Abstract
Social media platforms enable the rapid dissemination and consumption of information. However, users instantly consume such content regardless of the reliability of the shared data. Consequently, the latter crowdsourcing model is exposed to manipulation. This work contributes with an explainable and online classification method to recognize fake news in real-time. The proposed method combines both unsupervised and supervised Machine Learning approaches with online created lexica. The profiling is built using creator-, content- and context-based features using Natural Language Processing techniques. The explainable classification mechanism displays in a dashboard the features selected for classification and the prediction confidence. The performance of the proposed solution has been validated with real data sets from Twitter and the results attain 80% accuracy and macro F-measure. This proposal is the first to jointly provide data stream processing, profiling, classification and explainability. Ultimately, the proposed early detection, isolation and explanation of fake news contribute to increase the quality and trustworthiness of social media contents.

Abstract
Purpose: This paper intends to evaluate the impact of Toyota Way (TW) focused activities on operational performance and its connection to sustainability and longterm success. Methodology/Approach: Three theoretical-practical activities were implemented in a real pickup assembly plant. Performance was assessed through the recording of standard documentation before and after implementation, direct observation at the gemba, and anonymous qualitative surveys of those involved. Findings: Results show how TW enhances workers' skills alongside TPS through experiential learning, fostering continuous improvement with minimal or no financial investment and creating value iteratively and exponentially. However, it had a limited impact on environmental factors. TW emerges as a critical link between short-term operational performance and long-term sustainable growth. Research Limitations/Implications: The sample is restricted to a single assembly plant in Portugal. The surveys involved between 5 and 13 respondents per activity. Originality/Value of paper: In contrast to TPS and lean manufacturing, current literature on TW is limited, often outdated, and lacks clarity regarding its Japanese and American interpretations. Furthermore, few studies emphasise the human element as a driver of company growth-a factor often overlooked by companies. Category: Case study

Abstract
Adaptive protection schemes have been designed to handle the issue of variability in current contribution from the main network side, adjusting to state changes such as the connection and disconnection of distributed generation with inverter interfaces (IIDG). These schemes enhance the reliability and effectiveness of the system by reducing the risk of unnecessary load disconnections caused by inappropriate relay trips in the absence of actual fault conditions. In response to these challenges, this paper proposes an advanced algorithm that acts as a complementary tool for adaptive overcurrent protections. This algorithm is essential for recognizing state changes in the network, such as IIDG disconnections, and adjusting the relay settings to the new operational state. Identifying these conditions is complicated because disconnections of IIDGs, as well as other events like high impedance faults (HIF) and load switching, share the same characteristic of an increase in current observed by the relay that does not reach the overcurrent fault detection threshold, making them difficult to differentiate. To overcome this challenge, an enhanced feature extraction algorithm based on mathematical morphology has been developed, utilizing an adaptive triangular structuring element (SE) that conforms to the waveform of the input signal. This algorithm is capable of effectively distinguishing between various events such as HIF, load switching, and IIDG disconnections, enabling appropriate actions to be taken.

Abstract
The Machine Learning Data Market (MLDM), which relies on multi-agent systems, necessitates robust negotiation strategies to ensure efficient and fair transactions. The Contract Net Protocol (CNP), a well-established negotiation strategy within Multi-Agent Systems (MAS), offers a promising solution. This paper explores the integration of CNP into MLDM, proposing the CNP-MLDM model to facilitate data exchanges. Characterized by its task announcement and bidding process, CNP enhances negotiation efficiency in MLDM. This paper describes CNP tailored for MLDM, detailing the proposed protocol following experimental results.

Abstract
Accurate dynamics modelling of Unmanned Under-water Vehicles (UUV s) is critical for optimizing mission planning, minimizing collision risks, and ensuring the successful execution of tasks in diverse underwater environments. This paper presents a structured approach to estimating the hydrodynamic coeffi-cients of UUV s. Initially, it follows a detailed methodology for estimating hydrodynamic coefficients using simple geometries, a sphere and a spheroid, using the Computational Fluid Dy-namics (CFD) software OpenFoam, and comparing the results to analytical solutions, enabling the validation of the simulations approach. Following this, the paper provides an in-depth analysis of the damping and added mass coefficients for the Raya UUV, offering valuable insights into its hydrodynamic behaviour. © 2024 IEEE.

Abstract
Spectral imaging is a technique that captures spectral information from a scene and maps it onto a 2D image, featuring the potential to reveal hidden features and properties of objects that are invisible to the human eye, such as elemental and molecular compositions. Augmented reality (AR), on the other hand, is a technology that enhances the perception of reality by superimposing digital information on the physical world. While these technologies have different purposes, they can be considered one and the same in terms of providing an user-centric extension of reality. Spectral imaging provides the information that can reveal the underlying nature of objects, while AR provides the method of visualization that can display the information in an intuitive and interactive way. In this work, we present a novel Unity toolkit that combines spectral imaging and a HoloLens 2 AR device to create an interactive and immersive experience for the user. The toolkit enables the interactive visualization of various elemental maps of a 3D rock model in AR using a simple and intuitive interface. With this technique, the user can select a sample model and an elemental map from a preloaded asset library and then see the map projected onto the rock model in AR, using simple interactions such as zoom adjustment, rotation, and pan of the models to explore features and properties in detail. The toolkit offers several advantages, including better contextual interpretation of the spectral data by placing it in relation to the shape and texture of the rock, increased user engagement and curiosity through the creation of a realistic and immersive experience, and ease of decision-making through the provision of comparative tools. In short, by combining spectral imaging and AR, we present an innovative approach that can enrich the user experience and expand the user knowledge of the environment.