• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.11a
• /
• pp.521-526
• /
• 2003

In this study the traffic noises were investigated for the subjective allowing limitation ion and the testified classes, 7 point scale was selected to evaluate the annoyance level with vocabularies. As a result, 'relatively annoying' is the most suitable expression for the allowing 1imitation, and the sound pressure levels for the traffic was 44.4㏈.

• The Korean Journal of Zoology
• /
• v.39 no.2
• /
• pp.207-214
• /
• 1996

Five call types of the genus Hyla in habitats around South Korea were classified according to some attributes of their advertisement calls (note duration, note intenral, dominant frequency, sonagram patterns. Among the call types, the E-type was more distinctive than the other call types in that it had a metal sound and much longer note duration and note intenral. This result indicated that some divergence had occurred in the advertisement call of the genus Hylo, though this was found in alimited number of regions and its occurrence was small.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.239-246
• /
• 2023

In this paper, we propose an open-loop algorithm to classify speech and music signals using the spectral flux parameters and Mel Frequency Cepstral Coefficients(MFCC) parameters for the audio coder. To increase responsiveness, the MFCC was used as a short-term feature parameter and spectral fluxes were used as a long-term feature parameters to improve accuracy. The overall voice/music signal classification decision is made by combining the short-term classification method and the long-term classification method. The Gaussian Mixed Model (GMM) was used for pattern recognition and the optimal GMM parameters were extracted using the Expectation Maximization (EM) algorithm. The proposed long-term and short-term combined speech/music signal classification method showed an average classification error rate of 1.5% on various audio sound sources, and improved the classification error rate by 0.9% compared to the short-term single classification method and 0.6% compared to the long-term single classification method. The proposed speech/music signal classification method was able to improve the classification error rate performance by 9.1% in percussion music signals with attacks and 5.8% in voice signals compared to the Unified Speech Audio Coding (USAC) audio classification method.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.91-98
• /
• 2018

Automatic detection of pig wasting diseases is an important issue in the management of group-housed pigs. In particular, porcine respiratory diseases are one of the main causes of mortality among pigs and loss of productivity in intensive pig farming. In this paper, we propose a noise-robust system for the early detection and recognition of pig wasting diseases using sound data. In this method, first we convert one-dimensional sound signals to two-dimensional gray-level images by normalization, and extract texture images by means of dominant neighborhood structure technique. Lastly, the texture features are then used as inputs of convolutional neural networks as an early anomaly detector and a respiratory disease classifier. Our experimental results show that this new method can be used to detect pig wasting diseases both economically (low-cost sound sensor) and accurately (over 96% accuracy) even under noise-environmental conditions, either as a standalone solution or to complement known methods to obtain a more accurate solution.

• Journal of Oral Medicine and Pain
• /
• v.20 no.2
• /
• pp.407-420
• /
• 1995

This study was performed to evaluate and compare conservative treatment results by several parameters such as age, sex, symptom duration, type and timing of joint sound, parafunctional habits, splint type, and diagnostic classification. There have been too many articles reporting long term results of conservative treatment but articles related to comparison of treatment results by patients' self-evaluation have been rarely reported. For this study 258 patients with temporomandibular disorders(TMDs) were selected and examined by routine diagnostic procedure for TMDs. The subjects were classified into 5 TMDs subgroups ad treated with conservative treatments involving splints, physical modalities, jaw exercises, and counseling. Visual analogue scale(VAS) about pain, joint sound, and mouth opening limitation was recorded respectively during treatment period. From the VAS data and treatment duration, VAS treatment index(VAS Ti) was calculated. The obtained results were as follows : 1. Pain was the most frequent main symptom in subjects with temporomandibular disorders, and main symptom for mouth opening limitation was comparatively less than for pain or sound in disk displacement with reduction group or in degenerative joint disease group. 2. Degenerative joint disease group had the most poor treatment results and highest occlusal index of Helkim's index. 3. Good prognosis for conservative treatment was observed in acute group, under 6 months than chronic group, 6months over in symptom duration, and subjects with 40 years over in age showed the most poor prognosis. 4. Subjects treated with anterior repositioning splint had better treatment results than subjects treated with centric relation splint, but statistical significance in VAS Ti and treatment duration was not observed. 5. Treatment results according to affected side, types and point of joint sound did not show consistent statistical results. 6. The result for conservative treatment was observed poor in subjects with bruxism and clenching. 7. In studying coincidence between preferred chewing and affected side, frequency of preferred chewing side, in unilateral affection, was higher in ipsilateral than in contralateral side.

• The Journal of the Korea Contents Association
• /
• v.10 no.12
• /
• pp.27-33
• /
• 2010

In this study, we conducted the classification experiments with GMM (Gaussian Mixture Model) from combining the extracted features by using microphone, Gyro sensor and Acceleration sensor in 9 different environment types. Existing studies of Context Aware wanted to recognize the Environment situation mainly using the Environment sound data with microphone, but there was limitation of reflecting recognition owing to structural characteristics of Environment sound which are composed of various noises combination. Hence we proposed the additional application methods which added Gyro sensor and Acceleration sensor data in order to reflect recognition agent's movement feature. According to the experimental results, the method combining Acceleration sensor data with the data of existing Environment sound feature improves the recognition performance by more than 5%, when compared with existing methods of getting only Environment sound feature data from the Microphone.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.28 no.1
• /
• pp.155-169
• /
• 1998

The purpose of this study was to prove the relationship between arthrographic and clinical features in temporomandibular joint disorders. In order to carry out this study, ninety-eight arthrographic examinations of temporomandibular joints were performed on eighty-two patients who had the temporomandibular joint disorders. As the arthrographic examination, the cases were classified in three groups, disk displacement with reduction, disk displacement without reduction, within normal limit. After this, the cases were clinically examined, and the results were compared and analyzed in each other group. The obtained results were as follows; 1. As the classification by arthrographic examination, three groups (disc displacement with reduction, disc displacement without reduction, within normal limit) were 41 ％, 54％, 5％ of total cases in this study, respectively. 2. The third decade(65％) was most frequent in this study. The average age of each group (disc displacement with reduction, disc displacement without reduction, within normal limit) was 24, 28, 21, and disc displacement without reduction group was higher than any other group. 3. In the chief complaint, pain was the most frequent in all three groups. Joint sound was also frequent in disc displacement with reduction group, but in disc displacement without reduction group, limitation of mouth opening was more frequent. 4. Of the various pain, the movement pain was most frequent ( 61 ％) in this study. In joint sound, click(63％) was the most frequent in disc displacement with reduction group, but sound history(42％) and no sound (31 ％) were more frequent in disc displacement without reduction group. 5. The average maximum opening of each group (disc displacement with reduction, disc displacement without reduction, within normal limit) was 44mm, 32.9mm, 44mm, and disc displacement without reduction group was less than any other group. 6. The masticatory disturbance of each group (disc displacement with reduction, disc displacement without reduction, within normal limit) was 53％, 79％, 40％, and the trauma history of each group was 50％, 40％,60％.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.11
• /
• pp.1020-1028
• /
• 2011

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying artificial neural network. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes a neural-network-based fault diagnosis system using AR coefficients as feature vectors by LPC(linear predictive coding) and EIV(errors-in variables) analysis. We extracted feature vectors from sound, vibration and current faulty signals and evaluated the suitability of feature vectors depending on the classification results and training error rates by changing AR order and adding noise. From experimental results, we conclude that classification results using feature vectors by EIV analysis indicate more than 90 % stably for less than 10 orders and noise effect comparing to LPC.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.224-231
• /
• 2013

Defining the concept of prominent audio content as the most informative audio content from the users' perspective within a given unstructured audio segment, we propose a simple but robust intensity-based attack/release pattern features to detect the prominent audio content. We also propose a web-based annotation procedure to retrieve users' subjective perception and annotated 18 hours of video clips across various genres, such as cartoon, movie, news, etc. The experiments with a linear classification method whose models are trained for speech, music, and sound effect demonstrate promising - but varying across the genres of programs - results (e.g., 86.7% weighted accuracy for speech-oriented talk shows and 49.3% weighted accuracy for {action movies}).

• ETRI Journal
• /
• v.44 no.3
• /
• pp.413-425
• /
• 2022

The study of literary texts is one of the earliest disciplines practiced around the globe. Poetry is artistic writing in which words are carefully chosen and arranged for their meaning, sound, and rhythm. Poetry usually has a broad and profound sense that makes it difficult to be interpreted even by humans. The essence of poetry is Rasa, which signifies mood or emotion. In this paper, we propose a poetry classification-based approach to automatically extract similar poems from a repository. Specifically, we perform a novel Rasa-based classification of Hindi poetry. For the task, we primarily used lexical features in a bag-of-words model trained using the support vector machine classifier. In the model, we employed Hindi WordNet, Latent Semantic Indexing, and Word2Vec-based neural word embedding. To extract the rich feature vectors, we prepared a repository containing 37 717 poems collected from various sources. We evaluated the performance of the system on a manually constructed dataset containing 945 Hindi poems. Experimental results demonstrated that the proposed model attained satisfactory performance.