International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems

Investment decision making is a complex process. Important decision concerns the (pre)selection of potential investment instruments to compose an investment portfolio. Conscientious selection involves the application of quantitative multi-criteria procedures. The typical element of uncertainty (i.e. unstable return or investor’s vague preferences about the criteria importance) must be considered. This combination of the typical characteristics of investment on the capital market can be addressed by means of fuzzy multi-attribute decision making methods. These methods effectively quantify the vague elements by using fuzzy numbers. However, the applicability of a relevant method sufficiently depends on the actual investment decision making problem. This article focuses on open unit trusts because this market is recently becoming more popular in the Czech Republic. Unfortunately, under all the practical and theoretical specifics of this type of investment, there is no known evaluation method that can satisfactorily solved this problem. Therefore, the main aim of this article is to propose a novel fuzzy multi-attribute decision making method that works for all investment conditions. Its algorithm is inspired by some principles of the outranking methods. The evaluation of open unit trusts offered by the Česká spořitelna, clearly demonstrates all of the benefits of the proposed concept compared to the existing methods.

The target-oriented multi-criteria decision making is investigated based on the ordered weighted averaging (OWA) operator. The criteria evaluations are measured by using the likelihood of satisfying the targets of criteria. To aggregate the target-oriented criteria evaluations, the target-oriented OWA operator is firstly introduced, in which the target-oriented criteria evaluations are reordered and then aggregated by using the weight vector associated with the position of criteria evaluations. Four types of targets about criteria evaluations and four types of attitudinal characters about criteria weight vector are introduced, based on which, models are given to identify the potential best alternative(s), and estimate the ranges of attitudinal characters about criteria weight vector for each potential best alternative. The proposed models can not only analyze the sensitivity of each potential best alternative, but also can explore the impact of targets about criteria evaluations and attitudinal characters about criteria weight vector on the decision results. Models are further established to find the best and worst ranking orders of each alternative based on targets about criteria evaluations, and give decision analysis by considering specific ranking orders of alternatives. The proposed method considers the targets about criteria evaluations and attitudinal character about criteria weight vector at the same time and can provide decision makers more choices. Several examples are given to illustrate the proposed methods.

Uncertain time series analysis is a method to predict future values based on imprecisely observed values. As a basic model of uncertain time series, an uncertain autoregressive model has been presented. However, the existing paper ignores the temporal dependence information embedded in time-series data. In dealing with this issue, this paper adds a least absolute shrinkage and selection operator penalty to the traditional uncertain autoregressive model and selects the optimum order of the model according to Akaike’s final prediction error criterion. Finally, two numerical examples are given to illustrate the effectiveness of the model and compare the results predicted by the uncertain autoregressive model with the principle of least squares.

There are two kinds of sequential rules. They are classical sequential rules and common sequential rules. The common sequential rules present the relationship between unordered itemsets in which all the items in the antecedent part have to appear before the ones in the consequent part. All existing algorithms for mining common sequential rules can not apply to quantitative sequence databases. Furthermore, the common sequential rules found so far did not yet reveal the time gap about the apperance of itemsets in its antecedent and consequent parts. The purpose of this article is to overcome the two disadvantages mentioned above. Specifically, the article proposes an algorithm called IFERMiner to discover common sequential rules in quantitative sequence databases, where the time gap about appearance of two attribute sets in its antecedent and consequent parts is taken account. This algorithm was developed from the ERMiner algorithm that is the most efficient algorithm to discover common sequential rules in transactional sequence databases now. The computational complexity of the IFERMiner algorithm is also shown in the article and it is polynomial. The FCSI rules found out by the IFERMiner algorithm are useful for marketing domain and market analysis.

Collaborative Filtering algorithms suffer from the so-called cold-start problem. In particular, when a user has rated few items, recommendations offered by these algorithms are not too accurate. Profile Expansion techniques have been described as a way to tackle this problem without bothering the user with additional information requests by increasing automatically the size of the user profile. Up to now, only collaborative approaches had been proposed for Profile Expansion. However, content-based techniques can also be used. We perform a manual analysis of a movie dataset to analyze how content features behave. According to this analysis, we propose a content-based approach, which is also combined with collaborative information. Concretely, we expose the advantages and disadvantages of the combination with a popularity feature. Moreover, a comparison to pure collaborative approaches is performed. Our approach is evaluated in a new system situation. That is, not only the active user has few ratings, but also most of the users. The results show that content-based information is useful for rating prediction. In addition, recommendations are less personalized as popularity feature acquires more relevance for item selection.

In this paper, we present a new model closer to the real-life — called the fuzzy exchange economy with a continuum of agents (FXE-CA) — that combines fuzzy consumption and fuzzy initial endowment with the agent’s fuzzy preference in the fuzzy consumption set. To characterize the fuzzy competitive allocations of the FXE-CA, we define the indifference fuzzy core of a FXE-CA as the set of all fuzzy allocations that cannot be dominated by any coalition of agents. We also propose the Mas-Colell indifference fuzzy bargaining set, in which no coalition has a justified objection at a fuzzy allocation against any other coalition. Finally, we verify that the indifference fuzzy core and the indifference fuzzy bargaining set of a FXE-CA coincide with the set of all fuzzy competitive allocations under some conditions, respectively. This indicates that the agents unanimously distribute the fuzzy competitive allocations of a FXE-CA.

The currently observed developments in Artificial Intelligence (AI) and its influence on different types of industries mean that human-robot cooperation is of special importance. Various types of robots have been applied to the so-called field of Edutainment, i.e., the field that combines education with entertainment. This paper introduces a novel fuzzy-based system for a human-robot cooperative Edutainment. This co-learning system includes a brain-computer interface (BCI) ontology model and a Fuzzy Markup Language (FML)-based Reinforcement Learning Agent (FRL-Agent). The proposed FRL-Agent is composed of (1) a human learning agent, (2) a robotic teaching agent, (3) a Bayesian estimation agent, (4) a robotic BCI agent, (5) a fuzzy machine learning agent, and (6) a fuzzy BCI ontology. In order to verify the effectiveness of the proposed system, the FRL-Agent is used as a robot teacher in a number of elementary schools, junior high schools, and at a university to allow robot teachers and students to learn together in the classroom. The participated students use handheld devices to indirectly or directly interact with the robot teachers to learn English. Additionally, a number of university students wear a commercial EEG device with eight electrode channels to learn English and listen to music. In the experiments, the robotic BCI agent analyzes the collected signals from the EEG device and transforms them into five physiological indices when the students are learning or listening. The Bayesian estimation agent and fuzzy machine learning agent optimize the parameters of the FRL agent and store them in the fuzzy BCI ontology. The experimental results show that the robot teachers motivate students to learn and stimulate their progress. The fuzzy machine learning agent is able to predict the five physiological indices based on the eight-channel EEG data and the trained model. In addition, we also train the model to predict the other students’ feelings based on the analyzed physiological indices and labeled feelings. The FRL agent is able to provide personalized learning content based on the developed human and robot cooperative edutainment approaches. To our knowledge, the FRL agent has not applied to the teaching fields such as elementary schools before and it opens up a promising new line of research in human and robot co-learning. In the future, we hope the FRL agent will solve such an existing problem in the classroom that the high-performing students feel the learning contents are too simple to motivate their learning or the low-performing students are unable to keep up with the learning progress to choose to give up learning.

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA…