A review of adaptive online learning for artificial neural networks

In real applications learning algorithms have to address several issues such as, huge amount of data, samples which arrive continuously and underlying data generation processes that evolve over time. Classical learning is not always appropriate to work in these environments since independent and indentically distributed data are assumed. Taking into account the requirements of the learning process, systems should be able to modify both their structures and their parameters. In this survey, our aim is to review the developed methodologies for adaptive learning with artificial neural networks, analyzing the strategies that have been traditionally applied over the years. We focus on sequential learning, the handling of the concept drift problem and the determination of the network structure. Despite the research in this field, there are currently no standard methods to deal with these environments and diverse issues remain an open problem.     

Brazil’s new national policy on solid waste: challenges and opportunities

Brazil, one of the world’s largest developing countries, has recently introduced a new solid waste management regulatory policy. This new regulatory policy will have implications for a wide variety of stakeholders and sets the stage for opportunities and lessons to be learned. These issues are discussed in this article.     

Semi-automated and fully automated mammographic density measurement and breast cancer risk prediction

The task of breast density quantification is becoming increasingly relevant due to its association with breast cancer risk. In this work, a semi-automated and a fully automated tools to assess breast density from full-field digitized mammograms are presented. The first tool is based on a supervised interactive thresholding procedure for segmenting dense from fatty tissue and is used with a twofold goal: for assessing mammographic density (MD) in a more objective and accurate way than via visual-based methods and for labeling the mammograms that are later employed to train the fully automated tool. Although most automated methods rely on supervised approaches based on a global labeling of the mammogram, the proposed method relies on pixel-level labeling, allowing better tissue classification and density measurement on a continuous scale. The fully automated method presented combines a classification scheme based on local features and thresholding operations that improve the performance of the classifier. A dataset of 655 mammograms was used to test the concordance of both approaches in measuring MD. Three expert radiologists measured MD in each of the mammograms using the semi-automated tool (DM-Scan). It was then measured by the fully automated system and the correlation between both methods was computed. The relation between MD and breast cancer was then analyzed using a case–control dataset consisting of 230 mammograms. The Intraclass Correlation Coefficient (ICC) was used to compute reliability among raters and between techniques. The results obtained showed an average ICC = 0.922 among raters when using the semi-automated tool, whilst the average correlation between the semi-automated and automated measures was ICC = 0.838. In the case–control study, the results obtained showed Odds Ratios (OR) of 1.38 and 1.50 per 10% increase in MD when using the semi-automated and fully automated approaches respectively. It can therefore be concluded that the automated and semi-automated MD assessments present a good correlation. Both the methods also found an association between MD and breast cancer risk, which warrants the proposed tools for breast cancer risk prediction and clinical decision making. A full version of the DM-Scan is freely available.     

Regulated Necrosis in HeLa Cells Induced by ZnPc Photodynamic Treatment: A New Nuclear Morphology

Photodynamic therapy (PDT) is a cancer treatment modality based on the administration of a photosensitizer (PS), which accumulates preferentially in tumor cells. Subsequent irradiation of the neoplastic area triggers a cascade of photochemical reactions that leads to the formation of highly reactive oxygen species responsible for cell inactivation. Photodynamic treatments in vitro are performed with the PS, zinc-phthalocyanine (ZnPc). The PS is near the plasma membrane during uptake and internalization. Inactivation clearly occurs by a necrotic process, manifested by nuclear pyknosis, negative TUNEL and Annexin V assays and non-relocation of cytochrome c. In contrast, by increasing the incubation time, ZnPc is accumulated in the Golgi apparatus and produces cell inactivation with characteristics of apoptosis and necrosis: TUNEL positive, relocated cytochrome c and negative Annexin V assay. This type of death produces a still undescribed granulated nuclear morphology, which is different from that of necrosis or apoptosis. This morphology is inhibited by necrostatin-1, a specific inhibitor of regulated necrosis.     

Laboratory tests of filtration coefficient of selected materials used in liquidating shafts in collieries

There are a lot of dangers associated with closing mine shafts which may emerge during its liquidation works, and after liquidation of a shaft. The most important of them are: methane hazard, water hazard, and public safety hazard, which are commonly connected with occurrence of sinkholes. In the process of shaft liquidation it is extremely important to choose the right backfill materials, which determine stability of the backfill column and proper drainage of the backfill, which will match or exceed potential flow of water into a shaft. When the water flows into a liquidated shaft the main problem is a change in permeability coefficient of the used backfill materials due to grain degradation resulting from the fall into a shaft and the pressure within the backfill column. The article presents results of laboratory tests on the influence of vertical pressure on filtration coefficient and compressibility of the most commonly used backfill materials. During the tests, samples of the materials were loaded in a hydraulic press, simulating in this way the increase in vertical pressure within the backfill column. Compressibility of a given material and the change in filtration coefficient were assessed.     

Multifunctional Silver‐Exchanged Zeolite Micromotors for Catalytic Detoxification of Chemical and Biological Threats

Multifunctional reactive‐zeolite‐based micromotors have been developed and characterized toward effective and rapid elimination of chemical and biological threats. The incorporation of silver ions (Ag⁺) into aluminosilicate zeolite framework imparts several attractive functions, including strong binding to chemical warfare agents (CWA) followed by effective degradation, and enhanced antibacterial activity. The new zeolite‐micromotors protocol thus combines the remarkable adsorption capacity of zeolites and the efficient catalytic properties of the reactive Ag⁺ ions with the autonomous movement of the zeolite micromotors for an accelerated detoxification of CWA. Furthermore, the high antibacterial activity of Ag⁺ along with the rapid micromotor movement enhances the contact between bacteria and reactive Ag⁺, leading to a powerful “on‐the‐fly” bacteria killing capacity. These attractive adsorptive/catalytic features of the self‐propelled zeolite micromotors eliminate secondary environmental contamination compared to adsorptive micromotors. The distinct cubic geometry of the zeolite micromotors leads to enhanced bubble generation and faster movement, in unique movement trajectories, which increases the fluid convection and highly efficient detoxification of CWA and killing of bacteria. The attractive capabilities of these zeolite micromotors will pave the way for their diverse applications in defense, environmental and biomedical applications in more economical and sustainable manner.     

Analysing green supply chain management practices in Brazil’s electrical/electronics industry using interpretive structural modelling

Industries need to adopt the environmental management concepts in the traditional supply chain management. The green supply chain management (GSCM) is an established concept to ensure environment-friendly activities in industry. This paper identifies the relationship of driving and dependence that exists between GSCM practices with regard to their adoption within Brazilian electrical/electronic industry with the help of interpretive structural modelling (ISM). From the results, we infer that cooperation with customers for eco-design practice is driving other practices, and this practice acts as a vital role among other practices. Commitment to GSCM from senior managers and cooperation with customers for cleaner production occupy the highest level.     

Chlorophyll and Carotenoid Composition in Virgin Olive Oils from Various Spanish Olive Varieties

A study of chlorophyll and carotenoid composition of nine single-variety virgin olive oils from the main Spanish producing regions has shown differences depending on variety and ripening degree of the fruits. Pheophytin a was the major pigment in all the oils studied (44–58% total pigments), followed by lutein (18–38%) and β-carotene (6–17%). The chlorophyll pigments group also included pheophytin b and in some cases chlorophylls a and b . The carotenoid fraction also included the xanthophylls neoxanthin, violaxanthin, luteoxanthin, antheraxanthin, mutatoxanthin and β-cryptoxanthin. The mean provitamin A activity of the oils was 260 μg kg⁻¹ expressed as retinol equivalent. cis -α-Carotene (tentative), mono- and di-esterified xanthophylls and pheophorbide a were pigments exclusive to Arbequina variety, a fact that could be used as a chemo-taxonomic differentiator of the oils of this variety. The ratio between the chlorophyll fraction and the carotenoid fraction was maintained in most cases around 1, demonstrating that the green and yellow fractions were in balance, notwithstanding their greater or lesser total pigment content. The considerable range in the lutein/β-carotene ratio (between 1·3 and 5·1 depending on variety) makes this ratio a differentiator of single-variety oils. Despite the different sources of the oils, some general trends have been shown which suggest what chlorophyll and carotenoid pigments should be expected in an olive oil so as to include it within the denomination ‘virgin’.     

Analysis of the Content of Fatty Acid Methyl Esters in Biodiesel by Fourier-Transform Infrared Spectroscopy: Method and Comparison with Gas Chromatography

The increasing importance of sustainability in energy production has led to a global commitment to the use of fuels derived from renewable biological sources, such as biodiesel produced from plant crops or biomass residues, that do not compete with human food for their production. For a biofuel to be considered biodiesel, it must satisfy the specifications described in the UNE 14214, with the UNE-EN 14103 referring to the determination of fatty acid methyl ester content. This standard applies gas chromatography as an analytical technique. Gas chromatography is a widely used technique in the analysis of methyl ester although it has a number of drawbacks such as: long analysis times, a high consumption of high-quality gases and internal standards, does not allow the analysis of different compounds with the same column, etc. From an industrial production point of view, is necessary to know the fatty acid methyl ester content in biodiesel samples quickly. This paper studies the development of an analytical method using Fourier transform infrared spectroscopy (FTIR) as alternative to gas chromatography (GC), since it is a simple, rapid, and precise analytical technique to quantify fatty acid methyl ester content in biofuel samples.