Abstract
Traditional recurrent neural networks (RNNs) are essential for processing time-series data. However, they function as read-only models, lacking the ability to directly modify the data they learn from. In this study, we introduce the corrector long short-term memory (cLSTM), a Read & Write LSTM architecture that not only learns from the data but also dynamically adjusts it when necessary. The cLSTM model leverages two key components: (a) predicting LSTM’s cell states using Seasonal Autoregressive Integrated Moving Average (SARIMA) and (b) refining the training data based on discrepancies between actual and forecasted cell states. Our empirical validation demonstrates that cLSTM surpasses read-only LSTM models in forecasting accuracy across the Numenta Anomaly Benchmark (NAB) and M4 Competition datasets. Additionally, cLSTM exhibits superior performance in anomaly detection compared to hierarchical temporal memory (HTM) models. © The Author(s) 2024.

Abstract
Laser-induced breakdown spectroscopy allows fast and versatile elemental analysis, standing as a promising technique for a wide range of applications both at the research and industry levels. Yet, its high operation speed comes with a high throughput of data, which introduces some challenges at the level of the data processing domain, mainly due to the large computational load and data volume. In this work, we analyze and discuss opportunities of distributed computing paradigms and resources to address some of these challenges, covering most of the procedures usually employed in typical applications. We infer the possible impact of such computing resources by presenting some metrics of simple processing prototypes running in state-of-the-art computing facilities. Our results allow us to conclude that, while underexplored so far, these computing resources may allow for the development of tools for timely research and analysis in demanding applications and introduce novel solutions toward a more agile working environment.

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.

Abstract

Abstract
People are living longer, promoting new challenges in healthcare. Many older adults prefer to age in their own homes rather than in healthcare institutions. Portugal has seen a similar trend, and public and private home care solutions have been developed. However, age-related pathologies can affect an elderly person's ability to perform daily tasks independently. Ambient Assisted Living (AAL) is a domain that uses information and communication technologies to improve the quality of life of older adults. AI-based fall detection systems have been integrated into AAL studies, and posture estimation tools are important for monitoring patients. In this study, the OpenCV and the YOLOv7 machine learning framework are used to develop a fall detection system based on posture analysis. To protect patient privacy, the use of a thermal camera is proposed to prevent facial recognition. The developed system was applied and validated in the real scenario.

Abstract
This systematic literature review investigates the factors influencing cloud computing adoption within both educational and organizational settings. By synthesizing a comprehensive body of research, this study finds and analyzes the determinants that shape the decision-making process about cloud technology adoption. Security, cost-effectiveness, scalability, interoperability, and regulatory compliance are examined across educational institutions and organizational contexts. Additionally, socio-economic, political, and technological factors specific to each context are explored to provide a nuanced understanding of the challenges and opportunities associated with cloud computing adoption. The review reveals commonalities and differences in adoption drivers and barriers between education and organizational environments, offering insights into tailored strategies for effective implementation. This research contributes to the existing literature by shedding light on the multifaceted nature of cloud adoption and offering valuable guidance for educators, organizational leaders, policymakers, and technology providers looking to use cloud computing to enhance operations and services.