Time-motion and physiological assessments of ice hockey performance.

Ice hockey performance was studied during 10 contests to assess time-motion characteristics and associated physiological changes that occur for each position. Depending on the position played, the actual playing time per game for forwards and defensemen ranged between 20.7 and 28.0 min. The number of shifts ranged from 14 to 21 with an average playing time of 85.4 s/shift. Further analysis of each shift indicated that there was an average of 2.3 play stoppages which averaged 27.1 s, producing a continuous playing time of 39.7 s. Telemetered recordings of heart rate during each shift revealed sustained rates of between 170 and 174 beats/min over the three periods of the game. For both the forwards and defensemen, values for blood lactates were highest during the first and second periods (x = 78.0 and 66.1 mg/100 ml), then declined considerably during the third period (x = 44.5 mg/100 ml). Blood glucose showed a similar tendency (x = 139.3, 133.7, 114.1 mg/100 ml), while hematocrit and total protein showed little tendency to change.     

An optimal algorithm for automatic genotype elimination

In an effort to accelerate likelihood computations on pedigrees, Lange and Goradia defined a genotype-elimination algorithm that aims to identify those genotypes that need not be considered during the likelihood computation. For pedigrees without loops, they showed that their algorithm was optimal, in the sense that it identified all genotypes that lead to a Mendelian inconsistency. Their algorithm, however, is not optimal for pedigrees with loops, which continue to pose daunting computational challenges. We present here a simple extension of the Lange-Goradia algorithm that we prove is optimal on pedigrees with loops, and we give examples of how our new algorithm can be used to detect genotyping errors. We also introduce a more efficient and faster algorithm for carrying out the fundamental step in the Lange-Goradia algorithm-namely, genotype elimination within a nuclear family. Finally, we improve a common algorithm for computing the likelihood of a pedigree with multiple loops. This algorithm breaks each loop by duplicating a person in that loop and then carrying out a separate likelihood calculation for each vector of possible genotypes of the loop breakers. This algorithm, however, does unnecessary computations when the loop-breaker vector is inconsistent. In this paper we present a new recursive loop breaker-elimination algorithm that solves this problem and illustrate its effectiveness on a pedigree with six loops.     

An algorithm for automatic genotype elimination.

Automatic genotype elimination algorithms for a single locus play a central role in making likelihood computations on human pedigree data feasible. We present a simple algorithm that is fully efficient in pedigrees without loops. This algorithm can be easily coded and has been instrumental in greatly reducing computing times for pedigree analysis. A contrived counter-example demonstrates that some superfluous genotypes cannot be excluded for inbred pedigrees.     

BioLayout--an automatic graph layout algorithm for similarity visualization

Graph layout is extensively used in the field of mathematics and computer science, however these ideas and methods have not been extended in a general fashion to the construction of graphs for biological data. To this end, we have implemented a version of the Fruchterman Rheingold graph layout algorithm, extensively modified for the purpose of similarity analysis in biology. This algorithm rapidly and effectively generates clear two (2D) or three-dimensional (3D) graphs representing similarity relationships such as protein sequence similarity. The implementation of the algorithm is general and applicable to most types of similarity information for biological data. AVAILABILITY: BioLayout is available for most UNIX platforms at the following web-site: http://www.ebi.ac.uk/research/cgg/services/layout.     

A grid layout algorithm for automatic drawing of biochemical networks

MOTIVATION: Visualization is indispensable in the research of complex biochemical networks. Available graph layout algorithms are not adequate for satisfactorily drawing such networks. New methods are required to visualize automatically the topological architectures and facilitate the understanding of the functions of the networks. RESULTS: We propose a novel layout algorithm to draw complex biochemical networks. A network is modeled as a system of interacting nodes on squared grids. A discrete cost function between each node pair is designed based on the topological relation and the geometric positions of the two nodes. The layouts are produced by minimizing the total cost. We design a fast algorithm to minimize the discrete cost function, by which candidate layouts can be produced efficiently. A simulated annealing procedure is used to choose better candidates. Our algorithm demonstrates its ability to exhibit cluster structures clearly in relatively compact layout areas without any prior knowledge. We developed Windows software to implement the algorithm for CADLIVE. AVAILABILITY: All materials can be freely downloaded from http://kurata21.bio.kyutech.ac.jp/grid/grid_layout.htm; http://www.cadlive.jp/ SUPPLEMENTARY INFORMATION: http://kurata21.bio.kyutech.ac.jp/grid/grid_layout.htm; http://www.cadlive.jp/     

Pseudo-relaxation learning algorithm for complex-valued associative memory

HAM (Hopfield Associative Memory) and BAM (Bidirectinal Associative Memory) are representative associative memories by neural networks. The storage capacity by the Hebb rule, which is often used, is extremely low. In order to improve it, some learning methods, for example, pseudo-inverse matrix learning and gradient descent learning, have been introduced. Oh introduced pseudo-relaxation learning algorithm to HAM and BAM. In order to accelerate it, Hattori proposed quick learning. Noest proposed CAM (Complex-valued Associative Memory), which is complex-valued HAM. The storage capacity of CAM by the Hebb rule is also extremely low. Pseudo-inverse matrix learning and gradient descent learning have already been generalized to CAM. In this paper, we apply pseudo-relaxation learning algorithm to CAM in order to improve the capacity.     

A new learning algorithm for synergetic computers

We introduce a Lyapunov function which allows us to calculate the vectors, by which the synaptic strengths are determined, by means of a gradient dynamics. The approach does not require any back-propagation, nor simulated annealing, nor computations on a freely running (unclamped) network. The approach is applicable to noiseless patterns as well as to sets of noisy patterns defined by their second and fourth order moments.     

Backpropagation algorithm adaptation parameters using learning automata

Despite of the many successful applications of backpropagation for training multi-layer neural networks, it has many drawbocks. For complex problems it may require a long time to train the networks, and it may not train at all. Long training time can be the result of the non-optimal parameters. It is not easy to choose appropriate value of the parameters for a particular problem. In this paper, by interconnection of fixed structure learning automata (FSLA) to the feedforward neural networks, we apply learning automata (LA) scheme for adjusting these parameters based on the observation of random response of neural networks. The main motivation in using learning automata as an adaptation algorithm is to use its capability of global optimization when dealing with multi-modal surface. The feasibility of proposed method is shown through simulations on three learning problems: exclusive-or, encoding problem, and digit recognition. The simulation results show that the adaptation of these parameters using this method not only increases the convergence rate of learning but it increases the likelihood of escaping from the local minima.     

Extemporaneous analysis of myocardial performance by a programmable automatic dynamometer

This article describes a biophysical investigation to determine the physiological integrity of isolated cardiac fibers obtained during surgery. Immediate biopsy of myocardium can be analysed dynamically in various physiological conditions using an intelligent dynamometer controlled by an "APPLE II" microcomputer generally in less than fifteen minutes. Multiple tests including pharmacological and electrical properties of fibers can now be done with this cardiac analyser. Primary investigations on heart diseases show the importance of the method for evaluation of heart necrosis.     

Partially supervised learning using an EM-boosting algorithm

Training data in a supervised learning problem consist of the class label and its potential predictors for a set of observations. Constructing effective classifiers from training data is the goal of supervised learning. In biomedical sciences and other scientific applications, class labels may be subject to errors. We consider a setting where there are two classes but observations with labels corresponding to one of the classes may in fact be mislabeled. The application concerns the use of protein mass-spectrometry data to discriminate between serum samples from cancer and noncancer patients. The patients in the training set are classified on the basis of tissue biopsy. Although biopsy is 100% specific in the sense that a tissue that shows itself to have malignant cells is certainly cancer, it is less than 100% sensitive. Reference gold standards that are subject to this special type of misclassification due to imperfect diagnosis certainty arise in many fields. We consider the development of a supervised learning algorithm under these conditions and refer to it as partially supervised learning. Boosting is a supervised learning algorithm geared toward high-dimensional predictor data, such as those generated in protein mass-spectrometry. We propose a modification of the boosting algorithm for partially supervised learning. The proposal is to view the true class membership of the samples that are labeled with the error-prone class label as missing data, and apply an algorithm related to the EM algorithm for minimization of a loss function. To assess the usefulness of the proposed method, we artificially mislabeled a subset of samples and applied the original and EM-modified boosting (EM-Boost) algorithms for comparison. Notable improvements in misclassification rates are observed with EM-Boost.     

A genetic algorithm approach to optimization of asynchronous automatic assembly systems

This paper presents the application of genetic algorithms to the performance optimization of asynchronous automatic assembly systems (AAS). These stochastic systems are subject to blocking and starvation effects that make complete analytic performance modeling difficult. Therefore, this paper extends genetic algorithms to stochastic systems. The performance of the genetic algorithm is measured through comparison with the results of stochastic quasi-gradient (SQM) methods to the same AAS. The genetic algorithm performs reasonably well in obtaining good solutions (as compared with results of SQM) in this stochastic optimization example, even though genetic algorithms were designed for application to deterministic systems. However, the genetic algorithm's performance does not appear to be superior to SQM.     

Semi-quantitative assessments of dextran toxicity on corneal endothelium: conceptual design of a predictive algorithm

Dextran is added to corneal culture medium for at least 8 h prior to transplantation to ensure that the cornea is osmotically dehydrated. It is presumed that dextran has a certain toxic effect on corneal endothelium but the degree and the kinetics of this effect have not been quantified so far. We consider that such data regarding the toxicity of dextran on the corneal endothelium could have an impact on scheduling and logistics of corneal preparation in eye banking. In retrospective statistic analyses, we compared the progress of corneal endothelium (endothelium cell loss per day) of 1334 organ-cultured corneal explants in media with and without dextran. Also, the influence of donor-age, sex and cause of death on the observed dextran-mediated effect on endothelial cell counts was studied. Corneas cultured in dextran-free medium showed a mean endothelium cell count decrease of 0.7% per day. Dextran supplementation led to a mean endothelium cell loss of 2.01% per day; this reflects an increase by the factor of 2.9. The toxic impact of dextran was found to be time dependent; while the prevailing part of the effect was observed within the first 24 h after dextran-addition. Donor age, sex and cause of death did not seem to have an influence on the dextran-mediated toxicity. Based on these findings, we could design an algorithm which approximately describes the kinetics of dextran-toxicity. We reproduced the previously reported toxic effect of dextran on the corneal endothelium in vitro. Additionally, this is the first work that provides an algorithmic instrument for the semi-quantitative calculation of the putative endothelium cell count decrease in dextran containing medium for a given incubation time and could thus influence the time management and planning of corneal transplantations.     

Spatial discrimination performance of Drosophila melanogaster: Test-retest assessments and a reinterpretation

Two experiments found significant correlations between the performance of experimental flies, which were retrained on a spatial discrimination task, and yoked controls which were trained for the first time after having been allowed to explore the maze. The proportion of variance accounted for by the correlations equalled or exceeded that found for other variables in previous experiments. The data suggest that the performance of individual experimental flies and that of their control counterparts are not independent, seriously jeopardizing an instrumental learning interpretation of Drosophila performance.     

Diurnal variations in learning performance in chickens

Diurnal variations in the learning performance of young chicks were investigated using a visual discrimination task which requires birds to discrminate grains from a background of pebbles. Chicks accustomed to receiving fresh food daily in the morning were found to learn well during the day, in that they pecked almost exclusively at grains; but during the night they pecked indiscriminately at grains and pebbles. This occurred even though food was available ad libitum. Chicks accustomed to receiving fresh food daily in the evening learnt the task during the day, and also late at night. Thus the shape of the performance cycle depends in part on environmental factors. Other factors, such as activity, which may contribute to, or co-vary with, this variation in learning performance were investigated.     

A fast and convergent stochastic MLP learning algorithm

We propose a stochastic learning algorithm for multilayer perceptrons of linear-threshold function units, which theoretically converges with probability one and experimentally exhibits 100% convergence rate and remarkable speed on parity and classification problems with typical generalization accuracy. For learning the n bit parity function with n hidden units, the algorithm converged on all the trials we tested (n=2 to 12) after 5.8 x 4.1(n) presentations for 0.23 x 4.0(n-6) seconds on a 533MHz Alpha 21164A chip on average, which is five to ten times faster than Levenberg-Marquardt algorithm with restarts. For a medium size classification problem known as Thyroid in UCI repository, the algorithm is faster in speed and comparative in generalization accuracy than the standard backpropagation and Levenberg-Marquardt algorithms.     

Machine learning approach for automatic recognition of tomato-pollinating bees based on their buzzing-sounds

Bee-mediated pollination greatly increases the size and weight of tomato fruits. Therefore, distinguishing between the local set of bees–those that are efficient pollinators–is essential to improve the economic returns for farmers. To achieve this, it is important to know the identity of the visiting bees. Nevertheless, the traditional taxonomic identification of bees is not an easy task, requiring the participation of experts and the use of specialized equipment. Due to these limitations, the development and implementation of new technologies for the automatic recognition of bees become relevant. Hence, we aim to verify the capacity of Machine Learning (ML) algorithms in recognizing the taxonomic identity of visiting bees to tomato flowers based on the characteristics of their buzzing sounds. We compared the performance of the ML algorithms combined with the Mel Frequency Cepstral Coefficients (MFCC) and with classifications based solely on the fundamental frequency, leading to a direct comparison between the two approaches. In fact, some classifiers powered by the MFCC–especially the SVM–achieved better performance compared to the randomized and sound frequency-based trials. Moreover, the buzzing sounds produced during sonication were more relevant for the taxonomic recognition of bee species than analysis based on flight sounds alone. On the other hand, the ML classifiers performed better in recognizing bees genera based on flight sounds. Despite that, the maximum accuracy obtained here (73.39% by SVM) is still low compared to ML standards. Further studies analyzing larger recording samples, and applying unsupervised learning systems may yield better classification performance. Therefore, ML techniques could be used to automate the taxonomic recognition of flower-visiting bees of the cultivated tomato and other buzz-pollinated crops. This would be an interesting option for farmers and other professionals who have no experience in bee taxonomy but are interested in improving crop yields by increasing pollination.