scholarly journals PulseEdit: Editing Physiological Signal in Facial Videos for Privacy Protection

2021 ◽  
Author(s):  
Mingliang Chen ◽  
Xin Liao ◽  
Min Wu
Keyword(s):  
Physiological Signals ◽  
Physiological Status ◽  
Ambient Light ◽  
Rate Measurement ◽  
Visual Appearance ◽  
Physiological Signal ◽  
Remote Photoplethysmography ◽  
Human Faces ◽  
Privacy Issues ◽  
Visual Security

Recent studies have shown that physiological signals can be remotely captured from human faces using a portable color camera under ambient light. This technology, namely remote photoplethysmography (rPPG), can be used to collect users' physiological status who are sitting in front of a camera, which may raise physiological privacy issues. To avoid the privacy abuse of the rPPG technology, this paper develops PulseEdit, a novel and efficient algorithm that can edit the physiological signals in facial videos without affecting visual appearance to protect the user's physiological signal from disclosure. PulseEdit can either remove the trace of the physiological signal in a video or transform the video to contain a target physiological signal chosen by a user. Experimental results show that PulseEdit can effectively edit physiological signals in facial videos and prevent heart rate measurement based on rPPG. It is possible to utilize PulseEdit in adversarial scenarios against some rPPG-based visual security algorithms. We present analyses on the performance of PulseEdit against rPPG-based liveness detection and rPPG-based deepfake detection, and demonstrate its ability to circumvent these visual security algorithms.

scholarly journals PulseEdit: Editing Physiological Signal in Facial Videos for Privacy Protection

2021 ◽  
Author(s):  
Mingliang Chen ◽  
Xin Liao ◽  
Min Wu
Keyword(s):  
Physiological Signals ◽  
Physiological Status ◽  
Ambient Light ◽  
Rate Measurement ◽  
Visual Appearance ◽  
Physiological Signal ◽  
Remote Photoplethysmography ◽  
Human Faces ◽  
Privacy Issues ◽  
Visual Security

Recent studies have shown that physiological signals can be remotely captured from human faces using a portable color camera under ambient light. This technology, namely remote photoplethysmography (rPPG), can be used to collect users' physiological status who are sitting in front of a camera, which may raise physiological privacy issues. To avoid the privacy abuse of the rPPG technology, this paper develops PulseEdit, a novel and efficient algorithm that can edit the physiological signals in facial videos without affecting visual appearance to protect the user's physiological signal from disclosure. PulseEdit can either remove the trace of the physiological signal in a video or transform the video to contain a target physiological signal chosen by a user. Experimental results show that PulseEdit can effectively edit physiological signals in facial videos and prevent heart rate measurement based on rPPG. It is possible to utilize PulseEdit in adversarial scenarios against some rPPG-based visual security algorithms. We present analyses on the performance of PulseEdit against rPPG-based liveness detection and rPPG-based deepfake detection, and demonstrate its ability to circumvent these visual security algorithms.

scholarly journals PulseEdit: Editing Physiological Signal in Facial Videos for Privacy Protection

2021 ◽  
Author(s):  
Mingliang Chen ◽  
Xin Liao ◽  
Min Wu
Keyword(s):  
Physiological Signals ◽  
Physiological Status ◽  
Ambient Light ◽  
Rate Measurement ◽  
Visual Appearance ◽  
Physiological Signal ◽  
Remote Photoplethysmography ◽  
Human Faces ◽  
Privacy Issues ◽  
Visual Security

Recent studies have shown that physiological signals can be remotely captured from human faces using a portable color camera under ambient light. This technology, namely remote photoplethysmography (rPPG), can be used to collect users' physiological status who are sitting in front of a camera, which may raise physiological privacy issues. To avoid the privacy abuse of the rPPG technology, this paper develops PulseEdit, a novel and efficient algorithm that can edit the physiological signals in facial videos without affecting visual appearance to protect the user's physiological signal from disclosure. PulseEdit can either remove the trace of the physiological signal in a video or transform the video to contain a target physiological signal chosen by a user. Experimental results show that PulseEdit can effectively edit physiological signals in facial videos and prevent heart rate measurement based on rPPG. It is possible to utilize PulseEdit in adversarial scenarios against some rPPG-based visual security algorithms. We present analyses on the performance of PulseEdit against rPPG-based liveness detection and rPPG-based deepfake detection, and demonstrate its ability to circumvent these visual security algorithms.

scholarly journals PulseEdit: Editing Physiological Signal in Facial Videos for Privacy Protection

2021 ◽  
Author(s):  
Mingliang Chen ◽  
Xin Liao ◽  
Min Wu
Keyword(s):  
Physiological Signals ◽  
Physiological Status ◽  
Ambient Light ◽  
Rate Measurement ◽  
Visual Appearance ◽  
Physiological Signal ◽  
Remote Photoplethysmography ◽  
Human Faces ◽  
Privacy Issues ◽  
Visual Security

Recent studies have shown that physiological signals can be remotely captured from human faces using a portable color camera under ambient light. This technology, namely remote photoplethysmography (rPPG), can be used to collect users' physiological status who are sitting in front of a camera, which may raise physiological privacy issues. To avoid the privacy abuse of the rPPG technology, this paper develops PulseEdit, a novel and efficient algorithm that can edit the physiological signals in facial videos without affecting visual appearance to protect the user's physiological signal from disclosure. PulseEdit can either remove the trace of the physiological signal in a video or transform the video to contain a target physiological signal chosen by a user. Experimental results show that PulseEdit can effectively edit physiological signals in facial videos and prevent heart rate measurement based on rPPG. It is possible to utilize PulseEdit in adversarial scenarios against some rPPG-based visual security algorithms. We present analyses on the performance of PulseEdit against rPPG-based liveness detection and rPPG-based deepfake detection, and demonstrate its ability to circumvent these visual security algorithms.

PulseEdit: Editing Physiological Signal in Facial Videos for Privacy Protection

2021 ◽  
Author(s):  
Mingliang Chen ◽  
Xin Liao ◽  
Min Wu
Keyword(s):  
Physiological Signals ◽  
Physiological Status ◽  
Ambient Light ◽  
Rate Measurement ◽  
Visual Appearance ◽  
Physiological Signal ◽  
Remote Photoplethysmography ◽  
Human Faces ◽  
Privacy Issues ◽  
Visual Security

Recent studies have shown that physiological signals can be remotely captured from human faces using a portable color camera under ambient light. This technology, namely remote photoplethysmography (rPPG), can be used to collect users' physiological status who are sitting in front of a camera, which may raise physiological privacy issues. To avoid the privacy abuse of the rPPG technology, this paper develops PulseEdit, a novel and efficient algorithm that can edit the physiological signals in facial videos without affecting visual appearance to protect the user's physiological signal from disclosure. PulseEdit can either remove the trace of the physiological signal in a video or transform the video to contain a target physiological signal chosen by a user. Experimental results show that PulseEdit can effectively edit physiological signals in facial videos and prevent heart rate measurement based on rPPG. It is possible to utilize PulseEdit in adversarial scenarios against some rPPG-based visual security algorithms. We present analyses on the performance of PulseEdit against rPPG-based liveness detection and rPPG-based deepfake detection, and demonstrate its ability to circumvent these visual security algorithms.

Kansei’s Physiological Measurement and Its Application (2)

2010 ◽  
pp. 319-329 ◽  
Author(s):  
Santoso Handri ◽  
Shusaku Nomura
Keyword(s):  
Beating Heart ◽  
Physiological Signals ◽  
Kansei Engineering ◽  
Internal Organs ◽  
Physiological Measurement ◽  
New Approach ◽  
Engineering Research ◽  
Physiological Signal ◽  
Research Fields ◽  
Metabolic Activities

Physiological signals or biosignals are electrical, chemical, or mechanical signals that created by biological events such as a beating heart or a contracting muscle producing signals that can be measured and analyzed. These signals are generated from the metabolic activities of human internal organs. Therefore, in certain conditions, physiological signals have different pattern between healthy and unhealthy individuals. Based on this information, generally, physicians take some action and treat their patients. However, utilizing physiological signals is a new approach in Kansei engineering research fields for coping with human sensitivity. This study focuses on the possibility of physiological signal application in Kansei engineering.

scholarly journals Detection of Physiological Signals Based on Graphene Using a Simple and Low-Cost Method

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1656 ◽  
Author(s):  
Liping Xie ◽  
Xingyu Zi ◽  
Qingshi Meng ◽  
Zhiwen Liu ◽  
Lisheng Xu
Keyword(s):  
Graphene Sheet ◽  
Pulse Wave ◽  
Low Cost ◽  
Wearable Sensors ◽  
Unmet Need ◽  
Expansion Method ◽  
Physiological Signals ◽  
Physiological Signal ◽  
Solid Foundation ◽  
Processing Circuit

Despite that graphene has been extensively used in flexible wearable sensors, it remains an unmet need to fabricate a graphene-based sensor by a simple and low-cost method. Here, graphene nanoplatelets (GNPs) are prepared by thermal expansion method, and a sensor is fabricated by sealing of a graphene sheet with polyurethane (PU) medical film. Compared with other graphene-based sensors, it greatly simplifies the fabrication process and enables the effective measurement of signals. The resistance of graphene sheet changes linearly with the deformation of the graphene sensor, which lays a solid foundation for the detection of physiological signals. A signal processing circuit is developed to output the physiological signals in the form of electrical signals. The sensor was used to measure finger bending motion signals, respiration signals and pulse wave signals. All the results demonstrate that the graphene sensor fabricated by the simple and low-cost method is a promising platform for physiological signal measurement.

scholarly journals Design of User-Customized Negative Emotion Classifier Based on Feature Selection Using Physiological Signal Sensors

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4253 ◽  
Author(s):  
JeeEun Lee ◽  
Sun K. Yoo
Keyword(s):  
Feature Selection ◽  
Negative Emotion ◽  
Electrodermal Activity ◽  
Cognitive Status ◽  
Physiological Signals ◽  
Self Assessment ◽  
Physiological Signal ◽  
Distribution Shape ◽  
The Difference ◽  
The Individual

First, the Likert scale and self-assessment manikin are used to provide emotion analogies, but they have limits for reflecting subjective factors. To solve this problem, we use physiological signals that show objective responses from cognitive status. The physiological signals used are electrocardiogram, skin temperature, and electrodermal activity (EDA). Second, the degree of emotion felt, and the related physiological signals, vary according to the individual. KLD calculates the difference in probability distribution shape patterns between two classes. Therefore, it is possible to analyze the relationship between physiological signals and emotion. As the result, features from EDA are important for distinguishing negative emotion in all subjects. In addition, the proposed feature selection algorithm showed an average accuracy of 92.5% and made it possible to improve the accuracy of negative emotion recognition.

Linear and Nonlinear Approaches to the Analysis of R-R Interval Variability

2004 ◽  
Vol 5 (3) ◽  
pp. 211-221 ◽  
Author(s):  
Autumn Schumacher
Keyword(s):  
Signal Analysis ◽  
Interval Data ◽  
Isolated Rat Heart ◽  
Physiological Signals ◽  
Physiological Data ◽  
Analysis Techniques ◽  
Physiological Signal ◽  
Quantification Analysis ◽  
Linear And Nonlinear ◽  
Signal Variability

Analysis techniques derived from linear and non-linear dynamics systems theory qualify and quantify physiological signal variability. Both clinicians and researchers use physiological signals in their scopes of practice. The clinician monitors patients with signal-analysis technology, and the researcher analyzes physiological data with signal-analysis techniques. Understanding the theoretical basis for analyzing physiological signals within one’s scope of practice ensures proper interpretation of the relationship between physiological function and signal variability. This article explains the concepts of linear and nonlinear signal analysis and illustrates these concepts with descriptions of power spectrum analysis and recurrence quantification analysis. This article also briefly describes the relevance of these 2 techniques to R-to-R wave interval (i.e., heart rate variability) signal analysis and demonstrates their application to R-to-R wave interval data obtained from an isolated rat heart model.

scholarly journals Evaluating physiological signal salience for estimating metabolic energy cost from wearable sensors

2019 ◽  
Vol 126 (3) ◽  
pp. 717-729 ◽  
Author(s):  
Kimberly A. Ingraham ◽  
Daniel P. Ferris ◽  
C. David Remy
Keyword(s):  
Heart Rate ◽  
Steady State ◽  
Indirect Calorimetry ◽  
Energy Cost ◽  
Electrodermal Activity ◽  
Wearable Sensors ◽  
Metabolic Energy ◽  
Physiological Signals ◽  
Physiological Signal ◽  
Signal Salience

Body-in-the-loop optimization algorithms have the capability to automatically tune the parameters of robotic prostheses and exoskeletons to minimize the metabolic energy expenditure of the user. However, current body-in-the-loop algorithms rely on indirect calorimetry to obtain measurements of energy cost, which are noisy, sparsely sampled, time-delayed, and require wearing a respiratory mask. To improve these algorithms, the goal of this work is to predict a user’s steady-state energy cost quickly and accurately using physiological signals obtained from portable, wearable sensors. In this paper, we quantified physiological signal salience to discover which signals, or groups of signals, have the best predictive capability when estimating metabolic energy cost. We collected data from 10 healthy individuals performing 6 activities (walking, incline walking, backward walking, running, cycling, and stair climbing) at various speeds or intensities. Subjects wore a suite of physiological sensors that measured breath frequency and volume, limb accelerations, lower limb EMG, heart rate, electrodermal activity, skin temperature, and oxygen saturation; indirect calorimetry was used to establish the ‘ground truth’ energy cost for each activity. Evaluating Pearson’s correlation coefficients and single and multiple linear regression models with cross validation (leave-one- subject-out and leave-one- task-out), we found that 1) filtering the accelerations and EMG signals improved their predictive power, 2) global signals (e.g., heart rate, electrodermal activity) were more sensitive to unknown subjects than tasks, while local signals (e.g., accelerations) were more sensitive to unknown tasks than subjects, and 3) good predictive performance was obtained combining a small number of signals (4–5) from multiple sensor modalities. NEW & NOTEWORTHY In this paper, we systematically compare a large set of physiological signals collected from portable sensors and determine which sensor signals contain the most salient information for predicting steady-state metabolic energy cost, robust to unknown subjects or tasks. This information, together with the comprehensive data set that is published in conjunction with this paper, will enable researchers and clinicians across many fields to develop novel algorithms to predict energy cost from wearable sensors.

Sign in / Sign up

Export Citation Format

Share Document