Buggeisaksen2312

Biofeedback systems sense different physiological activities and help with gaining self-awareness. Understanding music's impact on the arousal state is of great importance for biofeedback stress management systems. In this study, we investigate a cognitive-stress-related arousal state modulated by different types of music. During our experiments, each subject was presented with neurological stimuli that elicit a cognitive-stress-related arousal response in a working memory experiment. Moreover, this cognitive-stress-related arousal was modulated by calming and vexing music played in the background. Electrodermal activity and functional near-infrared spectroscopy (fNIRS) measurements both contain information related to cognitive arousal and were collected in our study. By considering various fNIRS features, we selected three features based on variance, root mean square, and local fNIRS peaks as the most informative fNIRS observations in terms of cognitive arousal. The rate of neural impulse occurrence underlying EDA was taken as a binary observation. To retain a low computational complexity for our decoder and select the best fNIRS-based observations, two features were chosen as fNIRS-based observations at a time. A decoder based on one binary and two continuous observations was utilized to estimate the hidden cognitive-stress-related arousal state. This was done by using a Bayesian filtering approach within an expectation-maximization framework. Our results indicate that the decoded cognitive arousal modulated by vexing music was higher than calming music. Bromopyruvic Among the three fNIRS observations selected, a combination of observations based on root mean square and local fNIRS peaks resulted in the best decoded states for our experimental settings. This study serves as a proof of concept for utilizing fNIRS and EDA measurements to develop a low-dimensional decoder for tracking cognitive-stress-related arousal levels.Biomarkers are one of the primary medical signs to facilitate the early detection of Alzheimer's disease. The small beta-amyloid (Aβ) peptide is an important indicator for the disease. However, current methods to detect Aβ pathology are either invasive (lumbar puncture) or quite costly and not widely available (amyloid PET). Thus a less invasive and cheaper approach is demanded. MRI which has been used widely in preclinical AD has recently shown the capability to predict brain Aβ positivity. This motivates us to develop a method, SDF sparse convolution, taking MRI to predict Aβ positivity. We obtain subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and use our method to discriminate Aβ positivity. Theoretically, we provide analysis towards the understanding of what the network has learned. Empirically, it shows strong performance on par or even better than state of the art.Local field potentials (LFPs) have better long-term stability compared with spikes in brain-machine interfaces (BMIs). Many studies have shown promising results of LFP decoding, but the high-dimensional feature of LFP still hurdle the development of the BMIs to low-cost. In this paper, we proposed a framework of a 1D convolution neural network (CNN) to reduce the dimensionality of the LFP features. For evaluating the performance of this architecture, the reduced LFP features were decoded to cursor position (Center-out task) by a Kalman filter. The Principal components analysis (PCA) was also performed as a comparison. The results showed that the CNN model could reduce the dimensionality of LFP features to a smaller size without significant performance loss. The decoding result based on the CNN features outperformed that based on the PCA features. Moreover, the reduced features by CNN also showed robustness across different sessions. These results demonstrated that the LFP features reduced by the CNN model achieved low cost without sacrificing high-performance and robustness, suggesting that this method could be used for portable BMI systems in the future.Brain activation patterns vary according to the tasks performed by the subject. Neuroimaging techniques can be used to map the functioning of the cortex to capture brain activation patterns. Functional near-infrared spectroscopy (fNIRS) is a neuroimaging technique increasingly used for task classification based on brain activation patterns. fNIRS can be widely used in population studies due to the technology's economic,non-invasive, and portable nature. The multidimensional and complex nature of fNIRS data makes it ideal for deep learning algorithms for classification. Most deep learning algorithms need a large amount of data to be appropriately trained. Generative networks can be used in such cases where a substantial amount of data is required. Still, the collection is complex due to various constraints. Conditional Generative Adversarial Networks (CGAN) can generate artificial samples of a specific category to improve the deep learning classifier's accuracy when the sample size is insufficient. The proposed system uses an LSTM based CGAN with an LSTM classifier to enhance the accuracy through data augmentation. The system can determine whether the subject's task is a Left Finger Tap, Right Finger Tap, or Foot Tap based on the fNIRS data patterns. The authors obtained a task classification accuracy of 90.2% for the LSTM based GAN combination.Clinical relevance- Acquiring medical data present practical difficulties due to time, money, labor, and economic cost. The deep learning-based model can better perform medical image classification than hand-crafted features when dealing with many data. GAN-based networks can be valuable in the medical field where collecting extensive data is not feasible. GAN-generated synthetic data can be used to improve the classification accuracy of classification systems.The success of deep learning in computer vision has inspired the scientific community to explore new analysis methods. Within the field of neuroscience, specifically in electrophysiological neuroimaging, researchers are starting to explore leveraging deep learning to make predictions on EEG data. Research remains open on the network architecture and the feature space that is most effective for EEG decoding. This paper compares deep learning using minimally processed EEG raw data versus deep learning using EEG spectral features using two different deep convolutional neural architectures. One of them from Putten et al. (2018) is tailored to process raw data; the other was derived from the VGG16 vision network (Simonyan and Zisserman, 2015) which is designed to process EEG spectral features. We apply them to classify sex on 24-channel EEG from a large corpus of 1,574 participants. Not only do we improve on state-of-the-art classification performance for this type of classification problem, but we also show that in all cases, raw data classification leads to superior performance as compared to spectral EEG features. Interestingly we show that the neural network tailored to process EEG spectral features has increased performance when applied to raw data classification. Our approach suggests that the same convolutional networks used to process EEG spectral features yield superior performance when applied to EEG raw data.Suicide is a global health problem, and early and accurate identification of suicide attempt individuals has very important clinical significance. Thus the exploration of neurobiological mechanisms underlying suicidal behavior is crucial for systematically preventing suicide. However, the neurophysiological biomarkers for identifying affective disorders with suicidal attempt are remain unknown. Here, we recruited 28 patients with mental disorders from Tianjin Anding Hospital, and the subjects were divided into suicide attempt group (SA=14) and non suicide attempt group (NSA=14) according to whether they had attempted suicide. We also recruited 14 healthy subjects matched with age and sex ratio as healthy control group (HC=14). By recording the electroencephalogram(EEG) data of 60 electrodes in resting state for eight minutes (four minutes with open eyes and four minutes with close eyes), the absolute power of five frequency bands( delta(0.5-4Hz), theta(4-8Hz), alpha(8-13Hz), beta (13-30Hz), gamma(30-65Hz)) weral regions may be used as a potential clinical biomarker for preventing suicide.Deep learning-based cuff-less blood pressure (BP) estimation methods have recently gained increased attention as they can provide accurate BP estimation with only one physiological signal as input. In this paper, we present a simple and effective method for cuff-less BP estimation by training a small-scale convolutional neural network (CNN), modified from LeNet-5, with images created from short segments of the photoplethysmogram (PPG) signal via visibility graph (VG). Results show that the trained modified LeNet-5 model achieves an error performance of 0.184±7.457 mmHg for the systolic BP (SBP), and 0.343±4.065 mmHg for the diastolic BP (DBP) in terms of the mean error (ME) and the standard deviation (SD) of error between the estimated and reference BP. Both the SBP and the DBP accuracy rank grade A under the British Hypertension Society (BHS) protocol, demonstrating that our proposed method is an accurate way for cuff-less BP estimation.In this paper, an algorithm designed to detect characteristic cough events in audio recordings is presented, significantly reducing the time required for manual counting. Using time-frequency representations and independent subspace analysis (ISA), sound events that exhibit characteristics of coughs are automatically detected, producing a summary of the events detected without the need for a pre-trained model. Using a dataset created from publicly available audio recordings, this algorithm has been tested on a variety of synthesized audio scenarios representative of those likely to be encountered by subjects undergoing an ambulatory cough recording, achieving a true positive rate of 76% with an average of 2.85 false positives per minute.The estimation of Event-Related Potentials (ERPs) from the ambient EEG is a difficult task, usually achieved through the synchronous averaging of an extensive series of trials. However, this technique has some caveats the ERPs have to be strictly time-locked with similar shape, i.e. emitted with the same latency and the same profile, with minor fluctuations of their amplitudes. Also, the method requires a huge number of valid trials (~100) to efficiently raise the ERPs from the EEG trials. In the case of cognitive ERPs, as with the N400, the delivered stimulus has to be different for each trial, the latencies are varying, and the number of available trials is usually low. In this paper, an alternative method, coined Integral Shape Averaging (ISA) and its derivatives are detailed. ISA is robust to varying latencies and affine transforms of shape. Furthermore, a new method coined ISAD can be derived to extract ERPs even from a single trial experiment. The aim here is to illustrate the potential of ISAD for N400 component extraction on real EEG data, with emphasis on its general applicability for ERPs computation and its major assets like reduced experimental protocol. Some insights are also given on its potential use to study ERP variability, through shape and latency.Clinical Relevance- The proposed algorithm aims to be a helpful tool in clinical practice to analyze and interpret evoked responses in real experimental settings, especially for particularities in neurology.