Search

The objective of the research was to analyze the role of machine data learning in systematic literature reviews. The Natural Language Processing technique called topic modeling was applied to a set of titles and abstracts collected from the Scopus database. Specifically, the Latent Dirichlet Assignment (LDA) technique was used, from which it was possible to discover and understand the underlying themes in the collection of documents. The results showed the usefulness of the technique used in the exploratory literature review, by allowing the results to be grouped by theme. Likewise, it was possible to identify the specific areas and activities where machine learning has been applied the most, in relation to literature reviews. It is concluded that the LDA technique is an easy-to-use strategy and whose results allow a wide collection of documents to be approached in a systematic and coherent manner, notably reducing the review time. [ABSTRACT FROM AUTHOR]

this article examines the impact, potentials, challenges, and future prospects of using Machine Learning (ML) algorithms in clinical psychology, with a focus on basic research and clinical application. ML is reshaping both research and clinical practice by analyzing complex data and uncovering patterns for understanding mental disorders and predicting diagnoses, among other noteworthy aspects. despite the challenges of interpretation, privacy, and bias, the transformative potential of ML algorithms in clinical psychology is acknowledged. interdisciplinary collaboration is essential to maximize these benefits. emphasizing the importance of addressing ethical and practical considerations, this paper envisions a future where ML algorithms become integral tools in the research, diagnosis, and treatment of mental disorders, contributing to an overall enhancement in people's quality of life. [ABSTRACT FROM AUTHOR]

The water scarcity is a concern of the agricultural industry as it uses four fifths of the of the total fresh water consumed for irrigation and two thirds of the total used for human consumption. For this reason, the development of systems that optimize the use of water in irrigation is essential. In the greenhouses of the UEB "Valle del Yabú" of the Santa Clara municipality, irrigation is carried out using a drip-based system that requires the presence of an operator for decisionmaking who does not have information about some of the hydrometeorological variables that govern the crop. This paper focused on to design a support system for decision-making in irrigation based on machine learning. As an important parameter of the system, the evapotranspiration coefficient of the crop is calculated using the Turc formula. The collected environmental data is conditioned and linear regression, regressive random forests, and gradient-boosted trees regression models are trained with them to determine future evapotranspiration values using the Apache Spark framework. The model that obtained the best results was the regressive random forest with a coefficient of determination (r2) of 0,79 and with it the volume of water lost by the crop is calculated. Finally, the system was able to provide the estimates of both variables, which favour decision-making by specialists. [ABSTRACT FROM AUTHOR]

This paper proposes several techniques for simultaneous localization and mapping of the environment, which allow mobile robots to self-reference themselves in a navigation environment with reduced accessibility by external means, such as the Global Position System (GPS). The methodology consists of implementing four unsupervised machine learning algorithms, using data sets generated based on a cloud of range points delivered by LiDAR sensor measurements. The proposed approach identifies characteristics from a navigability map, whereas an additional method based on Extended Kalman Filter (EKF) allows to find the robot positioning in conjunction. The proposed approach identifies navigability map features and an additional method based on EKF. EKF allows finding the robot positioning that is conjugated with each of the proposed algorithms. The first proposed method consists of estimating the features of the environment using heuristic methods and shaping the map using geometric principles. The second method is based on K-Means to incorporate the uncertainty in the sensor measurement, while the third solution uses the Gaussian Mixture Model (GMM). The fourth method focuses on Density-Based Spatial Clustering (DBSCAN). An odometry error is induced in the robot to include uncertainty within the test environment, which propagates into the positioning readings. The results show that DBSCAN presents a better execution time for the proposed localization system than the other comparative methods. Additionally, the robot's localization is more accurate with this method, showing a 5% reduction of the error compared to the result obtained from the other proposed algorithms. Finally, with the results achieved, it is expected that the consumption of robot resources can be reduced with the reduction of localization error and automatic mapping. [ABSTRACT FROM AUTHOR]

Social media have established a new way of communicating and understanding social relationships. At the same time, there are downsides, especially, their use of algorithms that have been built and developed under their umbrella and their potential to alter public opinion. This paper tries to analyse the YouTube recommendation system from the perspectives of reverse engineering and semantic mining. The first result is that, contrary to expectations, the issues do not tend to be extreme from the point of view of polarisation in all cases. Next, and through the study of the selected themes, the results do not offer a clear answer to the proposed hypotheses, since, as has been shown in similar works, the factors that shape the recommendation system are very diverse. In fact, results show that polarising content does not behave in the same way for all the topics analysed, which may indicate the existence of moderators –or corporate actions– that alter the relationship between the variables. Another contribution is the confirmation that we are dealing with non-linear, but potentially systematic, processes. Nevertheless, the present work opens the door to further academic research on the topic to clarify the unknowns about the role of these algorithms in our societies. [ABSTRACT FROM AUTHOR]

In this paper three prime numbers are presented as high potentials to be Mersenne numbers and their application in computational primality testing is suggested. These numbers are constructed from a regression algorithm based on Support vector machines (SVM) and using a Gaussian Kernel. Data training is carried out using the Phyton programming language, In the study we address the current data of Mersenne primes and work with the Ova-angular classification group for Mersenne primes 31. [ABSTRACT FROM AUTHOR]

This paper presents a document classification service that allows multiple client (multi-tenant) document management systems to provide greater confidence and credibility regarding the document types assigned to documents uploaded by users. The research was carried out through the phases of CRISP-DM, where two document representation models were evaluated (bags of words with cumulative n-grams and BERT, which was recently proposed by Google) and five machine learning techniques (multilayer perceptron, random forests, k-nearest neighbors, decision trees, and naïve bayes). The experiments were carried out with data from two organizations, and the best results were obtained by multilayer perceptron, random forests, and k-nearest neighbors, which showed very similar results regarding general accuracy and recall by class. The results are not conclusive with respect to the ability to offer the service to multiple clients with a single model, since this also depends on their documents and document types. Therefore, a service is offered which is based on a microservices architecture that allows each organization to create its own model, monitor its performance in production, and update it when performance is not adequate. [ABSTRACT FROM AUTHOR]

Performance tests are crucial to measure the quality of software developments, since they allow identifying aspects to be improved in order to achieve customer satisfaction. The objective of this research was to identify the optimal Machine Learning technique to predict whether or not a software development meets the customer's acceptance criteria. A dataset with information obtained from web services performance tests and the F1-score quality metric were used. This paper concludes that, although the Random Forest technique obtained the best score, it is not correct to state that it is the best Machine Learning technique; the quantity and quality of the data used in the training play a very important role, as well as an adequate processing of the information. [ABSTRACT FROM AUTHOR]

Traffic control in data networks has recently become very important due to the massive use of computer networks in different areas of society. Different techniques are usually used to carry out effective traffic control, allowing, among other things, to classify, predict and monitor network traffic. These techniques have evolved and are currently supported by artificial intelligence tools, which have made it possible to improve the results obtained with conventional techniques. This paper collects the different contributions made by the field of artificial intelligence to the improvement of these techniques and network management in general. The article describes the contributions made in aspects such as security, prediction, and classification of data traffic, as well as the optimization of routing in a computer network. [ABSTRACT FROM AUTHOR]

In this paper we intend to substantiate the usefulness of Deep Learning, especially feedforward neuronal networks, in the prediction of business failure. This methodology provides very good results in terms of predictive performance when large sample sizes are available. Therefore, we have developed a business failure prediction model for European companies, based on this algorithm on a sample of 61,624 companies, of which 12,128 were declared bankrupt in 2016. As independent variables were considered ratios, and economic and financial data obtained from the financial statements for the year preceding the date of failure. Deep Learning achieves a predictive performance of 94%, where companies with larger size and lower solvency are more prone to failure. The obtained results have been tested on an independent test sample, different from that used to estimate and train the model. [ABSTRACT FROM AUTHOR]