• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.131-139
• /
• 2013

In this paper, we look into previous research in relation to each processing step for ECG diagnosis and propose detection and classification method of arrhythmia using rhythm features of ECG signal. Rhythm features for distribution of rhythm and heartbeat such as identity, regularity, etc. are extracted in feature extraction, and rhythm type is classified using rule-base constructed in advance for features of rhythm section in rhythm classification. Experimental results for all of rhythm types in the MIT-BIH arrhythmia database show detection performance of 100% for arrhythmia with only normal rhythm rule and applicability of classification for rhythm types with arrhythmia rhythm rules.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.43-51
• /
• 2013

Classification result by comprehensive analysis of rhythm section and heartbeat unit makes a reliable diagnosis of heart disease possible. In this paper, based on feature-points of ECG signals, rhythm analysis for constant section and heartbeat unit is conducted using rule-based classification and SVM-based classification respectively. Rhythm types are classified using a rule base deduced from clinical materials for features of rhythm section in rule-based classification, and monotonic rhythm or major abnormality heartbeats are classified using multiple SVMs trained previously for features of heartbeat unit in SVM-based classification. Experimental results for the MIT-BIH arrhythmia database show classification ratios of 68.52% by rule-based method alone and 87.04% by fusion method of rule-based and SVM-based for 11 rhythm types. The proposed fusion method is improved by about 19% through misclassification improvement for monotonic and arrangement rhythms by SVM-based method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.4
• /
• pp.405-413
• /
• 2012

Low misclassification performance is significant with high classification accuracy for a reliable diagnosis of ECG signals, and diagnosing abnormal state as normal state can especially raises a deadly problem to a person in ECG test. In this paper, we propose detection and classification method of abnormal rhythm by rule-based rhythm classification reflecting clinical criteria for disease. Rule-based classification classifies rhythm types using rule-base for feature of rhythm section, and rule-base deduces decision results corresponding to professional materials of clinical and internal fields. Experimental results for the MIT-BIH arrhythmia database show that the applicability of proposed method is confirmed to classify rhythm types for normal sinus, paced, and various abnormal rhythms, especially without misclassification in detection aspect of abnormal rhythm.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.217-223
• /
• 2023

In this paper, we propose a new model for the conditional generation of music, considering key and rhythm, fundamental elements of music. MIDI sheet music is converted into a WAV format, which is then transformed into a Mel Spectrogram using the Short-Time Fourier Transform (STFT). Using this information, key and rhythm details are classified by passing through two Convolutional Neural Networks (CNNs), and this information is again fed into the Music Transformer. The key and rhythm details are combined by differentially multiplying the weights and the embedding vectors of the MIDI events. Several experiments are conducted, including a process for determining the optimal weights. This research represents a new effort to integrate essential elements into music generation and explains the detailed structure and operating principles of the model, verifying its effects and potentials through experiments. In this study, the accuracy for rhythm classification reached 94.7%, the accuracy for key classification reached 92.1%, and the Negative Likelihood based on the weights of the embedding vector resulted in 3.01.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.2E
• /
• pp.56-62
• /
• 2007

This paper presents the automatic music emotion classification on acoustic data. A three-level structure is developed. The low-level extracts the timbre and rhythm features. The middle-level estimates the indication functions that represent the emotion probability of a single analysis unit. The high-level predicts the emotion result based on the indication function values. Experiments are carried out on 695 homogeneous music pieces labeled with four emotions, including pleasant, calm, sad, and excited. Three machine learning methods, GMM, MLP, and SVM, are compared on the high-level. The best result of 90.16% is obtained by MLP method.

• Journal of Korean Physical Therapy Science
• /
• v.3 no.4
• /
• pp.139-145
• /
• 1996

This study was carried out to investigate the scapular rhythm of normal persons. 16 persons was no disease, injury and after-effect in period for July 1, 1996 to July 14, 1996. The statistical measures were performed by SPSS/PC t-test for classification. The result of this study were as follow : 1. There was a significant difference between the body median line and scapular superior angle from the mean distance in 83.4 mm of male and 86.0 mm of female to shoulder neutral position(p<0.05). 2. The mean distance of body median line between scapular inferior angle was 97.9 mm of male and 92.0 mm of female to shoulder neutral position. 3. There was a significant difference between the body median line and scapular inferior angle from the mean distance with male and female to shoulder abduction $90^{\circ}$ position(p<0.05). 4. The mean angle of body median line between scapular angle was $6.4^{\circ}$ of male and $4.4^{\circ}$ of female with shoulder neutral position. 5. The mean ratio of scapular rhythm was 5.6 : 1 in shoulder abduction of $90^{\circ}$ and 5.1 : 1 in shoulder abduction of 180.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.55-64
• /
• 2015

The present study identified the brain based learning activities on the individual learning senses by using the brain laterality and the whole brain index. Students receive the information through the visual, auditory, and kinesthetic senses by Politano and Paquin's (2000) classification. These learning senses are reflected on brain by the various combinations of senses for learning. Measuring the types of the learning senses involving in brain laterality and whole brain is required to figure out the related learning styles. Self-directed learning involved in the learning senses shows the problem-based learning associated to the brain function by emphasizing the balanced brain utilization which is known as whole brain. These research results showed the successful whole brain learning is closely associated with elevated auditory learning and elevated visual learning in sensorimotor brainwave rhythm (SMR) while it shows the close association with elevated kinesthetic and elevated visual learning in beta brainwave rhythm.

• Journal of Oriental Neuropsychiatry
• /
• v.18 no.2
• /
• pp.89-100
• /
• 2007

Objective : The purpose of this study is to examine relationship between cognitive function and sasang constitution by analyzing EEG status of company workers in Cheon-An. Method : 59 company workers were tested with cognitive assessment EEG program and questionaire for the Sasang Constitution Classification II. They were assorted by Sasang Constitutions, and we analyzed its correlation with cognitive assessment score and EEG data. Results : 1. According to mean active EEG rhythm of Alpha. H-Beta, Gamma wave, there were no significant difference among Sasang Constitution. 2. According to mean success, error, concentration, response, workload and left/right brain activity score, there were no significant difference among Sasang Constitution. 3. According to mean active EEG rhythm of Theta, SMR, M-Beta wave, Soyangin(少陽人)'s value was significantly higher than that of Taeumin(太陰人) 4. According to mean cognitive strenghth score, Soyangin(少陽人)'s value was significantly higher than that of Taeumin(太陰人). Conclusion : In conclusion, Sasang Constitutional difference has no relevance with cognitive abilities However, Soyangin(少陽人) showed higher mean active EEG rhythm of Theta, SMR, M-Beta wave than that of Taeumin(太陰人). In addition, Soyangin(少陽人) also showed higher mean cognitive strenghth score than that of Taeumin(太陰人).

• Journal of Information Processing Systems
• /
• v.13 no.2
• /
• pp.400-416
• /
• 2017

Music emotion is an important component in the field of music information retrieval and computational musicology. This paper proposes an approach for automatic emotion classification, based on rough set (RS) theory. In the proposed approach, four different sets of music features are extracted, representing dynamics, rhythm, spectral, and harmony. From the features, five different statistical parameters are considered as attributes, including up to the $4^{th}$ order central moments of each feature, and covariance components of mutual ones. The large number of attributes is controlled by RS-based approach, in which superfluous features are removed, to obtain indispensable ones. In addition, RS-based approach makes it possible to visualize which attributes play a significant role in the generated rules, and also determine the strength of each rule for classification. The experiments have been performed to find out which audio features and which of the different statistical parameters derived from them are important for emotion classification. Also, the resulting indispensable attributes and the usefulness of covariance components have been discussed. The overall classification accuracy with all statistical parameters has recorded comparatively better than currently existing methods on a pair of datasets.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.4
• /
• pp.33-38
• /
• 2009

This paper proposes an automatic equalizer control method in automobile audio system. The proposed method discriminates the music segment from the consecutive real-time audio stream of the radio and the equalizer is controlled automatically according to the classified genre of the music segment. For enhancing the accuracy of the music genre classification in real-time, timbre feature and rhythm feature extracted from the consecutive audio stream is applied to GMM(Gaussian mixture model) classifier. The proposed method evaluates the performance of the music genre classification, which classified various audio segments segmented from the audio signal of the radio broadcast in automobile audio system into one of five music genres.