Adaptive Interactive Systems Research Articles

Layered evaluation of interactive adaptive systems: framework and formative methods

The evaluation of interactive adaptive systems has long been acknowledged to be a complicated and demanding endeavour. Some promising approaches in the recent past have attempted tackling the problem of evaluating adaptivity by decomposing and evaluating it in a piece-wise manner. Separating the evaluation of different aspects can help to identify problems in the adaptation process. This paper presents a framework that can be used to guide the layered evaluation of adaptive systems, and a set of formative methods that have been tailored or specially developed for the evaluation of adaptivity. The proposed framework unifies previous approaches in the literature and has already been used, in various guises, in recent research work. The presented methods are related to the layers in the framework and the stages in the development lifecycle of interactive systems. The paper also discusses practical issues surrounding the employment of the above, and provides a brief overview of complementary and alternative approaches in the literature.

Optimal Operation of a Multi-Purpose Reservoir Using Neuro-Fuzzy Technique

Present paper is aimed to develop operation policy for a multi-purpose reservoir using Neuro-Fuzzy technique in an efficient way. Ramganga reservoir behind Ramganga dam, Kalagarh, India has been considered as a study reservoir. The developed policy minimizes the damage due to floods and droughts and determines optimum releases against demands for domestic supply, irrigation and hydropower generation for monsoon and non-monsoon periods. Three Fuzzy Rule Based (FRB) models for monsoon period and three for non monsoon period have been developed and tested. Actual releases have been used to formulate the general operation fuzzy rules. Releases computed from all developed models using Fuzzy Mamdani (FM) and ANFIS (Adaptive Neuro-Fuzzy Interactive System) – Grid and Cluster have been compared and it was found that ANFIS-cluster gives the best results but FM is more users friendly. For any expected inflow, reservoir level and demand, release can be calculated using developed GUI windows of the models.

Marketing as an Interaction System

Marketing thinkers identify concepts of relationship, interaction, and network as useful. Edgar Crane (1972) saw interaction as essential to buyer-seller decision-making. David Ford, Kristian Möller, and Håkan Håkansson followed with explanations of how marketing operates. Christian Grönroos expanded the horizon with ‘interactive marketing’. Evert Gummesson saw interaction as “active contact” and all marketing as relationships and interaction in networks. The Relationship Marketing field flourished – at least for a time. Whilst many proponents of “interactive communication” and “social interaction” do not see the interaction concept as problematic, they focus attention on practices. I choose to re-examine both ‘interaction’ and ‘communication’, and to relate these concepts to the concepts of society and the social process we call “marketing”. The discussion proceeds from the general perspective of humans living among others, to the specific situation of marketing in society. I examine the concept of ‘interaction’, and consider social interaction as exchange –a dialogical view of human communication. The patterning of social interaction in markets as distinct from bureaucracies, solidarity groupings, and co-operative collectives is examined. An alternative sociological analysis of the social is compared with that of the social psychology tradition. Communication is discussed as a mode of interaction, to reveal monologic (technical) and dialogic (humanitarian) conceptions of communication prevalent in the marketing field. Within the context of an ‘Interaction Society’, marketing is explained as a complex dynamic adaptive interaction system, revealing a conversational nature. It is proposed that interaction directs and co-ordinates, but also co-creates – ‘interactional work’ has innovative capacity.

Fuzzy set based multiobjective allocation of resources and its applications

This paper presents results of research into the use of the Bellman-Zadeh approach to decision making in a fuzzy environment for solving multiobjective optimization problems. Its application conforms to the principle of guaranteed result and provides constructive lines in obtaining harmonious solutions on the basis of analyzing associated maxmin problems. The use of the Bellman-Zadeh approach has served as a basis for solving a problem of multiobjective allocation of resources (or their shortages) and developing a corresponding adaptive interactive decision-making system (AIDMS1). Its calculating kernel permits one to solve maxmin problems using an algorithm based on a nonlocal search (modification of the Gelfand's and Tsetlin's “long valley” method). The AIDMS1 includes procedures for considering linguistic variables to reflect conditions that are difficult to formalize as well as procedures for constructing and correcting vectors of importance factors for goals. The use of these procedures permits one to realize an adaptive approach to processing information of a decision maker to provide successive improving of the solution quality. C++ windows of the AIDMS1 are presented for input, output, and special possibilities related to considering linguistic variables and constructing and correcting vectors of importance factors. The results of the paper are universally applicable and are already being used to solve power engineering problems.

Drivers of supply chain vulnerability: an integrated framework

PurposeThis paper aims to report on findings of a cross‐sector empirical study of the sources and drivers of supply chain vulnerability.Design/methodology/approachThe research was undertaken in accordance with the realist tradition. It begins with a descriptive exploratory stage involving an in‐depth exploratory case study of aerospace industry supply chains, validated through in‐depth interviews with managers representing other “critical sectors” of the UK economy. This is followed by an explanatory theoretical stage. The work is supported throughout with reference to relevant literature sources.FindingsThe findings highlight the absence of any widespread understanding of the scope of and dynamic nature of the problem, which should be considered from multiple perspectives and at four levels of analysis: value stream/product or process; asset and infrastructure dependencies; organisations and inter‐organisational networks; and social and natural environment.Research limitations/implicationsThe paper is normative rather than positive, so focuses on understanding why supply chains are vulnerable to disruption, rather than presenting itself as a prescription for management. The paper does not investigate academic definitions or existing taxonomies of risk.Practical implicationsThe work provides some useful insights for practising managers and policy makers.Originality/valueThe paper reports on empirical research, then draws as appropriate on network theory and complex systems perspectives to produce a conceptual model of a supply chain as in interactive adaptive system.

PEXIS: Probabilistic experience representation based adaptive interaction system for personal robots

AbstractIn this paper the authors focus on the interaction between users and personal robots that can move in a real environment. When the creation of robots that can perform in an ordinary home or office is considered, it is difficult to imagine beforehand what kind of environment will be used, and so the approach in which developers embed environmental knowledge and strategies for autonomous movement fails. Thus, the authors propose an approach in which knowledge of the environment and the knowledge needed to move are acquired after development by allowing the robot and the user who is using the robot to engage in dialogue, and representing experience statistically. The authors introduce PEXIS, an interaction system developed using this approach, and then describe the characteristics and utility of their system via examples such as learning to avoid objects in an office environment and adapting to the vocabulary expressions of a particular user. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(6): 98–109, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10034

Quick fuzzy backpropagation algorithm

A modification of the fuzzy backpropagation (FBP) algorithm called QuickFBP algorithm is proposed, where the computation of the net function is significantly quicker. It is proved that the FBP algorithm is of exponential time complexity, while the QuickFBP algorithm is of polynomial time complexity. Convergence conditions of the QuickFBP, resp. the FBP algorithm are defined and proved for: (1) single output neural networks in case of training patterns with different targets; and (2) multiple output neural networks in case of training patterns with equivalued target vector. They support the automation of the weights training process (quasi-unsupervised learning) establishing the target value(s) depending on the network's input values. In these cases the simulation results confirm the convergence of both algorithms. An example with a large-sized neural network illustrates the significantly greater training speed of the QuickFBP rather than the FBP algorithm. The adaptation of an interactive web system to users on the basis of the QuickFBP algorithm is presented. Since the QuickFBP algorithm ensures quasi-unsupervised learning, this implies its broad applicability in areas of adaptive and adaptable interactive systems, data mining, etc. applications.

Creating and using models for engineering design: a machine-learning approach

An adaptive and interactive modeling system (AIMS) that integrates simulation, optimization and machine learning to help engineers make design decisions is described. AIMS views engineering decision making as a two-phase process of creating and then using models. The competitive relation learner and the induce-and-select optimizer, AIMS's two main components, and their roles in both phases of decision-making are discussed. AIMS's role in supporting the design of a diesel engine that outputs power within the 440- to 460-kW range and consumes the least amount of fuel is also discussed. >

A dynamic model of man-machine interactions: design and application with an audiographic learning facility

A generalized conceptual dynamic model of man-machine interactions with its symbolic description is proposed. The model is intended to represent the man-machine interactive behaviors of interactive adaptive logic systems. A study of an online audiographic learning facility, with emphasis on a pre-selected set of interactive functions, is presented to illustrate the use of the model.

STUDIES OF LINKAGE IN POPULATIONS. VII. TEMPORAL VARIATION AND X-CHROMOSOMAL LINKAGE DISEQUILIBRIUMS.

A fundamental tenet of modern evolutionary thought is that mechanisms must exist to promote the development of systems of interacting non-allelic genes, since few if any significant adaptations involve single gene effects. The preceding paper (Levitan, 1973) has demonstrated that the gene arrangements on the two arms of the X-chromosome of Drosophila robusta Sturtevant provide evidence for one such interaction system, inasmuch as the frequencies of certain combinations of these linked arrangements often exhibit cyclic seasonal variation not attributable to one or another of the constituent arrangements. The writer has shown earlier (Levitan, 1955, 1958a, 1961a, 1961b, 1964) that in several localities another manifestation of such an adaptive interaction system is the presence of linkage disequilibrium. A linkage disequilibrium or association exists when, contrary to theoretical expectations in the absence of selection (Robbins, 1916; Geiringer, 1944, 1948), certain combinations of linked genes or gene arrangements are significantly in excess of random proportions, other combinations deficient. A number of writers have since developed theoretical models outlining the conditions of recombination and selection for epistatic interaction that would be conducive to such disequilibriums (see Bodmer and Parsons (1962), Feldman and Crow (1970), and Sved (1971) for references to the work of Felsenstein, Karlin, Kimura, Lewontin, and others). The previously reported linkage disequilibriums were based on the frequencies of the arrangement combinations over a period of several years. They did not take into account the possibility that the total data were seasonally heterogeneous, as proved to be the case. This paper reanalyzes these data, and presents results from several additional localities, to determine whether the concept of linkage disequilibriums remains valid in the light of the variations in the component samples. It also examines the possibility that the seasonal samples themselves evidence disequilibriums and, if so, whether their nature are attributable to the fluctuations in the linkage combinations described by Levitan (1973). It turns out that the populations studied for temporal variation contain three different X-chromosomal disequilibrium (linkage association) systems. The data for each system will be discussed separately. Methods and notation are described in Levitan (1973).