Improving accuracy and speed of optimum-path forest classifier using combination of disjoint training subsets

The Optimum-Path Forest (OPF) classifier is a recent and promising method for pattern recognition, with a fast training algorithm and good accuracy results. Therefore, the investigation of a combining method for this kind of classifier can be important for many applications. In this paper we report a fast method to combine OPF-based classifiers trained with disjoint training subsets. Given a fixed number of subsets, the algorithm chooses random samples, without replacement, from the original training set. Each subset accuracy is improved by a learning procedure. The final decision is given by majority vote. Experiments with simulated and real data sets showed that the proposed combining method is more efficient and effective than naive approach provided some conditions. It was also showed that OPF training step runs faster for a series of small subsets than for the whole training set. The combining scheme was also designed to support parallel or distributed processing, speeding up the procedure even more. © 2011 Springer-Verlag.

Improving support vector solutions by selecting a sequence of training subsets

In this paper we demonstrate that it is possible to gradually improve the performance of support vector machine (SVM) classifiers by using a genetic algorithm to select a sequence of training subsets from the available data. Performance improvement is possible because the SVM solution generally lies some distance away from the Bayes optimal in the space of learning parameters. We illustrate performance improvements on a number of benchmark data sets.

Centroid training to achieve effective text classification

Traditional text classification technology based on machine learning and data mining techniques has made a big progress. However, it is still a big problem on how to draw an exact decision boundary between relevant and irrelevant objects in binary classification due to much uncertainty produced in the process of the traditional algorithms. The proposed model CTTC (Centroid Training for Text Classification) aims to build an uncertainty boundary to absorb as many indeterminate objects as possible so as to elevate the certainty of the relevant and irrelevant groups through the centroid clustering and training process. The clustering starts from the two training subsets labelled as relevant or irrelevant respectively to create two principal centroid vectors by which all the training samples are further separated into three groups: POS, NEG and BND, with all the indeterminate objects absorbed into the uncertain decision boundary BND. Two pairs of centroid vectors are proposed to be trained and optimized through the subsequent iterative multi-learning process, all of which are proposed to collaboratively help predict the polarities of the incoming objects thereafter. For the assessment of the proposed model, F1 and Accuracy have been chosen as the key evaluation measures. We stress the F1 measure because it can display the overall performance improvement of the final classifier better than Accuracy. A large number of experiments have been completed using the proposed model on the Reuters Corpus Volume 1 (RCV1) which is important standard dataset in the field. The experiment results show that the proposed model has significantly improved the binary text classification performance in both F1 and Accuracy compared with three other influential baseline models.

Immune cell changes in response to a swimming training session during a 24-h recovery period

Understanding the impact of training sessions on the immune response is crucial for the adequate periodization of training, to prevent both a negative influence on health and a performance impairment of the athlete. This study evaluated acute systemic immune cell changes in response to an actual swimming session, during a 24-h recovery period, controlling for sex, menstrual cycle phases, maturity, and age group. Competitive swimmers (30 females, 15 ± 1.3 years old; and 35 males, 16.5 ± 2.1 years old) performed a high-intensity training session. Blood samples were collected before, immediately after, 2 h after, and 24 h after exercise. Standard procedures for the assessment of leukogram by automated counting (Coulter LH 750, Beckman) and lymphocytes subsets by flow cytometry (FACS Calibur BD, Biosciences) were used. Subjects were grouped according to competitive age groups and pubertal Tanner stages. Menstrual cycle phase was monitored. The training session induced neutrophilia, lymphopenia, and a low eosinophil count, lasting for at least 2 h, independent of sex and maturity. At 24 h postexercise, the acquired immunity of juniors (15-17 years old), expressed by total lymphocytes and total T lymphocytes (CD3+), was not fully recovered. This should be accounted for when planning a weekly training program. The observed lymphopenia suggests a lower immune surveillance at the end of the session that may depress the immunity of athletes, highlighting the need for extra care when athletes are exposed to aggressive environmental agents such as swimming pools

In-vivo cell mediated immunity in elite swimmers in response to training

This study investigated in-vivo cell-mediated immune (CMI) responses in elite swimmers over a 5-month training season, to assess the impact of intense training on changes in T-lymphocyte function. The CMI Multitest was performed early in the season after a period of rest, during peak high-intensity training, and late in the season during the precompetition taper period. The CMI tests were performed at rest prior to a morning training session. There were no significant differences between the swimmers and a control group for any of the seven CMI antigen responses at any of the test points during the season. In the swimmers, there were no significant differences in the number of positive responses to the CMI antigens between the three test points (Friedman's test = 9.6364, p = 0.47) and no significant differences for the CMI cumulative scores (Friedman's test = 11.98, p = 0.29) at each test point. There was no consistent pattern for changes in CMI cumulative scores for individual swimmers over the training season. The findings of this study indicate that, despite reported transient T-lymphocyte immunosuppression immediately after intense exercise, probably associated with acute redistribution and temporary pooling of blood T cell subsets in extremities, the T-lymphocyte function involved in CMI responses is not compromised by extended periods of training at an elite level.

A Best Practice Process for Fleet Safety Training

This paper outlines a process for fleet safety training based on research and management development programmes undertaken at the University of Huddersfield in the UK (www.hud.ac.uk/sas/trans/transnews.htm) and CARRS-Q in Australia (www.carrsq.qut.edu.au/staff/Murray.jsp) over the past 10 years.