Cancelable HD-sEMG-Based Biometrics for Cross-Application Discrepant Personal Identification

Abstract

With the soaring development of body sensor network (BSN)-based health informatics, information security in such medical devices has attracted increasing attention in recent years. Employing the biosignals acquired directly by the BSN as biometrics for personal identification is an effective approach. Noncancelability and cross-application invariance are two natural flaws of most traditional biometric modalities. Once the biometric template is exposed, it is compromised forever. Even worse, because the same biometrics may be employed as tokens for different accounts in multiple applications, the exposed template can be used to compromise other accounts. In this work, we propose a cancelable and cross-application discrepant biometric approach based on high-density surface electromyogram (HD-sEMG) for personal identification. We enrolled two accounts for each user. HD-sEMG signals from the right dorsal hand under isometric contractions of different finger muscles were employed as biometrics tokens. Since isometric contraction, in contrast to dynamic contraction, requires no actual movement, the users' choice to login to different accounts is greatly protected against impostors. We realized a promising identification accuracy of 85.76% for 44 identities (22 subjects × 2 accounts) with training and testing data acquired 9 days apart. The high identification accuracy of different accounts for the same user demonstrates the promising cancelability and cross-application discrepancy of the proposed HD-sEMG-based biometrics. To the best of our knowledge, this is the first study to employ HD-sEMG in personal identification applications.

Score, Rank, and Decision-Level Fusion Strategies of Multicode Electromyogram-Based Verification and Identification Biometrics

“…A different verification study allowed users to choose 30 three out of four gestures as their authentication code [19]. An 31 identification study with a similar setup as in [16] presented 32 sEMG biometrics as a variant across multiple codelengths [20].…”

“…1(B)); authentication information from different codes or gestures can be integrated or fused at different levels of the processing pipeline. As mentioned earlier, the previous multicode sEMG studies used signals and features from all sequences that correspond to the sensor-and feature-level fusion [16,19,20]. As these fusion strategies limit the code-customization flexibility of authentication systems, they are not considered in this study.…”

Transcending Conventional Biometry Frontiers: Diffusive Dynamics PPG Biometry

“…In recent decades, the preliminary diagnostic examination of an individual’s state of health and its follow-up has been entrusted on many occasions to clinical analysis, through non-invasive methods, of the biological signals generated by the human body—more recently, with body sensor networks (BSN) and thanks to the rapid development of health informatics [ 9 , 10 ]. Among the different biological signals usually measured today, one particularly deserves special consideration, the photoplethysmographic (PPG) signal [ 11 , 12 ].…”

“…However, in this century, particular attention must be paid to the use of biological signals such as biometric markers, in addition to morphological and behavioral characteristics. In this regard, it is worth highlighting biometrics studies involving the analysis of electrocardiographic (ECG) and encephalographic (EEG) signals [ 36 ], to which could be added biometric applications that obtain biological signals from galvanic response of skin (GSR), electromyogram (EMG) [ 10 ], electrooculography (EOG), and mechanomyogram (MMG), among others [ 37 ].…”

Enhancing IoT Security via Cancelable HD-sEMG-Based Biometric Authentication Password, Encoded by Gesture

“…Accordingly, employing sEMG signals acquired directly by such wearable WBAN devices in IoT applications for user authentication is an efficient approach. Our previous work [9], for the first time, employed HD-sEMG as a biometric token, and proved the excellent cancelability of HD-sEMG signals [10], [11]. HD-sEMG signals acquired from the right dorsal side of the hand during isometric contractions of muscles corresponding to a specific finger and finger combinations, were used as biometric tokens.…”