Abstract
Emerging wearable technology able to monitor electrocardiogram (ECG) continuously for long periods of time without disrupting the patient's daily life represents a great opportunity to improve suboptimal current diagnosis of paroxysmal atrial fibrillation (AF). However, its integration into clinical practice is still limited because the acquired ECG recording is often strongly contaminated by transient noise, thus leading to numerous false alarms of AF and requiring manual interpretation of extensive amounts of ECG data. To improve this situation, automated selection of ECG segments with sufficient quality for precise diagnosis has been widely proposed, and numerous algorithms for such ECG quality assessment can be found. Although most have reported successful performance on ECG signals acquired from healthy subjects, only a recent algorithm based on a well-known pre-trained convolutional neural network (CNN), such as AlexNet, has maintained a similar efficiency in the context of paroxysmal AF. Hence, having in mind the latest major advances in the development of neural networks, the main goal of this work was to compare the most recent pre-trained CNN models in terms of classification performance between high- and low-quality ECG excerpts and computational time. In global values, all reported a similar classification performance, which was significantly superior than the one provided by previous methods based on combining hand-crafted ECG features with conventional machine learning classifiers. Nonetheless, shallow networks (such as AlexNet) trended to detect better high-quality ECG excerpts and deep CNN models to identify better noisy ECG segments. The networks with a moderate depth of about 20 layers presented the best balanced performance on both groups of ECG excerpts. Indeed, GoogLeNet (with a depth of 22 layers) obtained very close values of sensitivity and specificity about 87%. It also maintained a misclassification rate of AF episodes similar to AlexNet and an acceptable computation time, thus constituting the best alternative for quality assessment of wearable, long-term ECG recordings acquired from patients with paroxysmal AF.

Abstract
Energy consumption has been increasing in the last years and thus, energy efficiency is one of the most important topics actually. Besides, the consumption and energy generation forecast help in efficiency optimization. This paper presents the development of a system for forecasting surplus power generation to be used by residential loads connected to smart plugs. In this way, it is intended to collaborate with the use of surplus energy production in electrical devices in a residence instead of sending to batteries or to the grid. This work presents the theoretical basis of the project and the architecture of the developed system. A Machine Learning method applied to photovoltaic generation data in a residence was used to predict surplus energy. © 2023 IEEE.

Abstract

Abstract
Robotics and intelligent systems are key technologies to promote efficient and innovative applications in the most diverse domains (industry, healthcare, agriculture, construction, mobility, etc [...]

Abstract
The objective of this work is to evaluate the effects of different energy policies designed to favor decarbonization by increasing renewable sources. In particular, the implementation of energy efficiency policies and the application of hourly differential electricity tariffs. The Open-Source Energy Modelling System (OSeMOSYS) has been adopted to visualize the effects of each of the actions in the short, medium, and long term, from 2024 till 2046. From our results, the application of hourly differentiation tariffs does not favor either the increase in the implementation of renewable sources or decarbonization processes. The implementation of energy efficiency policies (1-1.25% annual demand decrease), in the long term, allows to reach 80% of energy production from renewable sources. In all the scenarios, the energy sources with a greater level of intermittency, such as wind or solar, strongly increased their contribution in the medium-term, thereby stabilizing their long-term contribution. Finally, the implementation of photovoltaic solar energy becomes necessary only in the long-term. It seems clear that this contribution, up to 20% of the renewable, is associated with the nuclear blackout.

Abstract
Language-guided generative models are increasingly used in audiovisual production. Image diffusion allows for the development of video sequences and some of its coordination can be established by text prompts. This research automates a video production pipeline leveraging CLIP-guidance with longform text inputs and a separate text-to-speech system. We introduce a method for producing frame-accurate video and audio summaries using a virtual timeline and document a set of video outputs with diverging parameters. Our approach was applied in the production of the film Irreplaceable Biography and contributes to a future where multimodal generative architectures are set as underlying mechanisms to establish visual sequences in time. We contribute to a practice where language modelling is part of a shared and learned representation which can support professional video production, specifically used as a vehicle throughout the composition process as potential videography in physical space.