Abstract
This paper proposes a methodology to detect early signs of Parkinson's disease (PD) through free-speech in uncontrolled background conditions. The early detection mechanism uses signal and speech processing techniques integrated with machine learning algorithms. Three distinct speech databases containing patients' recordings at different stages of the PD are used for estimation of the parameters during the training and evaluation stages. The results reveal the potential in using Random Forest (RF) or Support Vector Machine (SVM) techniques. Once tuned, these algorithms provide a reliable computational method for estimating the presence of PD with a very high accuracy.

Abstract
Wine counterfeiting is a major problem worldwide. Within this context, an approach to the problem of discerning original wine bottles from forged ones is the use of natural features present in the product, object and/or material (using it "as is"). The proposed application uses the cork stopper as a unique fingerprint, combined with state of the art image processing techniques to achieve individual object recognition and smartphones as the authentication equipment. The anti-counterfeiting scheme is divided into two phases: an enrollment phase, where every bottle is registered in a database using a photo of its cork stopper inside the bottle; and a verification phase, where an end-user/retailer captures a photo of the cork stopper using a regular smartphone, compares the photo with the previously-stored one and retrieves it if the wine bottle was previously registered. To evaluate the performance of the proposed application, two datasets of natural/agglomerate cork stoppers were built, totaling 1000 photos. The worst case results show a 100% precision ratio, an accuracy of 99.94% and a recall of 94.00%, using different smartphones. The perfect score in precision is a promising result, proving that this system can be applied to the prevention of wine counterfeiting and consumer/retailer security when purchasing a wine bottle.

Abstract
The use of Robotics as a teaching tool to foster knowledge in Science, Technology, Engineering and Mathematics - STEM for high school students is growing. Within this context, the need for solutions that decreases the overall cost of hardware is mandatory. In this work, a 25 euros Android-based mobile robot that allows connecting a smartphone to different robot "bodies" (each composed by different hardware: Arduino, LEGO, etc.) is proposed, targeting mainly high school students. The mobile platform was built using 3D printed parts and uses an Arduino board to control the servos used for the locomotion. To communicate with the Android application, a Bluetooth module is also used. The Android application takes advantage of the smartphone camera and has some pre-implemented image processing modules, allowing actions such as coloured line following, colour proximity detection and coloured object tracking. Another import feature present in the Android application is its coding capability, thanks to an embedded code interpreter. This feature was implemented using BeanShell, a lightweight script interpreter for Java. It allows writing scripts in Java programming language, which are then executed by the robot. This interpreter also provides a way for the user to write a set of instructions that defines the behaviour of the robot, primarily by checking the current status of the sensors and the smartphone camera, and manipulating the velocity of the motors. All of the necessary components (3D source CAD + STLs) of the mobile platform presented here are available online, enabling the recreation of a replica of the robot body. A detailed list of electronic components and its connections are also provided, as well as the Arduino source code along with the installation file needed for the Android application. All the necessary information can be accessed at: https://github.com/ee09115/squirlrob. The high school students are then challenged to solve classical robotics tasks like line following, obstacle avoidance, and using the virtual sensors to create new challenges. By providing this set of tools (Android app, source code, 3D CAD models, documentation), a promotion of knowledge is expected, thus developing enthusiast students in robotics multidisciplinary fields, such as mechanical designing, electronics designing, mathematics, coding, etc. (in short, all the relevant STEM areas). Finally, a general analysis of the usability, interoperability and feature extension capacity is made, always taking into consideration the educational purposes of this work.

Abstract
The purpose of this work is to explore the design principles for a Real-Time Robotic Multi Camera Vision System, in a case study involving a real world competition of autonomous driving. Design practices from vision and real-time research areas are applied into a Real-Time Robotic Vision application, thus exemplifying good algorithm design practices, the advantages of employing the "zero copy one pass" methodology and associated trade-offs leading to the selection of a controller platform. The vision tasks under study are: (i) recognition of a "flat" signal; and (ii) track following, requiring 3D reconstruction. This research firstly improves the used algorithms for the mentioned tasks and finally selects the controller hardware. Optimization for the shown algorithms yielded from 1.5 times to 190 times improvements, always with acceptable quality for the target application, with algorithm optimization being more important on lower computing power platforms. Results also include a 3-cm and five-degree accuracy for lane tracking and 100% accuracy for signalling panel recognition, which are better than most results found in the literature for this application. Clear results comparing different PC platforms for the mentioned Robotic Vision tasks are also shown, demonstrating trade-offs between accuracy and computing power, leading to the proper choice of control platform. The presented design principles are portable to other applications, where Real-Time constraints exist.

Abstract
Planning the optimal assembly and disassembly sequence plays a critical role when optimizing the production, maintenance and recycling of products. For tackling this problem, a recursive branch-and-bound algorithm was developed for finding the optimal disassembly plan. It takes into consideration the traveling distance of a robotic end effector along with a cost penalty when it needs to be changed. The precedences and part decoupling directions are automatically computed in the proposed geometric reasoning engine by analyzing the spatial relationships present in SolidWorks assemblies. For accelerating the optimization process, a best-first search algorithm was implemented for quickly finding an initial disassembly sequence solution that is used as an upper bound for pruning most of the non-optimal tree branches. For speeding up the search further, a caching technique was developed for reusing feasible disassembly operations computed on previous search steps, reducing the computational time by more than 18%. As a final stage, our SolidWorks add-in generates an exploded view animation for allowing intuitive analysis of the best solution found. For testing our approach, the disassembly of two starter motors and a single cylinder engine was performed for assessing the capabilities and time requirements of our algorithms. © 2018 IEEE.

Abstract
Replanning is often used to optimize results of an activity in an ever changing world. To address the challenge of preparing future engineers for success, a special course was created for all engineering freshmen of the Faculty of Engineering of the University of Porto, in Portugal. Presented as a case study, this special course underwent a careful replanning as a result of several years of experience in teaching practice alongside with a theoretical deepening in pedagogical and technological issues, under the aegis of the action-research methodology. Within the context of the case study course, the mentioned replanning was also based on a theoretical approach that clearly identifies teaching-learning-assessment methodologies that promote regulation from those that foster emancipation, using a specific instrument: a taxonomy of educational processes. The replanning was designed to globally boost results regarding the educational aims of the course such as furthering freshmen's integration into work environment and preparing them for success by fostering transversal skills (needed for study and work). Technology is seen as a mean of education enrichment as well as a productivity tool. The introduced innovations include fun-but-educational activities, several types of assessment over time and specific technological tools which were critical for the educational impact/achievement of this course. Success is demonstrated by encouraging feedback from the stakeholders, high students' classifications and a steady reduction in retention. It is advocated that large portions of the reasoning behind the replanning can be extrapolated to other courses.