Pub Date : 2024-09-02DOI: 10.1109/TNSRE.2024.3453222
Zahra Habibollahi;Yue Zhou;Mary E. Jenkins;S. Jayne Garland;Evan Friedman;Michael D. Naish;Ana Luisa Trejos
Parkinson’s disease (PD) and essential tremor are two major causes of pathological tremor among people over 60 years old. Due to the side effects and complications of traditional tremor management methods such as medication and deep brain surgery, non invasive tremor suppression methods have become more popular in recent years. Functional electrical stimulation (FES) is one of the methods used to reduce tremor in several studies. However, the effect of different FES parameters on tremor suppression and discomfort level, including amplitude, the number of pulses in each stimulation burst, frequency, and pulse width is yet to be studied for longer stimulation durations. Therefore, in this work, experiments were performed on 14 participants with PD to evaluate the effect of thirty seconds of out-of-phase electrical stimulation on wrist tremor at rest. Trials were conducted by varying the stimulation amplitude and the number of pulses while keeping the frequency and pulse width constant. Each test was repeated three times for each participant. The results showed an overall tremor suppression for 11 out of 14 participants and no average positive effects for three participants. It is concluded that despite the effectiveness of FES in tremor suppression, each set of FES parameters showed different suppression levels among participants due to the variability of tremor over time. Thus, for this method to be effective, an adaptive control system would be required to tune FES parameters in real time according to changes in tremor during extended stimulation periods.
{"title":"Tremor Suppression Using Functional Electrical Stimulation","authors":"Zahra Habibollahi;Yue Zhou;Mary E. Jenkins;S. Jayne Garland;Evan Friedman;Michael D. Naish;Ana Luisa Trejos","doi":"10.1109/TNSRE.2024.3453222","DOIUrl":"10.1109/TNSRE.2024.3453222","url":null,"abstract":"Parkinson’s disease (PD) and essential tremor are two major causes of pathological tremor among people over 60 years old. Due to the side effects and complications of traditional tremor management methods such as medication and deep brain surgery, non invasive tremor suppression methods have become more popular in recent years. Functional electrical stimulation (FES) is one of the methods used to reduce tremor in several studies. However, the effect of different FES parameters on tremor suppression and discomfort level, including amplitude, the number of pulses in each stimulation burst, frequency, and pulse width is yet to be studied for longer stimulation durations. Therefore, in this work, experiments were performed on 14 participants with PD to evaluate the effect of thirty seconds of out-of-phase electrical stimulation on wrist tremor at rest. Trials were conducted by varying the stimulation amplitude and the number of pulses while keeping the frequency and pulse width constant. Each test was repeated three times for each participant. The results showed an overall tremor suppression for 11 out of 14 participants and no average positive effects for three participants. It is concluded that despite the effectiveness of FES in tremor suppression, each set of FES parameters showed different suppression levels among participants due to the variability of tremor over time. Thus, for this method to be effective, an adaptive control system would be required to tune FES parameters in real time according to changes in tremor during extended stimulation periods.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3289-3298"},"PeriodicalIF":4.8,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10663274","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142119715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-30DOI: 10.1109/TNSRE.2024.3452315
Yifei Yu;Yuanxiang Li;Yunqing Zhou;Yingyan Wang;Jiwen Wang
Electroencephalography (EEG) artifacts are very common in clinical diagnosis and can heavily impact diagnosis. Manual screening of artifact events is labor-intensive with little benefit. Therefore, exploring algorithms for automatic detection and classification of EEG artifacts can significantly assist clinical diagnosis. In this paper, we propose a learnable and explainable wavelet neural network (WaveNet) for EEG artifact detection and classification. The model is powered by the wavelet decomposition block based on invertible neural network, which can extract signal features without information loss, and a tree generator for building wavelet tree structure automatically. They provide the model with good feature extraction capabilities and explainability. To evaluate the model’s performance more fairly, we introduce the base point level matching score (BASE) and the Event-Aligned Compensation Scoring (EACS) at the event level as two metrics for model performance evaluation. On the challenging Temple University EEG Artifact (TUAR) dataset, our model outperforms other baselines in terms of F1-score for both artifact detection and classification tasks. The case study also validates the model’s ability to offer explainability for predictions based on frequency band energy, suggesting potential applications in clinical diagnosis.
脑电图（EEG）伪像在临床诊断中非常常见，会严重影响诊断。人工筛选伪像事件耗费大量人力，但收效甚微。因此，探索自动检测和分类脑电图伪像的算法可以极大地帮助临床诊断。在本文中，我们提出了一种可学习、可解释的小波神经网络（WaveNet），用于脑电图伪像的检测和分类。该模型由基于可逆神经网络的小波分解块和用于自动构建小波树结构的小波树生成器提供支持，前者能在不损失信息的情况下提取信号特征，后者能在不损失信息的情况下提取信号特征。它们为模型提供了良好的特征提取能力和可解释性。为了更公平地评估模型的性能，我们引入了基点级匹配得分（BASE）和事件级事件对齐补偿得分（EACS）作为模型性能评估的两个指标。在具有挑战性的坦普尔大学脑电图伪像（TUAR）数据集上，我们的模型在伪像检测和分类任务中的 F1 分数均优于其他基线模型。案例研究还验证了该模型基于频带能量提供预测可解释性的能力，为临床诊断提供了潜在应用。
{"title":"A Learnable and Explainable Wavelet Neural Network for EEG Artifacts Detection and Classification","authors":"Yifei Yu;Yuanxiang Li;Yunqing Zhou;Yingyan Wang;Jiwen Wang","doi":"10.1109/TNSRE.2024.3452315","DOIUrl":"10.1109/TNSRE.2024.3452315","url":null,"abstract":"Electroencephalography (EEG) artifacts are very common in clinical diagnosis and can heavily impact diagnosis. Manual screening of artifact events is labor-intensive with little benefit. Therefore, exploring algorithms for automatic detection and classification of EEG artifacts can significantly assist clinical diagnosis. In this paper, we propose a learnable and explainable wavelet neural network (WaveNet) for EEG artifact detection and classification. The model is powered by the wavelet decomposition block based on invertible neural network, which can extract signal features without information loss, and a tree generator for building wavelet tree structure automatically. They provide the model with good feature extraction capabilities and explainability. To evaluate the model’s performance more fairly, we introduce the base point level matching score (BASE) and the Event-Aligned Compensation Scoring (EACS) at the event level as two metrics for model performance evaluation. On the challenging Temple University EEG Artifact (TUAR) dataset, our model outperforms other baselines in terms of F1-score for both artifact detection and classification tasks. The case study also validates the model’s ability to offer explainability for predictions based on frequency band energy, suggesting potential applications in clinical diagnosis.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3358-3368"},"PeriodicalIF":4.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10659751","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Most of current prostheses can offer motor function restoration for limb amputees but usually lack natural and intuitive sensory feedback. Many studies have demonstrated that Transcutaneous Electrical Nerve Stimulation (TENS) is promising in non-invasive sensation evoking for amputees. However, the objective evaluation and mechanism analysis on sensation feedback are still limited. This work utilized multi-channel TENS with diverse stimulus patterns to evoke sensations on four non-disabled subjects and two transradial amputees. Meanwhile, electroencephalogram (EEG) was collected to objectively assess the evoked sensations, where event-related potentials (ERPs), brain electrical activity maps (BEAMs), and functional connectivity (FC) were computed. The results show that various sensations could be successfully evoked for both amputees and non-disabled subjects by customizing stimulus parameters. The ERP confirmed the sensation and revealed the sensory-processing-related components like N100 and P200; the BEAMs confirmed the corresponding regions of somatosensory cortex were activated by stimulation; the FC indicated an increase of interactions between the regions of sensorimotor cortex. This study may shed light on how the brain responds to external stimulation as sensory feedback and serve as a pilot for further bidirectional closed-loop prosthetic control.
{"title":"Assessment of TENS-Evoked Tactile Sensations for Transradial Amputees via EEG Investigation","authors":"Yuanzhe Dong;Yuxiang Zhang;Qingge Li;Jianping Huang;Xiangxin Li;Naifu Jiang;Guanglin Li;Wenyuan Liang;Peng Fang","doi":"10.1109/TNSRE.2024.3452153","DOIUrl":"10.1109/TNSRE.2024.3452153","url":null,"abstract":"Most of current prostheses can offer motor function restoration for limb amputees but usually lack natural and intuitive sensory feedback. Many studies have demonstrated that Transcutaneous Electrical Nerve Stimulation (TENS) is promising in non-invasive sensation evoking for amputees. However, the objective evaluation and mechanism analysis on sensation feedback are still limited. This work utilized multi-channel TENS with diverse stimulus patterns to evoke sensations on four non-disabled subjects and two transradial amputees. Meanwhile, electroencephalogram (EEG) was collected to objectively assess the evoked sensations, where event-related potentials (ERPs), brain electrical activity maps (BEAMs), and functional connectivity (FC) were computed. The results show that various sensations could be successfully evoked for both amputees and non-disabled subjects by customizing stimulus parameters. The ERP confirmed the sensation and revealed the sensory-processing-related components like N100 and P200; the BEAMs confirmed the corresponding regions of somatosensory cortex were activated by stimulation; the FC indicated an increase of interactions between the regions of sensorimotor cortex. This study may shed light on how the brain responds to external stimulation as sensory feedback and serve as a pilot for further bidirectional closed-loop prosthetic control.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3261-3269"},"PeriodicalIF":4.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10659850","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, pressure-sensing mats have been widely used to capture static and dynamic pressure over sleep for posture recognition. Both a full-size mat with a low-density sensing array for figuring out the structure of the whole body and a miniature scale mat with a high-density sensing array for identifying the local characteristics around the chest have been investigated. However, both of the mat systems may face the challenge in the trade-off between the computational complexity (involving the size, density, etc. of the mat) and the performance of sleep posture recognition, where high performance may requires overcomplex computation and result in time latency in real-time sleep posture monitoring. In this paper, a lightweight neural network named ConcatNet, is proposed to realize sleep postures (supine, left, right, and prone) recognition in real time while maintaining a favorable performance. In ConcatNet, the inception module is proposed to extract the image features under multiple receptive fields, while the multi-layer feature fusion module is utilized to fuse deep and shallow features to enhance the model performance. To further improve the efficiency of the model, the depthwise convolution is adopoted. ConcatNet models in 3 different scales (ConcatNet-S, ConcatNet-M, and ConcatNet-L) are built to explore the impact of the sensor density on sleep posture recognition performance. Experimental results exhibit that ConcatNet-M corresponding to medium sensor density ( ${16}times {16}$ ) achieved the best comprehensive performance, with short-term data cross-validation accuracy at 95.56% and overnight data testing accuracy at 94.68%. The model size is 7.91KB, FLOPs is 56.47K, and the inference time is only 0.38ms, which shows an outstanding performance of real-time sleep posture recognition with minimum consumption, indicating the potential to be deployed in mobile devices.
{"title":"Lightweight Neural Network for Sleep Posture Classification Using Pressure Sensing Mat at Various Sensor Densities","authors":"Shaonan Wu;Haikang Diao;Yi Feng;Yiyuan Zhang;Hongyu Chen;Yasemin M. Akay;Metin Akay;Chen Chen;Wei Chen","doi":"10.1109/TNSRE.2024.3452431","DOIUrl":"10.1109/TNSRE.2024.3452431","url":null,"abstract":"Recently, pressure-sensing mats have been widely used to capture static and dynamic pressure over sleep for posture recognition. Both a full-size mat with a low-density sensing array for figuring out the structure of the whole body and a miniature scale mat with a high-density sensing array for identifying the local characteristics around the chest have been investigated. However, both of the mat systems may face the challenge in the trade-off between the computational complexity (involving the size, density, etc. of the mat) and the performance of sleep posture recognition, where high performance may requires overcomplex computation and result in time latency in real-time sleep posture monitoring. In this paper, a lightweight neural network named ConcatNet, is proposed to realize sleep postures (supine, left, right, and prone) recognition in real time while maintaining a favorable performance. In ConcatNet, the inception module is proposed to extract the image features under multiple receptive fields, while the multi-layer feature fusion module is utilized to fuse deep and shallow features to enhance the model performance. To further improve the efficiency of the model, the depthwise convolution is adopoted. ConcatNet models in 3 different scales (ConcatNet-S, ConcatNet-M, and ConcatNet-L) are built to explore the impact of the sensor density on sleep posture recognition performance. Experimental results exhibit that ConcatNet-M corresponding to medium sensor density (\u0000<inline-formula> <tex-math>${16}times {16}$ </tex-math></inline-formula>\u0000) achieved the best comprehensive performance, with short-term data cross-validation accuracy at 95.56% and overnight data testing accuracy at 94.68%. The model size is 7.91KB, FLOPs is 56.47K, and the inference time is only 0.38ms, which shows an outstanding performance of real-time sleep posture recognition with minimum consumption, indicating the potential to be deployed in mobile devices.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3410-3421"},"PeriodicalIF":4.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10659869","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-30DOI: 10.1109/TNSRE.2024.3452308
Javier Navallas;Cristina Mariscal;Armando Malanda;Javier Rodríguez-Falces
EMG filling curve characterizes the EMG filling process and EMG probability density function (PDF) shape change for the entire force range of a muscle. We aim to understand the relation between the physiological and recording variables, and the resulting EMG filling curves. We thereby present an analytical and simulation study to explain how the filling curve patterns relate to specific changes in the motor unit potential (MUP) waveforms and motor unit (MU) firing rates, the two main factors affecting the EMG PDF, but also to recording conditions in terms of noise level. We compare the analytical results with simulated cases verifying a perfect agreement with the analytical model. Finally, we present a set of real EMG filling curves with distinct patterns to explain the information about MUP amplitudes, MU firing rates, and noise level that these patterns provide in the light of the analytical study. Our findings reflect that the filling factor increases when firing rate increases or when newly recruited motor unit have potentials of smaller or equal amplitude than the former ones. On the other hand, the filling factor decreases when newly recruited potentials are larger in amplitude than the previous potentials. Filling curves are shown to be consistent under changes of the MUP waveform, and stretched under MUP amplitude scaling. Our findings also show how additive noise affects the filling curve and can even impede to obtain reliable information from the EMG PDF statistics.
{"title":"Understanding EMG PDF Changes With Motor Unit Potential Amplitudes, Firing Rates, and Noise Level Through EMG Filling Curve Analysis","authors":"Javier Navallas;Cristina Mariscal;Armando Malanda;Javier Rodríguez-Falces","doi":"10.1109/TNSRE.2024.3452308","DOIUrl":"10.1109/TNSRE.2024.3452308","url":null,"abstract":"EMG filling curve characterizes the EMG filling process and EMG probability density function (PDF) shape change for the entire force range of a muscle. We aim to understand the relation between the physiological and recording variables, and the resulting EMG filling curves. We thereby present an analytical and simulation study to explain how the filling curve patterns relate to specific changes in the motor unit potential (MUP) waveforms and motor unit (MU) firing rates, the two main factors affecting the EMG PDF, but also to recording conditions in terms of noise level. We compare the analytical results with simulated cases verifying a perfect agreement with the analytical model. Finally, we present a set of real EMG filling curves with distinct patterns to explain the information about MUP amplitudes, MU firing rates, and noise level that these patterns provide in the light of the analytical study. Our findings reflect that the filling factor increases when firing rate increases or when newly recruited motor unit have potentials of smaller or equal amplitude than the former ones. On the other hand, the filling factor decreases when newly recruited potentials are larger in amplitude than the previous potentials. Filling curves are shown to be consistent under changes of the MUP waveform, and stretched under MUP amplitude scaling. Our findings also show how additive noise affects the filling curve and can even impede to obtain reliable information from the EMG PDF statistics.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3240-3250"},"PeriodicalIF":4.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10659753","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1109/TNSRE.2024.3451651
Yanyan Liu;Ruiping Liu;Xinzhu Wan;Chunyan Chen;Yining Wang;Wanqi Yu;Jun OuYang;Lei Qian;Gang Liu
To investigate the biomechanical mechanisms underlying the pathogenesis and explore the effects of kinesiology taping (KT) on neuromuscular control in HV patients. The study population consisted of 16 young controls (YC group) and 15 patients with hallux valgus (HV group). All subjects underwent a natural velocity gait assessment. Additionally, 11 patients from the HV group received KT intervention over a period of one month, consisting of 15 sessions administered every other day. After the one-month intervention, these patients underwent a gait assessment and were included in the HV-KT group. The electromyography (EMG) and joint motion were evaluated using non-negative matrix factorization (NNMF) to compare the difference in muscle and kinematic synergy among the three groups. The center of plantar pressure (COP) and ground reaction force (GRF) were measured by the force platform. The number of synergies did not differ within the three groups, but the structure of muscle synergies and kinematic synergies differed in the HV group. The KT intervention (HV-KT group) altered the structure of synergies. The correlation between kinematic synergies and muscular synergies was lower in the HV group than in the YC group, whereas the correlation between the two increased after the KT intervention in the HV group. During gait, the HV group tended to activate more muscles around foot joints to maintain body stability. The visual analogue scale (VAS) scores, hallux valgus angle (HVA), and COP were significantly decreased after the intervention ( ${P}lt 0.05$ ). HV patients exhibited altered kinematic and muscular synergies structures as well as muscle activation. Also, it weakened the balance and athletic ability of HV patients. KT intervention improved neuromuscular control to provide a better gait performance.
{"title":"The Effect of Short-Term Kinesiology Taping on Neuromuscular Controls in Hallux Valgus During Gait: A Study of Muscle and Kinematic Synergy","authors":"Yanyan Liu;Ruiping Liu;Xinzhu Wan;Chunyan Chen;Yining Wang;Wanqi Yu;Jun OuYang;Lei Qian;Gang Liu","doi":"10.1109/TNSRE.2024.3451651","DOIUrl":"10.1109/TNSRE.2024.3451651","url":null,"abstract":"To investigate the biomechanical mechanisms underlying the pathogenesis and explore the effects of kinesiology taping (KT) on neuromuscular control in HV patients. The study population consisted of 16 young controls (YC group) and 15 patients with hallux valgus (HV group). All subjects underwent a natural velocity gait assessment. Additionally, 11 patients from the HV group received KT intervention over a period of one month, consisting of 15 sessions administered every other day. After the one-month intervention, these patients underwent a gait assessment and were included in the HV-KT group. The electromyography (EMG) and joint motion were evaluated using non-negative matrix factorization (NNMF) to compare the difference in muscle and kinematic synergy among the three groups. The center of plantar pressure (COP) and ground reaction force (GRF) were measured by the force platform. The number of synergies did not differ within the three groups, but the structure of muscle synergies and kinematic synergies differed in the HV group. The KT intervention (HV-KT group) altered the structure of synergies. The correlation between kinematic synergies and muscular synergies was lower in the HV group than in the YC group, whereas the correlation between the two increased after the KT intervention in the HV group. During gait, the HV group tended to activate more muscles around foot joints to maintain body stability. The visual analogue scale (VAS) scores, hallux valgus angle (HVA), and COP were significantly decreased after the intervention (\u0000<inline-formula> <tex-math>${P}lt 0.05$ </tex-math></inline-formula>\u0000). HV patients exhibited altered kinematic and muscular synergies structures as well as muscle activation. Also, it weakened the balance and athletic ability of HV patients. KT intervention improved neuromuscular control to provide a better gait performance.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3199-3209"},"PeriodicalIF":4.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10659205","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1109/TNSRE.2024.3451716
Chuncheng Liao;Shiyu Zhao;Jiacai Zhang
Features from EEG microstate models, such as time-domain statistical features and state transition probabilities, are typically manually selected based on experience. However, traditional microstate models assume abrupt transitions between states, and the classification features can vary among individuals due to personal differences. To date, both empirical and theoretical classification results of EEG microstate features have not been entirely satisfactory. Here, we introduce an enhanced feature extraction method that combines Joint label-Common and label-Specific Feature Exploration (JCSFE) with Gaussian Mixture Models (GMM) to explore microstate features. First, GMMs are employed to represent the smooth transitions of EEG spatiotemporal features within microstate models. Second, category-common and category-specific features are identified by applying regularization constraints to linear classifiers. Third, a graph regularizer is used to extract subject-invariant microstate features. Experimental results on publicly available datasets demonstrate that the proposed model effectively encodes microstate features and improves the accuracy of motor imagery recognition across subjects. The primary code is accessible for download from the website: https://github.com/liaoliao3450/GMM-JCSFE .
脑电图微状态模型的特征，如时域统计特征和状态转换概率，通常是根据经验人工选择的。然而，传统的微状态模型假定状态之间的转换是突然的，而且由于个体差异，分类特征也会因人而异。迄今为止，脑电图微状态特征的经验和理论分类结果都不尽如人意。在此，我们介绍一种增强型特征提取方法，该方法结合了联合标签-共性和标签-特定特征探索（Joint label-Common and label-Specific Feature Exploration，JCSFE）和高斯混杂模型（Gaussian Mixture Models，GMM）来探索微状态特征。首先，在微状态模型中采用 GMM 来表示脑电图时空特征的平滑转换。其次，通过对线性分类器应用正则化约束来识别类别共性和类别特异性特征。第三，使用图正则化器提取主体不变的微状态特征。在公开数据集上的实验结果表明，所提出的模型有效地编码了微状态特征，并提高了不同受试者运动图像识别的准确性。主要代码可从以下网站下载：https://github.com/liaoliao3450/GMM-JCSFE。
{"title":"Motor Imagery Recognition Based on GMM-JCSFE Model","authors":"Chuncheng Liao;Shiyu Zhao;Jiacai Zhang","doi":"10.1109/TNSRE.2024.3451716","DOIUrl":"10.1109/TNSRE.2024.3451716","url":null,"abstract":"Features from EEG microstate models, such as time-domain statistical features and state transition probabilities, are typically manually selected based on experience. However, traditional microstate models assume abrupt transitions between states, and the classification features can vary among individuals due to personal differences. To date, both empirical and theoretical classification results of EEG microstate features have not been entirely satisfactory. Here, we introduce an enhanced feature extraction method that combines Joint label-Common and label-Specific Feature Exploration (JCSFE) with Gaussian Mixture Models (GMM) to explore microstate features. First, GMMs are employed to represent the smooth transitions of EEG spatiotemporal features within microstate models. Second, category-common and category-specific features are identified by applying regularization constraints to linear classifiers. Third, a graph regularizer is used to extract subject-invariant microstate features. Experimental results on publicly available datasets demonstrate that the proposed model effectively encodes microstate features and improves the accuracy of motor imagery recognition across subjects. The primary code is accessible for download from the website: \u0000<uri>https://github.com/liaoliao3450/GMM-JCSFE</uri>\u0000.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3348-3357"},"PeriodicalIF":4.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10659131","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142107014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-28DOI: 10.1109/TNSRE.2024.3451015
Zhaohui Li;Ruoqing Zhang;Wenjing Li;Meng Li;Xiaogang Chen;Hongyan Cui
The hybrid brain-computer interface (BCI) is verified to reduce disadvantages of conventional BCI systems. Transcranial electrical stimulation (tES) can also improve the performance and applicability of BCI. However, enhancement in BCI performance attained solely from the perspective of users or solely from the angle of BCI system design is limited. In this study, a hybrid BCI system combining MI and SSVEP was proposed. Furthermore, transcranial alternating current stimulation (tACS) was utilized to enhance the performance of the proposed hybrid BCI system. The stimulation interface presented a depiction of grabbing a ball with both of hands, with left-hand and right-hand flickering at frequencies of 34 Hz and 35 Hz. Subjects watched the interface and imagined grabbing a ball with either left hand or right hand to perform SSVEP and MI task. The MI and SSVEP signals were processed separately using filter bank common spatial patterns (FBCSP) and filter bank canonical correlation analysis (FBCCA) algorithms, respectively. A fusion method was proposed to fuse the features extracted from MI and SSVEP. Twenty healthy subjects took part in the online experiment and underwent tACS sequentially. The fusion accuracy post-tACS reached 90.25% ± 11.40%, which was significantly different from pre-tACS. The fusion accuracy also surpassed MI accuracy and SSVEP accuracy respectively. These results indicated the superior performance of the hybrid BCI system and tACS would improve the performance of the hybrid BCI system.
经过验证，混合脑机接口（BCI）可以减少传统BCI系统的缺点。经颅电刺激（tES）也能提高 BCI 的性能和适用性。然而，仅从用户角度或仅从 BCI 系统设计角度实现的 BCI 性能提升是有限的。本研究提出了一种结合 MI 和 SSVEP 的混合 BCI 系统。此外，还利用经颅交变电流刺激（tACS）来增强所提出的混合 BCI 系统的性能。刺激界面呈现出双手抓球的画面，左手和右手以 34 Hz 和 35 Hz 的频率闪烁。受试者观看界面并想象用左手或右手抓球，以完成SSVEP和MI任务。分别使用滤波器组共同空间模式（FBCSP）和滤波器组典型相关分析（FBCCA）算法处理 MI 和 SSVEP 信号。研究人员提出了一种融合方法，用于融合从 MI 和 SSVEP 提取的特征。20 名健康受试者参加了在线实验，并依次接受了 tACS。tACS后的融合准确率达到90.25% ± 11.40%，与tACS前相比有显著差异。融合准确率也分别超过了 MI 准确率和 SSVEP 准确率。这些结果表明了混合生物识别系统的卓越性能，而 tACS 将提高混合生物识别系统的性能。
{"title":"Enhancement of Hybrid BCI System Performance Based on Motor Imagery and SSVEP by Transcranial Alternating Current Stimulation","authors":"Zhaohui Li;Ruoqing Zhang;Wenjing Li;Meng Li;Xiaogang Chen;Hongyan Cui","doi":"10.1109/TNSRE.2024.3451015","DOIUrl":"10.1109/TNSRE.2024.3451015","url":null,"abstract":"The hybrid brain-computer interface (BCI) is verified to reduce disadvantages of conventional BCI systems. Transcranial electrical stimulation (tES) can also improve the performance and applicability of BCI. However, enhancement in BCI performance attained solely from the perspective of users or solely from the angle of BCI system design is limited. In this study, a hybrid BCI system combining MI and SSVEP was proposed. Furthermore, transcranial alternating current stimulation (tACS) was utilized to enhance the performance of the proposed hybrid BCI system. The stimulation interface presented a depiction of grabbing a ball with both of hands, with left-hand and right-hand flickering at frequencies of 34 Hz and 35 Hz. Subjects watched the interface and imagined grabbing a ball with either left hand or right hand to perform SSVEP and MI task. The MI and SSVEP signals were processed separately using filter bank common spatial patterns (FBCSP) and filter bank canonical correlation analysis (FBCCA) algorithms, respectively. A fusion method was proposed to fuse the features extracted from MI and SSVEP. Twenty healthy subjects took part in the online experiment and underwent tACS sequentially. The fusion accuracy post-tACS reached 90.25% ± 11.40%, which was significantly different from pre-tACS. The fusion accuracy also surpassed MI accuracy and SSVEP accuracy respectively. These results indicated the superior performance of the hybrid BCI system and tACS would improve the performance of the hybrid BCI system.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3222-3230"},"PeriodicalIF":4.8,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10654315","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142086099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-28DOI: 10.1109/TNSRE.2024.3450848
Christian Nash;Rajesh Nair;Syed Mohsen Naqvi
Advancements in machine learning offer promising avenues for the identification of ADHD symptoms in adults, an endeavour traditionally encumbered by the intricacies of human behavioural patterns. In this paper, we introduce three innovative dual-stream models. The proposed approach utilises a novel multi-modal dataset recorded for ADHD symptoms detection, leveraging RGB video alongside facial, body posture and hand landmark data. The fusion of these different sub-modalities within video enhances the discriminative capability of the ADHD symptoms detection system. A primary objective was to maintain minimal model depth while achieving competitive performance. Through randomised search cross-validation and a rigorous leave-one-out validation scheme, the proposed model achieves high generalisability and robust symptom identification, suggesting strong potential for application in clinical environments. Evaluation boasts the state-of-the-art performance of the proposed model, demonstrating an accuracy of 98.67%, a precision of 98.01%, and a recall of 98.88%. These metrics attest to the model’s ability to consistently identify ADHD symptoms while maintaining a minimal parameter footprint. This delicate balance provides a significant step forward in behavioural health analytics.
{"title":"Insights Into Detecting Adult ADHD Symptoms Through Advanced Dual-Stream Machine Learning","authors":"Christian Nash;Rajesh Nair;Syed Mohsen Naqvi","doi":"10.1109/TNSRE.2024.3450848","DOIUrl":"10.1109/TNSRE.2024.3450848","url":null,"abstract":"Advancements in machine learning offer promising avenues for the identification of ADHD symptoms in adults, an endeavour traditionally encumbered by the intricacies of human behavioural patterns. In this paper, we introduce three innovative dual-stream models. The proposed approach utilises a novel multi-modal dataset recorded for ADHD symptoms detection, leveraging RGB video alongside facial, body posture and hand landmark data. The fusion of these different sub-modalities within video enhances the discriminative capability of the ADHD symptoms detection system. A primary objective was to maintain minimal model depth while achieving competitive performance. Through randomised search cross-validation and a rigorous leave-one-out validation scheme, the proposed model achieves high generalisability and robust symptom identification, suggesting strong potential for application in clinical environments. Evaluation boasts the state-of-the-art performance of the proposed model, demonstrating an accuracy of 98.67%, a precision of 98.01%, and a recall of 98.88%. These metrics attest to the model’s ability to consistently identify ADHD symptoms while maintaining a minimal parameter footprint. This delicate balance provides a significant step forward in behavioural health analytics.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3378-3387"},"PeriodicalIF":4.8,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10654367","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142086100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-28DOI: 10.1109/TNSRE.2024.3451010
Yassine El Ouahidi;Vincent Gripon;Bastien Pasdeloup;Ghaith Bouallegue;Nicolas Farrugia;Giulia Lioi
We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI. Our main motivation is to propose a simple and performing baseline that achieves high classification accuracy, using only standard ingredients from the literature, to serve as a standard for comparison. The proposed architecture is composed of standard layers, including 1D convolutions, batch normalisations, ReLU activation functions and pooling functions. EEG-SimpleConv architecture is accompanied by a straightforward and tailored training routine, which is subjected to an extensive ablation study to quantify the influence of its components. We evaluate its performance on four EEG Motor Imagery datasets, including simulated online setups, and compare it to recent Deep Learning and Machine Learning approaches. EEG-SimpleConv is at least as good or far more efficient than other approaches, showing strong knowledge-transfer capabilities across subjects, at the cost of a low inference time. We believe that using standard components and ingredients can significantly help the adoption of Deep Learning approaches for BCI. We make the code of the models and the experiments accessible.
{"title":"A Strong and Simple Deep Learning Baseline for BCI Motor Imagery Decoding","authors":"Yassine El Ouahidi;Vincent Gripon;Bastien Pasdeloup;Ghaith Bouallegue;Nicolas Farrugia;Giulia Lioi","doi":"10.1109/TNSRE.2024.3451010","DOIUrl":"10.1109/TNSRE.2024.3451010","url":null,"abstract":"We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI. Our main motivation is to propose a simple and performing baseline that achieves high classification accuracy, using only standard ingredients from the literature, to serve as a standard for comparison. The proposed architecture is composed of standard layers, including 1D convolutions, batch normalisations, ReLU activation functions and pooling functions. EEG-SimpleConv architecture is accompanied by a straightforward and tailored training routine, which is subjected to an extensive ablation study to quantify the influence of its components. We evaluate its performance on four EEG Motor Imagery datasets, including simulated online setups, and compare it to recent Deep Learning and Machine Learning approaches. EEG-SimpleConv is at least as good or far more efficient than other approaches, showing strong knowledge-transfer capabilities across subjects, at the cost of a low inference time. We believe that using standard components and ingredients can significantly help the adoption of Deep Learning approaches for BCI. We make the code of the models and the experiments accessible.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3338-3347"},"PeriodicalIF":4.8,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10654330","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142086096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：