This work proposes a methodology for sleep stage classification based on two main approaches: the combination of features extracted from electroencephalogram (EEG) signal by different extraction methods, and use stacked sequential learning to incorporate predicted information nearby stages in final classifier. The feature methods used this include three representative ways extracting EEG signals: Hjorth features, wavelet transformation symbolic representation. Feature selection was then...

Abstract Messaging platforms are applications, generally mediated by an app, desktop program or the web, mainly used for synchronous communication among users. As such, they have been widely adopted officially higher education establishments, after little no study of their impact and perception teachers. We think that introduction these new tools opportunities challenges needs to be studied carefully in order adopt model, as well tool, is most adequate all parties involved. already students,...

One of the most notable features collectible card games is deckbuilding, that is, defining a personalized deck before real game. Deckbuilding challenge involves big and rugged search space, with different unpredictable behaviour after simple changes even hidden information. In this paper, we explore possibility automated deckbuilding: genetic algorithm applied to task, evaluation delegated game simulator tests every potential against varied representative range human-made decks. these...

One of the most crucial problems in field business is financial forecasting. Many companies are interested forecasting their incoming status order to adapt current and environment avoid bankruptcy. In this work, due effectiveness Deep Learning methods with respect classification tasks, we compare performance three well-known (Long-Short Term Memory, Belief Network Multilayer Perceptron model 6 layers) bagging ensemble classifiers (Random Forest, Support Vector Machine K-Nearest Neighbor) two...

This study introduces a novel evaluation framework for predicting web page performance, utilizing state-of-the-art machine learning algorithms to enhance the accuracy and efficiency of quality assessment. We systematically identify analyze 59 key attributes that influence website derived from an extensive literature review spanning 2010 2024. By integrating comprehensive set performance metrics—encompassing usability, accessibility, content relevance, visual appeal, technical performance—our...

In a connected world, spare CPU cycles are up for grabs, if you only make its obtention easy enough. this paper we present distributed evolutionary computation system that uses the computational capabilities of ubiquituous web browser. Asynchronous Javascript and JSON (Javascript Object Notation, serialization protocol) allows anybody with browser (that is, mostly everybody to Internet) participate in genetic algorithm experiment little effort, or none at all. Since, case, computing becomes...

Videogames are a very interesting area of research for fields as diverse computer science, health, psychology or even social sciences. Every year growing number articles published in different topics inside this field, so it is convenient to study the bibliometric data order consolidate efforts. Thus, aim work conduct on distribution related videogames research, well measure their interest over time, identify sources, countries and authors with highest scientific production. In carry out...

KANTS is a swarm intelligence clustering algorithm inspired by the behavior of social insects. It uses stigmergy as strategy for large datasets and, result, displays typical complex systems: self-organization and global patterns emerging from local interaction simple units. This paper introduces simplified version describes recent experiments with in context contemporary artistic scientific trend called art, type generative art which systems are used to create artwork or ornamental objects....

This paper presents a hybrid algorithm that combines Fuzzy Logic Controller (FLC) and Genetic Algorithms (GAs) its application on traffic signal system. FLCs have been widely used in many applications diverse areas, such as control system, pattern recognition, processing, forecasting. They are, essentially, rule-based systems, which the definition of these rules fuzzy membership functions is generally based verbally formulated overlap through parameter space. great influence over performance...

This paper describes an Evolutionary Algorithm for evolving the decision engine of a bot designed to play Planet Wars game. game, which has been chosen Google Artificial Intelligence Challenge in 2010, requires that artificial player is able deal with multiple objectives, while achieving certain degree adaptability order defeat different opponents scenarios. The based on set rules have defined after empirical study. Then, used tuning constants, weights and probabilities define rules, and,...

Among Real-Time Strategy games few titles have enjoyed the continued success of StarCraft. Many research lines aimed at developing Artificial Intelligences, or "bots", capable challenging human players, use StarCraft as a platform. Several characteristics make this game particularly appealing for researchers, such as: asymmetric balanced factions, considerable complexity technology trees, large number units with unique features, and potential optimization both strategical tactical level. In...

Online reviews are important information that customers seek when deciding to buy products or services. Also, organizations benefit from these as essential feedback for their Such required reliability, especially during the Covid-19 pandemic which showed a massive increase in online due quarantine and sitting at home. Not only number of was boosted but also context preferences pandemic. Therefore, spam reviewers reflect on changes improve deception technique. Spam usually consist misleading,...

In this paper we analyse the resilience of a peer-to-peer (P2P) evolutionary algorithm (EA) subject to following dynamics: computing nodes acting as peers leave system independently from each other causing collective effect known churn. Since P2P EA has been designed tackle large instances computationally expensive problems, will assess its behaviour under these conditions, by performing scalability analysis in five different scenarios using massively multimodal deceptive problem benchmark....