Resposta da batata cv. Cupido à fertilização organomineral

Potato crop cycle is relatively short and presents high yield per area; therefore, it is a very demanding culture for available nutrients in the soil solution. Despite its importance and the large number of studies about the crop, there is little research on plant nutrition regarding the use of organomineral fertilizer. This study evaluated potato, cv. Cupid, development and productivity as a function of fertilization with pelletized organomineral fertilizer. The experiment was done in Perdizes, Minas Gerais, in the rainy season of 2014/2015. The experimental design was a randomized blocks, with factorial arrangement of 4 x 2 (doses x management) and a control with mineral fertilizer, with 3 repetitions. Organomineral fertilizer doses were 25, 50, 75 and 100% of the conventional mineral dose, which was 600 kg ha-1 K2SO4, 850 kg ha-1 NH4H2PO4, and 300 kg ha-1 (NH4)2SO4 of topdressing 19 days after planting (DAP). Fertilization managements were with or without topdressing at 19 DAP, when the potato was hilled. Two plants per plot were sampled at 36, 50, 64 and 81 DAP and analyzed for leaf, stem and dry matter contents. DRIS - Diagnosis and Recommendation Integrated System was applied at 36 DAP and the potatoes were harvested 112 DAP and subjected to tuber classification. Throughout the cycle, stem, leaf and tuber dry mass showed no significant differences between the fertilization managements. The doses of organomineral fertilizer and topdressing management does not affect productivity, and the lower doses (25%) were similar the greater ones and the control, with an average of 16.8 t ha-1, demonstrating that it is viable to make a single application of organomineral fertilizer at planting due to operational efficiency. The low yields observed were due to high rainfall and temperature, creating favorable conditions for the incidence of pests and diseases. According to DRIS, the organomineral dose 75% for topdressing, presented the best nutritional balance.

Uma abordagem baseada em filtragem colaborativa integrada a mapas de saliência para a recomendação de imagens

Nowadays, the amount of customers using sites for shopping is greatly increasing, mainly due to the easiness and rapidity of this way of consumption. The sites, differently from physical stores, can make anything available to customers. In this context, Recommender Systems (RS) have become indispensable to help consumers to find products that may possibly pleasant or be useful to them. These systems often use techniques of Collaborating Filtering (CF), whose main underlying idea is that products are recommended to a given user based on purchase information and evaluations of past, by a group of users similar to the user who is requesting recommendation. One of the main challenges faced by such a technique is the need of the user to provide some information about her preferences on products in order to get further recommendations from the system. When there are items that do not have ratings or that possess quite few ratings available, the recommender system performs poorly. This problem is known as new item cold-start. In this paper, we propose to investigate in what extent information on visual attention can help to produce more accurate recommendation models. We present a new CF strategy, called IKB-MS, that uses visual attention to characterize images and alleviate the new item cold-start problem. In order to validate this strategy, we created a clothing image database and we use three algorithms well known for the extraction of visual attention these images. An extensive set of experiments shows that our approach is efficient and outperforms state-of-the-art CF RS.