Speech Emotion Recognition (SER) is an important part of speech-based Human-Computer Interface (HCI) applications. Previous SER methods rely on the extraction of features and training an appropriate classifier. However, most of those features can be affected by emotionally irrelevant factors such as gender, speaking styles and environment. Here, an SER method has been proposed based on a concat...

Methods based on the neural network techniques are among the most accurate in the secondary structure prediction of globular proteins. Here the same principles have been used for the tertiary structure prediction problem. The map of dihedral phi and psi angles is divided into 10 by 10 squares each spanning 36 by 36 degrees. By predicting the classification of each residue in the protein chain i...

Introduction: Evoked potentials arisen by stimulating the brain can be utilized as a communication tool  between humans and machines. Most brain-computer interface (BCI) systems use the P300 component,  which is an evoked potential. In this paper, we evaluate the use of the hidden Markov model (HMM) for  detection of P300.  Materials and Methods: The wavelet transforms, wavelet-enhanced indepen...

Changes in Neural Activity during Brain-Machine Interface Control: from Information Encoding and Connectivity to Local Field Potentials

Progress in decoding neural signals has enabled the development of interfaces that translate cortical brain activities into commands for operating robotic arms and other devices. The electrical stimulation of sensory areas provides a means to create artificial sensory information about the state of a device. Taken together, neural activity recording and microstimulation techniques allow us to e...

In this paper we present a system which enables easy and fast computation of Kohonen's selfor-ganizing map (SOM). It is a hardware supported system consisting of diierent parts. A neural coprocessor (COKOS) is connected to a personal computer (PC) by a special, asynchronous interface. The neural coprocessor works vector-component-parallel and processing-element-serial and speeds up the performa...

| The NeuDB'95 system is a novel approach to the physical and conceptual integration of neural networks into an object-oriented database systems. In the context of the database system neural networks are seen as basic objects and are administrated by the standardized SQL interface of the system. The network paradigm of a neural network object is deened by the type hierarchy of the general neura...

Artificial neural networks have been used to investigate their capabilities at estimating key parameters for the characterisation of flow processes, based on electrical capacitance-sensed tomographic (ECT) data. The estimations of the parameters are done directly, without recourse to tomographic images. The parameters of interest include component height and interface orientation of twocomponen...