• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.688-690
• /
• 2004

최근 전자화된 문서 영상을 효율적으로 관리하고 검색하기 위한 문서구조분석 방법과 문서의 자동 분류에 관한 많은 연구가 발표되고 있다. 본 논문에서는 NMF(non-negative matrix factorization) 알고리즘을 사용하여 폰트를 자동으로 분류하는 방법을 제안한다. 제안된 방법은 폰트의 구분 특징들이 공간적으로 국부성을 가지는 부분으로 표현될 수 있다는 가정을 바탕으로, 전체의 폰트 이미지들로부터 각 폰트들의 구분 특징인 부분을 학습하고, 학습된 부분들을 특징으로 사용하여 폰트를 분류하는 방법이다. 학습된 폰트의 특징들은 계층적 군집화 알고리즘을 이용하여 템플릿을 생성하고, 테스트 패턴을 분류하기 위하여 템플릿 패턴과의 EMD(earth mover's distance)를 사용한다. 실험결과에서 폰트 이미지들의 공간적으로 국부적인 특징들이 조사되고, 그 특징들의 폰트 식별을 위한 적절성을 보였다. 제안된 방법이 기존의 문자인식. 문서 검색 시스템들의 전처리기로 사용되면. 그 시스템들의 성능을 향상시킬 것으로 기대된다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.46-54
• /
• 2006

Recently, the important of a personal identification is increasing according to expansion using each on-line commercial transaction and personal ID-card. Although a personal ID-card embedded RFID(Radio Frequency Identification) tag is gradually increased, the way for a person's identification is deficiency. So we need automatic methods. Because RFID tag is vary small storage capacity of memory, it needs effective feature extraction method to store personal biometrics information. We need new recognition method to compare each feature. In this paper, we studied the face verification system using Hippocampal neuron modeling algorithm which can remodel the hippocampal neuron as a principle of a man's brain in engineering, then it can learn the feature vector of the face images very fast. and construct the optimized feature each image. The system is composed of two parts mainly. One is feature extraction using NMF(Non-negative Matrix Factorization) and LDA(Linear Discriminants Analysis) mixture algorithm and the other is hippocampal neuron modeling and recognition simulation experiments confirm the each recognition rate, that are face changes, pose changes and low-level quality image. The results of experiments, we can compare a feature extraction and learning method proposed in this paper of any other methods, and we can confirm that the proposed method is superior to the existing method.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.47 no.2
• /
• pp.179-184
• /
• 2021

Stratum corneum known as a skin barrier, which maintains water in skin, is the outer layer of the skin. Natural moisturizing factors (NMF) are one of the constituents in stratum corneum and amino acids are the highest components among NMF. In this study, we designed stearic acid-based solid lipid nanoparticles (SLNs) for improved skin penetration of serine (Ser). Ser-capsulated SLN was manufactured by double-melting emulsification method. The mean particle size and zeta potential of SLNs were 256.30 ~ 416.93 nm and -17.60 ~ -35.27 mV, respectively. The higher the degree of hydrophobicity or hydrophilicity of emulsifiers, the smaller the particle size and the higher the stability and capsulation rate. In addition, skin penetration was conducted using SkinEthic^TM RHE which is one of the reconstructed human epidermis models. The results of Ser penetration demonstrated that all SLNs enhanced than serine solution. The amount of enhanced Ser penetration from SLNs were approximately 4.1 ~ 6.2 times higher than that from Ser solution. Therefore, Ser-loaded SLN might be a promising drug delivery system for moisturizing formulation in cosmeceutical.

• Journal of Nutrition and Health
• /
• v.39 no.6
• /
• pp.520-528
• /
• 2006

Free amino acids in epidermis function as a major component of Natural Moisturizing Factor (NMF), which maintains the optimal level of water in skin even at the low humidity. In fact, the depletion of free amino acids is reported in the epidermis of atopic dermatitis, the skin condition involving dryness. As an effort searching the dietary source for improving the level of water and free amino acid in epidermis, the dietary effects of silk protein, sericin (S) and fibroin (F) on trans epidermal water loss (TEWL), and plasma and epidermal levels of free amino acids were compared in this study. Thirty of male NC/Nga mice, an animal model of atopic dermatitis, were divided into three groups: group CA as an atopic control with control diet, group S: 1% sericin diet and group F: 1% fibroin diet. Ten of male BALB/c mice were served as group C (control group) with control diet. All mice were fed on diet and water ad libitum for 10weeks. Dry skin condition was established in group CA as TEWL was increased (148.7% of group C). In parallel, epidermal level of glutamate, one of major amino acids functioning as NMF, was dramatically decreased and epidermal levels of methionine and alanine were inversely elevated. Dietary supplementation of sericin (group S) reduced TEWL at the similar level with group C and increased epidermal levels of glutamate as well as serine and glycine, the other major amino acids as NMF. Despite a marked decrease of methionine and alanine, the reduction of TEWL and epidermal levels of glutamate, serine and glycine of group F were less than of group S. Furthermore, in contrast to similar levels of other free amino acids in plasma and epidermis of group S and group C, plasma and epidermal levels of other free amino acids, specifically phenylalanine, isoleucine, cysteine and tyrosine in epidermis of group F, were significantly higher than of group C. Together, our data demonstrate that dietary supplementation of sericin is more effective at improving dry skin condition that paralleled with the normalization of free amino acids in plasma and epidermis of NC/Nga mice.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.8
• /
• pp.3689-3696
• /
• 2011

In decision support system, knowledge workers require aggregation operations of the large data and are more interested in the trend analysis rather than in the punctual analysis. Therefore, it is necessary to provide fast approximate answers rather than exact answers, and to research approximate query answering techniques. In this paper, we propose a new approximation query answering method which is based on Fuzzy C-means clustering (FCM) method and Adaptive Neuro-Fuzzy Inference System (ANFIS). The proposed method using FCM-ANFIS can compute aggregate queries without accessing massive multidimensional data cube by producing the KR model of multidimensional data cube. In our experiments, we show that our method using the KR model outperforms the NMF method.

• Journal of Ubiquitous Convergence Technology
• /
• v.2 no.1
• /
• pp.18-26
• /
• 2008

The invariance relation existing in the non-negative matrix factorization (NMF) is used for constructing robust image hashes in this work. The image is first re-scaled to a fixed size. Low-pass filtering is performed on the luminance component of the re-sized image to produce a normalized matrix. Entries in the normalized matrix are pseudo-randomly re-arranged under the control of a secret key to generate a secondary image. Non-negative matrix factorization is then performed on the secondary image. As the relation between most pairs of adjacent entries in the NMF's coefficient matrix is basically invariant to ordinary image processing, a coarse quantization scheme is devised to compress the extracted features contained in the coefficient matrix. The obtained binary elements are used to form the image hash after being scrambled based on another key. Similarity between hashes is measured by the Hamming distance. Experimental results show that the proposed scheme is robust against perceptually acceptable modifications to the image such as Gaussian filtering, moderate noise contamination, JPEG compression, re-scaling, and watermark embedding. Hashes of different images have very low collision probability. Tampering to local image areas can be detected by comparing the Hamming distance with a predetermined threshold, indicating the usefulness of the technique in digital forensics.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.11
• /
• pp.5150-5155
• /
• 2011

Alzheimer's disease (AD) and vascular dementia (VD) are the most common dementia. In this paper, we proposed a region selection for classification of AD, VD and normal (NOR) based on micro-Raman spectra from platelet. The preprocessing step is a smoothing followed by background elimination to the original spectra. Then we applied the minmax method for normalization. After the inspection of the preprocessed spectra, we found that 725-777, 1504-1592 and 1632-1700 $cm^{-1}$ regions are the most discriminative features in AD, VD and NOR spectra. We applied the feature transformation using PCA (principal component analysis) and NMF (nonnegative matrix factorization). The classification result of MAP(maximum a posteriori probability) involving 327 spectra transformed features using proposed local region showed about 92.8 % true classification average rate.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.20 no.4
• /
• pp.225-235
• /
• 2010

This study was aimed to assess the status of working environment, health care management status and cause of exposure in manufactories using dimethylformamide (DMF). For the purpose, airborne concentration of DMF in the workplaces and N-methylformamide (NMF) in worker's urine were measured with job type and process. In addition, management of local exhaust ventilation system (LEV) and personal protective equipment (PPE) was evaluated at 35 work places (107 workers) located in Busan and Gimhae area. Mean DMF concentrations in work places by job type and process were of high level measured in printing and record media reproduction (5.23 ppm) and flaking process (2.48 ppm). Workers in adhesive job were measured a large amount of urine NMF (21.59 mg/${\ell}$). 98.1% of DMF handling workers were provided respirators, but 67.3% of those workers used them. The main reasons for not using respirators were inconvenience and difficulty of breathing. Airborne concentrations of DMF were higher in the workplaces in which LEVs were working abnormally, but there was not statistically significant. In addition, the urine NMF levels were correlated with management of LEV within the workers who did not use the respirators (p<0.048). These results implied that LEV should be installed and maintained properly to protect the workers from the exposure to DMF. Management of PPE should be also necessary to protect the workers from chemical hazards.

• Toxicological Research
• /
• v.29 no.3
• /
• pp.187-193
• /
• 2013

The effects of toluene in dimethylformamide (DMF)-induced hepatotoxicity were investigated with respect to the induction of cytochrome P-450 (CYP) and the activities of related enzymes. The rats were treated intraperitoneally with the organic solvents in olive oil (Single treatment groups: 450 [D1], 900 [D2], 1,800 [D3] mg DMF, and 346 mg toluene [T] per kg of body weight; Combined treatment groups: D1+T, D2+T, and D3+T) once a day for three days, while the control group received just the olive oil. Each group consisted of 4 rats. The activities of the xenobiotic metabolic enzymes and the hepatic morphology were assessed. The immunoblots indicated that the expression of CYP2E1 was considerably enhanced depending on the dosage of DMF and the CYP2E1 blot densities were significantly increased after treatment with both DMF and toluene, compared to treatment with DMF alone. The activities of glutathione-S-transferase and glutathione peroxidase were either decreased or remained unaltered after treatment with DMF and toluene, whereas the lipid peroxide levels were increased with increasing dosage of DMF and toluene. The liver tissue in the D3 group (1,800 mg/kg of DMF) showed signs of microvacuolation in the central vein region and a large necrotic zone around the central vein, in rats treated with both DMF (1,800 mg/kg) and toluene (D3T). These results suggest that the expression of CYP2E1 is induced by DMF and enhanced by toluene. These changes may have facilitated the accelerated formation of N-methylformamide (NMF) from toluene, and the generated NMF may directly induce liver damage.

• Journal of Korea Port Economic Association
• /
• v.39 no.2
• /
• pp.59-76
• /
• 2023

In this study, we tried to find out port safety from various perspectives through news data that can be easily accessed by the general public and domestic academic journal data that reflects the insights of port researchers. Non-negative Matrix Factorization(NMF) based topic modeling was conducted using Python to derive the main topics for each data, and then semantic analysis was conducted for each topic. The news data mainly derived natural and environmental factors among port safety risk factors, and the academic journal data derived security factors, mechanical factors, human factors, environmental factors, and natural factors. Through this, the need for strategies to strengthen the safety of domestic ports, such as strengthening the resilience of port safety, improve safety awareness to broaden the public's view of port safety, and conduct research to develop the port industry environment into a safe and specialized mature port. As a result, this study identified the main factors to be improved and provided basic data to develop into a mature port with a port safety culture.