• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.2 s.302
• /
• pp.39-48
• /
• 2005

This paper proposes a novel approach to recognize nine kinds of motion for a multifunction myoelectric hand, acquiring four channel EMG signals from electrodes placed on the forearm. To analyze EMG with properties of nonstationary signal, time-frequency features are extracted by wavelet packet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a feature projection composed of PCA and SOFM. The dimensionality reduction by PCA simplifies the structure of the classifier, and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features to a new feature space with high class separability. Finally a multilayer neural network is employed as the pattern classifier. From experimental results, we show that the proposed method enhances the recognition accuracy, and makes it possible to implement a real-time pattern recognition.

• Bulletin of the Korean Chemical Society
• /
• v.30 no.1
• /
• pp.137-144
• /
• 2009

In this study, quantitative and pattern recognition analyses for the quality evaluation of Herba Epimedii using HPLC was developed. For quantitative analysis, five major bioactive constituents, hyperin, epimedin A, epimedin B, epimedin C, and icariin were determined. Analysis was carried out on Capcell pak $C_{18}$ column ($250{\time}4.6$ mm, 5 ${\mu}m$) with a mobile phase of mixture of acetonitrile and 0.1% formic acid, using UV detection at 270 nm. The linear behavior was observed over the investigated concentration range (2-50 ${\mu}g/mL;\;r_2\;>$ 0.99) for all analytes. The intraand inter-day precisions were lower than 4.3% (as a relative standard deviation, RSD) and accuracies between 95.1% and 104.4%. The HPLC analytical method for pattern recognition analysis was validated by repeated analysis of one reference sample. The RSD of intra- and inter-day variation of relative retention time (RRT) and relative peak area (RPA) of the 12 selected common peaks were below 0.8% and 4.7%, respectively. The developed methods were applied to analysis of twenty Herba Epimedii extract samples. Contents of hyperin, epimedin A, epimedin B, epimedin C, and icariin were calculated to be 0$\sim$0.79, 0.69$\sim$1.91, 0.93$\sim$9.58, 0.65$\sim$3.05, and 2.43$\sim$11.8 mg/g dried plant. Principal component analysis (PCA) showed that most samples were clustered together with the reference samples but several apart from the main cluster in the PC score plot, indicating differences in overall chemical composition between two clusters. The present study suggests that quantitative determination of marker compounds combined with pattern-recognition method can provide a comprehensive approach for the quality assessment of herbal medicines.

• Journal of the Korean Home Economics Association
• /
• v.30 no.4
• /
• pp.231-247
• /
• 1992

A Study on Maternal Verbal Control Patterns and Children's Recognition against those. The primary objective of the material presented in this dissertation is the analysis of the maternal verbal control patterns. The major focus is given to the differences between maternal verbal control patterns and children's recognition against those. The purspoe of this study were; 1) to investigate the maternal verbal control patterns recognized by children according to their family and personal surroundings; 2) to investigate the verbal control patterns in mother's response according to the differences of family and personal surroundings; 3) to find the differences between children's recognition and maternal verbal control patterns; 4) How the maternal verbal control patterns recognized by children are? The materials of this study were 81(37; boys, 44; girl)) from kindergarten in Seou. The sample of age used in this study was 5 to 7 years old. The test about maternal verbal environment used the question sheet for reaction between mother and children by Gumperz. The kids got interviews with same questions as mothers with question sheet. The statistical tools used is the analysis of the data were frequency, crosstab, and t-test. The result of the study were summarized as follows; 1) The maternal verbal control patterns recognized by children had differences according to whether living with grand-parent or not. Living with grand-parent are more person-oriented than without grand-parent group. 2) The maternal verbal control patterns of mother response show the differences within mother's academic background, present situation of child, and parent's expection to child. The imperative verbal control pattern was more frequently used of low academic background who just fraduate the middle or high school. The personal verbal control pattern was more frequently used of high educational background's like university graduate or more educated group. 3) The differences between maternal verbal control patterns with children's recognition and with mother response is that mother responseis more person-oriented than children's. 4) The imperative verbal control pattern used command, verbal purnishment, and physical purnishment. the status-oriented verbal control pattern used univesal positional appeals and limited positional appeals. The person-oriented verbal control pattern used child-oriented cognitive affective appeals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.167-168
• /
• 2019

Lately, variety of algorithms using encryption technology has been adopted as methods of unlocking smartphone. It is advancing toward the direction to solve through human biometrics technology which has already succeeded in commercialization. These include finger print recognition, face recognition, and iris recognition. In this study, we selected biometrics recognition technology and pattern recognition and password input methods which are already commercialized as evaluation items. The evaluation items are five algorithms including finger print recognition, face recognition iris recognition, pattern recognition and password input method. Based on these algorithms, analytic hierarchy process is used to analyze the preference of smartphone users. Also, the theoretical implications are presented based on the analysis results.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.8
• /
• pp.2061-2068
• /
• 1993

Condition monitoring technology is of great importance for the maintenance of complex machinery in view of its early monitoring of the abnormal condition and the protection against failure. Several methods have been used for the detection of failure of journal bearings, one of the main elements of mechanical system. The methods most frequently used are vibration and temperature monitoring, but these are unable to monitor the wear conditions exactly. In this study, an ultrasonic measument method, one of the non-destructive testing methods, was introduced as the monitoring technology. Furtermore a pattem recognition method was applied to analyze the ultrasonic signal. The monitoring system using the pattern recognition method is composed of digital signal processing units and uses Hamming net algorithm for the recognition of ultrasonic waves. From the journal bearing wear test, the occurrence of adhesive wear of the white metal in rubbing contact with the shaft was exactly detected by this system, and the wear status of the journal bearing was monitored by measuring the wear thickness.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.97-103
• /
• 2001

The speaker recognition method using DTW algorithm has the problem that is reducing the performance of the speaker recognition system as the time variation. So there are many proposed algorithms to solve these problems. This paper proposes the new method If make the reference pattern that is acceptable to intra-speaker variation by reference pattern normalization. And to avoid reducing performance of speaker recognition system, we use the modified reference pattern to recognize the system user. The used methods in this paper are VQ and DTW. As the result of simulation we can obtain the $97.5\%$ of recognition accuracy rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2078-2093
• /
• 2019

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.5
• /
• pp.766-778
• /
• 2015

In this paper, we design a hybrid system for recognition and tracking realized with the aid of polynomial based RBFNNs pattern classifier and particle filter. The RBFNN classifier is built by learning the training data for diverse pose images. The optimized parameters of RBFNN classifier are obtained by Particle Swarm Optimization(PSO). Testing data for pose image is used as a face image obtained under real situation, where the face image is detected by AdaBoost algorithm. In order to improve the recognition performance for a detected image, pose estimation as preprocessing step is carried out before the face recognition step. PCA is used for pose estimation, the pose of detected image is assigned for the built pose by considering the featured difference between the previously built pose image and the newly detected image. The recognition of detected image is performed through polynomial based RBFNN pattern classifier, and if the detected image is equal to target for tracking, the target will be traced by particle filter in real time. Moreover, when tracking is failed by PF, Adaboost algorithm detects facial area again, and the procedures of both the pose estimation and the image recognition are repeated as mentioned above. Finally, experimental results are compared and analyzed by using Honda/UCSD data known as benchmark DB.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.215-220
• /
• 2002

This paper proposes a method to apply the Backpropagation(BP) algorithm of MVL(Multi-Valued Logic) Neural Network to pattern recognition. It extracts the property of an object density about an original pattern necessary for pattern processing and makes the property of the object density mapped to MVL. In addition, because it team the pattern by using multiple valued logic, it can reduce time f3r pattern and space fer memory to a minimum. There is, however, a demerit that existed MVL cannot adapt the change of circumstance. Through changing input into MVL function, not direct input of an existed Multiple pattern, and making it each variable loam by neural network after calculating each variable into liter function. Error has been reduced and convergence speed has become fast.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.6
• /
• pp.62-70
• /
• 2007

In this study, the natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.