JJJunyu Ji

Junyu Ji

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Junyu Ji has a total of 30 co-authors. Here are the top co-authors by number of shared publications:

  • Guanglin Li

    Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

    3 shared publications
  • Poly Z. H. Sun

    Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention, Department of Artificial Intelligence and Human Factors Engineering, School of Psychology and Cognitive Science, East China Normal University, Shanghai, China

    3 shared publications
  • Shixiong Chen

    School of Medicine, The Chinese University of Hong Kong, Shenzhen, China

    3 shared publications
  • Xin Wang

    Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

    3 shared publications
  • Haoshi Zhang

    Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

    2 shared publications
  • Hongguang Pan

    2 shared publications

Latest Publications

  • Enhancing Auditory Brainstem Response Extraction From Noised EEG With Adaptive Kalman Denoising Technique

    by Xin Wang, Junyu Ji, Haoshi Zhang, Xiaobei Jing, Xu Yong, Yangjie Xu, Hongguan Pan, Yuan Tao, Mingxing Zhu, Michael Chi Fai Tong, et al.

    Auditory brainstem response (ABR) is a weak evoked EEG signal that provides an objective measure for assessing auditory function. However, the traditional extraction method, namely, averaging is noise-sensitive and needs thousands of trials, which places high demands on the subjects and the experimental environment. Kalman weighted (KW) technique has the potential to extract ABR with high quality but relies heavily on expert experience for precise parameter tuning. In this article, an adaptive Kalman denoising technique, which can adaptively adjust the parameter, was developed. A comprehensive investigation was carried out on different noise types (pink noise/Gaussian white noise/uniform noise), proportions (20%/40%/60%/80%/100%), amplitudes (20/40/60/80 μV), and integrated manners (early-noised/intermittent-noised/late-noised). Multiple metrics, such as Pearson correlation coefficient, root mean square error, latency and amplitude of characteristics wave, and the wave recognition rate were calculated for evaluation. The simulation results showed that the proposed method outperformed the averaging and KW techniques over these evaluation metrics. Also, these evaluation metrics of the proposed method were much more stable than those of averaging the KW. Finally, we verified the proposed method in the real scenario. It is believed that the proposed method opens a window for daily ABR-based auditory health condition screening, which can benefit the early detection and diagnosis of auditory diseases.

  • Multi-scale fusion networks with enhanced attention mechanisms for auditory attention decoding from EEG

    by Ke Zhang, Shang Yan, Zenan Li, Xin Wang, Junyu Ji, Alice Kwai-Yee Siu, Yun Lu, Hua-Nong Ting, Song Cao, Hongguang Pan, et al.


  • Open Access

    ABR-Attention: An Attention-Based Model for Precisely Localizing Auditory Brainstem Response

    by Junyu Ji, Xin Wang, Xiaobei Jing, Mingxing Zhu, Hongguang Pan, Desheng Jia, Chunrui Zhao, Xu Yong, Yangjie Xu, Guoru Zhao, et al.

    Auditory Brainstem Response (ABR) is an evoked potential in the brainstem’s neural centers in response to sound stimuli. Clinically, characteristic waves, especially Wave V latency, extracted from ABR can objectively indicate auditory loss and diagnose diseases. Several methods have been developed for the extraction of characteristic waves. To ensure the effectiveness of the method, most of the methods are time-consuming and rely on the heavy workloads of clinicians. To reduce the workload of clinicians, automated extraction methods have been developed. However, the above methods also have limitations. This study introduces a novel deep learning network for automatic extraction of Wave V latency, named ABR-Attention. ABR-Attention model includes a self-attention module, first and second-derivative attention module, and regressor module. Experiments are conducted on the accuracy with 10-fold cross-validation, the effects on different sound pressure levels (SPLs), the effects of different error scales and the effects of ablation. ABR-Attention shows efficacy in extracting Wave V latency of ABR, with an overall accuracy of 96.76±0.41% and an error scale of 0.1ms, and provides a new solution for objective localization of ABR characteristic waves.


  • High-Quality Auditory Brainstem Response Acquisition in Motion via Adaptive Kalman Filtering

    by Xin Wang, Haoshi Zhang, Jingqian Tan, Yangjie Xu, Poly Z. H. Sun, Junyu Ji, Jiafa Lu, Mingxing Zhu, Michael Chi Fai Tong, Subhas Chandra Mukhopadhyay, et al.

    Auditory brainstem response (ABR) is a clinical auditory detection tool that can evaluate the function of the central auditory pathways through the brainstem, but is easy to be interfered with by noise, which requires subjects to keep quiet during tests. However, it is hard for children or adults that cannot cooperate to keep quiet for such a long time. Besides, the ABR test is time-consuming because thousands of trials are needed. In this study, an adaptive Kalman filtering (AKF) method was proposed to help with the ABR acquisition in the motion (chewing or mouth open). We first studied the feasibility of the AKF method by manually adding noise to electroencephalogram (EEG) trials that were used to acquire ABR on adult subjects. Then, we compared the performance of AKF with the traditionally used averaging (Ave) and artifact rejection (AR). The results showed that the AKF-based ABR achieved 96.16 ± 2.15% of the correlation coefficient and similar morphology as the Ave-based method in rest. In motion, the AKF-based ABRs had more recognizable characteristic waves, stable latencies, and higher wave V’s amplitudes than those of Ave or AR-based methods. It is believed that the AKF-based method provides the possibility of in-motion ABR acquisition.