Search

Hypoglycemia is a common occurrence in critically ill patients and is associated with significant mortality and morbidity. We developed a machine learning model to predict hypoglycemia by using a multicenter intensive care unit (ICU) electronic health record dataset. Machine learning algorithms were trained and tested on patient data from the publicly available eICU Collaborative Research Database. Forty-four features including patient demographics, laboratory test results, medications, and vitals sign recordings were considered. The outcome of interest was the occurrence of a hypoglycemic event (blood glucose

The papers in this special section focus on recent developments and emerging topics in the area of deep fuzzy models that address some of the problems and limitations above. These models have been known under different names, such as hierarchical fuzzy systems and fuzzy networks. They are usually well suited for performing multiple functional compositions at either crisp or linguistic level. Deep learning has gained significant attention within the computational intelligence community in recent years. Its success has been mainly due to the increased power of modern computational platforms in terms of their ability to collect, store, and process large volumes of data. This has led to a substantial increase in the effectiveness and efficiency of data management. As a result, it has become possible to achieve high accuracy for some benchmark learning tasks, such as object classification and image recognition within a short time frame. The most common implementation of deep learning has been through neural networks due to the ability of their layers of neurons to perform multiple functional compositions as part of a multistage learning process.

The majority of opportunities to energy savings today and in the next decades are in the existing building stock, including commercial and retail ones. These are constrained by old equipment, aging infrastructure, and inadequate operations resources. In particular, we focus on a retail store located in Lisbon, El Corte Ingles, to reduce its electricity consumption while maintaining the same level of service and continuing to be a profitable business. Improving the operation of the air-handling unit (AHU) and the operation schedule of floors illumination is our focus. Data provided had long-term records of variables as the building power consumption, exterior temperature, solar irradiation, elevators, and HVAC system. Two artificial neural networks (ANN) models were developed to predict the building power consumption and indoor average temperature, which allowed verifying the impact of small variations in the AHU electricity consumption. We deal both with the indoor average temperature (comfort) and power consumption of AHU to reduce the electric energy cost. The study leads to a decrease of 9.6% of the total electricity consumption, with an average indoor temperature increasing by only 0.15 °C. The total potential savings considering all the building 48 AHUs resulted in very good savings of 34,000 euros per year.

A digital twin of a pharmaceutical company’s internal supply chain is presented, along with a simulation-based rough cut capacity planning tool capable of giving estimates of the required monthly capacity for the different areas of the organization on the long-term. The work was a case study performed at a pharmaceutical company. The digital twin is delivered through a graphical user interface containing both its visualization and simulation tools. The proposed digital twin supplies accurate estimates of capacity needs to supply chain managers, giving the ability to easily visualize the resources required from different involved areas in the following 24 months.

In this paper, a new approach to the usage of 0-order Autonomous Learning Multi-Model (ALMMo-0) classifiers is proposed. ALMMo-0 classifiers are fully automatic and do not rely on any hyper-parameters. The creation of clouds relies on normalizing data points by their norm, which may remove an important degree of freedom from the data itself. The proposed approach consists of adding the initial radius of the clouds as an hyper-parameter, which makes it possible to skip the normalization step. This approach requires the search for the ideal value of the hyper-parameter. This way, upon training a set of models with different values for the initial radius, the user is expected to be able to choose from several models which range from more accurate to less complex. This approach was tested on three benchmark problems and compared to the results obtained using the original approach. Furthermore, this approach was also tested on a real dataset (Acute Kidney Injury). The obtained results enhance the versatility provided by the proposed method, successfully allowing the user to choose the model that fits better the design demands regarding accuracy, training time, and complexity.

ObjectiveGastrointestinal (GI) bleeding commonly requires intensive care unit (ICU) in cases of potentialhaemodynamiccompromise or likely urgent intervention. However, manypatientsadmitted to the ICU stop bleeding and do not require further intervention, including blood transfusion. The present work proposes an artificial intelligence (AI) solution for the prediction of rebleeding in patients with GI bleeding admitted to ICU.MethodsA machine learning algorithm was trained and tested using two publicly available ICU databases, the Medical Information Mart for Intensive Care V.1.4 database and eICU Collaborative Research Database using freedom from transfusion as a proxy for patients who potentially did not require ICU-level care. Multiple initial observation time frames were explored using readily available data including labs, demographics and clinical parameters for a total of 20 covariates.ResultsThe optimal model used a 5-hour observation period to achieve an area under the curve of the receiving operating curve (ROC-AUC) of greater than 0.80. The model was robust when tested against both ICU databases with a similar ROC-AUC for all.ConclusionsThe potential disruptive impact of AI in healthcare innovation is acknowledge, but awareness of AI-related risk on healthcare applications and current limitations should be considered before implementation and deployment. The proposed algorithm is not meant to replace but to inform clinical decision making. Prospective clinical trial validation as a triage tool is warranted.

As the industry continues to pursue the reduction of downtimes and increases in the efficiency of resource usage, data appears as a valuable business asset, empowering intelligent automation solutions. In order to deal with current challenges in acquisition and management of data in industrial settings, this paper proposes a framework for intelligent automation. The traditional automation pyramid does not cope with today’s application requirements, as intelligent automation needs to exchange, in realtime, information with all layers of the pyramid, simultaneously. The middleware for intelligent automation provides interoperability through integration software along with cloud functionalities and big data warehousing. The middleware also provides decentralization by connecting to remote decision support systems. This paper presents two real implementation examples of the framework in the wood and the chemical industry. The framework successfully addresses the requirements of key intelligent automation features and data characteristics, supporting the development of support decision systems into automation modules.

Funding Acknowledgements Type of funding sources: None. Introduction Adverse hemodynamic effects of right ventricular pacing are known, and the optimal right ventricular lead position is still being a matter of debate. According to the guidelines, upgrade to cardiac resynchronization therapy (CRT) is recommended in patients with indication for pacemaker and left ventricular ejection fraction less than 50% or who need more than 40% of ventricular pacing. Purpose To compare clinical outcomes and ejection fraction in patients with previous pacemaker (apical versus septal right ventricular pacing) who are upgrated to CRT. Methods Single-center retrospective study of 94 consecutive patients who had previous pacemaker and upgraded to CRT over a 4-year period. Of these patients, 64 had previous apical lead pacemaker and 30 had previous septal lead pacemaker. Data on comorbidities, New York Heart Association (NYHA), left ventricular ejection fraction and hospitalizations due to heart failure were collected. The results were obtained using Chi-square, Mann-Whitney and t-test. Results Patients with septal pacemaker had significantly more diabetes (p = 0.04) and chronic obstructive pulmonary disease (p = 0.01), tended to be more symptomatic (p = 0.198) and had more days of hospitalization before and after pacemaker implantation (12 ± 3 versus 7 ± 2 days and 8 ± 4 versus 3 ± 1 days, respectively), mostly due heart failure decompensation. Although there were no significant differences in the initial ejection fraction in patients with apical or septal pacemaker implantation (31.2 ± 1.2% and 29.1 ± 1.5%, respectively, p = 0.323), the time to upgrade to CRT was significantly shorter in patients with septal pacemaker implantation (1999 ± 227 days versus 3005 ± 279 days, p = 0.005). After upgrading to CRT, patients with apical lead had a significant increase in ejection fraction (8.2%, p = 0.011), while patients with septal lead had a non-significant improvement of ejection fraction (4.5%, p = 0.448). In both, apical and septal lead patients, there was a significant improvement in NYHA class after upgrade to CRT (p = 0.03 and p = 0.02, respectively). Conclusion Although patients with septal lead had more comorbidities and hospitalizations due to heart failure, they do not benefit from the upgrade to CRT, unlike what happens in patients with apical lead. These findings can be explained by the fact that the septal lead minimizes ventricular desynchrony induced by right ventricular pacing.

Aquaculture is one of the fastest-growing activities worldwide. This strong and rapid development of the sector tends to be reflected in significant environmental impacts and new challenges in the management of the coastal areas. In this context, this work intends to contribute to the sustainability of the sector, by proposing an innovative method to identify preferred locations to ensure sustainable expansion of fish and mussels aquaculture, under optimal hydrodynamic and water quality conditions in Ria de Aveiro (Portugal) and Rias Baixas (Spain). A habitat model was developed, integrating hydrodynamic and water quality modelling results into a suitability index based on the definition of variable suitability functions. The results show that 22% of Ria de Aveiro is very good for fish production. In contrast, the production of pelagic fish in Rias Baixas is not recommended due to vertical gradients of water temperature and seasonal events of hypoxia. Concerning to mussels, the habitat model classifies 31% of Ria de Aveiro area as very good for production, while most of the Rias Baixas area presents this highest classification, confirming the high exploitation of the region. The definition of appropriate areas for aquaculture exploitation is highly related with the different geomorphological, hydrological and biogeochemical processes of Ria de Aveiro and Rias Baixas. Results for Ria de Aveiro indicate that the upstream areas are the most vulnerable from the water quality point of view, highlighting the importance of the advective processes in the lagoon's water quality, in opposition to Rias Baixas dynamics, where stratification is more relevant. In Rias Baixas, the strong vertical gradient of water temperature and dissolved oxygen prevents fish from having sustainable growth rates. Therefore, this work demonstrated the potential of the proposed method based on hydrodynamic and biogeochemical modelling to support the decision-making process in planning aquaculture expansion.

This work was financed by the Operational ProgramMar2020 MAR02.01.01-FEAMP-0052 “Newcumber - Avanços para o cultivo sustentavel ´ de pepinos do mar”. It received further financial support from Fundaçao ˜ para a Ciˆencia e Tecnologia (project UIDB/04292/2020 and A.C. Brito with the Scientific Stimulus Programme – CEECIND/00095/ 2017). The intensive exploitation of sea cucumbers, mainly exported to Asian seafood markets, has contributed to deplete natural populations of several species. In Europe, the aquaculture production of these echinoderms is minimal, reflecting the low scientific production on the topic. In Portugal, like in Mediterranean countries, there are native species with high commercial value, which can be potential candidates for aquaculture. The control over the reproductive cycle is an important tool for rearing success, which, in turn, decreases the pressure over natural stocks. However, there are very few studies on the larval development of European species and none on the broodstock maturation in captivity. The present work studied the influence of three diets on the gonadal maturation and larval viability and development of Holothuria mammata. After 120-days of captivity the broodstock groups fed with a mixture of live microalgae (Diet 2) and a mixture of live microalgae and extruded dry food (Diet 3) reached the spawning stage, in contrast to the group fed with a mixture of frozen microalgae (Diet 1). Spawning was induced by thermal shock. Larval rearing from broodstock fed on Diet 2, total mortality was observed on the 12th day, after the onset of mid auricularia stage. The stocks of larvae from the broodstocks fed diets 1 and 3 reached the stage of pentactula on the 27th day. The success in spawning induction and embryonic development suggest that H. mammata may accept different types of diets as frozen microalgae mixes or live microalgae and dry feeds and still produce viable offspring. However, it is essential to develop more studies on the reproductive biology of H. mammata to optimize the hatcheries techniques to broodstock conditioning and larval rearing in captivity. info:eu-repo/semantics/publishedVersion

Analysis of real-world glucose and insulin clinical data recorded in electronic medical records can provide insights into tailored approaches to clinical care, yet presents many analytic challenges. This work makes publicly available a dataset that contains the curated entries of blood glucose readings and administered insulin on a per-patient basis during ICU admissions in the Medical Information Mart for Intensive Care (MIMIC-III) database version 1.4. Also, the present study details the data curation process used to extract and match glucose values to insulin therapy. The curation process includes the creation of glucose-insulin pairing rules according to clinical expert-defined physiologic and pharmacologic parameters. Through this approach, it was possible to align nearly 76% of insulin events to a preceding blood glucose reading for nearly 9,600 critically ill patients. This work has the potential to reveal trends in real-world practice for the management of blood glucose. This data extraction and processing serve as a framework for future studies of glucose and insulin in the intensive care unit., Measurement(s) Blood Glucose • insulin (human) Technology Type(s) glucose analyzer • glucometer • Electronic Medical Record Factor Type(s) glucose readings • insulin inputs Sample Characteristic - Organism Homo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.13564187

This paper proposes a flexible manufacturing system based on intelligent computational agents. A Multi-Agent System composed of 4 types of reactive agents was designed to control the operation of a real implementation in the Intelligent Automation Lab at Instituto Superior Tecnico. This implementation was based and constructed analogously to a known benchmark, AIP-PRIMECA. The agents were modelled using Petri nets and agent communications were defined through the combination of FIPA Interaction Protocols. The system was tested under the conditions of static and dynamic scenarios, having its performance validated whenever possible by comparison with results from a Potential Fields Approach in the same benchmark. Overall, the performance exhibited by the proposed MAS was slightly better and it is worth highlighting the simple behaviour of each agent and ability to respond in real-time to all the dynamic scenarios tested.

Introduction Cardiac resynchronization therapy (CRT) significantly reduces mortality and hospitalizations in patients with heart failure and reduced ejection fraction (EF). Atrial fibrillation (AF) is a very common comorbidity in these patients, however, CRT benefit in AF patients has been controversial. Purpose To compare the prognostic impact of CRT in patients (pts) with and without AF. Methods Prospective, single-center study that included pts undergoing CRT implantsince 2015. Clinical and echocardiographicevaluation were made before CRT implant and between 6-12 months post-implant. Pts with EF elevation ≥10% or LV end-systolic volume (ESV) reduction ≥15% were classified as responders. Patients with EF elevation ≥ 20% or ESV reduction ≥30% were classified as super-responders. All the parameters were compared between patients with and without AF.Prognostic impact of CRT was evaluated by comparing total mortality using the Cox regression and Kaplan-Meier methods. Results From 2015-2019, 566 CRTs were implanted (26.1% female, 72 ± 10.2 years old, follow-up duration 18.9 ± 15.8 months). From these patients, 166 patients (31%) had AF (73.5% males, mean age 72.2 ± 10.2 years, 37.3% ischemic, LVEF < 30% in 65.5%). The cardiovascular risk factors and comorbidities were similar in both populations (with and without AF), except for chronic kidney disease which was more frequent in AF pts(28% vs 17%, p = 0.012). The prevalence of complications and surgical revision were similar in both groups. The CRT response rate was similar in both groups (50% in AF group vs 59.6%, p = NS) as was the super-response rate (22.4% in FA pts vs 31.5%, p = NS). The 4-year survival rate of patients with AF was similar to non-AF (83.7% vs 84.3%). Conclusion Despite the controversy about the efficacy of CRT in AF pts, in our population the long-term survival and CRT response rates were comparable between patients with and without AF. Abstract Figure.

UID/CEC/50021/2019. Grant: FCT/MCTES TUBITAK/0008/2014 FCT/DAAD - 2018/2019 (Poc. DAAD 441.00). UID/EMS/50022/2019. project TIN2015-73566-JIN and by the Consellería de Cultura, Educación e Ordenación Universitaria (accreditation 2016–2019, ED431G/08 and reference competitive group 2019–2021, ED431C 2018/29) and the European Regional Development Fund (ERDF). The control logic underlying building automation systems has consisted, traditionally, of embedded discrete programs created using either low-level or proprietary scripting languages, or using general purpose fourth-generation visual languages like Simulink. It is also well known that programs developed in this way are hard to evolve, test, and maintain. These difficulties are intensified when continuous control problems have to be tackled or when the actuation must vary continually subject to the sensor inputs. Such is the case in day-lighting or occupancy-based control applications. In this paper, we propose a declarative high-level Domain-Specific Language that aims to reduce the effort required to specify the control logic of building automation systems. Our language combines fuzzy logic and temporal logic, enabling to define the behaviour in terms of domain abstractions. Finally, the approach has been validated in two ways: (i) in a case study that simulates the control system of an automated office room and (ii) by means of an empirical study to confirm usability (with a System Usability Scale questionnaire) and effectiveness, here regarded from the perspective of correctness, of the proposed language with respect to a well-known language like Simulink. authorsversion published

https://onlinelibrary.wiley.com/doi/abs/10.1111/are.15007 This work was financed by the Operational Program Mar2020 nº MAR-02.01.01-FEAMP-0052 ‘Newcumber - Avanços para o cultivo sustentável de pepinos-do-mar'. It received further financial support from Fundação para a Ciência e a Tecnologia (project UIDB/04292/2020). A.C. Brito was also supported by Fundação para a Ciência e a Tecnologia, through the FCT Investigator (IF/00331/2013) and Scientific Employment Stimulus Programmes (CEECIND/00095/2017). This work was financed by the Operational Program Mar2020 nº MAR-02.01.01-FEAMP-0052 ‘Newcumber - Avanços para o cultivo sustentável de pepinos-do-mar'. It received further financial support from Fundação para a Ciência e a Tecnologia (project UIDB/04292/2020). A.C. Brito was also supported by Fundação para a Ciência e a Tecnologia, through the FCT Investigator (IF/00331/2013) and Scientific Employment Stimulus Programmes (CEECIND/00095/2017). The high demand of sea cucumbers in international markets, mostly based in Asia, has left a deep impact on the natural stock of many species, leading to an investment in aquaculture techniques in order to mitigate these impacts. This study aimed to determine the effects of stock density in rearing broodstock of Holothuria (Panningoturia) forskali Delle Chiaje, 1823, a common species in the Mediterranean Sea and eastern Atlantic with commercial value. To do so, two different density treatments were selected: 1 kg/m2 and 2 kg/m2. The trial took place over five months and individuals were fed a mixture of frozen microalgae (Tetraselmis sp. and Phaeodactylum tricornutum). At the end of the trial, the effects of stock density on the individuals’ condition were assessed by analysing different variables, namely their fresh and gutted weight, evisceration and mortality rates, gonadosomatic index and oocyte size and even biochemical content, such as protein and lipid content in muscle bands. No significant differences were found between density treatments regarding any of the parameters assessed, aside from mean oocyte diameter. Individuals from the lower-density treatment presented a smaller mean oocyte diameter, supplied with fewer oocytes, than individuals in both the higher-density treatment and the baseline group. Regardless of this one difference, all trial individuals were able to maintain their elevated gonadal developmental stage for a full period of five months past their reproductive peak, with female holothurians subjected to the higher-density treatment showing signs of increasing vitellogenic reserves, a considerable advantage in aquaculture broodstock rearing. info:eu-repo/semantics/publishedVersion

Picado, A.; Oliveira, V.; Pereira, H.; Sousa, M.C.; Costa, L.; Almeida, A., and Dias, J.M., 2020. Assessing the potential of Minho and Lima estuaries for aquaculture. In: Malvarez, G. and Navas, F. (eds.), Global Coastal Issues of 2020. Journal of Coastal Research, Special Issue No. 95, pp. 148-152. Coconut Creek (Florida), ISSN 0749-0208.This work aims the identification of the best potential areas to develop aquaculture activities in Minho and Lima estuaries, especially for the species with the highest commercial value. The Analytic Hierarchy Process (AHP) methodology was applied to the results of an annual simulation with Delft3D model (including the hydrodynamic and water quality modules). After, each variable used in AHP was crossed with the environmental thresholds for development/growth of one bivalve (Portuguese Oyster) and one fish (Gilthead Seabream) species. In this way, an Exploration Index (EI) was defined in order to identify the most suitable regions according to water biophysical properties. This EI was mapped for both estuaries and results show that, in general, the low and middle estuaries present the best conditions for aquaculture development of bivalve and fish. In addition, the upper areas of both estuaries are unsuitable for aquaculture, due to the low salinity of these regions.

The development of dynamic data-based Decision Support Systems (DSSs) along with the increasing availability of data in the industry, makes real-time data acquisition and management a challenge. Intelligent automation appears as a holistic combination of automation with analytics and decisions made by artificial intelligence, delivering smart manufacturing and mass customization while improving resource efficiency. However, challenges towards the development of intelligent automation architectures include the lack of interoperability between systems, complex data preparation steps, and the inability to deal with both high-frequency and high-volume data in a timely fashion. This paper contributes to industrial frameworks focused on the development of standardized system architectures for Industry 4.0, closing the gap between generic architectures and physical realizations. It proposes a platform for intelligent automation relying on a gateway or middleware between field devices, enterprise databases, and DSSs in real-time scenarios. This is achieved by providing the middleware interoperability, determinism, and automatic data structuring over an industrial communication infrastructure such as the OPC UA Standard over Time Sensitive Networks (TSN). Cloud services and database warehousing used to address some of the challenges are handled using fog computing and a multi-workload database. This paper presents an implementation of the platform in the pharmaceutical industry, providing interoperability and real-time reaction capability to changes to an industrial prototype using dynamic scheduling algorithms.

This article presents a model for courier services designed to guide a fleet of vehicles over a dynamic set of requests. Motivation for this problem comes from a real-world scenario in an ever-changing environment, where the time to solve such optimization problem is constrained instead of endlessly searching for the optimal solution. First, a hybrid method combining Ant Colony Optimization with Local Search is proposed, which is used to solve a given static instance. Then, a framework to handle and adapt to dynamic changes over time is defined. A new method pairing nearest neighbourhood search with subtractive clustering is proposed to improve initial solutions and accelerate the convergence of the optimization algorithm. Overall, the proposed strategy presents good results for the dynamic environment and is suitable to be applied on real-world scenarios.

Neutron/gamma discrimination techniques are widely applied in scintillator-based neutron diagnostics for present nuclear fusion tokamak experiments (e.g. JET – Neutron Camera and compact neutron spectrometer) and will also be necessary for neutron diagnostics of up-coming machines (e.g. ITER Radial Neutron Camera). Neutron/gamma discrimination in scintillators relies on the fact that the detectors output pulses have different shapes depending on the impinging particle; several discrimination techniques are described in literature such as the charge-integration, curve-fitting and pattern recognition [1]. This paper aims at describing a new technique for neutron/gamma discrimination in scintillators based on trapezoidal filtering, which targets Field Programmable Gate Array (FPGA) implementation due to its recursive nature. Furthermore its capability to restore the baseline of each detected pulse and the fact that the output signals are shorter than the correspondent incoming pulses, points this technique as a promising solution for applications in high count rate conditions. First results coming from the application of a real-time FPGA implementation of the trapezoidal filter to simulated neutron/gamma data including pile-up events and to real scintillator data will be presented.

Macroalgae are increasingly viewed as a source of secondary metabolites with great potential for the development of new drugs. In this development, in vitro studies are only the first step in a long process, while in vivo studies and clinical trials are the most revealing stages of the true potential and limitations that a given metabolite may have as a new drug. This literature review aims to give a critical overview of the secondary metabolites that reveal the most interesting results in these two steps. Phlorotannins show great pharmaceutical potential in in vivo models and, among the several examples, the anti-dyslipidemia activity of dieckol must be highlighted because it was more effective than lovastatin in an in vivo model. The IRLIIVLMPILMA tridecapeptide that exhibits an in vivo level of activity similar to the hypotensive clinical drug captopril should still be stressed, as well as griffithsin which showed such stunning results over a variety of animal models and which will probably move onto clinical trials soon. Regarding clinical trials, studies with pure algal metabolites are scarce, limited to those carried out with kahalalide F and fucoxanthin. The majority of clinical trials currently aim to ascertain the effect of algae consumption, as extracts or fractions, on obesity and diabetes. This research was funded by project MACBIOBLUE (MAC/1.1b/086), program Interreg MAC 2014–2020 co-financed by DRCT (Azores Regional Government), supporting G.P. Rosa’s grant, as well as by FCT—Fundação para a Ciência e a Tecnologia, the European Union, QREN, FEDER, and COMPETE, through funding the cE3c center (FCT UID/BIA/00329/2013, 2015–2018 and UID/BIA/00329/2019) and the QOPNA research unit (FCT UID/QUI/00062/2019) info:eu-repo/semantics/publishedVersion

Fibre Reinforced Polymer (FRP) composites have been the source of an increasing interest in the field of rehabilitation, namely for repair and strengthening of reinforced concrete (RC) structures. One of the most effective techniques comprises externally bonded FRP composites, in which the efficacy of rehabilitation depends considerably on the integrity and durability of the bond established between the FRP and the substrate, which is provided by a structural adhesive. This paper presents a concise review of critical durability issues associated with the structural bond between FRP and concrete for rehabilitation purposes. A number of factors determining the durability of FRP-concrete bonded joints have been identified and grouped into the following categories: materials – adhesive and adherends, joint characteristics and in-service conditions. For each of those factors, the main findings obtained in previous studies are summarized and the aspects that need further investigation are outlined.

Sousa, M.C.; Ribeiro, A.S.; Des, M.; Mendes, R.; Alvarez, I.; Gomez-Gesteira, M., and Dias, J.M., 2018. Integrated high-resolution numerical model for the NW Iberian Peninsula coast and main estuarine systems. In: Shim, J.-S.; Chun, I., and Lim, H.S. (eds.), Proceedings from the International Coastal Symposium (ICS) 2018 (Busan, Republic of Korea). Journal of Coastal Research, Special Issue No. 85, pp. 66–70. Coconut Creek (Florida), ISSN 0749-0208.The NW Iberian Peninsula (NWIP) coast includes a large diversity of estuarine systems such as Rias, river estuaries and coastal lagoons, being characterized by a high primary production, responsible for the significant fisheries and aquaculture productivity of the region. Thus, the main objective of this study is the development of a novel integrated high-resolution circulation and hydrographic coastal model designed with Delft3D-flow and applied for a large and complex area integrating the NWIP continental shelf and main estuarine systems. A domain decomposition technique was adopted to resolve the complex geomorphology in the study area. This approach allows local refinement in estuarine systems with the capability of two-way communication of water level, currents and hydrographic properties between those areas and the coastal ocean. The model was successfully validated using sea surface elevation, salinity and water temperature data from various observational sources, including remotely sensed images. Numerical calculations show good agreement with the observed water level in the entire domain. In addition, measured salinity and water temperature are well reproduced by the model. Results from two real events (summer 2005 and winter 2012–2013) were compared with remote sensing products, revealing that predictions adequately represent the hydrographic patterns observed. Results showed a complex interaction among estuarine systems as well with the adjacent coast, in addition to the accuracy of the integrated high-resolution numerical model developed in reproducing the hydrodynamic and thermohaline patterns of the NWIP coast and main estuarine systems.

Introduction Co-management between internists and surgeons of selected patients is becoming one of the pillars of modern clinical management in large hospitals. Defining the patients to be co-managed is essential. The aim of this study is to create a decision tool using real-world patient data collected in the preoperative period, to support the decision on which patients should have the co-management service offered. Methods Data was collected from the electronic clinical health records of patients who had an International Classification of Diseases, 9th edition (ICD–9) code of colorectal surgery during the period between January 2012 and October 2014 in a 200 bed private teaching hospital in Lisbon. ICD–9 codes of colorectal surgery [48.5 and 48.6 (anterior rectal resection and abdominoperineal resection), 45.7 (partial colectomy), 45.8 (Total Colectomy), and 45.9 (Bowel Anastomosis)] were used. Only patients above 18 years old were considered. Patients with more than one procedure were excluded from the study. From these data the authors investigated the construction of predictive models using logistic regression and Takagi-Sugeno fuzzy modelling. Results Data contains information obtained from the clinical records of a cohort of 344 adult patients. Data from 398 emergent and elective surgeries were collected, from which 54 were excluded because they were second procedures for the same patients. Four preoperative variables were identified as being the most predictive of co-management, in multivariable regression analysis. The final model performed well after being internally validated (0.81 AUC, 77% accuracy, 74% sensitivity, 78% specificity, 93% negative predictive value). The results indicate that the decision process can be more objective and potentially automated. Conclusions The authors developed a prediction model based on preoperative characteristics, in order to support the decision for the co-management of surgical patients in the postoperative ward setting. The model is a simple bedside decision tool that uses only four numerical variables.

This paper proposes the use of mixed fuzzy clustering (MFC) algorithm to derive Takagi–Sugeno (T–S) fuzzy models (FMs). Mixed fuzzy clustering handles both time invariant and multivariate time variant features, allowing the user to control the weight of each component in the clustering process. Two model designs based on MFC are investigated. In the first, the antecedent fuzzy sets of the T–S model are obtained from the clusters obtained by the MFC algorithm. In the second, FMs based on fuzzy c-means (FCM) are constructed over the input space of the partition matrix generated by MFC. The proposed fuzzy modeling approaches are used in health care classification problems, where time series of unequal lengths are very common. MFC-based T–S FMs outperform FCM-based T–S FMs in four out of five datasets and k -nearest neighbors classifiers in five out of five datasets. Dynamic time warping performs better than the Euclidean distance in one dataset and similarly in the remaining. Given the different nature of time variant and invariant data, the choice of a clustering algorithm that treats data differently should be considered for model construction.

The ITER project demanding operating conditions, as well as other enabling experiments in relevant fusion projects, present new challenges to the diagnostics, control and instrumentation. The most critical requirements relate to the high acquisition rates (up to some gigasample per second), high physical event rate (up to several megaevents per second), need to handle enormous quantities of data in long experimental pulses (up to 30 minutes) and highly complex control and diagnostic algorithms. Radiation hardness of all equipment involved must also be taken into account for high magnetic fields as well as neutron irradiation in the fusion devices port cells. The implementation of state-of-the-art designs were tested both with in-house built prototypes and complete systems installed in the major international fusion experiments. The main technologies used include Advanced Telecommunications Computing Architecture (ATCA), high speed electronic devices for signal digitization, complex real-time algorithms for physics analysis, control and data compression implemented in high-performance computing using field-programmable gate arrays and multicore processor architectures. The control and data acquisition group at Instituto de Plasmas e Fusao Nuclear (Instituto Superior Tecnico - Lisboa) has conducted several projects and studies for the development of reliable high-performance processing tools and instrumentation for the diagnostics and control of fusion devices capable of complying with the most demanding requirements.

The Radial Neutron Camera (RNC) diagnostic is a neutron detection system with multiple collimators aiming at characterizing the neutron emission that will be produced by the ITER tokamak. The RNC plays a primary role for basic and advanced plasma control measurements and acts as backup for system machine protection measurements. During the RNC system level design phase the following real-time data processing algorithms were developed to assess RNC data throughput needs and measurement performances: (i) real-time data compression block (ii) real-time calculation of the neutron emissivity radial profile, based on Tikhonov regularization, starting from the line-integrated measurements, the line-of-sight geometry and using the magnetic flux information [1] (iii) real-time calculation of the neutron emissivity profile using a-priori trained neural networks, the line-integrated measurements and the magnetic flux information (the best output from different neural networks being evaluated by a figure of merit that maps the neutron emissivity profile to the original line-integrated measurements) [2] . This paper presents results for the processing times of the various algorithms and their minimum control cycle for different conditions, such as number of lines of sight, number of magnetic flux surfaces and measurement error on the line integrated RNC measurements.

This paper presents an optimization model to identity the best set of retrofitting measures applied to four different regions of Portugal; Lisbon, Porto, Braganca and Evora. The main objective is to maximize the annual energy savings, expressed in Euros, while minimizing the initial investment expressed also in Euros, considering the retrofit strategies as decisions variables and evaluating their effect in the usage of space heating and cooling and costs, depending on the chosen technology. A multi-objective genetic algorithm coded in MATLAB © to solve the optimization problem. Different energy efficiency measures are considered, such as the improvement of U-values in external walls and windows through the application of insulation materials, the change of lighting fixtures and refrigerator model to reduce the electricity consumption, and the usage of PV panels for self-consumption, and the use of Heat Pumps for space heating and cooling. The fitness function is subjected to different constraints related with the fulfillment of the demand, the physical limitation of household space, the capacity to comply with the heating and cooling needs, and the non-negativity nature of the variables. The best set of retrofitting options are presented, the budget to implement them and the amount of achieved energy savings.

Laboratories are critical components in drug manufacturing, and inefficiencies in laboratory management can have a major impact on the overall supply chain service level. The aim of this paper is to build a Discrete Event Simulation model of a Quality Control laboratory. To achieve this objective, a generic framework for information treatment and organization was built. In particular, information coming from different databases was organized into a single one that was used as input to a discrete event simulation model. The proposed model represents in detail the work flow of a quality control laboratory and it is intended as a support tool for planning, scheduling and decision making. The model was validated using real data, and it proved to be effective in the estimation of performance parameters such as, system throughput, equipment usage rate, system responsiveness and tasks processing times. Furthermore, the simulation model was tested with an alternative scheduling policy to evaluate how modifications on the system may improve its performance.

Developing energy efficiency strategies for Intelligent Buildings requires a continuous monitoring of the impacts of energy efficiency measures against baseline scenarios. Since not all consumption events can be linearly described, non-linear models based on fuzzy systems and neural networks are successful where linear models either become inaccurate or too complex to be employed in practice. Herein, we study the adequacy of plain-designed non-linear models to predict energy consumption in a real-world Intelligent Building setting by using simple predictor variables such as time-of-day, weather conditions, and occupancy as estimated from WiFi traffic. The developed Fuzzy Systems and Neural Network models achieve considerably better performance and accuracy indexes than linear regression models, with VAFs equal to 79.3% and 75.7% respectively, and MAE of 5.9 and 7.1 kWh, respectively, against 36.6% VAF and 12.8 kWh MAE for linear regression models, thus demonstrating that low complexity non-linear models can be used to accurately describe energy consumption baselines in Intelligent Buildings.

Understanding and forecasting future consequences of climate change in mussel aquaculture industry require the assessment of changes in physical parameters which may affect mussel growth. The FLOW module of Delft3D model forced with climatic data was validated and calibrated for the Rias Baixas (NW Iberian Peninsula), one of the areas with the highest mussel production in the world. This model was used to perform historical (1999–2018) and future (2080–2099) projections. Temperature and stratification water conditions were compared in order to determine at what extent climate change can affect mussel production. Thermal stress will increase in a non-homogeneous throughout the water column and the comfort level of mussels will be reduced by more than 60% in the upper layers and more than 30% in deep layers in most of the mussel raft polygons. Water column stratification will increase ~ 5–10 cycles h−1 in most of the polygons reducing the vertical exchange of nutrients and oxygen. Hereby changes in water temperature and stratification at the end of the century will not be favorable for mussel growth.

Introduction The optimization of the left ventricle (LV) pacing site guided by the electrical delay increases CRT response rate (RR), however it's necessary to develop technology that allows its universal use. Purpose The aim is automatically, and operator-independent, access the conduction delay between the right ventricular (RV) stimulus and the LV available veins in order to select the LV pacing site. It is further intended to compare the total procedure and radiation times in relation to an historical control group. Methods Prospective, single-center study that included patients undergoing CRT implant according to the current ESC Guidelines. All patients were submitted to a clinical, electrocardiographic and echocardiographic basal evaluation prior to CRT implantation and at 6 months of follow-up. To evaluate conduction delays between the RV lead and the LV available veins (RV-LV delay), an external interface - intelligent Box for CRT (iBox-CRT) was used. Four measurements in at least two different tributary veins were made. The implant of all the LV leads was guided by the longest measured delay. A positive response to CRT was defined as an improvement of >10% in left ventricle ejection fraction (LVEF) or a reduction of end-systolic volume (ESV)>15%. The results were compared to a control group (CG) of pts submitted to CRT implantation in the conventional way. Results 60 patients were included (68.3% males, 38% ischemic, mean age 67.4±10.2 years) and submitted to CRT implant (37 CRT-P; 23 CRT-D). At basal evaluation, LVEF was 28±7%, end-diastolic volume (EDV) was 200±73ml and ESV 145±64ml. CG (n=51) had similar characteristics. The RR was 85.7%, significantly higher compared to the CG (55.9%, p=0.003). The ESV reduced 38.2±3% in responders vs 5.7±2% in non-responders (NR) (p=0,005), EDV reduced 33.3±16% in responders vs 13.6±10% in NR (p=0.002), the mean LVEF improved 11% in responders vs −1% in NR (p=0.02). At follow-up, the mean ESV in the study group (SG) was 89±44 ml vs 132±75ml in the CG (p=0.002) and the EDV 136±51 vs 190±78 (p=0.007). In addition to a much better response rate, the responders in the study group had significantly higher mean LVEF at follow-up (39±11% vs 37±7%, p=0.032). The mean intra-procedure RV-LV delay was 187±34mseg. In the responder group the baseline delay was usually higher (190±35 msec) vs NR group RV-LV delay (165±23 msec; p=NS). Compared with CG, the automatic assessment of RV-LV delay with iBox-CRT did not increase fluoroscopy time (15±16min vs 18±16; p=NS) and shortened procedure time (65±34 vs 108±83min, p Conclusions The iBox-CRT use enabled an automatic and operator independent RV-LV delays measurement, in order to implant the LV lead at the most delayed site. This technique translated into a major increase in CTR response rate, not compromising the procedure duration nor increasing the radiation exposure.

The Caribbean has suitable conditions for a significant wind energy development, which makes a good planning for the future renewable energy mix essential. The impact of climate change on Caribbean wind power has been analyzed by means of an ensemble of CORDEX regional climate models (RCMs) under the RCP8.5 warming scenario. The offshore wind energy resource was classified for the historical period and for the future considering wind energy factors, environmental risk factors and cost factors whose weights were estimated by a Delphi method. Future projections show a maximum annual wind increase, ∼0.4 ms−1 (8%), in most of the Caribbean, except in the Yucatan Basin. This increment occurs mainly during the wet season, ∼0.5 ms−1 (∼10%), associated with changes in the extension of the North Atlantic Subtropical High, which will strengthen the Caribbean low-level jet. Additionally, the moderate wind increase, ∼0.2 ms−1 (∼4%), projected during the dry season is restricted to the southeastern coast and it is associated with an increment in the land-ocean temperature difference (∼1 °C), which will intensify local easterly winds. The low-level jet region was classified as the richest wind energy resource in the Caribbean for the future with a larger extension compared to the historical period.

This paper proposes a decision support system based on fuzzy clustering, fuzzy modeling and fuzzy fingerprints, to provide personalized therapy for critically ill patients. It is hypothesized that the ‘collective experience’ from large clinical databases, where clinical decisions are linked with patient outcomes, can be used to identify specific patient sub-groups and build personalized therapy models towards a new era of personalized medicine, allowing the improvement of patient outcomes in the Intensive Care Unit (ICU). The validity of the proposed systems will be tested using the case study of patients admitted to the ICU who then develop acute kidney injury (AKI); Two-thirds of patients with AKI require renal support therapy. Generalized severity scoring systems have consistently performed poorly for patients with AKI.

The ITER Radial Neutron Camera (RNC) Data Acquisition (DAQ) prototype is based on the PCIe protocol as the interface to be used between the I/O unit and the host computer, allowing the scalability of the final RNC DAQ system. The prototype architecture comprises two digitizer modules with two channels in each, installed in the host computer and the maximum produced data throughput is up to 1.6 GB/s per board, allowing a sustainable 2 MHz peak event to cope with the long plasma discharges, up to half an hour. The Linux Device Driver provides the interface between the hardware and the host applications running on a high-performance computer, which receives the acquired data through the Direct Memory Access (DMA) channels. The preliminary tests show that the Linux kernel miss some hardware interrupts when the time between interrupts is in the microsecond scale, which implies data loss if a traditional read technique based on interrupt handling is implemented. The direct usage of the polling mechanisms to retrieve the data is not suitable as the variable event rate over the same discharge does not allow to define an optimal fixed-time to retrieve data and identify missing data packets. This contribution presents the architecture, implementation and test of a different device driver approach using the polling mechanism which improves the performance and reliability. This allows the device driver to automatically check and transfer missing data blocks, recovering the data losses transparently for the host applications. The performance results for tests with different event data rates and duration up to an hour are also presented.

Nowadays, industry is being forced to produce smaller and more diverse batches, increasing the complexity of internal supply chains. Data has become a valuable asset, supporting the development of intelligent automation solutions. Decision support systems, which leverage data, require the automation pyramid to be more flexible, as information needs to be exchanged simultaneously and in real-time with all automation layers. This paper proposes a framework for intelligent automation to deal with current challenges in acquisition and management of data in industrial settings, towards feeding decision support systems. It frames the topic within the scope of internal supply chains, addressing the framework impact on work practices within the organisation. Two real industrial implementation cases are examined, in the wood and chemical industries. Results help practitioners address the most impactful challenges affecting the performance of internal supply chains, by developing systems which are faster, more flexible, efficient and with improved quality.

The surgical treatment of an exposed compounded comminuted fracture of the right radius and ulna in a free-ranging adult female Iberian Wolf (Canis lupus signatus) with an osteosynthesis plate and screws and subsequent post-operative care are described. The evolution of the fracture healing was very similar to those expected in a dog of the same size. The prompt surgical intervention and a proper housing, feeding and wound management adapted to a free-ranging wolf, in view to reduce manipulation and post-operative complications, allowed the subsequent rehabilitation and release of the animal. After 10th post-operative weeks the wolf was fitted with a Global Positioning System (GPS) for wildlife tracking collar and released in the same area where it has been caught. GPS telemetry data showed that the animal covered increasingly large distances confirming a complete functionality of the right thoracic limb and its successfully return to the wild. This report could constitute the first detailed report of a long bone fracture treatment in a free-ranging wolf and its successfully rehabilitation, release and adaptation to the wild. Resumo: O objetivo do presente artigo é a descrição da realização da estabilização de uma fratura cominutiva exposta do rádio e ulna do membro torácico direito em Lobo Ibérico selvagem por meio de osteossíntese com placa e parafusos ósseos bem como o manejo pós-operatório. A evolução da cicatrização da fratura óssea foi similar à esperada num canídeo doméstico de porte idêntico. A intervenção cirúrgica realizada rapidamente, bem como o alojamento adequado, alimentação e manejo adaptado a um lobo selvagem, visando minimizar a manipulação e o aparecimento de possíveis complicações pós-operatórias permitiram o sucesso na reabilitação e posterior libertação do animal. Na 10ª semana pós-operatória foi colocado um colar GPS no animal para deteção permanente da sua localização, tendo sido o animal libertado na mesma área onde havia sido capturado. Os dados obtidos por telemetria GPS demostraram que o lobo percorreu distâncias consideráveis, confirmando a completa recuperação do membro torácico direito e o sucesso da sua reintrodução na natureza. Este artigo poderá constituir a primeira descrição pormenorizada sobre a estabilização de fratura de ossos longos em um lobo selvagem com a sua posterior reintrodução na vida selvagem com sucesso.

Vasopressors administration in intensive care units is a risky surgical procedure that can be associated with infections, especially if done urgently such as in the case of unexpected systemic shock. The early prediction of a patient's transition to vasopressor dependence could improve overall outcomes associated with the procedure. Personalized medicine in the ICU encompasses the customization of healthcare on the level of individual patients, with diagnostic tests, monitoring interventions and treatments being fitted to the individual rather than the "average" patient. In this scope, this paper proposes an ensemble fuzzy modeling approach to a classification problem based on subgroups of patients identified by individual characteristics. A fuzzy c-means clustering algorithm was implemented to find subgroups of patients and each subgroup was used to develop a fuzzy model. The final classification of the ensemble fuzzy approach is obtained using two output selection criteria: an a priori decision criterion based on the distance from the cluster centers to the patients' characteristics, and an a posteriori decision criterion based on the uncertainty of the model output. The performance of the proposed approach is investigated using a real world clinical database and nine benchmark datasets. The ensemble fuzzy model approach performs better than the single model for the prediction of vasopressors administration in the ICU, being the a posteriori approach the best performer, with an average AUC of 0.85, showing this way the advantage of a personalized approach for patient care in the ICU.

The electrification of road vehicles was introduced as a way to significantly reduce oil dependence, increase efficiency, and reduce pollutant emissions, especially in urban areas. The goal of this paper is to find the best alternative vehicle to replace a conventional diesel bus operating in urban environments, aiming to reduce the carbon footprint and still being financially advantageous. The multi-objective nondominated sorting genetic algorithm is used to perform the vehicle optimization, covering pure electric and fuel cell hybrid possibilities (with and without plug-in capability). The used multi-objective genetic algorithm optimizes the powertrain components (type and size) and the energy management strategy. Although multiple optimal solutions were successfully achieved, a decision method is implemented to select one unique solution. A global criterion approach, a pseudo-weight vector approach, and a new multiple criteria score approach are considered to choose a preferred optimal vehicle. Real and synthetic driving cycles are used to compare the optimized buses concerning their powertrain components, efficiency and life cycle of fuel and vehicle materials. The conflict between objectives and the importance of the decision considerations in the final solutions are discussed. Passengers load and air conditioning system influence in the solutions and its life cycle is addressed.

The expected post-operatory weight loss is not always achieved after bariatric surgery. Efforts have been done to describe the causes. Recently, total weight loss (%TWL) has been pointed out to better assess weight loss in bariatric patients. However, there is no cut off point that delimits the patients who successfully achieve their weight goals after a bariatric surgery. In this work, a method based on fuzzy modeling is implemented to help clinicians setting up the best cut-off point in %TWL for a specific population. The best boundary to delimit success and failure will be selected based on the predictive performance of the assessed cut-off points: 25, 30, 35 and 40%TWL after one and two years of surgery. Area under the receiver operating characteristic curve (AUC) values of 0.70 and 0.75 were achieved for the first and second post-surgery periods, respectively. Further, features not previously described as predictors of weight loss were identified as good predictors of the outcome.

Up to two thirds of critically ill patients in Intensive Care Units (ICU) around the world develop Acute Kidney Injury (AKI). This complication is characterized by a reduction of kidney function and is intrinsically linked to an increased risk of mortality. AKI is also connected to higher costs in healthcare due to longer hospital stay times and ICU readmissions for affected patients. The present study developed a model capable of predicting which patients are at a larger risk of death and therefore allow for a more efficient use of hospital resources. Information regarding several physiological parameters of patients with AKI as well as data regarding their survival was used for the creation of a fuzzy model. The model achieved AUC values of up to 0.92 when using mean values for time series and analyzing a subset of patients with AKI at its most advanced stage. When analysing a general population of ICU patients, the algorithm can achieve AUC values of 0.86. This value can be compared with values obtained in similar studies of 0.85 and surpasses values obtained in traditional risk scores such as APACHE II and SOFA. A model such as this, shows the potential of using this type of predictive applications for scheduling human resources and managing monetary resources on critical patients according to their relative need for attention and treatment.

The Gamma-Ray Camera Upgrade (GCU) project aims at installing a new set of 19 scintillators with multi-pixel photon counter (MPPC) embedded, capable to meet the high fluxes expected during deuterium-tritium plasmas while improving the diagnostic spectroscopic capabilities. GCU will benefit from the Advanced Telecommunications Computing Architecture (ATCA)-based Data Acquisition System (DAQ), successfully installed and commissioned during the JET-EP2 enhancement. However, to cope with the new GCU detector signals, the DAQ Field Programmable Gate Array (FPGA) codes need to be rebuilt. This work presents the FPGA code upgrade for Gamma Camera (GC) DAQ, capable to sustain the expected fast response of new detectors, while exploiting the full capabilities of the DAQ. Dedicated codes were designed, capable to acquire the new signals at full rate, and simultaneously processing them in real-time through suitable algorithms, fitted to the new signals shape. First results of real-time processing codes applied to data from detector prototypes are presented.

The aim of this work was to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), and support vector machines (SVM) to predict physicochemical composition of bee pollen mixture given their botanical origin. To obtain the predominant plant genus of pollen (was the output variable), based on physicochemical composition (were the input variables of the predictive model), prediction models were learned from data. For the inverse case study, input/output variables were swapped. The probabilistic NN prediction model obtained 98.4% of correct classification of the predominant plant genus of pollen. To obtain the secondary and tertiary plant genus of pollen, the results present a lower accuracy. To predict the physicochemical characteristic of a mixture of bee pollen, given their botanical origin, fuzzy models proven the best results with small prediction errors, and variability lower than 10%. This work was partly supported by FCT, through IDMEC, under LAETA, project UID/EMS/50022/2013, and partly funded by FCT I.P.: Centro de Estudos Florestais, a research unit funded by FCT (UID/AGR/UI0239/2013); strategic programme UID/ BIA/04050/2013 (POCI-01-0145-FEDER- 007569) and strategic programme UID/BIA/04050/2013 (POCI-01-0145-FEDER-007569). In addition, it was also funded by the ERDF through the COMPETE2020 – Programa Operacional Competitividade e Internacionalização (POCI). info:eu-repo/semantics/publishedVersion

Objective The human nucleus accumbens (Acc) has become a target for deep brain stimulation (DBS) in some neuropsychiatric disorders. Nonetheless, even with the most recent advances in neuroimaging it remains difficult to accurately delineate the Acc and closely related subcortical structures, by conventional MRI sequences. It is our purpose to perform a MRI study of the human Acc and to determine whether there are reliable anatomical landmarks that enable the precise location and identification of the nucleus and its core/shell division. Methods For the Acc identification and delineation, based on anatomical landmarks, T1WI, T1IR and STIR 3T-MR images were acquired in 10 healthy volunteers. Additionally, 32-direction DTI was obtained for Acc segmentation. Seed masks for the Acc were generated with FreeSurfer and probabilistic tractography was performed using FSL. The probability of connectivity between the seed voxels and distinct brain areas was determined and subjected to k-means clustering analysis, defining 2 different regions. Results With conventional T1WI, the Acc borders are better defined through its surrounding anatomical structures. The DTI color-coded vector maps and IR sequences add further detail in the Acc identification and delineation. Additionally, using probabilistic tractography it is possible to segment the Acc into a core and shell division and establish its structural connectivity with different brain areas. Conclusions Advanced MRI techniques allow in vivo delineation and segmentation of the human Acc and represent an additional guiding tool in the precise and safe target definition for DBS.

The knowledge of the service life and durability of building components is paramount to sustainable analysis and decision making since it allows a more rational management of the maintenance of building and provides data for life cycle analysis procedures. Nevertheless, predicting the service life of a building or its components is a complex process with which a number of variables are associated. The main difficulties associated with service life prediction are related to the complexity of the degradation phenomena and to the lack of understanding of degradation factors and mechanisms. This paper aims at establishing a model for the service life prediction of rendered facades using a Takagi–Sugeno fuzzy model. The models proposed include the variables that influence the degradation of rendered facades (render age, render type, building height, facade orientation, exposure to damp, and facade protection level). In this study, the degradation condition of 100 case studies located in Portugal is analyzed based only on in situ visual inspections. The proposed models are able to describe appropriately the degradation of rendered facades and to predict the service life of the sample analyzed.

Left ventricular ejection fraction (LVEF) constitutes an important physiological parameter for the assessment of cardiac function, particularly in the settings of coronary artery disease and heart failure. This study explores the use of routinely and easily acquired variables in the intensive care unit (ICU) to predict severely depressed LVEF following ICU admission. A retrospective study was conducted. We extracted clinical physiological variables derived from ICU monitoring and available within the MIMIC II database and developed a fuzzy model using sequential feature selection and compared it with the conventional logistic regression (LR) model. Maximum predictive performance was observed using easily acquired ICU variables within 6 hours after admission and satisfactory predictive performance was achieved using variables acquired as early as one hour after admission. The fuzzy model is able to predict LVEF ≤ 25% with an AUC of 0.71 ± 0.07, outperforming the LR model, with an AUC of 0.67 ± 0.07. To the best of the authors’ knowledge, this is the first study predicting severely impaired LVEF using multivariate analysis of routinely collected data in the ICU. We recommend inclusion of these findings into triaged management plans that balance urgency with resources and clinical status, particularly for reducing the time of echocardiographic examination., MIT-Portugal Program, Portuguese Science and Technology Foundation (Project LAETA 2015-202, Reference UID/EMS/50022/2013), Portuguese Ministry of Education and Science (Portuguese Science and Technology Foundation Grant SFRH/BD/51028/2010), Portuguese Science and Technology Foundation (IC4U-Decision Support System for Preventing ICU Readmissions PTDC/EMS-SIS/3220/2012)

Logistic regression and Takagi-Sugeno fuzzy models are sequentially trained with categorical and numerical data in an ensemble-based multistage scheme. In the first stage, a logistic regression model is used to transform the binary feature space into a numerical feature that is used to train a second stage of models consisting of an ensemble of two Takagi-Sugeno fuzzy models. In the ensemble, one model is trained in the space of numerical features and first stage prediction values. The other model is trained only with samples that were classified with a low degree of confidence by the first stage model, in the space of numerical variables. The final output is given by the average of the ensemble predictions at second stage. This scheme was devised under the hypothesis that separating binary from numerical features in the modeling process would increase the performance of a single model using both types of features together. The proposed multistage approach is used to solve a clinical classification problem in a Portuguese hospital. The problem consists of predicting comanagement signalling based on patient clinical data, including diagnosis, procedures, comorbidities and numerical scores, collected before surgery. The multistage performed better in the comanagement dataset, and in 2 out of 5 benchmark datasets.

Fuel cell powered hybrid electric vehicles (FC-HEV) and plug-in hybrid electric vehicles (FC-PHEV) are being addressed by the automotive industry as improved and more sustainable alternative technologies relatively to conventional vehicles. Nevertheless, hybrid propulsion raises new challenges in designing the vehicle powertrain. This study highlights the significance of the driving conditions and the conflict between the optimization of investment cost, efficiency and life cycle impact (LCA) in powertrain design optimization of these kinds of vehicles. A single-objective (minimization of cost, fuel or LCA CO2eq) and multi-objective genetic algorithms (minimization of the couples cost and fuel, cost and LCA CO2eq, fuel and LCA CO2eq), linked with the vehicle simulation software ADVISOR, are used to optimize the design of powertrain components. The main outcomes of the research are as follows. The optimization of LCA CO2eq emissions and cost are conflicting as well as cost and energy use, what can be observed in the Pareto solutions. The fuel and LCA CO2eq emissions optimization are coupled for pure hybrids but not for plug-in hybrid configurations, due to the electricity consumption. Fuel cell buses can reduce the energy consumption by 58%, and emit 67% less LCA CO2eq than the conventional diesel bus, and achieve compensatory payback of 0.620 $/km (depending on the hydrogen price). The FC-PHEV configuration shows more potential for achieving higher operation efficiencies, but the FC-HEV shows to have lower life cycle impact and lower cost in general.

This paper presents an overview of the Control, Data Acquisition, and Communication system (CODAC) at the COMPASS tokamak: the hardware set-up, software implementation, and communication tools are described. The diagnostics and the data acquisition are tailored for high spatial and temporal resolution required by the COMPASS physics programme, which aims namely at studies of the plasma edge, pedestal, and Scrape-off-Layer (SOL). Studies of instabilities and turbulence are also an integral part of the programme. Therefore, the data acquisition consists of more than 1000 channels, sampled at rates from 500 kS/s up to 2 GS/s. Presently, the feedback system controls the plasma position and shape, plasma current, and density and it includes 32 analogue input channels as well as 1 digital input/output channel and 8 analogue outputs. The feedback control runs within the Multi-threaded Application Real-Time executor (MARTe) framework with two threads, a 500 μs cycle to control slow systems and a 50 μs cycle to control the fast feedback power supplies for plasma position control. In this paper, special attention is paid to the links between the systems, to the hardware and software connections, and to the communication. The hardware part is described, the software framework is addressed, and the particular implementation – the dedicated software modules, communication protocols, and links to the database are described.