Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 22.237
Filtrar
1.
Water Sci Technol ; 80(3): 466-477, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31596258

RESUMO

Wetlands are among the most productive ecosystems that provide services ranging from flood control to climate change mitigation. Wetlands are also critical habitats for the survival of numerous plant and animal species. In this study, we used satellite remote sensing techniques for classification and change detection at an internationally important wetland (Ramsar Site) in Turkey. Sultan Marshes is located at the center of semi-arid Develi closed basin. The wetlands have undergone significant changes since the 1980s due to changes in water flow regimes, but changes in recent years have not been sufficiently explored yet. In this study, we focused on the changes from 2005 to 2012. Two multispectral ASTER images with spatial resolution of 15 m, acquired on June 11, 2005 and May 20, 2012, were used in the analyses. After geometric correction, the images were classified into four information classes, namely water, marsh, agriculture, and steppe. The applicability of three classification methods (i.e. maximum likelihood (MLH), multi-layer perceptron type artificial neural networks (ANN) and support vector machines (SVM)) was assessed. The differences in classification accuracies were evaluated by the McNemar's test. The changes in the Sultan Marshes were determined by the post classification comparison method using the most accurate classified images. The results showed that the highest overall accuracy in image classifications was achieved with the SVM method. It was observed that marshes and steppe areas decreased while water and agricultural areas expanded from 2005 to 2012. These changes could be the results of water transfers to the marshes from neighboring watershed.


Assuntos
Monitoramento Ambiental/métodos , Máquina de Vetores de Suporte , Áreas Alagadas , Conservação dos Recursos Naturais , Ecossistema , Eugenol , Redes Neurais (Computação) , Turquia , Óxido de Zinco
2.
Water Sci Technol ; 80(2): 213-222, 2019 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-31537757

RESUMO

It is highly essential that municipal wastewater is treated before its discharge and reuse in order to meet the standard requirements for safe marine life and for farming and industries. It is beneficial to use reclaimed water, since availability of fresh water is inadequate. An investigation was conducted on the Jamnagar Municipal Corporation Sewage Treatment Plant (JMC-STP) to develop a feedforward artificial neural network (FF-ANN) model. It is an alternate for the modelling/ prediction of JMC-STP to circumvent over the versatile physical, chemical, and biological treatment process simulations. The models were developed to predict effluent quality parameters through influent characteristics. The parameters are pH, biochemical oxygen demand (BOD), chemical oxygen demand (COD), total suspended solids (TSS), total Kjeldahl nitrogen (TKN), ammonium nitrogen (AN) and total phosphorus (TP). The correlation coefficient RTRAINING and RALL were calculated for all parametric models. The MAD (mean absolute deviation), MSE (mean square error), RMSE (root mean square error) and MAPE (mean absolute percentage error) were evaluated for FF-ANN models. This proves to be a useful tool for the plant management to optimize the treatment quality as it enhances the performance and reliability of the plant. The simulation results were validated through the measured values.


Assuntos
Redes Neurais (Computação) , Eliminação de Resíduos Líquidos , Análise da Demanda Biológica de Oxigênio , Nitrogênio , Reprodutibilidade dos Testes , Esgotos
3.
Water Sci Technol ; 80(2): 243-253, 2019 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-31537760

RESUMO

Wastewater flow forecasting is key for proper management of wastewater treatment plants (WWTPs). However, to predict the amount of incoming wastewater in WWTPs, wastewater engineers face challenges arising from numerous complexities and uncertainties, such as the nonlinear precipitation-runoff relationships in combined sewer systems, unpredictability due to aging infrastructure, and frequently inconsistent data quality. To address such challenges, a time series analysis model (i.e., the autoregressive integrated moving average, ARIMA) and an artificial neural network model (i.e., the multilayer perceptron neural network, MLPNN) were developed for predicting wastewater inflow. A case study of the Barrie Wastewater Treatment Facility in Barrie, Canada, was carried out to demonstrate the performance of the proposed models. Fifteen-minute flow data over a period of 1 year were collected, and the resampled daily flow data were used to train and validate the developed models. The model performances were examined using root mean square error, mean absolute percentage error, coefficient of determination, and Nash-Sutcliffe efficiency. The results indicate that both models provided reliable forecasts, while ARIMA showed a slightly better performance than MLPNN in this case study. The proposed models can provide useful decision support for the optimization and management of WWTPs.


Assuntos
Modelos Estatísticos , Redes Neurais (Computação) , Águas Residuárias/estatística & dados numéricos , Movimentos da Água , Canadá , Previsões
4.
An Acad Bras Cienc ; 91(3): e20180424, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31553364

RESUMO

Abstract: Cardiovascular diseases (CVDs) are leading causes of death in the world, owing to noticeable incidence and mortality. Traditional Chinese Medicine (TCM) SINI Decoction (SND) is used to prevent and treat CVDs, which has attracted extensive attention for its moderate and little side effects. However, the involved molecular mechanisms are exceedingly complicated and remain unclear. Systems pharmacology, as a novel approach that integrates systems biology and pharmacology plays a significant role in investigating the molecular mechanism of TCM. In systems pharmacology approach, we use to systematically uncover the mechanisms of action in Chinese medicinal formula SND as an effective treatment for CVDs, which mainly includes:1) molecular database building; 2) ADME evaluation; 3) target-fishing 4) network construction and analysis. The results show that 78 underlying valid ingredients and their corresponding 71 direct targets of SND were obtained. And SND take part in cardiomyocyte protection, blood pressure regulation, and lipid regulation module in treatment of CVDs by cooperative way. Systems pharmacology as an emerging field that investigates the molecular mechanisms of TCM through pharmacokinetic evaluation target prediction, and pathway analysis, which will facilitate the development of traditional Chinese herbs in modern medicine.


Assuntos
Doenças Cardiovasculares/tratamento farmacológico , Medicamentos de Ervas Chinesas/química , Medicina Tradicional Chinesa , Redes Neurais (Computação) , Biologia de Sistemas/métodos , Humanos , Modelos Biológicos
5.
J Chem Phys ; 151(8): 084106, 2019 Aug 28.
Artigo em Inglês | MEDLINE | ID: mdl-31470712

RESUMO

A novel data-based machine learning algorithm for predicting amyloid aggregation rates is reported in this paper. Based on a highly nonlinear projection from 16 intrinsic features of a protein and 4 extrinsic features of the environment to the protein aggregation rate, a feedforward fully connected neural network (FCN) with one hidden layer is trained on a dataset composed of 21 different kinds of amyloid proteins and tested on 4 rest proteins. FCN shows a much better performance than traditional algorithms, such as multivariable linear regression and support vector regression, with an average accuracy higher than 90%. Furthermore, by the correlation analysis and the principal component analysis, seven key features, folding energy, HP patterns for helix, sheet and helices cross membrane, pH, ionic strength, and protein concentration, are shown to constitute a minimum feature set for characterizing the amyloid aggregation kinetics.


Assuntos
Amiloide/química , Aprendizado de Máquina , Agregados Proteicos , Cinética , Redes Neurais (Computação)
6.
Bioresour Technol ; 293: 122103, 2019 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-31505391

RESUMO

Efficient quantification of interfacial energy related with membrane fouling represents the primary interest in membrane bioreactors (MBRs) as interfacial energy determines foulant layer formation. In this study, radial basis function (RBF) artificial neural networks (ANNs) with five related factors as input variables were applied to quantify interfacial energy with randomly rough membrane surface. It was found that, RBF ANNs could well capture the complex non-linear relationships between the related factors and interfacial energy. RBF ANN quantification showed high regression coefficient and accuracy, suggesting its high capacity to quantify interfacial energy. Compared to at least one-week time consumption of the advanced extensive Derjaguin-Landau-Verwey-Overbeek (XDLVO) approach, quantification by RBF ANNs only took several seconds for a same case, indicating the high efficiency of RBF ANNs. Moreover, the abilities of RBF ANNs can be further improved. The robust RBF ANNs proposed paved a new way to study membrane fouling in MBRs.


Assuntos
Reatores Biológicos , Membranas Artificiais , Redes Neurais (Computação) , Fenômenos Físicos , Software
7.
Stud Health Technol Inform ; 267: 126-133, 2019 Sep 03.
Artigo em Inglês | MEDLINE | ID: mdl-31483264

RESUMO

Magnetic Resonance Fingerprinting (MRF) is an imaging technique acquiring unique time signals for different tissues. Although the acquisition is highly accelerated, the reconstruction time remains a problem, as the state-of-the-art template matching compares every signal with a set of possible signals. To overcome this limitation, deep learning based approaches, e.g. Convolutional Neural Networks (CNNs) have been proposed. In this work, we investigate the applicability of Recurrent Neural Networks (RNNs) for this reconstruction problem, as the signals are correlated in time. Compared to previous methods based on CNNs, RNN models yield significantly improved results using in-vivo data.


Assuntos
Algoritmos , Redes Neurais (Computação) , Bases de Dados Genéticas , Espectroscopia de Ressonância Magnética
8.
Stud Health Technol Inform ; 267: 150-155, 2019 Sep 03.
Artigo em Inglês | MEDLINE | ID: mdl-31483267

RESUMO

Informal caregivers often complain about missing knowledge. A knowledge-based personalized educational system is developed, which provides caregiving relatives with the information needed. Yet, evaluation against domain experts indicated, that parts of the knowledge-base are incorrect. To overcome these problems the system can be extended by a learning capacity and then be trained further utilizing feedback from real informal caregivers. To extend the existing system an artificial neural network was trained to represent a large part of the knowledge-based approach. This paper describes the found artificial neural network's structure and the training process. The found neural network structure is not deep but very wide. The training terminated after 374.700 epochs with a mean squared error of 7.731 ∗ 10-8 for the end validation set. The neural network represents the parts of the knowledge-based approach and can now be retrained with user feedback, which will be collected during a system test in April and May 2019.


Assuntos
Bases de Conhecimento , Redes Neurais (Computação)
9.
Stud Health Technol Inform ; 267: 181-186, 2019 Sep 03.
Artigo em Inglês | MEDLINE | ID: mdl-31483271

RESUMO

Gene expression data is commonly available in cancer research and provides a snapshot of the molecular status of a specific tumor tissue. This high-dimensional data can be analyzed for diagnoses, prognoses, and to suggest treatment options. Machine learning based methods are widely used for such analysis. Recently, a set of deep learning techniques was successfully applied in different domains including bioinformatics. One of these prominent techniques are convolutional neural networks (CNN). Currently, CNNs are extending to non-Euclidean domains like graphs. Molecular networks are commonly represented as graphs detailing interactions between molecules. Gene expression data can be assigned to the vertices of these graphs, and the edges can depict interactions, regulations and signal flow. In other words, gene expression data can be structured by utilizing molecular network information as prior knowledge. Here, we applied graph CNN to gene expression data of breast cancer patients to predict the occurrence of metastatic events. To structure the data we utilized a protein-protein interaction network. We show that the graph CNN exploiting the prior knowledge is able to provide classification improvements for the prediction of metastatic events compared to existing methods.


Assuntos
Neoplasias da Mama , Aprendizado Profundo , Humanos , Aprendizado de Máquina , Metástase Neoplásica , Redes Neurais (Computação)
10.
Medicine (Baltimore) ; 98(33): e16863, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31415420

RESUMO

Heart rate variability (HRV) is an objective measure of emotional regulation. This study aimed to estimate the accuracy with which an artificial neural network (ANN) algorithm could classify emotions using HRV data that were obtained using wristband heart rate monitors.Four emotions were evoked during gameplay: pleasure, happiness, fear, and anger. Seven normalized HRV features (i.e., 3 time-domain features, 3 frequency-domain features, and heart rate), which yielded 29,727 segments during gameplay, were collected and analyzed first by statistics and then classified by the trained ANN model.General linear model adjusted for individual differences in HRV showed that all HRV features significantly differed across emotions, despite disparities in their magnitudes and associations. When compared to neutral status (i.e., no emotion evoked), the mean of R-R interval was significantly higher for pleasure and fear but lower for happiness and anger. In addition, pleasure evidenced the HRV features that suggested a superior parasympathetic to sympathetic activation. Happiness was associated with a prominent sympathetic activation. These statistical findings suggest that HRV features significantly differ across emotions evoked by gameplay. When further utilizing ANN-based emotion classification, the accuracy rates for prediction were above 75.0% across the 4 emotions with accuracy rates for classification of paired emotions ranging from 82.0% to 93.4%.For classifying emotion in an individual person, the trained ANN model utilizing HRV features yielded a high accuracy rate in our study. ANN is a time-efficient and accurate means to classify emotions using HRV data obtained from wristband heart rate monitors. Thus, this integrated platform can help monitor and quantify human emotions and physiological biometrics.


Assuntos
Ira/fisiologia , Medo/fisiologia , Felicidade , Frequência Cardíaca/fisiologia , Redes Neurais (Computação) , Prazer/fisiologia , Adulto , Algoritmos , Humanos , Masculino , Smartphone , Jogos de Vídeo/psicologia , Dispositivos Eletrônicos Vestíveis , Adulto Jovem
11.
Stud Health Technol Inform ; 264: 1783-1784, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31438342

RESUMO

Patients' hospital length of stay (LOS) as a surgical outcome is important indicator of quality of care. We used EMR data to build artificial neural network models to better understand the impact of cold weather on outcome of first surgeries in a day in comparison to a matched cohort receiving surgical treatment in warm days. We found that LOS for first-in-a-day cardiac and orthopedic surgical cases are longer in very cold days.


Assuntos
Tempo de Internação , Redes Neurais (Computação) , Tempo (Meteorologia) , Estudos de Coortes , Humanos , Estudos Retrospectivos , Resultado do Tratamento
12.
BMC Bioinformatics ; 20(1): 415, 2019 Aug 06.
Artigo em Inglês | MEDLINE | ID: mdl-31387547

RESUMO

BACKGROUND: Predicting the effect of drug-drug interactions (DDIs) precisely is important for safer and more effective drug co-prescription. Many computational approaches to predict the effect of DDIs have been proposed, with the aim of reducing the effort of identifying these interactions in vivo or in vitro, but room remains for improvement in prediction performance. RESULTS: In this study, we propose a novel deep learning model to predict the effect of DDIs more accurately.. The proposed model uses autoencoders and a deep feed-forward network that are trained using the structural similarity profiles (SSP), Gene Ontology (GO) term similarity profiles (GSP), and target gene similarity profiles (TSP) of known drug pairs to predict the pharmacological effects of DDIs. The results show that GSP and TSP increase the prediction accuracy when using SSP alone, and the autoencoder is more effective than PCA for reducing the dimensions of each profile. Our model showed better performance than the existing methods, and identified a number of novel DDIs that are supported by medical databases or existing research. CONCLUSIONS: We present a novel deep learning model for more accurate prediction of DDIs and their effects, which may assist in future research to discover novel DDIs and their pharmacological effects.


Assuntos
Aprendizado Profundo , Interações de Medicamentos , Modelos Teóricos , Área Sob a Curva , Bases de Dados Factuais , Humanos , Redes Neurais (Computação) , Máquina de Vetores de Suporte
13.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi ; 36(4): 677-683, 2019 Aug 25.
Artigo em Chinês | MEDLINE | ID: mdl-31441271

RESUMO

With the development of image-guided surgery and radiotherapy, the demand for medical image registration is stronger and the challenge is greater. In recent years, deep learning, especially deep convolution neural networks, has made excellent achievements in medical image processing, and its research in registration has developed rapidly. In this paper, the research progress of medical image registration based on deep learning at home and abroad is reviewed according to the category of technical methods, which include similarity measurement with an iterative optimization strategy, direct estimation of transform parameters, etc. Then, the challenge of deep learning in medical image registration is analyzed, and the possible solutions and open research are proposed.


Assuntos
Aprendizado Profundo , Diagnóstico por Imagem , Redes Neurais (Computação) , Processamento de Imagem Assistida por Computador , Pesquisa
14.
Clin Exp Rheumatol ; 37 Suppl 118(3): 133-139, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31464678

RESUMO

OBJECTIVES: The aim of the present study was to verify whether artificial neural networks (ANNs) might help to elucidate the mechanisms underlying the increased prevalence of cardiovascular events (CV) in primary Sjögren's syndrome (pSS). METHODS: 408 pSS patients (395 F: 13 M), with a mean age of 61 (±14) years and mean disease duration of 8.8 (±7.8) years were retrospectively included. CV risk factors and events were analysed and correlated with the other pSS clinical and serological manifestations by using both a traditional statistical approach (i.e. Agglomerative Hierarchical Clustering (AHC)) and Auto-CM, a data mining tool based on ANNs. RESULTS: Five percent of pSS patients experienced one or more CV events, including heart failure (8/408), transient ischaemic attack (6/408), stroke (4/408), angina (4/408), myocardial infarction (3/408) and peripheral obliterative arteriopathy (2/408). The AHC provided a dendrogram with at least three clusters that did not allow us to infer specific differential associations among variables (i.e. CV comorbidity and pSS manifestations). On the other hand, Auto-CM identified two different patterns of distributions in CV risk factors, pSS-related features, and CV events. The first pattern, centered on "non-ischaemic CV events/generic condition of HF", was characterised by the presence of traditional CV risk factors and by a closer link with pSS glandular features rather than to pSS extra-glandular manifestations. The second pattern included "ischaemic neurological, cardiac events and peripheral obliterative arteriopathy" and appeared to be strictly associated with extra-glandular disease activity and longer disease duration. CONCLUSIONS: This study represents the first application of ANNs to the analysis of factors contributing to CV events in pSS. When compared to AHC, ANNs had the advantage of better stratifying CV risk in pSS, opening new avenues for planning specific interventions to prevent long-term CV complications in pSS patients.


Assuntos
Doenças Cardiovasculares , Síndrome de Sjogren , Idoso , Doenças Cardiovasculares/epidemiologia , Doenças Cardiovasculares/etiologia , Comorbidade , Diagnóstico por Computador/métodos , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Redes Neurais (Computação) , Estudos Retrospectivos , Medição de Risco , Fatores de Risco , Síndrome de Sjogren/complicações , Síndrome de Sjogren/epidemiologia
15.
Stud Health Technol Inform ; 264: 198-202, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437913

RESUMO

Although a number of foundational natural language processing (NLP) tasks like text segmentation are considered a simple problem in the general English domain dominated by well-formed text, complexities of clinical documentation lead to poor performance of existing solutions designed for the general English domain. We present an alternative solution that relies on a convolutional neural network layer followed by a bidirectional long short-term memory layer (CNN-Bi-LSTM) for the task of sentence boundary disambiguation and describe an ensemble approach for domain adaptation using two training corpora. Implementations using the Keras neural-networks API are available at https://github.com/NLPIE/clinical-sentences.


Assuntos
Processamento de Linguagem Natural , Redes Neurais (Computação) , Documentação , Linguagem
16.
Stud Health Technol Inform ; 264: 203-207, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437914

RESUMO

We devised annotation guidelines for the de-identification of German clinical documents and assembled a corpus of 1,106 discharge summaries and transfer letters with 44K annotated protected health information (PHI) items. After three iteration rounds, our annotation team finally reached an inter-annotator agreement of 0.96 on the instance level and 0.97 on the token level of annotation (averaged pair-wise F1 score). To establish a baseline for automatic de-identification on our corpus, we trained a recurrent neural network (RNN) and achieved F1 scores greater than 0.9 on most major PHI categories.


Assuntos
Anonimização de Dados , Registros Eletrônicos de Saúde , Processamento de Linguagem Natural , Redes Neurais (Computação)
17.
Stud Health Technol Inform ; 264: 258-262, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437925

RESUMO

Secondary use of regional EHR data suffers several problems, including data selection bias and limited data size caused by data incompleteness. Here, we propose knowledge learning symbiosis (KLS) as a framework to incorporate domain knowledge to address the problems and make better secondary use of EHR data. Under the framework, we introduce three main categories of methods: knowledge injection to input features, objective functions, and output labels, where knowledge-enhanced neural network (KENN) was first introduced to inject knowledge into objective functions. A case study was conducted to build a cardiovascular disease risk prediction model on the type 2 diabetes patient cohort using regional EHR repositories. By incorporating a well-established knowledge risk model as domain knowledge under our KLS framework, we increased risk prediction performance both on small and biased data, where KENN showed the best performance among all methods.


Assuntos
Registros Eletrônicos de Saúde , Diabetes Mellitus Tipo 2 , Humanos , Aprendizado de Máquina , Redes Neurais (Computação)
18.
Stud Health Technol Inform ; 264: 353-357, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437944

RESUMO

To provide the best treatment, a physician needs information about both the patient and the medicines matching the patient status and improving it. In this article, we present three methods for structuring the sections of medical prospectuses using neural networks. To structure the information from a medical prospectus we use 3 web sources with structured data from sections (with names sections from prospectuses and with uniformized names of sections) to train as input for neural networks. The tests were conducted on Romanian prospectuses. After running the three algorithms, the prospectuses were compared in terms of accuracy and execution time for each source. It was concluded that the accuracy is higher in convolutional networks and in the case of uniform name sections. The output data is used in applications with decision support for the treatment, matching best treatment with the patient's status.


Assuntos
Algoritmos , Redes Neurais (Computação) , Prescrições
19.
Stud Health Technol Inform ; 264: 378-382, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437949

RESUMO

An attractive feature of non-lattice-based ontology auditing methods is its ability to not only identify potential quality issues, but also automatically generate the corresponding fixes. However, exhaustive manual evaluation of the validity of suggested changes remains a challenge shared with virtually all auditing methods. To address this challenge, we explore machine learning techniques as an aid to systematically evaluate the strength of auto-suggested relational changes in the context of existing knowledge embedded in an ontology. We introduce a hybrid convolutional neural network and multilayer perception (CNN-MLP) classifier using a combination of graph, concept features and concept embeddings. We use lattice subgraphs to generate a curated, loosely-coupled training set of positive and negative instances to train the classifier. Our result shows that machine learning techniques have the potential to alleviate the manual effort required for validating and confirming changes generated by non-lattice-based auditing methods for SNOMED CT.


Assuntos
Aprendizado de Máquina , Systematized Nomenclature of Medicine , Redes Neurais (Computação)
20.
Stud Health Technol Inform ; 264: 423-427, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437958

RESUMO

We propose a method to create large-scale Japanese medical dictionaries that include symptom names and information about the relationship between a disease and its symptoms using a large web archive that includes large amounts of text written by non-medical experts. Our goal is to develop a diagnosis support system that makes a diagnosis according to the natural language (NL) inputs provided by patients. To achieve this, two medical dictionaries need to be constructed: one that includes a wide variety of symptom names expressed in NL and another that includes information about the relationship between a disease and its symptoms. Dictionaries will then be used to predict the patient's disease via two developed methods that extract symptom names and disease-symptom relationships. Both methods retrieve sentences using WISDOM X and then apply neural classifiers to them. Our experimental results show that our methods achieved 93.8% and 88.3% in the F1-score, respectively.


Assuntos
Processamento de Linguagem Natural , Redes Neurais (Computação) , Linguagem
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA