Abstract
In recent years, the use of remote sensing data obtained from satellite or unmanned aerial vehicle (UAV) imagery has grown in popularity for crop classification tasks such as yield prediction, soil classification or crop mapping. The ready availability of information, with improved temporal, radiometric, and spatial resolution, has resulted in the accumulation of vast amounts of data. Meeting the demands of analysing this data requires innovative solutions, and artificial intelligence techniques offer the necessary support. This systematic review aims to evaluate the effectiveness of deep learning techniques for crop classification using remote sensing data from aerial imagery. The reviewed papers focus on a variety of deep learning architectures, including convolutional neural networks (CNNs), long short-term memory networks, transformers, and hybrid CNN-recurrent neural network models, and incorporate techniques such as data augmentation, transfer learning, and multimodal fusion to improve model performance. The review analyses the use of these techniques to boost crop classification accuracy by developing new deep learning architectures or by combining various types of remote sensing data. Additionally, it assesses the impact of factors like spatial and spectral resolution, image annotation, and sample quality on crop classification. Ensembling models or integrating multiple data sources tends to enhance the classification accuracy of deep learning models. Satellite imagery is the most commonly used data source due to its accessibility and typically free availability. The study highlights the requirement for large amounts of training data and the incorporation of non-crop classes to enhance accuracy and provide valuable insights into the current state of deep learning models and datasets for crop classification tasks.

Abstract
Aircraft maintenance plays a vital role in ensuring not only public safety but also aircraft availability and financial viability. However, carrying out such activities traditionally leaves gaps for processual optimizations with the potential of increasing the overall performance and satisfaction of operators and engineers who deal with these responsibilities. Currently, available technologies may enable the increment of quality in aircraft maintenance processes, namely, the ones based on xReality and deep learning. Therefore, this paper proposes two use-cases based on real aircraft maintenance context requirements: one employing augmented reality for cable routing, enabling cataloguing and also previewing the position and paths of cable systems inside the fuselage kit; and another making use of deep learning and virtual environments to aid in the activities related with engine baroscopic inspections, with position awareness capabilities. Results regarding a few functional and usability tests are also presented and discussed. In spite of their still incipient maturity, both these tools showed potential for being involved in the pipelines of aircraft maintenance in the future.

Abstract
The main objective of this article is to investigate the factors that influence customers' intention to reuse chatbot-based services. The study employs a combination of the technology acceptance model (TAM) with other contributions in the literature to develop a theoretical model that predicts and explains customers' intention to reuse chatbots. The research uses structural equation modeling (PLS-SEM) to test the proposed hypotheses. Data collected from 201 chatbot users among Portuguese consumers were analyzed, and the results showed that user satisfaction, perceived usefulness, and subjective norm are significant predictors of chatbot reuse intentions. Additionally, the findings indicated that perceived usefulness, perceived ease of use, and trust have a positive impact on attitudes toward using chatbots. Trust was found to have a significant impact on perceived usefulness, user satisfaction, and attitudes toward using chatbots. However, there was no significant effect of attitude toward using chatbots, perceived ease of use, trust, and perceived social presence on reuse intentions. The article concludes with theoretical contributions and recommendations for managers.

Abstract
The oceans are abundant in natural diversity, minerals and energy resources, and there is an urgent need for a better understanding of its ecosystems and dynamics. The Synchronous Oceanic and Atmospheric Data Acquisition (SONDA) Project intends to contribute to better atmospheric and oceanic modelling and monitoring by launching High-Altitude Balloons (HAB) equipped with atmospheric and deep-sea probes to be released in oceanic areas of interest. This work reports the development and validation of three different probes: 1) atmospheric monitoring with APRS communications to be launched by HAB; 2) oceanographic monitoring; and 3) deep-sea monitoring with satellite communications. All probes were preliminarily tested in a semi-controlled fluvial environment, and posteriorly in real field conditions in the Azores Islands, Portugal. During the campaign, the Atmospheric probe was launched by HAB and its communications were tested with fixed and mobile ground stations, the oceanographic probe was deployed for three days to monitor the effect of a geothermal spring in the sea and the deep-sea probe was released into the Atlantic Ocean.

Abstract
Clinical decision support systems have been increasingly utilized in the healthcare industry to improve patient outcomes and enhance clinical decision-making, taking advantage of the growing digital medical data. Despite their potential, there are still obstacles in an extensive adoption of these systems, such as low usability and human factors. In this systematic review, several articles describing clinical decision support systems with clinical validation are used to address some of the gaps, as well as to map the current academic landscape for the given context. The selected articles are observed through a Human-Computer Interaction perspective, aiming to identify the state-of-the-art, as well as barriers to the application of these principles. From an initial database search resulting in 121 articles, 16 articles were selected that fulfilled the chosen criteria: (1) article must be available and written in English, (2) article must report experimental work, (3) the reported system must be clinically validated. The research strategy followed the PRISMA framework. We highlight the need for clinical validation, a standardized clinical decision support taxonomy and the evaluation of these tools across multiple variables. Based on the found results, a list of recommendations can be formed to aid the development of future CDSS, or the improvement of current ones.

Abstract
The effectiveness of digital marketing relies on the seamless integration of intelligent technology, enabling encounters that closely resemble those experienced with physical vendors in the real world. Thus, the importance of scalable artificial intelligence (AI) systems guided by a multimodal approach cannot be overstated, as they can be used to gain a deeper understanding of user preferences and engagement behaviors. The investigation conducted concerning multimodal learning in this review uncovers a variety of benefits and limitations on the available data, presenting consistency in finding the relationship between modalities. The results suggest multimodality as a topic with a noticeable dearth of research, yet a promising path to reduce uncertainty and develop innovative perspectives on decision-making for Digital Marketing improvement tasks. The complexity inherent in data processes like analysis, processing, and granular modulation requires a lot of effort for researchers to build accurate multimodal representations while trying to suppress imprecision in these new elements. Therefore, our approach aims to explore how theoretical foundations are successfully applied to learning operational procedures, considering real-life case comprehension, the technical challenges of the learning process, and the importance given to each feature. Even so, comparing the restrictions found in the state-of-the-art made possible the reformulation of limitations to this particular type of technology and encouraged the search for more guidelines on the entire process.