A comparative study of machine learning algorithms for physiological signal classification

Biagetti, Giorgio; Crippa, Paolo; Falaschetti, Laura; Tanoni, Giulia; Turchetti, Claudio

doi:10.1016/j.procs.2018.07.255

Cited by 24 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, these results show how traditional ML methodologies still hold a relevant place for highly complex tasks such as voice analysis with low-cardinality datasets; on a side note, as limited as the study population might be, this remains a work involving one the biggest datasets for PD detection to-date [ 91 ]. Thus, as many studies and results such as [ 20 , 92 ] and [ 93 ] suggest, ML algorithms can still provide significant results, sometimes improving the state-of-the-art diagnosis, if carefully fine-tuned and applied to the correct features.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Costantini

Cesarini

Leo

et al. 2023

Sensors

View full text Add to dashboard Cite

Parkinson’s Disease (PD) is one of the most common non-curable neurodegenerative diseases. Diagnosis is achieved clinically on the basis of different symptoms with considerable delays from the onset of neurodegenerative processes in the central nervous system. In this study, we investigated early and full-blown PD patients based on the analysis of their voice characteristics with the aid of the most commonly employed machine learning (ML) techniques. A custom dataset was made with hi-fi quality recordings of vocal tasks gathered from Italian healthy control subjects and PD patients, divided into early diagnosed, off-medication patients on the one hand, and mid-advanced patients treated with L-Dopa on the other. Following the current state-of-the-art, several ML pipelines were compared usingdifferent feature selection and classification algorithms, and deep learning was also explored with a custom CNN architecture. Results show how feature-based ML and deep learning achieve comparable results in terms of classification, with KNN, SVM and naïve Bayes classifiers performing similarly, with a slight edge for KNN. Much more evident is the predominance of CFS as the best feature selector. The selected features act as relevant vocal biomarkers capable of differentiating healthy subjects, early untreated PD patients and mid-advanced L-Dopa treated patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Costantini

Cesarini

Leo

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The choice of algorithm may also depend on factors such as the size and complexity of the dataset, available computing resources, and the desired classification accuracy and speed. However, the SVN algorithm has been used for this purpose since it allows for a high-speed and accurate classification of such time-domain signals, according to [ 40 , 41 ].…”

Section: Methodsmentioning

confidence: 99%

Wireless Body Area Network for Preventing Self-Inoculation Transmission of Respiratory Viral Diseases

Pawlicki

Fotyga

Rewieński

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper proposes an idea of Wireless Body Area Networks (WBANs) based on Bluetooth Low-Energy (BLE) standards to recognize and alarm a gesture of touching the face, and in effect, to prevent self-inoculation of respiratory viral diseases, such as COVID-19 or influenza A, B, or C. The proposed network comprises wireless modules placed in bracelets and a necklace. It relies on the received signal strength indicator (RSSI) measurements between the bracelet and necklace modules. The measured signal is cleared of noise using the exponential moving average (EMA). Next, we use a classification algorithm based on a Least-Squares Support Vector Machine (LSSVM) in order to detect facial touches. When the results of the classification indicate that the hand is moving toward the face, an alarm is sent through the neck module and the vibrator embedded in the wrist module is switched on. Based on the performed tests, it can be concluded that the proposed solution is characterized by high accuracy and reliability. It should be useful, especially for individuals who are regularly exposed to the risk of respiratory infections.

show abstract

“…The machine learning module is supposed to infer a physiological function that relates the features extracted from the PPG signal and the desired target [28]. Literature clearly portrays that most of the work involved in the detection of OSA has used neural network-based classifier [29]. It is also understood that deep learning neural networks have always outperformed the shallow neural networks and convolutional neural network is the widely used classifier in the recent years [30], [31].…”

Section: Classifier Modulementioning

confidence: 99%

An automatic screening approach for obstructive sleep apnea from photoplethysmograph using machine learning techniques

2021

View full text Add to dashboard Cite

Obstructive sleep apnea (OSA), a very common sleep disorder remains as an underdiagnosed root cause for several cardiovascular and cerebrovascular diseases. In this paper, we propose an efficient and accurate system that utilizes a single sensor for effective screening of OSA using machine learning algorithms. The automatic screening system involves a photoplethysmogram (PPG) signal, a novel algorithm to detect and remove the corrupted part of the signal, a feature extraction module to extract several features from the PPG waveform and a classifier module which helps in screening for OSA. The elemental idea behind this work is that there is a characteristic relationship between the shape of the PPG waveform and the oxygen desaturation in the apnea patients. The method as described was tested on 285 subjects, inclusive of both normal and apnea patients, and the results were obtained after 10-fold-cross validation of the different machine learning techniques viz., univariate regression, multivariate regression, support vector machine and random forest. The best results in screening OSA were obtained from random forest algorithm with the highest performance (Acc: 98.0%, Sen: 98.6%, Spec: 99.3%) for all the combined features. The proposed work is an effective system for automatic screening of OSA from a single PPG sensor, thereby reducing the need for a very expensive and overnight polysomnography sleep study.

show abstract

A comparative study of machine learning algorithms for physiological signal classification

Cited by 24 publications

References 21 publications

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Wireless Body Area Network for Preventing Self-Inoculation Transmission of Respiratory Viral Diseases

An automatic screening approach for obstructive sleep apnea from photoplethysmograph using machine learning techniques

Contact Info

Product

Resources

About