The evaluation of white blood cells is essential to assess the quality human immune system; however, assessment smear depends on pathologist's expertise. Most machine learning tools make a one-level classification for cell classification. This work presents two-stage hybrid multi-level scheme that efficiently classifies four groups: lymphocytes and monocytes (mononuclear) segmented neutrophils eosinophils (polymorphonuclear). At first level, Faster R-CNN network applied identification region...

Abstract The prediction of air pollution is great importance in highly populated areas because it directly impacts both the management city’s economic activity and health its inhabitants. This work evaluates predicts Spatio-temporal behavior quality Metropolitan Lima, Peru, using artificial neural networks. conventional feedforward backpropagation known as Multilayer Perceptron (MLP) Recurrent Artificial Neural network Long Short-Term Memory networks (LSTM) were implemented for hourly...

Nowadays, ageing related diseases represent one of the most relevant challenges for developed countries. The use healthcare remote technology may allow reducing management chronic meanwhile it also contribute to improvement elderly people's quality life. Unfortunately, despite advent Internet things and even decreasing price sensors, current proposals are not extensible during runtime meaning that they need be maintained offline by engineers. Therefore, in this paper we discuss how build an...

The fourth industrial revolution is mainly based on the Industrial Internet-of-Things (IoT), connectivity and cyber-physical systems, in which factories should reach important theoretical savings. In this paper, a transition procedure proposed to transform factory ‘Make Order’ (MTO) manufacturing process (comprised of legacy machinery) into smart level 2 (according Industry 4.0) fully aligned its organisational strategic goals that allows savings but without prohibitive cost replacing...

Experts and international organizations hypothesize that the number of cases fatal intimate partner violence against women increased during COVID-19 pandemic, primarily due to social distancing strategies implementation lockdowns reduce spread virus. We described attempted femicide in Chile before (January 2014 February 2020) (March 2020 June 2021) pandemic. The attempted-femicide rate pandemic (incidence ratio: 1.22 [95% confidence interval: 1.04 1.43], p value: 0.016), while remained...

A common problem that mashup developers face is the discovery of APIs suit their needs. This primary task becomes harder, tedious and time-consuming with proliferation new APIs. As humans, we learn by example, following community previous decisions when creating mashups. Most techniques do not consider at all reusing this social information. In paper, propose to combine current (exploration) information (exploitation). Our preliminary results show considering reciprocal influence both...

The academic success of university students is a problem that depends in multi-factorial way on the aspects related to student and career itself. A with this level complexity needs be faced integral approaches, which involves complement numerical quantitative analysis other types analysis. This study uses novel visual-predictive data approach obtain relevant information regarding performance from Peruvian university. joins together domain understanding data-visualization analysis,...

Web mashups are becoming the main approach to build applications. Current approaches enable component selection include description-based techniques and socially generated metadata. The explosive growth of APIs makes increasingly harder selecting appropriate components for each mashup. Unfortunately, rely heavily on quality authors' information, social-based suffer problems like "cold-start" "preferential attachment". This article proposes (1) two new measures ranked fitness candidate...

Due to the high proliferation of web services, selecting best services from functional equivalent service providers have become a real challenge, where quality plays crucial role. But is uncertain, therefore, several researchers applied Fuzzy logic address imprecision (QoS) constraints. Furthermore, market highly dynamic and competitive, are constantly entering exiting this market, they continually improving themselves due competition. Current fuzzy-based techniques expert and/or...

Hesitant fuzzy sets have been proposed as an extension of to address situations in which decision makers exhibit variations their alternatives' assessment values. However, real-world problems, the decision-making process has be accomplished under where these values may also drastically change over time. In this paper, we propose a prioritized aggregation operator combine time sequence hesitant information, time-based hesitancy due changing environment is mitigated. The method applied service...

Deep learning models are part of the family artificial neural networks and, as such, they suffer catastrophic interference when sequentially. In addition, greater number these have a rigid architecture which prevents incremental new classes. To overcome drawbacks, we propose Self-Improving Generative Artificial Neural Network (SIGANN), an end-to-end deep network system can ease forgetting problem this method, introduce novel detection model that automatically detects samples classes, and...

Requirements-aware systems address the need to reason about uncertainty at runtime support adaptation decisions, by representing quality of services (QoS) requirements for service-based (SBS) with precise values in run-time queryable model specification. However, current approaches do not updating specification reflect changes service market, like newly available or improved QoS existing ones. Thus, even if models design-time acceptable they may become obsolete and miss opportunities system...

Mashups are becoming the de facto approach to build customer-oriented Web applications, by combining several APIs into a single lightweight, rich, customized front-end. To help mashup builders choose among plethora of available assemble in their mashups, some existing recommendation techniques rank candidate using popularity (a social measure) or keyword-based measures (whether semantic unverified tags). This article proposes use information on co-usage previous mash ups suggest likely APIs,...

Cryptocurrencies have been receiving the sustained attention of investors since 2009. These new investment vehicles are digitally native, meaning that they traded exclusively on 24/7 digital platforms. Consequently, offer an excellent scenario to test Efficient Market Hypothesis, by developing algorithm-based trading strategies. Such strategies aim beat market. It has previously reported daily returns do not exhibit long range dependence. However, volatility in major cryptocurrencies is...

In datasets, the preponderance of imbalanced classes impedes accurate cyberattack categorization. While high aggregate accuracy is sought, it's paramount to adeptly classify all attack types, especially under-represented ones. Existing methodologies, such as Ensemble techniques and Synthetic Minority Oversampling Technique (SMOTE), address these disparities, yet dynamic nature underrepresented cyberattacks in cybersecurity remains a concern. To this, we introduce nested cascade model...

In most countries, a large percentage of children between the ages eight and thirteen have access to mobile device at home, where monitoring supervision by trusted adult is not enough, so statistics on victimized bullying damage integrity their personal data been increasing considerably.In this work, we design develop serious game, playful application that integrates delivers educational content cybersecurity users aged 8 12 years, allowing them basic ideas about responsibilities use current...

Component-based development is a useful approach for building large, complex software systems. However, component discovery and composition are quite expensive tasks, due to the ever growing number of components in market. This article proposes model providers consumers as multi-agent system, allowing advertise their offerings express requirements within shared quality model. The main contributions this paper propose testable process, which can become active actors seek systems that may...

Service-based systems (SBSs) need to be reconfigured when there is evidence that the selected Web services configurations no further satisfy specifications models and, thus decision-related will updated accordingly.However, such updates performed at right pace.On one hand, if are not quickly enough, reconfigurations required may detected due obsolescence of specification used runtime, which were specified design-time.On other extreme promote premature reconfiguration decisions based on...

Cardiovascular diseases represent the leading cause of death worldwide. Thus, cardiovascular rehabilitation programs are crucial to mitigate deaths caused by this condition each year, mainly in patients with coronary artery disease. COVID-19 was not only a challenge area but also an opportunity open remote or hybrid versions these programs, potentially reducing number who leave due geographical/time barriers. This paper presents method for building prediction model using retrospective and...

Information systems are prone to receiving multiple types of attacks over the network. Therefore, Network Intrusion Detection Systems (NIDSs) analyze behavior network traffic detect anomalies and eventual cyberattacks. The NIDS must be able these cyberattacks in an efficient effective manner based on a set features where it is expected that performance depends both selected machine learning technique used. main goal this work identify most relevant characteristics required detect, with high...