to produce personalized recommendations to a high number of users concurrently over a large pool of items.
BIGDATA: Collaborative Research: F: Discovering Context-Sensitive Impact in Complex Systems
Candan, Kasim Selcuk; Zhao, Ming
In complex systems, (a) it is critical to discover how one object influences others within specific contexts, rather than seeking an overall measure of impact, and (b) the context-aware understanding of impact has the potential to transform the way people explore, search, and make decisions in complex systems.The technical goal of this project is to establish the theoretical, algorithmic, and computational foundations of big data-driven context-sensitive impact discovery in complex systems. This project develops probabilistic and tensor-based models to capture context-sensitive impact from complex systems, often modeled as graphs, and designs efficient learning algorithms that can capture both the contexts and the impact scores among entities within these different contexts. The modeling of the context-sensitive impact considers dynamic nature of relevant contexts and the diverse applications.
Models for Dense Urban Areas
Papotti, Paulo; Candan, Kasim Selcuk
Big data technologies have been successfully applied to many disciplines for knowledge discovery and decision making, but the further growth and adoption of the big data paradigm face several critical challenges. Therefore, this project is developing the needed computational infrastructure to support GEARS (an enerGy-Efficient big-datA Research System) for studying heterogeneous and dynamic data using heterogeneous computing and storage resources. GEARS is a one-of-kind, energy-efficient big-data research infrastructure based on cohesively co-designed software and hardware components. It enables a variety of important studies on heterogeneous and dynamic data and advances the scientific knowledge in computer science as well as other data-driven disciplines.
II-New: GEARS - An Infrastructure for Energy-Efficient Big Data Research on Heterogenous and Dynamic Data
Zhao, Ming; Candan, Kasim Selcuk; Maciejewski, Ross; Tong, Hanghang; Davulcu, Hasan; Ren, Fengbo; He, Jingrui; Li, Baoxin; Liu, Huan
Big data technologies have been successfully applied to many disciplines for knowledge discovery and decision making, but the further growth and adoption of the big data paradigm face several critical challenges. Therefore, this project is developing the needed computational infrastructure to support GEARS (an enerGy-Efficient big-datA Research System) for studying heterogeneous and dynamic data using heterogeneous computing and storage resources. GEARS is a one-of-kind, energy-efficient big-data research infrastructure based on cohesively co-designed software and hardware components. It enables a variety of important studies on heterogeneous and dynamic data and advances the scientific knowledge in computer science as well as other data-driven disciplines.
SCC-Planning: Smart Connected Engaged Senior Communities
Wu, Teresa; O'Neill, Zheng; Mirchandani, Pitu; Knopf, Richard; Wen, Jin
This S&CC planning grant brings together researchers from three institutions (Arizona State University, Drexel University and University of Alabama) and seven disciplines (system engineering and health informatics, community development, transportation systems, computer science, mechanical engineering, electrical engineering and architectural engineering) to understand the unique challenges in senior communities. Fundamental research questions from six research themes are to be studied. The six themes are (1) community with the social connection; (2) smart transportation; (3) health mentors; (4) smart homes; (5) smart sensors; and (6) data management and integration. With strong engagements from senior communities, this project will enable knowledge discovery for design and development of smart, connected and engaged senior communities.
PFI: BIC Fraud Detection via Visual Analytics: An Infrastructure to Support Complex Financial Patterns (CFP)-based Real-Time Services Delivery
Davulcu, Hasan; Candan, Kasim Selcuk
This partnership for Innovation: Building Innovation Capacity (PFI: BIC) project from Arizona State University focuses on building a platform that will integrate data from multiple sources and explore data analysis techniques that can more accurately detect indications of financial fraud. According to Federal Trade Commission's (FTC) annual "Consumer Sentinel Network Data Book", the most comprehensive database of U.S. fraud trends, American consumers submitted more than 1.5 million complaints - a 62 percent increase in just three years, and they reported losing over $1.6 billion to fraud in 2013. Detecting increasingly complex fraud schemes requires services that are able to integrate and enrich data from disparate financial and other data sources and hunt for recurring and often interconnected anomalous patterns in large networks. The proposed platform will enable integration and enrichment of limited private financial data with larger publicly available data sets to detect fraud and reduce losses due to fraudulent transactions. The project will also include training and research experience for undergraduate and graduate students
CASCADE R&D is supported by funds from several funding agencies, including NSF and DOE, as well as various industrial partners.