Abstract

Abstract
Throughout this paper, a competition created to enable an inter-connection between the academic and industrial paradigms is presented, using Open Hardware and Software. This competition is called Robot at Factory Lite and serves as a case study as an additional enrollment for students to apply knowledge in the fields of programming, perception, motion planning, task planning, autonomous robotic, among others. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Abstract
Today, wireless networks are operating in increasingly complex environments, impacting the evaluation and validation of new networking solutions. Simulation, although fully controllable and easily reproducible, depends on simplified physical layer and channel models, which often produce optimistic results. Experimentation is also influenced by external random phenomena and limited testbed scale and availability, resulting in hardly repeatable and reproducible results. Previously, we have proposed the Trace-based Simulation (TS) approach to address the problem. TS uses traces of radio link quality and position of nodes to accurately reproduce past experiments in ns-3. Yet, in its current version, TS is not compatible with scenarios where Multiple-In-Multiple-Out (MIMO) is used. This is especially relevant since ns-3 assumes perfectly independent MIMO radio streams. In this paper, we introduce the Trace-based Wi-Fi Station Manager Model, which is capable of reproducing the Rate Adaptation of past Wi-Fi experiments, including the number of effective radio streams used. To validate the proposed model, the network throughput was measured in different experiments performed in the w-iLab.t testbed, considering Single-In-Single-Out (SISO) and MIMO operation using IEEE 802.11a/n/ac standards. The experimental results were then compared with the network throughput achieved using the improved TS and Pure Simulation (PS) approaches, validating the new proposed model and confirming its relevance to reproduce experiments previously executed in real environments.

Abstract
Privacy is becoming a crucial requirement in many machine learning systems. In this paper we introduce an efficient and secure distributed K-Means algorithm, that is robust to non-IID data. The base idea of our proposal consists in each client computing the K-Means algorithm locally, with a variable number of clusters. The server will use the resultant centroids to apply the K-Means algorithm again, discovering the global centroids. To maintain the client's privacy, homomorphic encryption and secure aggregation is used in the process of learning the global centroids. This algorithm is efficient and reduces transmission costs, since only the local centroids are used to find the global centroids. In our experimental evaluation, we demonstrate that our strategy achieves a similar performance to the centralized version even in cases where the data follows an extreme non-IID form.

Abstract
Automatic medical image segmentation via convolutional neural networks (CNNs) has shown promising results. However, they may not always be robust enough for clinical use. Sub-optimal segmentation would require clinician's to manually delineate the target object, causing frustration. To address this problem, a novel interactive CNN-based segmentation framework is proposed in this work. The aim is to represent the CNN segmentation contour as B-splines by utilising B-spline explicit active surfaces (BEAS). The interactive element of the framework allows the user to precisely edit the contour in real-time, and by utilising BEAS it ensures the final contour is smooth and anatomically plausible. This framework was applied to the task of 2D segmentation of the levator hiatus from 2D ultrasound (US) images, and compared to the current clinical tools used in pelvic floor disorder clinic (4DView, GE Healthcare; Zipf, Austria). Experimental results show that: 1) the proposed framework is more robust than current state-of-the-art CNNs; 2) the perceived workload calculated via the NASA-TLX index was reduced more than half for the proposed approach in comparison to current clinical tools; and 3) the proposed tool requires at least 13 s less user time than the clinical tools, which was significant (p = 0.001).

Abstract
Text mining (TM) is a semi-automatized, multi-step process, able to turn unstructured into structured data. TM relevance has increased upon machine learning (ML) and deep learning (DL) algorithms’ application in its various steps. When applied to biomedical literature, text mining is named biomedical text mining and its specificity lies in both the type of analyzed documents and the language and concepts retrieved. The array of documents that can be used ranges from scientific literature to patents or clinical data, and the biomedical concepts often include, despite not being limited to genes, proteins, drugs, and diseases. This review aims to gather the leading tools for biomedical TM, summarily describing and systematizing them. We also surveyed several resources to compile the most valuable ones for each category. © 2021 by the authors.