Microsleeps are brief lapses in awareness that pose significant risks, particularly in activities requiring continuous attention, such as driving. These episodes are common in sleep-deprived individuals and can lead to catastrophic outcomes. Electroencephalography (EEG) is a promising technique for detecting microsleeps due to its high temporal resolution, allowing real-time brain activity monitoring. The study aims to develop a lightweight version of the model to reduce computational costs and provide faster detection, enabling quicker intervention to prevent accidents in safety-critical environments. We propose a novel deep learning model, Hyper-Opt-ANN, designed to detect microsleep episodes from EEG signals. The model is evaluated across five time windows (1 second, 2 seconds, 3 seconds, 4 seconds, and 5 seconds), with the 4 seconds window showing the best performance. The Hyper-Opt-ANN model achieved a significant accuracy of 97.33%, demonstrating its efficacy and potential for accurate microsleep detection using EEG signals. This method significantly outperforms traditional approaches and has potential applications in safety-critical domains. This study demonstrates the feasibility of using EEG signals and advanced deep learning models for detecting microsleep and enhancing safety in high-risk environments.

Teaching-learning are part of the same process, before and especially in the context of contemporary digital culture. As mediators and disseminators of digital technology effective use in learning environments, teachers should apply appropriate pedagogical use of digital technologies in school, as well as to seek development of new skills for themselves and for students, facing new forms of learn. The article suggests reflections on the contemporary educational pedagogical process, evaluating adjustments to the speed of learning, due to cultural changes of the Information Society era, dealing with exploratory methodology offering reflection on the generation of pedagogical ideas attending this social transformation. This dialogue among ideas was supported by Focal Groups with specialized teachers, which have led us to the conclusion that Teaching, and Learning environment requires cognitive deepening face to computational interaction and competences development for a dynamic teaching role in the techno relational interface of contemporary humanization.

Fitness landscapes are a useful concept for studying the dynamics of meta-heuristics. In the last two decades, they have been successfully used for estimating the optimization capabilities of different flavors of evolutionary algorithms, including genetic algorithms and genetic programming. However, so far they have not been used for studying the performance of machine learning algorithms on unseen data, and they have not been applied to studying neuroevolution landscapes. This paper fills these gaps by applying fitness landscapes to neuroevolution, and using this concept to infer useful information about the learning and generalization ability of the machine learning method. For this task, we use a grammar-based approach to generate convolutional neural networks, and we study the dynamics of three different mutations used to evolve them. To characterize fitness landscapes, we study autocorrelation, entropic measure of ruggedness, and fitness clouds. Also, we propose the use of two additional evaluation measures: density clouds and overfitting measure. The results show that these measures are appropriate for estimating both the learning and the generalization ability of the considered neuroevolution configurations.

This paper analyses the main research direction for the digital transformation of manufacturing and its important drivers: cloud services and resource virtualization that have led to the new Cloud Manufacturing (CMfg) model – an industrial replica of Cloud Computing. This model is adopted for the higher layer of the Manufacturing Execution System (e.g. the centralised, hierarchical System Scheduler), while its lower layers distribute intelligence through agent- and service orientation in the holonic paradigm. In this approach, Intelligent Manufacturing Systems are assimilated to Cyber-Physical Production Systems in which informational and operational technologies are merged, the shop floor physical reality being mirrored by virtual counterparts – the digital twins that represent abstract entities specific for the manufacturing domain: products, orders and resources. Industry 4.0 represents the vision for the Industry of the Future which is based on Cyber-Physical Production Systems that assure the flexible, dynamically reconfigurable control of strongly coupled processes. In this picture of the future manufacturing industry, the Industrial Internet of Things framework provides connectivity and interoperability to integrate communications between different kinds of things: products, orders and resources and legacy manufacturing devices to the web service ecosystem. The paper describes the scientific issues related to big data processing, analytics and intelligent decision making through machine learning in predictive resource maintenance, optimized production planning and control, lists solutions and proposes new research directions.

It is imperative to take proactive measures in light of the escalating concerns about greenhouse gas (GHG) emissions of international shipping. The GHG study conducted by the International Maritime Organization (IMO) indicates that the sector accounted for 2.2% and 2.89 % of emissions in 2012 and 2018, respectively. As a result, IMO has endorsed strategies to reduce ship-induced emissions to 50% by 2050 and net zero emissions by 2100. For reducing carbon emissions, regulations such as the Energy Efficiency Design Index (EEDI) and Ship Energy Efficiency Management Plan (SEEMP) were implemented a decade ago. We collected data from 104 seafarers in 24 countries using purposive sampling, exploring how the energy-efficient operation of ships transforms their work cultures onboard ships. The majority of seafarers in our study agreed that energy-efficient ship operation has changed seafarers' working cultures over the last decade. Seafarers have adopted a variety of energy efficiency (EE) practices, including meticulous record-keeping of fuel consumption and adherence to Planned Maintenance Systems. As well as preparing for Port State Control (PSC) inspections, they follow energy-saving measures prescribed by the SEEMP. In addition to engine maintenance, energy-saving practices, accurate reporting and recording of EE-related data, and efficient power usage, they provide just-in-time arrival, crew training, energy-efficient lighting, environmental awareness, and slow steaming to minimize fuel consumption. The majority of seafarers implemented SEEMP successfully and met the company's objectives, but they did not receive any form of recognition or financial incentives. Although SEEMP can help shipping companies gain financial benefits and preserve the environment, seafarers do not receive tangible rewards or appreciation for implementing it. Only one-fourth of seafarers were rewarded with incentives, bonuses, formal recognition, or trophies. This study holds significant implications for policymakers, offering insight into seafarers' adaptation to energy-efficient ship operations and advocating for integrating Industry 4.0 technologies for EE regulations compliance by reducing seafarers' workloads and improving data accuracy.

In this case study we discuss different approaches to the study of literature in digital humanities and try to join two methodologies, namely distant reading and spatial analysis. We first describe shortly the two projects involved, the Atlas of Literary Landscapes of Mainland Portugal and Literateca, highlighting and quantifying the different ways to deal with place in literature in Portuguese. Then we describe some different paths to compare and harmonize the two approaches, focusing on annotation, extraction and geocoding of place names.

Radio-frequency energy harvesting (EH) is one of the enabling technologies for the next-generation wireless communication systems. EH techniques are specifically used to improve the energy efficiency of the system. Recently, the simultaneous wireless information and power transmission (SWIPT) protocol is adapted for EH. In this paper, we design a new receiver for joint carrier frequency offset (CFO) and channel estimation on single-carrier modulations with frequency-domain equalization along with SWIPT implementation for EH by using the pilot signal. The pilot signal is a highly energized signal, which is superimposed with the information signal. The superimposed signal is used not only to transmit power for EH purposes but also to estimate the CFO and channel conditions. The receiver is designed to accommodate the strong interference levels in the channel estimation and data detection. The proposed scheme offers a flexible design method and efficient resource utilization. We validate our analytical results using simulations.

Dead stock - unsold inventory with declining market relevance - poses significant challenges for retailers, especially in sectors like consumer electronics and home appliances, where financial impact per unit is high. Existing classification methods often fail to capture early signals of declining performance, such as ageing, decreasing turnover, or prolonged inactivity. This paper proposes a fuzzy inference system (FIS) to classify inventory items along a continuum of risk: No Dead Stock, Possible Dead Stock, and Dead Stock. The system integrates multiple inventory performance indicators, including turnover ratios, ageing, coverage, and sales quota, and is grounded in domain knowledge and refined through iterative modeling. A synthetic dataset of stock keeping unit (SKU) sales patterns - designed to reflect real-world retail conditions - was used to test the system. The results demonstrate that the FIS provides interpretable outputs and can identify early signs of stock obsolescence, offering a practical decision support tool for inventory managers.

The agricultural sector worldwide faces serious problems regarding water scarcity, which demands innovative management methods to optimise water use. In response, we propose the Intelligent Data-Driven Decision Support for Agricultural Systems (ID3SAS) methodology, which offers a scalable, flexible, and cloud-based decision support system for real-time supervision and control in agricultural environments. Aligned with the prevailing trends of Agriculture 4.0, ID3SAS integrates data acquisition, cloud-based storage, machine learning, predictive analysis, and run-time reasoning to facilitate decision-making processes, thereby assisting users in making more informed and sustainable decisions. In a case study with tomato plants, ID3SAS-irrigated plants showed 20.9% reduction in water consumption and 26.4% increase in crop production compared to traditional methods, which despite the controlled laboratory environment setting, highlights the methodology's promising potential in addressing water scarcity and enhancing agricultural productivity.

Unmanned aerial vehicles (UAVs) are the next technology to be incorporated into a telecommunications network to improve command and control on a large scale in both line-of-sight (LOS) and non-line-of-sight (NLOS) conditions. However, there is still room for improvement in terms of reliability. This paper investigates Constant Packet Combining (CPC) and Adaptive Packet Combining (APC) techniques applied to Unmanned Aerial Vehicle (UAV) communication in the presence of large-scale fading, where the channels are subject to sudden degradation for long periods due to obstructions. We use Single Carrier (SC) Frequency Domain Equalization (FDE) combined with the Iterative Block Decision-Feedback Equalizer (IB-DFE) to handle command and control messages mapped for UAV use cases. We present closed-form equations for the equalization design as well as the performance parameters such as Bit Error Rate (BER), the Packet Error Rate (PER), the throughput, the retransmissions amount, the goodput (the transmission rate without the retransmissions quantity), and the outage probability. Then, we analyze the system performance using correlated, independent, and equal channels. There is a trade-off between the overall available power, throughput, and reliability. For instance, more retransmissions result in higher reliability, power consumption and lower goodputs (effective data rates). CPC validates the transmission system and confirms the improvement of BER and PER parameters without energy efficiency optimization. APC is appealing because it can reduce the number of retransmissions for all channels used with the advantage of meeting energy efficiency requirements by adapting the overall power to the scenario experienced by the UAV.