• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.313-322
• /
• 2020

A large volume of data will improve the robustness of deep learning models and avoid overfitting problems. In automatic tongue segmentation, the availability of annotated tongue images is often limited because of the difficulty of collecting and labeling the tongue image datasets in reality. Data augmentation can expand the training dataset and increase the diversity of training data by using label-preserving transformations without collecting new data. In this paper, augmented tongue image datasets were developed using seven augmentation techniques such as image cropping, rotation, flipping, color transformations. Performance of the data augmentation techniques were studied using state-of-the-art transfer learning models, for instance, InceptionV3, EfficientNet, ResNet, DenseNet and etc. Our results show that geometric transformations can lead to more performance gains than color transformations and the segmentation accuracy can be increased by 5% to 20% compared with no augmentation. Furthermore, a random linear combination of geometric and color transformations augmentation dataset gives the superior segmentation performance than all other datasets and results in a better accuracy of 94.98% with InceptionV3 models.

• ETRI Journal
• /
• v.42 no.4
• /
• pp.518-526
• /
• 2020

This paper presents an efficient hardware random-number generator based on a beta source. The proposed generator counts the values of "0" and "1" and provides a method to distinguish between pseudo-random and true random numbers by comparing them using simple cumulative operations. The random-number generator produces labeled data indicating whether the count value is a pseudo- or true random number according to its bit value based on the generated labeling data. The proposed method is verified using a system based on Verilog RTL coding and LabVIEW for hardware implementation. The generated random numbers were tested according to the NIST SP 800-22 and SP 800-90B standards, and they satisfied the test items specified in the standard. Furthermore, the hardware is efficient and can be used for security, artificial intelligence, and Internet of Things applications in real time.

• Journal of muscle and joint health
• /
• v.13 no.1
• /
• pp.53-66
• /
• 2006

Aims. In order to analyze the concept of stigma, so to develop a valid instrument to measure stigma. Methods. First, a concept analysis was conducted with the aim of clarifying the state of the science of discipline-specific conceptualizations of stigma. The criterion-based method of concept analysis as described by Morse and colleagues was used (Morse et al., 1996; Morse, 2000). This analytic process enabled the assessment of the scientific maturity of the concept of stigma. The interdisciplinary concept of stigma was found to be immature. Based on this level of maturity it was determined that in order to advance the concept of stigma toward gloater maturity. techniques of concept development using the literature as data were applied. In this process, questions were 'asked of the data' (in this case, the selected disciplinary literatures) to identify the conceptual components of stigma. Results. The inquiry into the concept of stigma led to the development of an expanded interdisciplinary conceptual definition by merging the most coherent commonalties from each discipline. And the conceptual components of stigma were identified. The antecedent factors of stigma were "apart from social identity". The attributes of stigma were "devaluing, labeling, negative stereotypes, discrimination". The consequences of stigma were "social rejection, social isolation, deficiency of social support, low social status".

• Journal of Korea Game Society
• /
• v.10 no.5
• /
• pp.103-113
• /
• 2010

In this paper, we present a practical method for generating facial animation by using an optical motion capture system. In our setup, we assumed a situation of capturing the body motion and the facial expression simultaneously, which degrades the quality of the captured marker data. To overcome this problem, we provide an integrated framework based on the local coordinate system of each marker for labeling the marker data, hole-filling and removing noises. We justify the method by applying it to generate a short animated film.

• Journal of the Korean Society of Food Culture
• /
• v.35 no.3
• /
• pp.233-240
• /
• 2020

This study examined the nutrient content of HMR products and recipes by television chefs. Twelve menu items from the soup, stew, and broth category were chosen from HMR products and TV chef's recipes. The data on the nutrition labeling from the HMR products and TV chef's recipes were calculated using Can-Pro 5.0. The results of the analysis were the differences between the HMR products and TV recipes per serving size. The energy content of TV recipes 236.1 kcal was significantly higher than the HMR products. On the other hand, HMR products contained significantly higher sodium (926.9 mg) levels than the TV recipes (565.8 mg). In general, HMR products contained more sodium and less energy and protein than TV recipes. The highest sodium content containing products among the 12 menu items was the Spicy soft tofu stew (1,421.4 mg) from HMR products. The results revealed the significant differences in the macronutrient and sodium content between HMR products and the TV chef's recipe. This study provides supportive data for the need to reduce the sodium content in HMR products. TV cooking programs should focus on the importance of balanced nutrition, how to reduce sodium intake, and how to achieve this without disrupting well-balanced nutrition.

• Asian Journal of Business Environment
• /
• v.5 no.1
• /
• pp.5-11
• /
• 2015

Purpose - This study aims to explore the influence of combining "non-halal" labels with visual and textual warning labels on cigarette packages to induce the intention to quit smoking and boost the stop-smoking campaign. Research design, data, and methodology - This study examines"non-halal" labeling on cigarette packages using an experimental method. A total of 120 smokers, aged 18-23, were chosen from among Universitas Indonesia students. Data obtained were analyzed using ANOVA and T-Test. Results - The use of a "non-halal" label as a warning on cigarette packages is more effective to influence Muslim smokers to quit smoking. The results also suggest that "non-halal" labels more effectively increase intentions to quit smoking when use din combination with textual-visual labels. Conclusions - The study found that the addition of "non-halal" labels in textual or textual-visual warning labels on cigarette packages would significantly increase the intention of Moslems smokers to quit smoking. These results support previous research findings, that if cigarettes are labeled as "non-halal" (haram) products for Moslem teenagers, it will induce them to quit smoking.

• Food Science and Industry
• /
• v.54 no.3
• /
• pp.160-170
• /
• 2021

A recent advance in communication technologies accelerates the spread of food safety issues once presented by the news media. To respond to those safety issues and take steps in a timely manner, automatically detecting related information from the news data matters. This work presents an AI-based system that detects risk information within a food-related news article. Experts in food safety areas participated in labeling risk information from the food-related news articles; we acquired 43,527 articles in which food names and risk information are marked as labels. Based on the news document, our system automatically detects food names and risk information by analyzing similarities between words within a text by leveraging learned word embedding vectors. Our AI-based system shows higher detection accuracy scores over a non-AI rule-based system: achieving an absolute gain of +32.94% in F1 for the food name category and +41.53% for the risk information category.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.515-522
• /
• 2021

It is hard to prepare sufficient training data for speech emotion recognition due to the difficulty of emotion labeling. In this paper, we apply transfer learning with large-scale training data for speech recognition on a transformer-based model to improve the performance of speech emotion recognition. In addition, we propose a method to utilize context information without decoding by multi-task learning with speech recognition. According to the speech emotion recognition experiments using the IEMOCAP dataset, our model achieves a weighted accuracy of 70.6 % and an unweighted accuracy of 71.6 %, which shows that the proposed method is effective in improving the performance of speech emotion recognition.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.4
• /
• pp.455-463
• /
• 2021

The purpose of this study is to identify the relationship between firm's green marketing approach and firm's reputation improvement among customers. To investigate the object of the current study and provides adequate material to fill a gap in the literature, the current author collected abundant textual data from numerous extant literature. Because the author needed to augment about reliability and validity, textual data from trusted peer-reviewed sources was obtained from numerous databases. Based on a large body of literature, this study suggests that companies have to declare their stand based on their positioning to safeguard their reputation as an entity and that of its products and services. The five components of a company adopting a recognized environmental marketing strategy include product strategy, demand strategy, pricing strategy, distribution strategy, and labeling strategy Thus, firms' environmental marketing strategies have to be designed with the complete intent of transformation as a solution to enhance their reputation. The current study concludes that the comparison of environmental marketing strategies does not correctly help in ranking the concern in an effective way, and describe the exact details needed in each of the five categories for a company to carry its operations in a sustainable fashion.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.613-618
• /
• 2021

Facial expression recognition has long been established as a subject of continuous research in various fields. In this paper, the relationship between each landmark is analyzed using the features obtained by calculating the distance between the facial landmarks in the image, and five facial expressions are classified. We increased data and label reliability based on our labeling work with multiple observers. In addition, faces were recognized from the original data and landmark coordinates were extracted and used as features. A genetic algorithm was used to select features that are relatively more helpful for classification. We performed facial recognition classification and analysis with the method proposed in this paper, which shows the validity and effectiveness of the proposed method.