Abstract
Over the last few years, an extensive set of technologies have been systematically included in precision agriculture (PA) and also in precision viticulture (PV) practices, as tools that allow efficient monitoring of nearly any parameter to achieve sustainable crop management practices and to increase both crop yield and quality. However, many technologies and standards are not yet included on those practices. Therefore, potential benefits that may result from putting together agronomic knowledge with electronics and computer technologies are still not fully accomplished. Both emergent and established paradigms, such as the Internet of Everything (IoE), Internet of Things (IoT), cloud and fog computing, together with increasingly cheaper computing technologies - with very low power requirements and a diversity of wireless technologies, available to exchange data with increased efficiency - and intelligent systems, have evolved to a level where it is virtually possible to expeditiously create and deploy any required monitoring solution. Pushed by all of these technological trends and recent developments, data integration has emerged as the layer between crops and knowledge needed to efficiently manage it. In this paper, the mySense environment is presented, aimed to systematize data acquisition procedures to address common PA/PV issues. mySense builds over a 4-layer technological structure: sensor and sensor nodes, crop field and sensor networks, cloud services and support to front-end applications. It makes available a set of free tools based on the Do-It-Yourself (DIY) concept and enables the use of Arduino (R) and Raspberry Pi (RN) low-cost platforms to quickly prototype a complete monitoring application. Field experiments provide compelling evidences that mySense environment represents an important step forward towards Smart Farming, by enabling the use of low-cost, fast deployment, integrated and transparent technologies to increase PA/PV monitoring applications adoption.

Abstract
Authenticity, traceability and certification are key to assure both quality and confidence to wine consumers and an added commercial value to farmers and winemakers. Grapevine variety stands out as one of the most relevant factors to be considered in wine identification within the whole wine sector value chain. Ampelography is the science responsible for grapevine varieties identification based on (i) in-situ visual inspection of grapevine mature leaves and (ii) on the ampelographer experience. Laboratorial analysis is a costly and time-consuming alternative. Both the lack of experienced professionals and context-induced error can severely hinder official regulatory authorities’ role and therefore bring about a significant impact in the value chain. The purpose of this paper is to assess deep learning potential to classify grapevine varieties through the ampelometric analysis of leaves. Three convolutional neural networks architectures performance are evaluated using a dataset composed of six different grapevine varieties leaves. This preliminary approach identified Xception architecture as very promising to classify grapevine varieties and therefore support a future autonomous tool that assists the wine sector stakeholders, particularly the official regulatory authorities. © Springer Nature Switzerland AG 2019.

Abstract
Viticulture has a major impact in the European economy and over the years the intensive grapevine production led to the proliferation of many varieties. Traditionally these varieties are manually catalogued in the field, which is a costly and slow process and being, in many cases, very challenging to classify even for an experienced ampelographer. This article presents a cost-effective and automatic method for grapevine varieties classification based on the analysis of the leaf’s images, taken with an RGB sensor. The proposed method is divided into three steps: (1) color and shape features extraction; (2) training and; (3) classification using Linear Discriminant Analysis. This approach was applied in 240 leaf images of three different grapevine varieties acquired from the Douro Valley region in Portugal and it was able to correctly classify 87% of the grapevine leaves. The proposed method showed very promising classification capabilities considering the challenges presented by the leaves which had many shape irregularities and, in many cases, high color similarities for the different varieties. The obtained results compared with manual procedure suggest that it can be used as an effective alternative to the manual procedure for grapevine classification based on leaf features. Since the proposed method requires a simple and low-cost setup it can be easily integrated on a portable system with real-time processing to assist technicians in the field or other staff without any special skills and used offline for batch classification. © Springer Nature Switzerland AG 2019.

Abstract
Recent studies highlight the ability of inductive architectures to deliver therapeutic magnetic stimuli to target tissues and to be embedded into small-scale intracorporeal medical devices. However, to date, current micro-scale biomagnetic devices require very high electric current excitations (usually exceeding 1 A) to ensure the delivery of efficient magnetic flux densities. This is a critical problem as advanced implantable devices demand self-powering, stand-alone and long-term operation. This work provides, for the first time, a novel small-scale magnetic stimulation system that requires up to 50-fold lower electric current excitations than required by relevant biomagnetic technology recently proposed. Computational models were developed to analyse the magnetic stimuli distributions and densities delivered to cellular tissues during in vitro experiments, such that the feasibility of this novel stimulator can be firstly evaluated on cell culture tests. The results demonstrate that this new stimulative technology is able to deliver osteogenic stimuli (0.1-7 mT range) by current excitations in the 0.06-4.3 mA range. Moreover, it allows coil designs with heights lower than 1 mm without significant loss of magnetic stimuli capability. Finally, suitable core diameters and stimulator-stimulator distances allow to define heterogeneity or quasi-homogeneity stimuli distributions. These results support the design of high-sophisticated biomagnetic devices for a wide range of therapeutic applications.

Abstract
Frequently, the vineyards in the Douro Region present multiple grape varieties per parcel and even per row. An automatic algorithm for grape variety identification as an integrated software component was proposed that can be applied, for example, to a robotic harvesting system. However, some issues and constraints in its development were highlighted, namely, the images captured in natural environment, low volume of images, high similarity of the images among different grape varieties, leaf senescence, and significant changes on the grapevine leaf and bunch images in the harvest seasons, mainly due to adverse climatic conditions, diseases, and the presence of pesticides. In this paper, the performance of the transfer learning and fine-tuning techniques based on AlexNet architecture were evaluated when applied to the identification of grape varieties. Two natural vineyard image datasets were captured in different geographical locations and harvest seasons. To generate different datasets for training and classification, some image processing methods, including a proposed four-corners-in-one image warping algorithm, were used. The experimental results, obtained from the application of an AlexNet-based transfer learning scheme and trained on the image dataset pre-processed through the four-corners-in-one method, achieved a test accuracy score of 77.30%. Applying this classifier model, an accuracy of 89.75% on the popular Flavia leaf dataset was reached. The results obtained by the proposed approach are promising and encouraging in helping Douro wine growers in the automatic task of identifying grape varieties.

Abstract
Unmanned aerial vehicles have become a popular remote sensing platform for agricultural applications, with an emphasis on crop monitoring. Although there are several methods to detect vegetation through aerial imagery, these remain dependent of manual extraction of vegetation parameters. This article presents an automatic method that allows for individual tree detection and multi-temporal analysis, which is crucial in the detection of missing and new trees and monitoring their health conditions over time. The proposed method is based on the computation of vegetation indices (VIs), while using visible (RGB) and near-infrared (NIR) domain combination bands combined with the canopy height model. An overall segmentation accuracy above 95% was reached, even when RGB-based VIs were used. The proposed method is divided in three major steps: (1) segmentation and first clustering; (2) cluster isolation; and (3) feature extraction. This approach was applied to several chestnut plantations and some parameterssuch as the number of trees present in a plantation (accuracy above 97%), the canopy coverage (93% to 99% accuracy), the tree height (RMSE of 0.33 m and R-2 = 0.86), and the crown diameter (RMSE of 0.44 m and R-2 = 0.96)were automatically extracted. Therefore, by enabling the substitution of time-consuming and costly field campaigns, the proposed method represents a good contribution in managing chestnut plantations in a quicker and more sustainable way.