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.

Avaliação tribológica de novas modificações superficiais para cilindros de laminação a frio

The present work analyzed the tribological behavior of coatings/surface modifications traditionally used in cold rolling mill rolls and new coatings/surface modificationswith potential to replace the carcinogenic hard chrome. The study started with identification of wear mechanisms occurring in real coldrollingmill rolls. Due the high cost and dimensions of the rolls, thereplication technique was used. Replicas were obtained from 4 different rolling millBrazilian companies before and after a normal rolling campaign. Initial sliding tests were conducted using spherical and cylindrical counter bodies in order to verifywhichtribological conditions allowed to reproduce the wear mechanisms found in the replicas. These tests indicated the use of reciprocating sliding tests with cylindrical counter bodies (line contact), normal load of 100 N, and test times of and 1 h and 5 h. Different surface modifications were carried out on samples produced from a fragment of a rolling mill roll. The specimens were heat treated and ground on both sides. After, some specimens were surface textured by electrical discharge texturing (EDT). For both groups (ground and EDT), subsequent treatments of chromium plating, electroless NiP coating and plasma nitriding were carried out. The results of the reciprocating tests showed that specimens with electroless NiP coating presented the lowest friction coefficients, while plasma nitrided specimens showed the highest. In general, previous surface texturing before the coating/surface modification increased the wear of the counter bodies. Oneexceptionwas for EDT with subsequent electroless NiP coating, which presented the lowest counter bodies wear rate. The samples withelectroless NiP coating promoted a tribolayer consisting of Nickel, Phosphorus and Oxygen on both the specimens andthecounter bodies, which was apparently responsible for the reduction of friction coefficient and wear rate. The increase of the test time reduced the wear rate of the samples, apparently due the stability of the tribolayers formed, except for the nitrided samples. For the textured specimens, NiP coating showed the best performance in maintaining the surface topography of the specimens after the sliding tests.