Abstract
Surgical training for minimal invasive kidney interventions (MIKI) has huge importance within the urology field. Within this topic, simulate MIKI in a patient-specific virtual environment can be used for pre-operative planning using the real patient's anatomy, possibly resulting in a reduction of intra-operative medical complications. However, the validated VR simulators perform the training in a group of standard models and do not allow patient-specific training. For a patient-specific training, the standard simulator would need to be adapted using personalized models, which can be extracted from pre-operative images using segmentation strategies. To date, several methods have already been proposed to accurately segment the kidney in computed tomography (CT) images. However, most of these works focused on kidney segmentation only, neglecting the extraction of its internal compartments. In this work, we propose to adapt a coupled formulation of the B-Spline Explicit Active Surfaces (BEAS) framework to simultaneously segment the kidney and the renal collecting system (CS) from CT images. Moreover, from the difference of both kidney and CS segmentations, one is able to extract the renal parenchyma also. The segmentation process is guided by a new energy functional that combines both gradient and region-based energies. The method was evaluated in 10 kidneys from 5 CT datasets, with different image properties. Overall, the results demonstrate the accuracy of the proposed strategy, with a Dice overlap of 92.5%, 86.9% and 63.5%, and a point-to-surface error around 1.6 mm, 1.9 mm and 4 mm for the kidney, renal parenchyma and CS, respectively. © 2018 IEEE.

Abstract

Abstract
Production scheduling in the presence of real-time events is of great importance for the successful implementation of real-world scheduling systems. Most manufacturing systems operate in dynamic environments vulnerable to various stochastic real-time events which continuously forces reconsideration and revision of pre-established schedules. In an uncertain environment, efficient ways to adapt current solutions to unexpected events, are preferable to solutions that soon become obsolete. This reality motivated us to develop a tool that attempts to start filling the gap between scheduling theory and practice. The developed prototype is connected to the MRP software and uses meta heuristics to generate a predictive schedule. Then, whenever disruptions happen, like arrival of new tasks or cancelation of others, the tool starts rescheduling through a dynamic-event module that combines dispatching rules that best fit the performance measures pre-classified by Kano’s model. The proposed tool was tested in an in-depth computational study with dynamic task releases and stochastic execution time. The results demonstrate the effectiveness of the model. © 2020, Springer Nature Switzerland AG.

Abstract
An early detection of neurodegenerative diseases, such as Parkinson’s disease, can improve therapy effectiveness and, by consequence, the patient’s quality of life. This paper proposes a new methodology for automatic classification of voice samples regarding the presence of acoustic patterns of Parkinson’s disease, using a deep structured neural network. This is a low cost non-invasive approach that can raise alerts in a pre-clinical stage. Aiming to a higher diagnostic detail, it is also an objective to accurately estimate the stage of evolution of the disease allowing to understand in what extent the symptoms have developed. Therefore, two types of classification problems are explored: binary classification and multiclass classification. For binary classification, a deep structured neural network was developed, capable of correctly diagnosing 93.4% of cases. For the multiclass classification scenario, in addition to the deep neural network, a K-nearest neighbour algorithm was also used to establish a reference for comparison purposes, while using a common database. In both cases the original feature set was optimized using principal component analysis and the results showed that the proposed deep structure neural network was able to provide more accurate estimations about the disease’s stage, reaching a score of 84.7%. The obtained results are promising and create the motivation to further explore the model’s flexibility and to pursue better results. © 2020, Springer Nature Switzerland AG.

Abstract
With the recent development of weblogs and social networks, many supplier industries share their data on different websites and weblogs. Even the Small-to-Medium sized enterprises (SMEs) in the manufacturing sector (as well as non-manufacturing sector) are rapidly strengthening their web presence in order to improve their visibility, customer reachability and remain competitive in the global market. Our study aims to classify data into various groups so that users can identify the most appropriate content based on their choice at any given time. To classify and characterize manufacturing suppliers in supply chain through their capability narratives and textual portfolios obtained from websites of such suppliers online source portals for testing and Naive Bayes and support vector machine (SVM) Classification method at term-level for classification has been used. The performance of the proposed classifier was tested experimentally based on the standard metrics such as precision, recall, and F-measure.

Abstract
Recent studies have shown that the early detection of neurodegenerative diseases (such as Parkinson) can significantly improve the effectiveness of treatments that increase quality of life, reducing the costs associated with the disease. In this paper, the proposed methodology consists in detecting early signs of Parkinson's disease through speech, with the presence of background noise. The approach uses machine learning algorithms and signal processing techniques to correctly distinguish between healthy controls and Parkinson's disease patients. In order to detect early signs of the disease, a database with patients at different stages of the Parkinson's disease is used. The learning algorithms were optimized for generalization and accuracy. An analysis of the results obtained from the proposed methodology show potential uses of machine learning algorithms in biomedical applications to detect early signs of Parkinson's disease.