Combining meta-learning and search techniques to select parameters for support vector machines

Support Vector Machines (SVMs) have achieved very good performance on different learning problems. However, the success of SVMs depends on the adequate choice of the values of a number of parameters (e.g., the kernel and regularization parameters). In the current work, we propose the combination of meta-learning and search algorithms to deal with the problem of SVM parameter selection. In this combination, given a new problem to be solved, meta-learning is employed to recommend SVM parameter values based on parameter configurations that have been successfully adopted in previous similar problems. The parameter values returned by meta-learning are then used as initial search points by a search technique, which will further explore the parameter space. In this proposal, we envisioned that the initial solutions provided by meta-learning are located in good regions of the search space (i.e. they are closer to optimum solutions). Hence, the search algorithm would need to evaluate a lower number of candidate solutions when looking for an adequate solution. In this work, we investigate the combination of meta-learning with two search algorithms: Particle Swarm Optimization and Tabu Search. The implemented hybrid algorithms were used to select the values of two SVM parameters in the regression domain. These combinations were compared with the use of the search algorithms without meta-learning. The experimental results on a set of 40 regression problems showed that, on average, the proposed hybrid methods obtained lower error rates when compared to their components applied in isolation.

Spinal cord injury as a trigger to develop periodic leg movements during sleep: an evolutionary perspective

The primary trigger to periodic limb movement (PLM) during sleep is still unknown. Its association with the restless legs syndrome (RLS) is established in humans and was reported in spinal cord injury (SCI) patients classified by the American Spinal Injury Association (ASIA) as A. Its pathogenesis has not been completely unraveled, though recent advances might enhance our knowledge about those malfunctions. PLM association with central pattern generator (CPG) is one of the possible pathologic mechanisms involved. This article reviewed the advances in PLM and RLS genetics, the evolution of CPG functioning, and the neurotransmitters involved in CPG, PLM and RLS. We have proposed that SCI might be a trigger to develop PLM.

Techniques for the In Vitro Production of Queens in Stingless Bees (Apidae, Meliponini)

Considering the ecological importance of stingless bees as caretakers and pollinators of a variety of native plants makes it necessary to improve techniques which increase of colonies' number in order to preserve these species and the biodiversity associated with them. Thus, our aim was to develop a methodology of in vitro production of stingless bee queens by offering a large quantity of food to the larvae. Our methodology consisted of determining the amount of larval food needed for the development of the queens, collecting and storing the larval food, and feeding the food to the larvae in acrylic plates. We found that the total average amount of larval food in a worker bee cell of E varia is approximately 26.70 +/- 3.55 mu L. We observed that after the consumption of extra amounts of food (25, 30, 35 and 40 mu L) the larvae differentiate into queens (n = 98). Therefore, the average total volume of food needed for the differentiation of a young larva of F. varia queen is approximately 61.70 +/- 5.00 mu L. In other words; the larvae destined to become queens eat 2.31 times more food than the ones destined to become workers. We used the species Frieseomelitta varia as a model, however the methodology can be reproduced for all species of stingless bees whose mechanism of caste differentiation depends on the amount of food ingested by the larvae. Our results demonstrate the effectiveness of the in vitro technique developed herein, pointing to the possibility of its use as a tool to assist the production of queens on a large scale. This would allow for the artificial splitting of colonies and contribute to conservation efforts in native bees.

Determination of trace elements in bovine semen samples by inductively coupled plasma mass spectrometry and data mining techniques for identification of bovine class

The reproductive performance of cattle may be influenced by several factors, but mineral imbalances are crucial in terms of direct effects on reproduction. Several studies have shown that elements such as calcium, copper, iron, magnesium, selenium, and zinc are essential for reproduction and can prevent oxidative stress. However, toxic elements such as lead, nickel, and arsenic can have adverse effects on reproduction. In this paper, we applied a simple and fast method of multi-element analysis to bovine semen samples from Zebu and European classes used in reproduction programs and artificial insemination. Samples were analyzed by inductively coupled plasma spectrometry (ICP-MS) using aqueous medium calibration and the samples were diluted in a proportion of 1:50 in a solution containing 0.01% (vol/vol) Triton X-100 and 0.5% (vol/vol) nitric acid. Rhodium, iridium, and yttrium were used as the internal standards for ICP-MS analysis. To develop a reliable method of tracing the class of bovine semen, we used data mining techniques that make it possible to classify unknown samples after checking the differentiation of known-class samples. Based on the determination of 15 elements in 41 samples of bovine semen, 3 machine-learning tools for classification were applied to determine cattle class. Our results demonstrate the potential of support vector machine (SVM), multilayer perceptron (MLP), and random forest (RF) chemometric tools to identify cattle class. Moreover, the selection tools made it possible to reduce the number of chemical elements needed from 15 to just 8.