Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
10,240
result(s) for
"Feng, Ye"
Sort by:
Impact of massive open online courses in higher education using machine learning and decision based fuzzy frank power aggregation operators models
Massive open online courses (MOOCs) have transformed higher education by providing widespread access to quality educational content, and the integration of machine learning (ML) has significantly enhanced their effectiveness and adaptability. This article is designed to illustrate insufficient and vague types of information in expert’s judgment using a multi-criteria group decision-making (MCGDM) problem. For this purpose, we modify the theoretical concepts of circular intuitionistic fuzzy set (Cir-IFS), which is an extended framework of fuzzy theory and intuitionistic fuzzy models. We derive robust power aggregation operators to find out the degree of weights of conflicting criteria. Moreover, a list of new mathematical approaches to power-weighted average and power-weighted geometric operators is also deduced. Some appropriate properties and special cases are discussed to reveal the efficiency and feasibility of the proposed aggregation operators. The MCGDM problem is established to determine the flexible ranking of alternatives under different conflicting criteria. Using decision algorithms and mathematical models, resolve a numerical example to find an appropriate platform that offers different MOOCs to improve higher education in the country. Additionally, a comparative study is modified to showcase the superiority and effectiveness of developed mathematical methodologies.
Journal Article
FeAture Explorer (FAE): A tool for developing and comparing radiomics models
In radiomics studies, researchers usually need to develop a supervised machine learning model to map image features onto the clinical conclusion. A classical machine learning pipeline consists of several steps, including normalization, feature selection, and classification. It is often tedious to find an optimal pipeline with appropriate combinations. We designed an open-source software package named FeAture Explorer (FAE). It was programmed with Python and used NumPy, pandas, and scikit-learning modules. FAE can be used to extract image features, preprocess the feature matrix, develop different models automatically, and evaluate them with common clinical statistics. FAE features a user-friendly graphical user interface that can be used by radiologists and researchers to build many different pipelines, and to compare their results visually. To prove the effectiveness of FAE, we developed a candidate model to classify the clinical-significant prostate cancer (CS PCa) and non-CS PCa using the PROSTATEx dataset. We used FAE to try out different combinations of feature selectors and classifiers, compare the area under the receiver operating characteristic curve of different models on the validation dataset, and evaluate the model using independent test data. The final model with the analysis of variance as the feature selector and linear discriminate analysis as the classifier was selected and evaluated conveniently by FAE. The area under the receiver operating characteristic curve on the training, validation, and test dataset achieved results of 0.838, 0.814, and 0.824, respectively. FAE allows researchers to build radiomics models and evaluate them using an independent testing dataset. It also provides easy model comparison and result visualization. We believe FAE can be a convenient tool for radiomics studies and other medical studies involving supervised machine learning.
Journal Article
Geometric isotope effect of deuteration in a hydrogen-bonded host–guest crystal
Deuteration of a hydrogen bond by replacing protium (H) with deuterium (D) can cause geometric changes in the hydrogen bond, known as the geometric H/D isotope effect (GIE). Understanding the GIEs on global structures and bulk properties is of great importance to study structure–property relationships of hydrogen-bonded systems. Here, we report a hydrogen-bonded host–guest crystal, imidazolium hydrogen terephthalate, that exemplifies striking GIEs on its hydrogen bonds, phases, and bulk dielectric transition property. Upon deuteration, the donor–acceptor distance in the O–H···O hydrogen bonds in the host structure is found to increase, which results in a change in the global hydrogen-bonded supramolecular structure and the emergence of a new phase (i.e., isotopic polymorphism). Consequently, the dynamics of the confined guest, which depend on the internal pressure exerted by the host framework, are substantially altered, showing a downward shift of the dielectric switching temperature.
Deuterating a hydrogen bond can change the bond’s geometry, a phenomenon known as the geometric isotope effect (GIE). Here, the authors find that a hydrogen-bonded host–guest crystal, imidazolium hydrogen terephthalate, exhibits significant GIE on its hydrogen bonds, changing its crystal phases and bulk dielectric properties.
Journal Article
Development of a chimeric Zika vaccine using a licensed live-attenuated flavivirus vaccine as backbone
The global spread of Zika virus (ZIKV) and its unexpected association with congenital defects necessitates the rapid development of a safe and effective vaccine. Here we report the development and characterization of a recombinant chimeric ZIKV vaccine candidate (termed ChinZIKV) that expresses the prM-E proteins of ZIKV using the licensed Japanese encephalitis live-attenuated vaccine SA14-14-2 as the genetic backbone. ChinZIKV retains its replication activity and genetic stability in vitro, while exhibiting an attenuation phenotype in multiple animal models. Remarkably, immunization of mice and rhesus macaques with a single dose of ChinZIKV elicits robust and long-lasting immune responses, and confers complete protection against ZIKV challenge. Significantly, female mice immunized with ChinZIKV are protected against placental and fetal damage upon ZIKV challenge during pregnancy. Overall, our study provides an alternative vaccine platform in response to the ZIKV emergency, and the safety, immunogenicity, and protection profiles of ChinZIKV warrant further clinical development.
Given the recent Zika virus (ZIKV) epidemic, development of an effective vaccine is of high importance. Here, the authors use a licensed live-attenuated flavivirus vaccine backbone to develop a ZIKV vaccine and determine immunogenicity, safety and protection profiles in different animal models.
Journal Article
The clinical value of neutrophil-to-lymphocyte ratio (NLR), systemic immune-inflammation index (SII), platelet-to-lymphocyte ratio (PLR) and systemic inflammation response index (SIRI) for predicting the occurrence and severity of pneumonia in patients with intracerebral hemorrhage
Inflammatory mechanisms play important roles in intracerebral hemorrhage (ICH) and have been linked to the development of stroke-associated pneumonia (SAP). The neutrophil-to-lymphocyte ratio (NLR), systemic immune-inflammation index (SII), platelet-to-lymphocyte ratio (PLR) and systemic inflammation response index (SIRI) are inflammatory indexes that influence systemic inflammatory responses after stroke. In this study, we aimed to compare the predictive value of the NLR, SII, SIRI and PLR for SAP in patients with ICH to determine their application potential in the early identification of the severity of pneumonia.
Patients with ICH in four hospitals were prospectively enrolled. SAP was defined according to the modified Centers for Disease Control and Prevention criteria. Data on the NLR, SII, SIRI and PLR were collected at admission, and the correlation between these factors and the clinical pulmonary infection score (CPIS) was assessed through Spearman's analysis.
A total of 320 patients were enrolled in this study, among whom 126 (39.4%) developed SAP. The results of the receiver operating characteristic (ROC) analysis revealed that the NLR had the best predictive value for SAP (AUC: 0.748, 95% CI: 0.695-0.801), and this outcome remained significant after adjusting for other confounders in multivariable analysis (RR=1.090, 95% CI: 1.029-1.155). Among the four indexes, Spearman's analysis showed that the NLR was the most highly correlated with the CPIS (r=0.537, 95% CI: 0.395-0.654). The NLR could effectively predict ICU admission (AUC: 0.732, 95% CI: 0.671-0.786), and this finding remained significant in the multivariable analysis (RR=1.049, 95% CI: 1.009-1.089, P=0.036). Nomograms were created to predict the probability of SAP occurrence and ICU admission. Furthermore, the NLR could predict a good outcome at discharge (AUC: 0.761, 95% CI: 0.707-0.8147).
Among the four indexes, the NLR was the best predictor for SAP occurrence and a poor outcome at discharge in ICH patients. It can therefore be used for the early identification of severe SAP and to predict ICU admission.
Journal Article
Exosomal miRNA-19b-3p of tubular epithelial cells promotes M1 macrophage activation in kidney injury
Tubulointerstitial inflammation is a common characteristic of acute and chronic kidney injury. However, the mechanism by which the initial injury of tubular epithelial cells (TECs) drives interstitial inflammation remains unclear. This paper aims to explore the role of exosomal miRNAs derived from TECs in the development of tubulointerstitial inflammation. Global microRNA(miRNA) expression profiling of renal exosomes was examined in a LPS induced acute kidney injury (AKI) mouse model and miR-19b-3p was identified as the miRNA that was most notably increased in TEC-derived exosomes compared to controls. Similar results were also found in an adriamycin (ADR) induced chronic proteinuric kidney disease model in which exosomal miR-19b-3p was markedly released. Interestingly, once released, TEC-derived exosomal miR-19b-3p was internalized by macrophages, leading to M1 phenotype polarization through targeting NF-κB/SOCS-1. A dual-luciferase reporter assay confirmed that SOCS-1 was the direct target of miR-19b-3p. Importantly, the pathogenic role of exosomal miR-19b-3p in initiating renal inflammation was revealed by the ability of adoptively transferred of purified TEC-derived exosomes to cause tubulointerstitial inflammation in mice, which was reversed by inhibition of miR-19b-3p. Clinically, high levels of miR-19b-3p were found in urinary exosomes and were correlated with the severity of tubulointerstitial inflammation in patients with diabetic nephropathy. Thus, our studies demonstrated that exosomal miR-19b-3p mediated the communication between injured TECs and macrophages, leading to M1 macrophage activation. The exosome/miR-19b-3p/SOCS1 axis played a critical pathologic role in tubulointerstitial inflammation, representing a new therapeutic target for kidney disease.
Journal Article
Application of Cloud Service in Smart Tourism Management Based on Weighted Average Algorithm
Tourism has become the main force driving urban economic development. However, there are problems such as low utilization rate of tourism resources and inconsistency of tourism information. The new smart tourism management model can sense tourism resources, tourist information, tourism development, and other information in a timely manner through terminal devices such as the Internet. The core of smart tourism management is to obtain travel information of travelers through cloud service technology, organize travel information, and recommend personalized travel plans for travelers. Apply cloud services to smart tourism management, and use the weighted average algorithm to make regression predictions on passenger information. This paper compares and analyzes the application of cloud service based on the algorithm for calculating the weighted average and the application of ordinary cloud service in smart tourism management through experiments. The experimental results show that the cloud service by adding weights can improve the forecast of the traveler’s information by 36% and 22%, respectively, compared with the cloud service of the ordinary average algorithm. Also, the effect of tourists’ travel experience is 72.2% and 56.3%, respectively. In the forecast of tourism information in tourism resources, tourism economy, and tourism activities, cloud services by adding weights maintain stable economic growth and improve tourists’ tourism experience. The cloud service in the smart tourism management of the weighted average algorithm can formulate corresponding tourism marketing strategies through the integration and prediction of tourism information, enhance the growth of the tourism economy, and improve the tourism experience of tourists.
Journal Article
A Deep Neural Network Model for Speaker Identification
Speaker identification is a classification task which aims to identify a subject from a given time-series sequential data. Since the speech signal is a continuous one-dimensional time series, most of the current research methods are based on convolutional neural network (CNN) or recurrent neural network (RNN). Indeed, these methods perform well in many tasks, but there is no attempt to combine these two network models to study the speaker identification task. Due to the spectrogram that a speech signal contains, the spatial features of voiceprint (which corresponds to the voice spectrum) and CNN are effective for spatial feature extraction (which corresponds to modeling spectral correlations in acoustic features). At the same time, the speech signal is in a time series, and deep RNN can better represent long utterances than shallow networks. Considering the advantage of gated recurrent unit (GRU) (compared with traditional RNN) in the segmentation of sequence data, we decide to use stacked GRU layers in our model for frame-level feature extraction. In this paper, we propose a deep neural network (DNN) model based on a two-dimensional convolutional neural network (2-D CNN) and gated recurrent unit (GRU) for speaker identification. In the network model design, the convolutional layer is used for voiceprint feature extraction and reduces dimensionality in both the time and frequency domains, allowing for faster GRU layer computation. In addition, the stacked GRU recurrent network layers can learn a speaker’s acoustic features. During this research, we tried to use various neural network structures, including 2-D CNN, deep RNN, and deep LSTM. The above network models were evaluated on the Aishell-1 speech dataset. The experimental results showed that our proposed DNN model, which we call deep GRU, achieved a high recognition accuracy of 98.96%. At the same time, the results also demonstrate the effectiveness of the proposed deep GRU network model versus other models for speaker identification. Through further optimization, this method could be applied to other research similar to the study of speaker identification.
Journal Article
Direct observation of geometric and sliding ferroelectricity in an amphidynamic crystal
Sliding ferroelectricity is a recently observed polarity existing in two-dimensional materials. However, due to the weak polarization and poor electrical insulation in these materials, existing experimental evidences are indirect and mostly based on nanoscale transport properties or piezoresponse force microscopy. We report the direct observation of sliding ferroelectricity, using a high-quality amphidynamic single crystal (15-crown-5)Cd
3
Cl
6
, which possesses a large bandgap and so allows direct measurement of polarization–electric field hysteresis. This coordination polymer is a van der Waals material, which is composed of inorganic stators and organic rotators as determined by X-ray diffraction and NMR characterization. From density functional theory calculations, we find that after freezing the rotators, an electric dipole is generated in each layer driven by the geometric mechanism, while a comparable ferroelectric polarization originates from the interlayer sliding. The net polarization of these two components can be directly measured and manipulated. Our finding provides insight into low-dimensional ferroelectrics, especially control of the synchronous dynamics of rotating molecules and sliding layers in solids.
Two-dimensional materials can present ferroelectricity by layer sliding, but electrical confirmation is lacking due to narrow bandgaps. Here, a single-crystal coordination polymer with large bandgap enabling direct electrical measurement of
P
–
E
hysteresis is shown to present sliding ferroelectricity.
Journal Article