Fontes de matéria orgânica para a formulação de fertilizantes organominerais peletizados no desenvolvimento da cultura do sorgo

Organo-mineral fertilizers have been used to both meet plants’ nutritional needs and reduce producers’ reliance on mineral fertilizers. This practice improves both the use of nutrients by plants and the soil structure due to the organic matter in these fertilizers. This study aimed to determine the effect of organic matter sources in the composition of organomineral fertilizers and compare it to the effect of traditional mineral fertilizers when it comes to the initial development of sorghum. Research was carried out in a greenhouse at the Federal University of Uberlandia, in Uberlandia, Minas Gerais, Brazil. Sorghum seeds of grain-bearing simple hybrid 1G100 were used in the seeding process. The experiment followed a randomized complete block design in a 4 x 3 + 2 factorial arrangement. Factors included four levels (50, 75, 100 and 125% of 450 kg ha-1, which is the recommended dose for sorghum crops), three organic matter sources in the composition of the organomineral fertilizers (sewage sludge, filter cake, and peat), a control (100% mineral fertilizer), and an untreated check (no fertilizers). Each experimental plot consisted of four plants divided into two pots. Oxisol was used in all pots. Analyses were performed at 30 and 60 days after seeding (DAS) and targeted: plant height, stem diameter, chlorophyll A, chlorophyll B, and leaf area. After this period, plants were removed from the soil, and had their aerial parts isolated to be dried in an air-forced oven before measurement of their dry mass. Means of the organomineral fertilizers outperformed those of both control and untreated check plots in almost all variables at 30 DAS. The only exception was variable stem diameter, in which organomineral fertilizers outperformed untreated check plots only. Sorghum fertilized with organomineral fertilizers also showed positive results in the variables analyzed at 60 DAS: even with dose reduction, their means were similar to those found in control plots. Organomineral fertilizers had higher means in some variables, such as diameter and dry mass of the aerial part, than both control and untreated check plots. In the conditions set in this study and considering the variables herein reported, organomineral fertilizers can substitute mineral fertilizers in the initial development of sorghum, even with some dose reductions.

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.