Xiaolin Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaolin Huang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Yun Ge
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
5 shared publications Ying Chen
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
4 shared publications- Ying Chen
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
4 shared publications Chengyu Huo
Institute of Biomedical Electronic Engineering, School of Electronic Science and Engineering, Nanjing University, Nanjing 210093, China; School of Physics and Electronic Engineering, Changshu Institute of Technology, Changshu 215500, China
3 shared publications- Xinbao Ning
Nanjing University
3 shared publications Cheng Wang
School of Electronic Science and Engineering, Nanjing University, Nanjing, China
2 shared publications
Latest Publications
- 30 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10290-10305
Self-Similarity Prior Distillation for Unsupervised Remote Physiological Measurement
Remote photoplethysmography (rPPG) is a non-invasive technique that aims to capture subtle variations in facial pixels caused by changes in blood volume resulting from cardiac activities. Most existing unsupervised methods for rPPG tasks focus on the contrastive learning between samples while neglecting the inherent self-similarity prior in physiological signals. In this paper, we propose a Self-Similarity Prior Distillation (SSPD) framework for unsupervised rPPG estimation, which capitalizes on the intrinsic temporal self-similarity of cardiac activities. Specifically, we first introduce a physical-prior embedded augmentation technique to mitigate the effect of various types of noise. Then, we tailor a self-similarity-aware network to disentangle more reliable self-similar physiological features. Finally, we develop a hierarchical self-distillation paradigm for self-similarity-aware learning and rPPG signal decoupling. Comprehensive experiments demonstrate that the unsupervised SSPD framework achieves comparable or even superior performance compared to the state-of-the-art supervised methods. Meanwhile, SSPD has the lowest inference time and computation cost among end-to-end models.
- 30 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10290-10305
Self-Similarity Prior Distillation for Unsupervised Remote Physiological Measurement
Remote photoplethysmography (rPPG) is a non-invasive technique that aims to capture subtle variations in facial pixels caused by changes in blood volume resulting from cardiac activities. Most existing unsupervised methods for rPPG tasks focus on the contrastive learning between samples while neglecting the inherent self-similarity prior in physiological signals. In this paper, we propose a Self-Similarity Prior Distillation (SSPD) framework for unsupervised rPPG estimation, which capitalizes on the intrinsic temporal self-similarity of cardiac activities. Specifically, we first introduce a physical-prior embedded augmentation technique to mitigate the effect of various types of noise. Then, we tailor a self-similarity-aware network to disentangle more reliable self-similar physiological features. Finally, we develop a hierarchical self-distillation paradigm for self-similarity-aware learning and rPPG signal decoupling. Comprehensive experiments demonstrate that the unsupervised SSPD framework achieves comparable or even superior performance compared to the state-of-the-art supervised methods. Meanwhile, SSPD has the lowest inference time and computation cost among end-to-end models.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8214-8224
Resolve Domain Conflicts for Generalizable Remote Physiological Measurement
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8214-8224
Open AccessResolve Domain Conflicts for Generalizable Remote Physiological Measurement
- Open Access
- 1 May 2023
- Published by AIP Publishing in AIP Advances
- Vol. 13 (5)
An entropy-based method to measure phase-locking between LFP and spikes
Phase-locking between local field potential and spikes has been widely investigated through neurophysiological analysis. Two indices most frequently adopted traditionally include the mean resultant length and p of the Rayleigh test. However, the traditional method is found less reliable for cases with substantial sample sizes or with bimodal distribution. In this article, K we propose an entropy-based method to detect and measure phase-locking. Simulation results prove that the method can be effectively applied to cases with a relatively large sample size and it can effectively detect phase-locking even under bimodal conditions with two peaks of opposite phases. Furthermore, we propose thresholds to help measure the intensity of spike field phase-locking. We also apply the proposed method to our experimental data and find phase locking with two opposite phases, which would be left out in traditional phase-locking analysis.
- 1 May 2023
- Published by AIP Publishing in AIP Advances
- Vol. 13 (5)
Open AccessAn entropy-based method to measure phase-locking between LFP and spikes
Phase-locking between local field potential and spikes has been widely investigated through neurophysiological analysis. Two indices most frequently adopted traditionally include the mean resultant length and p of the Rayleigh test. However, the traditional method is found less reliable for cases with substantial sample sizes or with bimodal distribution. In this article, K we propose an entropy-based method to detect and measure phase-locking. Simulation results prove that the method can be effectively applied to cases with a relatively large sample size and it can effectively detect phase-locking even under bimodal conditions with two peaks of opposite phases. Furthermore, we propose thresholds to help measure the intensity of spike field phase-locking. We also apply the proposed method to our experimental data and find phase locking with two opposite phases, which would be left out in traditional phase-locking analysis.
- Open Access
- 28 June 2022
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2022, 1-16
Classification for Memory Activities: Experiments and EEG Analysis Based on Networks Constructed via Phase-Locking Value
Electroencephalogram (EEG) plays a crucial role in the study of working memory, which involves the complex coordination of brain regions. In this research, we designed and conducted series of experiments of memory with various memory loads or target forms and collected behavioral data as well as 32-lead EEG simultaneously. Combined with behavioral data analysis, we segmented EEG into slices; then, we calculated phase-locking value (PLV) of Gamma rhythms between every two leads, conducted binarization, constructed brain function network, and extracted three network characteristics of node degree, local clustering coefficient, and betweenness centrality. Finally, we inputted these network characteristics of all leads into support vector machines (SVM) for classification and obtained decent performances; i.e., all classification accuracies are greater than 0.78 on an independent test set. Particularly, PLV application was restricted to the narrow-band signals, and rare successful application to EEG Gamma rhythm, defined as wide as 30-100 Hz, had been reported. In order to address this limitation, we adopted simulation on band-pass filtered noise with the same frequency band as Gamma to help determine the PLV binarizing threshold. It turns out that network characteristics based on binarized PLV have the ability to distinguish the presence or absence of memory, as well as the intensity of the mental workload at the moment of memory. This work sheds a light upon phase-locking investigation between relatively wide-band signals, as well as memory research via EEG.
- 28 June 2022
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2022, 1-16
Open AccessClassification for Memory Activities: Experiments and EEG Analysis Based on Networks Constructed via Phase-Locking Value
Electroencephalogram (EEG) plays a crucial role in the study of working memory, which involves the complex coordination of brain regions. In this research, we designed and conducted series of experiments of memory with various memory loads or target forms and collected behavioral data as well as 32-lead EEG simultaneously. Combined with behavioral data analysis, we segmented EEG into slices; then, we calculated phase-locking value (PLV) of Gamma rhythms between every two leads, conducted binarization, constructed brain function network, and extracted three network characteristics of node degree, local clustering coefficient, and betweenness centrality. Finally, we inputted these network characteristics of all leads into support vector machines (SVM) for classification and obtained decent performances; i.e., all classification accuracies are greater than 0.78 on an independent test set. Particularly, PLV application was restricted to the narrow-band signals, and rare successful application to EEG Gamma rhythm, defined as wide as 30-100 Hz, had been reported. In order to address this limitation, we adopted simulation on band-pass filtered noise with the same frequency band as Gamma to help determine the PLV binarizing threshold. It turns out that network characteristics based on binarized PLV have the ability to distinguish the presence or absence of memory, as well as the intensity of the mental workload at the moment of memory. This work sheds a light upon phase-locking investigation between relatively wide-band signals, as well as memory research via EEG.
- Open Access
- 7 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 81841-81854
Intensive Care Unit False Alarm Identification Based on Convolution Neural Network
In the intensive care unit(ICU), excessive false alarms burden medical staff greatly, and cause a waste of medical resources as well. In order to alleviate false alarming in ICU, we constructed classification models based on convolutional neural network, which can directly deal with time series and avoid manually extracting features. Combining with grouping strategy, we tried two basic network structures, i.e. deep group convolutional neural network(DGCN) and embedded deep group convolutional network(EDGCN). After that, based on EDGCN, which was proved better, ensemble networks were constructed to elevate the performance further. Considering of the limited sample size, various data expansions were also tried. For comparison, we used a widely adopted index `Score', which is defined as 100×(TP+TN)/(TP+TN+FP + 5×FN), as performance evaluation. Finally, we tested our model in the online sandbox, and got a score of 80.68. Although it is slightly lower than the best scores that have been reported, our models are end-to-end, which means the original time series can be automatically mapped into a binary output, without manual feature extraction. In addition, the innovative adoption of group convolution makes full use of information from multi-channel signals. Besides, this work provides ideas for relating network parameter selection with physiological or physical natures of signals. In the end, after further discussion, we also proposed potential elevation solutions.
- 7 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 81841-81854
Open AccessIntensive Care Unit False Alarm Identification Based on Convolution Neural Network
In the intensive care unit(ICU), excessive false alarms burden medical staff greatly, and cause a waste of medical resources as well. In order to alleviate false alarming in ICU, we constructed classification models based on convolutional neural network, which can directly deal with time series and avoid manually extracting features. Combining with grouping strategy, we tried two basic network structures, i.e. deep group convolutional neural network(DGCN) and embedded deep group convolutional network(EDGCN). After that, based on EDGCN, which was proved better, ensemble networks were constructed to elevate the performance further. Considering of the limited sample size, various data expansions were also tried. For comparison, we used a widely adopted index `Score', which is defined as 100×(TP+TN)/(TP+TN+FP + 5×FN), as performance evaluation. Finally, we tested our model in the online sandbox, and got a score of 80.68. Although it is slightly lower than the best scores that have been reported, our models are end-to-end, which means the original time series can be automatically mapped into a binary output, without manual feature extraction. In addition, the innovative adoption of group convolution makes full use of information from multi-channel signals. Besides, this work provides ideas for relating network parameter selection with physiological or physical natures of signals. In the end, after further discussion, we also proposed potential elevation solutions.
- Open Access
- 21 December 2020
- Published by Springer Nature in Research Square
ICU False Alarm Identification Based on Convolution Neural Network
Background: In intensive care unit(ICU), excessive false alarms burden medical staff greatly, and cause medical resource waste as well. In order to alleviate false alarms in ICU, we constructed models for classification using convolutional neural networks, which can deal directly with time series and avoid extracting features manually. Results: Combining with grouping strategy, we tried two basic network structures, i.e. DGCN and EDGCN. After that, based on EDGCN, which was proved better, ensembling networks were also constructed to elevate the performance further. Considering of the limited sample size, different data expansions were also experimented. Finally, we tested our model in the online sandbox, and got a score of 78.14. Conclusions: Although the performance is slightly lower than the best scores that have been reported, our models are end-to-end, through which the original time series can be automatically mapped into a binary output, without manually feature extraction. In addition, our method innovatively uses grouped convolution to make full use of the information in multi-channel signals. In the end, we also discussed the potential solutions to further elevate performances.
- 21 December 2020
- Published by Springer Nature in Research Square
Open AccessICU False Alarm Identification Based on Convolution Neural Network
Background: In intensive care unit(ICU), excessive false alarms burden medical staff greatly, and cause medical resource waste as well. In order to alleviate false alarms in ICU, we constructed models for classification using convolutional neural networks, which can deal directly with time series and avoid extracting features manually. Results: Combining with grouping strategy, we tried two basic network structures, i.e. DGCN and EDGCN. After that, based on EDGCN, which was proved better, ensembling networks were also constructed to elevate the performance further. Considering of the limited sample size, different data expansions were also experimented. Finally, we tested our model in the online sandbox, and got a score of 78.14. Conclusions: Although the performance is slightly lower than the best scores that have been reported, our models are end-to-end, through which the original time series can be automatically mapped into a binary output, without manually feature extraction. In addition, our method innovatively uses grouped convolution to make full use of the information in multi-channel signals. In the end, we also discussed the potential solutions to further elevate performances.
- Open Access
- 27 May 2018
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2018, 1-9
Common Interferences Removal from Dense Multichannel EEG Using Independent Component Decomposition
To improve the spatial resolution, dense multichannel electroencephalogram with more than 32 leads has gained more and more applications. However, strong common interference will not only conceal the weak components generated from the specific isolated neural source, but also lead to severe spurious correlation between different brain regions, which results in great distortion on brain connectivity or brain network analysis. Starting from the fast independent component analysis algorithm, we first derive the mixing matrix of independent source components based on the baseline signals prior to tasks. Then, we identify the common interferences as those components whose mixing vectors span the minimum angles with respect to the unitary vector. By assuming that both the common interferences and their corresponding mixing vectors stay consistent during the entire experiment, we apply the demixing and mixing matrix to the task signals and remove the inferred common interferences. Subsequently, we validate the method using simulation. Finally, the index of global coherence is calculated for validation. It turns out that the proposed method can successfully remove the common interferences so that the prominent coherence of mu rhythms in motor imagery tasks is unmasked. The proposed method can gain wide applications because it reveals the true correlation between the local sources in spite of the low signal-to-noise ratio.
- 27 May 2018
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2018, 1-9
Open AccessCommon Interferences Removal from Dense Multichannel EEG Using Independent Component Decomposition
To improve the spatial resolution, dense multichannel electroencephalogram with more than 32 leads has gained more and more applications. However, strong common interference will not only conceal the weak components generated from the specific isolated neural source, but also lead to severe spurious correlation between different brain regions, which results in great distortion on brain connectivity or brain network analysis. Starting from the fast independent component analysis algorithm, we first derive the mixing matrix of independent source components based on the baseline signals prior to tasks. Then, we identify the common interferences as those components whose mixing vectors span the minimum angles with respect to the unitary vector. By assuming that both the common interferences and their corresponding mixing vectors stay consistent during the entire experiment, we apply the demixing and mixing matrix to the task signals and remove the inferred common interferences. Subsequently, we validate the method using simulation. Finally, the index of global coherence is calculated for validation. It turns out that the proposed method can successfully remove the common interferences so that the prominent coherence of mu rhythms in motor imagery tasks is unmasked. The proposed method can gain wide applications because it reveals the true correlation between the local sources in spite of the low signal-to-noise ratio.
- Open Access
- 1 January 2018
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 17, 1-13
Nearest Neighbor Method to Estimate Internal Target for Real-Time Tumor Tracking
Purpose: This work proposed a nearest neighbor estimation method to track the respiration-induced tumor motion. Methods: Based on the simultaneously collected motion traces of external surrogate and internal target during the modeling phase prior to treatment, we first obtain the nearest neighbors of the current surrogate in external space. Subsequently, the concurrent targets in internal space are determined and used to estimate the current target position. The method was validated on 71 cases that were from 3 open access databases. In addition, to evaluate the method’s estimation and prediction accuracy, we compared the method with other works. Results: Except for 2 cases, the nearest neighbor estimation achieved the root-mean-square error of <3 mm. The comparison indicated that the method had better estimation accuracy than polynomial model and good prediction performance. Discussion: The 2 exceptive cases were further analyzed for failure causes. We inferred that one was because of the lack of estimating new target in our method, and the other one was because of the mistake during data collection. Accordingly, the potential solutions were suggested. Besides, the method’s estimation for surrogate outliers, effects of modeling length, calibration, and extension were discussed. Conclusion: The results demonstrated nearest neighbor estimation’s effectiveness. Except for this, the method imposes no restrictions on the modality of the pretreatment target images and does not assume a specific correspondence function between the surrogate and the target. With only 1 critical parameter, this nearest neighbor estimation method is easy to implement in clinical setting and thus has potential for broad applications.
- 1 January 2018
- Published by SAGE Publications in Technology in Cancer Research & Treatment
- Vol. 17, 1-13
Open AccessNearest Neighbor Method to Estimate Internal Target for Real-Time Tumor Tracking
Purpose: This work proposed a nearest neighbor estimation method to track the respiration-induced tumor motion. Methods: Based on the simultaneously collected motion traces of external surrogate and internal target during the modeling phase prior to treatment, we first obtain the nearest neighbors of the current surrogate in external space. Subsequently, the concurrent targets in internal space are determined and used to estimate the current target position. The method was validated on 71 cases that were from 3 open access databases. In addition, to evaluate the method’s estimation and prediction accuracy, we compared the method with other works. Results: Except for 2 cases, the nearest neighbor estimation achieved the root-mean-square error of <3 mm. The comparison indicated that the method had better estimation accuracy than polynomial model and good prediction performance. Discussion: The 2 exceptive cases were further analyzed for failure causes. We inferred that one was because of the lack of estimating new target in our method, and the other one was because of the mistake during data collection. Accordingly, the potential solutions were suggested. Besides, the method’s estimation for surrogate outliers, effects of modeling length, calibration, and extension were discussed. Conclusion: The results demonstrated nearest neighbor estimation’s effectiveness. Except for this, the method imposes no restrictions on the modality of the pretreatment target images and does not assume a specific correspondence function between the surrogate and the target. With only 1 critical parameter, this nearest neighbor estimation method is easy to implement in clinical setting and thus has potential for broad applications.
- 16 October 2014
- Published by IOP Publishing in Medical Engineering & Physics
- Vol. 36 (12) , 1693-1698
A multi-scale feedback ratio analysis of heartbeat interval series in healthy vs. cardiac patients
The second-order difference plot, as a modified Poincaré plot, is one of the important approaches for assessing the dynamics of heart rate variability. However, corresponding quantitative analysis methods are relatively limited. Based on the second-order difference plot, we propose a novel method, called the multi-scale feedback ratio analysis, which can measure the feedback properties of heart rate fluctuations on different temporal scales. The index [R(TF([τ(1), τ(2)]) is then defined to quantify the average feedback ratio through a definite scale range. Analysis of Gaussian white, 1/f and Brownian noises show that the feedback ratios are indeed on different levels. The method is then applied to heartbeat interval series derived from healthy subjects, subjects with congestive heart failure and subjects with atrial fibrillation. Results show that, for all groups, the feedback ratios vary with increasing time scales, and gradually reach relatively stable states. The R(TF)([10,20]) values of the three groups are significantly different. Thus, R(TF)([10,20]) becomes an effective parameter for distinguishing healthy and pathologic states. In addition, RTF([10,20]) for healthy, congestive failure and atrial fibrillation subjects are close to those of the 1/f, Brownian and white noises respectively, indicating different intrinsic dynamics.
- 16 October 2014
- Published by IOP Publishing in Medical Engineering & Physics
- Vol. 36 (12) , 1693-1698
A multi-scale feedback ratio analysis of heartbeat interval series in healthy vs. cardiac patients
The second-order difference plot, as a modified Poincaré plot, is one of the important approaches for assessing the dynamics of heart rate variability. However, corresponding quantitative analysis methods are relatively limited. Based on the second-order difference plot, we propose a novel method, called the multi-scale feedback ratio analysis, which can measure the feedback properties of heart rate fluctuations on different temporal scales. The index [R(TF([τ(1), τ(2)]) is then defined to quantify the average feedback ratio through a definite scale range. Analysis of Gaussian white, 1/f and Brownian noises show that the feedback ratios are indeed on different levels. The method is then applied to heartbeat interval series derived from healthy subjects, subjects with congestive heart failure and subjects with atrial fibrillation. Results show that, for all groups, the feedback ratios vary with increasing time scales, and gradually reach relatively stable states. The R(TF)([10,20]) values of the three groups are significantly different. Thus, R(TF)([10,20]) becomes an effective parameter for distinguishing healthy and pathologic states. In addition, RTF([10,20]) for healthy, congestive failure and atrial fibrillation subjects are close to those of the 1/f, Brownian and white noises respectively, indicating different intrinsic dynamics.
- 18 April 2014
- Published by Springer Nature in Chinese Science Bulletin
- Vol. 59 (25) , 3107-3113
Multifractal analysis of resting state fMRI series in default mode network: age and gender effects
- 18 April 2014
- Published by Springer Nature in Chinese Science Bulletin
- Vol. 59 (25) , 3107-3113
Multifractal analysis of resting state fMRI series in default mode network: age and gender effects