More Like this

1. Deep Learning-based User Authentication with Surface EMG Images of Hand Gestures

   https://doi.org/10.1109/EMBC46164.2021.9630312  

   Li, Qingqing; Luo, Zhirui; Zheng, Jun (November 2021, Pu2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC))

   User authentication is an important security mechanism to prevent unauthorized accesses to systems or devices. In this paper, we propose a new user authentication method based on surface electromyogram (sEMG) images of hand gestures and deep anomaly detection. Multi-channel sEMG signals acquired during the user performing a hand gesture are converted into sEMG images which are used as the input of a deep anomaly detection model to classify the user as client or imposter. The performance of different sEMG image generation methods in three authentication test scenarios are investigated by using a public hand gesture sEMG dataset. Our experimental results demonstrate the viability of the proposed method for user authentication. 

   more » « less
2. Volitional Contractility Assessment of Plantar Flexors by Using Non-invasive Neuromuscular Measurements

   https://doi.org/10.1109/BioRob49111.2020.9224298  

   Zhang, Qiang; Iyer, Ashwin; Kim, Kang; Sharma, Nitin (November 2020, 2020 8th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob))

   null (Ed.)

   This paper investigates an ultrasound (US) imaging-based methodology to assess the contraction levels of plantar flexors quantitatively. Echogenicity derived from US imaging at different anatomical depths, including both lateral gastrocnemius (LGS) and soleus (SOL) muscles, is used for the prediction of the volitional isometric plantar flexion moment. Synchronous measurements, including a plantar flexion torque signal, a surface electromyography (sEMG) signal, and US imaging of both LGS and SOL muscles, are collected. Four feature sets, including sole sEMG, sole LGS echogenicity, sole SOL echogenicity, and their fusion, are used to train a Gaussian process regression (GPR) model and predict plantar flexion torque. The experimental results on four non-disabled participants show that the torque prediction accuracy is improved significantly by using the LGS or SOL echogenicity signal than using the sEMG signal. However, there is no significant improvement by using the fused feature compared to sole LGS or SOL echogenicity. The findings imply that using US imaging-derived signals improves the accuracy of predicting volitional effort on human plantar flexors. Potentially, US imaging can be used as a new sensing modality to measure or predict human lower limb motion intent in clinical rehabilitation devices. 

   more » « less
3. Enhancing the Security of Pattern Unlock with Surface EMG-Based Biometrics

   https://doi.org/10.3390/app10020541  

   Li, Qingqing; Dong, Penghui; Zheng, Jun (January 2020, Applied Sciences)

   Pattern unlock is a popular screen unlock scheme that protects the sensitive data and information stored in mobile devices from unauthorized access. However, it is also susceptible to various attacks, including guessing attacks, shoulder surfing attacks, smudge attacks, and side-channel attacks, which can achieve a high success rate in breaking the patterns. In this paper, we propose a new two-factor screen unlock scheme that incorporates surface electromyography (sEMG)-based biometrics with patterns for user authentication. sEMG signals are unique biometric traits suitable for person identification, which can greatly improve the security of pattern unlock. During a screen unlock session, sEMG signals are recorded when the user draws the pattern on the device screen. Time-domain features extracted from the recorded sEMG signals are then used as the input of a one-class classifier to identify the user is legitimate or not. We conducted an experiment involving 10 subjects to test the effectiveness of the proposed scheme. It is shown that the adopted time-domain sEMG features and one-class classifiers achieve good authentication performance in terms of the F 1 score and Half of Total Error Rate (HTER). The results demonstrate that the proposed scheme is a promising solution to enhance the security of pattern unlock. 

   more » « less
4. Assessing Wound Roll Quality using Measured Stiffness and Models

   Markum, R.; Good, J.K. (June 2019, Proceedings of the Fifteenth International Conference on Web Handling)

   For those concerned with roll quality it is difficult to suppress the urge to compress the outer surface of a wound roll with your thumb to sense how tightly the roll was wound and how large the internal pressures might be. If several rolls of a given web are wound at unique tensions a human could often arrange these rolls in order of ascending winding tension using their thumb test. The thumb senses the relative conforming deformation of the roll surface. A soft roll would deform more and have greater contact area with our thumb than a hard roll for a given load. The thumb test is most useful on softer rolls wound from nonwovens, tissues, some grades of paper and polymer films but less so on metal coils that deform little in comparison to our thumb. The physics define stiffness as the extent to which an object resists deformation in response to an applied force. This publication reports the results of research where the stiffness of the outer surface of a wound roll is used to characterize the internal residual stresses throughout the roll due to winding. Measurements of stiffness of the outer surface of wound rolls will be demonstrated using commercially available devices along with a proposed handheld device all having greater resolution than the thumb. These measurements will be coupled with models to allow the exploration of internal residual stresses in the wound roll that can be used to investigate winding defects and roll quality. 

   more » « less
5. Privacy-Preserving Motor Intent Classification via Feature Disentanglement

   Jiahao Fan, Xiaogang Hu (April 2023, 11th International IEEE EMBS Conference on Neural Engineering)

   Recent studies have revealed that sensitive and private attributes could be decoded from sEMG signals, which incurs significant privacy threats to the users of sEMG applications. Most researches so far focus on improving the accuracy and reliability of sEMG models, but much less attention has been paid to their privacy. To fill this gap, this paper implemented and evaluated a framework to optimize the sEMG-based data-sharing mechanism. Our primary goal is to remove sensitive attributes in the sEMG features before sharing them with primary tasks while maintaining the data utility. We disentangled the identity-invariant task-relevant representations from original sEMG features. We shared it with the downstream pattern recognition tasks to reduce the chance of sensitive attributes being inferred by potential attackers. The proposed method was evaluated on data from twenty subjects, with training and testing data acquired 3-25 days apart. Experimental results show that the disentangled representations significantly lower the success rate of identity inference attacks compared to the original feature and its sparse representations generated by the state-of-the-art feature projection methods. Furthermore, the utility of the disentangled representation is also evaluated in hand gesture recognition tasks, showing superior performance over other methods. This work shows that disentangled representations of sEMG signals are a promising solution for privacy-reserving applications. 

   more » « less