Search

In recent years, the European Commission and the International Maritime Organization (IMO) implemented various operational measures and policies to reduce ship fuel consumption and related emissions. The effectiveness of these measures relies upon developing accurate predictive models encompassing the influence of real operational conditions. This paper presents a deep learning method for the prediction of ship fuel consumption. The method utilizes big data analytics from sensors, voyage reporting and hydrometeorological data, comprising of 266 variables made available following sea trials of a Kamsarmax bulk carrier of Laskaridis Shipping Co. Ltd. A variable importance estimation model using a Decision Tree (DT) is used to understand the underlying relationships in the available dataset. Consequently, a deep learning model is developed to understand the influence of sailing speed, heading, displacement/draft, trim, weather, sea conditions, etc. on ship fuel consumption (SFC). This is achieved by incorporating attention mechanism into Bi-directional Long Short-Term Memory (Bi-LSTM) network. The potential of the new method is demonstrated by training data streams corresponding to real ship fuel consumption rates as well as internal and external operational conditions. A comprehensive comparison with existing methods indicates that the Bi-LSTM with attention mechanism presents the best fit when using high frequency data. It is concluded that subject to further testing and validation the method could be used for the development of decision support systems for monitoring environmentally sustainable ship operations. [ABSTRACT FROM AUTHOR]

This is the first paper to apply a combination of HAZOP and Risk Consequence Matrix plus Cross Impact Analysis (CIA) and Interpretative Structural Modeling (ISM) methods for analyzing complex cascading effects in Operational Risk Management in an industrial environment. This combination of methods allow obtain more information than using HAZOP and Risk Consequence Matrix because upgrades the individual risk analysis with the correlation between risks. Its main objective is to improve the understanding of the overall picture of an organization׳s risks. The paper summarizes the development of the combination of this methods of the interaction of 18 critical events of an industrial plant as a first step to improving organizational resilience based on the company׳s own estimations as well as the estimates of an expert panel. The main benefit of using these methods is to know the relationships between different risks and consequences, direct links, indirect and cascading effects. Having the possibility of knowing a full risk map and being able to make a forecast will help to mitigate the unexpected/unprepared effects and have a better response making better decisions after an emergency situations is the same as being more resilient. [ABSTRACT FROM AUTHOR]

An emerging question for photovoltaic (PV) solar power development is how to ascertain the optimal choice from a finite set of available alternatives under numerous conflicting criteria as well as high levels of imprecise, vague, and uncertain information. For the first time, we investigate the prioritization of the alternatives for the development of PV solar power via the interval-valued intuitionistic fuzzy sets (IVIFSs), which show great power in capturing ambiguous, uncertain, and vague information, and mitigating information loss. This paper presents a novel integrated intelligent decision support system comprising of Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis, Analytic Hierarchy Process (AHP), and Combined Compromise Solution (CoCoSo) within an interval-valued intuitionistic fuzzy (IVIF) framework. Four alternatives are considered. To rank these alternatives, twelve criteria are defined under four aspects of SWOT analysis based on literature review and discussion with decision-makers. Subsequently, the IVIF-AHP method is utilized to determine the weights assigned to each criterion and sub-criterion. Finally, the IVIF-CoCoSo method is employed to rank four alternatives. The results showed that giving proactive attention to mitigating potential adverse environmental impacts of PV solar systems is the most highly prioritized strategy for PV solar power development. The results of the comparative and sensitivity analyses showed that the proposed method generates highly robust outcomes. The formulated integrated intelligent decision support system can help energy policy authorities with a valuable resource to craft optimal techniques for developing PV solar power. • A novel integrated MCDM approach for the development of solar energy is presented. • Challenges to solar energy development are identified and evaluated. • Strategies to overcome these challenges are provided. • Sensitivity analysis is done to validate the stability of the integrated approach. [ABSTRACT FROM AUTHOR]

In the current era, blockchain technology has emerged as a novel technique to maintain the operations of healthcare management systems. The global COVID-19 disease has led to increase in the utilization of technology for healthcare supply chain, patient data management, and claims settlement. Data management in healthcare industry is a complex procedure where multiple organizations offer appropriate supply chain facilities in everyday life. Inadequate data handling disrupts the supply chain, which has a longstanding impact on the healthcare region. Blockchain-based solutions are renowned for their ability to produce safe and traceable results and effective in the health sector for secure data retrieval and storage, resulting in more effectual product creation and tracking. These technologies can deliver data provenance, sponsors candid healthcare industry demands, and certifies the immutability of multi direction transactions. Due to involvement of multiple factors/criteria, the selection of an effective blockchain platform-based healthcare supply chain can be treated as a decision support system (DSS) problem. Thus, the objective of this paper is to present a novel interval-valued Pythagorean fuzzy DSS for evaluating the blockchain platforms for healthcare supply chain and selecting a suitable one with respect to multiple criteria and uncertainty. The proposed DSS framework is divided into three stages. First, some fairly aggregation operators are presented to combine the individual's information and also discussed their desirable characteristics on interval-valued Pythagorean fuzzy sets (IVPFSs). Second, an integrated weighting tool is developed using entropy-based tool for objective weight of criteria and pivot pairwise relative criteria importance assessment (PIPRECIA) model for subjective weight of criteria with IVPFSs. For this purpose, new entropy is presented on IVPFSs. Third, the multi-attribute ideal-real comparative analysis (MAIRCA) model is developed with the combination of fairly aggregation operators, entropy-based weighting tool and PIPRECIA model with interval-valued Pythagorean fuzzy information. Further, the proposed DSS is used on a case study of blockchain platforms for healthcare supply chain evaluation, which confirms its applicability and usefulness. Sensitivity and comparative assessments are carried out to check the consistency, robustness and efficiency of the presented method. • Hybrid decision support system with interval-valued Pythagorean fuzzy sets (IVPFSs) is proposed. • New IVPF-fairly aggregation operator and IVPF-entropy are developed. • Integration of criteria weighting tool using an IVPF-entropy and IVPF-PIPRECIA is presented. • A case of blockchain platforms assessment for healthcare supply chain is discussed. [ABSTRACT FROM AUTHOR]

Using medical science alongside time series data analysis can be given a strong tool to develop efficient decision support systems in Corona pandemic. In this regard, many hybrid learning-oriented (HL) approaches have been presented, which rely on modeling the linear and non-linear components of the time series. However, there is a lack of comprehensive study of such approaches to achieve a macro vision of Covid-19 data prediction models in an unified reference. We conducted a comparative analytical study on (HL) approaches for predicting Covid-19 data. The main scope of current study is the investigate of such approaches. The original contribution of the paper is to present a reference-point and roadmap for future studies, which is provided in three forms. First, we experimentally evaluated the efficiency of all learning-based combinations on types of Covid-19 data in a similar context. Second, we tried to provide a guidance for choosing a more proper hybrid through valid empirical and statistical evaluations. Third, we presented an efficient and generalizable approach called HL-ALL (H ybrid L earning A RIMA L STM L STM). Evaluation results show high potential of HL-ALL in dealing Covid-19 data when prediction. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents the development of a decision support system for monitoring and diagnosis of the amine-based post-combustion carbon dioxide (CO2) capture process system at the International Test Centre for CO2 Capture (ITC) at the University of Regina. The amine-based CO2 absorption capture process system consists of dozens of components and generates more than a hundred different types of data. The vast amount of raw data produced by the system are measurements of the many reaction components, valves and pumps. The system operators often find it difficult to quickly detect, diagnose and correct any abnormal conditions that may arise during operation. Therefore, developing a decision support system for monitoring and diagnosis of the CO2 capture process system which aids the operator in monitoring and diagnosis of the system is a desirable objective. This paper describes development of the system based on the dual foundation of a domain ontology and an intelligent system framework in the domain of carbon dioxide capture process. The developed ontology provides the semantic knowledge foundation; it was implemented in the Knowledge Modeling System (KMS), and the knowledge was stored in the XML format. The intelligent system framework consists of system functions which can use the XML schema provided by the ontology and support the development process. A decision support expert system for process monitoring is a sample system developed on the dual foundation. [Copyright &y& Elsevier]

Abstract: In the past there has been no structured approach to learning from construction projects once they are completed. Now, however, the construction industry is adapting concepts of tacit and explicit knowledge management to improve the situation. Top managers generally assume that professionals in enterprises already possess tacit knowledge and experience for specific types of projects. Such knowledge is extremely important to organisations because, once a project is completed, professionals tend to forget it and start something new. Therefore, knowledge multifold utilisation is a key factor in productively executing a construction project. This paper discusses the benefits of knowledge management to construction industry organisations and projects and emphasises the significance of tacit knowledge. The main purpose of this paper is to present the integrated knowledge management model for the construction industry as well as system architecture and system of the Knowledge Based Decision Support System for Construction Projects Management (KDSS-CPM) which the authors of this paper have developed. Different knowledge management models that are presented in scientific literature are discussed and compared, and the proposed new, KDSS-CPM model, as developed by this paper’s authors, is introduced. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a comparison between different wavelet feature vectors for data mining of nonstationary time series that occurs in an electricity supply network. Three different wavelet algorithms are simulated and applied on nine classes of power signal time series, which primarily belongs to an important problem area called electric power quality. In contrast to the wavelet analysis, the paper presents a new approach called S-transform-based time frequency analysis in processing power quality disturbance data. Certain pertinent feature vectors are extracted using the well-known wavelet methods and the new approach using S-transform. Neural networks are then used to compute the classification accuracy of the feature vectors. Certain characteristics of the wavelet feature vectors are apparent from the results. Further in large data sets partitioning is done and similarities of pattern vectors present in different sections are determined. The approach is a general one and can be applied to pattern classification, similarity determination, and knowledge discovery in time varying data patterns occurring in many practical sciences and engineering problems. [Copyright &y& Elsevier]

Supply lead time constitutes a core parameter in inventory management and plays a critical role in supply chain performance. Yet, how to promote better supply lead time estimations that account for multivariate effects of historical supplier dynamics remains poorly understood. This paper proposes a decision support system that uses a supervised regression strategy with multivariate information for estimating supply lead times. We combine ideas from big data analytics and data mining to explore the effects of different supply-related variables on the dynamics of supply lead time. We design a robust rolling window evaluation scheme to compare both the statistical and inventory performance of different well-known data mining models. Numerical tests with empirical data from a large automotive manufacturer demonstrate that the Random Forest model consistently outperforms other competing models, leading to median decreases of 18%–24% in the mean absolute errors of supply lead time estimations. As a consequence of our results, we also provide insights on how these estimations contribute to the proactive management of safety stocks. [ABSTRACT FROM AUTHOR]

The work of criminal police in contemporary society is characterized by the proliferation of data and information to be processed, a more significant limitation of access to personal data, increased public monitoring, and higher expectations in the efficiency of identifying perpetrators. Also, all information collected during investigations is distributed through police systems separated by different levels and organization units, and often there are insufficient human and material resources. Resolving the perpetrator's identity in those circumstances is a complex task, and police decision support systems must group all available evidence related to specific persons. For that purpose, this paper proposes a new approach to unconstrained pairwise clustering of face feature vectors extracted from the histogram of oriented gradients descriptor, named Truth-value clustering (TVC), based on non-axiomatic logic and graphs. The clustering approach was experimentally tested with six different face image databases. They were created to simulate unconstrained conditions like IARPA Janus Benchmark-B Face Dataset (IJB-B), IMDb-Wiki, Labeled Faces in the Wild, and YouTube Faces. The results of the proposed solution are compared with other state-of-the-art methods, showing that the approach gives, in summary, significantly better results. Application of the IJB-B protocol created for testing face clustering showed that the new approach gives better results by an average of 8.25% (σ = 4. 2). The main advantage over other methods is the possibility of utilizing mechanisms from non-axiomatic logic such as revision, which can then acquire new knowledge based on information from different nodes of the distributed environment consisting of various police information systems. • Face clustering is base of a decision-supporting system for identity resolution. • The approach to pairwise face clustering is based on non-axiomatic logic. • Revision from non-axiomatic logic enables face clustering in a distributed environment. • The approach is tested on six datasets and compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In the classical vehicle routing problems, the objective function is usually to minimize the transportation cost without considering the pricing decision-making. However, in some practical applications, such as riding-share services and fast-food delivery services, logistics companies aim to maximize profits, involving decision-making issues closely related to the pricing and route planning. This paper designs an adaptive large neighborhood search (ALNS) based approach to solve a vehicle routing problem with zone-based pricing (VRPZ). In the studied problem, the customers in the same zone share the same price for transportation, and each customer could accept or reject the price given by the logistics company. On the one hand, a too-high pricing strategy may reduce the number of served customers; on the other hand, a too-low pricing strategy may result in low earnings for logistics companies. VRPZ optimizes the routing planning and seeks an appropriate pricing strategy to maximize the total profit, which is the difference value of total earnings and costs. Considering that the studied problem is a computational challenge, we have developed an algorithm incorporating the local search into ALNS, particularly nested with two varying pricing operators: price + + and price − − , to solve the problem. The proposed algorithm has been compared with pure ALNS, variable neighborhood search (VNS) and Simulated Annealing (SA) by solving 472 benchmark instances in the published work. The compared results, which are validated by the statistic tests, highlight the efficiency and effectiveness of the proposed algorithm. To our best knowledge, this is the first heuristic to achieve a good performance in solving the benchmark instances. This study is significant for the retail industry to find a reasonable logistics pricing strategy and improve operational efficiency, as well as lays a foundation for developing a decision support system. • We focused on a new vehicle routing problem. • We integrated ALNS with local search using a new framework. • Two new operators price＋＋ and price−− are specially designed for the algorithm. • The experimental results highlight the good performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Hesitant fuzzy set based linear regression model is used to solve decision making problems, where each element is assessed with multiple membership grades. However, in order to handle uncertainty properly, non-membership and abstinence degrees of each elements are also considered as equally significant, which are not captured by hesitant fuzzy set. To resolve these limitations of hesitant fuzzy set based model, this paper proposes hesitant t-spherical fuzzy linear regression model, where hesitant t-spherical fuzzy set can efficiently handle both non-membership and abstinence degrees along with membership degree. The regression model is used to determine the imprecise functional relationship between the dependent and independent variables which are represented using hesitant t-spherical fuzzy set. We apply gradient descent technique to estimate the optimal coefficients of the variables used in the proposed regression model. Finally, the residuals of the regression are computed for the purpose of decision making. The proposed approach has been illustrated using three real life applications (robot selection, revenue generation, and material selection) and compared with the existing approaches. Moreover, we have used sensitivity analysis and weighted spearman's rank correlation coefficient metrics to demonstrate that the outcome of the proposed model is more consistent and reliable to rank its best alternative compared to existing approaches, which shows its capability to solve real life uncertain decision-making problems. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of safety monitoring in underground coal mines. In particular, we investigate and compare practical methods for the assessment of seismic hazards using analytical models constructed based on sensory data and domain knowledge. For our case study, we use a rich data set collected during a period of over five years from several active Polish coal mines. We focus on comparing the prediction quality between expert methods which serve as a standard in the coal mining industry and state-of-the-art machine learning methods for mining high-dimensional time series data. We describe an international data mining challenge organized to facilitate our study. We also demonstrate a technique which we employed to construct an ensemble of regression models able to outperform other approaches used by participants of the challenge. Finally, we explain how we utilized the data obtained during the competition for the purpose of research on the cold start problem in deploying decision support systems at new mining sites. [ABSTRACT FROM AUTHOR]

Predictive Process Analytics is becoming an essential aid for organizations, providing online operational support of their processes. However, process stakeholders need to be provided with an explanation of the reasons why a given process execution is predicted to behave in a certain way. Otherwise, they will be unlikely to trust the predictive monitoring technology and, hence, adopt it. This paper proposes a predictive analytics framework that is also equipped with explanation capabilities based on the game theory of Shapley Values. The framework has been implemented in the IBM Process Mining suite and commercialized for business users. The framework has been tested on real-life event data to assess the quality of the predictions and the corresponding evaluations. In particular, a user evaluation has been performed in order to understand if the explanations provided by the system were intelligible to process stakeholders. • Predictive Business Process Monitoring provides online operational support. • Explainability is a necessary condition to build trust in the predictive technology. • Explainable AI framework needs to be validated with real end users. • Deployment of an Explainable Predictive framework to provide process insights. • Shapley values provide the importance of the factors influencing the prediction. [ABSTRACT FROM AUTHOR]

In industrial systems, a fault occurring on a process can create an alarm flood, a succession of alarms raised at a rate per minute so high it overwhelms the process operator in charge of the monitoring of the process. In this paper, a method to extract fault templates from a set of alarm lists raised on the occurrence of several faults is proposed. Alarm lists generated by the same fault are condensed into a weighted sequential fault template formed of the sequence of alarms the most frequently produced on the occurrence of the fault. Each alarm is weighted according to its relevance to diagnose the fault. It is further shown how the fault templates can be used to extract relevant information on the alarm system and be used by operators as guidelines for fault diagnosis. Moreover, an on line fault isolation method using a weighted sequential similarity measure is proposed. The results obtained by the method on a data set formed of alarm lists raised by the control system of the CERN LHC connected to a simulator of one of the LHC processes are presented and discussed. [ABSTRACT FROM AUTHOR]

Decision making is required by many tasks, such as shopping, nowadays assisted by software systems, and providing support to the decision making process is a feature that would significantly improve such systems. Many decision support systems and related approaches have been proposed to that purpose, but they often involve tedious elicitation processes or previously collected data. In this paper, we propose an automated decision making technique, which chooses an option from the set of those available based on preferences and priorities expressed in a high-level preference language, exploiting natural-language terms, such as expressive speech acts. Moreover, in order to make a decision, our technique goes beyond the provided preferences with psychology-inspired heuristics, which concern how humans make decisions, as provided preferences are typically not enough to resolve trade-offs among available options. Two studies were performed to evaluate our approach, and results indicate that our technique is effective both by comparing its recommendations with those made by a human expert, and by considering evaluation scores provided by users that experienced our technique. [ABSTRACT FROM AUTHOR]

Recently, mobile devices have dramatically improved their communications and processing capabilities, so enabling the possibility of embedding knowledge-based decision support components within Remote Health Monitoring (RHM) applications for the ubiquitous and seamless management of chronic patients. According to these considerations, this paper presents a light-weight, rule-based, reasoning system, purposely designed and optimized to build knowledge-based Decision Support Systems efficiently embeddable in mobile devices. The key issues of such a system are both a domain-independent reasoning algorithm and knowledge representation capabilities, specifically thought for both computation intensive and real-time RHM scenarios. The performance evaluation of the proposed system has been arranged according to the Taguchi’s experimental design and performed directly on a mobile device in order to quantitatively assess its effectiveness in terms of memory usage and response time. Moreover, a case study has been arranged in order to evaluate the effectiveness of the proposed system within a real RHM application for monitoring cardiovascular diseases. The evaluation results show that the system offers an innovative and efficient tool to build mobile DSSs for healthcare applications where real-time performance or computation intensive demands have to be met. [ABSTRACT FROM AUTHOR]

In the field of Supply Chain Risk Management, the attitude of managers toward risk affect the tactical decision-making process in collaborative supply chains under an uncertain environment, concerning especially capacity levels, lot-sizing rules, purchasing strategies, production scheduling,…, etc. The issue can be formulated as a sequential decision problem under uncertainty where the customer decisions affect the decisions made by the supplier. In this paper we deal with two kinds of uncertainties. The first one is the uncertainty on the indicators of performance (which are not comparable) used by the decision maker to choose a solution (for example: service quality or inventory cost). Hence, we propose an approach based on subjective probability to evaluate the probability that a decision is optimal for the first actor and the probability that it is optimal for both. From these two evaluations, we propose a ranking function to help the first actor to take into account the second one when selecting a decision. The second kind of uncertainty pertains to the demand. A classical criterion under total uncertainty is Hurwicz criterion where a weight expresses a degree of pessimism. Nevertheless, the degree of pessimism is itself ill-known. Thus, it becomes difficult to take into account the behavior of the actors. Hence, we propose an approach based on possibility theory and the so-called pignistic transform, which computes a subjective probability distribution over the criteria. Then, we apply the method used for uncertain criterion. This approach is illustrated through an example and an industrial case study. [ABSTRACT FROM AUTHOR]

Abstract: Many engineering design problems must optimize multiple objectives. While many objectives are explicit and can be mathematically modeled, some goals are subjective and cannot be included in a mathematical model of the optimization problem. A set of alternative non-dominated fronts that represent multiple optima for problem solution can be identified to provide insight about the decision space and to provide options and alternatives for decision-making. This paper presents a new algorithm, the Multi-objective Niching Co-evolutionary Algorithm (MNCA) that identifies distinct sets of non-dominated solutions which are maximally different in their decision vectors and are located in the same non-inferior regions of a Pareto front. MNCA is demonstrated to identify a set of non-dominated fronts with maximum difference in decision vectors for a set of real-valued problems. [Copyright &y& Elsevier]

Abstract: Optimum design introduces strong emphasis on compact geometry parameterization in order to reduce the dimensionality of the search space and consequently optimization run-time. This paper develops a decision support system for optimum shape which integrates geometric knowledge acquisition using 3D scanning and evolutionary shape re-engineering by applying genetic-algorithm based optimum search within a distributed computing workflow. A shape knowledge representation and compaction method is developed by creating 2D and 3D parameterizations based on adaptive chaining of piecewise Bezier curves and surfaces. Low-degree patches are used with adaptive subdivision of the target domain, thereby preserving locality. C1 inter-segment continuity is accomplished by generating additional control points without increasing the number of design variables. The control points positions are redistributed and compressed towards the sharp edges contained in the data-set for better representation of areas with sharp change in slopes and curvatures. The optimal decomposition of the points cloud or target surface into patches is based on the requested modeling accuracy, which works as lossy geometric data-set compression. The proposed method has advantages in non-recursive evaluation, possibility of chaining patches of different degrees, options of prescribing fixed values at selected intermediate points while maintaining C1 continuity, and uncoupled processing of individual patches. The developed procedure executes external application nodes using mutual communication via native data files and data mining. This adaptive interdisciplinary workflow integrates different algorithms and programs (3D shape acquisition, representation of geometry with data-set compaction using parametric surfaces, geometric modeling, distributed evolutionary optimization) such that optimized shape solutions are synthesized. 2D and 3D test cases encompassing holes and sharp edges are provided to prove the capacity and respective performance of the developed parameterizations, and the resulting optimized shapes for different load cases demonstrate the functionality of the overall distributed workflow. [Copyright &y& Elsevier]

Abstract: Competence management calls for automated knowledge-based services in order to take full advantage from the know-how of a company. This paper presents an integrated semantic-based knowledge management system providing decision support services for several activities typical of competence management, including core competence evaluation, human resources allocation, training programs planning. Knowledge resources are represented according to the formalism of Description Logics, which also allows for inference services crucial for the implemented solutions. We present the various features of our approach, which exploit advanced non-standard reasoning services from Description Logics, specifically developed to support knowledge management. [Copyright &y& Elsevier]

Abstract: Uncertain ground conditions represent the primary source of risk in underground tunnel construction. However, this problem can be solved by developing an accurate, probabilistic description of the geology. This paper presents a general model for probability based determination of tunnel geology that can be used as a basis for developing more effective decision support systems for tunneling design and construction. The proposed model is based on a Hidden Markov Model (HMM) and a neural network (NN). An approximate inference technique – a Particle Filter (PF) Algorithm – is used to simulate the geological parameters. This model overcomes the deficiencies of existing models by readily incorporating all available geologic information and updating geologic predictions based on observations given by the neural network. In order to validate the proposed model, the “Drainage Water Tunnel Project” at Zhong-He, Taipei, Taiwan was used. The results showed that the Neural-HMM model provides high accuracy in geological prediction. [Copyright &y& Elsevier]

Abstract: In this paper, we describe the development of an extended migration operator, which combats the negative effects of noise on the effective search capabilities of genetic algorithms. The research is motivated by the need to minimise the number of evaluations during hardware-in-the-loop experimentation, which can carry a significant cost penalty in terms of time or financial expense. The authors build on previous research, where convergence for search methods such as simulated annealing and variable neighbourhood search was accelerated by the implementation of an adaptive decision support operator. This methodology was found to be effective in searching noisy data surfaces. Providing that noise is not too significant, genetic algorithms can prove even more effective guiding experimentation. It will be shown that with the introduction of a controlled migration operator into the GA heuristic, data, which represents a significant signal-to-noise ratio, can be searched with significant beneficial effects on the efficiency of hardware-in-the-loop experimentation, without a priori parameter tuning. The method is tested on an engine-in-the-loop experimental example, and shown to bring significant performance benefits. [Copyright &y& Elsevier]

Abstract: Optimum design problems are frequently formulated using a single excellence criterion (minimum mass or similar) with evolutionary algorithms engaged as decision-support tools. Alternatively, multi-objective formulations are used with a posteriori decision-making amongst the Pareto candidate solutions. The former typically introduces excessive simplification in the decision space and subjectivity, the latter leads to extensive numerical effort and postpones the compromise decision-making. In both cases, engineering excellence metrics such as minimum mass can be misleading in terms of performance of the respective design in the given operational environment. This paper presents an alternative approach to conceptual design where a compound objective function based on the Net Present Value (NPV) and Internal Rate of Return (IRR) aggregate performance metrics is developed. This formulation models the integral value delivered by the candidate designs over their respective life-cycles by applying value-based NPV discounting to all objectives. It can be incorporated as an a priori compromise and consequently viewed as a weighted sum of individual objectives corresponding to their economically faithful representation over the entire operational life-time of the designs. The multi-objective design optimization is consequently expanded from purely engineering terms to coupled engineering–financial decision support. [Copyright &y& Elsevier]

Abstract: In this paper, we are considering that the design process can be modelled in the form of a constraint satisfaction problem (CSP). CSP modelling or resolution has proved its efficiency within the framework of single-designer design. We propose to extend the functions of CSP to the context of multi-concept design of the same artefact. We define CoCSP as cooperative constraint satisfaction problem including the actors of the design problem. We are presenting the operating principles of an algorithm for the real-time management of design decisions, based on a model described in the form of a CoCSP for the integration of supply-chain constraints. This algorithm enables the number of design decisions rejected at a given moment in design to be kept to a minimum. The algorithm forms the core of a prototype for an unsupervised, generic constraint-based collaborative design system. Our aim is to produce a platform centred on the notion of constraints that will enable a product design problem to be modelled and solved by integrating supply-chain constraints as far upstream as possible. [Copyright &y& Elsevier]

Abstract: This paper aims at providing real-time decision support in reaction to disruptive events in manufacturing environments. More precisely, we demonstrate how this approach can support the rescheduling process in enterprise resource planning (ERP)-controlled environments. Our demonstrative example, based on a real scenario in the aluminum industry, illustrates how a genetic algorithm and a real-time discrete event simulation model can be integrated within the common enterprise information systems. [Copyright &y& Elsevier]

Abstract: In knowledge discovery and data mining many measures of interestingness have been proposed in order to measure the relevance and utility of the discovered patterns. Among these measures, an important role is played by Bayesian confirmation measures, which express in what degree a premise confirms a conclusion. In this paper, we are considering knowledge patterns in a form of “if…, then…” rules with a fixed conclusion. We investigate a monotone link between Bayesian confirmation measures, and classic dimensions being rule support and confidence. In particular, we formulate and prove conditions for monotone dependence of two confirmation measures enjoying some desirable properties on rule support and confidence. As the confidence measure is unable to identify and eliminate non-interesting rules, for which a premise does not confirm a conclusion, we propose to substitute the confidence for one of the considered confirmation measures in mining the Pareto-optimal rules. We also provide general conclusions for the monotone link between any confirmation measure enjoying the desirable properties and rule support and confidence. Finally, we propose to mine rules maximizing rule support and minimizing rule anti-support, which is the number of examples, which satisfy the premise of the rule but not its conclusion (called counter-examples of the considered rule). We prove that in this way we are able to mine all the rules maximizing any confirmation measure enjoying the desirable properties. We also prove that this Pareto-optimal set includes all the rules from the previously considered Pareto-optimal borders. [Copyright &y& Elsevier]

This paper is concerned with a SOM-based data mining strategy for adaptive modelling of a slowly varying process. The aim is to follow the process in a way that makes a representative up-to-date data set of a reasonable size available at any time. The technique developed allows analysis and filtering of redundant data, detection of the need to update the process models and the core-module of the system itself and creation of process models of adaptive, data-dependent complexity. Experimental investigations performed using data from a slowly varying offset lithographic printing process have shown that the tools developed can follow the process and make the necessary adaptations of the data set and the process models. A low-process modelling error has been obtained by employing data-dependent committees for modelling the process. [Copyright &y& Elsevier]

Abstract: This paper describes two data analysis techniques adopted in a Decision Support System (DSS) that aids users in predicting oil production of an infill well. The system generates predictions in the form of a possible range of cumulative production and length of production life of an infill well. The system also shows the worst and best case scenarios based on different production curves so that the expert can examine the plots of predicted production rates for each existing well and decide which model gives the best fit. The production curve of each individual well was mathematically modeled so that production values beyond the historical data can be produced. Decline curve estimation and neural network approaches were adopted for data analysis in the system. The system was tested with data from two groups of wells from two different fields in Saskatchewan, Canada. Observations on the suitable duration that the historical data set should cover and a comparison among different curve estimation and neural network models are presented. [Copyright &y& Elsevier]

This paper presents the design of an artificial autonomous system (called AAS) for the stock market domain that considers an approximation from the Big Five model, which proposes that the personality of an individual belongs to one of five different personality profiles: openness, conscientiousness, extraversion, agreeableness, and neuroticism. Several studies have explored investment and financial issues while considering the Big Five model, usually by analyzing data obtained from surveys applied to real people. However, to the best of our knowledge, there are no proposals that suggest the design of an AAS for supporting investment decisions that use the Big Five model as the central approach. The main objective of this proposal is to design an AAS for making investment decisions, where the decisions are adjusted to market conditions through the use of a policy function that adapts over time. This policy function adjusts the consumption level and investment portfolio composition required by the investment profile, considering both the market conditions and the Big Five model profile associated with the AAS. The effectiveness of the investment process is measured by observing the variations in the accumulated wealth and utility. The utility is measured through an abstract representation of the well-being or satisfaction of the investor (i.e., the AAS). AAS—Extraversion obtained the highest accumulated wealth, while AAS—Agreeableness obtained the highest level of utility, showing that the accumulated wealth is only one factor influencing the investor's well-being. [ABSTRACT FROM AUTHOR]

Every year about one third of the food production intended for humans gets lost or wasted. This wastefulness of resources leads to the emission of unnecessary greenhouse gas, contributing to global warming and climate change. The solution proposed by the SORT project is to "recycle" the surplus of food by reconditioning it into animal feed or fuel for biogas/biomass power plants. In order to maximize the earnings and minimize the costs, several choices must be made during the reconditioning process. Given the extremely complex nature of the process, Decision Support Systems (DSSs) could be helpful to reduce the human effort in decision making. In this paper, we present a DSS for food recycling developed using two approaches for finding the optimal solution: one based on Binary Linear Programming (BLP) and the other based on Answer Set Programming (ASP), which outperform our previous approach based on Constraint Logic Programming (CLP) on Finite Domains (CLP(FD)). In particular, the BLP and the CLP(FD) approaches are developed in ECL i PS e , a Prolog system that interfaces with various state-of-the-art Mathematical and Constraint Programming solvers. The ASP approach, instead, is developed in clingo. The three approaches are compared on several synthetic datasets that simulate the operative conditions of the DSS. • We propose a Decision Support System (DSS) for aiding the process of food recycling. • Three techniques are compared: Constraint Logic Programming, Binary Linear Programming and Answer Set Programming. • The method based on Binary Linear Programming scales better in this application. [ABSTRACT FROM AUTHOR]

The production rate of an ore crushing circuit depends on the amount of equipment in operation. If the amount of active equipment is less than the optimum level, the reduced ore flow paths restrict the production rate. However, if the amount of active equipment is greater than the optimum level, the excess circulating load ore and extra energy consumption reduce the circuit efficiency. In addition, the optimum amount of active equipment can change over time due to changes in the ore characteristics, such as hardness and particle size. In this paper, a decision support system is proposed for optimizing the amount of active equipment for maximum crushing production considering changes in the circuit feed rate. The proposed solution is based on a simheuristic approach in which a simulated plant model is used to evaluate the production rate. Real production scenarios at a Brazilian mining plant are used in computational experiments. The results show that the simheuristic solutions generate a higher production rate and result in less energy consumption. Production is increased by up to 9%, and energy consumption is reduced by up to 59%, demonstrating the efficacy of the proposal. • A decision support system for equipment operation in a crushing circuit is proposed. • The proposed approach is based on a simheuristic strategy in an industrial simulator. • The objective function aims to maximize the production of a crushing plant. • Industrial cases are used to validate the effectiveness of the decision system. • The results show a 9% increase in production and a 59% reduction in energy consumption. [ABSTRACT FROM AUTHOR]

Mining frequent subgraphs is an important issue in graph mining. It is defined as finding all subgraphs whose occurrences in the dataset are greater than or equal to a given frequency threshold. In recent applications, such as social networks, the underlying graphs are very large. Algorithms for mining frequent subgraphs from a single large graph have been developing rapidly lately. Among all such algorithms, GraMi is considered the state-of-the-art. However, GraMi still consumes a lot of time and memory in the mining of a large graph. In this paper, we propose two effective strategies to optimize the GraMi algorithm, which help to increase performance as well as reduce memory consumption during execution. Firstly, GraMi only lists all frequent subgraphs, without computing the support of each mined subgraph. This is disadvantageous in decision support systems, which require information about the support of all subgraphs. Therefore, we optimize GraMi to compute the support values during the mining process. Secondly, we apply the strategy of sorting all edges in graphs by their frequencies, which means that edges with low frequencies will be mined first, and vice versa. This sorting strategy can reduce the number of possibly infrequent subgraph candidates, especially on large subgraphs that are usually derived from those edges with high frequency. Thirdly, we apply a parallel processing technique, in which each frequent edge is executed simultaneously in a separate thread, and improve our parallel strategy by combination with the sorting strategy. Our experiments were performed on three real datasets and the results showed that the performance, as well as memory requirements, are better than those of the original GraMi algorithm [ABSTRACT FROM AUTHOR]

Tunnel maintenance requires complex decision making, which involves pathology diagnosis and risk assessment, to ensure full safety while optimising maintenance and repair costs. A Decision Support System (DSS) can play a key role in this process by supporting the decision makers in identifying pathologies based on disorders present in various tunnel portions and contextual factors affecting a tunnel. Another key aspect is to identify which spatial stretches within a tunnel contain pathologies of similar kinds within neighbouring tunnel segments. This paper presents PADTUN, a novel intelligent decision support system that assists with pathology diagnosis and assessment of tunnels with respect to their disorders and diagnosis influencing factors. It utilises semantic web technologies for knowledge capture, representation, and reasoning. The core of PADTUN is a family of ontologies which represent the main concepts and relations associated with pathology assessment, and capture the decision process concerning tunnel maintenance. Tunnel inspection data is linked to these ontologies to take advantage of inference capabilities offered by semantic technologies. In addition, an intelligent mechanism is presented which exploits abstraction and inference capabilities. Thus PADTUN provides the world's first semantically based intelligent DSS for tunnel maintenance. PADTUN was developed by an interdisciplinary team of tunnel experts and knowledge engineers in real-world settings offered by the NeTTUN EU Project. An evaluation of the PADTUN system is performed using real-world tunnel data and diagnosis tasks. We show how the use of semantic technologies allows addressing the complex issues of tunnel pathology inferencing, aiding in, and matching transportation experts' expectations of decision support. The methodology is applicable to any linear transport structures, offering intelligent ways to aid with complex decision processes related to diagnosis and maintenance. • A pioneering semantically based decision system for intelligent tunnel diagnosis. • Infrastructure maintenance is of high societal and economic significance. • First tunnel diagnosis ontology, applied and validated on real tunnel data. • Key result from an EU NetTUN multinational, interdisciplinary project. [ABSTRACT FROM AUTHOR]