This paper is a tribute to the late Professor Jan Larsen's work on machine learning for condition monitoring of large diesel engines. We present the ultrasound signals used to monitor the condition of the large engines and revisit two methods for estimating the condition of the engines from the ultrasound signals. Finally, we touch upon the increased importance of condition monitoring in large diesel engine industry today.

Slow convergence is observed in the EM algorithm for linear state-space models. We propose to circumvent the problem by applying any off-the-shelf quasi-Newton-type optimizer, which operates on the gradient of the log-likelihood function. Such an algorithm is a practical alternative due to the fact that the exact gradient of the log-likelihood function can be computed by recycling components of the expectation-maximization (EM) algorithm. We demonstrate the efficiency of the proposed method in three relevant instances of the linear state-space model. In high signal-to-noise ratios, where EM is particularly prone to converge slowly, we show that gradient-based learning results in a sizable reduction of computation time.

In this paper we are presenting a novel multivariate analysis method. Our scheme is based on a novel kernel orthonormalized partial least squares (PLS) variant for feature extraction, imposing sparsity constrains in the solution to improve scalability. The algorithm is tested on a benchmark of UCI data sets, and on the analysis of integrated short-time music features for genre prediction. The upshot is that the method has strong expressive power even with rather few features, is clearly outperforming the ordinary kernel PLS, and therefore is an appealing method for feature extraction of labelled data.

We investigate two techniques for independent component analysis which use the expectation-maximization algorithm. Analysis and simulations show that convergence becomes extraordinarily slow for almost all cases, compared to other optimization techniques. The two alternatives considered are "adaptive overrelaxed EM" and Ucminf (a BFGS with soft line search), which both improves the convergence dramatically with little or no extra analytical work. We discuss the generality and perspectives of the findings.

We analyze convergence of the expectation maximization (EM) and variational Bayes EM (VBEM) schemes for parameter estimation in noisy linear models. The analysis shows that both schemes are inefficient in the low-noise limit. The linear model with additive noise includes as special cases independent component analysis, probabilistic principal component analysis, factor analysis, and Kalman filtering. Hence, the results are relevant for many practical applications.