Jiming Liu - Böcker

Providing a guided tour of the pioneering work and major technical issues, Multiagent Robotic Systems addresses learning and adaptation in decentralized autonomous robots. Its systematic examination demonstrates the interrelationships between the autonomy of individual robots and the emerged global behavior properties of a group performing a cooperative task. The author also includes descriptions of the essential building blocks of the architecture of autonomous mobile robots with respect to their requirement on local behavioral conditioning and group behavioral evolution.After reading this book you will be able to fully appreciate the strengths and usefulness of various approaches in the development and application of multiagent robotic systems. It covers:Why and how to develop and experimentally test the computational mechanisms for learning and evolving sensory-motor control behaviors in autonomous robots How to design and develop evolutionary algorithm-based group behavioral learning mechanisms for the optimal emergence of group behaviors How to enable group robots to converge to a finite number of desirable task states through group learning What are the effects of the local learning mechanisms on the emergent global behaviors How to use decentralized, self-organizing autonomous robots to perform cooperative tasks in an unknown environmentEarlier works have focused primarily on how to navigate in a spatially unknown environment, given certain predefined motion behaviors. What is missing, however, is an in-depth look at the important issues on how to effectively obtain such behaviors in group robots and how to enable behavioral learning and adaptation at the group level. Multiagent Robotic Systems examines the key methodological issues and gives you an understanding of the underlying computational models and techniques for multiagent systems.

Autonomy Oriented Computing is a comprehensive reference for scientists, engineers, and other professionals concerned with this promising development in computer science. It can also be used as a text in graduate/undergraduate programs in a broad range of computer-related disciplines, including Robotics and Automation, Amorphous Computing, Image Processing, Programming Paradigms, Computational Biology, etc. Part One describes the basic concepts and characteristics of an AOC system and enumerates the critical design and engineering issues faced in AOC system development. Part Two gives detailed analyses of methodologies and case studies to evaluate AOC used in problem solving and complex system modeling. The final chapter outlines possibilities for future research and development.Numerous illustrative examples, experimental case studies, and exercises at the end of each chapter of Autonomy Oriented Computing help particularize and consolidate the methodologies and theories presented.

Autonomy Oriented Computing is a comprehensive reference for scientists, engineers, and other professionals concerned with this promising development in computer science. It can also be used as a text in graduate/undergraduate programs in a broad range of computer-related disciplines, including Robotics and Automation, Amorphous Computing, Image Processing, Programming Paradigms, Computational Biology, etc. Part One describes the basic concepts and characteristics of an AOC system and enumerates the critical design and engineering issues faced in AOC system development. Part Two gives detailed analyses of methodologies and case studies to evaluate AOC used in problem solving and complex system modeling. The final chapter outlines possibilities for future research and development.Numerous illustrative examples, experimental case studies, and exercises at the end of each chapter of Autonomy Oriented Computing help particularize and consolidate the methodologies and theories presented.

This book constitutes the proceedings of the 24th International Symposium on Foundations of Intelligent Systems, ISMIS 2018, held in Limassol, Cyprus, in October 2018. The 32 full, 8 short, and 4 application papers presented in this volume were carefully reviewed and selected from 59 submissions. The papers deal with topics such as bioinformatics and health informatics, graph mining, image analysis, intelligent systems, mining complex patterns, novelty detection and class imbalance, social data analysis, spatio-temporal analysis, and topic modeling and opinion mining. In addition, three special sessions were organized, namely: Special Session on Granular and Soft Clustering for Data Science, Special Session on Intelligent Methodologies for Traffic Data Analysis and Mining, and Special Session on Advanced Methods in Machine Learning for Modeling Complex Data.

Healthcare service systems are of profound importance in promoting the public health and wellness of people. This book introduces a data-driven complex systems modeling approach (D2CSM) to systematically understand and improve the essence of healthcare service systems. In particular, this data-driven approach provides new perspectives on health service performance by unveiling the causes for service disparity, such as spatio-temporal variations in wait times across different hospitals.The approach integrates four methods -- Structural Equation Modeling (SEM)-based analysis; integrated projection; service management strategy design and evaluation; and behavior-based autonomy-oriented modeling -- to address respective challenges encountered in performing data analytics and modeling studies on healthcare services. The thrust and uniqueness of this approach lies in the following aspects:Ability to explore underlying complex relationships between observed or latent impact factors and service performance.Ability to predict the changes and demonstrate the corresponding dynamics of service utilization and service performance.Ability to strategically manage service resources with the adaptation of unpredictable patient arrivals.Ability to figure out the working mechanisms that account for certain spatio-temporal patterns of service utilization and performance.To show the practical effectiveness of the proposed systematic approach, this book provides a series of pilot studies within the context of cardiac care in Ontario, Canada. The exemplified studies have unveiled some novel findings, e.g., (1) service accessibility and education may relieve the pressure of population size on service utilization; (2) functionally coupled units may have a certain cross-unit wait-time relationship potentially because of a delay cascade phenomena; (3) strategically allocating time blocks in operating rooms (ORs) based on a feedback mechanism may benefit OR utilization; (4) patients’ and hospitals’ autonomous behavior, and their interactions via wait times may bear the responsible for the emergence of spatio-temporal patterns observed in the real-world cardiac care system. Furthermore, this book presents an intelligent healthcare decision support (iHDS) system, an integrated architecture for implementing the data-driven complex systems modeling approach to developing, analyzing, investigating, supporting and advising healthcare related decisions.In summary, this book provides a data-driven systematic approach for addressing practical decision-support problems confronted in healthcare service management. This approach will provide policy makers, researchers, and practitioners with a practically useful way for examining service utilization and service performance in various ``what-if" scenarios, inspiring the design of effectiveness resource-allocation strategies, and deepening the understanding of the nature of complex healthcare service systems.

This book provides a comprehensive introduction to computational epidemiology, highlighting its major methodological paradigms throughout the development of the field while emphasizing the needs for a new paradigm shift in order to most effectively address the increasingly complex real-world challenges in disease control and prevention. Specifically, the book presents the basic concepts, related computational models, and tools that are useful for characterizing disease transmission dynamics with respect to a heterogeneous host population. In addition, it shows how to develop and apply computational methods to tackle the challenges involved in population-level intervention, such as prioritized vaccine allocation. A unique feature of this book is that its examination on the issues of vaccination decision-making is not confined only to the question of how to develop strategic policies on prioritized interventions, as it further approaches the issues from the perspective of individuals, offering a well integrated cost-benefit and social-influence account for voluntary vaccination decisions. One of the most important contributions of this book lies in it offers a blueprint on a novel methodological paradigm in epidemiology, namely, systems epidemiology, with detailed systems modeling principles, as well as practical steps and real-world examples, which can readily be applied in addressing future systems epidemiological challenges.The book is intended to serve as a reference book for researchers and practitioners in the fields of computer science and epidemiology. Together with the provided references on the key concepts, methods, and examples being introduced, the book can also readily be adopted as an introductory text for undergraduate and graduate courses in computational epidemiology as well as systems epidemiology, and as training materials for practitioners and field workers.

This book provides a thorough overview of the Wisdom Web of Things (W2T), a holistic framework for computing and intelligence in an emerging hyper-world with a social-cyber-physical space. Fast-evolving Web intelligence research and development initiatives are now moving toward understanding the multifaceted nature of intelligence and incorporating it at the Web scale in a ubiquitous environment with data, connection and service explosion. The book focuses on the framework and methodology of W2T, as well as its applications in different problem domains, such as intelligent businesses, urban computing, social computing, brain informatics and healthcare. From the researcher and developer perspectives, the book takes a systematic, structured view of various W2T facets and their overall contribution to the development of W2T as a whole. Written by leading international researchers, this book is an essential reference for researchers, educators, professionals, and tertiary HDR students working on the World Wide Web, ubiquitous computing, knowledge management, and business intelligence.

This book provides a thorough overview of the Wisdom Web of Things (W2T), a holistic framework for computing and intelligence in an emerging hyper-world with a social-cyber-physical space.

This volume contains the papers presented at the International Workshop "Autonomous Intelligent Systems: Agents and Data Mining" (AIS-ADM 2005) held in St. Petersburg, Russia, during June 6-8, 2005. The workshop was - ganized by the St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS) in cooperation with Binghamton U- versity (SUNY, USA) and the Web Intelligence Consortium. Autonomous Intelligent Systems (AIS) constitute an emerging class of int- ligent information systems integrating recent advances in various technologies of Arti?cial Intelligence. Modern AIS incorporate multi-agent and data mining systemsprovidinganewdimensionforfurtherprogressinintelligentinformation technology. AIS-ADM 2005 provided an international forum to multi-agent and data mining researchers. A total of 29 papers from 15 countries relating to various aspects of both theory and applications of multi-agent systems, data mining and their joint area were submitted to AIS-ADM 2005. Out of them 17 were selected as regular presentations.Three technical sessions were organized, namely: In- gration of Multi-agent and Data Mining Techniques; Ontology Issues and Web Mining; and Applications and Case Studies of the Integrated Technology. The panel discussion was devoted to the mutual enrichment and challenging pr- lems emerging in the joint area of research. The AIS-ADM 2005 program was enriched by six distinguished invited speakers: Nick Jennings, Chengqi Zhang, Mircea Negoita, Pericles Mitkas, Hai Zhuge and Leonid Perlovsky.

The International Conference on Computational Intelligence and Security (CIS) is an annualinternationalconference that bringstogether researchers,engineers, developers and practitioners from both academia and industry to share expe- ence and exchange and cross-fertilize ideas on all areas of computational - telligence and information security. The conference serves as a forum for the dissemination of state-of-the-art research and the development, and implem- tationsof systems,technologiesandapplicationsinthese two broad,interrelated ?elds. This year CIS 2005 was co-organized by the IEEE (Hong Kong) Com- tational Intelligence Chapter and Xidian University, and co-sponsored by Hong Kong Baptist University, National Natural Science Foundation of China, Key Laboratory of Computer Networks and Information Security of the Ministry of EducationofChina,andGuangdongUniversityofTechnology. CIS2005received in total 1802 submissions from 41 countries and regions all over the world. All of them were strictly peer reviewed by the Program Committee and experts in the ?eld. Finally, 337 high-quality papers were accepted yielding an acc- tance rate of 18. 7%.Among them, 84 papers are the extended papers and 253 are the regular papers. The conference was greatly enriched by a wide range of topics covering all areas of computational intelligence and information security. Furthermore, tutorials and workshops were held for discussions of the proposed ideas. Such practice is extremely important for the e?ective development of the two ?elds and computer science in general. Wewouldliketothanktheorganizers:theIEEE(HongKong)Computational Intelligence Chapter and Xidian University for their great contributions and - forts in this big event.

Intelligent Data Engineering and Automated Learning (IDEAL) was initially a biennial forum dedicated to emerging and challenging topics in intelligent data analysis, knowledge discovery, and statistical and computational learning. The huge success of recent IDEAL conferences and the continuous growth of the ?eld have compelled it to become an annual conference after 2003. It is now a major international, interdisciplinary event covering subjects from data mining, inf- mation retrieval and management, autonomous learning, and agents to ?nancial engineering, neural networks, emerging learning paradigms and systems, bio- formatics, and pattern recognition. Data analysis and processing has become a common theme and plays a crucial role in many disciplines, especially in ?nance, biology, engineering, and information technology. Demand for intelligent met- dologies and tools is immense. The multidisciplinary nature of current research is pushing the traditional boundaries and bringing new ideas and solutions, and it is the way forward. This volume contains 164 refereed and ?nally accepted papers presented at the4thInternationalConferenceonIntelligentDataEngineeringandAutomated Learning (IDEAL 2003), held in Hong Kong, March 21-23, 2003.IDEAL 2003 received a record level of submissions, 321 in total, from all over the world. They were subsequently peer-reviewed by the Program Committee. The conference was held together with the 2003 IEEE International Conference on Computat- nal Intelligence for Financial Engineering at the modern and magni?cent Hong KongConventionandExhibitionCentre.

Spatial reasoning and planning is a core constituent in robotics, graphics, computer-aided design, and geographic information systems.After a review of previous work in the related areas, Liu and Daneshmend present here a unified framework for qualitative spatial representation and reasoning, which enables the generation of solutions to spatial problems where the geometric knowledge is imprecise. The approach utilizes qualitative spatial representation and reasoning integrated with a quantitative search procedure based on simulated annealing. Many graphical illustrations and detailed algorithm descriptions help the readers to comprehend the solution paths and to develop their own applications.The book is written as a self-contained text for researchers and graduate students in computer science and related engineering disciplines. The methodologies, algorithmic details, and case studies presented can be used as course material as well as a convenient reference.

Today we live in an information age: information has become a commodity, and every second thousands of new records are created. This explosion of massive data sets created by businesses, science and governments necessitates intelligent and more powerful computing paradigms so that users can benefit from this data. This information needs to be summarized and synthesized to support effective problem solving and decision making. The papers in this book assume an interdisciplinary approach based on three major methodologies: first, hybridization, i. e. , combining methods in order to harness their strengths and avoid their shortcomings; second, multiphase processing, i. e. , the step-wise preparation, evaluation and refinement of data; and, third, multi-agent and distributed processing, i. e. , using intelligent agents as well as Web or grid architectures. The final vision of the authors is an intelligent information technology, encompassing theories and applications from, for example, artificial intelligence, data mining, grid computing, and statistical learning.This monograph presents the current state of research and development in both theoretical and application aspects of intelligent information analysis. It is a source of reference and includes numerous examples for researchers, graduate students and advanced professionals working in areas such as electronic commerce, business intelligence, and knowledge grids.

This volume contains the papers selected for presentation at the First Asia- Paci?c Conference on Web Intelligence (WI 2001) held in Maebashi TERRSA, Maebashi City,Japan,October 23-26,2001. It was sponsored by ACM SIGART and Maebashi Institute of Technology,in cooperation with ACM SIGCHI,ACM SIGWEB,the Japanese Society for Arti?cial Intelligence (JSAI),JSAI SIGFAI, JSAI SIGKBS,and IEICE SIGKBSE. The conference was held jointly with the Second Asia-Paci?c Conference on Intelligent Agent Technology (IAT 2001). WI 2001 was the ?rst conference on a new and emerging sub?eld of computer science known as Web Intelligence. It provided an international forum for re- archers and practitioners to present the state of the art in the development of Web intelligence,to examine performance characteristics of various approaches in Web-based intelligent information technology,and to cross-fertilize ideas on the development of Web-based intelligent information systems among di?erent domains.By idea-sharing and discussions on the underlying foundations and the enabling technologies of Web intelligence,we hoped to stimulate the future development of new models,new methodologies,and new tools for building a variety of embodiments of Intelligent Web Information Systems (IWIS). In spite of its name,WI 2001 was truly an international conference that - tracted 153 full-length research paper submissions from 31 countries and regions of all continents. Each submitted paper was reviewed by at least three experts on the basis of technical soundness,relevance,originality,signi?cance,and clarity.

This book constitutes the refereed proceedings of the 6th International Computer Science Conference: Active Media Technology, AMT 2001, held in Hong Kong, China in December 2001. The 39 revised full papers presented were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on smart digital media; Web personalization; active interfaces; autonomous agents; facial image processing; AMT-supported commerce, business, learning, and health care; tool and techniques; and algorithms.

This excellently written monograph provides -- for the first time ever - a thorough introduction and systematic overview of all aspects of intelligent data processing on the Web. It presents both the current state of research as well as application aspects. All major topics related to Web Intelligence which can have impact on future directions and developments are presented in detail. This book will be a valuable source of reference for years to all research and development professionals interested in Web Intelligence. Students will also appreciate the numerous illustrations and examples.

This book constitutes the thoroughly refereed post-workshop proceedings of the First WICI International Workshop on Web Intelligence meets Brain Informatics, WImBI 2006, which was held in Beijing, China, in December 2006. The workshop explores a new perspective of Web Intelligence (WI) research from the viewpoint of Brain Informatics (BI). The 26 revised full-length papers presented together with three introductory lectures have been carefully reviewed and selected.

The2009InternationalWorkshoponAgentsandDataMiningInteraction(ADMI 2009) was a joint event with AAMAS2009. In recentyears,agents and data mining interaction (ADMI), or agent mining forshort,hasemergedasaverypromisingresearch?eld. Followingthesuccessof ADMI 2006 in Hong Kong, ADMI 2007 in San Jose, and ADMI 2008 in Sydney, the ADMI 2009 workshop in Budapest provided a premier forum for sharing research and engineering results, as well as potential challenges and prospects encountered in the synergy between agents and data mining. As usual, the ADMI workshop encouraged and promoted theoretical and applied research and development, which aims at: – Exploitingagent-drivendatamininganddemonstratinghowintelligentagent technology can contribute to critical data mining problems in theory and practice – Improving data mining-driven agents and showing how data mining can strengthen agent intelligence in research and practical applications – Exploring the integration of agents and data mining toward a super-intelligent information processing and systems – Identifying challenges and directions for future research on the synergy between agents and data mining ADMI 2009 featured two invited talks and twelve selected papers. The ?rst invited talk was on “Agents and Data Mining in Bioinformatics,” with the s- ond focusing on “Knowledge-Based Reinforcement Learning. ” The ten accepted papers are from seven countries. A majority of submissions came from Eu- pean countries, indicating the boom of ADMI research in Europe. In addition the two invited papers, addressed fundamental issues related to agent-driven data mining, data mining-driven agents, and agent mining applications. The proceedings of the ADMI workshops will be published as part of the LNAIseriesbySpringer.WeappreciatethesupportofSpringer,andinparticular Alfred Hofmann.

This book constitutes the refereed proceedings of the 5th International Conference on Active Media Technology, AMT 2009, held in Beijing, China, in October 2009. The 47 revised full papers and the 6 keynote talks were carefully reviewed and selected.The papers reflect the shared forum for researchers and practitioniers from diverse fields, such as computer science, information technology, artificial intelligence, media engineering, economics, data mining, data and knowledge engineering, intelligent agent technology, human computer interaction, complex systems and systems science. The book offers new insights into the main research challenges and development of AMT by revealing the interplay between the studies of human informatics and research of informatics on the Web/Internet, mobile and wireless centric intelligent information processing systems.

Today we live in an information age: information has become a commodity, and every second thousands of new records are created. This explosion of massive data sets created by businesses, science and governments necessitates intelligent and more powerful computing paradigms so that users can benefit from this data. This information needs to be summarized and synthesized to support effective problem solving and decision making. The papers in this book assume an interdisciplinary approach based on three major methodologies: first, hybridization, i.e., combining methods in order to harness their strengths and avoid their shortcomings; second, multiphase processing, i.e., the step-wise preparation, evaluation and refinement of data; and, third, multi-agent and distributed processing, i.e., using intelligent agents as well as Web or grid architectures. The final vision of the authors is an intelligent information technology, encompassing theories and applications from, for example, artificial intelligence, data mining, grid computing, and statistical learning.This monograph presents the current state of research and development in both theoretical and application aspects of intelligent information analysis. It is a source of reference and includes numerous examples for researchers, graduate students and advanced professionals working in areas such as electronic commerce, business intelligence, and knowledge grids.

This excellently written monograph provides -- for the first time ever - a thorough introduction and systematic overview of all aspects of intelligent data processing on the Web. It presents both the current state of research as well as application aspects. All major topics related to Web Intelligence which can have impact on future directions and developments are presented in detail. This book will be a valuable source of reference for years to all research and development professionals interested in Web Intelligence. Students will also appreciate the numerous illustrations and examples.

This volume contains the papers selected for presentation at The 2010 Int- national Conference on Brain Informatics (BI 2010) held at York University, Toronto, Canada, during August 28-30, 2010. It was organized by the Web - telligenceConsortium(WIC),theIEEEComputationalIntelligenceSocietyTask Force on Brain Informatics (IEEE-CIS TF-BI), and York University. The c- ference washeld jointly with the 2010InternationalConference on Active Media Technology (AMT 2010). Brain informatics (BI) hasemergedasaninterdisciplinaryresearch?eld that focuses on studying the mechanisms underlying the human information proce- ing system (HIPS). It investigates the essential functions of the brain, ranging from perception to thinking, and encompassing such areas as multi-perception, attention, memory, language, computation, heuristic search, reasoning, pl- ning, decision-making, problem-solving, learning, discovery, and creativity.The goal of BI is to develop and demonstrate a systematic approach to achieving an integrated understanding of both macroscopic and microscopic-level working principles of the brain, by means of experimental, computational, and cognitive neuroscience studies, as well as utilizing advanced Web intelligence (WI)-centric information technologies. BI represents a potentially revolutionary shift in the way that research is undertaken. It attempts to capture new forms of colla- rative and interdisciplinary work. In this vision, new kinds of BI methods and global research communities will emerge, through infrastructure on the wisdom Web and knowledge grids that enable high-speed and distributed, large-scale analysis and computations, and radically new ways of sharing data/knowledge. TheBrainInformaticsConferencesstartedwiththeFirstWICIInternational Workshop on Web Intelligence meets Brain Informatics (WImBI 2006), held at Beijing,China,December15-16,2006.

This book constitutes the refereed proceedings of the International Conference on Brain Informatics, BI 2011, held in Lanzhou, China, in September 2011. The 27 revised full papers and 6 keynote talks were carefully reviewed and selected for inclusion in the book. They are grouped in topcial sections on thinking and perception-centric investigations ofhuman information processing systems; information technologies for the management, analysis and useof brain data; cognition-inspired applications. Furthermore, there is a section with 8 papers from the workshop on meta-synthesis and complex systems.

This book constitutes the proceedings of the 20th International Symposium on Methodologies for Intelligent Systems, ISMIS 2012, held in Macau, China, in December 2012. The 42 regular papers and 11 short papers presented were carefully reviewed and selected from 88 submissions. They are organized in topical sections named: knowledge discovery and data mining; intelligent information systems; text mining and language processing; knowledge representation and integration; music information retrieval; recommender systems; technology intelligence and applications; product configuration; human factors in information retrieval; social recommender systems; and warehousing and OLAPing complex, spatial and spatio-temporal data.

Spatial reasoning and planning is a core constituent in robotics, graphics, computer-aided design, and geographic information systems.After a review of previous work in the related areas, Liu and Daneshmend present here a unified framework for qualitative spatial representation and reasoning, which enables the generation of solutions to spatial problems where the geometric knowledge is imprecise. The approach utilizes qualitative spatial representation and reasoning integrated with a quantitative search procedure based on simulated annealing. Many graphical illustrations and detailed algorithm descriptions help the readers to comprehend the solution paths and to develop their own applications.The book is written as a self-contained text for researchers and graduate students in computer science and related engineering disciplines. The methodologies, algorithmic details, and case studies presented can be used as course material as well as a convenient reference.

This is not a purely mathematical book. It presents the basic principle of wavelet theory to electrical and electronic engineers, computer scientists, and students, as well as the ideas of how wavelets can be applied to pattern recognition. It also contains many novel research results from the authors' research team.

This book is a collection of high quality technical papers contributed by active researchers and leading practitioners in intelligent agent technology. It offers a closer look at the state-of-the-art in the development of intelligent agents, and examines in depth the underlying logical, cognitive, physical, and biological foundations as well as the performance characteristics of various approaches in intelligent agent technology. It will stimulate the development of new models, new methodologies, and new tools for building a variety of embodiments of agent-based systems.

An autonomous agent is a computational system that acquires sensory data from its environment and decides by itself how to relate the external stimulus to its behaviors in order to attain certain goals. Responding to different stimuli received from its task environment, the agent may select and exhibit different behavioral patterns. The behavioral patterns may be carefully predefined or dynamically acquired by the agent based on some learning and adaptation mechanism(s). In order to achieve structural flexibility, reliability through redundancy, adaptability, and reconfigurability in real-world tasks, some researchers have started to address the issue of multiagent cooperation. Broadly speaking, the power of autonomous agents lies in their ability to deal with unpredictable, dynamically changing environments. Agent-based systems are becoming one of the most important computer technologies, holding out many promises for solving real-world problems.The aims of this book are to provide a guided tour to the pioneering work and the major technical issues in agent research, and to give an in-depth discussion on the computational mechanisms for behavioral engineering in autonomous agents. Through a systematic examination, the book attempts to provide the general design principles for building autonomous agents and the analytical tools for modeling the emerged behavioral properties of a multiagent system.

Agent engineering concerns the development of autonomous computational or physical entities capable of perceiving, reasoning, adapting, learning, cooperating and delegating in a dynamic environment. It is one of the most promising areas of research and development in information technology, computer science and engineering.This book addresses some of the key issues in agent engineering: What is meant by “autonomous agents”? How can we build agents with autonomy? What are the desirable capabilities of agents with respect to surviving (they will not die) and living (they will furthermore enjoy their being or existence)? How can agents cooperate among themselves? In order to achieve the optimal performance at the global level, how much optimization at the local, individual level and how much at the global level would be necessary?