• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.308-313
• /
• 2004

In this paper, we compared and analyzed the discrimination performance of speech/music about combinations of each features parameter. Audio signals are classified into 3 classes (speech, music, speech and music). On three types of features, Mel-cepstrum, energy, zero-crossings used to the experiments. Then compared and analyzed the best of the combinations between features to speech/ music discrimination performance. The best result is achieved using Mel-cepstrum, energy and zero-crossings in a single feature vector (speech: 95.1%, music: 61.9%, speech & music: 55.5%).

• Journal of the Korean Vacuum Society
• /
• v.6 no.1
• /
• pp.97-102
• /
• 1997

A medium energy ion scattering spectroscopy(ME1S) system has been developed and tested.In the MEIS system a toroidal electrostatic energy analyzer(TEA) and a two dimensional position sensitivedetector(PSD) were used. The energy resolution of MEIS system was estimated to be less than $4\times 10^{-3}$ and the overall angular resolution was less than 0.3". From the MEIS spectrum of $Ta_2O_5$(300 $\AA$)/ onSi analyzedousing 60 keV $H^+$, the energy loss factor(S.1 and depth resolution were estimated to he 42 eV/$\AA$ and 9.7 $\AA$, respectively. Also Si(100) surface was analyzed using the MEIS system. A random MElSspectrum was obtained from thc Si(100) covered with native oxide layers. At the double alignment condition, MElS spectrum showed ;i Si surface peak, a oxygen peak and a carbon peak.nd a carbon peak.

• Microbiology and Biotechnology Letters
• /
• v.30 no.2
• /
• pp.167-171
• /
• 2002

The resting cells of Candida sp. SY16 produced a large amount of mannosylerythritol lipid as a biosurfactant when incubated in the distilled water containing only the carbon source. The resting cells exhibited the highest production at 20 g cells per liter on the soybean oil of 75 g/1 as a sole substrate and pH 4∼5 in the shaking culture. Under the optimal conditions, the biosurfactant was extracellularly produced to 58 g/1 after 120 h in jar fermentor, and the yield became higher than that obtained by using the glowing cells of the strain in batch fermentation.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• International Journal of Fluid Machinery and Systems
• /
• v.9 no.1
• /
• pp.47-55
• /
• 2016

The portable hydraulic turbine we previously developed for open channels comprises an axial flow runner with an appended collection device and a diffuser section. The output power of this hydraulic turbine was improved by catching and accelerating an open-channel water flow using the kinetic energy of the water. This study aimed to further improve the performance of the hydraulic turbine. Using numerical analysis, we examined the performances and flow fields of a single runner and a composite body consisting of the runner and collection device by varying the airfoil and number of blades. Consequently, the maximum values of input power coefficient of the Runner D composite body with two blades (which adopts the MEL031 airfoil and alters the blade angle) are equivalent to those of the composite body with two blades (MEL021 airfoil). We found that the Runner D composite body has the highest turbine efficiency and thus the largest power coefficient. Furthermore, the performance of the Runner D composite body calculated from the numerical analysis was verified experimentally in an open-channel water flow test.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.6
• /
• pp.1393-1401
• /
• 2019

Recently as voice authentication function is installed in the system, it is becoming more important to accurately authenticate speakers. Accordingly, a model for verifying speakers in various ways has been suggested. In this paper, we propose a new method for verifying speaker verification using a Short-time Fourier Transform(STFT). Unlike the existing Mel-Frequency Cepstrum Coefficients(MFCC) extraction method, we used window function with overlap parameter of around 66.1%. In this case, the speech characteristics of the speaker with the temporal characteristics are studied using a deep running model called RNN (Recurrent Neural Network) with LSTM cell. The accuracy of proposed model is around 92.8% and approximately 5.5% higher than that of the existing speaker certification model.

• The Korean Journal of Physiology and Pharmacology
• /
• v.19 no.1
• /
• pp.29-34
• /
• 2015

Fucoidan, a fucose-rich sulfated polysaccharide derived from brown seaweed in the class Phaeophyceae, has been widely studied for its possible health benefits. However, the potential of fucoidan as a possible treatment for hyperpigmentation is not fully understood. This study investigated the effects of fucoidan on melanogenesis and related signaling pathways using Mel-Ab cells. Fucoidan significantly decreased melanin content. While fucoidan treatment decreased tyrosinase activity, it did not do so directly. Western blot analysis indicated that fucoidan downregulated microphthalmia-associated transcription factor and reduced tyrosinase protein expression. Further investigation showed that fucoidan activated the extracellular signal-regulated kinase (ERK) pathway, suggesting a possible mechanism for the inhibition of melanin synthesis. Treatment with PD98059, a specific ERK inhibitor, resulted in the recovery of melanin production. Taken together, these findings suggest that fucoidan inhibits melanogenesis via ERK phosphorylation.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.22-34
• /
• 2024

Exposure to varied noisy environments impairs the recognition performance of artificial intelligence-based speech recognition technologies. Degraded-performance services can be utilized as limited systems that assure good performance in certain environments, but impair the general quality of speech recognition services. This study introduces an audiovisual speech recognition (AVSR) model robust to various noise settings, mimicking human dialogue recognition elements. The model converts word embeddings and log-Mel spectrograms into feature vectors for audio recognition. A dense spatial-temporal convolutional neural network model extracts features from log-Mel spectrograms, transformed for visual-based recognition. This approach exhibits improved aural and visual recognition capabilities. We assess the signal-to-noise ratio in nine synthesized noise environments, with the proposed model exhibiting lower average error rates. The error rate for the AVSR model using a three-feature multi-fusion method is 1.711%, compared to the general 3.939% rate. This model is applicable in noise-affected environments owing to its enhanced stability and recognition rate.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.16 no.6
• /
• pp.1270-1276
• /
• 2002

Compounds 1 - 12 were tested for their growth inhibitory effects against tumor cell lines using two different 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl-2H-tetrazolium bromide (MTT) and sulforhodamine B protein (SRB) assays and antimicrobial activity. The cytotoxic activity of methyl-4-[{(2E)-3,7-dimethyl-2,6-octadienyl}oxy]-3-methoxy benzoate (1) exhibit more active than that of 5-fluorouracil (11) on human oral epithelioid carcinoma (KB, ATCC No. OCL 17) cell lines. But this compound (1) on human skin melanoma (SK-MEL-3, HBT 69) cell lines shows less active than that of adriamycin (12). However, compound 9 showed the antimicrobial activity against S. epidermidis (MIC, 15.625 ㎍/㎖), S. aureus, C. albicans (MIC, 31.25 ㎍/㎖), S. mutans, S. typhimurium, P. putida (MIC. 125 ㎍/㎖) and P. aeruginosa (MIC, 500 ㎍/㎖).

• Archives of Pharmacal Research
• /
• v.19 no.6
• /
• pp.559-561
• /
• 1996

A minor cytotoxic compound was isolated by bioassay-guided fractionation from Asiasari Radix and identified as aristolactam III(1) on the basis of spectral data and chemical evidence. This is the first report on the isolation of compound 1 from Asiasarum genus. Compound 1 exhibited a significant cytotoxic activity against the three kinds of human cancer cell lines (A 549, SK-MEL-2 and SK-OV-3).