The evaluation of white blood cells is essential to assess the quality of the human immune system; however, the assessment of the blood smear depends on the pathologist’s expertise. Most machine learning tools make a one-level classification for white blood cell classification. This work presents a two-stage hybrid multi-level scheme that efficiently classifies four cell groups: lymphocytes and monocytes (mononuclear) and segmented neutrophils and eosinophils (polymorphonuclear). At the first level, a Faster R-CNN network is applied for the identification of the region of interest of white blood cells, together with the separation of mononuclear cells from polymorphonuclear cells. Once separated, two parallel convolutional neural networks with the MobileNet structure are used to recognize the subclasses in the second level. The results obtained using Monte Carlo cross-validation show that the proposed model has a performance metric of around 98.4% (accuracy, recall, precision, and F1-score). The proposed model represents a good alternative for computer-aided diagnosis (CAD) tools for supporting the pathologist in the clinical laboratory in assessing white blood cells from blood smear images.

Nowadays, ageing related diseases represent one of the most relevant challenges for developed countries. The use of healthcare remote technology may allow reducing most of the management of the chronic diseases meanwhile it may also contribute to the improvement of elderly people's quality of life. Unfortunately, despite the advent of Internet of things and the even decreasing price of sensors, current proposals are not extensible during runtime meaning that they need to be maintained offline by engineers. Therefore, in this paper we discuss how to build an ad-hoc extensible (during runtime) healthcare monitoring system by using low cost wireless sensors and already existent Internet of things technology as communication platform. Moreover, we present a prototype of a basic healthcare remote monitoring system, which alerts, in real time, patients' relatives or medical doctors that an elderly people is experienced a problem that could need medical attention or hospitalization.

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 is proposed to transform a factory based on a ‘Make to Order’ (MTO) manufacturing process (comprised mainly of legacy machinery) into a smart factory level 2 (according to the Industry 4.0) fully aligned to its organisational strategic goals that allows to reach the theoretical savings but without the prohibitive cost of replacing legacy-based machinery by new one. This proposal was validated in a real case study during four months where operation efficiency was improved and the energy consumption, the projected costs and the percentage of human errors were reduced in 17%, 3% and 70%, respectively.

A common problem that mashup developers face is the discovery of APIs that suit their needs. This primary task becomes harder, tedious and time-consuming with the proliferation of 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 this paper, we propose to combine current discovery techniques (exploration) with social information (exploitation). Our preliminary results show that by considering the reciprocal influence of both sources, the discovery process reveals APIs that would remain with low rank because the preferential attachment (popularity) and/or the lack of better descriptions (discovery techniques). We present a case study focusing on a public Web-based API registry.

Experts and international organizations hypothesize that the number of cases of fatal intimate partner violence against women increased during the COVID-19 pandemic, primarily due to social distancing strategies and the implementation of lockdowns to reduce the spread of the virus. We described cases of attempted femicide and femicide in Chile before (January 2014 to February 2020) and during (March 2020 to June 2021) the pandemic. The attempted-femicide rate increased during the pandemic (incidence rate ratio: 1.22 [95% confidence interval: 1.04 to 1.43], p value: 0.016), while the rate of femicide cases remained unchanged. When a comparison between attempted-femicide and femicide cases was performed, being a foreigner, having an intimate partner relationship with a perpetrator aged 40 years or more, and the use of firearms during the assault were identified as factors associated independently with a higher probability of being a fatal victim in Chile. In conclusion, this study emphasizes that attempted femicide and femicide continued to occur frequently in family contexts both before and during the COVID-19 pandemic.