Abstract
Purpose The purpose of this paper is to present a programming by demonstration (PbD) system based on 3D stereoscopic vision and inertial sensing that provides a cost-effective pose tracking system, even during error-prone situations, such as camera occlusions. Design/methodology/approach The proposed PbD system is based on the 6D Mimic innovative solution, whose six degrees of freedom marker hardware had to be revised and restructured to accommodate an IMU sensor. Additionally, a new software pipeline was designed to include this new sensing device, seeking the improvement of the overall system's robustness in stereoscopic vision occlusion situations. Findings The IMU component and the new software pipeline allow the 6D Mimic system to successfully maintain the pose tracking when the main tracking tool, i.e. the stereoscopic vision, fails. Therefore, the system improves in terms of reliability, robustness, and accuracy which were verified by real experiments. Practical implications Based on this proposal, the 6D Mimic system reaches a reliable and low-cost PbD methodology. Therefore, the robot can accurately replicate, on an industrial scale, the artisan level performance of highly skilled shop-floor operators. Originality/value To the best of the authors' knowledge, the sensor fusion between stereoscopic images and IMU applied to robot PbD is a novel approach. The system is entirely designed aiming to reduce costs and taking advantage of an offline processing step for data analysis, filtering and fusion, enhancing the reliability of the PbD system.

Abstract
The seashore is the front door to the oceans and the sustain of many societies. However, humans still seem to be unable to unlock new paradigms to project sustainable growth of marine and coastal ecosystems. One of the reasons for this is the lack of knowledge about the natural processes that systematically change their balance. Thus, a new generation of tools is needed to gather data to validate and predict geostatistical models and protect this important resource. This manuscript reports the design and validation of a multi-parameter marine station installed in the estuary of Cavado - Portugal. For the last two years, the station has hosted several own-developed sensors to monitor water parameters, and it was designed to send the monitoring data, in real-time, to a public website so the information can be shared with the communities. So far, the monitoring station has been able to produce data about hydraulic and environmental dynamics, such as water column height or sediment displacement, as well as seasonal events and other extreme phenomena occurrences such as floods. The proposed monitoring system, built in a low-power and low-cost philosophy, aims to allow massive replication all over the coastal areas and to deliver qualitative and quantitative data for better management and planning of the littoral.

Abstract
Billions of interconnected Internet of Things (IoT) sensors and devices collect tremendous amounts of data from real-world scenarios. Big data is generating increasing interest in a wide range of industries. Once data is analyzed through compute-intensive Machine Learning (ML) methods, it can derive critical business value for organizations. Powerful platforms are essential to handle and process such massive collections of information cost-effectively and conveniently. This work introduces a distributed and scalable platform architecture that can be deployed for efficient real-world big data collection and analytics. The proposed system was tested with a case study for Predictive Maintenance of Home Appliances, where current and vibration sensors with high acquisition frequency were connected to washing machines and refrigerators. The introduced platform was used to collect, store, and analyze the data. The experimental results demonstrated that the presented system could be advantageous for tackling real-world IoT scenarios in a cost-effective and local approach.

Abstract
Despite the important advances observed, nowadays, the Engineering programmes keep being challenged to better prepare their students to work on complex and multidisciplinary projects while demonstrating awareness of environmental and socio-economic issues and other soft skills as communication and teamwork. Recently, to meet these challenges, the ISEP' Informatics Engineering programme (LEI) successfully adopted a project-based learning approach. In this approach, throughout the entire semester, students develop a real-world project that allows the application and assessment of the competencies taught by all course units of the semester in an integrated, multidisciplinary, and transversal way. In this paper, the authors (i) present this approach as well as the main challenges faced in implementing it; (ii) report the major findings and the perceived benefits and drawbacks; and (iii) discuss the ongoing adaptations and/or others seen as required to improve the approach and its results. © CDIO 2022.All rights reserved.

Abstract
The paper presents an innovative application to identify areas vulnerable to coronavirus disease 2019 (COVID-19) considering a combination of spatial analysis and a multi-criteria learning approach. We applied this methodology in the state of Pernambuco, Brazil identifying vulnerable areas by considering a set of determinants and risk factors for COVID-19, including demographic, economic and spatial characteristics and the number of human COVID-19 infections. Examining possible patterns over a set number of days taking the number of cases recorded, we arrived at a set of compatible decision rules to explain the relation between risk factors and COVID-19 cases. The results reveal why certain municipalities are critically vulnerable to COVID-19 high-lighting locations for which knowledge can be gained about envi-ronmental factors.

Abstract
Wide availability of edge computing platforms, as expected in emerging 5G networks, enables a computing continuum between centralized cloud services and the edge of the network, close to end-user devices. This is particularly appealing for online analytics as data collected by devices is made available for decisionmaking. However, cloud-based parallel-distributed data processing platforms are not able to directly access data on the edge. This can be circumvented, at the expense of freshness, with data synchronization that periodically uploads data to the cloud for processing. In this work, we propose an adaptive database synchronization system that makes distributed data in edge nodes available dynamically to the cloud by balancing between reducing the amount of data that needs to be transmitted and the computational effort needed to do so at the edge. This adapts to the availability of CPU and network resources as well as to the application workload.