Background: Eating disorders affect an increasing number of people. Social networks provide information that can help. Objective: We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain. Methods: We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model. Results: A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer–based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%). Conclusions: Bidirectional encoder representations from transformer–based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder–related tweets.
Parkinson’s disease is easy to diagnose when it is advanced, but it is very difficult to diagnose in its early stages. Early diagnosis is essential to be able to treat the symptoms. It impacts on daily activities and reduces the quality of life of both the patients and their families and it is also the second most prevalent neurodegenerative disorder after Alzheimer in people over the age of 60. Most current studies on the prediction of Parkinson’s severity are carried out in advanced stages of the disease. In this work, the study analyzes a set of variables that can be easily extracted from voice analysis, making it a very non-intrusive technique. In this paper, a method based on different deep learning techniques is proposed with two purposes. On the one hand, to find out if a person has severe or non-severe Parkinson’s disease, and on the other hand, to determine by means of regression techniques the degree of evolution of the disease in a given patient. The UPDRS (Unified Parkinson’s Disease Rating Scale) has been used by taking into account both the motor and total labels, and the best results have been obtained using a mixed multi-layer perceptron (MLP) that classifies and regresses at the same time and the most important features of the data obtained are taken as input, using an autoencoder. A success rate of 99.15% has been achieved in the problem of predicting whether a person suffers from severe Parkinson’s disease or non-severe Parkinson’s disease. In the degree of disease involvement prediction problem case, a MSE (Mean Squared Error) of 0.15 has been obtained. Using a full deep learning pipeline for data preprocessing and classification has proven to be very promising in the field Parkinson’s outperforming the state-of-the-art proposals.
The efficient design of the aerodynamic surfaces in the aircraft allows the optimal performance of the vehicle and the reduction of the fuel consumption. Among these surfaces, the wing is the main contributor to the force which lifts the aircraft enabling the flight. However, the application of this force out of the center of gravity generates a moment that must be balanced through a force applied in the Horizontal-Tail-Plane (HTP) reaching the longitudinal trim of the aircraft. Traditionally, the design of the wing and HTP have been performed iteratively attaining suboptimal or time ineffective results. In this paper, we solve this problem through the application of a Genetic Algorithm for the combined optimization of the wing and the HTP by adjusting the aspect ratio, the taper ratio, the twist angle and the incidence angle of both surfaces to produce the optimal balance of lift adjusting its distribution to an elliptical configuration and enabling the longitudinal trim. Results show the automatic adjustment of the parameters of the aerodynamic surfaces thus fulfilling the objectives of this paper.
Localization Wireless Sensor Networks (WSN) represent a research topic with increasing interest due to their numerous applications. However, the viability of these systems is compromised by the attained localization uncertainties once implemented, since the network performance is highly dependent on the sensors location. The Node Location Problem (NLP) aims to obtain the optimal distribution of sensors for a particular environment, a problem already categorized as NP-Hard. Furthermore, localization WSN usually perform a sensor selection for determining which nodes are to be utilized for maximizing the achieved accuracy. This problem, defined as the Sensor Selection Problem (SSP), has also been categorized as NP-Hard. While different metaheuristics have been proposed for attaining a near optimal solution in both problems, no approach has considered the two problems simultaneously, thus resulting in suboptimal solutions since the SSP is biased by the actual node distribution once deployed. In this paper, a combined approach of both problems simultaneously is proposed, thus considering the SSP within the NLP. Furthermore, a novel metaheuristic combining the Black Widow Optimization (BWO) algorithm and the Variable Neighbourhood Descent Chains (VND-Chains) local search, denominated as BWO-VND-Chains, is particularly devised for the first time in the author’s best knowledge for the NLP, resulting in a more efficient and robust optimization technique. Finally, a comparison of different metaheuristic algorithms is proposed over an actual urban scenario, considering different sensor selection criteria in order to attain the best methodology and selection technique. Results show that the newly devised algorithm with the SSP criteria optimization achieves mean localization uncertainties up to 19.66 % lower than traditional methodologies.