Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 23.740
Filtrar
1.
J Hazard Mater ; 421: 126688, 2022 01 05.
Artículo en Inglés | MEDLINE | ID: mdl-34315634

RESUMEN

Improper disposal of copper mining wastes can threaten the ecosystem and human health due to the high levels of potentially toxic elements released into the environment. The objective of this study was to determine the properties of Cu mining wastes generated in the eastern Amazon and their potential risks to environment and human health. Samples of forest soil and artisanal/industrial Cu mining wastes were collected and subjected to characterization of properties and pseudo-total concentrations of Al, As, Ba, Cd, Co, Cr, Cu, Fe, Hg, Mn, Mo, Ni, Pb, and Zn, in addition to chemical fractionation of Cu. The pH ranged from near neutrality to alkaline. Pseudo-total concentrations of Cu were high in all wastes, mainly in the artisanal rock waste, with 19,034 mg kg-1, of which 61% is concentrated in the most reactive fractions. Pollution indices indicated that the wastes are highly contaminated by Cu and moderately contaminated by Cr and Ni. However, only the artisanal rock waste is associated with environmental risk. Non-carcinogenic and carcinogenic human health risks were detected, especially from exposure to Cr in the artisanal rock waste. Prevention actions and monitoring of the artisanal mining area are necessary to avoid impacts to the local population.


Asunto(s)
Metales Pesados , Contaminantes del Suelo , Cobre/toxicidad , Ecosistema , Monitoreo del Ambiente , Humanos , Residuos Industriales/análisis , Metales Pesados/análisis , Minería , Medición de Riesgo , Contaminantes del Suelo/análisis
2.
J Hazard Mater ; 421: 126677, 2022 Jan 05.
Artículo en Inglés | MEDLINE | ID: mdl-34332476

RESUMEN

The co-management of different wastewater matrices can lead to synergistic effects in terms of pollutants removal. Here, the co-treatment of real municipal wastewater (MWW) and acid mine drainage (AMD) is comprehensively examined. Under the identified optimum co-treatment condition, i.e., 15 min contact time, 1:7 AMD to MWW liquid-to-liquid ratio, and ambient temperature and pH, the metal content of AMD (e.g., Al, Fe, Mn, Zn) was grossly (~95%) reduced along with sulphate (~92%), while MWW's phosphate content was practically removed (≥99%). The PHREEQC geochemical model predicted the formation of (oxy)-hydroxides, (oxy)-hydro-sulphates, metals hydroxides, and other mineral phases in the produced sludge, which were confirmed using state-of-the-art analytical techniques such as FE-SEM-EDS and XRD. The key mechanisms governing pollutants removal include dilution, precipitation, co-precipitation, adsorption, and crystallization. Beneficiation and valorisation of the produced sludge and co-treated effluent could promote resource recovery paradigms in wastewater management. Overall, the co-treatment of AMD and MWW appear to be feasible, yet not practical due to the excessive volume of MWW that is required to attain the desired treatment quality. Future research could focus on chemical addition for the control of the pH and the use of (photo)-Fenton for enhancing treatment efficiency.


Asunto(s)
Aguas Residuales , Contaminantes Químicos del Agua , Concentración de Iones de Hidrógeno , Minería , Fosfatos , Aguas del Alcantarillado , Eliminación de Residuos Líquidos , Contaminantes Químicos del Agua/análisis
3.
J Hazard Mater ; 421: 126790, 2022 01 05.
Artículo en Inglés | MEDLINE | ID: mdl-34358973

RESUMEN

Acid mine drainage (AMD) system represents one of the most unfavorable habitats for microorganisms due to its low pH and high concentrations of metals. Compared to bacteria and fungi, our understanding regarding the response of soil protozoa to such extremely acidic environments remains limited. This study characterized the structures of protozoan communities inhabiting a terrace heavily contaminated by AMD. The sharp environmental gradient of this terrace was generated by annual flooding from an AMD lake located below, which provided a natural setting to unravel the environment-protozoa interactions. Previously unrecognized protozoa, such as Apicomplexa and Euglenozoa, dominated the extremely acidic soils, rather than the commonly recognized members (e.g., Ciliophora and Cercozoa). pH was the most important factor regulating the abundance of protozoan taxa. Metagenomic analysis of protozoan metabolic potential showed that many functional genes encoding for the alleviation of acid stress and various metabolic pathways were enriched, which may facilitate the survival and adaptation of protozoa to acidic environments. In addition, numerous co-occurrences between protozoa and bacterial or fungal taxa were observed, suggesting shared environmental preferences or potential bio-interactions among them. Future studies are required to confirm the ecological roles of these previously unrecognized protozoa as being important soil microorganisms.


Asunto(s)
Minería , Suelo , Ácidos , Bacterias , Microbiología del Suelo
4.
J Environ Manage ; 301: 113816, 2022 Jan 01.
Artículo en Inglés | MEDLINE | ID: mdl-34571474

RESUMEN

The Mongolian Plateau, home to the world's largest contiguous temperate grasslands, has been known for its vast steppe landscapes and legendary history of the Mongol Empire. However, like temperate grasslands elsewhere around the world, the Mongolian steppe landscapes have been severely degraded by increasing human activities during the past several decades. The main objective of this study was to assess the landscape and ecosystem changes in the Wulagai River Basin (WRB) in Inner Mongolia, where China's last intact steppe ecosystem reportedly resides. Using remote sensing data and landscape metrics, we found that, during 1979-2016, WRB lost about 55 % of wetlands, 76 % of shrublands, and 46 % of sandy-land vegetation, with its most dominant vegetation type shifting from meadow steppe to dry steppe for the first time in history. Human land uses continued to intensify: cropland expanded by about 40 %; impervious surface area increased by almost 34 times; and surface coal mining rampaged through the heartland, tearing up vegetation and sucking up water near and far. The WRB landscape became more diverse compositionally (increasing land cover types), more fragmented ecologically (habitat loss and isolation), and more complex geometrically (anthropogenic and natural landscape elements entangled). Damming, mining, and overgrazing were the major direct drivers for the observed environmental changes. Government-sponsored restoration programs have had positive ecological changes across China, but landscape destruction and fragmentation in the Wulagai River Basin have continued. This dire situation demands urgent government policy intervention and stakeholder-involved governance actions to promote the sustainability of this legendary landscape.


Asunto(s)
Ecosistema , Ríos , China , Conservación de los Recursos Naturales , Monitoreo del Ambiente , Actividades Humanas , Humanos , Minería
5.
J Environ Manage ; 301: 113828, 2022 Jan 01.
Artículo en Inglés | MEDLINE | ID: mdl-34583283

RESUMEN

The application of CPB (Cemented Paste Backfill) can realize the clean, efficient, and safe mining of underground metal mines. Clear understanding on the triaxial mechanical properties of CPB is important to the CPB design and the stability analysis of the backfilled CPB structure. The triaxial mechanical properties of CPB can be significantly affected by the different curing conditions. In this research, triaxial compression tests of the CPB samples were carried out using the GCTS (Geotechnical Consulting & Testing System), and the considered curing conditions include different curing time (1, 3, 7 and 28 days), drainage conditions (drained and undrained) and curing temperatures (20 °C, 35 °C and 45 °C). The measured mechanical parameters were compared and analyzed against the framework of the Mohr-Coulomb criterion. Then, the vertical stress distribution of the backfilled CPB structure was calculated and discussed using the measured mechanical parameters. The results show that with the increase of the lateral constraint ratio (σc/Sd0), the elastoplastic stage of the measured deviator stress versus axial strain curve of CPB sample is gradually obvious. The peak deviator stress (Sdp) and the ultimate axial strain (εu) show the linear and negative exponential increase with the σc/Sd0 respectively. The number of cracks on the fractured surface of the CPB samples gradually decreased with the increase of σc/Sd0. The failure types of CPB samples were changed from tensile failure (σc/Sd0 = 0%) to the mixed tensile-shear failure (σc/Sd0≈10%) and compression-shear failure (σc/Sd0≥20%). Moreover, with the increase of curing time and curing temperature or under the drained curing condition, the peak deviator stress and cohesion (cb) of CPB can be significantly increased, but the corresponding internal friction angle (ϕb) is decreased. The shear mechanical parameters of CPB can significantly affect the vertical stress distribution inside the CPB structure. Therefore, when estimating the vertical stress distribution inside the backfilled CPB structure in engineering practices, it is necessary to focus on the changes of CPB shear parameters (cb and ϕb) caused by different curing conditions.


Asunto(s)
Materiales de Construcción , Sulfuros , Minería , Temperatura
6.
Philos Trans A Math Phys Eng Sci ; 380(2214): 20210125, 2022 Jan 10.
Artículo en Inglés | MEDLINE | ID: mdl-34802278

RESUMEN

The outbreak of the novel coronavirus, COVID-19, has become one of the most severe pandemics in human history. In this paper, we propose to leverage social media users as social sensors to simultaneously predict the pandemic trends and suggest potential risk factors for public health experts to understand spread situations and recommend proper interventions. More precisely, we develop novel deep learning models to recognize important entities and their relations over time, thereby establishing dynamic heterogeneous graphs to describe the observations of social media users. A dynamic graph neural network model can then forecast the trends (e.g. newly diagnosed cases and death rates) and identify high-risk events from social media. Based on the proposed computational method, we also develop a web-based system for domain experts without any computer science background to easily interact with. We conduct extensive experiments on large-scale datasets of COVID-19 related tweets provided by Twitter, which show that our method can precisely predict the new cases and death rates. We also demonstrate the robustness of our web-based pandemic surveillance system and its ability to retrieve essential knowledge and derive accurate predictions across a variety of circumstances. Our system is also available at http://scaiweb.cs.ucla.edu/covidsurveiller/. This article is part of the theme issue 'Data science approachs to infectious disease surveillance'.


Asunto(s)
COVID-19 , Medios de Comunicación Sociales , Minería de Datos , Humanos , Pandemias , SARS-CoV-2
7.
J Environ Manage ; 301: 113835, 2022 Jan 01.
Artículo en Inglés | MEDLINE | ID: mdl-34600421

RESUMEN

Mining of uranium for defense-related purposes has left a substantial legacy of pollution that threatens human and environmental health. Contaminated waters in the arid southwest are of particular concern, as water resource demand and water scarcity issues become more pronounced. The development of remediation strategies to treat uranium impacted waters will become increasingly vital to meet future water needs. Ion flotation is one technology with the potential to address legacy uranium contamination. The green biosurfactant rhamnolipid has been shown to bind uranium and act as an effective collector in ion flotation. In this study, uranium contaminated groundwater (∼440 µg L-1 U) from the Monument Valley processing site in northeast Arizona was used as a model solution to test the uranium removal efficacy of ion flotation with biosynthetic (bio-mRL) and three synthetic monorhamnolipids with varying hydrophobic chain lengths: Rha-C10-C10, Rha-C12-C12, and Rha-C14-C14. At the groundwater's native pH 8, and at an adjusted pH 7, no uranium was removed from solution by any collector. However, at pH 6.5 bio-mRL and Rha-C10-C10 removed 239.2 µg L-1 and 242.4 µg L-1 of uranium, respectively. By further decreasing the pH to 5.5, bio-mRL was able to reduce the uranium concentration to near or below the Environmental Protection Agency maximum contaminant level of 30 µg L-1. For the Rha-C12-C12 and Rha-C14-C14 collector ligands, decreasing the pH to 7 or below reduced the foam stability and quantity, such that these collectors were not suitable for treating this groundwater. To contextualize the results, a geochemical analysis of the groundwater was conducted, and a consideration of uranium speciation is described. Based on this study, the efficacy of monorhamnolipid-based ion flotation in real world groundwater has been demonstrated with suitable solution conditions and collectors identified.


Asunto(s)
Agua Subterránea , Uranio , Contaminantes Radiactivos del Agua , Contaminación Ambiental , Humanos , Minería , Uranio/análisis , Contaminantes Radiactivos del Agua/análisis
8.
Chemosphere ; 286(Pt 1): 131630, 2022 Jan.
Artículo en Inglés | MEDLINE | ID: mdl-34315071

RESUMEN

Anionic polyacrylamide (APAM) has widely been employed in backfill mining to accelerate the sedimentation of fine tailings particles and increase the concentration of tailings slurry. However, APAM inevitably remains in thickened tailings, leading to a nonnegligible influence on the rheological, mechanical, and heavy metal leaching properties of tailings-based cemented paste backfill (CPB). In an effort to solve these issues, the influences of APAM on CPB properties were examined in the present study. Experimental tests such as rheology, uniaxial compressive strength (UCS), toxicity leaching, and microscopy were conducted. The results showed that the presence of APAM first significantly increased the yield stress and viscosity of CPB slurry. APAM slightly improved the early UCS of CPB curing for 7 days but hindered the UCS development of samples cured for 28 days. Moreover, the presence of APAM restrained the hydration reaction, reduced the amounts of hydrated products, increased pore size, and loosed the microstructure of the test samples. Finally, the addition of APAM effectively reduced the leaching of Ag and As, while incremented that of Cu and slightly affected the leaching of Ba. In sum, these findings look promising for the safe production and environmental protection of the mining industry.


Asunto(s)
Materiales de Construcción , Metales Pesados , Resinas Acrílicas , Minería , Reología
9.
Chemosphere ; 286(Pt 3): 131805, 2022 Jan.
Artículo en Inglés | MEDLINE | ID: mdl-34391113

RESUMEN

Phytomining of noble metals (NMs) offers a promising possibility of metal extraction at sites where traditional mining activities or recovering NMs from low-grade minerals are not competitive. In addition to conventional mining, producing NMs from secondary resources strengthening the circular economy has been paid worldwide attention. The review presented in this paper links three scientific areas as the essential elements to form the phytomining chain of NMs. The accumulation of NMs in plants is the first step, referred as the phytoextraction process. This is followed by heightening the concentration of NMs via the enrichment stage. Eventually, although less well understood, extraction methods of NMs from biomass solid remains as well as from diverse secondary sources particularly incineration ashes are discussed that assist to visualize the potential pathways in phytomining.


Asunto(s)
Metales Pesados , Contaminantes del Suelo , Biodegradación Ambiental , Incineración , Metales , Metales Pesados/análisis , Minería , Contaminantes del Suelo/análisis
10.
Sci Total Environ ; 802: 149788, 2022 Jan 01.
Artículo en Inglés | MEDLINE | ID: mdl-34461479

RESUMEN

In Mexico, millions of tons of mining wastes are deposited in the open pit. Their content in potentially toxic elements (PTE) represents an environmental risk. In the tailings, pioneer plant communities are established, associated with a determined diversity of fungi; plants, and fungi are fundamental in the natural rehabilitation of mining wastes. The objective was to evaluate the impact of the natural establishment of two plant species on the microbial activity, on the composition of the fungal community, and on the mitigation of the effect of PTE in a contaminated mine tailing. In a tailing, we selected three sites: one non-vegetated; one vegetated by Reseda luteola, and one vegetated by Asphodelus fistulosus. In the substrates, we conducted a physical and chemical characterization; we evaluated the enzymatic activity, the mineralization of the carbon, and the concentration of PTE. We also determined the fungal diversity in the substrates and in the interior of the roots, and estimated the accumulation of carbon, nitrogen, phosphorus and PTE in plant tissues. The tailings had a high percentage of sand; the non-vegetated site presented the highest electric conductivity, and the plant cover reduced the concentration of PTE in the substrates. Plants increased the carbon content in tailings. The enzymatic activities of ß-glucosidase and dehydrogenase, and the mineralization of carbon were highest at the site vegetated with A. fistulosus. Both plant species accumulated PTE in their tissues and exhibited potential in the phytoremediation of lead (Pb), cadmium (Cd), and copper (Cu). Fungal diversity was more elevated at the vegetated sites than in the bare substrate. Ascomycota prevailed in the substrates; the substrates and the plants shared some fungal taxa, but other taxa were specific. The plant coverage and the rhizosphere promoted the natural attenuation and a rehabilitation of the extreme conditions of the mining wastes, modulated by the plant species.


Asunto(s)
Metales Pesados , Micobioma , Contaminantes del Suelo , Metales Pesados/análisis , Minería , Plantas , Rizosfera , Suelo , Contaminantes del Suelo/análisis
11.
Sci Total Environ ; 804: 150196, 2022 Jan 15.
Artículo en Inglés | MEDLINE | ID: mdl-34798738

RESUMEN

One of the largest environmental disasters worldwide occurred on November 5th, 2015, when the Fundão dam collapsed in Mariana (Minas Gerais State, Southeast Brazil). The tailing mud flooded the Doce River basin and reached the sea in the coast of Espírito Santo State (ES), Southeast Brazil. This coastal region is the habitat of the most isolated population of franciscana dolphins (Pontoporia blainvillei), with the lowest populational census and lowest genetic diversity in Franciscana Management Area Ia (FMA Ia) - 18° 25'S and 21° 17'S. This study aimed to assess the bioaccumulation of trace-elements (As, Cd, Cu, Fe, Hg, Mn, and Zn) in muscle, liver and kidney of franciscana dolphins collected near the Doce River's mouth before (n = 32) and after (n = 19) the tailing mud reached the sea. The Generalized Additive Model (GAM) showed increasing temporal trends of Hg and Zn in muscle and liver after the dam failure, probably related to higher concentrations and bioavailability in the water column and sediments from the Doce River. Declining trends were found for As and Cu muscular and hepatic concentrations and Fe concentrations in kidney due to their lower bioavailability after the disaster, caused by association with tailings mud trapped in the riverbanks and suspended particulate material. Additionally, higher As and Hg concentrations found in the first period of sampling may be due to historical contamination by mining activities. The full extent of the impacts caused by the Fundão dam failure is still unknown. However, due to their rapid increase and remobilization process, toxic effects can be induced in the biota by these elements. Elements' bioaccumulation in this study contributes to the knowledge of franciscana dolphins from FMA Ia. Considering the conservation concern regarding this franciscana population and its scarce knowledge, the impact of this disaster can be alarming for species conservation.


Asunto(s)
Desastres , Delfines , Oligoelementos , Contaminantes Químicos del Agua , Animales , Bioacumulación , Brasil , Monitoreo del Ambiente , Minería , Ríos , Oligoelementos/análisis , Contaminantes Químicos del Agua/análisis
12.
Sci Total Environ ; 804: 150218, 2022 Jan 15.
Artículo en Inglés | MEDLINE | ID: mdl-34798744

RESUMEN

In this study, knowledge gaps on Sb concentration in rocks, ores, tailings, soil, river water, sediments, and crops of mine areas were identified and discussed in terms of contamination levels, spatial distribution, and environmental effects. Accordingly, Xunyang Hg-Sb mine, the largest Hg-Sb deposit in China as research region in this study, field sampling and laboratory analysis were conducted. The results showed elevated concentrations of Sb in the soil, sediment, and river water. The X-ray diffraction analysis indicated that the main minerals of the rocks were quartz, dolomite, calcite, and margarite. Based on the TESCAN integrated mineral analyzer analysis, the main ore minerals in the Gongguan mine were dolomite (93.97%), cinnabar (2.50%), stibnite (2.48%), calcite (0.38%), and quartz (0.38%). The µ-XRF analysis indicated that Sb distribution was similar to those of S and O, instead of those of Hg and As. The clear spatial variation of Sb concentration in environmental media, mines, tailings, and settling ponds affected Sb accumulation. Actinobacteriota, Proteobacteria, Acidobacteriota, and Chloroflexi were the dominant phyla in the soil. Patescibacteria, Proteobacteria, and Bdellovibrionota were negatively correlated with Sb in the soil (p < 0.05). Exposure to Sb through maize grain and cabbage consumption poses serious non-carcinogenic health risk for residents. This work provides a scientific basis for the environmental quality assessment of Sb mine areas and development of applicable guidelines.


Asunto(s)
Mercurio , Contaminantes del Suelo , Antimonio/análisis , China , Monitoreo del Ambiente , Mercurio/análisis , Minería , Suelo , Contaminantes del Suelo/análisis
13.
BMC Med Inform Decis Mak ; 21(Suppl 9): 317, 2021 11 16.
Artículo en Inglés | MEDLINE | ID: mdl-34789262

RESUMEN

BACKGROUND: A lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB is a necessary part of the downstream application such as disease diagnosis and prescription of drugs. Such demand becomes more urgent in colloquial and informal situations like online medical consultation, where the medical language is more casual and vaguer. In this article, we propose an unsupervised method to link the Chinese medical symptom mentions to the ICD10 classification in a colloquial background. METHODS: We propose an unsupervised entity linking model using multi-instance learning (MIL). Our approach builds on a basic unsupervised entity linking method (named BEL), which is an embedding similarity-based EL model in this paper, and uses MIL training paradigm to boost the performance of BEL. First, we construct a dataset from an unlabeled large-scale Chinese medical consultation corpus with the help of BEL. Subsequently, we use a variety of encoders to obtain the representations of mention-context and the ICD10 entities. Then the representations are fed into a ranking network to score candidate entities. RESULTS: We evaluate the proposed model on the test dataset annotated by professional doctors. The evaluation results show that our method achieves 60.34% accuracy, exceeding the fundamental BEL by 1.72%. CONCLUSIONS: We propose an unsupervised entity linking method to the entity linking in the medical domain, using MIL training manner. We annotate a test set for evaluation. The experimental results show that our model behaves better than the fundamental model BEL, and provides an insight for future research.


Asunto(s)
Minería de Datos , Procesamiento de Lenguaje Natural , Humanos , Bases del Conocimiento , Lenguaje
14.
Comput Intell Neurosci ; 2021: 1194565, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34804137

RESUMEN

Food quality and safety issues occurred frequently in recent years, which have attracted more and more attention of social and international organizations. Considering the increased quality risk in the food supply chain, many researchers have applied various information technologies to develop real-time risk identification and traceability systems (RITSs) for preferable food safety guarantee. This paper presents an innovative approach by utilizing the deep-stacking network method for hazardous risk identification, which relies on massive multisource data monitored by the Internet of Things timely in the whole food supply chain. The aim of the proposed method is to help managers and operators in food enterprises to find accurate risk levels of food security in advance and to provide regulatory authorities and consumers with potential rules for better decision-making, thereby maintaining the safety and sustainability of food product supply. The verification experiments show that the proposed method has the best performance in terms of prediction accuracy up to 97.62%, meanwhile achieves the appropriate model parameters only up to 211.26 megabytes. Moreover, the case analysis is implemented to illustrate the outperforming performance of the proposed method in risk level identification. It can effectively enhance the RITS ability for assuring food supply chain security and attaining multiple cooperation between regulators, enterprises, and consumers.


Asunto(s)
Minería de Datos , Abastecimiento de Alimentos
15.
Stud Health Technol Inform ; 287: 3-7, 2021 Nov 18.
Artículo en Inglés | MEDLINE | ID: mdl-34795068

RESUMEN

Federated learning has a great potential to create solutions working over different sources without data transfer. However current federated methods are not explainable nor auditable. In this paper we propose a Federated data mining method to discover association rules. More accurately, we define what we consider as interesting itemsets and propose an algorithm to obtain them. This approach facilitates the interoperability and reusability, and it is based on the accessibility to data. These properties are quite aligned with the FAIR principles.


Asunto(s)
Algoritmos , Privacidad , Minería de Datos , Proyectos de Investigación
16.
Artículo en Inglés | MEDLINE | ID: mdl-34769870

RESUMEN

Mining dam failures have increased worldwide since the 1980s. Two large mining dam failures occurred recently in Mariana and Brumadinho, both in the state of Minas Gerais, Brazil. We hypothesize that there were significant differences in legal post-disaster decisions. The aim of this article is to understand the similarities and differences of post-disaster actions and controversies in Mariana and Brumadinho. We reviewed 686 news reports about court decisions and settlement agreements from the websites of state and federal courts and judicial institutions. After classifying the reports using an adapted protocol from a media health observatory, we conducted a thematic analysis. Our analysis suggests that there were significant differences in legal post-disaster decisions in the cases of Mariana and Brumadinho. In Mariana, there was privatization of post-disaster management, with the creation of the Renova Foundation, a mediated indemnity program, lack of access to information for those affected, and uncertainties in health and resettlement issues. In Brumadinho, there was faster implementation of the recovery and compensation measures, faster recognition of affected parties, and stronger participation of the population since the first hearings. Even though there were particularities in post-disaster management, the ultimate goal of the corporations responsible for the disasters was to protect their profits.


Asunto(s)
Desastres , Minería , Brasil
17.
Sensors (Basel) ; 21(21)2021 Nov 04.
Artículo en Inglés | MEDLINE | ID: mdl-34770639

RESUMEN

A wide range of applications based on sequential data, named time series, have become increasingly popular in recent years, mainly those based on the Internet of Things (IoT). Several different machine learning algorithms exploit the patterns extracted from sequential data to support multiple tasks. However, this data can suffer from unreliable readings that can lead to low accuracy models due to the low-quality training sets available. Detecting the change point between high representative segments is an important ally to find and thread biased subsequences. By constructing a framework based on the Augmented Dickey-Fuller (ADF) test for data stationarity, two proposals to automatically segment subsequences in a time series were developed. The former proposal, called Change Detector segmentation, relies on change detection methods of data stream mining. The latter, called ADF-based segmentation, is constructed on a new change detector derived from the ADF test only. Experiments over real-file IoT databases and benchmarks showed the improvement provided by our proposals for prediction tasks with traditional Autoregressive integrated moving average (ARIMA) and Deep Learning (Long short-term memory and Temporal Convolutional Networks) methods. Results obtained by the Long short-term memory predictive model reduced the relative prediction error from 1 to 0.67, compared to time series without segmentation.


Asunto(s)
Aprendizaje Automático , Redes Neurales de la Computación , Algoritmos , Minería de Datos , Bases de Datos Factuales
18.
Artículo en Inglés | MEDLINE | ID: mdl-34769535

RESUMEN

BACKGROUND: Health equity features prominently in the 2030 Agenda for Sustainable Development, yet there are wide disparities in health between and within countries. In settings of natural resource extraction (e.g., industrial mines), the health of surrounding communities is affected through myriad changes in the physical, social, and economic environment. How changes triggered by such projects translate into health inequities is poorly understood. METHODS: This qualitative study explores potential layers of inequities by systematically coding perceived inequities of affected communities. Drawing on the framework method, we thematically analyzed data from 83 focus group discussions, which enrolled 791 participants from 10 study sites in Burkina Faso, Mozambique, and Tanzania. RESULTS: Participants perceived inequities related to their individual characteristics, intermediate factors acting on the community level, and structural conditions. Due to environmental pollution and land loss, participants were concerned about unsecured livelihoods. Positive impacts, such as job opportunities at the mine, remained scarce for local communities and were claimed not to be equally distributed among community members. CONCLUSION: Extractive industries bear considerable risks to widen existing health gaps. In order to create equal opportunities among affected populations, the wider determinants of health must be considered more explicitly in the licensing process of resource extraction projects.


Asunto(s)
Equidad en Salud , Minería , Burkina Faso , Humanos , Mozambique , Tanzanía
19.
Artículo en Inglés | MEDLINE | ID: mdl-34769651

RESUMEN

Mining activities are among the most long-lasting anthropogenic pressures on streams and rivers. Therefore, detecting different benthic macroinvertebrate assemblages in the areas recovered from mining activities is essential to establish conservation and management plans for improving the freshwater biodiversity in streams located near mining areas. We compared the stability of benthic macroinvertebrate communities between streams affected by mining activities (Hwangjicheon: NHJ and Cheolamcheon: NCA) and the least disturbed stream (Songjeonricheon: NSJ) using network analysis, self-organizing map, and indicator species analysis. Species richness was lowest at sites where stream sediments were reddened or whitened due to mining impacts in NHJ and NCA. Among functional feeding groups, the ratio of scrapers was lower (i.e., NHJ) or not observed (i.e., NCA) in the affected sites by mining. The networks (species interactions) were less connected in NHJ and NCA than in NSJ, indicating that community stability decreased in the area affected by mining activity. We identified five groups based on the similarity of benthic macroinvertebrate communities according to the gradients of mining impacts using a self-organizing map. the samples from the reference stream (clusters 1 and 5), sites located near the mining water inflow area (cluster 4), sites where stream sediments acid-sulfated (cluster 2), and sites that had recovered from mining impacts (cluster 3). Among the 40 taxa selected as indicators defined from the five clusters in self-organizing map, only few (Physa acuta, Tipula KUa, and Nemoura KUb) indicator species were selected in each cluster representing the mining-impacted sites. Our results highlighted that the benthic macroinvertebrate community complexity was lower in streams affected by mining activity. Furthermore, the range of disturbed areas in the streams, where conservation and management plans should be prioritized, can be quantified by examining alterations in the benthic macroinvertebrate community.


Asunto(s)
Monitoreo del Ambiente , Invertebrados , Animales , Ecosistema , Minería , Ríos
20.
J Med Internet Res ; 23(11): e28999, 2021 11 02.
Artículo en Inglés | MEDLINE | ID: mdl-34726612

RESUMEN

BACKGROUND: There is huge variability in the way that individuals with tinnitus respond to interventions. These experiential variations, together with a range of associated etiologies, contribute to tinnitus being a highly heterogeneous condition. Despite this heterogeneity, a "one size fits all" approach is taken when making management recommendations. Although there are various management approaches, not all are equally effective. Psychological approaches such as cognitive behavioral therapy have the most evidence base. Managing tinnitus is challenging due to the significant variations in tinnitus experiences and treatment successes. Tailored interventions based on individual tinnitus profiles may improve outcomes. Predictive models of treatment success are, however, lacking. OBJECTIVE: This study aimed to use exploratory data mining techniques (ie, decision tree models) to identify the variables associated with the treatment success of internet-based cognitive behavioral therapy (ICBT) for tinnitus. METHODS: Individuals (N=228) who underwent ICBT in 3 separate clinical trials were included in this analysis. The primary outcome variable was a reduction of 13 points in tinnitus severity, which was measured by using the Tinnitus Functional Index following the intervention. The predictor variables included demographic characteristics, tinnitus and hearing-related variables, and clinical factors (ie, anxiety, depression, insomnia, hyperacusis, hearing disability, cognitive function, and life satisfaction). Analyses were undertaken by using various exploratory machine learning algorithms to identify the most influencing variables. In total, 6 decision tree models were implemented, namely the classification and regression tree (CART), C5.0, GB, XGBoost, AdaBoost algorithm and random forest models. The Shapley additive explanations framework was applied to the two optimal decision tree models to determine relative predictor importance. RESULTS: Among the six decision tree models, the CART (accuracy: mean 70.7%, SD 2.4%; sensitivity: mean 74%, SD 5.5%; specificity: mean 64%, SD 3.7%; area under the receiver operating characteristic curve [AUC]: mean 0.69, SD 0.001) and gradient boosting (accuracy: mean 71.8%, SD 1.5%; sensitivity: mean 78.3%, SD 2.8%; specificity: 58.7%, SD 4.2%; AUC: mean 0.68, SD 0.02) models were found to be the best predictive models. Although the other models had acceptable accuracy (range 56.3%-66.7%) and sensitivity (range 68.6%-77.9%), they all had relatively weak specificity (range 31.1%-50%) and AUCs (range 0.52-0.62). A higher education level was the most influencing factor for ICBT outcomes. The CART decision tree model identified 3 participant groups who had at least an 85% success probability following the undertaking of ICBT. CONCLUSIONS: Decision tree models, especially the CART and gradient boosting models, appeared to be promising in predicting ICBT outcomes. Their predictive power may be improved by using larger sample sizes and including a wider range of predictive factors in future studies.


Asunto(s)
Terapia Cognitivo-Conductual , Acúfeno , Minería de Datos , Árboles de Decisión , Humanos , Internet , Aprendizaje Automático , Acúfeno/terapia
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA
...