Forensic Pathological Diagnosis of Acute and Old Myocardial Infarction Using Fourier Transform Infrared Spectroscopy / 法医学杂志

OBJECTIVES@#Fourier transform infrared spectroscopy (FTIR) was used to analyze myocardial infarction tissues at different stages of pathological change to achieve the forensic pathology diagnosis of acute and old myocardial infarction.@*METHODS@#FTIR spectra data of early ischemic myocardium, necrotic myocardium, and myocardial fibrous tissue in the left ventricular anterior wall of the sudden death group of atherosclerotic heart disease and the myocardium of the normal control group were collected using hematoxylin-eosin (HE) and immunohistochemistry (IHC) staining as a reference, and the data were analyzed using multivariate statistical analysis.@*RESULTS@#The mean normalized spectra of control myocardium, early ischemic myocardium and necrotic myocardium were relatively similar, but the mean second derivative spectra were significantly different. The peak intensity of secondary structure of proteins in early ischemic myocardium was significantly higher than in other types of myocardium, and the peak intensity of the α-helix in necrotic myocardium was the lowest. The peaks of amide Ⅰ and amide Ⅱ in the mean normalized spectra of myocardial fibrous tissue significantly shifted towards higher wave numbers, the peak intensities of amide Ⅱ and amide Ⅲ were higher than those of other types of myocardium, and the peak intensities at 1 338, 1 284, 1 238 and 1 204 cm-1 in the mean second derivative spectra were significantly enhanced. Principal component analysis (PCA) and partial least square-discriminant analysis (PLS-DA) showed that FTIR could distinguish different types of myocardium.@*CONCLUSIONS@#FTIR technique has the potential to diagnose acute and old myocardial infarction, and provides a new basis for the analysis of the causes of sudden cardiac death.

Metabonomics Analysis of Brain Stem Tissue in Rats with Primary Brain Stem Injury Caused Death / 法医学杂志

OBJECTIVES@#To explore the potential biomarkers for the diagnosis of primary brain stem injury (PBSI) by using metabonomics method to observe the changes of metabolites in rats with PBSI caused death.@*METHODS@#PBSI, non-brain stem brain injury and decapitation rat models were established, and metabolic maps of brain stem were obtained by LC-MS metabonomics method and annotated to the HMDB database. Partial least square-discriminant analysis (PLS-DA) and random forest methods were used to screen potential biomarkers associated with PBSI diagnosis.@*RESULTS@#Eighty-six potential metabolic markers associated with PBSI were screened by PLS-DA. They were modeled and predicted by random forest algorithm with an accuracy rate of 83.3%. The 818 metabolic markers annotated to HMDB database were used for random forest modeling and prediction, and the accuracy rate was 88.9%. According to the importance in the identification of cause of death, the most important metabolic markers that were significantly up-regulated in PBSI group were HMDB0038126 (genipinic acid, GA), HMDB0013272 (N-lauroylglycine), HMDB0005199 [(R)-salsolinol] and HMDB0013645 (N,N-dimethylsphingosine).@*CONCLUSIONS@#GA, N-lauroylglycine, (R)-salsolinol and N,N-dimethylsphingosine are expected to be important metabolite indicators in the diagnosis of PBSI caused death, thus providing clues for forensic medicine practice.

Using signalling theory to assess the Government of Ghana's risk communication during the COVID-19 pandemic

Background: The proliferation of information through social media and on other communication networks during the corona virus disease 2019 (COVID-19) era altered information transfer in many countries. The content of the messages from government officials, media coverage and alternative narratives, affected the level of compliance in adhering to the various health protocols amongst the public. Aim: This article aimed to determine the relationship between the message used, media coverage, alternative narratives, the public's attitude towards staying at home and their commitment to stay at home during the COVID-19 pandemic campaign period in Ghana. Setting: A total of 352 respondents was sampled from the Kumasi metropolis. Methods: A survey sample strategy and a convenience sampling technique were used while structural equation modelling with Partial least square (PLS) version 3.0 was used for the analysis. Results: The study revealed that the nature of media coverage employed and the alternative narratives had a significant positive effect on the attitude of the respondents, whilst the content of the message had insignificant effects on the attitude of the public. Finally, the attitude of the people had a significant positive influence on their respective commitment to stay home. Conclusion: Developing countries in Africa need to fight pandemics using purely subsidised health officials or directorates rather than have government-appointed health experts and officials spearheading activities during a pandemic.

Inferring Postmortem Submersion Interval in Rats Found in Water Based on Vitreous Humor Metabolites / 法医学杂志

OBJECTIVES@#The metabolomics technique of LC-MS/MS combined with data analysis was used to detect changes and differences in metabolic profiles in the vitreous humor of early rat carcasses found in water, and to explore the feasibility of its use for early postmortem submersion interval (PMSI) estimation and the cause of death determination.@*METHODS@#The experimental model was established in natural lake water with 100 SD rats were randomly divided into a drowning group (n=50) and a postmortem (CO2 suffocation) immediately submersion group (n=50). Vitreous humor was extracted from 10 rats in each group at 0, 6, 12, 18 and 24 h postmortem for metabolomics analyses, of which 8 were used as the training set to build the model, and 2 were used as test set. PCA and PLS multivariate statistical analysis were performed to explore the differences in metabolic profiles among PMSI and causes of death in the training set samples. Then random forest (RF) algorithm was used to screen several biomarkers to establish a model.@*RESULTS@#PCA and PLS analysis showed that the metabolic profiles had time regularity, but no differences were found among different causes of death. Thirteen small molecule biomarkers with good temporal correlation were selected by RF algorithm. A simple PMSI estimation model was constructed based on this indicator set, and the data of the test samples showed the mean absolute error (MAE) of the model was 0.847 h.@*CONCLUSIONS@#The 13 metabolic markers screened in the vitreous humor of rat corpses in water had good correlations with the early PMSI. The simplified PMSI estimation model constructed by RF can be used to estimate the PMSI. Additionally, the metabolic profiles of vitreous humor cannot be used for early identification of cause of death in water carcasses.

Preliminary study on inversion model of radioactive release source terms / 中国辐射卫生

Objective Based on the monitoring data, Gaussian plume model and optimization algorithm, the inversion model of radioactive release source term was preliminarily studied. Methods By comparing the application conditions and performance of several optimization algorithms, the accuracy of source term inversion results of different algorithms under the same conditions was compared and verified. Results The preliminary study of radioactive release source term inversion model shows that it is feasible to use the least square method to optimize the inversion model based on Gaussian plume. The accuracy of the optimized model is 0.92 times of the measured value for flat terrain, and 1.5 times of the measured value for complex terrain, whose error is relatively large because of the limitation of the model itself. Conclusion The results show that the optimized source term inversion model based on Gaussian plume and least square method can better meet the needs of nuclear accident consequence assessment and emergency decision-making in terms of computational performance and accuracy.

Nigeria's cocoa exports: a gravity model approach / Exportações de cacau da Nigéria: uma abordagem do modelo gravitacional

ABSTRACT: What are the major factors affecting Nigeria's cocoa export flows? In answering this question, the authors suggest a commodity-specific gravity model with three different analytical approaches, (the Heckman Sample Selection Model, the Generalised Least Square, and the Poisson Pseudo Maximum Likelihood), based on a period of 24 years of panel data for Nigeria and it's 36 importing partners to estimate the models. The results showed that GDP, exchange rate policy, WTO, EU, and colonial link are positively associated with the Nigerian cocoa export flows. Further, the negative impact of the GDP per capita, landlocked, distance, AU, and ECOWAS are observed. The need for the expansion of exports to the trading partners, especially the EU members (Netherlands, Germany, France, United Kingdom, Belgium, Spain, etc.), Canada, Malaysia, and the USA is particularly highlighted. These results are important for the formulation of future trade policy that could boost up the Nigerian cocoa exports. This would eventually contribute to the diversification of the Nigerian exports and also enhance the country's foreign earnings.

RESUMO: Quais são os principais fatores que afetam os fluxos de exportação de cacau da Nigéria? Ao responder a esta pergunta, os autores sugerem um modelo de gravidade específica de mercadoria com três abordagens analíticas diferentes (o Modelo de Seleção de Amostras de Heckman, o Mínimo Quadrado Generalizado e a Pseudo Máxima Verossimilhança de Poisson), com base em um período de 24 anos de dados em painel para a Nigéria e seus parceiros importadores para estimar os modelos. Os resultados mostram que o PIB, a política cambial, a OMC, a UE e a ligação colonial estão positivamente associados aos fluxos de exportação de cacau da Nigéria. Além disso, é observado o impacto negativo do PIB per capita, sem litoral, distância, UA e CEDEAO. Destaca-se a necessidade de ampliação das exportações para os parceiros comerciais, especialmente os membros da UE (Holanda, Alemanha, França, Reino Unido, Bélgica, Espanha, etc.), Canadá, Malásia e Estados Unidos. Esses resultados são importantes para a formulação de uma política comercial futura que possa impulsionar as exportações de cacau nigeriano. Isso acabaria por contribuir para a diversificação das exportações nigerianas e também aumentar as receitas externas do país.

The application of FTIR spectroscopy and chemometrics for classification of Mangosteen extract and its correlation with alpha-mangostin

Alpha-mangostin is the major component in Mangosteen (Garcinia mangostana Linn) pericarp having severalpharmacological activities including reducing blood pressure, antidiabetic, anticancer, and antioxidants. The objectiveof this study was to develop Fourier transform infrared spectroscopy-multivariate calibration of partial least square(PLS) for quantitative analysis of alpha-mangostin and to classify mangosteen pericarp using principal componentanalysis. Mangosteen pericarps from different locations (Java provinces and South Sulawesi, Republic of Indonesia)were extracted using ethanol and were subjected to high performance liquid chromatography (HPLC) for the analysisof alpha-mangostin and Fourier transform infrared (FTIR) spectroscopy measurements. HPLC was used to determinethe levels of alpha-mangostin and used as actual values during FTIR spectroscopy analysis. The prediction of alphamangostin was obtained from the correlation between actual values and FTIR predicted values and facilitated withthe PLS model. The results showed that the wavenumbers region of 3,825–937 cm−1 offered a reliable model with acoefficient correlation (r) value of 0.9927 and root mean square error of calibration of 0.0831%. The validation modelsalso exhibited the accurate and precise results for the prediction of alpha-mangostin with an r-value of 0.9754 androot mean square error of prediction value of 0.174%. Furthermore, the chemometrics of principal component analysisusing variables of absorbances at selected fingerprint (1,000–800 cm−1) could classify mangosteen pericarp fromdifferent regions. FTIR spectroscopy combined with chemometrics offered a reliable method for quality assurance ofmangosteen pericarp

The Region of Interest in Boundary Calibration for Palatal Ru-gae Image of Forensic Identification / 法医学杂志

Objective To examine the method of least-square fitting for calibrating the palatal rugae boundary. Methods According to the distribution of the teeth, the feature points were selected; when they were fit, the boundary of the palatal rugae area was created, thereby constructing a mask. The mask was used to remove the part located outside the boundary and filter out the interference. Three samples were utilized for the ex-periments and analyses to come. Results To evaluate the quantitative results of the fitting curves, the correla-tion coefficients(r)of the samples and the relationship between the actual mean value and ideal mean value was obtained through six fitting processes. The differences between the actual mean and ideal mean were found to be significantly small (from 0.2857 to 2.5000) in the six fitting processes, with the range of r close to 1(from 0.9896 to 0.9995). Conclusion The effect of the cubic polynomial fitting method adopted in this study was stable.The proposed boundary calibration method can effectively locate the palatal rugae boundary and remove the interference area, further promoting the practice of forensic identification.

Dynamic changes of volatile components of Qiai from different harvest time based on GC-MS and chemometrics analysis / 中国中药杂志

Artemisiae Argyi Folium, the dried leaves of Artemisia argyi, has been widely used in traditional Chinese and folk medicines for a long time. Qiai is one of the top-geoherb of Artemisiae Argyi Folium. Qiai contains various bioactive constituents, such as volatile oils, phenolic acids, flavonoids and terpenoids. Phytochemical studies demonstrated that volatile compounds are the main bioactive constituents in Qiai. Try to investigate dynamic changes of volatile components of Qiai from different harvest time and explore the optimum harvest time of Qiai, in this study, the contents of total volatile oils in Qiai collected from five different harvest time were analyzed by steam distillation method. The results showed that the contents of volatile oils of Qiai were higher in the third harvest time(around the Dragon Boat Festival), which is basically consistent with the traditional harvest time. Furthermore, a sensitive method based on gas chromatography-mass spectrometry(GC-MS) was established for qualitative analysis of volatile compounds in Qiai, and a total of thirty volatile compounds were identified. Chemometrics methods including principal component analysis(PCA) and orthogonal partial least-squares discriminate analysis(OPLS-DA) were applied to explore chemical markers and dynamic changes of volatile components in Qiai from different harvest time, and the results indicated that there were obvious differences in the relative contents of volatile compounds of Qiai samples from different harvest time. Eight volatile compounds, including α-terpinene, γ-terpinene, D-camphor, trans-carveol, α-copaene, isobornylisobutyrate, humulene, and caryophyllene oxide were selected as potential chemical markers. Among the eight chemical markers, the relative contents of α-terpinene, γ-terpinene, α-copaene and caryophyllene oxide were higher in the third harvest period(around the Dragon Boat Festival), which is consistent with the contents of total volatile oils. The present study could provide the basis for investigating the optimum harvest time of Qiai, and might be useful for the quality control of this herbal medicine.

Determining Temperature Extreme in Warri City, Niger-Delta Region, Nigeria

Climate change and global warming which is also known as a change in Earth’s overall climate or rising temperature have taken centre stage in international concerns, several fora and treaties have been observed with a view of stemming trend, in rising temperatures. This study evaluated ten years of maximum and minimum annual temperature of Warri in Nigeria between (2005 and 2015) to determine trends and identified extreme fluctuation in temperature. Data used for this study were sourced from the Nigerian Meteorological Agency’s Zonal Office, Warri. An objective method for determining temperature extreme has been used. Least square linear regression equation has been used to estimate temperature that would be equalled or surpassed 1%, 5% and 10% of the hours at any given location during the warmest and coldest months of the year. These equations are based on an index calculated from the three readily available parameters; the mean monthly temperature, the mean daily maximum temperature for the month and the mean daily minimum temperature for the month. The warmest month in Warri was March with a mean monthly temperature of 33.9 while the coldest month was July with mean monthly of 25.8.

HPLC fingerprints research on decoction pieces of Citri Reticulatae Pericarpium based on chemometrics methods combined with orthogonal partial least square discriminate analysis / 中草药

Objective To establish an HPLC method for the fingerprints analysis of decoction pieces of tangerine peel, so as to provide reference for the quality control of it. Methods Fingerprints of 17 batches of decoction pieces of tangerine peel were established by HPLC and evaluated by cluster analysis (CA), principal component analysis (PCA) and orthogonal partial least square discriminate analysis (OPLS-DA). Results The method of fingerprint of decoction pieces of tangerine peel was established, the similarities were greater than 0.9. There were 25 common peaks in the HPLC fingerprint, of which variable importance projection (VIP) of 14 peaks were greater than 1. Compared with the spectrogram of reference substances, peak 13 was narirutin, peak 14 was hesperidin, peak 23 was nobiletin, peak 24 was 3,5,6,7,8,3’,4’-heptamethoxy flavone, and peak 25 was hesperetin. Conclusion This simple and reliable method can be used for the identification and quality control of decoction pieces of Citri Reticulatae Pericarpium.

Hplc fingerprint and chemical pattern recognition of valeriana jatamansi / 中国药学杂志

OBJECTIVE: To establish the HPLC fingerprint of Valeriana jatamansi and provide a reference for its effective quality control. METHODS: The HPLC-DAD analysis was performed on Diamonsil C18 column (4.6 mm×250 mm, 5 μm), with acetonitrile (A)-0.1% formic acid (B) solution as the mobile phase for gradient elution, the detection wavelength was set at 327 nm (0-33 min) and 256 nm (33-90 min), the flow rate was 1.0 mL•min-1, and the column temperature was maintained at 30 ℃. The fingerprints of 25 batches of Valeriana jatamansi samples were analyzed by similarity analysis, hierarchical clustering analysis (HCA), principal component analysis (PCA), and orthogonal partial least squares discriminant analysis (PLS-DA). RESULTS: The fingerprints of 25 batches of Valeriana jatamansi samples were established. There were 36 common peaks in the fingerprints and nine common peaks were identified by reference substances. The fingerprints similarity of 18 batches of samples was over 0.9, and the samples were classified into two groups. Six components were the main markers that cause differences in different batches of samples, including valepotriate, acevaltrate, isochlorogenic acid A, and some others. CONCLUSION: HPLC fingerprint combined with recognition of chemical pattern can reflect the intrinsic quality of Valeriana jatamansi, which may provide reference for the quality control and evaluation of Valeriana jatamansi.

Intelligent fetal state assessment based on genetic algorithm and least square support vector machine / 生物医学工程学杂志

Cardiotocography (CTG) is a commonly used technique of electronic fetal monitoring (EFM) for evaluating fetal well-being, which has the disadvantage of lower diagnostic rate caused by subjective factors. To reduce the rate of misdiagnosis and assist obstetricians in making accurate medical decisions, this paper proposed an intelligent assessment approach for analyzing fetal state based on fetal heart rate (FHR) signals. First, the FHR signals from the public database of the Czech Technical University-University Hospital in Brno (CTU-UHB) was preprocessed, and the comprehensive features were extracted. Then the optimal feature subset based on the -nearest neighbor (KNN) genetic algorithm (GA) was selected. At last the classification using least square support vector machine (LS-SVM) was executed. The experimental results showed that the classification of fetal state achieved better performance using the proposed method in this paper: the accuracy is 91%, sensitivity is 89%, specificity is 94%, quality index is 92%, and area under the receiver operating characteristic curve is 92%, which can assist clinicians in assessing fetal state effectively.

Quality research of Puerariae Lobatae Radix from different habitats with UPLC fingerprint and determination of multi-component content / 中国中药杂志

To establish ultra performance liquid chromatography( UPLC) fingerprint of Puerariae Lobatae Radix from different habitats and simultaneously determine the contents of six isoflavonoids. The UPLC fingerprint analysis and content determination were performed on a Waters ACQUITY UPLC BEH C_(18)( 2. 1 mm×50 mm,1. 7 μm) chromatographic column,with acetonitrile-0. 05% formic acid as mobile phase for gradient elution. The detection wavelength was set at 250 nm; the flow rate was 0. 2 mL·min~(-1); the column temperature was 30 ℃ and the injection volume was 2 μL. Similarity evaluation system for chromatographic fingerprint of traditional Chinese medicine( TCM) was adopted; principal component analysis( PCA) and discriminant analysis by partial least square method( PLS-DA) in Simca-P software were used to identify the differential components in samples from three habitats. The similarity was over 0. 90 in 29 batches of samples,indicating good consistency of the samples. The samples were clustered into 3 categories by PCA and PLS-DA,and six differential components such as puerarin apioside,daidzin,and isoflavoues aglycone were found. The determination results of 6 isoflavones,including 3'-hydroxy puerarin,puerarin,3'-methoxy puerarin,puerarin apioside,daidzin,and isoflavoues aglycone,showed that the content of the same component and the fluctuation range between different components were all different among different habitats. The total content of 6 isoflavones from different regions was Anhui 11. 21% >Henan 10. 97% >Shannxi 9. 38%. The establishment of UPLC fingerprint combined with simultaneous determination of 6 active components provides a more comprehensive reference for quality control and quality evaluation of Puerariae Lobatae Radix.

Application Status of Near Infrared Spectroscopy Combined with Chemometrics in Analysis of Traditional Chinese Medicine / 中国实验方剂学杂志

In recent years, near-infrared spectroscopy has developed into an analytical technique widely used in various fields. Because of its advantages of fast, green and non-destructive, it plays an increasingly prominent role in the field of traditional Chinese medicine (TCM) analysis. However, due to the complexity and overlap of spectra, near-infrared spectroscopy needs to be combined with chemometrics for analysis and calculation. The principle, application scope, advantages and limitations of near infrared spectroscopy and chemometrics are summarized in detail, in addition, their combined applications in the identification of the origin, authenticity, processed products, composition prediction and water content detection of TCM are reviewed. The authors discussed and analyzed the joint application of near-infrared spectroscopy and chemometrics in the field of TCM analysis, and summarized the unique advantages of the combined technology in the field of TCM, which had certain guiding significance for medical workers to better use this technology.

Identification of active components in Longxue Tongluo Capsules against ischemic brain injury based on component-activity relationship / 中国中药杂志

Ten fractions(A-J) were prepared by separation of Longxue Tongluo Capsules(LTC) by using silica gel column chromatography and orthogonal experimental design,showing similar chemical profiles with different abundances of peaks.These ten samples were assessed with UHPLC-QE OrbitrapHRMS for 97 common peaks.For the pharmacological activity experiment,three kinds of in vitro cell models including lipopolysaccharide(LPS)-induced BV-2 microglial cells NO release model,oxygen-glucose deprivation/reoxygenation(OGD/R)-treated HUVEC vascular endothelial cells injury model,and OGD/R-treated PC-12 nerve cells injury model were employed to evaluated the bioactivity of each fraction.Based on the contribution of each identified component,grey relation analysis and partial least squares(PLS) analysis were performed to establish component-activity relationship of LTC,identify the potential active components.After that,validation of the potential active components in LTC was carried out by using the same models.The results indicated that 4 phenolic compounds including 7,4'-dihydroxyhomoisoflavanone,loureirin C,4,4'-dihydroxy-2,6-dimethoxydihydrochalcone,and homoisosocotrin-4'-ol,might be the active components for anti-neuroinflammation effect;five phenolic compounds such as 3,5,7,4'-tetrahydroxyhomoisoflavanone,loureirin D,7,4'-dihydroxyhomoisoflavane,and 5,7-dihydroxy-4'-methoxy-8-methyflavane,might have positive effects on the vascular endothelial injury;three phenolic compounds including 5,7,4'-trihydroxyflavanone,7,4'-dihydroxy-5-methoxyhomoisoflavane,and loureirin D,might be the active components in LTC against neuronal injury.

Nondestructive Analysis of Litchi Fruit Quality Using FT-NIR Spectroscopy

A non-destructive optical method based on near-infrared spectroscopy has been used for the evaluation of litchi fruit quality. Diffuse reflectance measurements (12500–3600 cm-1), physical, and biochemical measurements were performed individually on 100 litchi fruits of cv.Shahi cultivar harvested at different ripening stages. Relationships between spectral wavelengths and quality attributes were evaluated by application of chemometric techniques based on partial least squares (PLS) regression. The fruit set was divided into two groups: 60 fruits for calibration and 39 for validation. Good prediction performance was obtained for pH, soluble solids, and titratable acidity with correlation coefficients of 0.96, 0.91 and 0.94 respectively and root mean square errors of prediction of 0.009, 0.291ºBrix and 0.011% malic acid respectively. For the other quality traits such as vitamin C and color the prediction models were not satisfactorily accurate due to the higherror of calibration and prediction.

The Analysis of the Accelerated Degradation Test for Protein-type Biological Standard Substances / 中国药学杂志

OBJECTIVE: To establish a weighted least square method for the accelerated degradation analysis of protein-type biological standard substances.METHODS: A mathematical model was proposed to estimate the parameters of degradation rate constants k at the elevated temperatures based on the Arrhenius or Eyring equation and chemical reaction principles under the suitable assumptions. Hence, it is probably to predict the stability of biological standard at the normal condition by solving the model.RESULTS: According to the experimental data of recombinant human granulocyte colony-stimulating factor and interferon α-2a, the preliminary numerical experiments were also performed and the results confirm the reliability of the method in the paper.CONCLUSION: The same methodology may be applied in the pharmaceutical industry where it is necessary to predict the viable shelf-life of biological products.

Evaluation by damped least-square algorithm on target identification ability of intracranial focal bidirectional electrical impedance perturbation / 医疗卫生装备

Objective To evaluate the effect of damped least-square algorithm on the identification of focal bidirectional electrical impedance perturbation in the intracranial area, and to analyze the influence of this kind of perturbation on the reconstruction quality of electrical impedance tomography. Methods Focal bidirectional electrical impedance perturbation was built based on the three-dimensional model and damped least-square algorithm was introduced into imaging. The position error and resolution were used to evaluate the imaging performance.Results When the focal electrical impedance perturbation existed,the target whose conductivity varied greatly or volume was large was more likely to be identified in the images while the target with smaller volume or variable conductivity presented in the reconstruction image was not obvious. It's pointed out that it may cause reconstruction images in some cases could not truly reflect the location and change information of the object of primary cerebral hemorrhage.At the same time,it affected the reconstruction precision,causing the position error and resolution with large fluctuation. Conclusion In reconstruction algorithm linearity correct matrix introduced for bidirectional electrical impedance perturbation contributes to enhancing the recognition of bidirectional perturbation, so that the characterization of the electrical impedance imaging can be augmented for clinical intracerebral hemorrhage.

An echo state network algorithm based on recursive least square for electrocardiogram denoising / 生物医学工程学杂志

Electrocardiogram (ECG) is easily submerged in noise of the complex environment during remote medical treatment, and this affects the intelligent diagnosis of cardiovascular diseases. Considering this situation, this paper proposes an echo state network (ESN) denoising algorithm based on recursive least square (RLS) for ECG signals. The algorithm trains the ESN through the RLS method, and can automatically learn the deep nonlinear and differentiated characteristics in the noisy ECG data, and then the network can use these characteristic to separate out clear ECG signals automatically. In the experiment, the proposed method is compared with the wavelet transform with subband dependent threshold and the S-transform method by evaluating the signal-to-noise ratio and root mean square error. Experimental results show that the denoising accuracy is better and the low frequency component of the signal is well preserved. This method can effectively filter out complex noise and effectively preserve the effective information of ECG signals, which lays a foundation for the recognition of ECG signal feature waveform and the intelligent diagnosis of cardiovascular disease.