scholarly journals Spatial Mixture Copula Model For Multiple Correlated Responses With An Environmental Application

Author(s):  
Mohomed Abraj ◽  
M. Helen Thompson ◽  
You-Gan Wang

Abstract In environmental monitoring, multiple measurements are often collected at many locations and these measurements depend on each other in complex ways, such as nonlinear dependence. In this research, a novel copula-based geostatistical modelling approach was developed to model multivariate continuous spatial random fields using mixture copulas that captures both spatial and joint dependence of multiple responses over two-dimensional locations. In a bivariate context, the mixture copulas were used to capture the joint spatial dependence of a bivariate random field and the spatial copula of the bivariate random field was constructed as the convex combination of mixture copulas. The proposed model was applied to real forest data and simulated nonlinear data. The performance of the novel method was compared with existing spatial methods, which included a univariate spatial pair-copula model, a multivariate spatial pair-copula model that utilises nonlinear principal component analysis (NLPCA), and conventional kriging. The results show that the proposed model outperforms the existing methods in the interpolation of individual responses and reproduction of their bivariate dependence.

2018 ◽  
Vol 30 (10) ◽  
pp. 2833-2854 ◽  
Author(s):  
Tingwei Gao ◽  
Yueting Chai

This study focuses on predicting stock closing prices by using recurrent neural networks (RNNs). A long short-term memory (LSTM) model, a type of RNN coupled with stock basic trading data and technical indicators, is introduced as a novel method to predict the closing price of the stock market. We realize dimension reduction for the technical indicators by conducting principal component analysis (PCA). To train the model, some optimization strategies are followed, including adaptive moment estimation (Adam) and Glorot uniform initialization. Case studies are conducted on Standard & Poor's 500, NASDAQ, and Apple (AAPL). Plenty of comparison experiments are performed using a series of evaluation criteria to evaluate this model. Accurate prediction of stock market is considered an extremely challenging task because of the noisy environment and high volatility associated with the external factors. We hope the methodology we propose advances the research for analyzing and predicting stock time series. As the results of experiments suggest, the proposed model achieves a good level of fitness.


2021 ◽  
Vol 13 (3) ◽  
pp. 526
Author(s):  
Shengliang Pu ◽  
Yuanfeng Wu ◽  
Xu Sun ◽  
Xiaotong Sun

The nascent graph representation learning has shown superiority for resolving graph data. Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships. Faced with hyperspectral image (HSI) classification, the priority problem might be how to convert hyperspectral data into irregular domains from regular grids. In this regard, we present a novel method that performs the localized graph convolutional filtering on HSIs based on spectral graph theory. First, we conducted principal component analysis (PCA) preprocessing to create localized hyperspectral data cubes with unsupervised feature reduction. These feature cubes combined with localized adjacent matrices were fed into the popular graph convolution network in a standard supervised learning paradigm. Finally, we succeeded in analyzing diversified land covers by considering local graph structure with graph convolutional filtering. Experiments on real hyperspectral datasets demonstrated that the presented method offers promising classification performance compared with other popular competitors.


Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3527
Author(s):  
Melanija Vezočnik ◽  
Roman Kamnik ◽  
Matjaz B. Juric

Inertial sensor-based step length estimation has become increasingly important with the emergence of pedestrian-dead-reckoning-based (PDR-based) indoor positioning. So far, many refined step length estimation models have been proposed to overcome the inaccuracy in estimating distance walked. Both the kinematics associated with the human body during walking and actual step lengths are rarely used in their derivation. Our paper presents a new step length estimation model that utilizes acceleration magnitude. To the best of our knowledge, we are the first to employ principal component analysis (PCA) to characterize the experimental data for the derivation of the model. These data were collected from anatomical landmarks on the human body during walking using a highly accurate optical measurement system. We evaluated the performance of the proposed model for four typical smartphone positions for long-term human walking and obtained promising results: the proposed model outperformed all acceleration-based models selected for the comparison producing an overall mean absolute stride length estimation error of 6.44 cm. The proposed model was also least affected by walking speed and smartphone position among acceleration-based models and is unaffected by smartphone orientation. Therefore, the proposed model can be used in the PDR-based indoor positioning with an important advantage that no special care regarding orientation is needed in attaching the smartphone to a particular body segment. All the sensory data acquired by smartphones that we utilized for evaluation are publicly available and include more than 10 h of walking measurements.


2020 ◽  
Vol 8 (6) ◽  
pp. 5820-5825

Human computer interaction is a fast growing area of research where in the physiological signals are used to identify human emotion states. Identifying emotion states can be done using various approaches. One such approach which gained interest of research is through physiological signals using EEG. In the present work, a novel approach is proposed to elicit emotion states using 3-D Video-audio stimuli. Around 66 subjects were involved during data acquisition using 32 channel Enobio device. FIR filter is used to preprocess the acquired raw EEG signals. The desired frequency bands like alpha, delta, beta and theta are extracted using 8-level DWT. The statistical features, Hurst exponential, entropy, power, energy, differential entropy of each bands are computed. Artificial Neural network is implemented using Sequential Keras model and applied on the extracted features to classify in to four classes (HVLA, HVHA, LVHA and LVLA) and eight discrete emotion states like clam, relax, happy, joy, sad, fear, tensed and bored. The performance of ANN classifier found to perform better for 4- classes than 8-classes with a classification rate of 90.835% and 74.0446% respectively. The proposed model achieved better performance rate in detecting discrete emotion states. This model can be used to build applications on health like stress / depression detection and on entertainment to build emotional DJ.


Author(s):  
Mark Christopher Arokiaraj ◽  
Jarad Wilson

AbstractBackgroundCoronary artery diseases and autoimmune disorders are common in clinical practice. In this study, a novel method of immune-modulation to modify the endothelial function was studied to modulate the features of the endothelial cells, and thereby to reduce coronary artery disease and other disorders modulated by endothelium.MethodsHUVEC cells were seeded in the cell culture, and streptococcus pyogenes were added to the cell culture, and the supernatant was studied for the secreted proteins. In the second phase, the bacterial lysate was synthesized, and the lysate was added to cell culture; and the proteins in the supernatant were studied at various time intervals.ResultsWhen streptococcus pyogenes alone was added to culture, E Cadherin, Angiostatin, EpCAM and PDGF-AB were some of the biomarkers elevated significantly. HCC1, IGFBP2 and TIMP were some of the biomarkers which showed a reduction. When the lysate was added, the cell-culture was maintained for a longer time, and it showed the synthesis of immune regulatory cytokines. Heatmap analysis showed a significant number of proteins/cytokines concerning the immune/pathways, and toll-like receptors superfamily were modified. BLC, IL 17, BMP 7, PARC, Contactin2, IL 10 Rb, NAP 2 (CXCL 7), Eotaxin 2 were maximally increased. By principal component analysis, the results observed were significant.ConclusionThere is potential for a novel method of immunomodulation of the endothelial cells, which have pleiotropic functions, using streptococcus pyogenes and its lysates.


2021 ◽  
Author(s):  
Dezhou Shen

Abstract Chinese word segment is widely studied in document analysis. The accuracy of the current popular word segment model, LSTM+CRF, is still not satisfactory. Models trained by the popular dataset often fails in the out-domain situation. In this paper, combining the Transformer-XL layer, the Fully-Connect layer, and the Conditional Random Field layer, the proposed model improved 3.23% in the macro-F1 score, comparing to the BERT+CRF model, on the MSR2005 Chinese word segment test dataset.


Author(s):  
Ammar Alnahhas ◽  
Bassel Alkhatib

As the data on the online social networks is getting larger, it is important to build personalized recommendation systems that recommend suitable content to users, there has been much research in this field that uses conceptual representations of text to match user models with best content. This article presents a novel method to build a user model that depends on conceptual representation of text by using ConceptNet concepts that exceed the named entities to include the common-sense meaning of words and phrases. The model includes the contextual information of concepts as well, the authors also show a novel method to exploit the semantic relations of the knowledge base to extend user models, the experiment shows that the proposed model and associated recommendation algorithms outperform all previous methods as a detailed comparison shows in this article.


1995 ◽  
Vol 50 (11-12) ◽  
pp. 757-765 ◽  
Author(s):  
Yasunobu Sakoda ◽  
Kenji Matsui ◽  
Tadahiko Kajiwara ◽  
Akikazu Hatanaka

In order to elucidate chemical structure-odor correlation in the all isomers of n-nonen-1- ols, an entire series of these alcohols were synthesized stereo-selectively in high purity. For unequivocal syntheses of them, geometrically selective hydrogenation of the respective acetylenic compound was adopted. The synthesized alcohols were converted to their 3,5-dinitrobenzoate derivatives with 3,5-dinitrobenzoyl chloride, and then purified by repeated recrystallization. Chemical structure-odor correlations in all the isomers of n-nonen-1-ols were elucidated by introducing a novel method to evaluate odor characteristics and by treating the obtained data statistically with the principal component analysis method (Cramer et al., 1988). The odor profiles of the tested compounds were attributable largely to the positions of the carbon- double bond. The geometries of compounds had only a little effect. With the principal component analysis, the odor profiles of the series of compounds were successfully integrated into the first and the second principal components. The first component (PC-1) consisted of combined characteristics of fruity, fresh, sweet, herbal and oily-fatty, in which herbal and oily-fatty were conversely correlated each other to the position of double-bond of the tested compounds. Of these, only (6Z)-nonen-1-ol deviated markedly from the correlation, indicative of some special interaction between the spatial structure of this compound and the sensory machinery of human.


RSC Advances ◽  
2019 ◽  
Vol 9 (59) ◽  
pp. 34196-34206
Author(s):  
Zhe Li ◽  
Shunhao Huang ◽  
Juan Chen

Establish soft measurement model of total chlorine: cyclic voltammetry curves, principal component analysis and support vector regression.


Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-17 ◽  
Author(s):  
Zhijian Wang ◽  
Likang Zheng ◽  
Wenhua Du ◽  
Wenan Cai ◽  
Jie Zhou ◽  
...  

In the era of big data, data-driven methods mainly based on deep learning have been widely used in the field of intelligent fault diagnosis. Traditional neural networks tend to be more subjective when classifying fault time-frequency graphs, such as pooling layer, and ignore the location relationship of features. The newly proposed neural network named capsules network takes into account the size and location of the image. Inspired by this, capsules network combined with the Xception module (XCN) is applied in intelligent fault diagnosis, so as to improve the classification accuracy of intelligent fault diagnosis. Firstly, the fault time-frequency graphs are obtained by wavelet time-frequency analysis. Then the time-frequency graphs data which are adjusted the pixel size are input into XCN for training. In order to accelerate the learning rate, the parameters which have bigger change are punished by cost function in the process of training. After the operation of dynamic routing, the length of the capsule is used to classify the types of faults and get the classification of loss. Then the longest capsule is used to reconstruct fault time-frequency graphs which are used to measure the reconstruction of loss. In order to determine the convergence condition, the three losses are combined through the weight coefficient. Finally, the proposed model and the traditional methods are, respectively, trained and tested under laboratory conditions and actual wind turbine gearbox conditions to verify the classification ability and reliable ability.


Sign in / Sign up

Export Citation Format

Share Document