Abstract
Deep learning (DL) incorporates a modern technique for image processing and big data analysis with large potential. Deep learning is a recent tool in the agricultural domain, being already successfully applied to other domains. This article performs a survey of different deep learning techniques applied to various agricultural problems, such as disease detection/identification, fruit/plants classification and fruit counting among other domains. The paper analyses the specific employed models, the source of the data, the performance of each study, the employed hardware and the possibility of real-time application to study eventual integration with autonomous robotic platforms. The conclusions indicate that deep learning provides high accuracy results, surpassing, with occasional exceptions, alternative traditional image processing techniques in terms of accuracy.

Abstract

Abstract

Abstract
This work proposes a mathematical linear programming model that addresses the food provisioning problem of the food bank of Madrid. It aims to determine the most appropriate weekly decisions to meet the macro-nutritional requirements of the beneficiaries of this social service, by minimizing the total cost considering third-party donations. The model has been applied to a realistic case study considering a sociological structure of beneficiaries categorized by age and gender and representing the first decile of incomes of the Spanish population. The demand of macronutrients is satisfied by means of nine different groups of food, used to provide some level of variability in the consumption patterns of the beneficiaries. The results provide insight on cost-cutting opportunities related to centralizing the decision-making process, indicating a 10% reduction both in provisioning costs and food quantities. This suggests that the proposed model might serve as a tool for designing new strategies for the provisioning or evaluation of economic and social support policies for the food bank of Madrid.

Abstract

Abstract
Software documentation is an important part of the captured knowledge of a software project and documentation patterns have often been used as a systematic way to describe good practices on software documentation. Still, many software teams are challenged by what to document, how to keep the documentation consistent and how to make their consumers aware of the relevant documents. A literature review was done over 14 publications and identified 16 quality attributes and 114 patterns about software documentation. This knowledge was analysed and classified and led to the proposal of new categories and relationships between the existing patterns. These are depicted as a new pattern map that provides a new perspective of documentation patterns and can be used to guide teams in adopting software documentation practices. © 2020 Owner/Author.