Search results for "Performance prediction"

Student Performance Prediction Based on Blended Learning

2021

Contribution: This article explored blended learning by implementing a student-centered teaching method based on the flipped classroom and small private online course (SPOC). The impact of general online learning behavior on student performance was analyzed. This work is practical and provides enlightenment for learning analysis and individualized teaching in blended learning. Background: Providing individualized teaching in a large class is an effective way to improve teaching quality, but the traditional teaching method makes it difficult for teachers to learn about each student’s learning situation. Blended learning offers the possibility of individualized teaching for teachers. The comb…

Simplified models for the performance evaluation of desiccant wheel dehumidification

2002

In the present communication, simple models have been presented to evaluate the performance of rotary desiccant wheels based on different kind of solid desiccants e.g. silica gel and LiCl. The first part of the paper presents ‘Model 54’ which is developed for silica gel desiccant rotor. The model has been derived from the interpolation of experimental data obtained from the industry and the correlations have been developed for predicting outlet temperature and absolute humidity. The ‘Model 54’ consists of 54 coefficients corresponding to each correlation for outlet absolute humidity and temperature and it is found that the model predicts very well the performance of silica gel desiccant rot…

Update on desiccant wheel model

2004

This short communication presents the update on the desiccant wheel models, developed earlier by the present authors. It is to be mentioned here that the psycrometric model presented earlier (Int. J. Energy Res., 2003; 27:17) is valid only for the desiccant wheel running with identical volume air-flows in supply and regeneration sides. However, when system runs with volume air flow ratio between supply and regeneration side (α), different from 1 (one), the model need further modifications. In the present work, correction factors were developed and incorporated in order to update the earlier model for predicting correctly the temperature and humidity of processed air at the outlet of desicca…

Coupling CFD with a one-dimensional model to predict the performance of reverse electrodialysis stacks

2017

Abstract Different computer-based simulation models, able to predict the performance of Reverse ElectroDialysis (RED) systems, are currently used to investigate the potentials of alternative designs, to orient experimental activities and to design/optimize prototypes. The simulation approach described here combines a one-dimensional modelling of a RED stack with a fully three-dimensional finite volume modelling of the electrolyte channels, either planar or equipped with different spacers or profiled membranes. An advanced three-dimensional code was used to provide correlations for the friction coefficient (based on 3-D solutions of the continuity and Navier-Stokes equations) and the Sherwoo…

ASR performance prediction on unseen broadcast programs using convolutional neural networks

2018

In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance prediction based on regression (engineered features) and a new strategy based on convolutional neural networks (learnt features). We particularly focus on the combination of both textual (ASR transcription) and signal inputs. While the joint use of textual and signal features did not work for the regression baseline, the combination of inputs for CNNs leads to the best WER prediction performance. We also show that our CNN prediction remarkably …

Analyzing Learned Representations of a Deep ASR Performance Prediction Model

2018

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to predict word error rate. This work is dedicated to the analysis of speech signal embeddings and text embeddings learnt by the CNN while training our prediction model. We try to better understand which information is captured by the deep model and its relation with different conditioning factors. It is shown that hidden layers convey a clear signal about speech style, accent and broadcast type. We then try to leverage these 3 types of information …

A machine learning approach to determine airport asphalt concrete layer moduli using heavy weight deflectometer data

2021

An integrated approach based on machine learning and data augmentation techniques has been developed in order to predict the stiffness modulus of the asphalt concrete layer of an airport runway, from data acquired with a heavy weight deflectometer (HWD). The predictive model relies on a shallow neural network (SNN) trained with the results of a backcalculation, by means of a data augmentation method and can produce estimations of the stiffness modulus even at runway points not yet sampled. The Bayesian regularization algorithm was used for training of the feedforward backpropagation SNN, and a k-fold cross-validation procedure was implemented for a fair performance evaluation. The testing p…

Interactive effects of emotions on performance: an exploratory study in elite skeet shooters

2021

Este estudio investiga los efectos interactivos de múltiples emociones en el rendimiento (resultado) de tres tiradores de skeet de elite. La escala de emociones agregadas Emotional State Profile-40 (ESP-40; Hanin, 2010b) evalúa las experiencias emocionales recordadas asociadas con rendimientos exitosos y pobres y con rendimientos actuales. El rendimiento actual consiste en 20 series de 25 tiros. Los resultados confirman la utilidad práctica de la escala ESP-40 en la evaluación de los efectos interactivos de cuatro categorías de emoción en el rendimiento deportivo. Las emociones recordadas fueron instrumentales en la predicción de los resultados actuales. Se discute la utilidad de la regresi…

Analyzing and forecasting the performance of water drive gas reservoirs

2019

Contributions to the knowledge base on PV performance: Evaluation of the operation of PV systems using different technologies installed in southern N…

2011

To assist in establishing an accepted knowledge base on PV-modules and systems performance using a representative range of technologies, devices have to be installed at diverse locations, covering a broad range of environmental conditions. For the example of a high latitude location, modules and systems are installed and under investigation in southern Norway (Kristiansand region) by the University of Agder in cooperation with industrial partners. This paper presents first results of the analysis of module performance. The operational behavior of the modules is used to derive a modeling scheme applicable for performance prediction. This use is demonstrated by giving the expected annual perf…