Louiqa Raschid - US grants

This project investigates techniques that allow programs written in the Production System (PS) paradigm to reason correctly and efficiently with large databases located on secondary storage. A class of stratified PS programs are identified. For this class of programs, an operational semantics and a model theoretic semantics are developed. The correct semantics ensure that a stratified PS program will correspond to a consistent theory, the execution of the program will not produce incorrect, inconsistent answers and execution of the program will terminate. Implementation techniques for stratified PS programs using relational data structures and relational queries are developed as well as strategies for the concurrent execution of productions in stratified PS programs. The results of this research will provide a foundation for expert systems, written as stratified PS programs, to reason correctly and efficiently with data in relational databases.

Applicants to the NSF 1992 Minority Graduate Fellowship competition who were awarded "Honorable Mention" status and who enrolled in a computer science or computer engineering graduate program at a U.S. university were eligible to apply to the CISE Directorate for this special award. The purpose of the award is to assist the student in both research and educational activities related to his/her graduate education. The award is made on behalf of the student to the institution with the student's advisor designated as principal investigator.

9422138 Dorr This award is to purchase equipment (cost-shared with The Institute for Advanced Computer Studies (UMIACS) and Department of Linguistics at the University of Maryland) dedicated to support specific projects in the laboratory for Computational Linguistics and Information Processing (CLIP). These projects are in the areas of information mediation, language translation and tutoring, and text filtering and retrieval. The software requirements include large dictionaries, corpora, data models and databases, high-level database query languages, and a Prolog interpreter. Since many of these resources are available only on CD ROMs, the hardware requirements include an optical disk controller and large disks for storage. Also there is a need for two workstations with significant computing power for indexing and processing of text and installation of an object server. Finally, four Xterminals for extensive prototype development and an eye-tracker for testing hypotheses related to the development of psycholinguistically-grounded NLP models are needed. ***

This research addresses a number of challenges related to the full realization of the potential of supply chain infrastructures(SCIs), which include those software systems used to support enterprise requirements planning (ERP) and supply chain management (SCM). A software testbed, which initially will include an SCM component, an ERP component and a middleware component, will be constructed. The research will employ techniques from operations research, computer science and empirical information systems. Integer programming based resource allocation models will be developed and embedded within a simulation. The simulation will be used in conjunction with two empirical studies of organizational decision making to explore the relationships between SCIs and organization structure. Research on the development of mechanisms for effective query processing in web-like settings will be pursued with the goal of improving efficient SCI implementation in large organizations. ERP and SCM systems are achieving significant levels of deployment throughout the world. The research undertaken here is aimed at improving the efficiency of
these systems and their effectiveness in enhancing organizational performance.
Practical contributions are anticipated in the following areas: improvements in the understanding
of how information technology impacts organizations and the how organizations should adapt to take advantage of new SCI technology; the development of decision models that both explain how supply chain decision making should take place in organizations and provide new techniques for supply chain decision support; new methods for efficiently implementing scalable web-based applications.

EIA-0130422
Louiqa Raschid
University of Maryland College Park

CISE Research Resources: Infrastructure to Develop a Large Scale Experiment Testbed of Multi-model Resources

The use of the widely distributed collections of structured and unstructured information expressed in multiple languages or modalities provided by the Internet, requires production of scalable, robust algorithms for the discovery of replicated content, determination of delay or access latency of sources, and the confrontation of the inherently dynamic nature of the Internet.

This project's objective is to establish a laboratory testbed providing a controlled environment that captures structural, content, and latency characteristics of the (publicly accessible) Web. This will stimulate collaboration between researchers whose interests range over natural language applications, language independent processing of scanned documents, analysis of video information sources, information retrieval, and wide area applications and resource discovery across heterogeneous servers.

The testbed will support the development and testing of: (1) tools for broad-scale, cross-linguistic analysis and discovery of relevant information across languages and modalities, (2) cost models and access cost catalogs for wide area environments, reflecting the temporal variability in access latency, (3) distributed content based indexing and association of media clips for resource discovery, (4) transcoding and scheduling of multimedia resources for delivery any time and anywhere to disparate clients; from mobile wireless to high speed optical links.

The goal of this research project is to develop a performance target (PT) sensitive optimizer. Performance targets are relevant in the noisy wide area environment where access costs to Internet accessible WebSources exhibit transient behavior, and are best characterized by a distribution of access costs. A PT sensitive optimizer will have the ability to differentiate among multiple alternate WebSources, and to choose a combination of WebSources so as to best meet a performance target for some query (and its query evaluation plan). The ability to meet a target is quantified by a utility function. Existing optimizers and their cost model consider either specific values or expected values for access costs, and are not sensitive to performance targets. This approach characterizes each plan with the expected value of the cost of the plan, as well as the delay; delay is the deviation above the expected value. A Cost-Delay measure (CDM) combines these two values using a cost factor and a delay factor. A simulation based study of the optimizer's aggregate behavior, for a set of queries and a set of remote relations on WebSources will be used to correlate the PT optimizer's selection of plans and WebSources with its success in maximizing utility or meeting a performance target. The results of this project will provide a tunable optimizer for noisy environments that allow applications to be sensitive to performance targets and to better utilize Internet resources.

This proposal will explore fundamental research issues that impact performance and scalability of Wide Area Applications. The proposed research undertakes a comprehensive study of the access latencies and changing behavior of digital resources over time and across different applications, when accessed via the dynamic WAN. One objective of this research is to develop appropriate latency profiles and resource profiles to characterize this behavior. Latency profiles will be developed to reflect the end-to-end delay experienced by a cluster of clients and resources (servers). Resource profiles reflect appropriate metrics, such as existence checking, testing reachability over time, and learning patterns of updates. These profiles will be used to customize service and information delivery to clients, considering both application requirements and the noisy WAN environment. The corresponding algorithms will explore the trade-offs between end-to-end latency and data obsolescence for different application requirements. Research results will aim to establish a consistent framework for profiling and to answer the following question: to what extent can profiling be used in improving clients' availability to resources. Formal results developed in the theoretical study will be evaluated on large scale applications. Collaboration with Corporation for National Research Initiative (CNRI) Handle protocol developers will provide a test-bed for large scale

Collaborative Research: Semantic Map of Biological Data Sources: Entity Identity and Path Characterization

A fundamental problem facing the biological researcher today is correctly identifying a specific instance of a biological entity, e.g., a specific gene or protein, and then obtaining a complete functional characterization of this entity instance by exploring a multiplicity of inter-related sources. While the diversity of available data presents an opportunity to attack this problem, it is accompanied by difficulties in harnessing and exploring data. This collaborative interdisciplinary, inter-institutional research project exploits the researchers' prior expertise on wrapper and mediator technology and apply domain specific semantic knowledge to this problem. The goal is the correct identification and complete characterization of scientific entities by exploring multiple data sources. This project will address three tasks: (1) Construction of a Semantic Map of biological data sources including unique identifiers; links between sources; attributes; and search and query; (2) Learning at the data source, schema, domain and instance level uses the concept of Identity Link to identify equivalent identifiers for the same instance, and (3) Learning the properties of physical links and paths that are implemented among multiple data sources. The topology of links (paths) based on their properties, and Link (Path) Equivalence is applied to the tasks of entity identity and characterization. The tools developed in this project will be accessible via the project Web site (http://www.umiacs.umd.edu/research/CLIP/BFEnt02/), and can be applied by biologists to support ongoing scientific investigations in cancer research and diabetes, resulting in a broad impact in medical research and treatment. The educational impact includes a course on data management solutions for bioinformatics researchers and a workshop on experiment planning using data sources for biologists.

ABSTRACT

While biological databases are well-curated and richly interconnected, data integration remains a manual, time-intensive, and error-prone process. The proposal develops a computational infrastructure that exploits biologists' domain expertise to express and execute data integration protocols for biological pipelines. Several challenges to be addressed include: (1) an exploration interface that can express high-level complex queries that in turn are translated into lower-level data manipulation operators, (2) the specification and population of an alternative splice protein analysis pipeline, and (3) a mediation testbed that is implemented using XML based wrapper technology and mediator technology (IBM DB2 II).

The metrics of links and paths existing between integrated databases may be used to characterize query results in ways that are useful to biologists and data administrators and this proposal develops models to predict these metrics. Navigational queries require traversing multiple paths that differ in cost and benefit (result cardinality). Cost models and domain and task specific semantics are used to choose the best path or set of paths for a biological pipeline.

The research addresses many of the SEIII challenges of large scale data sharing. The project addresses the exploration of databases by biologists; captures and exploits domain specific knowledge; develops efficient methodology to compute results and designs and populates a publicly accessible pipeline and website. The broader impact beyond the specific biological resources and protein pipeline is the development of a methodology and evaluation platform that can be applied to any task that requires access to, and analysis of, multiple inter-connected heterogeneous resources.

The December 26, 2004 Sumatran-Andaman earthquake and subsequent tsunami led to the discovery of two critical scenarios. There is a deficit of information management systems within the government sector countries on the coast of the Indian Ocean. Globally, there is no disaster management software that can handle a variety of disaster information management needs. This project explores intellectual challenges of data management, in the context of Sahana, an open source disaster information management system that was deployed in Sri Lanka within days of the disaster.

The first challenge is the design of the data management component for disaster information management. While database design is not a challenge, understanding the scope of information that should be accessed during and after a disaster is a challenge. The second challenge is a plan for data acquisition, data cleaning,
integration and quality, in the context of a National Data Center (NDC) for Sri Lanka. While solutions to similar challenges have been reported in the literature, the lack of computerized information management systems in Sri Lanka makes the task a challenge. This US research team has expertise in wide area database
management (Raschid) and open source development and Web services (Weerawarana). Karunaratne from the University of Colombo School of Computing (UCSC) and Madurapperuma from the the University of
Moratuwa in Sri Lanka provide domain expertise. The need for broader impact is met via the development of open source global disaster management systems and the design of a national information infrastructure for Sri Lanka. The project Web site http://www.umiacs.umd.edu/labs/CLIP/Handle/SGERtsunami.html is to be used for communication about the exploratory project and for disseminating results.

An Industry/University Cooperative Research Center (I/UCRC) Planning meeting will be conducted to determine the organization and viability of forming a new multi-university I/UCRC for Health Information and Decision Systems with the University of Maryland as the lead, and the Massachusetts General Hospital as a research site. This new Center aims to advance the science of information technology implementation and decision analysis in the health care sector and to better understand its impacts at all levels, including organizational, provider, and individual outcomes.

ABSTRACT

Access to up-to-date and quality information can have a significant impact on the humanitarian relief community as they coordinate relief efforts. In addition to data that is created and curated by experts, there is a vast volunteer community who are empowered by the social Web to generate community curated content on sites such as Flickr, Del.icio.us, and Google Earth. Combining data from experts and volunteers can facilitate the efforts of relief agencies. In order to effectively use this data, one needs to (1) discover relevant sources, (2) assess quality, and (3) understand their content. Fortunately, the wealth of content and metadata, i.e., annotations in the form of tags, on the social Web, can aid in this task of semantic discovery and quality assessment.

The GeoNets project will develop methods to analyze social content and metadata in order to extract concepts, including geospatial concepts and generate semantically-rich geospatial data. GeoNets can also increase the re-use of data by suggesting terms to improve the quality of existing annotations. GeoNets will develop methodologies for semantic discovery and quality assessment to create a GeoNets dataspace and provide a user friendly query language.

The methods developed by the project also apply to other fields where information created by a lay community augments the knowledge produced by professionals. In several scientific disciplines, including astronomy, biology and ecology, an army of passionate amateurs is making new observations and discoveries. GeoNets will create tools that will enable scientists to leverage community-generated knowledge to create up-to-date, semantically rich dataspaces."

The life science research community generates an abundance of data on genes, proteins, sequences, etc. These are captured in publicly available resources such as Entrez Gene, PDB and PubMed and in focused collections such as TAIR and OMIM. A number of ontologies such as GO, PO and UMLS are in use to increase interoperability. Records in these resources are typically annotated with controlled vocabulary (CV) terms from one or more ontologies. Records are often hyperlinked to those in other repositories, creating a richly curated biological Web of semantic knowledge.

The objective of this project is to develop tools to explore and mine this rich Web of annotated and hyperlinked entries so as to discover meaningful patterns.
The approach builds upon finding potentially meaningful and novel associations between pairs of CV terms cross multiple ontologies. The bridge of associations across ontologies reflects annotation practices across repositories. A variety of graph data mining and network analysis techniques are being explored to find complex patterns of groups of CV terms cross multiple ontologies. The intent is to identify biologically meaningful associations that yield nuggets of actionable knowledge to be made available to the scientist together with a set of golden publications that support the identified patterns.

The intellectual merit of the project is that it is unique in comparison to other bioinformatics data integration and analysis projects. Data is integrated from across numerous sources including genes, gene annotations, ontologies, and the literature. The exploratory nature (EAGER) of this research is both with respect to the biological and the computer science disciplines. From the biological viewpoint, a high level of speculation is associated with any discovered biological patterns. Discovered patterns night not necessarily meet criteria for experimental validation. The research methodology combines algorithmic and analytical techniques from multiple computer science sub-disciplines. While specific technical innovations are expected, an inter-related set of computer science challenges needs to be defined.
This research has the potential for broader impact since the methodology can be applied to any type of interlinked resources on the biological semantic Web as well as to any collection of hyperlinked resources. This research is a collaboration between the University of Maryland and the University of Iowa. For further information see the project web pages at the following URL:
http://www.umiacs.umd.edu/research/CLIP/RSEAGER2009/

Workshop on Knowledge Representation and Information Management for Financial Risk Management (KR-Financial Risk)

The credit crisis of 2008 and the ensuing Great Recession have shone a light into the hitherto esoteric world of investment data processing. The lack of consensus or acceptable best practices around standards, agreed upon definitions, procedures, metrics, and mathematical techniques have left supervisory agencies unable to ingest market information in either a timely manner that would permit a macro-prudential response, or even determine what information might be missing. This has resulted in the following unsatisfactory situation:
* Corporate managers are uncertain of the trustworthiness of
their internal risk and accounting numbers;
* The academic community is lacking the information required to
examine and analyze actual market operations and behavior;
* Regulators, analysts, and the financial press are denied an
understanding of capital market operations sufficient to
forge knowledgeable and prudent financial policy.

The purpose of this NSF-sponsored workshop is to help develop the underlying theory and framework that might unify the disparate ongoing and planned efforts at understanding and managing the enormous data and information flows in the financial services industry, and to develop a comprehensive list of the challenges in this domain with respect to robust risk assessment and management.

The workshop will draw upon an interdisciplinary team of experts from computer science (data management and mining and knowledge representation), finance, mathematics, economics and operations research. The workshop will generate a report which will develop a comprehensive list of the challenges in this domain including the fundamental forces and constraints and policies and models of information management that are critical for robust financial risk management.

The proposal aims at studying authorship flows in information diffusion in social media. The proposal takes an individual level approach to understanding diffusion and authorship flow as compared to existing macro level approaches. The proposed approach is to study the impact of factors such as the type of media format, the type of topics diffused and the valence of the information in information diffusion and authorship flow. An initial taxonomy will be used to classify the type of media format that may evolve with the study. Three models will be combined in the research. The dataset to be used large-scale blogs and tweets. If successful, the project can help to establish a theoretical foundation for understanding the diffusion and authority in digital media.

The Great Recession of 2008, and its reverberations that are being felt all over the world even several years later, have highlighted significant limitations in the ability of regulators and analysts/researchers to monitor and model the national and global financial ecosystem. Specifically, there is an urgent need for financial cyberinfrastructure to ingest and process numerous streams of financial transactions, as well as the accompanying data streams of economic activity, in real time. Also absent are open standards and shared semantics so that this data can be used to populate models of individual markets, financial networks and the interconnected ecosystem representing the global financial system. This calls for focused efforts aimed at developing computational research frameworks, models and methods, as well as the necessary cyberinfrastructure for regulating systemic risk in financial systems on par with efforts in other areas of national priority.

Against this background, this workshop (and related activities) aims to bring together an interdisciplinary group of academics in Computer Science, Finance, Economics and Social Sciences to work closely with the OFR and other regulatory agencies, and the financial and the computing industrises to: (1) Develop a blueprint for next generation financial cyberinfrastructure for regulating and mitigating systemic risk in financial markets (2) Identify the computational research challenges that need to be addressed in order to realize a cyber-enabled framework for regulating systemic risk; (3) Develop best practices for a cyber-enabled regulatory framework; and (4) Prepare a diverse cadre of PhD students to pursue multi-disciplinary research in Finance Informatics.

A one and a half day workshop will be organized in Washington D.C. A doctoral consortium will be held concurrently with the workshop and continued at the University of Maryland. The doctoral consortium will be aimed at graduate students with strong backgrounds in mathematics and computer science and an interest in some aspect of finance informatics. The doctoral consortium participants will be exposed to a multi-disciplinary curriculum that reflects many of research areas and methodologies that are discussed in the report on computational research challenges. The workshop report will be widely disseminated through a variety of venues.

Collaborative grants have been awarded to the University of Maryland, the University of Iowa and St. Bonaventure University to develop a methodology that exploits the wealth of annotation knowledge, notably Gene Ontology (GO) and Plant Ontology (PO) annotations of Arabidopsis genes. Motivated by the availability of rich and as yet insufficiently tapped collections of gene annotations, the project aims to facilitate the discovery of hidden knowledge that could be the basis of further scientific research. The methodology will extract patterns of interest from annotation graphs (pattern discovery). Literature-based methods will extract sentences that validate the biological meaning underlying these patterns (pattern validation). To demonstrate the methodology, the PattArAn tool (Patterns in Arabidopsis Annotations) will be customized for Arabidopsis. PattArAn will provide the user with a graphical presentation of patterns of Arabidopsis genes and associated GO and PO CV terms. Graph data mining techniques and efficient algorithmic solutions to identify dense subgraphs (DSG) and to perform graph summarization (GS) will be developed. Algorithms to mine the literature for relevant sentences for an extracted pattern (referred to as the imprint) will be developed. PattArAn will enable iterative exploration and will incorporate allied steps such as consulting gene function prediction. The project will involve collaboration with biologists for building and refining annotation graphs, and validating patterns to ensure relevance to their research.

The project makes broad contributions to the Arabidopsis thaliana community. PattArAn may assist Arabidopsis curators to manage GO-PO annotations and complement existing tools such as Textpresso and AraNet. It can also be used to bootstrap an annotation database for other plant species given that their genome sequence information is available. The project offers significant research and educational experiences for graduate students (University of Maryland and Iowa) and undergraduate students (St. Bonaventure University). Team members will continue to mentor women and students from under-represented communities, participate in outreach activities, lead a Journal Club, etc. The outcomes from this research project will be disseminated via biology and bioinformatics venues. More information may be obtained at the project website: https://wiki.umiacs.umd.edu/clip/pattaran/.

There is an urgent need for models of financial ecosystems that are driven and informed by data. Unfortunately, current financial cyberinfrastructures severely restrict the availability of data to market participants, regulators and researchers. There are constraints on the data collection authority of regulators that are exacerbated by the lack of ontologies and standards. Beyond these limitations is the inherent challenge of dealing with the complexity of financial information and meeting the diverse and sophisticated analyses required to model heterogeneous ecosystems.

For computer scientists to get engaged, a central requirement is the availability of data -- as exemplar and for testing and benchmarking. While some types of data are easily available, many other important types of financial data are proprietary and generally unavailable to the computing research community. The creation of a community infrastructure can go a long way toward meeting this need and hence enabling computer science research in a new domain of data science for finance.

The impact of the next generation of community financial cyberinfrastructure and a framework of data science for finance will be significant. There will be increasing synergy from applying computational technology, BIGDATA and Linked Data, and social media, to address difficult modeling and monitoring problems. This may result in improved tools for regulators, as well as fundamentally new designs of market mechanisms, recommendations, ratings, etc. On the educational frontier, data science for finance should nurture a new generation of multi-disciplinary scholars who will blend computational solutions with theories, models and methodologies from finance, economics, mathematics and statistics.

A data and information revolution is transforming all aspects of our life, all disciplines, and all sectors of the economy. The "big data" market is predicted to reach $50 billion by 2017, with 40% and 22% market share for services and software, respectively. While products and services continue to mature, assured and scalable data services remain major challenges. This necessitates data architectures and tools that can match the scale of the data and support timely and assured decision making. 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. The center will support the innovation of data architectures and tools that can match the scale of the data, and that support timely and assured decision making. Methods for information integration, analytics and visualization will help non-data-experts (in governmental and commercial sectors) to make decisions and to generate value. The key audience for the proposed NSF I/UCRC Center for Assured and SCAlable Data Engineering (CASCADE) include (a) small, medium, and large companies that rely heavily on data services (especially in the finance and energy sectors), (b) small, medium, and large companies in data technologies, and (c) government agencies and regulators. CASCADE will play an important role in developing assured and scalable data technologies that in turn will enable applications and services with significant economic and environmental impact. This includes financial fraud prevention, monitoring financial supply chains and applications in the energy and sustainability sectors. The broader impacts of the proposed project will include technology and knowledge transfer to the industrial sector, graduate and undergraduate education through mentoring of PhD students, and updates to the CSE curriculum through the incorporation of research into existing undergraduate and graduate classes. CASCADE activities will train computer science students in the methodologies that support scalable and secure data engineering and will familiarize them with real world challenges in critical domains including the financial sector and clean energy. CASCADE will also contribute to diversity on the workforce through recruitment of female and minority students.

If we want to fundamentally alter the way data systems are designed and significantly change current practices, we need to ensure that data analysis, data assurance, and data management technology components are developed synergistically to achieve the following targets: (1) The design and development of each component is informed by the requirements and limitations of the others; (2) Each takes full advantage of the services and capabilities provided by the others; (3) They continuously adapt as the analysis, assurance, and management contexts evolve with the needs of the deployed application systems that they all support. A key CASCADE goal is to empower domain experts and decision makers through assured and scalable data systems, and to provide reliable and timely decision making through a sense&integrate, simulate&predict, validate&interpret, and act&adapt feedback loop. This planning grant's objective is to organize a meeting with industry partners and the universities to outline a research agenda for CASCADE. The industrial/academic partnerships of CASCADE will enable new algorithms, tools, and systems that securely manage, share, access, and analyze heterogeneous sets of static or transient data to accommodate diverse security requirements, including trust, availability, confidentiality, and integrity. 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.

The NSF Convergence Accelerator supports team-based, multidisciplinary efforts that address challenges of national importance and show potential for deliverables in the near future.

The broader impact and potential societal benefit of this Convergence Accelerator Phase I project is to lay the foundation for capturing the essential knowledge about businesses, innovation, and markets and to use the latest techniques in computer science to make this knowledge freely available in easily usable forms. The project is a partnership between faculty in business schools and computer science departments and will engage partners in regulatory agencies as well as financial technology companies. The proposed Business Open Knowledge Network (BOKN) will provide the resources necessary for entrepreneurs to fully understand the competitive landscape as they create small businesses, allow regulators to quickly identify issues to help prevent the next financial crisis, and enable researchers to develop and test theories to transform our nation's business practices. Using the BOKN resource, a new generation of students and scholars will be able to blend computational solutions with theories, models, and methodologies from finance, economics, mathematics, and statistics leading to increased understanding as well as broader opportunities for scholarship.

The project efforts to develop the BOKN will require the development of new research approaches that can combine state-of-the-art computational approaches for extracting, representing, linking, and analyzing data with complex and nuanced knowledge about the business domain. The project team will develop business and finance-specific computational tools that can leverage a wealth of unstructured data on the Web, as well as semi-structured data and time series datasets provided for regulatory or legal purposes, and reference datasets with standard identifiers and metadata that enable cross-resource federation. Business expertise will drive these computational tools by defining a concrete ontology of concepts, identifying the key entities of interest, and validating the extracted knowledge and downstream predictions in a series of practical use cases. One expected technical result is the creation of a hybrid knowledge graph that supports traditional symbolic knowledge representation and reasoning enhanced by high-dimensional vector space embeddings capturing temporal evolution and semantic relationships that support machine learning applications.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

This COVID-19 RAPID project combines the efforts of the NSF Convergence Accelerator Business Open Knowledge Network (BOKN) and Manufacturing Open Knowledge Network (MOKN) in order to develop a knowledge resource to support the discovery of manufacturers and materials suppliers to help assemble new supply chains, particularly focusing on personal protective equipment (PPE), such as ventilators. The BOKN encodes information about businesses and their capabilities, while the MOKN encodes manufacturing information about goods. By combining information and capabilities from both networks, this integrative COVID RAPID project will develop search and matching tools that will help entrepreneurs and manufacturers to adapt swiftly to the supply chains and processes needed to produce new types of products. The key information along with analysis capabilities for performing information extraction, data cleaning, and data representation will be accessible via a web portal, initially focusing on supply chains for PPE. The resources developed can be used equally well by small businesses and entrepreneurs as well as more established organizations.

The project will harness data from a diverse set of sources, including manufacturing designs open-sourced by manufacturers; component information from shipping manifests; and manufacturing capabilities of firms sourced from websites and social media pages. Services provided via the web portal will enable users to find data, determine where to source components, and/or which designs to produce from these components. The project will develop an end-to-end system for generating, representing and populating new supply chains and processes focusing, initially, on the manufacture of PPE. These objectives will be achieved by the creation of enhanced interfaces for navigating company information, including relationships to other companies and profile information about each business. Learned representations of manufacturing firms will be developed in vector space models to better capture manufacturing capabilities and to investigate fuzzy matching capabilities for materials, parts, and sub-components. The materials and parts mentioned in patent claims for PPE will be of particular interest. The project will create the relationships between bill of lading data and domestic importers, and potential suppliers of materials and parts. Users will be able to integrate offerings from multiple information sources to rapidly meet emergent production needs, beginning initially with PPE, but extendibly to other critical products.

This RAPID award is made by the Convergence Accelerator program in the Office of Integrative Activities and is associated with the Convergence Accelerator Track A: Open Knowledge Network.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

An effective response to fight the spread of a pandemic requires a clear understanding of the complex interactions between biological, environmental and human networks. The COVID19 pandemic revealed both human and systemic failures along this chain. A key takeaway was the need for timely, relevant and actionable information to support effective public messaging and policy making that can impact in-real-life (IRL) outcomes. The COVID19 pandemic also revealed the need for messaging and policy making at a local scale, when national- or state-level approaches might not appropriately address the needs at community scale. Frontline public health officials often had little insight into the individuals that they wished to serve. Decision makers who managed cities or school systems often relied on epidemiological models that did not account for the impact of human beliefs and in-real-life behaviors - e.g., the willingness to wear a mask - on disease transmission. The PandEval project will address these challenges, so as to ultimately increase the trust and confidence in our public health infrastructure. If successful, public health officials will gain insight into the success of (past) messaging campaigns so that they can deliver the right message at the right time. In addition, decision makers will be able to use the outcomes of the epidemiological models, customized to population segments, while planning vaccine rollout, or admitting visitors to congregate living.<br/><br/>The innovation of the PandEval project is to rely on curating rich complex multimodal datasets. Social media-based models of community beliefs and attitudes around science skepticism, moral foundations, or the willingness to contribute to the public good, will be developed. Baseline profiles of in-real-life (IRL) behavior tracked by human mobility traces will be computed. Compartmental epidemiological models that account for population characteristics will be customized to account for a diversity of micro-targeted population segments and regions across the US. The PandEval platform will be engineered to measure the effectiveness of community targeted messaging around pandemic mitigation, including recommendations and mandates, and to measure the prediction accuracy of the customized epidemiological models. As the nation faces the potential of endemic COVID19, the PandEval project will create and curate Pand-Index, an index of online social beliefs and in-real-life (IRL) profiles at a national scale. Pand-Index profiles will help individuals to make personalized decisions about social distancing or masking versus working from home.<br/><br/>This award is supported by the cross-directorate Predictive Intelligence for Pandemic Prevention Phase I (PIPP) program, which is jointly funded by the Directorates for Biological Sciences (BIO), Computer Information Science and Engineering (CISE), Engineering (ENG) and Social, Behavioral and Economic Sciences (SBE).<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

The goal of this workshop is to explore active human centered approaches to develop a framework that supports the integration of ethical considerations and constraints into the design of AIs, from the ground up, and starting from an early phase of requirements gathering and feature specification. The hope is thatthe human centered active approach, and the early consideration of ethical and social requirements, will have a significant payoff in promoting human well-being.<br/><br/>The workshop will address four areas: 1.) Knowledge Representation: The development of methodology(ies)for the acquisition, validation, and representation of ethical information in a way that can be incorporated into system design; 2.) Design Guidelines: Strategies that incorporate human centered design principles into the design of User Interfaces (UIs); 3.) Metrics: The definition of evaluation metrics to test the success and limitations of prototype AI solutions in some selected domains; 4.) Regulation and Compliance: Crafting regulations to be more easily incorporated during design to improve and ensure compliance.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.