Session Program

Abstract - This article describes the implementation of the fuzzy deductive database system FuzzyDES, where concepts underlying the fuzzy logic programming system Bousi-Prolog are adapted and improved to be transferred to the DES deductive database system. We take advantage of the DES tabled-based implementation to propose new methods for rule compiling and t-closure computing, developing a terminating query answering system with graded rules. A description of the system, an example, and a link to a publicly-available, comprehensive system are provided.

Abstract - In this paper, we present a study on the use of fuzzy neural networks and their application to the prediction of times series generated by complex processes of the real-world. The new learning strategy is suited to any fuzzy inference model, especially in the case of higher-order Sugeno-type fuzzy rules. The data considered herein are real-world cases concerning chaotic benchmarks as well as environmental time series. The comparison with respect to well-known neural and fuzzy neural models will prove that our approach is able to follow the behavior of the underlying, unknown process with a good prediction of the observed time series.

Abstract - Cloud Computing (CC) service providers are becoming more popular as the demand for outsourcing information and communication technology (ICT) section of enterprises has increased. Selecting the most appropriate service provider for an enterprise depends on many criteria that are based on the strategies, requirements, and resources of the enterprise. Since this decision problem is dependent on various conflicting criteria and a decision-maker has to choose the best alternative while satisfying these criteria; therefore, it can be modeled as a Multi-criteria Decision Making (MCDM) problem. In this research, a pilot case study is conducted in which the CC service provider selection problem is modeled as a MCDM problem and Fuzzy Analytical Hierarchical Process (FAHP) which is the most widely used methodology in the domain of MCDM, is implemented to select the most appropriate service provider.

Abstract - In this paper, ad hoc and system identification methods are used to generate fuzzy If-Then rules for a zero-order Takagi-Sugeno-Kang (TSK) Fuzzy Inference System (FIS) using a set of multi-attribute monotone data. Convex and normal trapezoidal fuzzy sets, with a strong fuzzy partition strategy, is employed. Our analysis shows that even with multi-attribute monotone data, non-monotone fuzzy If-Then rules can be produced using an ad hoc method. The same observation can be made, empirically, using a system identification method, e.g., a derivative-based optimization method and the genetic algorithm. This finding is important for modeling a monotone FIS model, as the result shows that even with a "clean" data set pertaining to a monotone system, the generated fuzzy If-Then rules may need to be pre-processed, before being used for FIS modeling. As such, monotone fuzzy rule relabeling is useful. Besides that, a constrained non-linear programming method for FIS modelling is suggested, as a variant of the system identification method.

Abstract - This paper concerns the application of fuzzy clustering methods in the evaluation of compost bedded pack (CBP) barns. Fuzzy classifiers are developed to assist decision making regarding the control of associated variables such as bed moisture, temperature and aeration. The idea is to promote dairy cattle welfare and therefore improve productivity indices. The data was obtained from CBP barns in the state of Kentucky, US. Details about the data acquisition methodology are given. Well-known clustering methods, namely K-Means (KM), Fuzzy C-Means (FCM), Gustafson-Kessel (GK), and Gath- Geva (GG), are considered for data analysis. The efficiency of the methods is determined by validation indices such as the Xie-Beni criterion, Partition Coefficient, and Partition and Dunn indices. Six classes were identified in the data; they are related to the degree of efficiency of the composting process, where efficiency means stability, maturity and activeness of the compost, and ideal bacterial concentration in the bed. The GG method showed to be the most accurate method according to the majority of the validation indices, followed by the GK method. The main reason for the best results is the use of maximum-likelihood-based and Mahalanobis distance measures instead of Euclidean measure. Fuzzy modeling results and linguistic information have shown to be useful to help decision making in farms that adopt CBP barns as containment systems for dairy cattle.

Abstract - Plagiarism, i.e., copying the work of others and trying to pass it off as one own, is a debated topic in different fields. In particular, in music field, the plagiarism is a controversial and debated phenomenon that has to do with the huge amount of money that music is able to generate. However, the existing mechanisms for plagiarism detection mainly apply superficial and brute-force string matching techniques. Such well-known metrics, widely used to discover similarities in text documents, cannot work well in discovering similarities in music compositions. Despite the wide-spread belief that few notes in common between two songs is enough to decide whether a plagiarism exists, the analysis of similarities is a very complex process. In this work, we provide novel perspectives in the field of automatic music plagiarism detection, and specifically, we propose an approach based on a fuzzy vectorial-based similarity. Given a suspicious melody, our approach envisions three steps: (1) its transformation in a vectorial representation, (2) retrieving of a list of similar melodies, (3) analysis and comparison with this subset of associated similar scores by using a fuzzy degree of similarity, that varies in a range between 0 for melodies that are fully musically different, and 1 for identical melodies. To assess the effectiveness of our system we performed tests on a large dataset of ascertained plagiarisms. Results show that it is able to reach an accuracy of 93\%.