Neural network models for group behavior prediction: a case of soccer match attendance

Soccer match attendance is an example of group behavior with noisy context that can only be approximated by a limited set of quantifiable factors. However, match attendance is representative of a wider spectrum of context-based behaviors for which only the aggregate effect of otherwise individual decisions is observable. Modeling of such behaviors is desirable from the perspective of economics, psychology, and other social studies with prospective use in simulators, games, product planning, and advertising. In this paper, we evaluate the efficiency of different neural network architectures as models of context in attendance behavior by comparing the achieved prediction accuracy of a multilayer perceptron (MLP), an Elman recurrent neural network (RNN), a time-lagged feedforward neural network (TLFN), and a radial basis function network (RBFN) against a multiple linear regression model, an autoregressive moving average model with exogenous inputs, and a naive cumulative mean model. We show that the MLP, TLFN, and RNN are superior to the RBFN and achieve comparable prediction accuracy on datasets of three teams from the English Football League Championship, which indicates weak importance of context transition modeled by the TLFN and the RNN. The experiments demonstrate that all neural network models outperform linear predictors by a significant margin. We show that neural models built on individual datasets achieve better performance than a generalized neural model constructed from pooled data. We analyze the input parameter influences extracted from trained networks and show that there is an agreement between nonlinear and linear measures about the most significant attributes.

     

Future trends of bioethanol co-production in Serbian sugar plants

Due to the reduction of the economic support for refined sugar efforts have been made to find new ways of using sugar beet outside food industry. This paper investigates the possibilities of introducing bioethanol co-production in Serbian sugar plants. Research shows current state of Serbian sugar industry and technical aspects of bioethanol co-production in sugar plants. These results represent important step toward mass production of bioethanol in Serbian factories. The main goals of introducing the concept of sugar and bioethanol coproduction would be efficient use of available resources for the production of energy, reduction of greenhouse gases emission, decreased dependence on import and creation of new jobs. Besides that, it would provide flexibility in terms of variation of produced quantities of sugar and ethanol, depending on the conditions prevailing on the market.     

Distributed Jacobi Joint Diagonalization on Clusters of Personal Computers

A new algorithm is described for distributed joint diagonalization of real symmetric or complex Hermitian matrices. The approach, which is based on the Jacobi diagonalization, utilizes distribution of the computational power and memory space, minimizes the communication costs, and runs on clusters of personal computers. It further combines two-step load balancing algorithm with a standard Kalman filter to enable quick but low-cost adaptation to resource varying conditions. Theoretical analysis of its performance shows that the communication costs (when normalized by computational costs) decline linearly with the number and size of the diagonalized matrices. This is also confirmed by experimental results: the measured speedup ratio yields 42.2 when jointly diagonalizing 800 matrices of size 400 × 400 on a cluster of 50 personal computers.     

An approach to surface EMG decomposition based on higher-order cumulants

We are addressing a possible approach to the decomposition of surface electromyograms (SEMGs). It is based on higher-order cumulants implemented in a two-step procedure. Firstly, a multivariate version of the w-slice method is applied in order to extract coarse approximations of motor-unit action potentials (MUAPs) out of the measured SEMGs. Secondly, these coarse estimates are refined by modified Newton-Gauss iteration to achieve an optimum fit of the model-based and the observation-based cumulant estimates. All the necessary conditions are derived theoretically and, afterwards, implemented in simulation runs in order to prove the decomposition power of the proposed approach on synthetic SEMGs. The first-norm difference between the original and the decomposed MUAPs, obtained at the signal length of 102400 samples and expressed in percentage of the MUAP amplitude span, yields 5.4% in the noise-free case, 6.0% with a signal-to-noise ratio (SNR) of 10dB, and 6.5% with a SNR of 0 dB.     

Cost function analysis in the structural optimization of steel frames

An objective function used in structural optimization should be formulated in such a way that the most economic solution can be found. However, the objective function is usually simplified to represent the weight, disregarding the fabrication and erection costs of the structure. The paper presents a very detailed objective function that considers the self-manufacturing costs of the whole structure. The cost function includes all essential fabrication and erection activities. It considers both manufacturing costs as well as material costs. It is formulated in an open manner, offering users the possibility to define their own parameters on the basis of a certain production line. The cost function is implemented into the optimization system for planar steel frames.     

Improved prediction-based ovarian follicle detection from a sequence of ultrasound images

A new algorithm is presented for ovarian follicle recognition from a sequence of ultrasound images. The basic version of the prediction-based algorithm is upgraded by means of two improvements. The negative influence brought by the gross measurement errors is suppressed, and the locality of the treated process is considered. The basis for both improvements is the Kalman filter. The proposed algorithm is a combination of three mutually dependent Kalman filters: a global one whose parameters are then modified by two additional ones, firstly detecting the gross measurement errors and secondly, regarding the recognised contour of the object. The obtained results show that the follicles recognised using the final prediction algorithm are about 2% more compact and about 6% more accurate, on average, when compared to the values obtained using the basic prediction-based algorithm.     

Influence of Monomer Structure,Initiation, and Porosity on Mechanical and Morphological Characteristics of Thiol-ene PolyHIPEs

Combining high internal phase emulsion templating with thiol-ene click chemistry produces porous polymers with high yields and degradable ester linkages. This study compares the influence of the monomer functionalities (tri versus tetra), internal phase volume, and initiation type (photo versus thermal) on the morphological and mechanical properties of poly(high internal phase emulsions) (polyHIPEs). For the synthesis of the polyHIPEs pentaerythritol tetrakis(3-mercaptopropionate) (PETMP, tetrafunctional), trimethylolpropane tris(3-mercaptopropionate) (TMPTMP, trifunctional), pentaerythritol tetraacrylate (PETA, tetrafunctional), and trimethylolpropane triacrylate (TMPTA, trifunctional) are used. The main factors influencing the properties of the polyHIPEs are the monomer structures and the internal phase volume, while the initiation type influences the morphology of the trifunctional system (pore size and morphology type) resulting in an interconnected cellular morphology in all cases except in the case of the photopolymerization of the emulsion with 85 vol% of the internal phase. The average pore diameter of the trifunctional system ranges from 8.0 to 27.8 µm, while for the tetrafunctional system it ranges from 8.1 to 12.3 µm. The compression moduli of the trifunctional system range from 0.093 to 0.240 MPa and for the tetrafunctional system they range from 1.906 to 7.670 MPa. The compression moduli decrease with increasing internal phase volume (porosity).