|
||||||||||||||||||||||||||||||||||||||||||||||||
|
|
||||||||||||||||||||||||||||||||||||||||||||||||
|
Invited Speakers Talk Abstracts and Speaker Bios Accepted Papers Selected Paper Abstracts Program Schedule Invited Speakers Dr. Romain Murenzi, former Rwandan Minister of Science & Technology V.S. Subrahmanian, University of Maryland Dylan Schmorrow, Office of the Secretary of Defence Philip Schrodt, Pennsylvania State University Brian Kettler, Lockheed Martin Talk Abstracts and Speaker Bios An Attempt at Computational Modeling of Conflict Resolution in Africa Using the Rwanda Model by the Hon. Romain Murenzi In this lecture, we will first discuss some conflicts in Africa with a special focus to the “Great Lakes region” located in Central East Africa (Rwanda, Burundi, Congo, Uganda, Tanzania, and Kenya). This region has received extensive international attention due the “Genocide of the Tutsi” that occurred in Rwanda fifteen (15) years ago from April 7 to July 4, 1994. This genocide was a result of planning by the government of the time. It used Hutu majority to kill, in a barbaric way, the “Tutsi” minority with the aim of wiping them out. In this conflict, one million “Tutsi” lost their lives. The genocide had a negative impact on the whole region as the genocidal forces fled to the neighboring countries: Burundi, Uganda, Tanzania, and mostly the Congo. The main base for the “Genocidal Forces” is in Congo. Their intention is to come back to Rwanda and finish the job. Secondly, we will discuss how the current government was able to avoid the status of “failed state” and build a united, democratic, economically viable state, culminating in the adoption of the constitution in 2003 and the first free presidential election in the same year. This led Ambassador Andrew Young to produce a film in 2007 entitled: ”Rising Rwanda.” The successes of Rwanda can be summarized in this quote from the current US Secretary of State, Hillary Clinton, at the 8th AGOA Kenya forum on August 8, 2009: Today, we look to nearby Rwanda. Progress sometimes comes so slowly. But in a country that had been ravaged by genocidal conflict, the progress is amazing. It has one of the fastest growing economies in Africa, even in the midst of the global recession. Health indicators are improving. The Rwandan people believed in themselves. And their leaders, led by President Kagame, believed in policies based on evidence and measurable results, including a nationwide emphasis on family planning, cross-cutting partnerships with donors and NGOs, a greater premium on professionalism in the government and the health sector.” Thirdly, we will discuss how the Government has been paramount in building peace in the Region. In conclusion, we will discuss the most salient features of the Rwanda’s conflict resolution mechanism. We will conclude by asking following questions: a) Can the Rwanda model/approach to conflict resolution be analyzed in order to find some key ingredients to modern ethnic conflicts? b) Can the methods used in the Laboratory for Computational Cultural Dynamics be applied to these ingredients for building a model for post-conflict nation building? c) Can this model be applied other regions such as Afghanistan and Iraq? Biography Hon. Romain Murenzi is currently a Visiting Professor at the University of Maryland Institute of Advanced Computer Studies, a Senior Scholar at the American Association for the Advancement of Science, and Visiting Professor of Physics at Howard University. From 2006 to 2009 Murenzi served the nation of Rwanda as the Minister for Science, Technology, and Scientific Research. From 2001 to 2006 he was the Minister of Education, Science, Technology, and Scientific Research. From 1999 to 2001 Murenzi was the Chairman of the Physics Department at Clark Atlanta University. Romain Murenzi serves the Council of Third World Academy of Science as Vice President for Africa, is on the Advisory Board of Scientists Without Borders, the board of the African Institute of Mathematical Sciences, and a member of the Scientific Board of UNESCO International Basic Science Program. Reasoning About Diverse Cultures Using Multi-Disciplinary Teams and Computer Technology in the Human Social Culture Behavior (HSCB) Modeling Program by Cmdr. Dylan Schmorrow The Human Social Culture Behavior (HSCB) Modeling program vision includes developing unbiased, objective, valid science-based approaches to enable DoD Operations Planning, Information Operations, Analysis, Intelligence, Experimentation, and Training. Specifically, quantitative models and shaping tools that provide assessments, forecasts, options for courses of action, and decision support for understanding and reasoning about the human terrain of battlespaces. Multi-disciplinary research is necessary in developing computational models for cultural dynamics. HSCB performers have addressed this need by forming multi-disciplinary teams in the same organization, subcontracting to organizations with the necessary skills, or hiring consultants. In addition, the HSCB Modeling program is taking advantage of advances in computer technologies to support data gathering, tool/model/training environment development, system integration, and results visualization and interpretation. An illustrative mission thread will be used to highlight how multi-disciplinary teams and advances in computer technology are supporting the collection of data-to use of that data in tools/models-through visualizing and interpreting results. Finally, HSCB success stories of computational models for cultural dynamics that enhanced cultural sensitivity will be shared. Biography Commander Schmorrow is a U.S. Naval Officer in the Navy’s Medical Service Corps and serves as the Specialty Leader of the Aerospace Experimental Psychologist community. He is also an Acquisition Professional in the Naval Acquisition Corps and is currently serving in the Office of the Director, Defense Research and Engineering as Biosystems Associate Director, Human Systems. He is responsible for S&T programs in the Human Systems (HS) Technology area, which includes DoD programs in personnel selection, training and leadership, cognitive sciences, interface design, personnel protection, combat feeding, human systems integration and human performance. He monitors S&T planning and programming to facilitate applicable insertion into military acquisition programs supporting U.S. warfighters. He also serves as the Program Director for the OSD Human, Social, Culture and Behavioral Modeling research and development program that is focused on providing DoD and the US Government with the ability to understand and effectively operate in human/social/culture terrains inherent to non-conventional warfare missions. His interests include advancing information technology, neuroscience, human-factors, training, autonomy, and decision upport technologies to maximize human performance. He frequently collaborates with the National Science Foundation, the National Institutes of Health, the Department of Homeland Security, the Defense Advanced Research Projects Agency (DARPA), and the DoD Services to improve warfighting capabilities and to support academic and industry performers in advancing science and building new technologies. Trends and Challenges in Political Event Data Analysis by Philp Schrodt Political event data -- brief records recording when who did what to whom in a political system -- were originally developed in the 1960s under DARPA and NSF funding, and are one of the most common formal methodologies used for forecasting political developments. In recent years, the field has experienced a resurgence due to the availability of near-real-time data produced using automated methods working with news stories available on the Web and from commercial sources such as Factiva and Lexis-Nexis, as well as a substantial expansion in the types of forecasting methods that are used. This talk will survey the current state of the art in event data production and analysis, with a focus on conflict forecasting, and outline a number of challenges that might be addressed by work in cognate fields. Biography Dr. Philip A. Schrodt is a professor of political science at Pennsylvania State University. He received an M.A. in mathematics and a Ph.D. in political science from Indiana University in 1976. Prior to coming to the Penn State, he taught for twenty-one years at the University of Kansas, and eleven years at Northwestern University, where he helped develop Northwestern's programs on Mathematical Methods in the Social Sciences and the multidisciplinary program in international studies. Dr. Schrodt has also taught at the Naval Postgraduate School in Monterey, California, the American University in Cairo, the University of California at Davis, Bir Zeit University in the West Bank, and spent a year at the University of Lancaster (England) on a NATO Postdoctoral fellowship. Dr. Schrodt's major areas of research are formal models of political behavior, with an emphasis on international politics, and political methodology. His current research focuses on predicting political change using statistical and pattern recognition methods. He teaches a variety of courses in international relations, with an emphasis on international conflict, and U.S. defense policy. Dr. Schrodt has published more than 75 articles in political science, served as president of the Society for Political Methodology, and his Kansas Event Data System computer program won the "Outstanding Computer Software Award" from the American Political Science Association in 1995. Mixed Methods Stability Forecasting and Mitigation for the DARPA ICEWS Program by Brian Kettler, PhD The DARPA Integrated Crisis Early Warning System (ICEWS) program seeks to develop a comprehensive, integrated, automated, generalizable, and validated system to monitor, assess, and forecast national, sub-national, and international crises in a way that supports decisions on how to allocate resources to mitigate them. ICEWS will provide Combatant Commanders (COCOMs) with a powerful, systematic capability to anticipate and respond to stability challenges in the Area of Responsibility (AOR); allocate resources efficiently in accordance to the risks they are designed to mitigate; and track and measure the effectiveness of resource allocations toward end-state stability objectives, in near-real time. This talk will describe the mixed-methods approach and progress by the LM ATL ICEWS team for stability forecasting and our initial investigations into modeling of stability mitigating actions. Biography Dr. Brian Kettler is the ISX Lab Chief Scientist and a Principal Research Engineer for Lockheed Martin Advanced Technology Laboratories (LM ATL). He has over 12 years experience leading research and development efforts and over 22 years experience in software engineering. At LM ATL and previously at ISX Corporation, Dr. Kettler the Principal Investigator on a number of advanced technology, applied R&D programs sponsored by the Defense Advanced Research Projects Agency (DARPA), Intelligence Advanced Research Projects Activity (IARPA), and the Air Force Research Lab (AFRL). Recent programs include the DARPA Integrated Crisis Early Warning System (ICEWS) and IARPA Collaborative Analyst/System Effectiveness program. As PI on the ICEWS program – DARPA’s flagship computational social science effort – Dr. Kettler has been coordinating the technical R&D activities of a 10 organization team of universities and commercial companies for the past two years to develop model-based decision aids for country instability forecasting and mitigation. Dr. Kettler received his PhD in Computer Science from the University of Maryland College Park in 1995 with dissertation work in Artificial Intelligence (case-based planning systems). He received his BS in Computer Science from the University of Massachusetts at Amherst in 1987 with a concentration in natural language processing and a minor in Linguistics. Besides LM ATL and ISX Corporation, he has held software engineering positions at Brightware, Inc., IBM, and Digital Equipment Corporation. His research interests include context-aware computing, semantic web technologies, computational social science, intelligent agents, AI planning systems, case-based reasoning, and cognitive science. Accepted Papers Agent-based modeling of counterinsurgency operations Jason Martinez and Ben Fitzpatrick The Cultural Geography Model: An Agent Based Modeling Framework for Analysis of the Impact of Culture in Irregular Warfare Jonathan Alt and Leroy Jackson SCARE: A Case Study with Baghdad Paulo Shakarian, V.S. Subrahmanian and Maria Luisa Sapino Designing Maximally, or Otherwise, Diverse Teams: Group-Diversity Indexes for Testing Computational Models of Cultural and Other Social-Group Dynamics Rik Warren Using Fuzzy Decision Trees and Information Visualization to Study the Effects of Cultural Diversity on Team Planning and Communication Yan Liu and Rik Warren AutoMed - An Automated Mediator for Multi-Issue Bilateral Negotiations Michal Chalamish and Sarit Kraus Near-Optimal Play in a Social Learning Game James Carr, Eric Raboin, Austin Parker and Dana Nau Piracy Model: Understanding Emergence of Piracy and Ensuring Maritime Security Abdul Ahmed Mapping Socio-Cultural Dynamics in Indonesian Blogosphere Shamanth Kumar, Huan Liu, Nitin Agarwal and Merlyna Lim A Trend Pattern Approach to Forecasting Socio-Political Violence Kurt Rohloff, Robert Battle, Jim Chatigny, Rick Schantz and Victor Asal Selected Paper Abstracts SCARE: A Case Study with Baghdad Paulo Shakarian, V.S. Subrahmanian and Maria Luisa Sapino In this paper we introduce SCARE - the Spatial Cultural Abductive Reasoning Engine which implements three algorithms that solve spatial abduction problems (Shakarian, Subrahmanian, and Sapino 2009). We review results of SCARE for activities by Iranian sponsored "Special Groups" (Kagan, Kagan, and Pletka 2008) operating throughout the Baghdad urban area and compare these findings with new experiments where we predict IED cache sites of the Special Groups in Sadr City. We find that by localizing the spatial abduction problem to a smaller area we obtain greater accuracy - predicting cache sites within 0.33 km as opposed to 0.72 km for all of Baghdad. We suspect that local factors of physical and cultural geography impact reasoning with spatial abduction for this problem. AutoMed - An Automated Mediator for Multi-Issue Bilateral Negotiations Michal Chalamish and Sarit Kraus In this paper, we present AutoMed, an automated mediator for multi-issue bilateral negotiation under time constraints. AutoMed uses a qualitative model to represent the negotiators' preferences. It analyzes the negotiators' preferences, monitors the negotiations and proposes possible solutions for resolving the conflict. We conducted experiments in a simulated environment. The results show that negotiations mediated by AutoMed are concluded significantly faster than non-mediated ones and without any of the negotiators opting out. Furthermore, the subjects in the mediated negotiations are more satisfied from the resolutions than the subjects in the non-mediated negotiations. Using Fuzzy Decision Trees and Information Visualization to Study the Effects of Cultural Diversity on Team Planning and Communication Yan Liu and Rik Warren Virtual teams that span multiple geographic and cultural boundaries have become commonplace in numerous organizations due to the competitive advantages they provide in human resources, products, financial means, knowledge sharing and many others. However, the promises of multinational and multicultural (MNMC) distributed teams are accompanied by a number of challenges. Many research studies have suggested that one of the most challenging barriers to the effective implementation of MNMC distributed teams is culture. In this study, data collected from the experiment conducted by the NATO RTO Human Factors and Medicine Panel Research Task Group (HFM-138/RTG) on "Adapatability in Multinational Coalitions" has been analyzed to study the effects of cultural diversity on team planning and communication. Fuzzy decision trees have been derived to model the effects, and information visualization techniques are used to facilitate understanding of the derived classification patterns. Results of this research suggest that there are no single and straightforward conclusions on how cultural diversity affects team planning and communication. Different dimensions of culture values interact in influencing team behaviors. However, some cultural dimensions seem to play more influential roles than others.
Program Schedule
Day 2 - December 8, 2009
|
||||||||||||||||||||||||||||||||||||||||||||||||
|
This conference is sponsored by the University of Maryland Institute for
Advanced Computer Studies (UMIACS), Air
Force Office of Scientific Research (AFOSR), Association for the Advancement of
Artificial Intelligence (AAAI), and the Laboratory for Computational
Cultural Dynamics (LCCD).
|
