• Geophysics and Geophysical Exploration
• /
• v.6 no.3
• /
• pp.119-125
• /
• 2003

The small-loop electromagnetic (EM) technique has been used successfully for many geophysical investigations, particularly for shallow engineering and environmental surveys. In conventional small loop EM operating at small induction numbers, geometric sounding has been widely used because the depth of penetration of EM energy depends only on the source-receiver separation. Recently developed small loop EM system, however, measures the secondary magnetic field, $H^S$, at multiple frequencies with a fixed source-receiver separation and frequency sounding is tried actively. In this study, we analyzed the behavior of in-phase and quadrature components of ${H^S}_z$, for horizonal coplanar (HCP) configuration over two-layer models. Through this theoretical analysis, it was found that the in-phase component of ${H^S}_z$ is more suitable for frequency sounding than the quadrature component. But, the in-phase component of ${H^S}_z$ is too small to measure, especially in resistive and noisy environment like Korea. Using the fact that the quadrature component is much greater than the in-phase component and the difference of quadrature component of ${H^S}_z$ measured at two frequencies shows the same behavoir as the in-phase component, we suggested an alternative frequency sounding technique. Also, we defined an apparent conductivity, which reflects well the conductivity of subsurface layers.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.348-355
• /
• 2010

In spite of development in speech recognition technology, speech recognition under noisy environment is still a difficult task. To solve this problem, Researchers has been proposed different methods where they have been used visual information except audio information for visual speech recognition. However, visual information also has visual noises as well as the noises of audio information, and this visual noises cause degradation in visual speech recognition. Therefore, it is one the field of interest how to extract visual features parameter for enhancing visual speech recognition performance. In this paper, we propose a method for visual feature parameter extraction based on image-base approach for enhancing recognition performance of the HMM based visual speech recognizer. For experiments, we have constructed Audio-visual database which is consisted with 105 speackers and each speaker has uttered 62 words. We have applied histogram matching, lip folding, RASTA filtering, Liner Mask, DCT and PCA. The experimental results show that the recognition performance of our proposed method enhanced at about 21% than the baseline method.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.9
• /
• pp.265-273
• /
• 2018

In this paper, we propose an acoustic event detection method in tunnels using non-negative tensor factorization (NTF) and hidden Markov model (HMM) applied to multi-channel audio signals. Incidents in tunnel are inherent to the system and occur unavoidably with known probability. Incidents can easily happen minor accidents and extend right through to major disaster. Most incident detection systems deploy visual incident detection (VID) systems that often cause false alarms due to various constraints such as night obstacles and a limit of viewing angle. To this end, the proposed method first tries to separate and detect every acoustic event, which is assumed to be an in-tunnel incident, from noisy acoustic signals by using an NTF technique. Then, maximum likelihood estimation using Gaussian mixture model (GMM)-HMMs is carried out to verify whether or not each detected event is an actual incident. Performance evaluation shows that the proposed method operates in real time and achieves high detection accuracy under simulated tunnel conditions.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.544-551
• /
• 2023

Speech enhancement used to improve the perceptual quality and intelligibility of noise speech has been studied as a method using a complex-valued spectrum that can improve both magnitude and phase in a method using a magnitude spectrum. In this paper, a study was conducted on how to apply attention mechanism to complex-valued spectrum-based speech enhancement systems to further improve the intelligibility and quality of noise speech. The attention is performed based on additive attention and allows the attention weight to be calculated in consideration of the complex-valued spectrum. In addition, the global average pooling was used to consider the importance of the feature map. Complex-valued spectrum-based speech enhancement was performed based on the Deep Complex U-Net (DCUNET) model, and additive attention was conducted based on the proposed method in the Attention U-Net model. The results of the experiments on noise speech in a living room environment showed that the proposed method is improved performance over the baseline model according to evaluation metrics such as Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short Time Object Intelligence (STOI), and consistently improved performance across various background noise environments and low Signal-to-Noise Ratio (SNR) conditions. Through this, the proposed speech enhancement system demonstrated its effectiveness in improving the intelligibility and quality of noisy speech.

• Journal of Preventive Medicine and Public Health
• /
• v.29 no.2 s.53
• /
• pp.239-254
• /
• 1996

Health services on industrial noisy environment have been provided only for noise-induced hearing loss management until now. But gradually, modem diseases and death have come to be related to stress and mental health deeply, therefore noise-induced mental disorder, like a stress became very important. In this point, the purpose of this study was to analyze the relationship between noise exposure level in worksite and workers' stress symptoms. This study included a survey of 786 manual workers selected from 89 worksites in 21 factories in Puchon. The results were as follows: 1. For demographic characteristics, most of the workers were males(80.8%), the $20\sim29years$ old were 34.5% and those who graduated from high school were 65.3%. The workers whose monthly income ranged from 100,000 to 800,000 won were 37.5% and who have a religion were 47.9%. 2. For occupational characteristics, workers who had worked $1\sim5$ years in the factories were 33.0%. Those who were much for them workload were 43.9% and who worked more than 8 hours a day were 73.9%. Those who were disatisfied with their job and pay were 31.9% and 50.6%. The workers who responsed ventilation condition of their worksites were bad were 51.9% and the dissatisfed with working environment of their worksites were 45.9%. 3. Workers who were suffering from tinnitus were 53.3% and those who perceived hearing loss were 50.1%. Persons who reported they always wore earplugs at work were 35.4%. Those who felt earplugs bigger than their ears were 30.6% and those who experienced eardiseases caused by earplugs were 25.6%. 4. For the noise exposure level in worksite, workers who were exposed to $80\sim90dB$ were 30.3%, $90\sim100dB$ were 26.4% and $50\sim70dB$ were 19.2%. 5. Workers' stress symptoms were significantly related to marital status and their monthly income(p<0.05). Workers who were single and had lower monthly income showed higher PSI (Psychiatric Symptom Index) scores than those who were married and had higher monthly income. Higher PSI scores were also significantly related to $1\sim2$ days hight-work per week, much for them workload, dissatisfaction with their job, and bad relationship with their bosses and coworkers. 6. Higher PSI scores were significantly related to severe tinnitus and perceived hearing losso(p<0.001). Workers who felt the earplugs they use did not fit their ears showed significantly higher PSI scores(p<0.01). Workers who reported that they did not feel they need earplugs showed. significantly higher PSI scores (p<0.05). Increased experience of eardisease caused by earplugs that did not fit were also significantly related to higher PSI scores(p<0.01). 7. The higher noise exposure level in worksite from 80dB was, the more severe stress symptoms including PSI subparts were reported; Anxiety, Anger, Depression, and Cognitive disorder(p<0.001). 5. According to the results of stepwise multiple regression analysis, factors affecting workers' PSI scores were perceived hearing loss$(R^2=0.160)$, noise exposure level in worksite$(R^2=0.110)$, realtionship with coworkers, amount of workload, monthly income and relationship with bosses orderly and the total $R^2$ of this 6 factors was 0.371. 9. The most significant factors that have impact on manual workers' stress symptoms were perceived hearing loss and noise exposure level in worksite, especially noise exposure level in the worksite was the most affective factor on the depression symptom.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.6
• /
• pp.875-882
• /
• 2021

To minimize occupational noise induced hearing loss, it is recommended that workers should not be exposed to noise levels exceeding 85 dBA for over 8 h. In the present study, noise exposure levels were measured for seven workers based on their tasks on a training ship. The A-weighted noise exposure level (L_ex,24h) was measured by taking into account the A-weighted equivalent continuous sound level (L_Aeq,i), duration (h) and noise contribution (L_ex,24h,i) from the workers' locations. Results are thus obtained for different job categories as follows: officer group L_ex,24h=56.1 dB, navigation crew L_ex,24h=58.9 dB, navigation cadet L_ex,24h=62.0 dB, ship's cook L_ex,24h=64.3 dB, engine cadet L_ex,24h=91.1 dB, engineer L_ex,24h=91.1 dB, and engine crew L_ex,24h=95.1 dB. It was determined that the engineers, engine crews, and engine cadets in charge of machinery must wear hearing protection devices. By wearing hearing protection devices when working in highly noisy engine rooms, it is estimated that the noise expose levels could be reduced by the following amounts: engineer L_ex,24h=23.1 dB, engine Crew L_ex,24h=24.4 dB, and engine cadet L_ex,24h=21.5 dB. Moreover, if the no. 2 lecture room and mess room bottom plates in the cadets accommodations were improved to the 64 mm A-60-class floating plates, then further reductions are possible as follows: navigation cadet L_ex,24h=4.3 dB and engine cadet L_ex,24h=1.8 dB.

• Korean Journal of Occupational Health Nursing
• /
• v.11 no.1
• /
• pp.13-30
• /
• 2002

Industrial shift workers feels suffer mental stresses which are caused by unfamiliar day sleep, noisy environment, sleeping disorder by bright light, unusual contacts with family, difficulty in meeting with friends or having formal social meetings and other social limitations such as the use of transportation. Such stresses influence health of the workers negatively. Thus the health promotion policy for shift workers should be made considering the workers' ways of living and shift work specially. This study attempted to provide basic information for development of the health promotion program for industrial shift workers by examining predictive factors influencing health promotion behaviors of those workers. In designing the study, three power generation plants located in Pusan and south Kyungsang province were randomly selected and therefrom 280 workers at central control, boiler and turbine rooms and environmental chemistry parts whose processes require shift works were sampled as subjects of the study. Data were collected two times from September 17 to October 8, 1999 using questionnaires with helps of safety and health managers of the plants. The questionnaires were distributed through mails or direct visits. Means for the study included the measurement tool of health promotion behavior provided by Park(1995), the tool of self-efficacy measurement by Suh(1995), the tool of internal locus of control measurement by Oh(1987), the measurement tool of perceived health state by Park(1995) and the tool of social support measurement by Paek(1995). The collected data were analyzed using SPSS program. Controlling factors of the subjects were evaluated in terms of frequency and percentage ratio Perceived factors and health promotion behaviors of the subjects were done so in terms of mean and standard deviation, and average mark and standard deviation, respectively. Relations between controlling and perceived factors were analyzed using t-test and ANOVA and those between perceived factors and the performance of health promotion behaviors, using Pearson's Correlation Coefficient. The performance of health promotion behaviors was tested using t-test, ANOVA and post multi-comparison (Scheffe test). Predictive factors of health promotion behavior were examined through the Stepwise Multiple Regression Analysis. Results of the study are summarized as follows. 1. The performance of health promotion behaviors by the subjects was evaluated as having the value of mean, $161.27{\pm}26.73$ points(min.:60, max.:240) and average mark, $2.68{\pm}0.44$ points(min.:1, max.:4). When the performance was analyzed according to related aspects, it showed the highest level in harmonious relation with average mark, $3.15{\pm}.56$ points, followed by hygienic life($3.03{\pm}.55$), self-realization ($2.84{\pm}.55$), emotional support($2.73{\pm}.61$), regular meals($2.71{\pm}.76$), self-control($2.62{\pm}.63$), health diet($2.62{\pm}.56$), rest and sleep($2.60{\pm}.59$), exercise and activity($2.53{\pm}.57$), diet control($2.52{\pm}.56$) and special health management($2.06{\pm}.65$). 2. In relations between perceived factors of the subjects(self-efficacy, internal locus of control, perceived health state) and the performance of health promotion behaviors, the performance was found having significantly pure relations with self-efficacy (r=.524, P=.000), internal locus of control (r=.225, P=.000) and perceived health state(r=.244, P=.000). The higher each evaluated point of the three factors was, the higher the performance was in level. 3. When relations between the controlling factors(demography-based social, health-related, job-related and human relations characteristics) and the performance of health promotion behaviors were analyzed, the performance showed significant differences according to marital status (t=2.09, P= .03), religion(F=3.93, P= .00) and participation in religious activities (F=8.10, P= .00) out of demography-based characteristics, medical examination results (F=7.20, P= .00) and methods of the collection of health knowledge and information(F=3.41, P= .01) and methods of desired health education(F=3.41, P= .01) out of health-related characteristics, detrimental factors perception(F=4.49, P= .01) and job satisfaction(F=8.41, P= .00) out of job-related characteristics and social support(F=14.69, P= .00) out of human relations characteristics. 4. The factor which is a variable predicting best the performance of health promotion behaviors by the subjects was the self-efficacy accounting for 27.4% of the prediction, followed by participation in religious activities, social support, job satisfaction, received health state and internal locus of control in order all of which totally account for 41.0%. In conclusion, the predictive factor which most influence the performance of health promotion behaviors by shift workers was self-efficacy. To promote the sense, therefore, it is necessary to develop the nursing intervention program considering predictive factors as variables identified in this study. Further industrial nurses should play their roles actively to help shift workers increase their capability of self-management of health.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.4
• /
• pp.347-357
• /
• 2003

This paper describes on the suppression of sea clutter on marine radar display using a cell-averaging CFAR(constant false alarm rate) technique, and on the analysis of radar echo signal data in relation to the estimation of ARPA functions and the detection of the shadow effect in clutter returns. The echo signal was measured using a X -band radar, that is located on the Pukyong National University, with a horizontal beamwidth of $$3.9^{\circ}$$, a vertical beamwidth of $20^{\circ}$, pulsewidth of $0.8 {\mu}s$ and a transmitted peak power of 4 ㎾ The suppression performance of sea clutter was investigated for the probability of false alarm between $l0-^0.25;and; 10^-1.0$. Also the performance of cell averaging CFAR was compared with that of ideal fixed threshold. The motion vectors and trajectory of ships was extracted and the shadow effect in clutter returns was analyzed. The results obtained are summarized as follows；1. The ARPA plotting results and motion vectors for acquired targets extracted by analyzing the echo signal data were displayed on the PC based radar system and the continuous trajectory of ships was tracked in real time. 2. To suppress the sea clutter under noisy environment, a cell averaging CFAR processor having total CFAR window of 47 samples(20+20 reference cells, 3+3 guard cells and the cell under test) was designed. On a particular data set acquired at Suyong Man, Busan, Korea, when the probability of false alarm applied to the designed cell averaging CFAR processor was 10$^{-0}$.75/ the suppression performance of radar clutter was significantly improved. The results obtained suggest that the designed cell averaging CFAR processor was very effective in uniform clutter environments. 3. It is concluded that the cell averaging CF AR may be able to give a considerable improvement in suppression performance of uniform sea clutter compared to the ideal fixed threshold. 4. The effective height of target, that was estimated by analyzing the shadow effect in clutter returns for a number of range bins behind the target as seen from the radar antenna, was approximately 1.2 m and the information for this height can be used to extract the shape parameter of tracked target..

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.453-462
• /
• 2021

A lot of license plate data is required for car number recognition. License plate data needs to be balanced from past license plates to the latest license plates. However, it is difficult to obtain data from the actual past license plate to the latest ones. In order to solve this problem, a license plate recognition study through deep learning is being conducted by creating a synthetic license plates. Since the synthetic data have differences from real data, and various data augmentation techniques are used to solve these problems. Existing data augmentation simply used methods such as brightness, rotation, affine transformation, blur, and noise. In this paper, we apply a style transformation method that transforms synthetic data into real-world data styles with data augmentation methods. In addition, real license plate data are noisy when it is captured from a distance and under the dark environment. If we simply recognize characters with input data, chances of misrecognition are high. To improve character recognition, in this paper, we applied the DeblurGANv2 method as a quality improvement method for character recognition, increasing the accuracy of license plate recognition. The method of deep learning for license plate detection and license plate number recognition used YOLO-V5. To determine the performance of the synthetic license plate data, we construct a test set by collecting our own secured license plates. License plate detection without style conversion recorded 0.614 mAP. As a result of applying the style transformation, we confirm that the license plate detection performance was improved by recording 0.679mAP. In addition, the successul detection rate without image enhancement was 0.872, and the detection rate was 0.915 after image enhancement, confirming that the performance improved.