Design and evaluation of the effectiveness of a sonification technique for real time heart-rate data

Stahl, Benjamin; Thoshkahna, Balaji

doi:10.1007/s12193-016-0218-7

Cited by 8 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A handmade holder with a mobile phone is depicted in Figure 4 (during the experiment the phone was permanently fixed in the car door in the same position); The other smartphone in the experiment was always the participant’s private mobile phone in order to be able to collect his/her environment and activity data with sensors embedded into a smartphone, and to avoid using additional devices; A car—each participant’s private car; The Polar H7 chest belt (Polar Company, Kempele, Finland). The Polar H7 was used as a reliable sensor for collecting the HR data in many researches [ 51 , 52 ], serving as the ground truth data for estimation of the driver’s stress level [ 53 ]. A U-blox GPS device for gathering speed and acceleration data.…”

Section: Experiments Setup and Proceduresmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of the Driving Style Based on the Users’ Activity and Environment Influence

Sysoev

Kos

Guna

et al. 2017

Sensors

View full text Add to dashboard Cite

New models and methods have been designed to predict the influence of the user’s environment and activity information to the driving style in standard automotive environments. For these purposes, an experiment was conducted providing two types of analysis: (i) the evaluation of a self-assessment of the driving style; (ii) the prediction of aggressive driving style based on drivers’ activity and environment parameters. Sixty seven h of driving data from 10 drivers were collected for analysis in this study. The new parameters used in the experiment are the car door opening and closing manner, which were applied to improve the prediction accuracy. An Android application called Sensoric was developed to collect low-level smartphone data about the users’ activity. The driving style was predicted from the user’s environment and activity data collected before driving. The prediction was tested against the actual driving style, calculated from objective driving data. The prediction has shown encouraging results, with precision values ranging from 0.727 up to 0.909 for aggressive driving recognition rate. The obtained results lend support to the hypothesis that user’s environment and activity data could be used for the prediction of the aggressive driving style in advance, before the driving starts.

show abstract

Section: Experiments Setup and Proceduresmentioning

confidence: 99%

“…The Polar H7 chest belt (Polar Company, Kempele, Finland). The Polar H7 was used as a reliable sensor for collecting the HR data in many researches [ 51 , 52 ], serving as the ground truth data for estimation of the driver’s stress level [ 53 ].…”

Section: Experiments Setup and Proceduresmentioning

confidence: 99%

Estimation of the Driving Style Based on the Users’ Activity and Environment Influence

Sysoev

Kos

Guna

et al. 2017

Sensors

View full text Add to dashboard Cite

show abstract

“…Horsak et al [9] presents and evaluates a wireless insole system that can be used to drive gait sonification while Stahl and Thoshkahna [15] presents and evaluates a sonification technique aimed to assist athletes in maintaining their heart rate within a pre-defined range. Tordini et al [17] investigates auditory salience as an important design aspect of auditory displays, focusing specifically on the effect and interaction of tempo and brightness on salience between concurrent signals.…”

Section: Overview Of the Special Issue Contentsmentioning

confidence: 99%

Advances in auditory display research

Katz

Marentakis²

2016

J Multimodal User Interfaces

View full text Add to dashboard Cite

The research community on Auditory Design has been active and organized now for almost 25 years. Work in Auditory Display is pluri-disciplinary/inter-disciplinary in nature, and involves disciplines such as perception, acoustics, digital signal processing, multimodality, ergonomics, aesthetics, cognition, etc. Published works have spanned fundamental, phenomenological, theoretical, applicative, and artistic studies. Over the years, various journals have had special issues related to such work. The range of the associated journals reflects the variety of implicated domains. This current special issue presents a collection of extended works that were selected from papers presented at the 2015 International Conference on Auditory Display. We present here an overview of the selection process and the accepted papers.

show abstract

“…For example, higher HRV in atrial fibrillation could be heard as a discontinuous jump between high and low pitches with relatively constant tinkling sounds. Further studies investigated the appropriate HRV features to improve the perceptual quality and sonification interpretability [ 23 , 24 , 25 , 26 , 27 ]. An important application was highlighted in aiding the training of athletes who were able to maintain stable target heart rates by using sonification-assisted visual monitoring of HRV [ 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Convolutional Neural Network for Decoding of 12-Lead Electrocardiogram from a Frequency-Modulated Audio Stream (Sonified ECG)

Krasteva,

Iliev,

Tabakov

2024

Sensors

View full text Add to dashboard Cite

Research of novel biosignal modalities with application to remote patient monitoring is a subject of state-of-the-art developments. This study is focused on sonified ECG modality, which can be transmitted as an acoustic wave and received by GSM (Global System for Mobile Communications) microphones. Thus, the wireless connection between the patient module and the cloud server can be provided over an audio channel, such as a standard telephone call or audio message. Patients, especially the elderly or visually impaired, can benefit from ECG sonification because the wireless interface is readily available, facilitating the communication and transmission of secure ECG data from the patient monitoring device to the remote server. The aim of this study is to develop an AI-driven algorithm for 12-lead ECG sonification to support diagnostic reliability in the signal processing chain of the audio ECG stream. Our methods present the design of two algorithms: (1) a transformer (ECG-to-Audio) based on the frequency modulation (FM) of eight independent ECG leads in the very low frequency band (300–2700 Hz); and (2) a transformer (Audio-to-ECG) based on a four-layer 1D convolutional neural network (CNN) to decode the audio ECG stream (10 s @ 11 kHz) to the original eight-lead ECG (10 s @ 250 Hz). The CNN model is trained in unsupervised regression mode, searching for the minimum error between the transformed and original ECG signals. The results are reported using the PTB-XL 12-lead ECG database (21,837 recordings), split 50:50 for training and test. The quality of FM-modulated ECG audio is monitored by short-time Fourier transform, and examples are illustrated in this paper and supplementary audio files. The errors of the reconstructed ECG are estimated by a popular ECG diagnostic toolbox. They are substantially low in all ECG leads: amplitude error (quartile range RMSE = 3–7 μV, PRD = 2–5.2%), QRS detector (Se, PPV > 99.7%), P-QRS-T fiducial points’ time deviation (<2 ms). Low errors generalized across diverse patients and arrhythmias are a testament to the efficacy of the developments. They support 12-lead ECG sonification as a wireless interface to provide reliable data for diagnostic measurements by automated tools or medical experts.

show abstract

Design and evaluation of the effectiveness of a sonification technique for real time heart-rate data

Cited by 8 publications

References 3 publications

Estimation of the Driving Style Based on the Users’ Activity and Environment Influence

Estimation of the Driving Style Based on the Users’ Activity and Environment Influence

Advances in auditory display research

Application of Convolutional Neural Network for Decoding of 12-Lead Electrocardiogram from a Frequency-Modulated Audio Stream (Sonified ECG)

Contact Info

Product

Resources

About