This paper investigates a relationship between the fuzziness of a classifier and the misclassification rate of the classifier on a group of samples. For a given trained classifier that outputs a membership vector, we demonstrate experimentally that samples with higher fuzziness outputted by the classifier mean a bigger risk of misclassification. We then propose a fuzziness category based divide-and-conquer strategy which separates the high-fuzziness samples from the low fuzziness samples. A particular technique is used to handle the high-fuzziness samples for promoting the classifier performance. The reasonability of the approach is theoretically explained and its effectiveness is experimentally demonstrated.
Countering cyber threats, especially attack detection, is a challenging area of research in the field of information assurance. Intruders use polymorphic mechanisms to masquerade the attack payload and evade the detection techniques. Many supervised and unsupervised learning approaches from the field of machine learning and pattern recognition have been used to increase the efficacy of intrusion detection systems (IDSs). Supervised learning approaches use only labeled samples to train a classifier, but obtaining sufficient labeled samples is cumbersome, and requires the efforts of domain experts. However, unlabeled samples can easily be obtained in many real world problems. Compared to supervised learning approaches, semi-supervised learning (SSL) addresses this issue by considering large amount of unlabeled samples together with the labeled samples to build a better classifier. This paper proposes a novel fuzziness based semi-supervised learning approach by utilizing unlabeled samples assisted with supervised learning algorithm to improve the classifier’s performance for the IDSs. A single hidden layer feed-forward neural network (SLFN) is trained to output a fuzzy membership vector, and the sample categorization (low, mid, and high fuzziness categories) on unlabeled samples is performed using the fuzzy quantity. The classifier is retrained after incorporating each category separately into the original training set. The experimental results using this technique of intrusion detection on the NSL-KDD dataset show that unlabeled samples belonging to low and high fuzziness groups make major contributions to improve the classifier’s performance compared to existing classifiers e.g., naive bayes, support vector machine, random forests, etc.
, , and have become ubiquitous in today's mass media and are universally known terms used in everyday speech. If we look behind these often misused buzzwords, we find at least one common element, namely data. Although we hardly use these terms in the “classic discipline” of mineral economics, we find various similarities. The case of phosphate data bears numerous challenges in multiple forms such as uncertainties, fuzziness, or misunderstandings. Often simulation models are used to support decision-making processes. For all these models, reliable and accurate sets of data are an essential premise. A significant number of data series relating to the phosphorus supply chain, including resource inventory or production, consumption, and trade data ranging from phosphate rock to intermediates like marketable concentrate to final phosphate fertilizers, is available. Data analysts and modelers must often choose from various sources, and they also depend on data access. Based on a transdisciplinary orientation, we aim to help colleagues in all fields by illustrating quantitative differences among the reported data, taking a somewhat engineering approach. We use common descriptive statistics to measure and causally explain discrepancies in global phosphate-rock production data issued by the US Geological Survey, the British Geological Survey, Austrian World Mining Data, the International Fertilizer Association, and CRU International over time, with a focus on the most recent years. Furthermore, we provide two snapshots of global-trade flows for phosphate-rock concentrate, in 2015 and 1985, and compare these to an approach using total-nutrient data. We find discrepancies of up to 30% in reported global production volume, whereby the major share could be assigned directly to China and Peru. Consequently, we call for a global, independent agency to collect and monitor phosphate data in order to reduce uncertainties or fuzziness and, thereby, ultimately support policy-making processes.
We investigate essential relationships between generalization capabilities and fuzziness of fuzzy classifiers (viz., the classifiers whose outputs are vectors of membership grades of a pattern to the individual classes). The study makes a claim and offers sound evidence behind the observation that higher fuzziness of a fuzzy classifier may imply better generalization aspects of the classifier, especially for classification data exhibiting complex boundaries. This observation is not intuitive with a commonly accepted position in "traditional" pattern recognition. The relationship that obeys the conditional maximum entropy principle is experimentally confirmed. Furthermore, the relationship can be explained by the fact that samples located close to classification boundaries are more difficult to be correctly classified than the samples positioned far from the boundaries. This relationship is expected to provide some guidelines as to the improvement of generalization aspects of fuzzy classifiers.
Giant planets are thought to have cores in their deep interiors, and the division into a heavy-element core and hydrogen-helium envelope is applied in both formation and structure models. We show that the primordial internal structure depends on the planetary growth rate, in particular, the ratio of heavy elements accretion to gas accretion. For a wide range of likely conditions, this ratio is in one-to-one correspondence with the resulting post-accretion profile of heavy elements within the planet. This flux ratio depends sensitively on the assumed solid-surface density in the surrounding nebula. We suggest that giant planets' cores might not be distinct from the envelope and includes some hydrogen and helium, and the deep interior can have a gradual heavy-element structure. Accordingly, Jupiter's core may not be well defined. Accurate measurements of Jupiter's gravitational field by Juno could put constraints on Jupiter's core mass. However, as we suggest here, the definition of Jupiter's core is complex, and the core's physical properties (mass, density) depend on the actual definition of the core and on the planet's growth history.
The astonishing propagation of microfinance institutions (MFIs) around the world has been followed by an indiscriminate proliferation of concepts for describing these organizations. These have in common the tendency to overlook the historical roots of microfinance, to disregard some types of MFIs, to impose arbitrarily discrete categories over a non-uniform field, and to neglect important constitutive attributes inherent to all MFIs. This conceptual fuzziness brings about several theoretical and practical obstacles. In this paper we address this issue by providing a two-dimensional framework built on the five constitutive attributes inherent to all MFIs to reduce microfinance conceptual blurriness. In doing so, we deliver a threefold contribution: 1) We address the call to reduce the conceptual fuzziness within the microfinance field by providing a tool for characterizing and distinguishing between the different MFIs based on their constitutive attributes across this industry. In addition, we advance the growing literature on microfinance that considers MFIs as hybrid organizations. 2) By exposing these five attributes, we dislocate the focus of policy makers from one idealistic (and limiting) best model of MFIs to account for a more diverse range of organizational configurations which provides the possibility of a better fit for their specific target public and context. 3) Finally we expose how the different types of microfinance can foster sustainable development.
We study the stability of the noncommutative Schwarzschild black hole interior by analysing the propagation of a massless scalar field between the two horizons. We show that the spacetime fuzziness triggered by the field higher momenta can cure the classical exponential blue-shift divergence, suppressing the emergence of infinite energy density in a region nearby the Cauchy horizon.
Rough set theory and fuzzy set theory are two useful mathematical tools for dealing with uncertainty and granularity in information systems. Motivated by the studies of roughness and fuzziness in algebraic systems and partially ordered sets such as semigroups, rings and lattices, in this paper we introduce first the notions of fuzzy (prime, semi-prime, primary) ideals of quantales and investigate their properties. Several characterizations of such ideals are presented. Then, we introduce the concepts of weak fuzzy prime ideals and strong fuzzy prime ideals of quantales, and establish relationships between these ideals and fuzzy prime ideals of quantales. By applying rough set theory to fuzzy ideals of quantales, we furthermore define rough fuzzy (prime, semi-prime, primary) ideals of quantales, generalizing Yang and Xu’s work on quantales to the fuzzy environment. Finally, relationships between the upper (resp. lower) rough fuzzy ideals of quantales and the upper (resp. lower) approximations of their homomorphic images are also discussed.