Institution
Worcester Polytechnic Institute
Education•Worcester, Massachusetts, United States•
About: Worcester Polytechnic Institute is a education organization based out in Worcester, Massachusetts, United States. It is known for research contribution in the topics: Computer science & Population. The organization has 6270 authors who have published 12704 publications receiving 332081 citations. The organization is also known as: WPI.
Topics: Computer science, Population, Data envelopment analysis, Nonlinear system, Finite element method
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this article, the steady flow of Herschel-Bulkley fluids in a canonical three-dimensional expansion was modeled using a regularized continuous constitutive relation, and the flow was obtained numerically using a mixed-Galerkin finite element formulation with a Newton-Raphson iteration procedure coupled to an iterative solver.
Abstract: In this paper we study steady flow of Herschel–Bulkley fluids in a canonical three-dimensional expansion. The fluid behavior was modeled using a regularized continuous constitutive relation, and the flow was obtained numerically using a mixed-Galerkin finite element formulation with a Newton–Raphson iteration procedure coupled to an iterative solver. Results for the topology of the yielded and unyielded regions, and recirculation zones as a function of the Reynolds and Bingham numbers and the power-law exponent, are presented and discussed for a 2:1 and a 4:1 expansion ratio. The results reveal the strong interplay between the Bingham and Reynolds numbers and their influence on the formation and break up of stagnant zones in the corner of the expansion and on the size and location of core regions.
124 citations
•
01 Jan 2016TL;DR: It is determined that the DKT findings don't hold an overall edge when compared to the PFA model, when applied to properly prepared datasets that are limited to main (i.e. nonscaffolding) questions.
Abstract: Over the last couple of decades, there have been a large variety of approaches towards modeling student knowledge within intelligent tutoring systems. With the booming development of deep learning and large-scale artificial neural networks, there have been empirical successes in a number of machine learning and data mining applications, including student knowledge modeling. Deep Knowledge Tracing (DKT), a pioneer algorithm that utilizes recurrent neural networks to model student learning, reports substantial improvements in prediction performance. To help the EDM community better understand the promising techniques of deep learning, we examine DKT alongside two well-studied models for knowledge modeling, PFA and BKT. In addition to sharing a primer on the internal computational structures of DKT, we also report on potential issues that arise from data formatting. We take steps to reproduce the experiments of Deep Knowledge Tracing by implementing a DKT algorithm using Google’s TensorFlow framework; we also reproduce similar results on new datasets. We determine that the DKT findings don't hold an overall edge when compared to the PFA model, when applied to properly prepared datasets that are limited to main (i.e. nonscaffolding) questions. More importantly, during the investigation of DKT, we not only discovered a data quality issue in a public available data set, but we also detected a vulnerability of DKT at how it handles multiple skill sequences.
124 citations
••
01 Jan 2013TL;DR: In this article, a thermally thick slab of polymethyl methacrylate was used to study the effects of the inclination angle of a fuel surface on upward flame spread and the influence of buoyancy-induced flows in modifying heat-flux profiles ahead of the flame front, which controlled flame spread, and in affecting the heat flux to the burning surface of the fuel.
Abstract: A thermally thick slab of polymethyl methacrylate was used to study the effects of the inclination angle of a fuel surface on upward flame spread. While investigation of upward spread over solid fuels has typically been restricted to an upright orientation, inclination of the fuel surface from the vertical is a common occurrence that has not yet been adequately addressed. By performing experiments on 10 cm wide by 20 cm tall fuel samples it was found that the maximum flame-spread rate, occurring nearly in a vertical configuration, does not correspond to the maximum fuel mass-loss rate, which occurs closer to a horizontal configuration. A detailed study of both flame spread and steady burning at different angles of inclination revealed the influence of buoyancy-induced flows in modifying heat-flux profiles ahead of the flame front, which control flame spread, and in affecting the heat flux to the burning surface of the fuel, which controls fuel mass-loss rates.
123 citations
••
TL;DR: A novel approach that utilizes deep two-dimensional (2-D) Convolutional Neural Networks to extract features from 2-D scalograms generated from PV system data in order to effectively detect and classify PV system faults is presented.
Abstract: Fault diagnosis in photovoltaic (PV) arrays is essential in enhancing power output as well as the useful life span of a PV system. Severe faults such as Partial Shading (PS) and high impedance faults, low location mismatch, and the presence of Maximum Power Point Tracking (MPPT) make fault detection challenging in harsh environmental conditions. In this regard, there have been several attempts made by various researchers to identify PV array faults. However, most of the previous work has focused on fault detection and classification in only a few faulty scenarios. This paper presents a novel approach that utilizes deep two-dimensional (2-D) Convolutional Neural Networks (CNN) to extract features from 2-D scalograms generated from PV system data in order to effectively detect and classify PV system faults. An in-depth quantitative evaluation of the proposed approach is presented and compared with previous classification methods for PV array faults - both classical machine learning based and deep learning based. Unlike contemporary work, five different faulty cases (including faults in PS - on which no work has been done before in the machine learning domain) have been considered in our study, along with the incorporation of MPPT. We generate a consistent dataset over which to compare ours and previous approaches, to make for the first (to the best of our knowledge) comprehensive and meaningful comparative evaluation of fault diagnosis. It is observed that the proposed method involving fine-tuned pre-trained CNN outperforms existing techniques, achieving a high fault detection accuracy of 73.53%. Our study also highlights the importance of representative and discriminative features to classify faults (as opposed to the use of raw data), especially in the noisy scenario, where our method achieves the best performance of 70.45%. We believe that our work will serve to guide future research in PV system fault diagnosis.
123 citations
••
TL;DR: It is proved that even a subset of available RF features provides an acceptable classification rate, which may result in less computational cost and easier implementation by using the proposed scheme.
Abstract: The real-time health monitoring system is a promising body area network application to enhance the safety of firefighters when they are working in harsh and dangerous environments. Other than monitoring the physiological status of the firefighters, on-body monitoring networks can be also regarded as a candidate solution of motion detection and classification. In this paper, we consider motion classification with features obtained from the on-body radio frequency (RF) channel. Various relevant RF features have been identified and a support vector machine (SVM) has been implemented to facilitate human motion classification. In particular, we distinguish the most frequently appearing human motions of firefighters including standing, walking, running, lying, crawling, climbing, and running upstairs with an average true classification rate of 88.69 percent. Classification performance has been analyzed from three different perspectives including typical classification results, effects of candidate human motions, and effects of on-body sensor locations. We prove that even a subset of available RF features provides an acceptable classification rate, which may result in less computational cost and easier implementation by using our proposed scheme.
122 citations
Authors
Showing all 6336 results
Name | H-index | Papers | Citations |
---|---|---|---|
Andrew G. Clark | 140 | 823 | 123333 |
Ming Li | 103 | 1669 | 62672 |
Joseph Sarkis | 101 | 482 | 45116 |
Arthur C. Graesser | 95 | 614 | 38549 |
Kevin J. Harrington | 85 | 682 | 33625 |
Kui Ren | 83 | 501 | 32490 |
Bart Preneel | 82 | 844 | 25572 |
Ming-Hui Chen | 82 | 525 | 29184 |
Yuguang Fang | 79 | 572 | 20715 |
Wenjing Lou | 77 | 311 | 29405 |
Bernard Lown | 73 | 330 | 20320 |
Joe Zhu | 72 | 231 | 19017 |
Y.S. Lin | 71 | 304 | 16100 |
Kevin Talbot | 71 | 268 | 15669 |
Christof Paar | 69 | 399 | 21790 |