Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification.Signal-processing methods can ex...Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification.Signal-processing methods can extract the potent time-frequency-domain characteristics of signals;however,the performance of conventional characteristics-based classification needs to be improved.Widely used deep learning algorithms(e.g.,convolutional neural networks(CNNs))can conduct classification by extracting high-dimensional data features,with outstanding performance.Hence,combining the advantages of signal processing and deep-learning algorithms can significantly enhance vibration recognition performance.A novel vibration recognition method based on signal processing and deep neural networks is proposed herein.First,environmental vibration signals are collected;then,signal processing is conducted to obtain the coefficient matrices of the time-frequency-domain characteristics using three typical algorithms:the wavelet transform,Hilbert-Huang transform,and Mel frequency cepstral coefficient extraction method.Subsequently,CNNs,long short-term memory(LSTM)networks,and combined deep CNN-LSTM networks are trained for vibration recognition,according to the time-frequencydomain characteristics.Finally,the performance of the trained deep neural networks is evaluated and validated.The results confirm the effectiveness of the proposed vibration recognition method combining signal preprocessing and deep learning.展开更多
Background The renin-angiotensin-aldosterone system （RAAS） is important for the development of essential hypertension, and many antihypertensive drugs target it. This study was undertaken to determine whether polymo...Background The renin-angiotensin-aldosterone system （RAAS） is important for the development of essential hypertension, and many antihypertensive drugs target it. This study was undertaken to determine whether polymorphisms in the renin-angiotensin-aldosterone system are related to the blood pressure （BP） response to diuretic treatment in a Chinese Han ethnic population. Methods Fifty-four patients with essential hypertension received hydrochlorothiazide （12.5 mg, once daily） as monotherapy for four weeks. Seven polymorphisms in RAAS genes were genotyped by gene chip technology. The relationship between these polymorphisms and the change in blood pressure was observed after the 4-week treatment. Results The patients with angiotensinogen （AGT） -6G allele showed a greater reduction in diastolic BP （P=- 0.025） and mean BP （P=-0.039） than those carrying AA genotype. Patients carrying aldosterone synthase （CYP11B2） CC genotype exhibited a greater BP reduction than those carrying CT and TT genotypes （systolic BP： P=- 0.030; diastolic BP： P=- 0.026; mean BP： P=-0.003）. In addition, patients with a combination of CYP11B2 CC genotype and angiotensin converting enzyme （ACE） D allele might have a more pronounced reduction of systolic BP than those with any other genotypic combinations of the two genes （P=0.007）. Conclusions AGT-6G allele, CYP11B2 -344CC genotype and its combination with ACE D allele are associated with BP response to hydrochlorothiazide treatment. Larger studies are warranted to validate this finding.展开更多
文摘Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification.Signal-processing methods can extract the potent time-frequency-domain characteristics of signals;however,the performance of conventional characteristics-based classification needs to be improved.Widely used deep learning algorithms(e.g.,convolutional neural networks(CNNs))can conduct classification by extracting high-dimensional data features,with outstanding performance.Hence,combining the advantages of signal processing and deep-learning algorithms can significantly enhance vibration recognition performance.A novel vibration recognition method based on signal processing and deep neural networks is proposed herein.First,environmental vibration signals are collected;then,signal processing is conducted to obtain the coefficient matrices of the time-frequency-domain characteristics using three typical algorithms:the wavelet transform,Hilbert-Huang transform,and Mel frequency cepstral coefficient extraction method.Subsequently,CNNs,long short-term memory(LSTM)networks,and combined deep CNN-LSTM networks are trained for vibration recognition,according to the time-frequencydomain characteristics.Finally,the performance of the trained deep neural networks is evaluated and validated.The results confirm the effectiveness of the proposed vibration recognition method combining signal preprocessing and deep learning.
文摘Background The renin-angiotensin-aldosterone system （RAAS） is important for the development of essential hypertension, and many antihypertensive drugs target it. This study was undertaken to determine whether polymorphisms in the renin-angiotensin-aldosterone system are related to the blood pressure （BP） response to diuretic treatment in a Chinese Han ethnic population. Methods Fifty-four patients with essential hypertension received hydrochlorothiazide （12.5 mg, once daily） as monotherapy for four weeks. Seven polymorphisms in RAAS genes were genotyped by gene chip technology. The relationship between these polymorphisms and the change in blood pressure was observed after the 4-week treatment. Results The patients with angiotensinogen （AGT） -6G allele showed a greater reduction in diastolic BP （P=- 0.025） and mean BP （P=-0.039） than those carrying AA genotype. Patients carrying aldosterone synthase （CYP11B2） CC genotype exhibited a greater BP reduction than those carrying CT and TT genotypes （systolic BP： P=- 0.030; diastolic BP： P=- 0.026; mean BP： P=-0.003）. In addition, patients with a combination of CYP11B2 CC genotype and angiotensin converting enzyme （ACE） D allele might have a more pronounced reduction of systolic BP than those with any other genotypic combinations of the two genes （P=0.007）. Conclusions AGT-6G allele, CYP11B2 -344CC genotype and its combination with ACE D allele are associated with BP response to hydrochlorothiazide treatment. Larger studies are warranted to validate this finding.
