scholarly journals Design of Ensemble Stacked Auto-Encoder for Classification of Horse Gaits with MEMS Inertial Sensor Technology

Micromachines ◽  
2018 ◽  
Vol 9 (8) ◽  
pp. 411 ◽  
Author(s):  
Jae-Neung Lee ◽  
Yeong-Hyeon Byeon ◽  
Keun-Chang Kwak
Keyword(s):  
Mean Squared Error ◽  
Inertial Sensor ◽  
Wavelet Packet ◽  
Back Propagation ◽  
Sensor Technology ◽  
Support Vector ◽  
Softmax Classifier ◽  
National Team ◽  
Motion Data

This paper discusses the classification of horse gaits for self-coaching using an ensemble stacked auto-encoder (ESAE) based on wavelet packets from the motion data of the horse rider. For this purpose, we built an ESAE and used probability values at the end of the softmax classifier. First, we initialized variables such as hidden nodes, weight, and max epoch using the options of the auto-encoder (AE). Second, the ESAE model is trained by feedforward, back propagation, and gradient calculation. Next, the parameters are updated by a gradient descent mechanism as new parameters. Finally, once the error value is satisfied, the algorithm terminates. The experiments were performed to classify horse gaits for self-coaching. We constructed the motion data of a horse rider. For the experiment, an expert horse rider of the national team wore a suit containing 16 inertial sensors based on a wireless network. To improve and quantify the performance of the classification, we used three methods (wavelet packet, statistical value, and ensemble model), as well as cross entropy with mean squared error. The experimental results revealed that the proposed method showed good performance when compared with conventional algorithms such as the support vector machine (SVM).

scholarly journals Fault Identification of Gearbox Degradation with Optimized Wavelet Neural Network

2013 ◽  
Vol 20 (2) ◽  
pp. 247-262 ◽  
Author(s):  
Hanxin Chen ◽  
Yanjun Lu ◽  
Ling Tu
Keyword(s):  
Neural Network ◽  
Wavelet Packet ◽  
Back Propagation ◽  
Experimental System ◽  
Vibration Signal ◽  
Wavelet Neural Network ◽  
Acceleration Sensors ◽  
Gear Fault ◽  
Gear Crack

A novel intelligent method based on wavelet neural network (WNN) was proposed to identify the gear crack degradation in gearbox in this paper. The wavelet packet analysis (WPA) is applied to extract the fault feature of the vibration signal, which is collected by two acceleration sensors mounted on the gearbox along the vertical and horizontal direction. The back-propagation (BP) algorithm is studied and applied to optimize the scale and translation parameters of the Morlet wavelet function, the weight coefficients, threshold values in WNN structure. Four different gear crack damage levels under three different loads and three various motor speeds are presented to obtain the different gear fault modes and gear crack degradation in the experimental system. The results show the feasibility and effectiveness of the proposed method by the identification and classification of the four gear modes and degradation.

scholarly journals Electro-myographic patterns of sub-vocal Speech: Records and classification

2015 ◽  
Vol 12 (2) ◽  
Author(s):  
Luis Enrique Mendoza ◽  
Jesus Peña ◽  
Jairo Lenin Ramón Valencia
Keyword(s):  
Wavelet Packet ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Discrete Wavelet ◽  
Classification Rate ◽  
Time Frequency ◽  
Surface Electrodes ◽  
Area Of Interest ◽  
Vocal Speech

<p>This paper describes the results obtained from recording, processing and classification of words in spoken Spanish by means of analysis of subvocal speech signals. The processed database has six words (forward, backward, right, left, start and stop), In this article, the signals are sensed with surface electrodes (placed on the surface of the throat) and acquired at a sampling frequency of 50 kHz. The signal conditioning consists of a couple of steps, namely the location of area of interest, using energy analysis; and a filtering stage, using Discrete Wavelet Transform. Finally, feature extraction is achieved in the time-frequency domain using Wavelet Packet and statistical techniques for windowing. Classification is carried out with a back propagation neural network whose training is performed with 70% of the database obtained. The correct classification rate was 75%±2.</p>

Arrhythmia Classification Based on Multiple Features Fusion and Random Forest Using ECG

2019 ◽  
Vol 9 (8) ◽  
pp. 1645-1654
Author(s):  
Zhizhong Wang ◽  
Hongyi Li ◽  
Chuang Han ◽  
Songwei Wang ◽  
Li Shi
Keyword(s):  
Random Forest ◽  
Wavelet Packet ◽  
Back Propagation ◽  
Principal Component ◽  
Support Vector ◽  
Features Fusion ◽  
Specificity And Sensitivity ◽  
Average Accuracy ◽  
Skewness Coefficient ◽  
Novel Method

Cardiovascular diseases have become more and more prominent in recent years, which have proven to be a major threat to people's health. Accurate detection of arrhythmia in patients has important implications for clinical treatment. The aim of this study was to propose a novel automatic classification method for arrhythmia in order to improve classification accuracy. The electrocardiogram (ECG) signal was subjected preprocessing for denoising purposes using a wavelet transform. Then, the local and global characteristics of the beat, which contained RR interval features according with the clinical diagnosis criterion, morphology features based on wavelet packet decomposition and statistical features along with kurtosis coefficient, skewness coefficient and variance are exploited and fused. Meanwhile, the dimensionality of wavelet packet coefficients were reduced via principal component analysis (PCA). Finally, these features were used as the input of the random forest classifier to train the model and were then compared with the support vector machine (SVM) and back propagation (BP) neural networks. Based on 100,647 beats from the MIT-BIH database, the proposed method achieved an average accuracy, specificity and sensitivity of 99.08%, 99.00% and 89.31%, respectively, using the intra-patient beats, and 92.31%, 89.98% and 37.47%, respectively, using the inter-patient beats. Moreover, two classification schemes, namely, inter-patient and intra-patient scheme, were validated. Compared with the other methods referred to in this paper, the performance of the novel method yielded better results.

scholarly journals SVM versus MAP on Accelerometer Data to Distinguish among Locomotor Activities Executed at Different Speeds

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Maurizio Schmid ◽  
Francesco Riganti-Fulginei ◽  
Ivan Bernabucci ◽  
Antonino Laudani ◽  
Daniele Bibbo ◽  
...  
Keyword(s):  
Inertial Sensor ◽  
Stair Climbing ◽  
Support Vector ◽  
Accelerometer Data ◽  
Sammon’S Mapping ◽  
Locomotor Activities ◽  
Artificial Neural Network Ann ◽  
Better Than ◽  
Bayes Approach

Two approaches to the classification of different locomotor activities performed at various speeds are here presented and evaluated: a maximum a posteriori (MAP) Bayes’ classification scheme and a Support Vector Machine (SVM) are applied on a 2D projection of 16 features extracted from accelerometer data. The locomotor activities (level walking, stair climbing, and stair descending) were recorded by an inertial sensor placed on the shank (preferred leg), performed in a natural indoor-outdoor scenario by 10 healthy young adults (age 25–35 yrs.). From each segmented activity epoch, sixteen features were chosen in the frequency and time domain. Dimension reduction was then performed through 2D Sammon’s mapping. An Artificial Neural Network (ANN) was trained to mimic Sammon’s mapping on the whole dataset. In the Bayes’ approach, the two features were then fed to a Bayes’ classifier that incorporates an update rule, while, in the SVM scheme, the ANN was considered as the kernel function of the classifier. Bayes’ approach performed slightly better than SVM on both the training set (91.4% versus 90.7%) and the testing set (84.2% versus 76.0%), favoring the proposed Bayes’ scheme as more suitable than the proposed SVM in distinguishing among the different monitored activities.

scholarly journals Fourier Descriptors Based Expert Decision Classification of Plug Seedlings

2019 ◽  
Vol 2019 ◽  
pp. 1-10
Author(s):  
Yanhu He ◽  
Rongyang Wang ◽  
Yanfeng Wang ◽  
Chuanyu Wu
Keyword(s):  
Expert System ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Identification Accuracy ◽  
Support Vector ◽  
Fourier Descriptors ◽  
Identification Rate ◽  
Image Acquisition System ◽  
Seedling Leaf

To enable automatic transplantation of plug seedlings and improve identification accuracy, an algorithm to identify ideal seedling leaf sets based on Fourier descriptors is developed, and a classification method based on expert system is adopted to improve the identification rate of the plug seedlings. First, the image of the plug seedlings is captured by image acquisition system, followed by application of K-means clustering for image segmentation and binary processing and identification of the ideal seedling leaf set by Fourier descriptors. Then we obtain feature vectors, such as gray scale (R+B+G)/3, hue H, and rectangularity. After that the knowledge model of the plug seedlings is defined, and the inference engine based on knowledge is designed. Finally, the recognizing test is carried out. The success rate of the identification of 10 varieties of plug seedlings from 190 plates is 98.5%. For the same sample, the recognizing rate of support vector machine (SVM) is 85%, the recognizing rate of particle-swarm optimization SVM (PSOSVM) is 87%, the recognizing rate of back propagation neural network (BP) is 63%, and the recognizing rate of Fourier descriptors SVM (FDSVM) is 87%. These results show that our recognition method based on an expert system satisfies the requirements of automatic transplanting.

Sign in / Sign up

Export Citation Format

Share Document