Considering the need to adopt more sustainable agricultural systems, it is important that sweet potato breeding programs seek to increase not only root productivity, but also the productivity and quality of branches for silage production. The objective was to evaluate the genetic divergence and the importance of traits associated with the production and quality of branch silage in sweet potato genotypes. The experiment was conducted on the JK Campus of the Federal University of Vales do Jequitinhonha and Mucuri Valleys in a randomized block design with 12 treatments and four repetitions. Twelve characteristics of branches and silage were evaluated. There was genetic variability between the genotypes, making it possible to select parents divergent for future breeding programs for silage production. The genotypes BD-54 and BD-31TO were the most divergent in relation to the others, being indicated its use in crossbreeding aiming the improvement of the culture for silage, once the high performance per se of all genotypes evaluated has already been verified in previous works. The characteristics Na, TDN and NDF were those that most contributed to the divergence.

Vascular access in hemodialysis is one of the pillars of success of the program. Therefore, efforts should be directed firstly to achieve the greatest number of vascular accesses of the arteriovenous fistula type, and secondly to reduce complications related to access cannulation in order to functionally preserve the access. Several strategies have been described to improve this last aspect; this article describes the use of ultrasound to improve the probability of successful cannulation in cases considered difficult by the nursing team.

The integration of medical images is the process of registering and fusing them to obtain a greater amount of diagnostic information. In this work an analysis is performed for the integration of images obtained through computed axial tomography and magnetic resonance imaging, for which a tool was developed in the Matlab program, where the registration is implemented through equivalent features; in addition, the pairs of images are compared by several fusion rules, with a view to identify the best algorithm in which the resulting fused image contains the most information from the original representations.

Currently there is a great acceptance in medicine and dentistry that clinical practice should be “evidence-based” as much as possible. That is why multiple works have been published aimed at decreasing radiation doses in the different types of imaging modalities used in dentistry, since the greater effect of radiation, especially in children, forces us to take necessary measures to rationalize its use, especially with Cone Beam computed tomography (CBCT), the method that provides the highest doses in dentistry. This review was written using such an approach with the purpose of rationalizing the radiation dose in our patients. In order to formulate recommendations that contribute to the optimization of the use of ionizing radiation in dentistry, the SEDENTEXCT project team compiled and analyzed relevant publications in the literature, guidelines that have demonstrated their efficiency in the past, thus helping to see with different perspectives the dose received by patients, and with this, it is recommended taking into account this document so as to prescribe more adequately the complementary examinations that we use on a daily basis.

Cartography includes two major tasks: map making and map application, which is inextricably linked to artificial intelligence technology. The cartographic expert system experienced the intelligent expression of symbolism. After the spatial optimization decision of behaviorism intelligent expression, cartography faces the combination of deep learning under connectionism to improve the intelligent level of cartography. This paper discusses three problems about the proposition of “deep learning + cartography”. One is the consistency between the deep learning method and the map space problem solving strategy, based on gradient descent, local correlation, feature reduction and non-linear nature that answer the feasibility of the combination of “deep learning + cartography”; the second is to analyze the challenges faced by the combination of cartography from its unique disciplinary characteristics and technical environment, involving the non-standard organization of map data, professional requirements for sample establishment, the integration of geometric and geographical features, as well as the inherent spatial scale of the map; thirdly, the entry points and specific methods for integrating map making and map application into deep learning are discussed respectively.

Spectrum map is the foundation of spectrum resource management, security governance and spectrum warfare. Aiming at the problem that the traditional spectrum mapping is limited to two-dimensional space, a three-dimensional spectrum data acquisition and mapping system architecture for the integration of space, sky and earth is presented, and a spectrum map reconstruction scheme driven by propagation model is proposed, which can achieve high-precision three-dimensional spectrum map rendering under the condition of sparse sampling. The spectrum map reconstructed by this method in the case of single radiation source and multiple radiation sources is in good agreement with the theoretical results based on ray tracing method. In addition, the measured results of typical scenes further verify the feasibility of this method.