Heart sound classification algorithm based on time-frequency combination feature and adaptive fuzzy neural network / 生物医学工程学杂志

Feature extraction methods and classifier selection are two critical steps in heart sound classification. To capture the pathological features of heart sound signals, this paper introduces a feature extraction method that combines mel-frequency cepstral coefficients (MFCC) and power spectral density (PSD). Unlike conventional classifiers, the adaptive neuro-fuzzy inference system (ANFIS) was chosen as the classifier for this study. In terms of experimental design, we compared different PSDs across various time intervals and frequency ranges, selecting the characteristics with the most effective classification outcomes. We compared four statistical properties, including mean PSD, standard deviation PSD, variance PSD, and median PSD. Through experimental comparisons, we found that combining the features of median PSD and MFCC with heart sound systolic period of 100-300 Hz yielded the best results. The accuracy, precision, sensitivity, specificity, and F1 score were determined to be 96.50%, 99.27%, 93.35%, 99.60%, and 96.35%, respectively. These results demonstrate the algorithm's significant potential for aiding in the diagnosis of congenital heart disease.

Automatic sleep staging based on power spectral density and random forest / 生物医学工程学杂志

The method of using deep learning technology to realize automatic sleep staging needs a lot of data support, and its computational complexity is also high. In this paper, an automatic sleep staging method based on power spectral density (PSD) and random forest is proposed. Firstly, the PSDs of six characteristic waves (K complex wave, δ wave, θ wave, α wave, spindle wave, β wave) in electroencephalogram (EEG) signals were extracted as the classification features, and then five sleep states (W, N1, N2, N3, REM) were automatically classified by random forest classifier. The whole night sleep EEG data of healthy subjects in the Sleep-EDF database were used as experimental data. The effects of using different EEG signals (Fpz-Cz single channel, Pz-Oz single channel, Fpz-Cz + Pz-Oz dual channel), different classifiers (random forest, adaptive boost, gradient boost, Gaussian naïve Bayes, decision tree, K-nearest neighbor), and different training and test set divisions (2-fold cross-validation, 5-fold cross-validation, 10-fold cross-validation, single subject) on the classification effect were compared. The experimental results showed that the effect was the best when the input was Pz-Oz single-channel EEG signal and the random forest classifier was used, no matter how the training set and test set were transformed, the classification accuracy was above 90.79%. The overall classification accuracy, macro average F1 value, and Kappa coefficient could reach 91.94%, 73.2% and 0.845 respectively at the highest, which proved that this method was effective and not susceptible to data volume, and had good stability. Compared with the existing research, our method is more accurate and simpler, and is suitable for automation.

Research on electroencephalogram power spectral density of stroke patients under transcranial direct current stimulation / 生物医学工程学杂志

Transcranial direct current stimulation (tDCS) has become a new method of post-stroke rehabilitation treatment and is gradually accepted by people. However, the neurophysiological mechanism of tDCS in the treatment of stroke still needs further study. In this study, we recruited 30 stroke patients with damage to the left side of the brain and randomly divided them into a real tDCS group (15 cases) and a sham tDCS group (15 cases). The resting EEG signals of the two groups of subjects before and after stimulation were collected, then the difference of power spectral density was analyzed and compared in the band of delta, theta, alpha and beta, and the delta/alpha power ratio (DAR) was calculated. The results showed that after real tDCS, delta band energy decreased significantly in the left temporal lobes, and the difference was statistically significant ( P < 0.05); alpha band energy enhanced significantly in the occipital lobes, and the difference was statistically significant ( P < 0.05); the difference of theta and beta band energy was not statistically significant in the whole brain region ( P > 0.05). Furthermore, the difference of delta, theta, alpha and beta band energy was not statistically significant after sham tDCS ( P > 0.05). On the other hand, the DAR value of stroke patients decreased significantly after real tDCS, and the difference was statistically significant ( P < 0.05), and there was no significant difference in sham tDCS ( P > 0.05). This study reveals to a certain extent the neurophysiological mechanism of tDCS in the treatment of stroke.

The sedative effect of electro-acupuncture on healthy people and its possible mechanism using electroencephalogram power spectral density / 西安交通大学学报(医学版)

Objective: To explore the sedative effect of electro-acupuncture on healthy people and its possible mechanism by using EEG power spectral density. Methods: Totally 12 healthy subjects were stimulated by electro-acupuncture at bilateral Zusanli (ST36), Shenmen (HT7) and Sanyinjiao (SP6) acupoints. The multichannel EEG signals induced by electro-acupuncture in electroacupuncture-free state (resting state) and electro-acupuncture state were recorded for 30 minutes respectively. The sedation level of the subjects was monitored by bispectral index monitor (BIS). The power spectrum density (PSD) was employed to analyze the power changes of EEG during electro-acupuncture. Results: Compared with that of the resting state, the BIS value of electro-acupuncture state decreased significantly (P<0.05), the δ band power of EEG signal increased significantly (P<0.05), the α band power of EEG signal decreased significantly (P<0.05). Conclusion: Electro-acupuncture alone can produce sedative effect. The change of EEG activity and the increase of slow wave activity may be related to the sedative effect.

Differential Effect of Light Emitting Diode Light on Electroencephalographic Oscillations in Young and Old Healthy Subjects

OBJECTIVES: To investigate brain oscillatory characteristics according to brightness and color temperature of light emitting diode (LED) light in young and elderly subjects. METHODS: We analyzed 22 young (age, 29.0±5.2 years) and 23 elderly (age, 64.8±4.5 years) healthy subjects. A LED light source was used with a combination of two color temperature (6,500 K vs. 3,000 K) and two brightness (700 lx vs. 300 lx) conditions. Participants were exposed to each light condition in relaxed wakefulness. Then, we analyzed power spectral density and functional connectivity from eye-open electroencephalography. RESULTS: A main effect of brightness on delta (p=0.044) and theta (p=0.038) power was significant in the elderly subjects. Bright light enhanced delta and theta power in the frontal region. By contrast, power spectral density of young subjects was affected by color temperature; high color temperature significantly increased beta-band power of the central region (p=0.034). Regarding functional connectivity, a significant effect of color temperature was observed in delta (p=0.006) and beta (p=0.046) frequencies. High color temperature light enhanced beta connectivity of young subjects (p=0.007), while not affecting that of elderly subjects (p=0.979). CONCLUSIONS: The present study demonstrated that spectral power and functional connectivity as well as subjective feelings are affected by the brightness and color temperature of LED light. These results might help us to understand the neurophysiological effects of light and identify the optimal indoor lighting conditions for an individual's environment.

The study of the theta oscillation characteristic for working memory in frontal lobe epilepsy / 天津医药

Objective To investigate the characteristic of theta oscillation in patients with frontal lobe epilepsy (FLE) by the analysis of multi-channel electroencephalographs (EEGs) during rest state and working memory(WM) maintenance. Methods The 19 FLE patients and 17 healthy subjects underwent EEG recording with 34-channel EEG machine during visual working memory task performance. The differences of behavioral results were analyzed between FLE group and controls. Short-time Fourier transform was used to calculate the power spectral density of different frequency bands in 34 channels. The theta power values during the retention period of working memory and rest state were compared between two groups. Results Compared with controls, reaction time of FLE increased significantly (P<0.01) and accuracy decreased (P<0.05). The power spectral density of theta band for FLE increased both in Fz and frontal region during rest state (P<0.01). Compared with controls, the power spectral density of theta oscillation decreased significantly in the frontal region for FLE during WM maintenance. Conclusion Our results suggest that working memory in patients with FLE was impaired. The absence of theta oscillation during the WM delayde period may provide a possible neural mechanism for the working memory dysfunction in FLE.

Power spectrum density analysis for the influence of complete denture on the brain function of edentulous patients - pilot study

PURPOSE: This pilot study was to find the influence of complete denture on the brain activity and cognitive function of edentulous patients measured through Electroencephalogram (EEG) signals. MATERIALS AND METHODS: The study recruited 20 patients aged from 50 to 60 years requiring complete dentures with inclusion and exclusion criteria. The brain function and cognitive function were analyzed with a mental state questionnaire and a 15-minute analysis of power spectral density of EEG alpha waves. The analysis included edentulous phase and post denture insertion adaptive phase, each done before and after chewing. The results obtained were statistically evaluated. RESULTS: Power Spectral Density (PSD) values increased from edentulous phase to post denture insertion adaption phase. The data were grouped as edentulous phase before chewing (EEG p1-0.0064), edentulous phase after chewing (EEG p2-0.0073), post denture insertion adaptive phase before chewing (EEG p3-0.0077), and post denture insertion adaptive phase after chewing (EEG p4-0.0096). The acquired values were statistically analyzed using paired t-test, which showed statistically significant results (P<.05). CONCLUSION: This pilot study showed functional improvement in brain function of edentulous patients with complete dentures rehabilitation.

A Comparative Analysis of Heart Rate Variability of Electrocardiogram and Pulse-wave Using Time Series / 대한의료정보학회지

The estimation of power spectrum based on the heart rate variability is studied to evaluate the variation of the tension and physiological workloads by the activity of the autonomic system as evaluation parameter. In this paper, we made an attempt to apply the pulse wave to estimate the variation of physiological condition quantitatively instead of the evaluation of power spectrum of HRV through electrocardiogram in the past by comparing and analyzing time series data for the similarity of the heart rate of electrocardiogram and pulse wave. For the similarity of two signals, we can get the likeness by calculating an average, a variance, a correlation coefficient, and the power peak and the shape of power spectral density from the time series data. In the experimental result, it is shown that same subject have a similar variation of time series and power spectrum density for electrocardiogram and pulse wave. As a result, it is expected to estimate a change of the tension and physical condition quantitatively through the evaluation of a power ~pectrum of HRV by Pulse Wave in the future.

Comparison between Myocardial Infarction and Congestive Heart Failure Using by Heart Rate Variability Analysis of 24 hours Holter Monitoring

OBJECTIVES: Power spectrum analysis decomposes the heart rate signal into its frequency components and facilitates separation of sympathetic (low frequency) and parasympathetic (high frequency) activity. In congestive heart failure, augmented sympathetic tone and decreased parasympathetic tone were found. Autonomic nervous system was normalized 6 months after myocardial infarction. So we compared the autonomic nervous system activity by the heart rate variability in congestive heart failure and old myocardial infarction. METHODS: The protocol involved 20 healthy subjects (Group 1), 5 congestive heart failure patients not caused by myocardial infarction (Group 2), 4 congestive heart failure patients due to myocardial infarction and 11 old myocardial infarction patients without heart failure. We took 24 hour Holter monitoring by Del Mar Avionic tape recorder. All Holter tapes were analyzed with use of Model 563 Stratascan Holter Analysis System. We computed power spectra on each 256 sec segment of each hour during 24 hour recording. So, RR interval, SD of RR interval by time domain, and LF, HF, LF/HF ratio, Total PSD by frequency domain were measured. RESULTS: In congestive heart failure, nocturnal HF peak and diurnal variation of LF/HF ratio was decreased relative to healthy subjects. Nocturnal HF peak in old myocardial infarction was not visualized. All of LF, HF and Total PSD in congestive heart failure and old myocardial infarction patients relative to healthy subjects. CONCLUSION: On heart rate variability analysis using by 24 hour Holter monitoring, abnormal autonomic nervous activity was demonstrated in congestive heart failure and old myocardial infarction patients relative to healthy subjects.