Ricardo Buettner

Bio: Ricardo Buettner is an academic researcher from University of Bayreuth. The author has contributed to research in topics: Convolutional neural network & Systematic review. The author has an hindex of 9, co-authored 28 publications receiving 272 citations.

High-performance exclusion of schizophrenia using a novel machine learning method on EEG data

Abstract: Using the Random Forest method, we developed a fast-high-performance classification model, which can exclude a potential schizophrenic disorder in a diagnosis of potentially exposed people. Our model mainly consists of three preprocessing steps: ICA, Spectral Analysis using Buettner et al.’s 99-frequency-band-method and normalization. Using this preprocessing pipeline followed by a Random Forest, validated with different parameters, random states and a 10-fold-cross-validation, we could exclude schizophrenia with an accuracy of 100%. By applying this model in combination with a differential diagnoses system, treatments in ICUs can be done much faster, more accurately and be less expensive.

Efficient machine learning based detection of heart disease

Abstract: This paper describes a method to detect possible heart disease using the Random Forests algorithm. Cardiovascular diseases are the number 1 cause of death globally - an estimated 17.9 million people died from it in 2016. This machine learning work contributes to healthcare and can detect heart disease on the basis of clinical data and test data from different patients. The result and contribution of this paper is to identify whether a patient has heart disease or not, based on the information of clinical data and test results and so support doctors in making decisions about patient treatments.

High-performance detection of epilepsy in seizure-free EEG recordings: A novel machine learning approach using very specific epileptic EEG sub-bands

Abstract: We applied machine learning to diagnose epilepsy based on the fine-graded spectral analysis of seizure-free (resting state) EEG recordings. Despite using unspecific agglomerated EEG spectra, our fine-graded spectral analysis specifically identified the two EEG resting state sub-bands differentiating healthy people from epileptics (1.5-2 Hz and 11-12.5 Hz). The rigorous evaluation of completely unseen data of 100 EEG recordings (50 belonging to epileptics and the other 50 to healthy people) shows that the approach works successfully, achieving an outstanding accuracy of 99 percent, which significantly outperforms the current benchmark of 70% to 95% by a panel of up to three experienced neurologists. Our epilepsy diagnosis classifier can be implemented in modern EEG analysis devices, especially in intensive care units where early diagnosis and appropriate treatment are decisive in life and death scenarios and where physicians’ error rates are particularly high. Our approach is accurate, robust, fast, and cost-efficient and substantially contributes to Information Systems research in healthcare. The approach is also of high practical and theoretical relevance.

High-performance detection of alcoholism by unfolding the amalgamated EEG spectra using the Random Forests method

Abstract: We show that by unfolding the outdated EEG standard bandwidths in a fine-grade equidistant 99-point spectrum we can precisely detect alcoholism. Using this novel pre-processing step prior to entering a random forests classifier, our method substantially outperforms all previous results with a balanced accuracy of 97.4 percent. Our machine learning work contributes to healthcare and information systems. Due to its drastic and protracted consequences, alcohol consumption is always a critical issue in our society. Consequences of alcoholism in the brain can be recorded using electroencephalography (EEG). Our work can be used to automatically detect alcoholism in EEG mass data within milliseconds. In addition, our results challenge the medically outdated EEG standard bandwidths.

Microsaccades as a Predictor of a User’s Level of Concentration

Abstract: In comparison to voluntary eye movements (saccades), micro-saccades are very small, jerk-like and involuntary. While microsaccades and cognition has become one of the most rapidly growing areas of study in visual neuroscience [Trends Neurosci. 32: 463–475], microsaccades are still neglected in NeuroIS. Using experimental data by Walcher et al. [Conscious Cogn. 53:165–175; Data Brief 15:18–24] we demonstrate the potential of microsaccades to evaluate the level of concentration a user perceives during task fulfillment. As a result we found a substantial negative relationship between the magnitudes of the microsaccades and the level of concentration (p < 0.01).

A deep learning-based model for defect detection in laser-powder bed fusion using in-situ thermographic monitoring

Abstract: Additive manufacturing of metal components with laser-powder bed fusion is a very complex process, since powder has to be melted and cooled in each layer to produce a part. Many parameters influence the printing process; however, defects resulting from suboptimal parameter settings are usually detected after the process. To detect these defects during the printing, different process monitoring techniques such as melt pool monitoring or off-axis infrared monitoring have been proposed. In this work, we used a combination of thermographic off-axis imaging as data source and deep learning-based neural network architectures, to detect printing defects. For the network training, a k-fold cross validation and a hold-out cross validation were used. With these techniques, defects such as delamination and splatter can be recognized with an accuracy of 96.80%. In addition, the model was evaluated with computing class activation heatmaps. The architecture is very small and has low computing costs, which means that it is suitable to operate in real time even on less powerful hardware.

Development of a Machine Learning Based Algorithm To Accurately Detect Schizophrenia based on One-minute EEG Recordings

Abstract: While diagnosing schizophrenia by physicians based on patients' history and their overall mental health is inaccurate, we report on promising results using a novel, fast and reliable machine learning approach based on electroencephalography (EEG) recordings. We show that a fine granular division of EEG spectra in combination with the Random Forest classifier allows a distinction to be made between paranoid schizophrenic (ICD-10 F20.0) and nonschizophrenic persons with a very good balanced accuracy of 96.77 percent. We evaluate our approach on EEG data from an open neurological and psychiatric repository containing 499 one-minute recordings of n=28 participants (14 paranoid schizophrenic and 14 healthy controls). Since the fact that neither diagnostic tests nor biomarkers are available yet to diagnose paranoid schizophrenia, our approach paves the way to a quick and reliable diagnosis with a high accuracy. Furthermore, interesting insights about the most predictive subbands were gained by analyzing the electroencephalographic spectrum up to 100 Hz.

Transfer learning with deep convolutional neural network for automated detection of schizophrenia from EEG signals.

Abstract: Schizophrenia (SZ) is a severe disorder of the human brain which disturbs behavioral characteristics such as interruption in thinking, memory, perception, speech and other living activities. If the patient suffering from SZ is not diagnosed and treated in the early stages, damage to human behavioral abilities in its later stages could become more severe. Therefore, early discovery of SZ may help to cure or limit the effects. Electroencephalogram (EEG) is prominently used to study brain diseases such as SZ due to having high temporal resolution information, and being a noninvasive and inexpensive method. This paper introduces an automatic methodology based on transfer learning with deep convolutional neural networks (CNNs) for the diagnosis of SZ patients from healthy controls. First, EEG signals are converted into images by applying a time–frequency approach called continuous wavelet transform (CWT) method. Then, the images of EEG signals are applied to the four popular pre-trained CNNs: AlexNet, ResNet-18, VGG-19 and Inception-v3. The output of convolutional and pooling layers of these models are used as deep features and are fed into the support vector machine (SVM) classifier. We have tuned the parameters of SVM to classify SZ patients and healthy subjects. The efficiency of the proposed method is evaluated on EEG signals from 14 healthy subjects and 14 SZ patients. The experiments showed that the combination of frontal, central, parietal, and occipital regions applied to the ResNet-18-SVM achieved best results with accuracy, sensitivity and specificity of 98.60% ± 2.29, 99.65% ± 2.35 and 96.92% ± 2.25, respectively. Therefore, the proposed method as a diagnostic tool can help clinicians in detection of the SZ patients for early diagnosis and treatment.

Automatic detection of schizophrenia by applying deep learning over spectrogram images of EEG signals

Abstract: Received: 17 January 2020 Accepted: 20 March 2020 This study presents a method that aims to automatically diagnose Schizophrenia (SZ) patients by using EEG recordings. Unlike many literature studies, the proposed method does not manually extract features from EEG recordings, instead it transforms the raw EEG into 2D by using Short-time Fourier Transform (STFT) in order to have a useful representation of frequency-time features. This work is the first in the relevant literature in using 2D timefrequency features for the purpose of automatic diagnosis of SZ patients. In order to extract most useful features out of all present in the 2D space and classify samples with high accuracy, a state-of-art Convolutional Neural Network architecture, namely VGG-16, is trained. The experimental results show that the method presented in the paper is successful in the task of classifying SZ patients and healthy controls with a classification accuracy of 95% and 97% in two datasets of different age groups. With this performance, the proposed method outperforms most of the literature methods. The experiments of the study also reveal that there is a relationship between frequency components of an EEG recording and the SZ disease. Moreover, Grad-CAM images presented in the paper clearly show that mid-level frequency components matter more while discriminating a SZ patient from a healthy control.