Objective To investigate the methods for EGG data compression and accurate QRS detection. Methods The quick fitting of LADT was improved and the combination of the improved quick fitting of LADT and neural network was used for the detection of the location of the QRS complex. Results Test by the MIT/BIH arrhythmia database revealed high accuracy rate of QRS detection and easy real time application. Conclusion The purposes of accurate detection of QRS with a little time are realized.

The extraction and identification of ECG (electrocardiogram) signal characteristic parameters are the basic steps toward ECG analysis and diagnosis. The fast and precise detection of QRS complexes is very important in ECG signal analysis, for it is the precondition of the correlative parameters calculation and diagnosis. In our work, firstly, we used the modulus value of complex wavelet decomposition to detect QRS complexes from ECG signal. As the shape and amplitude of ECG signal varies from person to person, we utilized the self-learning algorithm for adjusting the threshold to adapt the changes. The correct detection rate of QRS complexes is up to 99.81% based on MIT-BIH ECG data. Finally, we used the similar methods to detect the P and T waves, after QRS complexes detection.
Algorithms ; Electrocardiography ; methods ; Humans ; Signal Processing, Computer-Assisted

The aim of this study was to detect QRS complex powers accurately. ECG was approximated by lines. It produced number of classes with main features of the whole ECG. Then these number of classes were analyzed in detail. The QRS detection rate reached 99.9% as validated by using single lead signals from MIT/BIH database. Complex powers can be recognized accurately with this method.
Algorithms ; Databases, Factual ; Electrocardiography ; classification ; Humans

The extraction and identification of ECG (electrocardiogram) signal characteristic parameters are the basis of ECG analysis and diagnosis. The fast and precise detection of QRS complexes is very important in ECG signal analysis; for it is a pre-requisite for the correlative parameters calculation as well as for correct diagnosis. In our work, firstly, the modulus maximum of wavelet transform is applied to the QRS complexes detection from ECG signal. Once there are mis-detections or missed detections happening, we utilize the Golden Section Search algorithm to adjust the threshold of maxima determination. The correct detection rate of the QRS complexes is up to 99.6% based on MIT-BIH ECG data.
Algorithms ; Electrocardiography ; methods ; Humans ; Signal Processing, Computer-Assisted

Objective To investigate the affecting factors on auditory and speech performances in preschool children with unilateral cochlear implantation (CI) .Methods The clinical data of the preschool children (n=165) with unilateral cochlear implantation in the Second Xiangya hospital from January 2006 to April 2013 were collected . These children received rehabilitation according to the method recommended by the China Rehabilitation Research Center for Deaf Children ,and the data were analyzed retrospectively .The categories of auditory performance (CAP) and speech intelligibility rating (SIR) were used to assess their auditory and speech performances .The relationships between the performance and gender ,implanted age ,genotype ,inner ear malformation ,history of hearing aid were evaluated .Results Implanted ages and genotypes were associated with the auditory and speech performance of par‐ticipants (P<0 .05) ,while genders ,hearing aid experience ,and inner ear malformations(enlarged vestibular aque‐duct syndrome ,EVAS)were not significant related (P<0 .05) .Children were found to have achieved better CAP and SIR growths when CI was implanted during 1~3 years old and 2~4 years old ,respectively (P<0 .05) .The outcomes of CI recipients with GJB2 mutation were significantly better than those of the GJB2-nonrelated CI recipi‐ents (P<0 .05) .Conclusion This study provides evidence that CIs during first 1~3 years old having better auditory rehabilitation results than those of during 4~6 years old ,and CIs during 2~4 years old obtaining a better speech development in the first 12 months after operation .Deaf children with GJB2 mutation show better auditory and speech performances after CIs than those of the peers without GJB2 mutation .CIs can be effectively performed in deaf children associated with EVAs as in those without EVAS .

In this paper is proposed a new method that approximates line segment with angle to control line as a basis for improving radial fitting. Experiments on selected records from the Massachusettes Institute of Technology and Boston's Beth Isral Hospital (MIT-BIH) arrhythmia database have revealed that the improved algorithm not only increases computation quantity, but also improves approximating quality and potentiates Real-time application of the linear approximation distance thresholding (LADT).
Algorithms ; Data Compression ; Electrocardiography ; methods ; Humans ; Signal Processing, Computer-Assisted

Electrocardiogram (ECG) signal is important for physician to diagnose diseases. Various existing techniques on ECG classification have been reported. Generally, these techniques classify only two or three arrhythmias and need significantly long processing time. A new algorithm based on Support vector machine (SVM) is presented to solve the problem in this paper, which has been successfully applied to the classification of ECG. And in this paper are clarified the fundamental ideas of the classification of ECG based on SVM. Compared with the traditional neural network, this method is superior to it in theory. Because this new method deals with the minimization of the test samples, not the training samples.
Algorithms ; Artificial Intelligence ; Diagnosis, Computer-Assisted ; methods ; Electrocardiography ; methods ; statistics & numerical data ; Humans ; Models, Statistical ; Signal Processing, Computer-Assisted

An electrocardiogram (ECG) classify system based on the features of the ECG and neural network classification, which is the simulation of the real world situation, was present. First, a modified approach of the linear approximation distance thresholding (LADT) algorithm was studied and the features of the ECG were obtained. Then a neural network which can classify the multi-lead ECG data was trained with these features along the theory of the ECG diagnosis and the situation of ECG diagnosis in practice. Thus take a new idea for the ECG automatic analysis. The algorithm was tested using several ECG signals of MIT-BIH, and the performance was good. The correct rate of the trained wave is 100%, untrained is 78.2%.
Algorithms ; Databases, Factual ; Electrocardiography ; classification ; Neural Networks (Computer) ; Signal Processing, Computer-Assisted

In this paper, we using Mexican-hat wavelet transform to detect characteristic points of ECG signal based on the characteristic points corresponding with the extremes of Mexican-hat wavelet transform. It offers a new detection method of ECG signal analysis. This method is simple and it is proved to be accurate and reliable. The correct rate of QRS detection rate examined by the MIT-BIT arrhythmia database rises up to 99.9%.
Algorithms ; Electrocardiography ; Humans ; Signal Processing, Computer-Assisted

The similarity measures between Vague sets are one of the most important technologies in Vague sets, In this paper, the new similarity measures based on Huang Guoshun's related works are presented and applied in electrocardiogram auto-recognition. Based on medical requiresments, in this paper, the characteristic parameters of signals from Massachusettes Institute of Technology (database) have been picked up and studied with BP neural network. In the end, the electrocardiogram samples are classified with the use of those characteristic parameters. The result shows that the accuracy of recognition goes up to 99.04%.
Algorithms ; Electrocardiography ; methods ; Fuzzy Logic ; Humans ; Neural Networks (Computer) ; Pattern Recognition, Automated ; Signal Processing, Computer-Assisted