Yujiao Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yujiao Lu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Shuo Gao
Beihang University
3 shared publications - Lijun Xu
Beihang University
2 shared publications - Ziang Cui
School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China
2 shared publications - Chenyu Tang
University of Cambridge
1 shared publication - Fuqiang Zhou
Beihang University
1 shared publication Hejian Liu
School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 11 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (20) , 24070-24077
Piezoelectric and Machine Learning Based Keystroke Dynamics for Highly Secure User Authentication
Cyber security is of significance in today’s e-commerce applications. In this article, we present a piezoelectric touch sensing supported keystroke dynamics based identity authentication technique, for providing a secure access manner to smartphones. Here, the polyvinylidene fluoride (PVDF) based piezoelectric touch panel can learn detailed force touch habits of users. With a support vector machine (SVM) algorithm, our proposed frequency domain features experimentally demonstrate a better authentication accuracy of 98.3%, compared to the traditional time domain features. The work showcases a feasible method of combining functional materials and artificial intelligence (AI) for satisfying highly secure requirements.
- 11 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (20) , 24070-24077
Piezoelectric and Machine Learning Based Keystroke Dynamics for Highly Secure User Authentication
Cyber security is of significance in today’s e-commerce applications. In this article, we present a piezoelectric touch sensing supported keystroke dynamics based identity authentication technique, for providing a secure access manner to smartphones. Here, the polyvinylidene fluoride (PVDF) based piezoelectric touch panel can learn detailed force touch habits of users. With a support vector machine (SVM) algorithm, our proposed frequency domain features experimentally demonstrate a better authentication accuracy of 98.3%, compared to the traditional time domain features. The work showcases a feasible method of combining functional materials and artificial intelligence (AI) for satisfying highly secure requirements.
- 10 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (23) , 26373-26381
A Machine-Learning-Based Touch Orientation Detection Method for Piezoelectric Touch Sensing in Noisy Environment
Touch orientation detection is important for piezoelectric touch panels to stabilize force-voltage responsivities. Current touch orientation estimation techniques utilize machine learning algorithms for orientation classification. However, environmental noise could weaken the data quality which will result in a lowered detection accuracy. To address this issue, in this article, we present a noise robustness technique, in which different levels of noise data are injected into the training data. The performance of “dirty” data trained model exhibits a good performance (average mean absolute error (MAE) of 7.8 degrees) among signal-to-noise ratio (SNR) from 3 dB to 40 dB, indicating that an improved user experience can be obtained.
- 10 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (23) , 26373-26381
A Machine-Learning-Based Touch Orientation Detection Method for Piezoelectric Touch Sensing in Noisy Environment
Touch orientation detection is important for piezoelectric touch panels to stabilize force-voltage responsivities. Current touch orientation estimation techniques utilize machine learning algorithms for orientation classification. However, environmental noise could weaken the data quality which will result in a lowered detection accuracy. To address this issue, in this article, we present a noise robustness technique, in which different levels of noise data are injected into the training data. The performance of “dirty” data trained model exhibits a good performance (average mean absolute error (MAE) of 7.8 degrees) among signal-to-noise ratio (SNR) from 3 dB to 40 dB, indicating that an improved user experience can be obtained.
- 10 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (23) , 26311-26319
Flexible and Wearable EMG and PSD Sensors Enabled Locomotion Mode Recognition for IoHT-Based In-Home Rehabilitation
Benefiting from the development of the Internet of Healthcare Things (IoHT) in recent years, locomotion mode recognition using wearable sensors plays a more and more important role in the field of in-home rehabilitation. In this paper, a smart sensing system utilizing flexible electromyography (EMG) sensors and a forty-eight-channel plantar stress distribution sensor for locomotion mode recognition is presented, together with its use under the IoHT architecture. EMG and plantar stress distribution (PSD) information from ten healthy subjects in five common locomotion modes in daily life were collected, analyzed, and then transmitted to remote end terminals (e.g., personal computers). The data analysis process was implemented with machine learning techniques, through which the locomotion modes were determined with a high accuracy of 96.53%. This article demonstrates a feasible means for accurate locomotion mode recognition by combining wearable sensing techniques and the machine learning algorithm, potentially advancing the development for IoHT based in-home rehabilitation.
- 10 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (23) , 26311-26319
Flexible and Wearable EMG and PSD Sensors Enabled Locomotion Mode Recognition for IoHT-Based In-Home Rehabilitation
Benefiting from the development of the Internet of Healthcare Things (IoHT) in recent years, locomotion mode recognition using wearable sensors plays a more and more important role in the field of in-home rehabilitation. In this paper, a smart sensing system utilizing flexible electromyography (EMG) sensors and a forty-eight-channel plantar stress distribution sensor for locomotion mode recognition is presented, together with its use under the IoHT architecture. EMG and plantar stress distribution (PSD) information from ten healthy subjects in five common locomotion modes in daily life were collected, analyzed, and then transmitted to remote end terminals (e.g., personal computers). The data analysis process was implemented with machine learning techniques, through which the locomotion modes were determined with a high accuracy of 96.53%. This article demonstrates a feasible means for accurate locomotion mode recognition by combining wearable sensing techniques and the machine learning algorithm, potentially advancing the development for IoHT based in-home rehabilitation.