A pace recognition method for exoskeleton wearers based on support vector machine-hidden Markov model / 生物医学工程学杂志

In order to improve the motion fluency and coordination of lower extremity exoskeleton robots and wearers, a pace recognition method of exoskeleton wearer is proposed base on inertial sensors. Firstly, the triaxial acceleration and triaxial angular velocity signals at the thigh and calf were collected by inertial sensors. Then the signal segment of 0.5 seconds before the current time was extracted by the time window method. And the Fourier transform coefficients in the frequency domain signal were used as eigenvalues. Then the support vector machine (SVM) and hidden Markov model (HMM) were combined as a classification model, which was trained and tested for pace recognition. Finally, the pace change rule and the human-machine interaction force were combined in this model and the current pace was predicted by the model. The experimental results showed that the pace intention of the lower extremity exoskeleton wearer could be effectively identified by the method proposed in this article. And the recognition rate of the seven pace patterns could reach 92.14%. It provides a new way for the smooth control of the exoskeleton.

A Gaussian mixture-hidden Markov model of human visual behavior / 生物医学工程学杂志

Vision is an important way for human beings to interact with the outside world and obtain information. In order to research human visual behavior under different conditions, this paper uses a Gaussian mixture-hidden Markov model (GMM-HMM) to model the scanpath, and proposes a new model optimization method, time-shifting segmentation (TSS). The TSS method can highlight the characteristics of the time dimension in the scanpath, improve the pattern recognition results, and enhance the stability of the model. In this paper, a linear discriminant analysis (LDA) method is used for multi-dimensional feature pattern recognition to evaluates the rationality and the accuracy of the proposed model. Four sets of comparative trials were carried out for the model evaluation. The first group applied the GMM-HMM to model the scanpath, and the average accuracy of the classification could reach 0.507, which is greater than the opportunity probability of three classification (0.333). The second set of trial applied TSS method, and the mean accuracy of classification was raised to 0.610. The third group combined GMM-HMM with TSS method, and the mean accuracy of classification reached 0.602, which was more stable than the second model. Finally, comparing the model analysis results with the saccade amplitude (SA) characteristics analysis results, the modeling analysis method is much better than the basic information analysis method. Via analyzing the characteristics of three types of tasks, the results show that the free viewing task have higher specificity value and a higher sensitivity to the cued object search task. In summary, the application of GMM-HMM model has a good performance in scanpath pattern recognition, and the introduction of TSS method can enhance the difference of scanpath characteristics. Especially for the recognition of the scanpath of search-type tasks, the model has better advantages. And it also provides a new solution for a single state eye movement sequence.

Segmentation of heart sound signals based on duration hidden Markov model / 生物医学工程学杂志

Heart sound segmentation is a key step before heart sound classification. It refers to the processing of the acquired heart sound signal that separates the cardiac cycle into systolic and diastolic, etc. To solve the accuracy limitation of heart sound segmentation without relying on electrocardiogram, an algorithm based on the duration hidden Markov model (DHMM) was proposed. Firstly, the heart sound samples were positionally labeled. Then autocorrelation estimation method was used to estimate cardiac cycle duration, and Gaussian mixture distribution was used to model the duration of sample-state. Next, the hidden Markov model (HMM) was optimized in the training set and the DHMM was established. Finally, the Viterbi algorithm was used to track back the state of heart sounds to obtain S

Hidden Markov models for human interactive behavior / 生物医学工程学杂志

In order to meet the requirements in the cooperation and competition experiments for an individual patient in clinical application, two human interactive behavior key-press models based on hidden Markov model (HMM) were proposed. To validate the cooperative and competitive models, a verification experimental task was designed and the data were collected. The correlation of the score and subjects' participation level has been used to analyze the reasonability verification. Behavior verification was conducted by comparing the statistical difference in response time for subjects between human-human and human-computer experiment. In order to verify the physiological validity of the models, we have utilized the coherence analysis to analyze the deep information of prefrontal brain area. Reasonability verification shows that the correlation coefficient for the training data and the testing data is 0.883 1 and 0.578 6 respectively based on cooperation model, and 0.813 1 and 0.617 8 respectively based on the competition model. The behavioral verification result shows that the cooperation and competition models have an accuracy of 71.43% respectively. The results of physiological validity show that the deep information of prefrontal brain area could been extracted based on the cooperation and competition models, and reveal the consistency of coherence between the double key-press cooperative and competitive experiments, respectively. Above all, the high consistency is obtained between the cooperatio/competition model and the double key-press experiment by the behavioral and physiological evaluation results. Consequently, the cooperation and competition models could be applied to clinical trials.

Identification of Asymmetry Gait in Parkinson's Disease Based on Kinect / 中国康复理论与实践

@#Objective To develop a non-contact identification method for gait asymmetry in Parkinson's disease based on depth image to assist medical diagnosis and assessment, to avoid the cost, impact on normal life, and complex process of high wear-out sensing equipment. Methods From July to August, 2016, eight patients with Parkinson's disease and ten healthy subjects were collected the gait parameters of walking six meters with Kinect V2.0. The parameters of left and right foot were filtered and clustered. Then similarity matrix algorithm was used to find the difference between healthy subject and patient similarity values. Finally, the recognition effect of this method was verified by Hidden Markov Model. Results The similarity of clustering sequences of left and right foot parameters was less in the patients than in the healthy individuals. There were twelve of 14 data identified in patients, and 35 of 46 in the healthy. Conclusion A non-contact identification method for the asymmetry of gait has been developed based on the parameter clustering results of left and right foot, which is some effective on identifying Parkinson's patients.

Novel type of unperturbed sleep monitoring scheme under pillow based on hidden Markov model / 生物医学工程学杂志

Sleep status is an important indicator to evaluate the health status of human beings. In this paper, we proposed a novel type of unperturbed sleep monitoring system under pillow to identify the pattern change of heart rate variability (HRV) through obtained RR interval signal, and to calculate the corresponding sleep stages combined with hidden Markov model (HMM) under the no-perception condition. In order to solve the existing problems of sleep staging based on HMM, ensemble empirical mode decomposition (EEMD) was proposed to eliminate the error caused by the individual differences in HRV and then to calculate the corresponding sleep stages. Ten normal subjects of different age and gender without sleep disorders were selected from Guangzhou Institute of Respirator Diseases for heart rate monitoring. Comparing sleep stage results based on HMM to that of polysomnography (PSG), the experimental results validate that the proposed noninvasive monitoring system can capture the sleep stages S1-S4 with an accuracy more than 60%, and performs superior to that of the existing sleep staging scheme based on HMM.

Human action and road condition recognition based on the inertial information / 生物医学工程学杂志

Rapid and accurate recognition of human action and road condition is a foundation and precondition of implementing self-control of intelligent prosthesis. In this paper, a Gaussian mixture model and hidden Markov model are used to recognize the road condition and human motion modes based on the inertial sensor in artificial limb (lower limb). Firstly, the inertial sensor is used to collect the acceleration, angle and angular velocity signals in the direction of , and axes of lower limbs. Then we intercept the signal segment with the time window and eliminate the noise by wavelet packet transform, and the fast Fourier transform is used to extract the features of motion. Then the principal component analysis (PCA) is carried out to remove redundant information of the features. Finally, Gaussian mixture model and hidden Markov model are used to identify the human motion modes and road condition. The experimental results show that the recognition rate of routine movement (walking, running, riding, uphill, downhill, up stairs and down stairs) is 96.25%, 92.5%, 96.25%, 91.25%, 93.75%, 88.75% and 90% respectively. Compared with the support vector machine (SVM) method, the results show that the recognition rate of our proposed method is obviously higher, and it can provide a new way for the monitoring and control of the intelligent prosthesis in the future.

Study on Automatic Word Segmentation for Traditional Chinese Medical Record Literature / 中国中医药信息杂志

Objective To study the automatic word segmentation scheme suitable for traditional Chinese medical record literature. Methods Hierarchical Hidden Markov Model was used as segmentation model. Totally 300 ancient medical record literature and 300 modern medical record literature were set as experimental subjects to establish the dictionary of traditional Chinese medicine and the test corpus, with a purpose to segment the words and evaluate of the results. Results Without using dictionary of traditional Chinese medicine, the word segmentation accuracy of two kinds of medical record literature was about 75%;the part-of-speech tagging accuracy of ancient medical literature was 56.74%, the modern medical literature accuracy was 64.81%. By using dictionary of tradition Chinese medicine, the word segmentation accuracy of ancient medical record literature was 90.73%, the modern medical record literature accuracy was 95.66%;the part-of-speech tagging accuracy of ancient medical record literature was 78.47%, the modern medical record literature accuracy was 91.45%, which was obviously higher than that of ancient medical record literature. Conclusion The current word segmentation scheme has initially solved the problem of word segmentation of traditional Chinese medical record literature and part-of-speech tagging of modern medical record literature. Part of speech tagging is basically correct, but part-of-speech tagging of ancient medical record literature tagging needs further study for many influencing factors.

Hidden Markov model for protein structural class prediction based on MATLAB / 国际生物医学工程杂志

Objective Predicting protein structural class is the basis for predicting protein spatial structure,so it is important to improve the prediction accuracy of protein structural class.Methods We proposed 3-state and 8-state Hidden Markov model (HMM),and applied these HMMs to the prediction of protein structural class,respectively.We evaluated their accuracy on two different datasets through the rigorous jackknife cross-validation test.Results Prediction ability of 8-state HMM and 3-state HMM to all α class were excellent,the prediction accuracy of 3-state HMM even reached above 95％.Compared with Chou data set,the prediction accuracy of Zhou data set for all β class and α/β class of was improved,while overall prediction accuracy increased by 2％.Conclusion HMM is an effective method to predict protein structural class.

Heart Sound Classification Using Variable Number of States in Hidden Markov Model Considering Characteristics of the Signal / 대한의료정보학회지

Hidden Markov model (HMM) is known to be one of the most powerful methods in the acoustic modeling of heart sound signals. Conventionally, we usually use a fixed number of states for each HMM. However, due to the various types of the heart sound signals, it seems that more accurate acoustic modeling is possible by varying the number of states in the HMM depending on the signal types to be modeled. In this paper, we propose to assign different number of states to the HMM for better acoustic modeling and consequently, improving the classification performance of the heart sound signals. Compared with when fixing the number of states, the proposed approach has shown some performance improvement in the classification experiments on various types of heart sound signals.

Classification of Continuous Heart Sound Signals Using the Ergodic Hidden Markov Model / 대한의료정보학회지

Recently, hidden Markov models (HMMs) have been found to be very effective in classifying heart sound signals. For the classification based on the HMM, the continuous cyclic heart sound signal needs to be manually segmented to obtain isolated cycles of the signal. However, the manual segmentation will be practically inadequate in real environments. Although, there have been some research efforts for the automatic segmentation, the segmentation errors seem to be inevitable and will result in performance degradation in the classification. To solve the problem of the segmentation, we propose to use the ergodic HMM for the classification of the continuous heart sound signal. In the classification experiments, the proposed method performed successfully with an accuracy of about 99(%) requiring no segmentation information.

A Hybrid Machine Learning Approach To the Promoter Prediction Problem / 대한의료정보학회지

With recent explosive growth of bulky biological data available, there are great needs of developing rapid autonomous algorithms in bioinformatics. In result, there has be en a great deal of attempts to apply various data mining techniques and learning algorithms to various fields of bioinformatics and a good example of this trend is the promoter and motif search area to which NN (Neural Network), HMM (Hidden Markov Model), and clustering algorithms have been applied and several good public software programs are available. Learning algorithms explore a part of big learning space effectively by their own biases. Thus, in many occasions, different learning algorithms have radically different results especially when the target concept is uncertain or stochastically defined and/or the background knowledge of the problem is limited. In this case, it is useful to apply a hybrid learning approach which two or more mutually compensative algorithms (e.g. a low false positive algorithm and a low false negative algorithm) are effectively combined. In this paper, we report a series of experiments with a hybrid learning approach in promoter prediction problem. Three available public software systems are tested and two of them (McPromoter and PROMOTER SCAN) are hierarchically combined and tested. The result shows that the hybrid learning model in this problem is quite plausible (better than any of the two base systems in accuracy and low false alarms) and many other learning algorithms could be more useful in this approach than being applied independently.