Progress in the field of Non-Intrusive Load Monitoring (NILM) has been attributed to the rise in the application of artificial intelligence. Nevertheless, the ability of energy disaggregation algorithms to disaggregate different appliance signatures from aggregated smart grid data poses some privacy issues. This paper introduces a new notion of disclosure risk termed energy disaggregation risk. The performance of Sequence-to-Sequence (Seq2Seq) NILM deep learning algorithm along with three activation extraction methods are studied using two publicly available datasets. To understand the extent of disclosure, we study three inference attacks on aggregated data. The results show that Variance Sensitive Thresholding (VST) event detection method outperformed the other two methods in revealing households' lifestyles based on the signature of the appliances. To reduce energy disaggregation risk, we investigate the performance of two privacy-preserving mechanisms based on microaggregation and Discrete Fourier Transform (DFT). Empirically, for the first scenario of inference attack on UK-DALE, VST produces disaggregation risks of 99%, 100%, 89% and 99% for fridge, dish washer, microwave, and kettle respectively. For washing machine, Activation Time Extraction (ATE) method produces a disaggregation risk of 87%. We obtain similar results for other inference attack scenarios and the risk reduces using the two privacy-protection mechanisms.

In the continuous case, analytical computations of the Choquet integral are limited, despite being commonly used in various applications. One can either use the definition, which is computationally demanding and impractical, or apply already existing formulas restricted only to monotone nonnegative functions on a real interval starting at zero. This article aims to present more convenient computational formulas for continuous functions without imposing restrictions on their monotonicity given any real interval. First, a more general approach to monotone functions is provided for both positive and negative functions. Then, reordering techniques are introduced to compute the Choquet integral of an arbitrary continuous function, and with these, a monotone equivalent to every function can be constructed. This equivalent function preserves the final Choquet integral value, implying that only formulas for monotone functions are required. In addition to general fuzzy measures, the article assumes particular cases of distorted Lebesgue measures and distorted probabilities as the most commonly used fuzzy measures.

Abstract Data-driven models strongly depend on data. Nevertheless, for research and academic purposes, public data sets are usually considered and analyzed. For example, most machine learning algorithms are applied and tested using the UCI Machine Learning repository. There is a current need for not i.i.d. data sets for distributed machine learning. Recall that i.i.d. random variables stand for independent and identically distributed (i.i.d.) random variables. An example of this need is federated learning. In federated learning, the typical scenario is to consider a set of agents each one with its own data set. Agents are typically heterogeneous and because of that, it is not appropriate to consider that the data of these agents follow the same distributions. In this paper we propose an approach to build non-identically distributed data sets from a single data set for machine learning classification, where we may suppose or not that all instances follow the same distribution. Each device will have only instances of a subset of the classes. The approach uses optimization to distribute the data set into a set of subsets, each one following a different distribution. Our goal is to define an approach for building subsets for training that is as systematic as the approaches used for cross-validation/k-fold validation.

Logic aggregators are all aggregators characterized by andness/orness. In this paper we present necessary properties of logic aggregators and use them to compare major implementations of andness-characterized aggregators: means, t-norms/conorms, ordered weighted average family, fuzzy integrals, and graded conjunction/disjunction. Our goal is to provide methodology for justifiable selection of the most suitable aggregator for various information fusion problems. When aggregating arguments from [0, 1], such arguments are regularly interpreted as degrees of truth or degrees of fuzzy membership. In such cases we deal with logic aggregators that must have appropriate logic properties. Our analysis identifies 10 necessary properties that are critical for decision support applications and must be satisfied by logic aggregators. Then, we evaluate and compare five families of logic aggregators that offer different levels of support to desired logic properties.

Graphs can be used to model many different types of interaction networks, for example, online social networks or animal transport networks. Several algorithms have thus been introduced to build graphs according to some predefined conditions. In this paper, we present an algorithm that generates spatial graphs with a given degree sequence. In spatial graphs, nodes are located in a space equiped with a metric. Our goal is to define a graph in such a way that the nodes and edges are positioned according to an underlying metric. More particularly, we have constructed a greedy algorithm that generates nodes proportional to an underlying probability distribution from the spatial structure, and then generates edges inversely proportional to the Euclidean distance between nodes. The algorithm first generates a graph that can be a multigraph, and then corrects multiedges. Our motivation is in data privacy for social networks, where a key problem is the ability to build synthetic graphs. These graphs need to satisfy a set of required properties (e.g., the degrees of the nodes) but also be realistic, and thus, nodes (individuals) should be located according to a spatial structure and connections should be added taking into account nearness.

The necessity of dealing with uncertainty in real world problems has been a long-term research challenge that has originated different methodologies and theories. Fuzzy sets along with their extensions, such as type-2 fuzzy sets, interval-valued fuzzy sets, and Atanassov's intuitionistic fuzzy sets, have provided a wide range of tools that are able to deal with uncertainty in different types of problems. Recently, a new extension of fuzzy sets so-called hesitant fuzzy sets has been introduced to deal with hesitant situations, which were not well managed by the previous tools. Hesitant fuzzy sets have attracted very quickly the attention of many researchers that have proposed diverse extensions, several types of operators to compute with such types of information, and eventually some applications have been developed. Because of such a growth, this paper presents an overview on hesitant fuzzy sets with the aim of providing a clear perspective on the different concepts, tools and trends related to this extension of fuzzy sets.

In this paper, we consider the problem of anonymization on large networks. There are some anonymization methods for networks, but most of them can not be applied on large networks because of their complexity. We present an algorithm for k-degree anonymity on large networks. Given a network G, we construct a k-degree anonymous network, G, by the minimum number of edge modifications. We devise a simple and efficient algorithm for solving this problem on large networks. Our algorithm uses univariate micro-aggregation to anonymize the degree sequence, and then it modifies the graph structure to meet the k-degree anonymous sequence. We apply our algorithm to a different large real datasets and demonstrate their efficiency and practical utility.

In this paper, we tackle the private information retrieval (PIR) problem associated with the use of Internet search engines. We address the desire for a user to retrieve information from the Web without the search provider learning about it. Traditional PIR protocols present two main shortcomings for their application: (i) They assume cooperation by the database, which is not affordable for a real-world search engine like Google and (ii) their computational complexity is linear in the size of the database, which is unfeasible in the case of the Web. More recent approaches relax PIR conditions to overcome these limitations and present some level of privacy. Mostly, they aim to distort server logs regardless of the loss of information that is involved. Server logs are used by search engines for profiling and, thereby, provide personalized results. This becomes a user's need given the growth of the Web and can also be used for targeted advertising. This study focuses on a noncooperative agent for private search that considers profiling as valuable data used for both sides of the search process. It is based on the assumption that the user's identity is formed by the union of various areas of interests or facets. Managing the HTTP connections properly, submitted queries are mapped to different server logs according to these facets. The rationale is that these logs cannot be used for tracing the user while they are still helpful for profiling. We present a personalized query classification approach based on the user's browsing history and to provide empirical results; we developed an attacking algorithm against the agent that shows that the disclosure risk is reduced.

Parameter selection is a well-known problem in the fuzzy clustering community. In this paper, we propose to tackle this problem using a computationally intensive approach. We apply this approach to a new method for clustering recently introduced in the literature. It is the fuzzy c-means with tolerance. This method permits data to include some error, and this is modeled by moving data in a particular direction within a particular range when clusters are defined. The proper application of this approach needs the correct definition of the parameter κ. A value that might be different for each record and corresponds to the maximum shift allowed to the data. In this paper, we review this method and we study the definition of this parameter κ when the same value of κ is used for all data elements. Our approach is based on the analysis of sets of data with increasing noise and an exhaustive analysis of the behavior of the algorithm with different values of κ. The analysis is motivated in privacy preserving data mining. The same approach can be used for parameter selection in other clustering algorithms. © 2010 Wiley Periodicals, Inc.

Several extensions and generalizations of fuzzy sets have been introduced in the literature, for example, Atanassov's intuitionistic fuzzy sets, type 2 fuzzy sets, and fuzzy multisets. In this paper, we propose hesitant fuzzy sets. Although from a formal point of view, they can be seen as fuzzy multisets, we will show that their interpretation differs from the two existing approaches for fuzzy multisets. Because of this, together with their definition, we also introduce some basic operations. In addition, we also study their relationship with intuitionistic fuzzy sets. We prove that the envelope of the hesitant fuzzy sets is an intuitionistic fuzzy set. We prove also that the operations we propose are consistent with the ones of intuitionistic fuzzy sets when applied to the envelope of the hesitant fuzzy sets. © 2010 Wiley Periodicals, Inc.

The weighted ordered weighted averaging (WOWA) operator is one of the existing aggregation methods that can be used to fuse numerical data. The application of this operator to a set of data requires an interpolation function. In this paper, we present a few results about the sensitivity of the operator according to the interpolation method used. © 2009 Wiley Periodicals, Inc.

This paper presents the so-called measures of simultaneous belongingness. These measures are used in clustering for establishing in which extent two objects belong to the same clusters. In the case of fuzzy clustering, the measure also takes into account fuzzy membership. In this paper, we establish a more general framework and, in particular, we introduce a definition that permits to compute this measure for sets of objects (instead of only to pairs of them). © 2008 Wiley Periodicals, Inc.

Given two-data databases, record linkage algorithms try to establish which records of these files contain information on the same individual. Standard record linkage algorithms assume that both files are described using the same attributes. In this article, we study the nonstandard case when the attributes are not the same. We apply aggregation operators for extracting relevant information for this purpose. We restrict to the case of numerical databases. © 2008 Wiley Periodicals, Inc.

Abstract In this article we present a system for the exploration of video sequences. The system, GAMBAL for the Exploration of Video Sequences (GAMBAL‐EVS), segments video sequences, extracting an image for each shot, and then clusters such images and presents them in a visualization system. The system allows the user to find similarities between images and to proceed through the video sequences to find the relevant ones.

Choquet integral and multistep Choquet integrals have been used in recent years as models for decision making and information aggregation. Such models can be used to fuse information when information sources are not independent. A basic property of such models is that their output is monotonically increasing with respect to inputs. In this article we study two alternative models built on the basis of such Choquet integrals. The motivation is, on the one hand, to study the modeling capabilities of such operators and, on the other, to build models that are capable of approximating any arbitrary functions (not only monotonic ones). In this article we describe and study two models that are universal approximators. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 1017–1036, 2005.

This article studies aggregation operators in ordinal scales for their application to clustering (more specifically, to microaggregation for statistical disclosure risk). In particular, we consider these operators in the process of prototype construction. This study analyzes main aggregation operators for ordinal scales [plurality rule, medians, Sugeno integrals (SI), and ordinal weighted means (OWM), among others] and shows the difficulties for their application in this particular setting. Then, we propose two approaches to solve the drawbacks and we study their properties. Special emphasis is given to the study of monotonicity because the operator is proven nonsatisfactory for this property. Exhaustive empirical work shows that in most practical situations, this cannot be considered a problem. © 2003 Wiley Periodicals, Inc.

In this paper we show how clustering can be used to aggregate different versions of the same data set in order to discover confidential information. Having these tools helps to not publish data that could be reidentified, which is known as Statistical Disclosure Control. In particular, the paper is focused on the case of dealing with categorical values. © 2003 Wiley Periodicals, Inc.

Statistical database protection is a part of information security which tries to prevent published statistical information (tables, individual records) from disclosing the contribution of specific respondents. This paper shows how to use information-theoretic concepts to measure disclosure risk for tabular data. The proposed disclosure risk measure is compatible with a broad class of disclosure protection methods and can be extended for computing disclosure risk for a set of linked tables.

Fuzzy rule-based systems are nowadays one of the most successful applications of fuzzy sets and fuzzy logic. Most applications use a flat set of fuzzy rules. However, in complex applications with a large set of variables, it is not appropriate to define the system with a flat set of rules because, among other problems, the number of rules increases exponentially with the number of variables. Hierarchical fuzzy systems are one of the alternatives presented in the literature to overcome this problem. In this article we review the latest results related with this type of fuzzy system. © 2002 Wiley Periodicals, Inc.

In this article we compare two contrasting methods, active set method (ASM) and genetic algorithms, for learning the weights in aggregation operators, such as weighted mean (WM), ordered weighted average (OWA), and weighted ordered weighted average (WOWA). We give the formal definitions for each of the aggregation operators, explain the two learning methods, give results of processing for each of the methods and operators with simple test datasets, and contrast the approaches and results. © 2001 John Wiley & Sons, Inc.

In this work, we introduce aggregation operators for linguistic labels (this is, ordinal scales) when different experts (or information sources) use different domains to express their knowledge. The aggregated value is computed (i) building first a unified framework, (ii) transforming all the initial values into this new framework, (iii) aggregating the transformed values, and (iv) finally applying a reversal transformation. Transformations and all the constructions are based on assuming an existing semantics for all the domains. In this work, we consider the semantics based on the existence of an antonym (or a set of them) for each element in the domain. This is equivalent to a semantics based on negation functions. © 2001 John Wiley & Sons, Inc.

In this work we introduce hierarchically decomposable fuzzy measures that allow the user to define measures more general than t-decomposable ones without having to deal with exponential complexity. ©1999 John Wiley & Sons, Inc.

In this work, we establish the relations between neural networks and hierarchies of quasiarithmetic means. We show that a neural network with the same activation function in all the neurons gives an output that is isomorphic to the result that can be obtained with a hierarchy of quasiarithmetic means. From this result, we show that hierarchies of quasiarithmetic means are universal approximations. ©1999 John Wiley & Sons, Inc.

In this work we propose a new discretization method for quantitative domains. We give an overview of the methods in the literature and we introduce a new one that returns better results. As the need for a discretization method appeared in the definition of a procedure for evaluating the semantics of linguistic labels defined in a previous paper, we also give in this paper an overview of this semantics and of its analysis. ©1999 John Wiley & Sons, Inc.

One of the properties that the OWA operator satisfies is commutativity. This condition, that is not satisfied by the weighted mean, stands for equal reliability of all the information sources that supply the data. In this article we define a new combination function, the WOWA (Weighted OWA), that combines the advantages of the OWA operator and the ones of the weighted mean. We study some of its properties and show how it can be extended to deal with linguistic labels. © 1997 John Wiley & Sons, Inc.

After arguing that in the knowledge acquisition framework experts cannot always supply a precise semantics for the linguistic labels they use, we show that negation functions over an ordered set of linguistics labels induce a semantics. We study the semantics induced by classical negation, functions from L to L, and also the one induced by negation functions from L to parts of L. © 1996 John Wiley & Sons, Inc.

This article studies the combination of basic probability assignment (bpa) in evidence theory. After introducing an interpretation of the mass function we show that given two bpa Dempster's rule of combination does not build a coherent bpa with respect to the interpretation. Next we give a new combination function that overcomes this problem and study some of its properties. © 1995 John Wiley & Sons, Inc.