Neural network in signal analysis of heart rate variability

Digital image recognition of plant diseases could reduce the dependence of agricultural production on the professional and technical personnel in plant protection field and is conducive to the development of plant protection informatization. In order to find out a method to realize image recognition of plant diseases, four kinds of neural networks including backpropagation (BP) networks, radial basis function (RBF) neural networks, generalized regression networks (GRNNs) and probabilistic neural networks (PNNs) were used to distinguish wheat stripe rust from wheat leaf rust and to distinguish grape downy mildew from grape powdery mildew based on color features, shape features and texture features extracted from the disease images. The results showed that identification and diagnosis of the plant diseases could be effectively achieved using BP networks, RBF neural networks, GRNNs and PNNs based on image processing. For the two kinds of wheat diseases, the best prediction accuracy was 100% with the fitting accuracy equal to 100% while BP networks, GRNNs or PNNs were used, and the best prediction accuracy was 97.50% with the fitting accuracy equal to 100% while RBF neural networks were used. For the two kinds of grape diseases, the best prediction accuracy was 100% with the fitting accuracy equal to 100% while BP networks, GRNNs or PNNs were used, and the best prediction accuracy was 94.29% with the fitting accuracy equal to 100% while RBF neural networks were used.

In order to forecast missile storage reliability better, the paper researched a forecasting method based on neural network which is with the ability of actualizing multi-nonlinear mapping from input to output, and discussed steps of forecasting based on back propagation (BP) network and radial basis function (RBF) network respectively. At last, the storage reliability of one type ship-to-ship missile is forecasted based on BP network and RBF network respectively. The results show that both of the BP and RBF are suitable for Missile storage reliability forecasting, and the precision of the train goal is better by using RBF network. RBF network is more suitable for dealing with this problem.

To improve the network performance of radial basis function (RBF) and back-propagation (BP) networks on complex nonlinear problems, an integrated neural network model with pre-RBF kernels is proposed. The proposed method is based on the framework of a single optimized BP network and an RBF network. By integrating and connecting the RBF kernel mapping layer and BP neural network, the local features of a sample set can be effectively extracted to improve separability; subsequently, the connected BP network can be used to perform learning and classification in the kernel space. Experiments on an artificial dataset and three benchmark datasets show that the proposed model combines the advantages of RBF and BP networks, as well as improves the performances of the two networks. Finally, the effectiveness of the proposed method is verified.

This paper describes a speaker-dependent, isolated Chinese word recognition system based on neural networks. An improved neural network is applied to the recognition of speaker-dependent isolated Chinese words. The improved neural network is composed of several BP (back-propagation) networks. The isolated Chinese word sets are partitioned into a group of subsets based on a priori phonological knowledge. One of the BP networks identifies the subset to which the input word belongs; the others recognize the words in the subset. The improved neural network has the following advantages over a single BP network: training time is reduced; higher recognition accuracy is obtained with less training samples; new words can be easily added by adding new subsets. >

Artificial neural networks (ANN) consider classification as one of the most dynamic research and application areas. ANN is the branch of Artificial Intelligence (AI). The neural network was trained by back propagation algorithm [1]. A neural network represent a mathematical models of information processing, benefited from the human biological systems (i.e. a brain or nerve cell), where the neutral network can be trained and learned the same as a human brain does. The learning will be done by changing the weight during the training process and by using certain formula. One of the most known neural networks is the Back Propagation Network. This net has been used in variety of application areas. One of the, the classification of certain objects by known only a portion of information of the object to be classified. In this paper we shall use the back propagation network to classify the human blood groups, also we shall use the same program to be same analysis to find the best number of neurons in hidden layer that gives lower number of iteration.

We have applied principal component analysis-artificial neural network (PCA-ANN) in near infrared (NIR) spectroscopy to synchronous and rapid determining the contents of polysaccharide and protein in the Coriolus versicolor Powders. Back-Propagation (BP) Networks which adopt Levenberg-Marquardt training algorithm have been developed. Via analyzing the NIR spectra matrix by principal component analysis (PCA) method, we have obtained the principal components (PC) scores. The original NIR spectra and PC scores were respectively used as input data. These developed BP Networks have been optimized by selecting suitable topologic parameters and the best numbers of training. Compare with original NIR spectra, using the PC scores as input data, the capabilities of BP networks were much better. Using these optimized BP Networks for predicting the contents of polysaccharide and protein in prediction set, the root mean square error of prediction (RMSEP) are 0.0141 and 0.0138. These results are so satisfied and NIR spectroscopy technology is convenient, rapid, no pretreatment and no pollution that this method could be popularized in the in situ measurement and the on-line quality control for fermentation.

In this paper the Artificial Neural Network (ANN) model is developed to predict the surface roughness in Wire Electrical Discharge Machining (WEDM) of Cr-Mo-V alloyed special steel, which is used in automobile industry. The neural network Models strained with experimental results conducted using L16 orthogonal array by considering the input parameters such as pulse duration, open voltage, wire speed and dielectric flushing pressure at four different levels. The mathematical relation between the work piece surface roughness and WEDM cutting parameters is also established by multiple regression analysis method. Predicted values of surface roughness by Back-propagation (BPN), General regression neural networks (GRNN) using MATLAB NN tool and regression analysis, were compared with the experimental values and their closeness with the experimental values. The predicted values in BPN network with two hidden layers are very close to the experimental results than GRNN network and multiful regression values.

Purpose: Stepwise exercise testing, with workload increasing every two minutes, determines progressive changes of autonomic nervous system (ANS) adaptations that might affect stationarity during the intervals sampled for Standard Short term (SST) heart rate variability analysis (HRVa) according to ESC guidelines. To quantify such transients short-lasting changes very-short (VST) and ultra-short term (UST) analysis (HRVa) might be more appropriate, but have not been validated so far. The study aimed to evaluate, in healthy subjects (HS), the information provided by VST and UST HRVa in comparison with SSTHRVa, during exercise testing. Methods: 12-lead ECG recorded in 25 HS, before, at each workload step and during recovery after maximal exercise testing with a bicycle ergometer (workload increasing by 25 watts, every two minutes). The coefficients of variation (CV) and of reproducibility (CR) and the Pearson correlation (R2) of the same linear [time-domain (TD) and frequency-domain (FD)] and nonlinear (NL) HRV parameters, computed from SST (5-minutes), VST (60-seconds) and UST (30-seconds) intervals with Kubios HRV 2.1, (Biosignal Analysis and Medical Imaging Group, Department of Physics, University of Kuopio, Finland), were evaluated. VST and UST intervals were selected at the end of each step. Results: SSTHRVa was appropriate only at rest, before exercise and in the recovery phase. A significant correlation was found among parameters estimated from 5-minutes, 60- and 30-seconds time intervals (Pearson R2 range: 0.42 -0.98, p< 0.05 – 0.000001), except for a certain degree of variability of frequency peaks estimated with the Fast Fourier transform. At peak workload only VST and USTHRVa parameters were significantly correlated (R2 range: 0.6 -0.99, p< 0.01 – 0.000001), whereas the 5-minute interval was too long and averaged ther consecutive workload steps. At peak exercise, the CV and the CR of LF/HF, estimated from 60- and 30-seconds time-intervals were 9.3 and 0.54, respectively, thus almost optimal. Among NL methods, only the Poincare plot was calculable in all conditions. Instead recurrence plot, detrended fluctuation, approximate entropy, sample entropy and correlation dimension parameters required at least 40-seconds intervals, unless heart rate exceeded 100 bpm. Discussion: The good correlation among HRV parameters estimated at rest from 5-minutes, 60- and 30-seconds time intervals proves that VST or UST HRVa are a feasible option to evaluate changes of cardiac autonomic modulation induced by stepwise exercise testing when time-variant HRVa is unavailable.

The article provide an improvement of the method of Bendiksen et. al. (1990) adopting the backpropagation (BP) network for voiced/unvoiced speech classification, by using the HRFNN, adapting it to the non-linear pronunciation model. The comparison test has shown that the HRFNN has a 100 times higher training rate than the BP network and the recognition accuracy is better than the BP network. As for the dynamic time-changing characterization of the speech signals and non-right-cross distribution of the C/V features, it was very difficult to search for the accurate CV transforming point in the past. A time-delay HRFNN is put forward, it is very effective for recognition of the CV transforming point, and for the automatic segmentation of continuous speech, it has a fast training rate, high recognition accuracy, and good dynamic characterization. The theory and experiments have shown that the network model is of high robustness.

Evaluation of heart rate variability (HRV) detects the early subclinical alterations of the autonomic nervous system. Thus, impaired HRV is the earliest subclinical marker of cardiac autonomic neuropathy (CAN) in type 1 diabetes mellitus (T1DM). We aimed to explore the HRV parameters in asymptomatic T1DM patients and compare them with the results obtained in healthy subjects. Potential associations between HRV parameters and the established risk factors for CAN and cardiovascular diseases were also investigated. Seventy T1DM patients (38 ± 12 years, 46 females) and 30 healthy subjects were enrolled into the study. For HRV analysis, beat-to-beat heart rate was recorded for 30min. The less noisy 5-min segment of the recording was analyzed by Bittium Cardiac Navigator HRV analysis software. Time domain, frequency domain, and nonlinear indices were calculated. Regarding ratio of low to high frequency component (LF/HF), no differences were found between the two populations (p = 0.227). All the further, time domain, frequency domain, and nonlinear HRV indices were significantly lower in T1DM patients (each p < 0.001). In multiple linear models, disease duration remained the only independent predictor of LF/HF ratio (p = 0.019). HbA1c was found to be significant independent predictor of all further time domain (SDNN, p < 0.001; rMSSD, p < 0.001), frequency domain (VLF, p < 0.001; LF, p = 0.002; HF, p = 0.006; Total Power, p = 0.002), and nonlinear indices (SD1, p = 0.006; SD2, p = 0.007), alone, or in combination with other factors, such as age or body mass index. Asymptomatic T1DM patients have significantly reduced overall HRV as compared with healthy subjects, indicating subclinical CAN. Quality of the glycemic control is important determinant of HRV among T1DM patients. This relationship is independent of other risk factors for CAN or cardiovascular diseases.

Chaos and spectral analyses of heart rate variability during head-up tilting in essential hypertension

The cold chain transportation monitoring system is mainly responsible for data monitoring and control in the cold chain transportation environment, ensuring the stability of the cold chain compartment environment, and playing an important role in the transportation and storage of fresh agricultural products. The traditional Internet of Things cold chain control system uses manual input of control parameters to realize the monitoring of the cold chain compartment environment, which lacks intelligence. Therefore, the BP (Back propagation, BP) neural network is used to build a cold chain transportation monitoring model to realize the dynamic monitoring of the cold chain compartment environment. Considering that the BP network is easy to fall into the problem of “local fall”, which leads to the decline of the prediction accuracy of the model, the improved discrete artificial bee colony algorithm is used to optimize the parameters of the BP neural network, and the fish swarm algorithm is used to decode the discrete population to obtain the final result. Decimal value to construct the DABC-BP cold chain transportation control model. The experimental simulation results show that in the $$f_{1} (x)$$ function optimization test, the improved DABC-BP (Discrete Artificial Bee Colony-Back Propagation Neural Network, DABC-BP) algorithm has the best optimization accuracy, and the minimum logarithm after 1000 iterations is 10−7. Meanwhile, the DABC algorithm has the best convergence performance, reaching convergence after 821 iterations. Compared with related hybrid algorithms such as mayfly algorithm and extreme learning machine, this research method is suitable for harsher environments and more sensitive to temperature monitoring. The research has important reference value for the transportation and storage of modern agricultural products.

Instantaneous learning is a desirable feature in neural networks. This type of learning enables the network to be trained very quickly, typically in just one or two passes of the training set as opposed to hundreds or even thousands of passes for networks trained by an iterative process, such as the error backpropagation (BP) algorithm. This dissertation first reviews several existing types of neural networks with instantaneous learning capability. It then proposes a new network called the Fuzzy Classification (FC) Neural Network that can be trained with two passes of the training samples. The first pass assigns the synaptic weights for the input and output layers. The second pass determines the radius of generalization r for each training sample. The network exhibits fuzziness in two regards: (1) by fuzzification of the location of each training vector in the input space; and (2) by assigning fuzzy memberships of output classes to new input vectors. The operation of the FC network is analyzed from different perspectives, namely, separability of patterns, curve fitting and kernel regression. It is shown that one mode of operation of the FC network can be made to behave like a Radial Basis Function (RBF) network by proper choice of membership function and network parameter. The performance of the FC network as a pattern classifier is also discussed in a statistical framework. The generalization performance of the FC network is compared against that of the CC4 Comer Classification Neural Network, the RBF network, and the Multilayer Perceptron network trained by the BP algorithm. Experiments involving a Henon map time series, a Mackey-Glass time series, and a spiral pattern are used in the comparison. The performance of the FC network is found to be comparable to that of RBF and BP networks, and better than that of the CC4 network. Its performance is also more scalable than those of CC4 and RBF networks. Further, the time taken to design an FC network for any given problem is much shorter compared to the other three networks.

It is of clinical interest to estimate pure-tone thresholds from potentially available objective measures, such as stimulus-frequency otoacoustic emissions (SFOAEs). SFOAEs can determine hearing status (normal hearing vs. hearing loss), but few studies have explored their further potential in predicting audiometric thresholds. The current study investigates the ability of SFOAEs to predict hearing thresholds at octave frequencies from 0.5 to 8 kHz. SFOAE input/output functions and pure-tone thresholds were measured from 230 ears with normal hearing and 737 ears with sensorineural hearing loss. Two methods were used to predict hearing thresholds. Method 1 is a linear regression model; Method 2 proposed in this study is a back propagation (BP) network predictor built on the bases of a BP neural network and principal component analysis. In addition, a BP network classifier was built to identify hearing status. Both Methods 1 and 2 were able to predict hearing thresholds from 0.5 to 8 kHz, but Method 2 achieved better performance than Method 1. The BP network classifiers achieved excellent performance in determining the presence or absence of hearing loss at all test frequencies. The results show that SFOAEs are not only able to identify hearing status with great accuracy at all test frequencies but, more importantly, can predict hearing thresholds at octave frequencies from 0.5 to 8 kHz, with best performance at 0.5 to 4 kHz. The BP network predictor is a potential tool for quantitatively predicting hearing thresholds, at least at 0.5 to 4 kHz.

Purpose In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Design/methodology/approach In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Findings In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Originality/value In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.