Complex Application Domains Research Articles

Solving Two-Person Zero-Sum Stochastic Games With Incomplete Information Using Learning Automata With Artificial Barriers.

Learning automata (LA) with artificially absorbing barriers was a completely new horizon of research in the 1980s (Oommen, 1986). These new machines yielded properties that were previously unknown. More recently, absorbing barriers have been introduced in continuous estimator algorithms so that the proofs could follow a martingale property, as opposed to monotonicity (Zhang et al., 2014), (Zhang et al., 2015). However, the applications of LA with artificial barriers are almost nonexistent. In that regard, this article is pioneering in that it provides effective and accurate solutions to an extremely complex application domain, namely that of solving two-person zero-sum stochastic games that are provided with incomplete information. LA have been previously used (Sastry et al., 1994) to design algorithms capable of converging to the game's Nash equilibrium under limited information. Those algorithms have focused on the case where the saddle point of the game exists in a pure strategy. However, the majority of the LA algorithms used for games are absorbing in the probability simplex space, and thus, they converge to an exclusive choice of a single action. These LA are thus unable to converge to other mixed Nash equilibria when the game possesses no saddle point for a pure strategy. The pioneering contribution of this article is that we propose an LA solution that is able to converge to an optimal mixed Nash equilibrium even though there may be no saddle point when a pure strategy is invoked. The scheme, being of the linear reward-inaction ( LR-I ) paradigm, is in and of itself, absorbing. However, by incorporating artificial barriers, we prevent it from being "stuck" or getting absorbed in pure strategies. Unlike the linear reward- ϵ penalty ( LR-ϵP ) scheme proposed by Lakshmivarahan and Narendra almost four decades ago, our new scheme achieves the same goal with much less parameter tuning and in a more elegant manner. This article includes the nontrial proofs of the theoretical results characterizing our scheme and also contains experimental verification that confirms our theoretical findings.

Towards intelligent welding systems from a HCPS perspective: A technology framework and implementation roadmap

A framework and implementation roadmap for an intelligent welding system (IWS) is proposed from the human-cyber-physical systems (HCPS) perspective of integrating cyber systems with humans and physical systems. Key technologies and system requirements for the framework are comprehensively analyzed. A technology network is proposed to explore the link between complex IWS technologies and application domain requirements. To investigate the practical extent of the state-of-the-art, an example enterprise illustrates the technologies necessary to implement an IWS and the representative technological gaps. Technologies required for IWS were evaluated for their maturity, benefit, and market availability using the Gartner hype-cycle and priority matrix methodology. Finally, an implementation roadmap with research suggestions towards IWS is recommended. This work can support enterprises or factories that want to implement intelligent welding into their operations by clarifying the development state of intelligent technologies and the priority by which further development should be pursued.

Parallel best-first search algorithms for planning problems on multi-core processors

The multiplication of computing cores in modern processor units permits revisiting the design of classical algorithms to improve computational performance in complex application domains. Artificial Intelligence planning is one of those applications where large search spaces require intelligent and more exhaustive search control. In this paper, parallel planning algorithms, derived from best-first search, are proposed for shared memory architectures. The parallel algorithms, based on the asynchronous work pool paradigm, maintain good thread occupancy in multi-core CPUs. All algorithms use one ordered global list of states stored in shared memory from where they select nodes for expansion. A parallel best-first search algorithm that develops new states with depth equal to one is proposed first. Then, we propose an extension of this parallel algorithm that features a diversification strategy in order to escape local minima. We study and analyse a set of computational experiments for problems that come from the International Planning Competition and real-world industry applications. The empirical evaluation shows that the parallel algorithms solve most of the domains efficiently without incurring higher solutions costs. In those problems with partial results, we highlight the potential shortcomings of the proposed approaches for promising future directions.

Performance Assessment of Supervised Classifiers for Designing Intrusion Detection Systems: A Comprehensive Review and Recommendations for Future Research

Supervised learning and pattern recognition is a crucial area of research in information retrieval, knowledge engineering, image processing, medical imaging, and intrusion detection. Numerous algorithms have been designed to address such complex application domains. Despite an enormous array of supervised classifiers, researchers are yet to recognize a robust classification mechanism that accurately and quickly classifies the target dataset, especially in the field of intrusion detection systems (IDSs). Most of the existing literature considers the accuracy and false-positive rate for assessing the performance of classification algorithms. The absence of other performance measures, such as model build time, misclassification rate, and precision, should be considered the main limitation for classifier performance evaluation. This paper’s main contribution is to analyze the current literature status in the field of network intrusion detection, highlighting the number of classifiers used, dataset size, performance outputs, inferences, and research gaps. Therefore, fifty-four state-of-the-art classifiers of various different groups, i.e., Bayes, functions, lazy, rule-based, and decision tree, have been analyzed and explored in detail, considering the sixteen most popular performance measures. This research work aims to recognize a robust classifier, which is suitable for consideration as the base learner, while designing a host-based or network-based intrusion detection system. The NSLKDD, ISCXIDS2012, and CICIDS2017 datasets have been used for training and testing purposes. Furthermore, a widespread decision-making algorithm, referred to as Techniques for Order Preference by Similarity to the Ideal Solution (TOPSIS), allocated ranks to the classifiers based on observed performance reading on the concern datasets. The J48Consolidated provided the highest accuracy of 99.868%, a misclassification rate of 0.1319%, and a Kappa value of 0.998. Therefore, this classifier has been proposed as the ideal classifier for designing IDSs.

Inference and reasoning in a Bayesian knowledge-intensive CBR system

This paper presents the inference and reasoning methods in a Bayesian supported knowledge-intensive case-based reasoning (CBR) system called BNCreek. The inference and reasoning process in this system is a combination of three methods. The semantic network inference methods and the CBR method are employed to handle the difficulties of inferencing and reasoning in uncertain domains. The Bayesian network inference methods are employed to make the process more accurate. An experiment from oil well drilling as a complex and uncertain application domain is conducted. The system is evaluated against expert estimations and compared with seven other corresponding systems. The normalized discounted cumulative gain (NDCG) as a rank-based metric, the weighted error (WE), and root-square error (RSE) as the statistical metrics are employed to evaluate different aspects of the system capabilities. The results show the efficiency of the developed inference and reasoning methods.

On the Joint Calibration of Multivariate Seasonal Climate Forecasts from GCMs

Abstract Multivariate seasonal climate forecasts are increasingly required for quantitative modeling in support of natural resources management and agriculture. GCM forecasts typically require postprocessing to reduce biases and improve reliability; however, current seasonal postprocessing methods often ignore multivariate dependence. In low-dimensional settings, fully parametric methods may sufficiently model intervariable covariance. On the other hand, empirical ensemble reordering techniques can inject desired multivariate dependence in ensembles from template data after univariate postprocessing. To investigate the best approach for seasonal forecasting, this study develops and tests several strategies for calibrating seasonal GCM forecasts of rainfall, minimum temperature, and maximum temperature with intervariable dependence: 1) simultaneous calibration of multiple climate variables using the Bayesian joint probability modeling approach; 2) univariate BJP calibration coupled with an ensemble reordering method (the Schaake shuffle); and 3) transformation-based quantile mapping, which borrows intervariable dependence from the raw forecasts. Applied to Australian seasonal forecasts from the ECMWF System4 model, univariate calibration paired with empirical ensemble reordering performs best in terms of univariate and multivariate forecast verification metrics, including the energy and variogram scores. However, the performance of empirical ensemble reordering using the Schaake shuffle is influenced by the selection of historical data in constructing a dependence template. Direct multivariate calibration is the second-best method, with its far superior performance in in-sample testing vanishing in cross validation, likely because of insufficient data relative to the number of parameters. The continued development of multivariate forecast calibration methods will support the uptake of seasonal climate forecasts in complex application domains such as agriculture and hydrology.

Bringing Order to Chaos – A Compact Representation of Partial Order in SAT-Based HTN Planning

HTN planning provides an expressive formalism to model complex application domains. It has been widely used in realworld applications. However, the development of domainindependent planning techniques for such models is still lacking behind. The need to be informed about both statetransitions and the task hierarchy makes the realisation of search-based approaches difficult, especially with unrestricted partial ordering of tasks in HTN domains. Recently, a translation of HTN planning problems into propositional logic has shown promising empirical results. Such planners benefit from a unified representation of state and hierarchy, but until now require very large formulae to represent partial order. In this paper, we introduce a novel encoding of HTN Planning as SAT. In contrast to related work, most of the reasoning on ordering relations is not left to the SAT solver, but done beforehand. This results in much smaller formulae and, as shown in our evaluation, in a planner that outperforms previous SAT-based approaches as well as the state-of-the-art in search-based HTN planning.

Constraint programming heuristics for configuring optimal products in multi product lines

Nowadays, complex application domains require configuring multi-product lines where product features and constraints among them are specified in several variability models. These variability models are enriched with inter-model constraints representing the existing relations among domain concerns, and with non-functional properties modeled as attributes attached to product features. Multiple techniques use constraint programming to automate the cumbersome task of manually configuring a suitable product. Currently, there are some proposals to improve the performance of constraint solvers when configuring single-model product lines, however configuration scenarios with multiple interrelated and attributed models are not yet targeted. This paper proposes and evaluates three search heuristics used to configure optimal products regarding multi-objective criteria. Results are compared against the default search strategy of the Choco constraint solver. We evaluated the performance for configuring optimal products in four state-of-the-art product lines and 130 generated variability models representing multi-product lines that scale up to 6400 features and 960 constraints. As a result, we observe that the proposed heuristics perform better than the default solver strategy when the variability models scale in terms of features. In contrast, the default strategy and one of the proposed heuristics perform better as the number of interdependencies between variability models increases.

Generation and evolution of multiple operation states in passively mode-locked thulium-doped fiber laser by using a graphene-covered-microfiber**Project supported by the National Natural Science Foundation of China (Grant Nos. 11304409 and 61705028), the Natural Science Foundation of Chongqing City, China (Grant Nos. csct2013jcyjA4004 and cstc2017jcyjA0893), the Scientific and Technological Research Program of Chongqing Municipal Education Commission, China (Grant No. KJ1500422), and

Using graphene-covered-microfiber (GCM) as a saturable absorber, the generation and evolution of multiple operation states are proposed and demonstrated in passively mode-locked thulium-doped fiber laser. The microfiber was fabricated using the flame brushing method to an interaction length of ∼ 1.2 cm with a waist diameter of ∼ 10 μm. Graphene layers were grown on copper foils by chemical vapor deposition and transferred onto the polydimethylsiloxane (PDMS) to form a PDMS/graphene film, which allowed light-graphene interaction via evanescent field. With the increase of the pump power from 1.25 W to 2.15 W, five different lasing regimes, including continuous-wave, conventional soliton mode-locking, multi-soliton mode-locking, a period of transition, and noise-like mode-locking, were achieved in a fiber ring cavity. To the best of our knowledge, it is the first report of the generation and evolution of multiple operation states by covering graphene on the microfiber in the 2-μm region. The results demonstrate that GCM can be a promising method for fabricating all fiber SA, and the switchable operation states can provide more portability in complex application domain.

Static and Dynamic Aspects of Application Domains: An Inductively Defined Modeling Technique That Allows Decomposition

Modeling is one of the most important parts of requirements engineering. Most modeling techniques focus primarily on their pragmatics and pay less attention to their syntax and semantics. Different modeling techniques describe different aspects, for example, Object-Role Modeling (ORM) describes underlying concepts and their relations while System Dynamics (SD) focuses on the dynamic behavior of relevant objects in the underlying application domain. In this paper we provide an inductive definition for a generic modeling technique. Not only do we describe the underlying data structure, we also show how states can be introduced for relevant concepts and how their life cycles can be modeled in terms of System Dynamics. We also show how decomposition can be applied to master complex application domains. As a result we get an integrated modeling technique covering both static and dynamic aspects of application domains. The inductive definition of this integrated modeling technique will facilitate the implementation of supporting tools for practitioners.

On the Importance of Subtext in Recommender Systems

Abstract Conversational recommender systems have been shown capable of allowing users to navigate even complex and unknown application domains effectively. However, optimizing preference elicitation remains a largely unsolved problem. In this paper we introduce SPEECHREC, a speech-enabled, knowledge-based recommender system, that engages the user in a natural-language dialog, identifying not only purely factual constraints from the users’ input, but also integrating nuanced lexical qualifiers and paralinguistic information into the recommendation strategy. In order to assess the viability of this concept, we present the results of an empirical study where we compare SPEECHREC to a traditional knowledge-based recommender system and show how incorporating more granular user preferences in the recommendation strategy can increase recommendation quality, while reducing median session length by 46 %.

Multi-stage dynamic ensemble selection using heterogeneous learning algorithms: application on classification problems

Classification is one of the most popular and significant machine learning research focuses. It particularly takes paramount importance when a data repository contains samples that can be used as the basis for future decision making. To improve classification accuracy in complex application domains, there has been a growing research activity in the study of efficient methods to construct classifier sets (or multi-classifiers approaches) by combining the results of several classifiers. For pattern classification, dynamic ensemble learning methods explore the use of different classifiers for different samples, therefore, obtaining better generalisation abilities than static ensemble learning methods. This paper introduces a new dynamic selection of learning algorithm based on competence and results of output classes classifier and entropy diversity measure. Obtained performances are compared to the ones of six multiple classifiers systems, using data sets taken from the UCI Machine Learning Repository and IFN-ENIT database. The proposed approach outperformed the benchmark systems in terms of classification accuracies regardless of the type of used classifiers.

A survey of flexible agent interaction approaches

The dynamic and complex application domains of today demand increased flexibility in inter-agent interactions, i.e. an increased ability of agents to consider changes in the system or behavior of other agents and choose from multiple ways of interacting with other agents to achieve the same goals. A number of approaches to support such flexible interactions have been proposed in the existing literature, and we offer an extensive review of these approaches, classifying them according to the manner in which they achieve flexibility. Each type of approaches is appraised using our novel analytical framework. Finally, we demonstrate how this framework can be used to identify which approaches are suitable for a given application domain, and we exemplify this aspect using the domains of e-commerce and dynamic service composition.

Overlapping correlation clustering

We introduce a new approach for finding overlapping clusters given pairwise similarities of objects. In particular, we relax the problem of correlation clustering by allowing an object to be assigned to more than one cluster. At the core of our approach is an optimization problem in which each data point is mapped to a small set of labels, representing membership in different clusters. The objective is to find a mapping so that the given similarities between objects agree as much as possible with similarities taken over their label sets. The number of labels can vary across objects. To define a similarity between label sets, we consider two measures: (i) a 0–1 function indicating whether the two label sets have non-zero intersection and (ii) the Jaccard coefficient between the two label sets. The algorithm we propose is an iterative local-search method. The definitions of label set similarity give rise to two non-trivial optimization problems, which, for the measures of set-intersection and Jaccard, we solve using a greedy strategy and non-negative least squares, respectively. We also develop a distributed version of our algorithm based on the BSP model and implement it using a Pregel framework. Our algorithm uses as input pairwise similarities of objects and can thus be applied when clustering structured objects for which feature vectors are not available. As a proof of concept, we apply our algorithms on three different and complex application domains: trajectories, amino-acid sequences, and textual documents.

4.5.2 Next Generation Systems Engineering: Expansion, Foundation, Unification

AbstractThe field of Systems Engineering (SE) is expanding into new more complex application domains. This paper argues that this expansion needs to be done in a systematic way that requires expansion of the science foundation of SE to provide adequate support of SE expansion and to achieve unification with traditional SE. The paper first discusses the vision of and motivation for next‐generation SE in terms of the characteristics of expansion, foundation, and unification. The remainder of the paper provides a sketch of a proposed approach to achieving the vision, based primarily on model‐orientation. The focus of the sketch is a model‐oriented science of SE.

Designing core ontologies

One of the key factors that hinders integration of distributed, heterogeneous information systems is the lack of a formal basis for modeling the complex, structured knowledge that is to be exchanged. To alleviate this situation, we present an approach based on core ontologies. Core ontologies are characterized by a high degree of axiomatization and formal precision. This is achieved by basing on a foundational ontology. In addition, core ontologies should follow a pattern-oriented design approach. By this, they are modular and extensible. Core ontologies allow for reusing the structured knowledge they define as well as integrating existing domain knowledge. The structured knowledge of the core ontologies is clearly separated from the domain-specific knowledge. Such core ontologies allow for both formally conceptualize their particular fields and to be flexibly combined to cover the needs of concrete, complex application domains. Over the last years, we have developed three independent core ontologies for events and objects, multimedia annotations and personal information management. In this paper, we present the simultaneous use and integration of our core ontologies at the example of a complex, distributed socio-technical system of emergency response. We describe our design approach for core ontologies and discuss the lessons learned in designing them. Finally, we elaborate on the beauty aspects of our core ontologies.

An attempt to model the relationship between MMI attenuation and engineering ground-motion parameters using artificial neural networks and genetic algorithms

Abstract. Complex application domains involve difficult pattern classification problems. This paper introduces a model of MMI attenuation and its dependence on engineering ground motion parameters based on artificial neural networks (ANNs) and genetic algorithms (GAs). The ultimate goal of this investigation is to evaluate the target-region applicability of ground-motion attenuation relations developed for a host region based on training an ANN using the seismic patterns of the host region. This ANN learning is based on supervised learning using existing data from past earthquakes. The combination of these two learning procedures (that is, GA and ANN) allows us to introduce a new method for pattern recognition in the context of seismological applications. The performance of this new GA-ANN regression method has been evaluated using a Greek seismological database with satisfactory results.

Implementing reactive BDI agents with user-given constraints and objectives

CASO is an agent-oriented programming language based on AgentSpeak(L), one of the most influential abstract languages based on the beliefs-desires-intentions (BDI) architecture. For many applications, it is more convenient to let the user provide in real time, a more elaborate specification consisting of constraints and preferences over possible goal states. Then, let the system discover a plan for the most desirable among the feasible goal states. CASO incorporates constraints and objectives into the symbolic approach of reactive BDI model which lead to better expressive capabilities as well as more efficient computation. Jason is a fully-fledged interpreter for a much improved version of AgentSpeak(L). In this work, we modify Jason to incorporate the operational semantics of CASO. CASO also uses ECLiPSe, an open source constraint solver, to apply constraint solving techniques. Our preliminary results show that CASO can be used as a powerful multi-agent programming language in solving problems in complex application domains.

A survey on the history of transaction management: from flat to grid transactions

Transactions have been around since the Seventies to provide reliable information processing in automated information systems. Originally developed for simple `debit-credit' style database operations in centralized systems, they have moved into much more complex application domains including aspects like distribution, process-orientation and loose coupling. The amount of published research work on transactions is huge and a number of overview papers and books already exist. A concise historic analysis providing an overview of the various phases of development of transaction models and mechanisms in the context of growing complexity of application domains is still missing, however. To fill this gap, this paper presents a historic overview of transaction models organized in several `transaction management eras', thereby investigating numerous transaction models ranging from the classical flat transactions, via advanced and workflow transactions to the Web Services and Grid transaction models. The key concepts and techniques with respect to transaction management are investigated. Placing well-known research efforts in historical perspective reveals specific trends and developments in the area of transaction management. As such, this paper provides a comprehensive, structured overview of developments in the area.

Kernel methods and flexible inference for complex stochastic dynamics

Approximation theory suggests that series expansions and projections represent standard tools for random process applications from both numerical and statistical standpoints. Such instruments emphasize the role of both sparsity and smoothness for compression purposes, the decorrelation power achieved in the expansion coefficients space compared to the signal space, and the reproducing kernel property when some special conditions are met. We consider these three aspects central to the discussion in this paper, and attempt to analyze the characteristics of some known approximation instruments employed in a complex application domain such as financial market time series. Volatility models are often built ad hoc, parametrically and through very sophisticated methodologies. But they can hardly deal with stochastic processes with regard to non-Gaussianity, covariance non-stationarity or complex dependence without paying a big price in terms of either model mis-specification or computational efficiency. It is thus a good idea to look at other more flexible inference tools; hence the strategy of combining greedy approximation and space dimensionality reduction techniques, which are less dependent on distributional assumptions and more targeted to achieve computationally efficient performances. Advantages and limitations of their use will be evaluated by looking at algorithmic and model building strategies, and by reporting statistical diagnostics.