Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

Applications of machine learning to machine fault diagnosis: A review and roadmap

Machinery health prognostics: A systematic review from data acquisition to RUL prediction

We report on a data-driven approach for the remaining useful life (RUL) estimation of rolling element bearings based on e-Support Vector Regression ( e-SVR). Lifetime data are analyzed and evaluated. The occurrence of critical faults in every test is located, and a critical operational threshold is established. Multiple statistical features from the time-domain, frequency domain, and time-scale domain through a wavelet transform are extracted from the recordings of two accelerometers, and assessed for their diagnostic performance. Among those features, Wiener entropy is utilized for the first time in the condition monitoring of rolling bearings. A SVR model is trained and tested for the prediction of RUL on unseen data. Special attention is given in the tuning and the optimization of the user-defined hyper-parameters of the e-SVR model. Error bounds are estimated at each prediction point through a Bayesian treatment of the classical SVR model. The results are in good agreement to the actual RUL curve for all the tested cases. Prognostic performance metrics are also provided, and the discussion on the test results concludes with the generic character of the proposed methodology and its applicability in any prognostic task.

Remaining Useful Life Estimation in Rolling Bearings Utilizing Data-Driven Probabilistic E-Support Vectors Regression

Cardiotocography is the main method used for fetal assessment in everyday clinical practice for the last 30 years. Many attempts have been made to increase the effectiveness of the evaluation of cardiotocographic recordings and minimize the variations of their interpretation utilizing technological advances. This research work proposes and focuses on an advanced method able to identify fetuses compromised and suspicious of developing metabolic acidosis. The core of the proposed method is the introduction of a support vector machine to "foresee" undesirable and risky situations for the fetus, based on features extracted from the fetal heart rate signal at the time and frequency domains along with some morphological features. This method has been tested successfully on a data set of intrapartum recordings, achieving better and balanced overall performance compared to other classification methods, constituting,therefore, a promising new automatic methodology for the prediction of metabolicacidosis

Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines

Bearing fault detection based on hybrid ensemble detector and empirical mode decomposition

This paper presents a pattern recognition approach for the identification of basic hand movements using surface electromyographic (EMG) data. The EMG signal is decomposed using Empirical Mode Decomposition (EMD) into Intrinsic Mode Functions (IMFs) and subsequently a feature extraction stage takes place. Various combinations of feature subsets are tested using a simple linear classifier for the detection task. Our results suggest that the use of EMD can increase the discrimination ability of the conventional feature sets extracted from the raw EMG signal.

George Georgoulas

Papers

Remaining Useful Life Estimation in Rolling Bearings Utilizing Data-Driven Probabilistic E-Support Vectors Regression

Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines

Bearing fault detection based on hybrid ensemble detector and empirical mode decomposition

Improving EMG based classification of basic hand movements using EMD

Using nonlinear features for fetal heart rate classification