In this paper, a novel AI method for failure prediction in transmission lines components is presented. The method combines machine learning and deep learning capabilities. The approach was tested using degradation simulated data of a composite ...

Physics-informed neural networks allow the neural network to be trained by both the training data and prior domain knowledge about the physical system that models the data. In particular, it has a loss function for the data and the physics, where ...

With an increase in the diversity of data that companies in our society produce today, extracting insights from them manually has become an arduous task. One of the processes of extracting knowledge from the data is the application of anomaly ...

One-dimensional (string) formal languages and their learning have been studied in considerable depth. However, the knowledge of their two-dimensional (picture) counterpart, which retains similar importance, is lacking. We investigate the problem ...

Cardiac arrhythmias are heartbeat disorders in which the electrical impulses that coordinate the cardiac cycle malfunction. The heart’s electrical activity is recorded using electrocardiography (ECG), a non-invasive method that helps diagnose ...

Regional neuraxial analgesia is a safe method for pain relief during labor, but its effectiveness must be assessed carefully. As a non-invasive technique, thermal imaging is gaining increasing acclaim as an objective way to quantify blood flow ...

This paper describes experiments on phonetic speech segmentation of audiobooks by using LSTM neural networks. The segmentation procedure includes an iterative adaptation of an initial speaker-independent model. The experimental data involves 5 ...

Sign Language is the language that the Deaf adopted to communicate. However, most hearing people do not know how to communicate in sign language, creating natural barriers between these groups. Aiming to reduce such barriers, Sign Language ...

Sign language translation (SLT) is an active field of study that encompasses human-computer interaction, computer vision, natural language processing and machine learning. Progress on this field could lead to higher levels of integration of deaf ...

Antonymy-Synonymy Discrimination (ASD) is a challenging NLP task that has been tackled mainly for English. We present a dataset for ASD in Spanish, built using online dictionaries and Wordnet in Spanish. To evaluate the quality of the dataset, we ...

Stress is a social problem affecting society in different ways. Obtaining an accurate diagnosis of stress is complex because the symptoms of stress are very similar to the symptoms of many other illnesses. Some studies have used wearable sensors ...

In this work, a semi-supervised hierarchical classifier based on local information (SSHC-BLI) is proposed. SSHC-BLI is a semi-supervised learning algorithm that can be applied to hierarchical classification, that is, it can handle labeled and ...

Automated Machine Learning (AutoML) is an area of research that focuses on developing methods to generate machine learning models automatically. The idea of being able to build machine learning models with very little human intervention represents ...

Deep learning algorithms automatically extract features from ECG signals, eliminating the manual feature extraction step. Deep learning approaches require extensive data to be trained, and access to an ECG database with a large variety of cardiac ...

Biodiversity monitoring has taken a relevant role in conservation management plans, where several methodologies have been proposed to assess biological information of landscapes. Recently, soundscape studies have allowed biodiversity monitoring by ...

Interactive applications are becoming increasingly popular to gather feedback from users in different fields (e.g., Urbanism, Design, Economy, or Sociology). However, it is difficult to keep users engaged with an application to provide high-...

One of the most important limitation of deep learning and deep reinforcement learning, is the number of parameters in their models (dozens to hundreds of millions). Different model compression techniques, such as policy distillation, have been ...

The Colombian armed conflict has affected in some degree its entire population. Health authorities require markers to determine this exposure and provide proper mental-health interventions. Unsupervised learning techniques allow clustering ...

Internal Combustion Engines (ICE) are widely used in everyday life regardless of its contaminant emissions production, in order to reduce the impact of these emissions it is necessary to maximize the engines’ efficiency and diagnosing them it is ...

Kernel density estimation (KDE) is one of the most widely used nonparametric density estimation methods. The fact that it is a memory-based method, i.e., it uses the entire training data set for prediction, makes it unsuitable for most current big ...