A simple and general method is described that can combine diierent knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automatically trainable, acquiring information from both positive and negative examples. In experiments, the method was tested on a 1000-utterance sample of unseen ATIS data.

In the last years, the Authors have proposed the use of the Random-Fuzzy Variables (RFVs) to represent measurements results. An RFV is an extension of a fuzzy variable, which is the natural variable in the mathematical possibility theory (in the same way the random variable is the natural variable in the probability theory). The aim of this presentation is to show, through a remotely controlled...

SUMMARY One of the main parameter for urban heat island mapping is the land cover information. Satellite data were used to map the land cover over the study area, CyberJaya. Remotely sensed data were processed using pixel based and object based image processing techniques. Most traditional classification approaches are based exclusively on the digital number of the pixel itself. Thereby only th...

this paper consider the   general  forms of $(alpha,beta)$-fuzzyleft ideals (right ideals, bi-ideals, interior ideals) of an orderedsemigroup, where$alpha,betain{in_{gamma},q_{delta},in_{gamma}wedgeq_{delta}, in_{gamma}vee q_{delta}}$ and $alphaneqin_{gamma}wedge q_{delta}$. special attention is paid to$(in_{gamma},ivq)$-left ideals (right ideals, bi-ideals, interiorideals) and some related  pr...

We prove the basic fuzzy Korovkin theorem via a fuzzy Shisha– Mond inequality given here. This determines the degree of convergence with rates of a sequence of fuzzy positive linear operators to the fuzzy unit operator. The surprising fact is that only the real case Korovkin assumptions are enough for the validity of the fuzzy Korovkin theorem, along with a natural realization condition fulfill...

Optical Character Recognition software (OCR) are important tools for obtaining accessible texts. We propose the use of artificial neural networks (ANN) in order to develop pattern recognition algorithms capable of recognizing both normal texts and formulae. We present an original improvement of the backpropagation algorithm. Moreover, we describe a novel image segmentation algorithm that exploi...

It is well known that emotion recognition performance is not ideal. The work of this research is devoted to improving emotion recognition performance by employing a two-stage recognizer that combines and integrates gender recognizer and emotion recognizer into one system. Hidden Markov Models (HMMs) and Suprasegmental Hidden Markov Models (SPHMMs) have been used as classifiers in the two-stage ...

Takagi–Sugeno (TS) fuzzy systems have been employed as fuzzy controllers and fuzzy models in successfully solving difficult control and modeling problems in practice. Virtually all the TS fuzzy systems use linear rule consequent. At present, there exist no results (qualitative or quantitative) to answer the fundamentally important question that is especially critical to TS fuzzy systems as fuzz...