Search

Algeria is currently experiencing a real water shortage and leaks in the distribution networks, which affect the water supply. To reduce losses, the authorities have adopted a rehabilitation policy that requires resources that are not necessarily available. In this context, the aim of this study is to develop a decision support methodology for managers to enable them to plan urgent rehabilitation and to evaluate the benefits generated. The methodology consists of two phases: the diagnostic phase to identify a set of criteria, taking into account national specificities, and the planning phase, including the choice of Fuzzy-AHP for weighting and PROMETHEE II for ranking. An application is carried out on the Fouka network in Bejaia city (Algeria), consisting of 204 pipes. The application enabled the 204 pipes to be ranked in order of urgency and the benefits generated to be assessed in terms of environmental, economic, social, and technical parameters. The recovered water is significant in the first 60% of rehabilitated pipes. Investment costs are recovered within 3 years of the network being fully rehabilitated. The average reduction in network age is 5 years for every 10% of pipes rehabilitated. Complaints will be 0 after 70% of the pipes are rehabilitated. [ABSTRACT FROM AUTHOR]

Decision makers are commonly challenged with comparing, and ultimately ranking, elements with regards to the degree to which they satisfy multiple criteria and in terms of their own preferences. This calls for a new decision making framework, which we formally present here. Within such a framework, we present multi-criteria lex-cel : a new method for ranking single elements. Furthermore, we formally establish that our contributions generalise recent results in the social choice literature. We also illustrate our contributions through a case study that poses an ethical decision-making problem. [ABSTRACT FROM AUTHOR]

• Algorithmic trading using self-attention based recurrent reinforcement learning is developed. • Self-attention layer reallocates temporal weights in the sequence of temporal embedding. • Hybrid loss feature is incorporated to have predictive and reconstructive power. Algorithmic trading based on machine learning has the advantage of using intrinsic features and embedded causality in complex stock price time series. We propose a novel algorithmic trading model based on recurrent reinforcement learning, optimized for making consecutive trading signals. This paper elaborates on how temporal features from complex observation are optimally extracted to maximize the expected rewards of the reinforcement learning model. Our model incorporates the hybrid learning loss to allow sequences of hidden features for reinforcement learning to contain the original state's characteristics fully. The self-attention mechanism is also introduced to our model for learning the temporal importance of the hidden representation series, which helps the reinforcement learning model to be aware of temporal dependence for its decision-making. In this paper, we verify the effectiveness of proposed model using some major market indices and the representative stocks in each sector of S&P500. The augmented structure that we propose has a significant dominance on trading performance. Our proposed model, self-attention based deep direct recurrent reinforcement learning with hybrid loss (SA-DDR-HL), shows superior performance over well-known baseline benchmark models, including machine learning and time series models. [ABSTRACT FROM AUTHOR]

• Three-way decision and conformal prediction are two popular cautious ML methods. • We investigate the theoretical properties and relationships among these two methods. • The proposed theoretical constructions are shown to improve performance in benchmarks. • The utility of proposed cautious ML methods is shown through a medical case study. The aim of this article is to study the relationship between two popular Cautious Learning approaches, namely: Three-way decision (TWD) and conformal prediction (CP). Based on the novel proposal of a technique to transform three-way decision classifiers into conformal predictors, and vice versa, we provide conditions for the equivalence between TWD and CP. These theoretical results provide error-bound guarantees for TWD, together with a formal construction to define cost-sensitive cautious classifiers based on CP. The proposed techniques are then applied and evaluated on a collection of benchmark and real-world datasets. The results of the experiments show that the proposed techniques can be used to obtain cautious learning classifiers that are competitive with, and often out-perform, state-of-the-art approaches. Further, through a qualitative medical case study we discuss the usefulness of cautious learning in the development of robust Machine Learning. [ABSTRACT FROM AUTHOR]

With the development of the social economy, small and medium-sized enterprises (SMEs) play a vital role in promoting economic development. Multiple local governments in China are developing policy recommended platforms in order to help SMEs better understand the inclusive policy. However, these online platforms manually extract the key information from the inclusive policy texts, which takes a lot of time and causes low efficiency. The policy text is composed of some paragraphs and each paragraph corresponds to a topic. When we classify the paragraphs into different topics, there exists a decision risk of text misclassification. Therefore, we design two-stage based three-way enhanced technique to automatically classify these text paragraphs into the predefined categories. At the first stage, by using ensemble learning algorithms, we construct an ensemble convolution neural network (CNN) model in order to ensure the generalization ability and stability of text classification results. Meanwhile, we develop a new weight determination method to integrate the prediction results of all base classifiers according to the accuracy and classification confidence. With the help of three-way decisions (3WD), we assign the samples with poor resolution to the boundary area for secondary classification, which can reduce the decision risk. At the second stage, in order to classify the boundary region samples and improve the overall classification results, we further utilize traditional machine learning method as the secondary classifier. Finally, we develop some comparison experiments to verify our proposed method. The experimental results show that the two-stage three-way enhanced classification framework is valid and obtains a better performance. Our proposed method can effectively support the designment of policy recommended platforms and serve SMEs. [ABSTRACT FROM AUTHOR]

Uncertainty in model-based decision support is commonly addressed using mixed methods rather than a single method. Different mixes of methods result in different modelling and processes for robust decision support, and subsequently different decision outcomes. This article focuses on the notion of 'good' modelling practice and develops a reporting guideline to make the use of multiple methods in robust decision support transparent. The guideline raises awareness about the characteristics of methodological and mixing design choices made throughout the modelling process. While not intending to be universally applicable, the guideline represents a move towards the development of universal standards to promote the generalisability, reproducibility, and comparability of different practices of robust decision support and to improve the recognition of the values of specific robust decision support frameworks. The article demonstrates the process for the use of mixed methods in an illustrative case in asset life cycle planning. The case study explains choices made at each step of this mixing process and presents justifications for the choices made, using the suggested guideline. The illustrative case also demonstrates generated decision insights resulted from the choices made. • The use of multiple methods is popular in model-based decision support. • Modeller methodological and mixing design choices lead to different decision outcomes. • The clarification of choices supports a 'good' modelling practice in decision support. • We develop a guideline to clarify methodological and mixing design choices in robust decision support. [ABSTRACT FROM AUTHOR]

Fuzzy rule-based systems are widely applied for real-world decision support, such as policy formation, public health analysis, medical diagnosis, and risk assessment. However, they face significant challenges when the application problem at hand suffers from the "curse of dimensionality" or "sparse knowledge base". Combination of hierarchical fuzzy rule models and fuzzy rule interpolation offers a potentially efficient and effective approach to dealing with both of these issues simultaneously. In particular, backward fuzzy rule interpolation (B-FRI) facilitates approximate reasoning to be performed given a sparse rule base where rules do not fully cover all observations or the observations are not complete, missing antecedent values in certain available rules. This paper presents a hierarchical bidirectional fuzzy reasoning mechanism by integrating hierarchical rule structures and forward/backward rule interpolation. A computational method is proposed, building on the resulting hierarchical bidirectional fuzzy interpolation to maintain consistency in sparse fuzzy rule bases. The proposed techniques are utilised to address a range of decision support problems, successfully demonstrating their efficacy. [ABSTRACT FROM AUTHOR]

A series of three laboratory experiments were conducted to assess the influence of graphical and color-enhanced information presentation modes on decision quality, decision making time, use of information, and user perceptions. The experimental design allowed for the unconfounded study of line graphs and color using a variety of information presentation designs for the same decision making task. Based on the findings of these studies, propositions about the impact of graphics and color on individual decision makers are presented. The influence of presentation mode on human performance and the perceived value of information is related to how well it supports the solution approach to a particular task. The benefits of graphics are limited to reducing decision making time but only when the graphical report has been designed to directly assist in solving the task. Multicolor reports aid in decision making, but only in specific circumstances, that is, their benefits are not pervasive. It appears that color is more advantageous when associated with graphical reports, for certain decision maker types, during learning periods, and in time constrained environments. [ABSTRACT FROM AUTHOR]

Highlights • Drug candidates choice from a vendor database recast as portfolio selection problem. • Three alternative formulations are introduced and tested on three molecules datasets. • Expected return of molecule is related to its activity, price and potential gain. • Risk of not finding a drug is associated with diversity of the portfolio. • Exact and approximate methods for multiobjective portfolio optimization are evaluated. Graphical abstract Abstract In this work, a problem of selecting a subset of molecules, which are potential lead candidates for drug discovery, is considered. Such molecule subset selection problem is formulated as a portfolio optimization, well known and studied in financial management. The financial return, more precisely the return rate, is interpreted as return rate from a potential lead and calculated as a product of gain and probability of success (probability that a selected molecule becomes a lead), which is related to performance of the molecule, in particular, its (bio-)activity. The risk is associated with not finding active molecules and is related to the level of diversity of the molecules selected in portfolio. It is due to potential of some molecules to contribute to the diversity of the set of molecules selected in portfolio and hence decreasing risk of portfolio as a whole. Even though such molecules considered in isolation look inefficient, they are located in sparsely sampled regions of chemical space and are different from more promising molecules. One way of computing diversity of a set is associated with a covariance matrix, and here it is represented by the Solow-Polasky measure. Several formulations of molecule portfolio optimization are considered taking into account the limited budget provided for buying molecules and the fixed size of the portfolio. The proposed approach is tested in experimental settings for three molecules datasets using exact and/or evolutionary approaches. The results obtained for these datasets look promising and encouraging for application of the proposed portfolio-based approach for molecule subset selection in real settings. [ABSTRACT FROM AUTHOR]

Purpose Online product ratings play an important role in the decision-making process of consumers, which are not only sources of information used by consumers to understand the function and quality of a product or service but also sources of information used to find desirable products. The purpose of this paper is to develop a decision-based method for supporting the purchase decisions of consumers based on not only the online product ratings but also the actual product attributes.Design/methodology/approach First, two types of utility values are designed to measure the preference of the consumer based on either online ratings or actual product attributes. Then, the traditional TOPSIS method is adopted to achieve a comprehensive value by integrating the two types of utility values so that all of the alternative products can be ranked. Further, a product selection support system prototype is designed and developed to support the purchase decisions of consumers.Findings To help consumers select desirable products efficiently, it is necessary to develop a product selection method based on the online ratings of alternative products and consumer expectations.Practical implications The research shows that the proposed method can not only support consumers’ purchase decisions based on a large number of online product ratings but also help manufacturers to find out consumers’ demands or requirements on products so as to facilitate the design of new products or the improvement of products. On the basis of the proposed method, the developed system prototype is helpful for consumers to select desirable products.Originality/value To support the purchase decisions of consumers, a new decision-based method for selecting desirable online products is proposed. [ABSTRACT FROM AUTHOR]

The calculation of pullback by the analysis of strain on pipe shows that it involves many disciplines. It is hard to build a mechanical model that is very consistent with the actual working conditions and with the general applicability. After summarizing the calculation method of domestic and foreign authorities or national standards, the paper derives a set of its own formulas. Based on statistical data of actual projects, the paper develops a formula more suitable for ultra-long pullback by comparing the computing result with the actual measured drag force, that is for engineering design and site construction personnel reference. The calculated value of ultra-long pullback coincides well with the engineering value. Three components of pullback resistance, all occupy a high proportion in back-dragging load, and the contribution of the pullback load weights back Trawler changes dynamically. Thus proving that the method is a reasonable, simple, reliable and effective method to predict pipeline status, and makes a useful exploration for the research to improve the existing prediction models in the future. [ABSTRACT FROM AUTHOR]

This paper introduces a new probabilistic graphical model called gated Bayesian network (GBN). This model evolved from the need to represent processes that include several distinct phases. In essence, a GBN is a model that combines several Bayesian networks (BNs) in such a manner that they may be active or inactive during queries to the model. We use objects called gates to combine BNs, and to activate and deactivate them when predefined logical statements are satisfied. In this paper we also present an algorithm for semi-automatic learning of GBNs. We use the algorithm to learn GBNs that output buy and sell decisions for use in algorithmic trading systems. We show how the learnt GBNs can substantially lower risk towards invested capital, while they at the same time generate similar or better rewards, compared to the benchmark investment strategy buy-and-hold . We also explore some differences and similarities between GBNs and other related formalisms. [ABSTRACT FROM AUTHOR]

Ensuring reliable structural condition of sewers is an important criterion for sewer rehabilitation decisions. Deterioration models applied to sewer pipes support the rehabilitation planning by means of prioritising pipes according to their current and predicted structural status. There is a benefit in applying such models if sufficient inspection data for calibration, an appropriate deterioration model, and adequate covariates to explain the variability in the conditions are available. In this paper it is discussed up to what level the application of sewer deterioration models can be beneficial under limited data availability. The findings show that the indirect nature of the explanatory covariates which are commonly used in sewer deterioration models makes it difficult to harness any benefit from modelling sewer conditions at a network level, but that the deterioration model application still may be beneficial for prioritising inspection candidates. The prediction power of the current sewer deterioration models is limited by the adequacy of the explanatory variables available, and by the fact that different failure modes are mixed in the aggregated condition class, and not modelled explicitly. [ABSTRACT FROM AUTHOR]

New economic conditions have led to innovations in retail industries, such as more dynamic retail approaches based on flexible strategies. We propose and compare different approaches incorporating nonlinear methods for promotional decision-making using retail aggregated data registered at the point of the sale. Specifically, this paper describes a reliable quantification tool as an effective information system leveraged on recent and historical data that provides managers with an operative vision. Furthermore, a new set of indicators are proposed to evaluate the reliability and stability of the data model in the multidimensional feature space by using nonparametric resampling techniques. This allows the user to make a clearer comparison among linear, nonlinear, static, and dynamic data models, and to identify the uncertainty of different feature space regions, for example, corresponding to the most frequent deal features. This methodology allows retailers to use aggregated data in suitable conditions that will result in acceptable confidence intervals. To test the proposed methodology, we used a database containing the sales history of representative products registered by a Spanish retail chain. The results indicate that: (1) the deal effect curve analysis and the time series linear model do not provide enough expressive capacity, and (2) nonlinear promotional models more accurately follow the actual sales pattern obtained in response to the implemented sales promotions. The quarterly temporal analysis conducted enabled the authors to identify long-term changes in the dynamics of the model for several products, especially during the early stage of most recent economic crisis, consistent with the information provided by the reliability indices in terms of the feature space. We conclude that the proposed method provides a reliable operative tool for decision support, allowing retailers to alter their strategies to accommodate consumer behavior. [ABSTRACT FROM AUTHOR]

Abstract: This article describes the implementation of machine learning techniques that assist cycling experts in the crucial decision-making processes for athlete selection and strategic planning in the track cycling omnium. The omnium is a multi-event competition that was included in the Olympic Games for the first time in 2012. Presently, selectors and cycling coaches make decisions based on experience and opinion. They rarely have access to knowledge that helps predict athletic performances. The omnium presents a unique and complex decision-making challenge as it is not clear what type of athlete is best suited to the omnium (e.g., sprint or endurance specialist) and tactical decisions made by the coach and athlete during the event will have significant effects on the overall performance of the athlete. In the present work, a variety of machine learning techniques were used to analyze omnium competition data from the World Championships since 2007. The analysis indicates that sprint events have slightly more influence in determining the medalists, than endurance-based events. Using a probabilistic analysis, we created a model of performance prediction that provides an unprecedented level of supporting information that assists coaches with strategic and tactical decisions during the omnium. [Copyright &y& Elsevier]

This paper reviews recent developments in cost-benefit analysis for water policy researchers who wish to understand the applications of economic principles to inform emerging water policy debates. The cost-benefit framework can provide a comparison of total economic gains and losses resulting from a proposed water policy. Cost-benefit analysis can provide decision-makers with a comparison of the impacts of two or more water policy options using methods that are grounded in time-tested economic principles. Economic efficiency, measured as the difference between added benefits and added costs, can inform water managers and the public of the economic impacts of water programs to address peace, development, health, the environment, climate and poverty. Faced by limited resources, cost-benefit analysis can inform policy choices by summarizing trade offs involved in designing, applying, or reviewing a wide range of water programs. The data required to conduct a cost-benefit analysis are often poor but the steps needed to carry out that analysis require posing the right questions. [ABSTRACT FROM AUTHOR]

This paper presents a decision support methodology aimed at assisting Water Distribution System (WDS) operators in the timely location of pipe bursts. This will enable them to react more systematically and promptly. The information gathered from various data sources to help locate where a pipe burst might have occurred is frequently conflicting and imperfect. The methodology developed in this paper deals effectively with such information sources. The raw data collected in the field is first processed by means of several models, namely the pipe burst prediction model, the hydraulic model and the customer contacts model. The Dempster-Shafer Theory of Evidence is then used to combine the outputs of these models with the aim of increasing the certainty of determining the location of a pipe burst within a WDS. This new methodology has been applied to several semi-real case studies. The results obtained demonstrate that the method shows potential for locating the area of a pipe burst by capturing the varying credibility of the individual models based on their historical performance. [ABSTRACT FROM AUTHOR]

Greenhouses are used in many climates for season extension or year-round production and can be expensive to heat. Greenhouse users and growers are often tilted with management decisions that reply on an understanding of how temperature settings, heating systems, fuel types, and construction decisions influence overall heating costs. There are no easy-to-use programs to calculate heating costs associated with these factors over full cropping seasons. A computer program called Virtual Grower was created that helps calculate heating costs at many U.S. sites. The program uses a weather database of typical hourly temperature, light, and wind information of 230 sites from the National Renewable Energy Laboratory in the calculations. A user can define unique design characteristics such as building material and construction style. The user also defines the type of heating system and heating schedule, and then the program will predict beating costs based on typical weather at the selected location. Shorter-term predictions with weather forecasts of 2 days or less can be made with the software if there is an internet connection through integration with local weather forecasts. Virtual Grower can serve as a platform from which many other features can be added, such as plant growth and scheduling. Continued development will improve the software and allow users to perform baseline analysis of their heating costs, identify areas in their production to improve efficiency, and take some of the guesswork out of energy analysis in unique greenhouses. [ABSTRACT FROM AUTHOR]

Abstract: Clustering is a popular non-directed learning data mining technique for partitioning a dataset into a set of clusters (i.e. a segmentation). Although there are many clustering algorithms, none is superior on all datasets, and so it is never clear which algorithm and which parameter settings are the most appropriate for a given dataset. This suggests that an appropriate approach to clustering should involve the application of multiple clustering algorithms with different parameter settings and a non-taxing approach for comparing the various segmentations that would be generated by these algorithms. In this paper we are concerned with the situation where a domain expert has to evaluate several segmentations in order to determine the most appropriate segmentation (set of clusters) based on his/her specified objective(s). We illustrate how a data mining process model could be applied to address this problem. [Copyright &y& Elsevier]

This paper aims to present the information-based technologies used for water management in a test basin within the scope of the EU-sponsored SMART and OPTIMA projects. The study uses a dynamic simulation model with its associated databases and a water resources planning and optimization system, established through a web-based client-server implementation to support distributed use and easy access for multi-criteria optimization and decision support. The results clearly illustrate how a consistent and well-integrated set of advanced but practical Decision Support System (DSS) tools can be used for efficient "optimal" water management strategies and policies of use, designed for a participatory public decision-making process. [ABSTRACT FROM AUTHOR]

The paper applies the travel cost method (TCM) to estimate the value that rural households in the Steelpoort sub-basin of South Africa place on river and collective tap water. While the TCM calculations are based on the opportunity cost of the time household members spend on water collection, the resulting welfare values are close in magnitude to the estimates obtained using a contingent valuation method (CVM) on the same sample. The paper shows that in the absence of price data, the TCM provides satisfactory estimates of benefits where direct estimation of demand elasticity would otherwise be impossible. According to both methods, households consuming river water attribute higher value to the resource than collective tap users. The income elasticity of the trip generating function is much higher than that of the opportunity cost of time (price), implying that household's water use behaviour would be more responsive to factors affecting household income than to price incentives. Comparing the estimated values with actual operating and maintenance cost of water provision in the study area suggests that policies promoting cost-covering water tariffs have a potential to succeed. [ABSTRACT FROM AUTHOR]

Abstract: Bayesian inference provides a formal framework for assessing the odds of hypotheses in light of evidence. This makes Bayesian inference applicable to a wide range of diagnostic challenges in the field of chance discovery, including the problem of disputed authorship that arises in electronic commerce, counter-terrorism and other forensic applications. For example, when two documents are so similar that one is likely to be a hoax written from the other, the question is: Which document is most likely the source and which document is most likely the hoax? Here I review a Bayesian study of disputed authorship performed by a biblical scholar, and I show that the scholar makes critical errors with respect to several issues, namely: Causal Basis, Likelihood Judgment and Conditional Dependency. The scholar’s errors are important because they have a large effect on his conclusions and because similar errors often occur when people, both experts and novices, are faced with the challenges of Bayesian inference. As a practical solution, I introduce a graphical system designed to help prevent the observed errors. I discuss how this decision support system applies more generally to any problem of Bayesian inference, and how it differs from the graphical models of Bayesian Networks. [Copyright &y& Elsevier]

In the industrial environment a short down time of CNC machine-tools is increasingly important. One approach to counter the loss of production is to make the machines more reliable, thereby reducing their times of non-use. Another is to enable machine operators to solve the problem themselves, thereby avoiding the delay until maintenance staff is sent from different locations. Operators may be supported in the fault-finding process by a knowledge-based decision–support system. The questions are how to avoid the negative consequences of using such systems and how to even increase competence on the job is addressed by competence promoting multi-agent system for support (ComPASS), a system based on a multi-agent architecture, and an instrument to measure competence enhancement.A running, functioning prototype was developed and evaluated. Based on this experience the system is currently being extended and improved, first results of which are presented here. [Copyright &y& Elsevier]

To make decisions has long been considered an art more than a science. Today the area has been formalized under the name of praxeology and includes the use of computers as decision aids. In this paper some basic decision models are analysed together with some psychological phenomena often connected to them. Managerial problems and needs are examined and related to available computer decision support. The military command, control, communication, and intelligence structure is presented and compared to the corresponding civilian framework. The conclusion was that computer support in decision making now is firmly established among middle level decision makers. Top level managers, on the other hand, were found to derive no major benefit from such systems. Here good intuition, good guesses and a certain feeling for the task were the most important tools. [ABSTRACT FROM AUTHOR]

• In this study, skin tumor images were classified as benign and malignant. • The dataset has been rebuilt by the Autoencoder model. • In the study, the MobileNetV2 convolutional model was used for training. • The features extracted from the datasets by the MobileNetV2 model have been combined. • Spiking networks contributed to the MobileNetV2 model by training the feature set. Melanocytes are skin cells that give color to the skin and form melanin color pigments. The unbalanced division and proliferation of these cells result in skin cancer. The early diagnosis and proper treatment of skin cancer are so important. In this scope, a novel model that relies upon the autoencoder, spiking, and convolutional neural networks is proposed to ensure a useful decision support tool in this study. The experiments were carried out on an open-access dataset called the ISIC skin cancer consisting of 1800 being and 1497 malignant tumor images. In the proposed approach, the dataset is reconstructed using the autoencoder model. The original dataset and structured dataset were trained and classified by the MobileNetV2 model that consists of residual blocks, and the spiking networks. The classification success rate of the study was 95.27%. As a result, it was seen that the autoencoder model and spiking networks contributed to enhancing the performance of the MobileNetV2 model. Thanks to the proposed model, a novel fully automated decision support tool with high sensitivity was ensured for skin cancer detection. [Display omitted] [ABSTRACT FROM AUTHOR]

Decision Support spins off software company Databases are like children: They're great, especially when they're talking to each other. But there's trouble when the databases aren't compatible. It can cost [...]

Bayesian single sampling inspection plans involve minimizing expected total losses when the prior distribution of batch quality and the sampling distribution are specified. The choice of an optimal sampling plan is impacted by a decision maker's aversion to risk. Comparisons are then made with classical linear cost models. Differences are identified. An optimization algorithm is discussed. It develops an optimal sampling plan based on maximizing the expected utility. Tables of numerical results are available.