Semi-supervised learning with concept drift using particle dynamics applied to network intrusion detection data

Concept drift, which refers to non stationary learning problems over time, has increasing importance in machine learning and data mining. Many concept drift applications require fast response, which means an algorithm must always be (re)trained with the latest available data. But the process of data labeling is usually expensive and/or time consuming when compared to acquisition of unlabeled data, thus usually only a small fraction of the incoming data may be effectively labeled. Semi-supervised learning methods may help in this scenario, as they use both labeled and unlabeled data in the training process. However, most of them are based on assumptions that the data is static. Therefore, semi-supervised learning with concept drifts is still an open challenging task in machine learning. Recently, a particle competition and cooperation approach has been developed to realize graph-based semi-supervised learning from static data. We have extend that approach to handle data streams and concept drift. The result is a passive algorithm which uses a single classifier approach, naturally adapted to concept changes without any explicit drift detection mechanism. It has built-in mechanisms that provide a natural way of learning from new data, gradually "forgetting" older knowledge as older data items are no longer useful for the classification of newer data items. The proposed algorithm is applied to the KDD Cup 1999 Data of network intrusion, showing its effectiveness.

Resistance training with excessive training load and insufficient recovery alters skeletal muscle mass-related protein expression

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Harmony Search applied for Support Vector Machines Training Optimization

Since the beginning, some pattern recognition techniques have faced the problem of high computational burden for dataset learning. Among the most widely used techniques, we may highlight Support Vector Machines (SVM), which have obtained very promising results for data classification. However, this classifier requires an expensive training phase, which is dominated by a parameter optimization that aims to make SVM less prone to errors over the training set. In this paper, we model the problem of finding such parameters as a metaheuristic-based optimization task, which is performed through Harmony Search (HS) and some of its variants. The experimental results have showen the robustness of HS-based approaches for such task in comparison against with an exhaustive (grid) search, and also a Particle Swarm Optimization-based implementation.

Laboratory testes with quality data in Dentistry

In laboratory tests, just following the manufacturer’s instructions of materials or equipments may not be enough to obtain reliable data. Thus, intra and inter-examiners studies may be required. The aim of this study was to illustrate the application of the Intraclass Correlation Coefficient (r) in a study related to the color changing and hardness of composite resin conducted by two examiners. The color and hardness of 10 specimens of composite resin were evaluated by a colorimetric spectrophotometer and hardness tester, respectively, at two different times. Two trained examiners performed two measurements with an interval of one week. Specimens were stored in artificial saliva at 37±1ºC for 7 days. The Intraclass Correlation was used for analysis of intra and inter-examiner reproducibility. The intra-examiner reproducibility was 0.79, 0.44 and 0.76 for L, a and b color coordinates for the examiner 1 and 0.84, 0.23, 0.21 for examiner 2. For hardness, r-values were 0.00 and 0.23 for the examiner 1 and 2, respectively, showing unsatisfactory agreement on color and hardness evaluation for both examiners. It was noted that only the observation of protocol for use of equipment and examiners training were not sufficient to collect reliable information. Thus, adjustments in the experimental protocol were made and devices were produced to standardize the measurements. The reproducibility study was performed again. For examiner 1, values as 0.90, 0.59 and 0.79 were verified for L, a and b coordinates and, for examiner 2 were obtained values of 0.90, 0.75, 0.95. In relation to hardness, r-values of 0.75 and 0.71 were obtained for examiners 1 and 2, respectively. The inter-examiner reproducibility was 0.86, 0.87, 0.91 for L, a and b coordinates and 0.79 for hardness. It was concluded that intra and inter-examiner calibration is essential for obtaining quality measurements in laboratory tests.

Impact of patient training patterns on peritonitis rates in a large national cohort study

Background. Ideal training methods that could ensure best peritoneal dialysis (PD) outcome have not been defined in previous reports. The aim of the present study was to evaluate the impact of training characteristics on peritonitis rates in a large Brazilian cohort.Methods. Incident patients with valid data on training recruited in the Brazilian Peritoneal Dialysis Multicenter Study (BRAZPD II) from January 2008 to January 2011 were included. Peritonitis was diagnosed according to International Society for Peritoneal Dialysis guidelines; incidence rate of peritonitis (episodes/patient-months) and time to the first peritonitis were used as end points.Results. Two thousand two hundred and forty-three adult patients were included in the analysis: 59 +/- 16 years old, 51.8% female, 64.7% with <= 4 years of education. The median training time was 15 h (IQI 10-20 h). Patients were followed for a median of 11.2 months (range 3-36.5). The overall peritonitis rate was 0.29 per year at risk (1 episode/41 patient-months). The mean number of hours of training per day was 1.8 +/- 2.4. Less than 1 h of training/day was associated with higher incidence rate when compared with the intervals of 1-2 h/day (P = 0.03) and > 2 h/day (P = 0.02). Patients who received a cumulative training of > 15 h had significantly lower incidence of peritonitis compared with < 15 h (0.26 per year at risk versus 0.32 per year at risk, P = 0.01). The presence of a caregiver and the number of people trained were not significantly associated with peritonitis incidence rate. Training in the immediate 10 days after implantation of the catheter was associated with the highest peritonitis rate (0.32 per year), compared with training prior to catheter implantation (0.28 per year) or > 10 days after implantation (0.23 per year). More experienced centers had a lower risk for the first peritonitis (P = 0.003).Conclusions. This is the first study to analyze the association between training characteristics and outcomes in a large cohort of PD patients. Low training time (particularly < 15 h), smaller center size and the timing of training in relation to catheter implantation were associated with a higher incidence of peritonitis. These results support the recommendation of a minimum amount of training hours to reduce peritonitis incidence regardless of the number of hours trained per day.

Agro-ecology as a mediating science between the training of the agronomist and sustainable agriculture

Agro-ecology plays an important role in the implementation of sustainable development, and an agronomist can be a leading agent in the dissemination of that culture. In this perspective, a survey was carried out with the attendants of the course in Agronomy at the Instituto Federal de Educacao, Ciencia e Tecnologia do Mato Grosso, Campus Campo Novo do Parecis, Brazil. The object of the study was to analyze the participation of the academics in agro-ecological activities, seeking to observe the acceptance, perceptions and possible indications of incorporation of these principles in the training. The survey was conducted during the period July-December 2011. The approach was the qualitative method and the instruments used in data collection were participant observation and interviews during the activities. The results revealed the satisfaction of students in engaging in agro-ecological activities: Students developed concepts and incorporated the proposal of agro-ecology throughout the project. The contents of the agronomy course offered at the institution, in the perception of students, is strongly linked to the principles of conventional farming, not fully considering training to meet the challenges, and current and emerging demands of agriculture.

Environmental training and environmental management maturity of Brazilian companies with ISO14001: empirical evidence

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Impact of functional training on cardiac autonomic modulation, cardiopulmonary parameters and quality of life in healthy women

Coordenação de Aperfeiçoamentode Pessoal de Nível Superior (CAPES)

High-intensity resistance training attenuates dexamethasone-induced muscle atrophy

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Green training supporting eco-innovation in three Brazilian companies: practices and levels of integration

Purpose – The purpose of this paper is to show results from the relationship between green/environmental training and the development of three projects of low-carbon eco-innovations in top Brazilian companies. Design/methodology/approach – This study includes three organizational projects for low-carbon eco-innovations in products (A, B and C) with the objective of reducing their impact on GHG emissions, the so-called low-carbon products. Data were collected from several sources of evidence, including in-depth interviews, document analyses and direct observations. Findings – The authors verified that the environmental training interface for mitigating climate change is relevant for the systematic development of low-carbon products in most of the cases studied. Originality/value – Low-carbon eco-innovations are a trend in the corporate world; however, there is not enough literature and practical evidence on this subject. Thus, this paper adds new evidence to the literature.