Abstract

Abstract
The most current forecasts point to a decrease in the amount of potable water available. This increase in water scarcity is a problem with which sustainable agricultural production is facing. This has led to an increasing search for technical solutions in order to improve the efficiency of irrigation systems. In this context, this work describes the architecture of an agent-based network and the cyberphysical elements which will be deployed in a strawberry fertigation production plant. The operation of this architecture relies on local information provided by LoRA based wireless sensor network that is described in this paper. Using the information provided by the array of measurement nodes, cross-referenced with local meteorological data, grower experience and the actual crop vegetative state, it will be possible to better define the amount of required irrigation solution and then to optimise the water usage. © Springer Nature Switzerland AG 2019.

Abstract
Tawny Port wine is a category of the famous Portuguese fortified wine commercialized worldwide and produced in the Douro Demarcated Region. Tawny Port wine oxidative aging is a multifactorial process critical for reaching the wanted quality. Real time monitoring of important intrinsic and extrinsic factors that are known to affect both time and quality of the aging process are important to optimize and to manage the natural variability between wines aged in different long-used wood barrels. This study presents the design, development and implementation of a remote distributed system to monitor parameters that are known to be critical for Tawny Port wine aging process. Results indicate that the distributed monitoring system was capable to detect differences between oak wood barrels and between the different storage conditions. Indeed, oxygen and redox potential were the wine's parameters where the differences found between different barrels were greater under the same storage conditions. Considering that Tawny Port wine aging process is oxidative, a variation in the wine's aging process between different wood barrels is to be expected. Actually, significant differences were detected in the oxygen consumption rate amongst the different barrels. Differences in the phenolic composition was also observed in the aged wine (controlled temperature and room temperature).

Abstract
This work aims to develop an embedded system and mobile application within Internet of Things (IoT) context, which allow the evaluation of control techniques widely used in the industry, for both remote configuration and monitoring of environment inside storage silos in laboratory scale. The developed system contributes to the validation of the recent released KNoT meta platform and extends its application to agricultural area. Preliminary results for on-off and PID temperature control suggest its feasibility for remote transmission of setpoint data to local controllers and data acquisition for monitoring by a mobile application. © Springer Nature Switzerland AG 2019.

Abstract
This book presents, in an integrated form, both the analysis and synthesis of three different types of hidden Markov models. Unlike other books on the subject, it is generic and does not focus on a specific theme, e.g. speech processing. Moreover, it presents the translation of hidden Markov models’ concepts from the domain of formal mathematics into computer codes using MATLAB®. The unique feature of this book is that the theoretical concepts are first presented using an intuition-based approach followed by the description of the fundamental algorithms behind hidden Markov models using MATLAB®. This approach, by means of analysis followed by synthesis, is suitable for those who want to study the subject using a more empirical approach.

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.