• A didactically motivated PLS prediction algorithm 

      Ergon, Rolf; Esbensen, Kim H. (Journal article; Peer reviewed, 2001)
      The intention of this paper is to develop an easily understood PLS prediction algorithm, especially for the control community. The algorithm is based on an explicit latent variables model, and is otherwise a combination ...
    • Compression into two-component PLS factorizations 

      Ergon, Rolf (Journal article; Peer reviewed, 2003)
      Partial least squares regression (PLSR) often requires more than two components also in the case of a scalar response variable. As shown in papers on orthogonal signal correction (OSC), it is possible to reduce the number ...
    • Constrained numerical optimization of PCR/PLSR predictors 

      Ergon, Rolf (Journal article; Peer reviewed, 2003)
      Assuming a fully known latent variables (LV) model, the optimal multivariate calibration predictor is found from Kalman filtering theory. From this follows the best possible column space for a loading weight matrix Wopt. ...
    • Delayed density-dependent onset of spring reproduction in a fluctuating population of field voles 

      Ergon, Torbjørn; Ergon, Rolf; Begon, Mike; Telfer, Sandra; Lambin, Xavier (Journal article; Peer reviewed, 2011)
      Delayed density-dependent demographic processes are thought to be the basis for multi-annual cyclic fluctuations in small rodent populations, but evidence for delayed density dependence of a particular demographic trait ...
    • Dynamic system calibration by system identification methods 

      Ergon, Rolf; Di Ruscio, David (Conference object; Peer reviewed, 1997)
      Primary output variables from industrial processes can be estimated from known input variables and secondary process measurements. As a basis for this, the dynamic predictor has to be identi ed from data collected during ...
    • Dynamic system multivariate calibration 

      Ergon, Rolf (Journal article; Peer reviewed, 1998)
      In the first part of the paper, the optimal estimator for normally nonmeasured primary outputs from a linear, time invariant and stable dynamic system is developed. The optimal estimator is based on all available information ...
    • Dynamic system multivariate calibration based on multirate sampling data 

      Ergon, Rolf; Halstensen, Maths (Journal article; Peer reviewed, 2001)
    • Dynamic system multivariate calibration for optimal primary output estimation 

      Ergon, Rolf (Doctoral thesis; Peer reviewed, 1999)
      In industrial plants and other types of dynamic systems, it is a common situation that measurements of primary system outputs are not available on-line. The primary outputs may for example be quality properties, that can ...
    • Dynamic system multivariate calibration with low-sampling-rate y data 

      Ergon, Rolf; Halstensen, Maths (Journal article; Peer reviewed, 2000)
      When the data in principal component regression (PCR) or partial least squares regression (PLSR) form time series, it may be possible to improve the prediction/estimation results by utilizing the correlation between ...
    • Estimation, system identification and chemometrics 

      Ergon, Rolf; Di Ruscio, David; Esbensen, Kim H.; Hagen, Svein Thore (Conference object, 2000)
      In our master degree program in process automation, traditional modeling and control courses are supplemented by courses in experimental design and chemometrics. A corresponding inter-disciplinary research program supports ...
    • Finding Y-relevant part of X by use of PCR and PLSR model reduction methods 

      Ergon, Rolf (Journal article; Peer reviewed, 2007)
      The paper is considering the following question: using principal component regression (PCR) or partial least squares regression (PLSR), how much data can be removed from X while retaining the original ability to predict ...
    • Informative PLS score-loading plots for process understanding 

      Ergon, Rolf (Journal article; Peer reviewed, 2004)
      Principal component regression (PCR) based on principal component analysis (PCA) and partial least squares regression (PLSR) are well known projection methods for analysis of multivariate data. They result in scores and ...
    • Informative score-loading-contribution plots for multi-response process monitoring 

      Ergon, Rolf (Journal article; Peer reviewed, 2009)
      The projection based multivariate data methods of principal component regression (PCR) and partial least squares regression (PLSR) are well established in the eld of process monitoring. Use of score and loading plots for ...
    • Modified Smith-predictor multirate control utilizing secondary process measurements 

      Ergon, Rolf (Conference object, 2001)
      The Smith-predictor is a well-known control structure for industrial time delay systems, where the basic idea is to estimate the nondelayed process output by use of a process model, and to use this estimate in an inner ...
    • Modified Smith-predictor multirate control utilizing secondary process measurements 

      Ergon, Rolf (Journal article; Peer reviewed, 2007)
      The Smith-predictor is a well-known control structure for industrial time delay systems, where the basic idea is to estimate the non-delayed process output by use of a process model, and to use this estimate in an inner ...
    • Noise handling capabilities of multivariate methods 

      Ergon, Rolf (Journal article; Peer reviewed, 2002)
      The noise handling capabilities of principal component regression (PCR) and partial least squares regression (PLSR) are somewhat disputed issues, especially regarding regressor noise. In an attempt to indicate an answer ...
    • On primary output estimation by use of secondary measurements as inputsignals in system identification 

      Ergon, Rolf (Journal article; Peer reviewed, 1999)
      In many cases, vital output variables in, e.g., industrial processes cannot be measured online. It is then of interest to estimate these primary variables from manipulated and measured inputs and the secondary output ...
    • PCR/PLSR optimization based on noise covariance estimation and Kalman filtering theory 

      Ergon, Rolf; Esbensen, Kim H. (Journal article; Peer reviewed, 2002)
      The theoretical connection between principal component regression (PCR) and partial least squares regression (PLSR) on one hand and Kalman filtering (KF) on the other is known from earlier work. In the present paper we ...
    • PLS post-processing by similarity transformation: a simple alternative to OPLS 

      Ergon, Rolf (Journal article; Peer reviewed, 2005)
      Several methods for orthogonal signal correction (OSC) based on pre-processing of the modeling data have been developed in recent years, and OPLS (orthogonal projections to latent structures) is a well known algorithm. ...
    • PLS score-loading correspondence and a bi-orthogonal factorization 

      Ergon, Rolf (Journal article; Peer reviewed, 2002)
      It is established industrial practice to use the correspondence between partial least squares (PLS) scores and loadings or loading weights as a means for process monitoring and control. Deviations from the normal operating ...