Abstract

Abstract
This study analyzed the accuracy of a BGL predictive model (BGL-PM) for type 1 diabetes mellitus patients (T1DM) in a real-world environment. The study population consisted of 10 individuals with T1DM, half of them were female, age 33 (SD:11.2), BMI of 26.1 (4.2) and 60% were under carbohydrate-count treatment. After consent, patients underwent a medical evaluation and registered their daily activities using a smartphone application (GlucoTrends) for 28 days, with BGL and heart rate continuously monitored. BGL-PM was developed using a Deep Learning architecture, based on Recurrent Neural Networks. Models were trained for each patient using different training sets sizes (7, 14, 21 days). Prediction accuracy was evaluated by Mean Absolute Percentage Error (MAPE) on the last 5 days for different Prediction Horizons (PH): 30, 60, 120, 180 and 360 minutes, comparing full day and nocturnal period. The model predicted BGL with relevant accuracy for the dataset with 21 training days up to 60 minutes in both periods: full day (median MAPE 22.5%) and nocturnal (14.3%) (Figure). The BGL-PM was able to provide useful BGL predictions, especially during the night period, which can be improved by increasing the training period. Consequently, this BGL-PM poses as a complementary tool for the prevention of acute complications such as hypoglycemia and hyperglycemia in the management of DM. Disclosure M. Foss-Freitas: None. G.S. Moreira: Stock/Shareholder; Self; GlucoGear Tecnologia. V.P. Antloga: Stock/Shareholder; Self; GlucoGear Tecnologia. C.R. Neto: Research Support; Self; University of Sao Paulo. E.M. Rodrigues: Consultant; Self; GlucoGear Tecnologia. M.F. da Costa: Research Support; Self; GlucoGear. A.P. dos Santos: None. Y.K. Matsumoto: Board Member; Self; GlucoGear. Stock/Shareholder; Self; GlucoGear. Other Relationship; Self; GlucoGear.

Abstract
In this paper, a daily plan model to the irrigation of a crop field using optimal control was developed. This daily plan model have in consideration: weather data (temperatures, rainfall, wind speed), the type of crop, the location, humidity in the soil at the initial time, the type of soil and the type of irrigation. The aim is to minimise the water used in the irrigation systems ensuring that the field crop is kept in a good state of preservation. MATLAB was used to develop our mathematical model and obtain its output. Its results were compared with experimental ones obtained from a real farm field of grass in Portugal. This comparison not only allowed us to validate our model, but also allowed us to conclude that, using optimal control considerable savings in water resources, while keeping the crop safe are obtained. Some real test cases were simulated and the comparison between the optimised water to be used by the irrigation system (calculated by software) and the real amount of water used in irrigation site (on-off control system for irrigation) produced water savings above 10%. © 2019 Inderscience Enterprises Ltd.

Abstract
Live Programming is an idea pioneered by programming environments from the earliest days of computing, such as those for Lisp and Smalltalk. One thing they had in common is liveness: an always accessible evaluation and nearly instantaneous feedback, usually focused on coding activities. In this paper, we argue for Live Software Development (LiveSD), bringing liveness to software development activities beyond coding, to make software easier to visualize, simpler to understand, and faster to evolve. Multiple challenges may vary with the activity and application domain. Research on this topic needs to consider the more important liveness gaps in software development, which representations and abstractions better support developers, and which tools are needed to support it. © 2019 Association for Computing Machinery.

Abstract
Millions of people worldwide suffer from motor disabilities, which bring alongside many other related problems, such as self-esteem issues and their constant need for a carer. While there are treatments to reduce the impact of the impairment on the patient's life, they can be either very costly or be alternative methods that are not directly aimed at rehabilitation purposes, such as the usage of Kinect Adventures to make the patient perform favorable poses and stretching limbs to help the undergoing treatment. Even though a low-cost device, the Kinect can acquire valuable data and make the patient perform exercises. However, a more direct and targeted approach might achieve better results with a game aimed for them. To attend to the many forms and variations of motor impairments, a starting point may be necessary for the development of exergames that fulfill the needs of each patient and impairment. The result is a low-cost base project that can be easily used, created using only online free tools while giving the developer creative freedom and a properly aimed solution to the patients.

Abstract
A multi-item inventory distribution problem motivated by a practical case study occurring in the logistic operations of a hospital is considered. There, a single warehouse supplies several nursing wards. The distribution of medical products is done by two different teams of workers using a heterogeneous fleet, that is, the available vehicles have different capacities and different structures required to be used in specific nursing wards. The goal is to define a weekly distribution plan of medical products ensuring a balanced workload of both working teams and satisfying all the required constraints (inventory capacities, safety stock levels, vehicle capacities, etc.) that minimizes the total number of visits to locations. A mixed integer formulation is presented and several improvements are discussed. This is a NP-hard problem hardly solved to optimality within a reasonable amount of time, and more so for real size instances, with hundreds to few thousand of products. To circumvent this issue, a matheuristic is proposed to solve the problem. Finally, computational tests are reported and discussed. © 2019, Springer Nature Switzerland AG.