Fei Wang

Hebei University of Technology, Ho-pei-ts’un, Beijing, China

Are you Fei Wang?

Claim your profile

Publications (140)96.48 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: A significant advance of rubber composite is obtained by 100 phr modified attapulgite.•The optimum content of silane is 3% when composite tensile strength reaches maximum.•The optimal titanate content is 2–3%, and the tensile strength reaches maximum value.•The free energy of immersion is at maximum with optimal coupling agent-modified OAT.•We report a new method to predict tensile strength before preparing rubber products.
    Powder Technology 01/2015; 270. · 2.27 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Risk stratification is instrumental to modern clinical decision support systems. Comprehensive risk stratification should be able to provide the clinicians with not only the accurate assessment of a patient's risk but also the clinical context to be acted upon. However, existing risk stratification techniques mainly focus on predicting the risk score for individual patients; at the cohort level, they offer little insight beyond a flat score-based segmentation. This essentially reduces a patient to a score and thus removes him/her from his/her clinical context. To address this limitation, in this paper we propose a bilinear model for risk stratification that simultaneously captures the three key aspects of risk stratification: (1) it predicts the risk of each individual patient; (2) it stratifies the patient cohort based on not only the risk score but also the clinical characteristics; and (3) it embeds all patients into clinical contexts with clear interpretation. We apply our model to a cohort of 4977 patients, 1127 among which were diagnosed with Congestive Heart Failure (CHF). We demonstrate that our model cannot only accurately predict the onset risk of CHF but also provide rich and actionable clinical insights into the patient cohort. Copyright © 2014 Elsevier Inc. All rights reserved.
    Journal of Biomedical Informatics 10/2014; · 2.48 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this article, the supercells of pure anatase titanium dioxide, nitrogen and/or chromium doping anatase titanium dioxide were computed using first-principles with the plane-wave ultrasoft pseudopotentials method, and the electronic structure and optical properties of different ions doping models were also studied. The results indicated that the band gap and charge carriers recombination rate of nitrogen and chromium codoped system are all decreased effectively, and the separation of electron–hole pairs becomes more favorable due to impurity energy levels formation in the band gap of anatase titanium dioxide, which could play an important role in enhancing the catalytic activity and visible light absorption of anatase titanium dioxide. Furthermore, the optical absorption curves of nitrogen and chromium codoped anatase titanium dioxide indicate the highest photoresponse for visible-light, which is consistent with the previous experimental results. The above results would be quite helpful for research guiding and further developing of titanium dioxide photocatalyst.
    Journal of Alloys and Compounds 10/2014; 611:125–129. · 2.73 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Behavioral pattern discovery is increasingly being studied to understand human behavior and the discovered patterns can be used in many real world applications such as web search, recommender system and advertisement targeting. Traditional methods usually consider the behaviors as simple user and item connections, or represent them with a static model. In real world, however, human behaviors are actually complex and dynamic: they include correlations between user and multiple types of objects and also continuously evolve along time. These characteristics cause severe data sparsity and computational complexity problem, which pose great challenge to human behavioral analysis and prediction. In this paper, we propose a Flexible Evolutionary Multi-faceted Analysis (FEMA) framework for both behavior prediction and pattern mining. FEMA utilizes a flexible and dynamic factorization scheme for analyzing human behavioral data sequences, which can incorporate various knowledge embedded in different object domains to alleviate the sparsity problem. We give approximation algorithms for efficiency, where the bound of approximation loss is theoretically proved. We extensively evaluate the proposed method in two real datasets. For the prediction of human behaviors, the proposed FEMA significantly outperforms other state-of-the-art baseline methods by 17.4%. Moreover, FEMA is able to discover quite a number of interesting multi-faceted temporal patterns on human behaviors with good interpretability. More importantly, it can reduce the run time from hours to minutes, which is significant for industry to serve real-time applications.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Inferring phenotypic patterns from population-scale clinical data is a core computational task in the development of personalized medicine. One important source of data on which to conduct this type of research is patient Electronic Medical Records (EMR). However, the patient EMRs are typically sparse and noisy, which creates significant challenges if we use them directly to represent patient phenotypes. In this paper, we propose a data driven phenotyping framework called Pacifier (PAtient reCord densIFIER), where we interpret the longitudinal EMR data of each patient as a sparse matrix with a feature dimension and a time dimension, and derive more robust patient phenotypes by exploring the latent structure of those matrices. Specifically, we assume that each derived phenotype is composed of a subset of the medical features contained in original patient EMR, whose value evolves smoothly over time. We propose two formulations to achieve such goal. One is Individual Basis Approach (IBA), which assumes the phenotypes are different for every patient. The other is Shared Basis Approach (SBA), which assumes the patient population shares a common set of phenotypes. We develop an efficient optimization algorithm that is capable of resolving both problems efficiently. Finally we validate Pacifier on two real world EMR cohorts for the tasks of early prediction of Congestive Heart Failure (CHF) and End Stage Renal Disease (ESRD). Our results show that the predictive performance in both tasks can be improved significantly by the proposed algorithms (average AUC score improved from 0.689 to 0.816 on CHF, and from 0.756 to 0.838 on ESRD respectively, on diagnosis group granularity). We also illustrate some interesting phenotypes derived from our data.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Logistic regression is one core predictive modeling technique that has been used extensively in health and biomedical problems. Recently a lot of research has been focusing on enforcing sparsity on the learned model to enhance its effectiveness and interpretability, which results in sparse logistic regression model. However, no matter the original or sparse logistic regression, they require the inputs to be in vector form. This limits the applicability of logistic regression in the problems when the data cannot be naturally represented vectors (e.g., functional magnetic resonance imaging and electroencephalography signals). To handle the cases when the data are in the form of multi-dimensional arrays, we propose MulSLR: Multilinear Sparse Logistic Regression. MulSLR can be viewed as a high order extension of sparse logistic regression. Instead of solving one classification vector as in conventional logistic regression, we solve for K classification vectors in MulSLR (K is the number of modes in the data). We propose a block proximal descent approach to solve the problem and prove its convergence. The convergence rate of the proposed algorithm is also analyzed. Finally we validate the efficiency and effectiveness of MulSLR on predicting the onset risk of patients with Alzheimer's disease and heart failure.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this article, a new Heusler alloy V2CuAl with Hg2CuTi-type structure has been obtained by first-principles calculations. The electric structure and magnetic performance of the alloy have also been investigated. The results show that the alloy has a total magnetic moment of 0.87μB per unit cell obtained by first-principles calculations. In addition, the conducting character and metal property are presented by the majority and minority spin band structures calculations. Furthermore, the magnetic moments of V(1) atom and V(2) atom are 0.36μB and 0.38μB, respectively, indicating that the alloy is a ferromagnet.
    Journal of Alloys and Compounds 08/2014; 603:180–182. · 2.73 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Glaze is composed of glassy phase, pores and a small amount of crystal phase. The glazed product is endowed high technological properties such as low water absorption, good cleanability, high bending strength and abrasion resistance, excellent chemical and soil resistance. Nevertheless, surface degradation might lead to opening of closed bubbles in glaze thus diminishing the cleanability. As a result, a study of bubble formation in glaze layer would favor the improvement of mechanical property and cleanability of final products. In this paper, glaze slurry was prepared by milling for 30 min, then applied to green bodies and dried for later use. The same glaze was fired in hot stage microscope to measure melting behavior. Two characteristic points were obtained: start of melting temperature of 1184 °C; half sphere temperature of 1220 °C. The firing curves applied to glaze can be designed according to the characteristic points, and then the dried samples were fired. The bubbles in fired glaze were observed by 3D depth of field microscope. Microhardness was performed using Vickers hardness tester. A solution was proposed to decrease bubbles and increase microhardness via changing firing process. The results showed the formation of bubbles in glaze was determined by firing process
    Thermochimica Acta 07/2014; · 2.11 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The modified sepiolite nanofibers were obtained by organic modification, using γ-(2,3-epoxypropoxy)propytrimethoxysilane as silane coupling agent. On the basis, rigid polyurethane foams composite materials containing modified sepiolite nanofibers and hollow glass microspheres were obtained, and the effect of modified sepiolite nanofibers and hollow glass microspheres on performance of rigid polyurethane foams composite materials were also studied. The microstructure, mechanical properties and thermal stability of the composite materials were measured by scanning electron microscope, Fourier transform infrared spectrum, universal tensile testing machine and differential thermal analyzer. The results indicated that sepiolite nanofibers and hollow glass microspheres dispersed in rigid polyurethane foams matrix homogeneously with strong physical and chemical interaction, and surface functional groups with special structure were formed. Consequently, modified sepiolite nanofibers and hollow glass microspheres have great influence on the mechanical properties and thermal stability of the rigid polyurethane foams composite materials. When the contents of sepiolite nanofibers and hollow glass microspheres were 15% and 10%, the tensile strength, breaking elongation rate and compressive strength of the composite materials were increased by 240%, 410% and 300%, respectively. Thermal weight loss central temperature of the composite materials was increased obviously, showing the better thermal stability of the composite materials after being reinforced by modified sepiolite nanofibers and hollow glass microspheres.
    Nanoscience and Nanotechnology Letters 06/2014; 6(6). · 1.44 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Nano zinc oxide with a high refractive index has good thermal reflection performance, hollow glass microspheres have good thermal reflection and insulation performance, and sepiolite nanofibers with many nanostructural pores have good thermal insulation performance. The dispensability of nano zinc oxide in coating materials was improved by optimizing surface silane coupling agent modification process, leading to the good thermal reflection performance. The thermal insulation performance was improved by hollow glass microspheres and sepiolite nanofibers. On this basis, the thermal insulation coating materials were prepared by exploring the effect of amount, complex mode, and other factors of the above three kinds of functional fillers on the thermal reflection and insulation performance of coating materials. The results showed that the surface modification effect of nano zinc oxide was the best when the silane coupling agent addition was 6%. The reflection and insulation performance of the coatings were the best when the additions of modified nano zinc oxide, hollow glass microspheres, and sepiolite nanofibers were 3%, 4%, and 4%, respectively. Compared with the control coating materials, the thermal insulation effect was improved obviously, which was evaluated by the -13.5 degrees C increase of maximum temperature difference between the upper and the lower surfaces.
    Journal of Nanoscience and Nanotechnology 05/2014; 14(5):3861-7. · 1.34 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Surface modification is used to regulate surface free energy of sepiolite with 3-glycidoxypropyltrimethoxysilanes (3-GPTMS), 3-methacryloxypropyltrimethoxysilanes (3-MAPTMS) and 3-mercaptopropyltrimethoxysilane (3-MPTMS). Through characterization by Fourier transform infrared spectroscopy, surface free energy, zeta potential and sedimentation measurements and infrared emissivity, it is found that the surface free energy of 3-MPTMS modified sepiolite decreases to 31.72 mJ/m2 and the percentage of polar component increases to 89.75%, thus leading to that the infrared emissivity of 3-MPTMS modified sepiolite increase to be higher than 0.8 and the dispersion of sepiolite has been improved. The excellent thermal insulation property of coating is prepared with 10% additive amount of 3-MPTMS modified sepiolite and the temperature difference between upper and lower box of modified sepiolite coatings is 10 degrees C which is higher than the untreated sepiolite.
    Journal of Nanoscience and Nanotechnology 05/2014; 14(5):3515-20. · 1.34 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The longitudinal and cross sectional TEM images of sepiolite mineral nanofibers were prepared by cutting in the direction parallel and perpendicular to nanofibers, and the channel microstructure of sepiolite nanofibers was studied. The thermal insulation mechanism of sepiolite nanofibers was analyzed according to the diagrammatic sketch obtained from the above experimental method. The results showed that many discontinuously connected bending shape channels with about 23-26 nm in diameter existed in the center region of nanofibers, and many discontinuously connected irregular micropores and mesopores with the size of about 1-9 nm existed on the wall of nanofibers. The main reasons for the formation of channel microstructure in sepiolite nanofibers were their minerogenetic conditions and the interaction between acid and high-speed airflow in the process of nanofibers preparation, and bubbles in the hydrotherm played a significant role in the microstructure formation. The thermal insulation performance of sepiolite nanofibers could be attributed to obstructive and infrared radiative thermal insulation.
    Journal of Nanoscience and Nanotechnology 05/2014; 14(5):3937-42. · 1.34 Impact Factor
  • David Gotz, Fei Wang, Adam Perer
    [Show abstract] [Hide abstract]
    ABSTRACT: Patients’ medical conditions often evolve in complex and seemingly unpredictable ways. Even within a relatively narrow and well-defined episode of care, variations between patients in both their progression and eventual outcome can be dramatic. Understanding the patterns of events observed within a population that most correlate with differences in outcome is therefore an important task in many types of studies using retrospective electronic health data. In this paper, we present a method for interactive pattern mining and analysis that supports ad hoc visual exploration of patterns mined from retrospective clinical patient data. Our approach combines (1) visual query capabilities to interactively specify episode definitions, (2) pattern mining techniques to help discover important intermediate events within an episode, and (3) interactive visualization techniques that help uncover event patterns that most impact outcome and how those associations change over time. In addition to presenting our methodology, we describe a prototype implementation and present use cases highlighting the types of insights or hypotheses that our approach can help uncover.
    Journal of Biomedical Informatics 04/2014; · 2.13 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A new Heusler alloy V2NiSb with Hg2CuTi-type structure has been obtained by means of first-principles calculations. The electric structure and magnetic properties of the alloy have been also investigated. The results show that the alloy has a total magnetic moment of 0.82μ B per unit cell on first-principles calculations. The magnetic moment of atom Ni is 0.13μ B ; the magnetic moments of V(1) atom and V(2) atom are −0.48μ B and 0.76μ B , respectively, indicating that the alloy is a antiferrimagnet.
    Journal of Superconductivity and Novel Magnetism 03/2014; 27(3). · 0.93 Impact Factor
  • Adam Perer, Fei Wang
    [Show abstract] [Hide abstract]
    ABSTRACT: Extracting insights from temporal event sequences is an important challenge. In particular, mining frequent patterns from event sequences is a desired capability for many domains. However, most techniques for mining frequent patterns are ineffective for real-world data that may be low-resolution, concurrent, or feature many types of events, or the algorithms may produce results too complex to interpret. To address these challenges, we propose Frequence, an intelligent user interface that integrates data mining and visualization in an interactive hierarchical information exploration system for finding frequent patterns from longitudinal event sequences. Frequence features a novel frequent sequence mining algorithm to handle multiple levels-of-detail, temporal context, concurrency, and outcome analysis. Frequence also features a visual interface designed to support insights, and support exploration of patterns of the level-of-detail relevant to users. Frequence's effectiveness is demonstrated with two use cases: medical research mining event sequences from clinical records to understand the progression of a disease, and social network research using frequent sequences from Foursquare to understand the mobility of people in an urban environment.
    Proceedings of the 19th international conference on Intelligent User Interfaces; 02/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: On top of an enterprise social platform, we are building a smart social QA system that automatically routes questions to suitable employees who are willing, able, and ready to provide answers. Due to a lack of social QA history (training data) to start with, in this paper, we present an optimization-based approach that recommends both top-matched active (seed) and inactive (prospect) answerers for a given question. Our approach includes three parts. First, it uses a predictive model to find top-ranked seed answerers by their fitness, including their ability and willingness, to answer a question. Second, it uses distance metric learning to discover prospects most similar to the seeds identified in the first step. Third, it uses a constraint-based approach to balance the selection of both seeds and prospects identified in the first two steps. As a result, not only does our solution route questions to top-matched active users, but it also engages inactive users to grow the pool of answerers. Our real-world experiments that routed 114 questions to 684 people identified from 400,000+ employees included 641 prospects (93.7%) and achieved about 70% answering rate with 83% of answers received a lot/full confidence.
    Proceedings of the 19th international conference on Intelligent User Interfaces; 02/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Diffusion and cascades have been studied for many years in sociology, and different theoretical models have been developed. However, experimental validation has been always carried out in relatively small datasets. In recent years, with the availability of large-scale network and cascade data, research on cascading and diffusion phenomena has aroused considerable interests from various fields in computer science. One of the main goals is to discover different propagation patterns from historical cascade data. In this context, understanding the mechanisms underlying diffusion in both micro- and macro-scale levels and further develop predictive model of diffusion are fundamental problems of crucial importance.
    Proceedings of the 7th ACM international conference on Web search and data mining; 02/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Nowadays, the Heusler alloy is a hot material system explored for new functional materials in condensed matter physics and materials science. A lot of Heusler alloys usually have a cubic L21 structure with high chemical ordering. The L21 structure has two types: Cu2MnAl-type and Hg2CuTi-type. For given elements, different L21 structures can generate different properties. Based on the minimum energy theory, a method is proposed to determine which structure will be chosen from the two in the crystallization of an L21 structure.
    Journal of Superconductivity and Novel Magnetism 02/2014; 27(2). · 0.93 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Spintronics is attracting increasing attention due to the potential applications of spintronic devices in information storage, microprocessors, and a host of other technologies. Half-metal, as one of the most important spin injection source in spintronics, should be investigated deeply. Based on the above reason, this paper briefly summarizes the research progress of different kinds of half-metallic materials, and research orientations related to half-metallic materials are also proposed.
    Journal of Superconductivity and Novel Magnetism 02/2014; 27(2). · 0.93 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Care pathways (CPs) as a means of healthcare quality control are getting increasing attention due to widespread recognition in the healthcare industry of the need for well coordinated, evidence based and personalized care. To keep the promise, CPs require continuous refinement in order to stay up to date with regard to both clinical guidelines and data-driven insights from real world practices. There is therefore a strong demand for a unified platform that allows harmonization of evidence coming from multiple sources. In this paper we describe Care Pathway Workbench, a web-based platform that enables users to build and continuously improve Case Management Model and Notation based CPs by harmonizing evidences from guidelines and patient data. To illustrate the functionalities, we describe how a CHF (Congestive Heart Failure) Ambulatory Care Pathway can be developed using this workbench by first extracting key elements from widely accepted guidelines for CHF management, then incorporating evidence mined from clinical practice data, and finally transforming and exporting the resulting CP model to a care management product.
    Studies in health technology and informatics 01/2014; 205:23-27.

Publication Stats

936 Citations
96.48 Total Impact Points


  • 2010–2015
    • Hebei University of Technology
      • Institute of Power Source and Ecomaterials Science
      Ho-pei-ts’un, Beijing, China
    • Cornell University
      • Department of Statistical Science
      Ithaca, New York, United States
  • 2014
    • Huaiyin Institute of Technology
      Ch’ing-chiang, Jiangsu Sheng, China
  • 2011–2014
    • IBM
      Armonk, New York, United States
    • Purdue University
      • Department of Computer Science
      West Lafayette, IN, United States
  • 2009–2011
    • Florida International University
      • School of Computing and Information Sciences
      Miami, Florida, United States
  • 2005–2011
    • Tsinghua University
      • Department of Automation
      Beijing, Beijing Shi, China