Collective Intelligence Systems Research Articles

Second-order agent-based models of emergent behaviour of Dictyostelium discoideum and their inspiration for swarm robotics

By studying and modelling the behaviour of Dictyostelium discoideum, we aim at deriving mechanisms useful for engineering collective artificial intelligence systems. This paper discusses a selection of agent-based models reproducing second-order behaviour of Dictyostelium discoideum, occurring during the migration phase; their corresponding biological illustrations; and how we used them as an inspiration for transposing this behaviour into swarms of Kilobots. For the models, we focus on: (1) the transition phase from first- to second-order emergent behaviour; (2) slugs’ uniform distribution around a light source; and (3) the relationship between slugs’ speed and length occurring during the migration phase of the life cycle of D. discoideum. Results show the impact of the length of the slug on its speed and the effect of ammonia on the distribution of slugs. Our computational results show similar behaviour to our biological experiments, using Ax2(ka) strain. For swarm robotics experiments, we focus on the transition phase, slugs’ chaining, merging and moving away from each other.

Description of HVAC System and Identification of Flow Rates and Pressures in HVAC Based on Collective Intelligence System

The efficient control of the HVAC system is important for the reduction of energy consumption in buildings. The water and air distribution network of HVAC system not only consume energy but also determine whether the cold and heat are delivered properly in the building according to the cooling and heating loads. The optimal control of the HVAC distribution system is complex due to the scale of the network and the coupling effects between HVAC devices. This paper proposes a novel distributed control system using standard computing process nodes, which is called the Collective Intelligence System (CIS). The proposed method is validated using a typical HVAC system in a real office building. The description of the HVAC system and the identification of flow rates and pressures of the distribution network is demonstrated using the decentralized identification algorithm.

Fuzzy logic based associative classifier for slow learners prediction

Education is a collective intelligence system where a group of persons ranging from students to management thinks and work together to achieve institutions’ goals. The primary goal of every institution is to accomplish excellent end-semester examination results. A good result is achieved through pr oper training given by the educators and in response to the performance of students in the examination. Training is cost accounting, whereas students’ performance is unpredictable. Outlier analysis in the education system has been stipulated in recent decades to predict the students’ uncertain behavior in learning activities which are utilized to alert the education systems. Fuzzy Logic System can handle such uncertainties in learning activities. The major issues that affect the accuracy of fuzzy based outlier detection methods are fixing appropriate membership function and validating the fuzzy rules before extracting outliers. To remedy these issues the proposed Fuzzy Temporal Outlier Detection (FTOD) method detects outliers from mid-semester examination results using fuzzy logic based associative classifier with optimal membership functions. The resultant outliers distinguish the slow learners from spurious-slow learners with high accuracy than the existing FARIM and modified-FARIM algorithms. Thus, educators can provide cost-effective training to enrich the slow learners’ cognition to score high in end-semester examinations.

Online Social Network Viability: Misinformation Management Based on Service and Systems Theories

This paper provides a practical example of how service and systems theories can be successfully integrated to develop a comprehensive analysis and theorization of solutions for a specific issue, that is, misinformation management in online social network sites (OSNs). A literature review and elaboration of different theories (service science, service-dominant logic, viable systems approach) and approaches (collective intelligence and collective knowledge systems, group decision making) specifically related to ONS is developed and presented in the form of propositions and constructs. It results that the issue of misinformation in OSNs can be analyzed as a threat to service (eco) system viability, while technological solutions, engagement and the participation of communities by means of collective knowledge systems should be adopted as strategies to align with relevant supra-systems to survive. The originality of the paper relies on the following: (i) expanding service research analysis horizons to OSNs; (ii) providing a practical example of how Service Science, Service-Dominant Logic and Viable Systems Approach perspectives can be integrated to theorize and practically find ways to re-shape contexts, such as OSN misinformation management; and (iii) presenting a multidisciplinary conceptual model to the OSN literature, based on service systems and service ecosystems, linking theory to practice.

Can we solve wicked problems? A conceptual framework and a collective intelligence system to support problem analysis and solution design for complex social issues

Wicked problems are complex and multifaceted issues that have no single solution, and are perceived by different stakeholders through contrasting views. Examples in the social context include climate change, poverty, energy production, sanitation, sustainable cities, pollution and homeland security. Extant research has been addressed to support open discussion and collaborative decision making in wicked scenarios, but complexities derive from the difficulty to leverage multiple contributions, coming from both experts and non-experts, through a structured approach. In such view, we present a conceptual framework for the study of wicked problem solving as a complex and multi-stakeholder process. Afterwards, we describe an integrated system of tools and associated operational guidelines aimed to support collective problem analysis and solution design. The main value of the article is to highlight the relevance of collective approaches in the endeavor of wicked problem resolution, and to provide an integrated framework of activities, actors and purposeful tools.

Intellectual capital management in the fourth stage of IC research

PurposeThe purpose of this paper is to present a case study of a university that uses a collective intelligence approach for managing its intellectual capital (IC). Specifically, the authors investigate how one of Europe’s oldest business schools, Ca’ Foscari University of Venice (Italy), manages IC through stakeholder engagement to achieve academia’s third mission so contributing to social and economic development.Design/methodology/approachData are collected through semi-structured interviews and Ca’ Foscari University’s strategic plan. Secundo et al.’s (2016) collective intelligence framework is used to analyse the data. Alvesson and Deetz’s (2000, pp. 19-20) critical management tasks – insight, critique and transformative redefinition – are adopted to frame and discuss the results.FindingsOn the assumption that a university is a collective intelligence system, the findings demonstrate that IC management needs to change to incorporate an ecosystem perspective, reflecting the fourth stage of IC research. The IC management at the university incorporates its core goal (what), the collective involvement of internal and external stakeholders to achieve the goal (who), the motivations behind the achievement of the goal (why) and, finally, the processes activated inside the university (how) and indicators to assess value creation.Research limitations/implicationsA new perspective for managing IC in universities that adopts a collective intelligence approach is further developed. Contributions to the fourth stage of IC research – IC in an ecosystem – are highlighted that expand the concept of IC value creation beyond universities into wider society.Practical implicationsTwo key consequences of this case study are that more stakeholders have become involved in IC management and that IC management requires critical rethinking, given the universities’ evolving role.Originality/valueThis paper brings together issues that are usually dealt with in separate domains of the literature: IC management and collective intelligence in the university setting.

Managing intellectual capital through a collective intelligence approach

Purpose– The purpose of this paper is to provide a new framework for managing intellectual capital (IC) inside a university considering the collective intelligence perspective.Design/methodology/approach– The research method uses the fourth stage of IC research and adopts the collective intelligence approach. The underlying assumption behind the framework is to consider the university as a collective intelligence system in which the tangible and intellectual assets are coordinated towards the achievement of strategic goals.Findings– The conceptual framework for IC management harnesses the power of IC, collectively created by the engagement of multiple stakeholders inside the university network. The main components are the final goal of a university (what); the collective human capital to achieve the goal (who); the processes activated inside the university (how); and finally the motivations behind the achievement of the goal (why).Research limitations/implications– The research is exploratory and the framework offers opportunities for refinement. Future research is needed to verify the application of the framework to other organisations in the public sector intended as collective intelligence systems. A new perspective for managing IC in universities adopting the collective intelligence approach is developed. Contribution to the fourth stage (ecosystem) of IC research is highlighted, expanding the concept of IC value creation beyond the university into wider society.Practical implications– The framework can be used to manage IC strategically in all the systems interpreted as collective intelligence systems in which the role of IC creation from multiple actors is relevant. This makes possible the understanding of how IC helps create value for the society and the region in which the university operates.Originality/value– The originality of the paper is in bringing together issues usually dealt within the literature in separate domains, such as IC management and collective intelligence perspective. The concept of collective intelligence remains an unexplored field in relation to IC management in the public sector. The collective intelligence approach provides a novel contribution to managing IC and is intended to inspire future research.

Decrypting Financial Markets through E-Joint Attention Efforts: On-Line Adaptive Networks of Investors in Periods of Market Uncertainty.

This paper looks at 800,000 messages on the Unicredit stock, exchanged by 7,500 investors in the Finanzaonline.com forum, between 2005 and 2012 and measured collective interpretations of stock market trends. We examined the correlation patterns between market uncertainty, bad news and investors' network structure by measuring the investors' communication patterns. Our results showed that the investors' network reacted to market trends in different ways: While less turbulent market phases implied less communication, higher market volatility generated more complex communication patterns. While the information content of messages was less technical in situations of uncertainty, bad news caused more informative messages only when market volatility was lower. This meant that bad news had a different impact on network behaviour, depending on market uncertainty. By measuring the investors' expertise, we found that their behaviour could help predict changes in daily stock returns. We also found that expert investors were more influential in communication processes during high volatility market phases, whereas they had less influence on the real-time forum's reaction after bad news. Our findings confirm the crucial role of e-communication platforms. However, they also show the need to reconsider the fragility of these collective intelligence systems when under external shocks.

Utilizing data consortia to monitor safety and effectiveness of biosimilars and their innovator products.

The Biologics Price Competition and Innovation Act, introduced as part of the Affordable Care Act, directed the FDA to create an approval pathway for biologic products shown to be biosimilar or interchangeable with an FDA-approved innovator drug. These biosimilars will not be chemically identical to the reference agent. Investigational studies conducted with biosimilar agents will likely provide limited real-world evidence of their effectiveness and safety. How do we best monitor effectiveness and safety of biosimilar products once approved by the FDA and used more extensively by patients? To determine the feasibility of developing a distributed research network that will use health insurance plan and health delivery system data to detect biosimilar safety and effectiveness signals early and be able to answer important managed care pharmacy questions from both the government and managed care organizations. Twenty-one members of the AMCP Task Force on Biosimilar Collective Intelligence Systems met November 12, 2013, to discuss issues involved in designing this consortium and to explore next steps. The task force concluded that a managed care biosimilars research consortium would be of significant value. Task force members agreed that it is best to use a distributed research network structurally similar to existing DARTNet, HMO Research Network, and Mini-Sentinel consortia. However, for some surveillance projects that it undertakes, the task force recognizes it may need supplemental data from managed care and other sources (i.e., a "hybrid" structure model). The task force believes that AMCP is well positioned to lead the biosimilar-monitoring effort and that the next step to developing a biosimilar-innovator collective intelligence system is to convene an advisory council to address organizational governance.

Evolving toward Conscious-Technology from the Global Situation with Collective Intelligence

The increasing integration of our biology with technology and the increasing integration of artificial intelligence with the built environment could make a continuum of human consciousness and technology giving birth to a “Conscious-Technology” civilization. Although humanity has made great progress, the avoidance of new long-term threats is not guaranteed and will likely require global collective intelligence systems to help us make the decisions on the scale necessary for future survival and the continued human evolution.

Community Discovery for Knowledge Collaborations in Collective intelligence Systems

Knowledge collaborative communities play an important role in collective intelligence systems. To discover a knowledge collaborative community, we need to consider not only the structure of a network but also the performance of knowledge collaboration among members within the community. Traditional community discovery approaches are not suitable to discover knowledge collaborative communities since most of them focus too much on the network topologies, and ignore some other important factors. In this paper, we propose two community discovery approaches, which can be used in different sizes of networks, and take more knowledge collaboration factors into account. Compared with some other existing approaches, the proposed approach can perform better in forming knowledge collaborative communities for multi-domain problem solving.

Collective intelligence systems and an application by The Millennium Project for the Egyptian Academy of Scientific Research and Technology

There are several definitions for “collective intelligence” and its applications. We define collective intelligence as an emergent property from synergies among three elements: 1) data/information/knowledge; 2) software/hardware; and 3) experts and others with insight that continually learns from feedback to produce just-in-time knowledge for better decisions than any of these elements acting alone. This paper will briefly discuss what collective intelligence is, why it is needed, some early approaches, how The Millennium Project (MP) is creating its own system — Global Futures Intelligence System (GFIS), and how MP is applying the elements of GFIS for the creation of ISIS (Integrated Synergistic Information System) for the Egyptian Academy of Scientific Research and Technology. ISIS is adapted from GFIS to provide a common platform for Egyptians to explore possible futures for input to national short- and long-term strategy.

Water: how collective intelligence initiatives can address this challenge

Purpose – The purpose is to examine how collective intelligence initiatives can help address the challenge of water supply globally. Design/methodology/approach – The methodology used was desk research and interview. The paper commences with a review of collective intelligence as a subject area. It then assesses water as an issue, paying particular attention to the new set of World Water Scenarios currently being undertaken by the World Water Assessment Program of UNESCO and its latest World Water Development Report (2012). It considers the application of collective intelligence systems to the challenge of water provision with particular reference to a recent initiative led by the International Water Association (IWA), the IWA WaterWiki. It examines potential future developments from a collective intelligence viewpoint. Findings – It is increasingly recognised that the drivers that affect water provision are linked to the change drivers of other global issues. There is a need to deal with the inadequacies of currently available water data. Online collective intelligence systems make it easier to set practical goals and monitor progress and send, receive and act on the latest research and new information. Complementary collective intelligence systems in other areas are needed. Originality/value – The paper deals with current developments in the water sector. It will be of interest to all foresight professionals involved with this sector or collective intelligence.

FROM COLLECTIVE INTELLIGENCE TO COLLECTIVE INTELLIGENCE SYSTEMS: DEFINITIONS AND A SEMI-STRUCTURED MODEL

Collective intelligence (CI) has become a popular research topic over the past few years. However, the CI debate suffers from several problems such as that there is no unanimously agreed-upon definition of CI that clearly differentiates between CI and related terms such as swarm intelligence (SI) and collective intelligence systems (CIS). Furthermore, a model of such CIS is lacking for purposes of research and the design of new CIS. This paper aims at untangling the definitions of CI and other related terms, especially CIS, and at providing a semi-structured model of CIS as a first step towards more structured research. The authors of this paper argue that CI can be defined as the ability of sufficiently large groups of individuals to create an emergent solution for a specific class of problems or tasks. The authors show that other alleged properties of CI which are not covered by this definition, are, in fact, properties of CIS and can be understood by regarding CIS as complex socio-technical systems (STS) that enable the realization of CI. The model defined in this article serves as a means to structure open questions in CIS research and helps to understand which research methodology is adequate for different aspects of CIS.

EVOLUTION OF THE SOFTWARE-AS-A-SERVICE INNOVATION SYSTEM THROUGH COLLECTIVE INTELLIGENCE

One of the notable trends in the software industry is that software vendors provide their software on a platform as a service. Software users consume those software services or compose new services by combining those existing software services. The software vendors, their services, software users, and the platform represent an open innovation system. Collective intelligence is the underlying mechanism for the cooperation between the users of the system, i.e. their continuous reuse of existing software services for the creation of new services. A successfully working software services system (i.e. collective intelligence system) is a system that is continuously adapted by its users to meet their needs. The evolution of this software-as-a-service (SaaS) innovation system and the behavior of SaaS users within this system are still unknown. In this paper, we describe the evolution of a SaaS network. The SaaS network consists of nodes (i.e. software services with open interfaces) and links (i.e. the co-development relationships of software services with open interfaces). The results suggest that the SaaS network has gradually grown into a scale-free network with a slight concavity in its cumulative degree distribution. The results also suggest that the topology characteristics are invariant over time except for the early time periods. Furthermore, the results suggest that the SaaS network is not as open (i.e. inter-operable) as its technology let us expect. Considering these results, we imply that SaaS innovation is achieved by platform providers striving to capture users with a few, leading SaaS services. That means, SaaS innovation is not achieved through the possibilities of potential combinations between any kind of SaaS services as could be expected theoretically. These findings are expected to stir further research on the actual structure of open innovation systems that are driven by collective intelligence.

Collective Intelligence and an Application by The Millennium Project

There are a range of definitions for “collective intelligence” and applications. I define collective intelligence as “an emergent property from synergies among three elements—(1) data/info/knowledge, (2) software/hardware, and (3) experts and others with insight—that continually learns from feedback to produce just-in-time knowledge for better decisions than any of these elements acting alone.” This paper will briefly discuss why collective intelligence is needed, some early approaches to creating collective intelligence, what specifically is needed today, and an approach to constructing a collective intelligence system proposed by The Millennium Project called the Global Futures Intelligence System. This online integrated platform is designed to help support and improve global foresight as well as to provide a common platform for conducting futures research.

Social Influence Bias: A Randomized Experiment

Our society is increasingly relying on the digitized, aggregated opinions of others to make decisions. We therefore designed and analyzed a large-scale randomized experiment on a social news aggregation Web site to investigate whether knowledge of such aggregates distorts decision-making. Prior ratings created significant bias in individual rating behavior, and positive and negative social influences created asymmetric herding effects. Whereas negative social influence inspired users to correct manipulated ratings, positive social influence increased the likelihood of positive ratings by 32% and created accumulating positive herding that increased final ratings by 25% on average. This positive herding was topic-dependent and affected by whether individuals were viewing the opinions of friends or enemies. A mixture of changing opinion and greater turnout under both manipulations together with a natural tendency to up-vote on the site combined to create the herding effects. Such findings will help interpret collective judgment accurately and avoid social influence bias in collective intelligence in the future.

Computational model of collective intelligence for meta-level analysis and prediction of free or quasi-free market economy

This paper encourages the use of a computational model of Collective Intelligence as a major (meta-level) tool to analyze and predict behavior of socio-economical systems like free (or quasi-free) markets are. Researchers are aware, that economics is a study of human behavior, but lack of a proper formal tool has shifted research in economics into the language of money, production, consumption, etc. From an economic point of view, when analyzing free (quasi-free) markets, more important is group behavior than individual behavior because they result in changes of market indexes. Group behavior leads in specific cases to the emergence of “group intelligence” with the most famous case named “A. Smith invisible hand of market”. A computational model of Collective Intelligence allows for the formal extraction of the “system of inference processes” which run in an unconscious way in socio-economic structures. The construction of a proper formal and simulation model of such Collective Intelligence inferences allows us to take an attempt to predict outcomes in terms of economical results. The paper will present a formal basis, methodology of constructing Collective Intelligence systems for given socio-economic structures.

Collective Intelligence Systems: Classification and Modeling

Collective intelligence (CI) is an emerging research field that seeks to merge human and machine intelligence, with an aim to achieve results unattainable by either one of these entities alone. CI systems may significantly vary in nature, from collaborative systems, like open source software development communities, to competitive ones, like problem-solving companies that benefit from the competition among participating user teams to identify solutions to various R&D problems. The advantages that CI systems earn user communities, together with the fact that they share a number of basic common features, provide the potential for designing a general methodology for their efficient modeling, development and evaluation. In this paper we describe a modeling process which identifies the common features, as well as the main challenges that the construction of generic collective intelligence systems poses. First a basic categorization of CI systems is performed, followed by a description of the proposed modeling approach. This approach includes concepts such as the set of possible user actions, the CI system state and the individual and community objectives, as well as a number of necessary functions, which estimate various parameters of the CI system, such as the expected user actions, the future system state and the level of objective fulfillment. Finally, based on the proposed modeling approach, certain current CI systems are described, a number of problems that they face are identified and specific solutions are suggested. The proposed modeling approach is expected to promote more efficient CI system design, so that the benefit gained by the participating community and individuals, will be maximized.

Analysis of the Emergence in Swarm Model Based on Largest Lyapunov Exponent

Emergent behaviors of collective intelligence systems, exemplified by swarm model, have attracted broad interests in recent years. However, current research mostly stops at observational interpretations and qualitative descriptions of emergent phenomena and is essentially short of quantitative analysis and evaluation. In this paper, we conduct a quantitative study on the emergence of swarm model by using chaos analysis of complex dynamic systems. This helps to achieve a more exact understanding of emergent phenomena. In particular, we evaluate the emergent behaviors of swarm model quantitatively by using the chaos and stability analysis of swarm model based on largest Lyapunov exponent. It is concluded that swarm model is at the edge of chaos when emergence occurs, and whether chaotic or stable at the beginning, swarm model will converge to stability with the elapse of time along with interactions among agents.