Permutation Entropy as a Conceptual Model to Analyse Brain Activity in Sleep

Sleep stage classification is a widely discussed topic, due to its importance in the diagnosis of sleep disorders, e.g. insomnia. Analysis of the brain activity during sleep is necessary to gain further insight into the processing that occurs in our brains. We want to use permutation entropy as a model for this analysis. Therefore, the signal processing in terms of electroencephalography is described. This results in a time discrete signal, that can be further processed by applying the method of permutation entropy, which is a modification of the Shannon entropy as a measure of information processing. The method is applied to 18 data sets, nine electroencephalography measurements of patients suffering from insomnia and nine of people without a sleep disorder. A strong correlation between the permutation entropy value and the sleep stages was found during the simulation runs. The results are analysed and presented using boxplot diagrams of the permutation entropy over the sleep stages. Furthermore, it is investigated that there is a steady decrease in the value when the patient is in a deeper sleep. This suggests that the method is a good parameter for sleep stage classification. Finally, we propose an extension of the conceptual model to other pathological conditions and also to the analysis of brain activity during surgery.

Novel features for the detection of bearing faults in railway vehicles

{In this paper, we address the challenging problem of detecting bearing faults from vibration signals. For this, several time- and frequency-domain features have been proposed already in the past. However, these features are usually evaluated on data originating from relatively simple scenarios and a significant performance loss can be observed if more realistic scenarios are considered. To overcome this, we introduce Mel-Frequency Cepstral Coefficients (MFCCs) and features extracted from the Amplitude Modulation Spectrogram (AMS) as features for the detection of bearing faults. Both AMS and MFCCs were originally introduced in the context of audio signal processing but it is demonstrated that a significantly improved classification performance can be obtained by using these features. Furthermore, to tackle the characteristic data imbalance problem in the context of bearing fault detection, i.e., typically much more data from healthy bearings than from damaged bearings is available, we propose to train a One-class \ac{SVM} with data from healthy bearings only. Bearing faults are then classified by the detection of outliers. Our approach is evaluated with data measured in a highly challenging scenario comprising a state-of-the-art commuter railway engine which is supplied by an industrial power converter and coupled to a load machine.

Airborne-Sound Analysis for the Detection of Bearing Faults in Railway Vehicles with Real-World Data

In this paper, we address the challenging problem of detecting bearing faults in railway vehicles by analyzing acoustic signals recorded during regular operation. For this, we introduce Mel Frequency Cepstral Coefficients (MFCCs) as features, which form the input to a simple Multi-Layer Perceptron classifier. The proposed method is evaluated with real-world data that was obtained for state-of-the-art commuter railway vehicles in a measurement campaign. The experiments show that with the chosen MFCC features bearing faults can be reliably detected even for bearing damages that were not included in training.

1-D Residual Convolutional Neural Network coupled with Data Augmentation and Regularization Techniques for the ICPHM 2023 Data Challenge

In this article, we present our contribution to the ICPHM 2023 Data Challenge on Industrial Systems' Health Monitoring using Vibration Analysis. For the task of classifying sun gear faults in a gearbox, we propose a residual Convolutional Neural Network that operates on raw three-channel time-domain vibration signals. In conjunction with data augmentation and regularization techniques, the proposed model yields very good results in a multi-class classification scenario with real-world data despite its relatively small size, i.e., with less than 30,000 trainable parameters. Even when presented with data obtained from multiple operating conditions, the network is still capable to accurately predict the condition of the gearbox under inspection.