Haitao Yu
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
Research Subjects
Haitao Yu has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Jiang Wang
School of Electrical and Information Engineering, Tianjin University
16 shared publications Jiang Wang
8 shared publications- Chen Liu
School of Electrical and Information Engineering, Tianjin Key Laboratory of Process Measurement and Control, Tianjin University, Tianjin, China
7 shared publications - Bin Deng
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
6 shared publications Kai Li
School of Electrical and Information Engineering, Tianjin University, Tianjin, China
6 shared publicationsJing Liu
5 shared publications
Latest Publications
- Top Cited Papers
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (3) , 2694-2707
Spatiospectral Representation and Neural Decoding of Somatic Perception of Acupuncture Stimulations
Characterizing the neural representations underlying somatic perception is crucial for neural decoding of external stimulations. Acupuncture is an important therapeutic method of traditional Chinese medicine and can effectively modulate brain activity for the treatment of neural diseases. In this work, we investigate the neural representations based on the power spectral density (PSD) estimated from electroencephalogram (EEG) across the whole brain with deep learning. Frequency and spatial characteristics of PSD can reliably represent the dynamical brain responses to acupuncture with different manipulations, manifesting enhanced alpha power in parietal lobe. By removing aperiodic components, periodic spatial spectrum shows a higher representation ability of different brain states during acupuncture stimulations, and twiring-rotating (TR) manipulation have a more pronounced modulatory effect than lifting-thrusting (LT) manipulation. Moreover, we further infer the low-dimensional feature-disentangled representations with generative adversarial network (GAN), i.e., w-latents of StyleGAN, which can capture the latent features of periodic spatial spectrum and strike a balance between separability and generalizability. The effectiveness of feature-disentangled representations is evaluated by decoding the acupuncture states, which can achieve a highest accuracy of 95.71% with Transformer classifier. Compared with high-dimensional spatial spectrum, low-dimensional latent features can best characterize different brain states, indicating a precise representation of somatic perception of acupuncture stimulations. Taken together, our results highlight the significant role of spatial spectral representation underlying somatic perception and serve as an important benchmark for the evaluation of acupuncture effect on human brain.
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (3) , 2694-2707
Top Cited PapersSpatiospectral Representation and Neural Decoding of Somatic Perception of Acupuncture Stimulations
Characterizing the neural representations underlying somatic perception is crucial for neural decoding of external stimulations. Acupuncture is an important therapeutic method of traditional Chinese medicine and can effectively modulate brain activity for the treatment of neural diseases. In this work, we investigate the neural representations based on the power spectral density (PSD) estimated from electroencephalogram (EEG) across the whole brain with deep learning. Frequency and spatial characteristics of PSD can reliably represent the dynamical brain responses to acupuncture with different manipulations, manifesting enhanced alpha power in parietal lobe. By removing aperiodic components, periodic spatial spectrum shows a higher representation ability of different brain states during acupuncture stimulations, and twiring-rotating (TR) manipulation have a more pronounced modulatory effect than lifting-thrusting (LT) manipulation. Moreover, we further infer the low-dimensional feature-disentangled representations with generative adversarial network (GAN), i.e., w-latents of StyleGAN, which can capture the latent features of periodic spatial spectrum and strike a balance between separability and generalizability. The effectiveness of feature-disentangled representations is evaluated by decoding the acupuncture states, which can achieve a highest accuracy of 95.71% with Transformer classifier. Compared with high-dimensional spatial spectrum, low-dimensional latent features can best characterize different brain states, indicating a precise representation of somatic perception of acupuncture stimulations. Taken together, our results highlight the significant role of spatial spectral representation underlying somatic perception and serve as an important benchmark for the evaluation of acupuncture effect on human brain.
- Top Cited Papers
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (6) , 4147-4160
Neural Manifold Decoder for Acupuncture Stimulations With Representation Learning: An Acupuncture-Brain Interface
Acupuncture stimulations in somatosensory system can modulate spatiotemporal brain activity and improve cognitive functions of patients with neurological disorders. The correlation between these somatosensory stimulations and dynamical brain responses is still unclear. We proposed a deep learning framework using electroencephalographic activity of stimulated subjects to decode the needling processes of various acupuncture manipulations performed on Zusanli acupoint. Contrastive representation learning integrated with domain adaptation strategy was applied to estimate 3D hand postures and hand joint motion trajectories of acupuncturist with video recordings, by which finite dimensional representations of behavior manifolds for needling operations were inferred. Distinct transition dynamics of behavior manifold were observed for acupuncture with lifting-thrusting and twisting-rotating manipulations. Moreover, latent neural manifolds of acupuncture evoked EEG signals were estimated in low dimensional state space of brain activities with unsupervised manifold learning, which can reliably represent acupuncture stimulations. Furthermore, a nonlinear decoder based on neural networks was designed to transform neural manifolds to behavior manifolds and further predict acupuncture manipulation as well as needling process. Experimental results demonstrated a high performance of the proposed decoding framework for four types of acupuncture manipulations with a precision of 92.42%. The EEG decoder provides an acupuncture-brain interface linking somatosensory stimulations with neural representations, an effective scheme for revealing clinical efficacy of acupuncture treatment.
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (6) , 4147-4160
Top Cited PapersNeural Manifold Decoder for Acupuncture Stimulations With Representation Learning: An Acupuncture-Brain Interface
Acupuncture stimulations in somatosensory system can modulate spatiotemporal brain activity and improve cognitive functions of patients with neurological disorders. The correlation between these somatosensory stimulations and dynamical brain responses is still unclear. We proposed a deep learning framework using electroencephalographic activity of stimulated subjects to decode the needling processes of various acupuncture manipulations performed on Zusanli acupoint. Contrastive representation learning integrated with domain adaptation strategy was applied to estimate 3D hand postures and hand joint motion trajectories of acupuncturist with video recordings, by which finite dimensional representations of behavior manifolds for needling operations were inferred. Distinct transition dynamics of behavior manifold were observed for acupuncture with lifting-thrusting and twisting-rotating manipulations. Moreover, latent neural manifolds of acupuncture evoked EEG signals were estimated in low dimensional state space of brain activities with unsupervised manifold learning, which can reliably represent acupuncture stimulations. Furthermore, a nonlinear decoder based on neural networks was designed to transform neural manifolds to behavior manifolds and further predict acupuncture manipulation as well as needling process. Experimental results demonstrated a high performance of the proposed decoding framework for four types of acupuncture manipulations with a precision of 92.42%. The EEG decoder provides an acupuncture-brain interface linking somatosensory stimulations with neural representations, an effective scheme for revealing clinical efficacy of acupuncture treatment.
- Open Access
- 5 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 3993-4003
Spatiotemporal Dynamics of Periodic and Aperiodic Brain Activity Under Peripheral Nerve Stimulation With Acupuncture
Brain activities are a mixture of periodic and aperiodic components, manifesting in the power spectral density (PSD) as rhythmic oscillations with spectral peaks and broadband fluctuations. Periodic oscillatory properties of brain response to external stimulation are widely studied, while aperiodic component responses remain unclear. Here, we investigate spatiotemporal dynamics of periodic and aperiodic brain activity under peripheral nerve stimulation with acupuncture by parameterization of power spectra of EEG signals. Regarding periodic brain activity, spectral peak in delta band emerges in frontal and central brain regions indicates a typical phenomenon of neural entrainment, which is formed by coupling periodic brain activity to external rhythmic acupuncture stimulation. In addition, the statistical results show that alpha periodic power is an important indicator for characterizing the modulatory effects of acupuncture on periodic brain activity. As for aperiodic brain activity, broadband EEG spectral trend analysis demonstrates a steeper aperiodic slope in left parietal lobe and a stronger negative correlation with the aperiodic offset under acupuncture compared with resting state, with the absolute value of correlation coefficient increasing from 0.27 to 0.50. Based on the two parameters that can best characterize the acupuncture effect, alpha periodic power and aperiodic slope, the accurate decoding of acupuncture manipulation is realized with AUC = 0.87. This work shows the modulatory effect of peripheral nerve stimulation with acupuncture on the brain activity by characterizing the periodic and aperiodic spectrum features of EEG, providing new insights into the comprehensive understanding of the response processes of human brain to acupuncture stimulation.
- 5 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 3993-4003
Open AccessSpatiotemporal Dynamics of Periodic and Aperiodic Brain Activity Under Peripheral Nerve Stimulation With Acupuncture
Brain activities are a mixture of periodic and aperiodic components, manifesting in the power spectral density (PSD) as rhythmic oscillations with spectral peaks and broadband fluctuations. Periodic oscillatory properties of brain response to external stimulation are widely studied, while aperiodic component responses remain unclear. Here, we investigate spatiotemporal dynamics of periodic and aperiodic brain activity under peripheral nerve stimulation with acupuncture by parameterization of power spectra of EEG signals. Regarding periodic brain activity, spectral peak in delta band emerges in frontal and central brain regions indicates a typical phenomenon of neural entrainment, which is formed by coupling periodic brain activity to external rhythmic acupuncture stimulation. In addition, the statistical results show that alpha periodic power is an important indicator for characterizing the modulatory effects of acupuncture on periodic brain activity. As for aperiodic brain activity, broadband EEG spectral trend analysis demonstrates a steeper aperiodic slope in left parietal lobe and a stronger negative correlation with the aperiodic offset under acupuncture compared with resting state, with the absolute value of correlation coefficient increasing from 0.27 to 0.50. Based on the two parameters that can best characterize the acupuncture effect, alpha periodic power and aperiodic slope, the accurate decoding of acupuncture manipulation is realized with AUC = 0.87. This work shows the modulatory effect of peripheral nerve stimulation with acupuncture on the brain activity by characterizing the periodic and aperiodic spectrum features of EEG, providing new insights into the comprehensive understanding of the response processes of human brain to acupuncture stimulation.
- Top Cited PapersOpen Access
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 2450-2459
Evaluation of Acupuncture Efficacy in Modulating Brain Activity With Periodic-Aperiodic EEG Measurements
Acupuncture is an important therapeutic method of traditional Chinese medicine and can effectively modulate brain disorders. The therapeutic efficacy of acupuncture is hard to evaluate due to lacking of effective measurements of brain activity. In this work, we design an EEG-based monitoring system to evaluate therapeutic effect of acupuncture on human brain by extracting periodic-aperiodic features. Power spectral density is estimated to compute the adjusted power of periodic oscillatory rhythm in EEG under acupuncture stimulation. It is exhibited that the brain activity in alpha band (8–12 Hz) is significantly enhanced during acupuncture, especially in parietal and occipital lobe regions. To probe the modulatory effect of acupuncture on aperiodic brain activity, we calculate the aperiodic exponent based on the parameterization of EEG power spectra. The aperiodic exponent decreases along with acupuncture process, which is more significant in central and frontal lobe regions. Furthermore, sensitivity of different brain regions to acupuncture is assessed by the integration of adjusted power and aperiodic exponent. Experimental results demonstrate the effectiveness of proposed periodic-aperiodic measurements of EEG signals, by which different effects of four acupuncture manipulations are precisely evaluated and a knowledge graph is established. The monitoring system provides a new perspective to quantitatively evaluate acupuncture effect on human brain and improve its therapeutic efficacy in clinical applications for neural disorders.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 2450-2459
Top Cited PapersOpen AccessEvaluation of Acupuncture Efficacy in Modulating Brain Activity With Periodic-Aperiodic EEG Measurements
Acupuncture is an important therapeutic method of traditional Chinese medicine and can effectively modulate brain disorders. The therapeutic efficacy of acupuncture is hard to evaluate due to lacking of effective measurements of brain activity. In this work, we design an EEG-based monitoring system to evaluate therapeutic effect of acupuncture on human brain by extracting periodic-aperiodic features. Power spectral density is estimated to compute the adjusted power of periodic oscillatory rhythm in EEG under acupuncture stimulation. It is exhibited that the brain activity in alpha band (8–12 Hz) is significantly enhanced during acupuncture, especially in parietal and occipital lobe regions. To probe the modulatory effect of acupuncture on aperiodic brain activity, we calculate the aperiodic exponent based on the parameterization of EEG power spectra. The aperiodic exponent decreases along with acupuncture process, which is more significant in central and frontal lobe regions. Furthermore, sensitivity of different brain regions to acupuncture is assessed by the integration of adjusted power and aperiodic exponent. Experimental results demonstrate the effectiveness of proposed periodic-aperiodic measurements of EEG signals, by which different effects of four acupuncture manipulations are precisely evaluated and a knowledge graph is established. The monitoring system provides a new perspective to quantitatively evaluate acupuncture effect on human brain and improve its therapeutic efficacy in clinical applications for neural disorders.
- 12 February 2024
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 92
Kinematic-driven human-robot interaction system with deep learning for flexible acupuncture needling manipulations
- 12 February 2024
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 92
Kinematic-driven human-robot interaction system with deep learning for flexible acupuncture needling manipulations
- 6 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-10
A Dynamic Transformer Network With Early Exit Mechanism for Fast Detection of Multiscale Surface Defects
Efficiency of surface defect detection is largely improved with the application of convolutional neural networks (CNNs). However, CNNs encounter difficulties in accurately modeling the multiscale features of defects due to the inherent locality of convolution. Additionally, existing methods for cross-level feature fusion introduce cumbersome computational complexity. Consequently, current networks struggle to reconcile location accuracy of multiscale defects with detection efficiency, resulting in poor performance in real-time detection. To this end, we proposed a dynamic transformer network for surface defect detection, utilizing self-attention-based transformers to precisely capture long-range semantic information within a routing space. Meanwhile, the network dynamically selected feature fusion paths according to inputs, enhancing its ability to aggregate multiscale defect features. Additionally, an early exit mechanism was designed by introducing a multi-task loss function to induce defect-free inputs to exit from shallow layers of the network, thereby improving the detection speed. Furthermore, a novel learning algorithm was proposed with a consistent prediction loss function to strengthen the hierarchical relationship between the classification task and segmentation task. By performing experiments on self-built steel surface dataset with multiscale defects, the proposed framework outperformed all competing models in terms of detection accuracy and inference speed, demonstrating that the proposed network can be used for online accurate detection for multiscale surface defects.
- 6 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-10
A Dynamic Transformer Network With Early Exit Mechanism for Fast Detection of Multiscale Surface Defects
Efficiency of surface defect detection is largely improved with the application of convolutional neural networks (CNNs). However, CNNs encounter difficulties in accurately modeling the multiscale features of defects due to the inherent locality of convolution. Additionally, existing methods for cross-level feature fusion introduce cumbersome computational complexity. Consequently, current networks struggle to reconcile location accuracy of multiscale defects with detection efficiency, resulting in poor performance in real-time detection. To this end, we proposed a dynamic transformer network for surface defect detection, utilizing self-attention-based transformers to precisely capture long-range semantic information within a routing space. Meanwhile, the network dynamically selected feature fusion paths according to inputs, enhancing its ability to aggregate multiscale defect features. Additionally, an early exit mechanism was designed by introducing a multi-task loss function to induce defect-free inputs to exit from shallow layers of the network, thereby improving the detection speed. Furthermore, a novel learning algorithm was proposed with a consistent prediction loss function to strengthen the hierarchical relationship between the classification task and segmentation task. By performing experiments on self-built steel surface dataset with multiscale defects, the proposed framework outperformed all competing models in terms of detection accuracy and inference speed, demonstrating that the proposed network can be used for online accurate detection for multiscale surface defects.
- Open Access
- 21 July 2023
- Published by Springer Nature in BioMedical Engineering OnLine
- Vol. 22 (1) , 1-20
Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning
Background: Colorectal cancer is one of the most serious malignant tumors, and lymph node metastasis (LNM) from colorectal cancer is a major factor for patient management and prognosis. Accurate image detection of LNM is an important task to help clinicians diagnose cancer. Recently, the U-Net architecture based on convolutional neural networks (CNNs) has been widely used to segment image to accomplish more precise cancer diagnosis. However, the accurate segmentation of important regions with high diagnostic value is still a great challenge due to the insufficient capability of CNN and codec structure in aggregating the detailed and non-local contextual information. In this work, we propose a high performance and low computation solution. Methods: Inspired by the working principle of Fovea in visual neuroscience, a novel network framework based on U-Net for cancer segmentation named Fovea-UNet is proposed to adaptively adjust the resolution according to the importance-aware of information and selectively focuses on the region most relevant to colorectal LNM. Specifically, we design an effective adaptively optimized pooling operation called Fovea Pooling (FP), which dynamically aggregate the detailed and non-local contextual information according to the pixel-level feature importance. In addition, the improved lightweight backbone network based on GhostNet is adopted to reduce the computational cost caused by FP. Results: Experimental results show that our proposed framework can achieve higher performance than other state-of-the-art segmentation networks with 79.38% IoU, 88.51% DSC, 92.82% sensitivity and 84.57% precision on the LNM dataset, and the parameter amount is reduced to 23.23 MB. Conclusions: The proposed framework can provide a valid tool for cancer diagnosis, especially for LNM of colorectal cancer.
- 21 July 2023
- Published by Springer Nature in BioMedical Engineering OnLine
- Vol. 22 (1) , 1-20
Open AccessFovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning
Background: Colorectal cancer is one of the most serious malignant tumors, and lymph node metastasis (LNM) from colorectal cancer is a major factor for patient management and prognosis. Accurate image detection of LNM is an important task to help clinicians diagnose cancer. Recently, the U-Net architecture based on convolutional neural networks (CNNs) has been widely used to segment image to accomplish more precise cancer diagnosis. However, the accurate segmentation of important regions with high diagnostic value is still a great challenge due to the insufficient capability of CNN and codec structure in aggregating the detailed and non-local contextual information. In this work, we propose a high performance and low computation solution. Methods: Inspired by the working principle of Fovea in visual neuroscience, a novel network framework based on U-Net for cancer segmentation named Fovea-UNet is proposed to adaptively adjust the resolution according to the importance-aware of information and selectively focuses on the region most relevant to colorectal LNM. Specifically, we design an effective adaptively optimized pooling operation called Fovea Pooling (FP), which dynamically aggregate the detailed and non-local contextual information according to the pixel-level feature importance. In addition, the improved lightweight backbone network based on GhostNet is adopted to reduce the computational cost caused by FP. Results: Experimental results show that our proposed framework can achieve higher performance than other state-of-the-art segmentation networks with 79.38% IoU, 88.51% DSC, 92.82% sensitivity and 84.57% precision on the LNM dataset, and the parameter amount is reduced to 23.23 MB. Conclusions: The proposed framework can provide a valid tool for cancer diagnosis, especially for LNM of colorectal cancer.