Search

Abstract This study focuses on consensus-reaching in social network group decision-making. Using Archimedean t- norms and t- conorms as the basis, this study introduces a family of interval-valued dual trust propagation (IVDTP) operators. A perfect knowledge degree-induced ordered weighted averaging (PKD-IOWA) aggregation operator is also put forward for obtaining the overall trust and distrust values. The proposed PKD-IOWA aggregation operator makes full use of the knowledge in each trust path, which can effectively overcome the limitations of existing trust aggregation operators. The weights of the experts can then be derived by combining the IVDTP operators and the PKD-IOWA aggregation operator. Three levels of consensus indices are defined to identify the incompatible experts in a group. A two-fold feedback mechanism comprising a judgment feedback mechanism (JFM) and a weight feedback mechanism (WFM), is designed to reach consensus. In each round of this interaction model, the most incompatible expert is advised to modify his/her judgments on the basis of the JFM. If the expert rejects the suggestion, then his/her weight will be reduced according to the WFM, which can act as an incentive or penalty to force him/her to accept the judgment feedback suggestion. Two illustrative examples are used to validate the feasibility and effectiveness of the proposed approach, followed by comparative analysis and discussion. [ABSTRACT FROM AUTHOR]

Abstract The sustainability challenge is increasingly driving the adoption of supercritical water gasification (SCWG) technology to ensure the elimination and recovery of pollution produced by sewage sludge treatment (SST). Risk evaluation by failure mode and effects analysis (FMEA) plays a crucial role in guaranteeing the reliability and safety of SCWG systems. However, some limitations in existing FMEA methods need to be ameliorated. Multiple risk factors are involved in prioritizing risk levels for failure modes in SCWG systems, it is essential a multiple criteria decision making (MCDM) process, in which overall assessments of failure modes should be provided according to their performances from several points during a system operation period. Due to differences in knowledge backgrounds and experiences, FMEA team members prefer to utilize multi-granular linguistic term sets to express their assessments of system risk. A hybrid risk evaluation model by FMEA is exploited with multi-granular linguistic distribution assessments to suit practical case. Best-worst and maximizing derivation methods are adopted to determine subjective and objective combined weights for distinguishing the importance of risk factors. Complex proportional assessment method is used to prioritize failure modes for explicitly and effectively reflecting the risk level of each failure mode. The proposed model is applied in a practical case of an SCWG system used in SST. Results derived from comparative and sensitivity analyses fully demonstrate the reliability and validity of the model. [ABSTRACT FROM AUTHOR]

Faced with risks aroused by the ever-increasing expansion of industrialization and urbanization, water security sustainability takes more and more effect on balancing regional sustainability and development, especially for industrial regions. Introducing sustainability into the indicator framework of water security is an indispensable issue should be addressed. The indicators of water security sustainability in practice are measured by observation data obtained from a monitoring period. These data are commonly expressed in various forms, such as ratio and qualitative linguistic, which makes them hard to be quantified and evaluated. As multiply influential criteria are involved the water security sustainability evaluation process, it can be treated as a multi-criteria decision making problem. An appropriate evaluation framework with scientific and strategic multi-criteria decision making techniques is supposed to be constructed. This paper incorporates the dimensions related to sustainability into the indicator framework of water security sustainability. Another contribution of this paper is that it establishes an observation data conversion standard and adopts linguistic distribution assessments as information representation. Linguistic distribution assessments can capture the natural characteristics of the observation data of water security sustainability indicators. More importantly, a multistage decision support framework integrated with multi-criteria decision making techniques, such as best-worst method (BWM), decision making trial and evaluation laboratory (DEMATEL) and technique for order performance by similarity to ideal solution (TOPSIS), is constructed for water security sustainability evaluation. Then, deep analyzes about the evaluation results and influential factors are provided, thereby certifying the reliability of evaluation results and facilitating the enhancement of water security sustainability. [ABSTRACT FROM AUTHOR]

The smart bike-sharing program (BSP), which is a novel bike-sharing mode of traditional BSP, has become popular in many cities in China. However, most BSP studies focus only on the socio-economic characteristics of the users, bike-sharing patterns, and impacts that influence bike-sharing demand. This study increases the knowledge on BSPs by presenting a hybrid fuzzy multi-criteria decision-making approach that is based on multi-phase quality function deployment. This approach covers the performance evaluation of smart BSPs allowing for customer voices under uncertain conditions. This method combines the fuzzy best-worst method (BWM), fuzzy maximizing deviation method (MDM), and fuzzy multi-objective optimization by ratio analysis plus the full multiplicative form (MULTIMOORA). It uses fuzzy BWM to determine priorities of customer requirements and company strategies and to obtain subjective importance coefficients of criteria. Fuzzy MDM is used to derive objective importance coefficients of criteria and fuzzy MULTIMOORA is used to rank alternatives in terms of each criterion. An empirical case in Changsha, which is one of the pilot areas for comprehensively supporting the reform for an environment-friendly and resource-conserving society ("two-oriented society") in China, is provided to illustrate the application of the proposed framework. Results can help enterprises and organizations improve their performance and provide high-quality products and services for customers. [ABSTRACT FROM AUTHOR]

• Forecast electricity demand considering residents' psychological preferences. • Stationarity time series are established to avoid the impact of irregular factors. • Personalizes exogenous variables, combines correlations and importance. • A hybrid machine learning based model is built to improve forecasting performance. • Multiple implications are provided for the government and institutions. Faced with the explosive growth of population and rapid development of industrialization, household electricity demand (HED) has recently become an essential sector of energy demand. Very-short-term forecasting of HED is closely related to monitoring insecurity, detecting emergency and potential crisis. Consider challenges triggered by the characteristics of time series, firstly, a phase of data pre-processing with stationarity of time series is constructed to manage irregular trend factors. Subsequently, in the feature selection phase, a two-layer feature selection method is proposed with the combination of random forest and autocorrelation analysis to select the most relevant features, which simultaneously considers correlations and importance of input lagged variables as well as exogenous variables. After that, hybrid HED forecasting methods are constructed with incorporating multiple machine learning techniques in the forecasting phase, namely k-nearest neighbor, support vector regression , random forest and multilayer perceptron, using their respective advantages of managing different situations. As residents' psychological preferences and calendar variables highly affect future HED, this paper intends to add and test their effects on HED. Finally, the proposed methods are examined on a 10-min-ahead horizon application, whose forecasting results, comparison analyses and an extended experiment are given to illustrate their effectiveness, after which some implications are provided to show the insights gained from the results. [ABSTRACT FROM AUTHOR]

• A hotel selection model driven by online textual reviews is explored to assist tourists selecting hotels. • To express tourists' feelings and differentiate sentiment words' degree, an improved sentiment dictionary is explored. • Linguistic distribution assessments are used to denote semantic and multi-angle information. • To address conflicting evidence and ensure rational results, an evidence theory-based fusion method is proposed. • Promotion strategies of different hotels are formulated through experiments. Browsing online reviews before selecting a satisfactory hotel has become a trend. Multiple criteria decision making models are powerful tools to provide competitive guidance. The first research gap motivating this study is that online textual reviews perform well in describing abundant perceptions and sentiments hidden in texts, while customer ratings used in existing models ignore them. Moreover, the existing sentiment analysis and hotel selection approaches have limited capacity in differentiating sentiment degrees, expressing natural languages, conveying comprehensive hotel descriptions and managing conflicting attitudes of different tourists. To narrow these gaps, a novel hotel selection model driven by online textual reviews on TripAdvisor.com is constructed. A semantic mapping function and the method of building this dictionary are proposed. Moreover, an evidence theory-based fusion method is proposed, which can guarantee the reliability of the results. Finally, the proposed model is tested in a case study and in robustness and comparative analyses. [ABSTRACT FROM AUTHOR]

• An anomaly detection method is developed for the records of UEBMI. • A combination method is utilized to preprocess the experimental data. • A feature selection method involves two aspects, variance and similarity. • An extended OCSVM model is established to improve the model performance. • Interesting findings provide some guideline for the future research and practical issues. Detecting and preventing unusual claims behavior in medical insurance can reduce the drawdown of a group medical insurance pool. Taking the case of the urban employee basic medical insurance (UEBMI) in China, this paper develops a method to detect unusual medical claim patterns in the UEBMI. We collect public domain records involving gastric malignancy as the experimental sample. A method to preprocess the experimental sample for data learning is provided. We present a feature selection method, involving variance analysis and similarity analysis, to determine the core features. Next, we establish an extended one-class support vector machine (OCSVM) model, the kernel density estimation (KDE)-OCSVM, which exploits the Kullback-Leibler divergence and the KDE method to estimate the parameter v of the OCSVM model, to improve model performance. An experiment and two analyses are performed to validate the proposed method. [ABSTRACT FROM AUTHOR]