Abstract
The capabilities of the most recent language models have increased the interest in integrating them into real-world applications. However, the fact that these models generate plausible, yet incorrect text poses a constraint when considering their use in several domains. Healthcare is a prime example of a domain where text-generative trustworthiness is a hard requirement to safeguard patient well-being. In this paper, we present Physio, a chat-based application for physical rehabilitation. Physio is capable of making an initial diagnosis while citing reliable health sources to support the information provided. Furthermore, drawing upon external knowledge databases, Physio can recommend rehabilitation exercises and over-the-counter medication for symptom relief. By combining these features, Physio can leverage the power of generative models for language processing while also conditioning its response on dependable and verifiable sources. A live demo of Physio is available at https://physio.inesctec.pt.

Abstract

Abstract
Hosting capacity (HC) describes the electricity network's ability to accommodate distributed generation (DG) without deteriorating electrical performance indicators. Distribution system operators typically express their networks' HC as a single threshold, called static hosting capacity (SHC). SHC is determined via conservative regulatory criteria, increasing connection costs and time. This paper explores the potential for additional energy injection into the network via dynamic hosting capacity (DHC). A network node's DHC is derived from the hourly operation of the network, accounting for the time variability of existing distributed generation (DG) output and demand. The methodology considers the network assets' N-1 contingencies and their probabilities, defining the security-aware DHC (SDHC). The SDHC definition is technologically neutral. Through a case study of a radial medium voltage distribution network, the paper highlights the significant limitations of SHC due to conservative calculation criteria mandated by regulators. Annual injectable energy is increased by 62% to 76% when comparing DHC to SHC. Variations between average DHC and SDHC are below 0.01% due to low N-1 probabilities. This finding points out the potential of dynamic hosting capacity definitions, allowing more efficient use of the existing network and facilitating the integration of new DG capacity with reduced connection costs and time.

Abstract
The concept of Demand Responsive Transport (DRT) has been around for more than 40 years and is a promising mobility alternative when traditional public transport proves inadequate in terms of its effectiveness or efficiency, as is the case of low-density areas. DRT systems have a wide range of operational configurations, being highly adaptable to different contexts and environments. Therefore, the design of a DRT mobility solution can become a quite complex and challenging problem. To assist in the design of DRTs, this paper aims to present a comprehensive classification of DRT features and to identify some common design choices in different operational scenarios. The proposed classification is based on a review of reports from available literature and previous European DRT projects. In addition, an analysis of the most usual configurations for different purposes and scenarios is presented. In this research, the operational, demand, and administrative characteristics of DRTs are addressed. Demand aspects encompass features that directly influence trip demand, such as service areas, target passengers, and hours of operation. Operational features include characteristics that will affect daily operations as the type of stops, frequency of the operation, booking methodology, vehicle route, pick-up and drop-off locations, and the vehicle type used. Administrative characteristics address the relationship between consumers and the system, such as the purpose of the system, fares, visual identification of stops, and booking methods. Regarding the usual design choices, our survey shows that rural DRTs are primarily oriented to serve populations in need in low-density areas and to complement existing PT gaps, while urban DRTs are mainly viewed as a mobility alternative to fill existing PT gaps. Defining design patterns for peri-urban and multi-area DRTs presents challenges due to their transitional nature, thus combining attributes of both rural and urban systems.

Abstract
This study aims to test the forecasting accuracy of recently implemented econometric tools as compared to the forecasting accuracy of widely used traditional models when predicting cash demand at ATMs. It also aims to verify whether the pandemic-driven change in market conditions impacted the predictive power of the tested models. Our conclusions were derived based on a data set that consisted of daily withdrawals from 61 ATMs of one of the largest European ATM networks operating in Krakow, Poland, and covered the period between January 2017 and April 2021. The results proved that the recently implemented methods of forecasting ATM withdrawals were more accurate as compared to the traditional ones, with XGBoost providing the best forecasts in the majority of the tested cases. Moreover, it was found that the pandemic-driven change in market conditions affected the predictive power of the models. Both of these results seem particularly useful for improving the efficiency of ATM networks.

Abstract
In urban environments, last-mile item delivery relies heavily on trucks, causing issues like noise pollution and traffic congestion. Unmanned Aerial Vehicles (UAVs) offer a promising solution to these challenges. This study compares the effectiveness of delivery using trucks versus drones. Two customer datasets, one clustered and one random, were used for testing. Route optimization involved four deterministic and four non-deterministic algorithms. The performance of these algorithms, considering the total distance traveled, was evaluated across different datasets and vehicle types. The top two algorithms were further assessed for environmental impact and cost efficiency. Battery consumption along the routes was also analyzed to gauge operational feasibility.