Abstract
The ionosphere is a fundamental component of the Earth's atmosphere, impacting human activities such as communication transmissions, navigation systems, satellite functions, power network systems, and natural gas pipelines, even endangering human life or health. As technology moves forward, understanding the impact of the ionosphere on our daily lives becomes increasingly important. CubeSats are a promising way to increase understanding of this important atmospheric layer. This paper reviews the state of the art of CubeSat missions designed for ionospheric studies. Their main instrumentation payload and orbits are also analyzed from the point of view of their importance for the missions. It also focuses on the importance of data and metadata, and makes an approach to the aspects that need to be improved.

Abstract
The impact of climate change on global temperature and precipitation patterns can lead to an increase in extreme environmental events. These events can create favourable conditions for the spread of plant pests and diseases, leading to significant production losses in agriculture. To mitigate these losses, early detection of pests is crucial in order to implement effective and safe control management strategies, to protect the crops, public health and the environment. Our work focuses on the development of a computer vision framework to detect and classify the olive fruit fly, also known as Bactrocera oleae, from images, which is a serious concern to the EU’s olive tree industry. The images of the olive fruit fly were obtained from traps placed throughout olive orchards located in Greece. The approach entails augmenting the dataset and fine-tuning the YOLOv7 model to improve the model performance, in identifying and classifying olive fruit flies. A Portuguese dataset was also used to further perform detection. To assess the model, a set of metrics were calculated, and the experimental results indicated that the model can precisely identify the positive class, which is the olive fruit fly.

Abstract
Several systems that employ machine learning models are subject to strict latency requirements. Fraud detection systems, transportation control systems, network traffic analysis and footwear manufacturing processes are a few examples. These requirements are imposed at inference time, when the model is queried. However, it is not trivial how to adjust model architecture and hyperparameters in order to obtain a good trade-off between predictive ability and inference time. This paper provides a contribution in this direction by presenting a study of how different architectural and hyperparameter choices affect the inference time of a Convolutional Neural Network for network traffic analysis. Our case study focus on a model for traffic correlation attacks to the Tor network, that requires the correlation of a large volume of network flows in a short amount of time. Our findings suggest that hyperparameters related to convolution operations-such as stride, and the number of filters-and the reduction of convolution and max-pooling layers can substantially reduce inference time, often with a relatively small cost in predictive performance.

Abstract
In an automatic music playlist generator, such as an automated online radio channel, how should the system react when a user hits the skip button? Can we use this type of negative feedback to improve the list of songs we will playback for the user next? We propose SkipAwareRec, a next-item recommendation system based on reinforcement learning. SkipAwareRec recommends the best next music categories, considering positive feedback consisting of normal listening behaviour, and negative feedback in the form of song skips. Since SkipAwareRec recommends broad categories, it needs to be coupled with a model able to choose the best individual items. To do this, we propose Hybrid SkipAwareRec. This hybrid model combines the SkipAwareRec with an incremental Matrix Factorisation (MF) algorithm that selects specific songs within the recommended categories. Our experiments with Spotify's Sequential Skip Prediction Challenge dataset show that Hybrid SkipAwareRec has the potential to improve recommendations by a considerable amount with respect to the skip-agnostic MF algorithm. This strongly suggests that reformulating the next recommendations based on skips improves the quality of automatic playlists. Although in this work we focus on sequential music recommendation, our proposal can be applied to other sequential content recommendation domains, such as health for user engagement.

Abstract
Presence is often used to evaluate Virtual Reality (VR) applications. However, the raw scores are hard to interpret and need to be compared to other data to be meaningful. This paper leverages a database of 1909 responses to the Igroup Presence Questionnaire (IPQ) in different contexts to put forward a scale that qualitatively interprets raw Presence scores for VR experiences. The qualitative grading encompasses the acceptability dimension and analogous academic grading scales ranging from A to F and the adjective of such scores in a scale from Excellent to Unacceptable. Furthermore, the qualitative grading system encompasses Presence and its subscales Spatial Presence, Involvement, and Experienced Realism as defined by the IPQ. Adopting this grading system, supported by a robust dataset of Presence scores, enables practitioners to evaluate and interpret individual IPQ scores, allowing them to gain insights regarding the evaluated applications' effectiveness.

Abstract
The adoption of immersive virtual experiences (IVEs) opened new research lines where the impact of realism is being studied, allowing developers to focus resources on realism factors proven to improve the user experience the most. We analyzed papers that compared different levels of realism and evaluated their impact on user experience. Exploratorily, we also synthesized the realism terms used by authors. From 1,300 initial documents, 79 met the eligibility criteria. Overall, most of the studies reported that higher realism has a positive impact on user experience. These data allow a better understanding of realism in IVEs, guiding future R&D.