An MLP-based model for identifying qEEG in depression

Manual differentiation of electroencephalography (EEG) paper recordings in cases of depression is not very helpful. So, a Multilayer Perceptron (MLP) has been used to differentiate the EEG power density spectra (qEEG) in the wakeful state from animals (control, exercised and depressed). The qEEG ranging from 1 to 30 Hz, at 1 Hz increments (30 input features) and also a slow, medium and fast activity (represented by three ranges of frequencies at the input) were used. After training with depressed and control qEEG only, the MLP has been found to distinguish successfully between the normal and the depressed rats in more than 80% of the cases, identifying, in the process, most of the exercised groups' EEG as normal. The reduction in the dimension of input features from 30 individual frequencies to 3 frequency bands has produced similar results. The rules generated for making such distinctions have been found to be similar to the clinical views.     

Electric conduction in float-zone silicon after prolonged gamma irradiation

The electric conductivities of float-zone silicon doped with arsenic for ntype and with boron for ptype have been measured before and after gamma irradiation using a four-point probe. Some new phenomena after prolonged irradiation are reported, and a brief discussion is given.     

On probability distributions of contact force magnitudes in loaded dense granular media

This paper discusses possible models for probability distributions of contact force magnitudes in loaded granular media. Many authors have studied such distributions, based on experiments with real particles as well as simulations in 2D and 3D. This has led to various and partly contradicting suggestions for the form of those distributions, which are described in the present paper. Its new theoretical investigations start from the empirically justified assumption that the components of contact forces follow exponential distributions with a certain dependence structure. This leads to distributions of force magnitudes similar to Gamma distributions with shape parameters depending on space dimension, which is in good agreement to results from experiments and numerical simulations. Also the analytical and statistical difficulties of the problem of determination of distributions of force magnitudes are discussed.In a discussion of Stefan Luding and D.S. the idea arose to consider dependent force components. Niels Kruyt supported our work by sending his papers and by patient discussions via e-mail and a careful reading of an earlier version of this paper.We had a very useful discussion with Farhang Radjai about the problem P(0)=0 and experiments with real disks. Finally, we are grateful to Tomaso Aste for leading our attention to infinitely divisible distributions.     

Hierarchical learning architecture with automatic feature selection for multiclass protein fold classification

The structure classification of proteins plays a very important role in bioinformatics, since the relationships and characteristics among those known proteins can be exploited to predict the structure of new proteins. The success of a classification system depends heavily on two things: the tools being used and the features considered. For the bioinformatics applications, the role of appropriate features has not been paid adequate importance. In this investigation we use three novel ideas for multiclass protein fold classification. First, we use the gating neural network, where each input node is associated with a gate. This network can select important features in an online manner when the learning goes on. At the beginning of the training, all gates are almost closed, i.e., no feature is allowed to enter the network. Through the training, gates corresponding to good features are completely opened while gates corresponding to bad features are closed more tightly, and some gates may be partially open. The second novel idea is to use a hierarchical learning architecture (HLA). The classifier in the first level of HLA classifies the protein features into four major classes: all alpha, all beta, alpha + beta, and alpha/beta. And in the next level we have another set of classifiers, which further classifies the protein features into 27 folds. The third novel idea is to induce the indirect coding features from the amino-acid composition sequence of proteins based on the N-gram concept. This provides us with more representative and discriminative new local features of protein sequences for multiclass protein fold classification. The proposed HLA with new indirect coding features increases the protein fold classification accuracy by about 12%. Moreover, the gating neural network is found to reduce the number of features drastically. Using only half of the original features selected by the gating neural network can reach comparable test accuracy as that using all the original features. The gating mechanism also helps us to get a better insight into the folding process of proteins. For example, tracking the evolution of different gates we can find which characteristics (features) of the data are more important for the folding process. And, of course, it also reduces the computation time.     

Modeling and computer simulation of ultrasonic/sonic driller/corer (USDC)

Simulation and analytical models for the ultrasonic/sonic drill/corer (USDC) are described in this paper. The USDC was developed as a tool for in-situ rock sampling and analysis in support of the NASA planetary exploration program. The USDC uses a novel drive mechanism, which transfers ultrasonic vibrations of a piezoelectric actuator into larger oscillations of a free-flying mass (free-mass). The free-mass impact on the drill bit creates a stress pulse at the drill tip/rock interface causing fracture in the rock. The main parts of the device (transducer, free-mass, bit, and rock) and the interactions between them were analyzed and numerically modeled to explore the drive mechanism. Each of these interactions is normally described by a time-dependent 2- or 3-D model involving slowly converging solutions, which makes the conventional approach unsuitable for USDC optimization studies. A simplified integrated model using tabulated data was developed to simulate the operation of the USDC on desktop PC and successfully predicted the characteristics of the device under a variety of conditions. The simulated results of the model and the experimental data used to verify the model are presented.     

Experimental set-up for measuring diffusive and advective transport of radon through building materials

This study describes an approach for measuring and modelling diffusive and advective transport of radon through building materials. The goal of these measurements and model calculations is to improve our understanding concerning the factors influencing the transport of radon through building materials. To reach this goal, a number of experiments have to be conducted. These experiments, including measurements in a large cylinder for creating diffusive and advective transport of radon under controlled, 'dwelling-like' conditions, are described here and the initial results are presented. A better understanding about the transport of radon through building materials will lead to more effective ways to decrease or to prevent the entrance of radon into dwellings.     

Stemming via Distribution-Based Word Segregation for Classification and Retrieval

A novel corpus-based method for stemmer refinement, which can provide improvement in both classification and retrieval, is described. The method models the given words as generated from a multinomial distribution over the topics available in the corpus and includes a procedurelike sequential hypothesis testing that enables grouping together distributionally similar words. The system can refine any stemmer, and its strength can be controlled with parameters that reflect the amount of tolerance to be allowed in computing the similarity between the distributions of two words. Although obtaining the morphological roots of the given words is not the primary objective, the algorithm automatically does that to some extent. Despite a huge reduction in dictionary size, classification accuracies are seen to improve significantly when the proposed system is applied on some existing stemmers for classifying 20 Newsgroups and WebKB data. The refinements obtained are also suitable for cross-corpus stemming. Regarding retrieval, its superiority is extensively demonstrated with respect to four existing methods