Abstract
The number of smartphone users has increased significantly, and the development of mobile applications has brought convenience to daily life. However, large numbers of users who have various barriers, such as visual or hearing impairments, and physical disorders, are not able to fully access and use the referred applications, which is unfair to them, especially when considering its use by students in a university campus where all users should be able to enjoy equal opportunities and experiences. The main goal of this study is to assess accessibility in mobile applications of the education sector. Thus, an evaluation model is also proposed to assess the accessibility of the applications from two perspectives, which are the inherent properties of the applications and the user experience of different disability categories. 46 official mobile applications were tested which related to 23 universities and institutes of Portugal, using automatic and manual testing methods. Several frequently occurring accessibility issues in the apps were identified and summarized, such as color contrast, touch target, missing focus. The results of the accessibility testing showed that the status of web accessibility of mobile applications in the higher education sector in Portugal is unsatisfactory. Most apps have multiple accessibility issues, and they are extremely unfriendly to the users with visual impairments. In addition, the study also proposed a series of accessibility recommendations for mobile application designers and developers, with the purpose of improving the accessibility of apps and providing an equitable user experience for all users. © 2022, Springer Nature Switzerland AG.

Abstract
Probabilistic load forecasting (PLF) is necessary for power system operations and control as it assists in proper scheduling and dispatch. Moreover, PLF adequately captures the uncertainty whether that uncertainty is related to load data or the forecasting model. And there are not many PLF models, and those which exist are very complex or difficult to interpret. This paper proposes a novel neuroevolution algorithm for handling the uncertainty associated with load forecasting. In this paper, a new modified evolutionary algorithm is proposed which is used to find the optimal hyperparameters of 1D-Convolutional neural network (CNN). The probabilistic forecasts are produced by minimizing the mean scaled interval score loss function at 50%, 90% and 95% prediction intervals. The proposed neuroevolution algorithm is tested on a global energy forecasting competition (GEFCom-2014) load dataset, and two different experiments are conducted considering load only and one with load and temperature. Strong conclusions are drawn from these experiments. Also, the proposed model is compared with other benchmark models, and it has been shown that it outperforms the other models.

Abstract
Purpose The purpose of this study is to explore the human resource management practices and the associated dimensions of quality of employment in university spin-offs. Through this, it becomes possible to explore and recognize the practices and difficulties placed on the employees of university spin-offs. Design/methodology/approach The United Nations Economic Commission for Europe (UNECE) framework to assess the quality of work in the European Union is adopted. It is used a qualitative approach through the development of four case studies at university spin-offs located in Portugal. These case studies relate to four sectors of activity, such as information technology, urban mobility, health and electronics. Findings The findings reveal that most of the challenges of quality of work in a spin-off university are common to those in an SME or micro company. Among these factors, the authors highlight the lack of job security, reduced or no social protection and very low income and nonwage pecuniary benefits. Other factors specific to university spin-offs also emerge, such as the numerous opportunities for skills development and training, the potentialities to become an entrepreneur and the high number of working hours that are necessary to face the vibrant market dynamics. Originality/value The study aims to contribute, in a theoretical and empirically grounded basis, to the knowledge about the quality of employment in a spin-off university. This work becomes relevant for policymakers to understand in depth the specific challenges faced by employees of a spin-off university.

Abstract
Refactoring helps improve the design of software systems, making them more understandable, readable, maintainable, cleaner, and self-explanatory. Many refactoring tools allow developers to select and execute the best refactorings for their code. However, most of them lack quick and continuous feedback, support, and guidance, leading to a poor refactoring experience. To fill this gap, we are researching ways to increase liveness in refactoring. Live Refactoring consists of continuously knowing, in real-time, what and why to refactor. To explore the concept of Live Refactoring and its main components - recommendation, visualization, and application, we prototyped a Live Refactoring Environment focused on the Extract Method refactoring. With it, developers can receive recommendations about the best refactoring options and have support to apply them automatically. This work helped us reinforce the hypothesis that early and continuous refactoring feedback helps to shorten the time needed to create high-quality systems.

Abstract
Learning programming boils down to the practice of solving exercises. However, although there are good and diversified exercises, these are held in proprietary systems hindering their interoperability. This article presents a simple scraping tool, called ScraPE, which through a navigation, interaction and data extraction script, materialized in a domain-specific language, allows extracting the data necessary from Web pages – typically online judges – to compose programming exercises in a standard language. The tool is validated by extracting exercises from a specific online judge. This tool is part of a larger project where the main objective is to provide programming exercises through a simple GraphQL API.

Abstract
Vineyard classification is an important process within viticulture-related decision-support systems. Indeed, it improves grapevine vegetation detection, enabling both the assessment of vineyard vegetative properties and the optimization of in-field management tasks. Aerial data acquired by sensors coupled to unmanned aerial vehicles (UAVs) may be used to achieve it. Flight campaigns were conducted to acquire both RGB and multispectral data from three vineyards located in Portugal and in Italy. Red, green, blue and near infrared orthorectified mosaics resulted from the photogrammetric processing of the acquired data. They were then used to calculate RGB and multispectral vegetation indices, as well as a crop surface model (CSM). Three different supervised machine learning (ML) approaches-support vector machine (SVM), random forest (RF) and artificial neural network (ANN)-were trained to classify elements present within each vineyard into one of four classes: grapevine, shadow, soil and other vegetation. The trained models were then used to classify vineyards objects, generated from an object-based image analysis (OBIA) approach, into the four classes. Classification outcomes were compared with an automatic point-cloud classification approach and threshold-based approaches. Results shown that ANN provided a better overall classification performance, regardless of the type of features used. Features based on RGB data showed better performance than the ones based only on multispectral data. However, a higher performance was achieved when using features from both sensors. The methods presented in this study that resort to data acquired from different sensors are suitable to be used in the vineyard classification process. Furthermore, they also may be applied in other land use classification scenarios.