• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.55-67
• /
• 2022

Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.

• Archives of design research
• /
• v.16 no.2
• /
• pp.375-384
• /
• 2003

This study is on the strategy for establishing successful corporate brand image, by understanding the need for increasing brand value based on the level of brand recognition. In order to carry this out, the PICS (Product Image Concentration System) is suggested, which includes Brand Image Analysis on a high-level, Product Image Programming based on the result of the image analysis, and Product Image Coherency Assessment and Management, resulting in setting up a guideline for gaining competitive advantage and brand management. Brand Image Analysis is a method that utilizes image association to understand brand disposition by analyzing the association pattern among available visual materials to measure the corporate and brand image inclinations. As the next step, Product Image Programming establishes design philosophy and principles based on the analysis of brand image, and the Visual Programming is a process for visualizing the intended product image direction. Lastly, Product Image Coherency Assessment examines whether to incorporate design philosophy and principles or not to arrive at an agreed evaluation criteria for developing designs coherent with the brand image. The PICS (Product Image Concentration System) is a practical method for increasing a company' competitive advantage and managing brand. The expectation on this system is to provide a guideline for applying brand image in design process more objectively. For further study, diversification of image spectrum based on expressive keywords and comparative analysis on images as well as a product image interpretation program to understand the order of visual materials will be necessary.

• Journal of Korean Academy of Nursing
• /
• v.30 no.1
• /
• pp.122-136
• /
• 2000

Chronic illness requiring attention and management during a long period of time puts great burden onto patients, their family and society. For patients with chronic illnesses, providing social support is the most important, and the fundamental support comes from their spouses. Amount and quality of support from spouses seems to differentiated according to the sex of patients. Female patients tend to believe that their spouses are not very supportive. Therefore, the researchers assessed the burden of husbands of female arthritis patients to discover the factors that result in greater burden. Also, they developed a theoretical model of husbands′ care for their wives through a qualitative research into husbands′ experience. Method 1: The study material was 650 female arthritis patients registered in an arthritis clinic. The questionnaire about the disease experience of female arthritis patients and the burden of husbands were sent. Returned questionnaires numbered 210(32.3%) and 27 were excluded because of inadequate answers. The remaining 183 questionnaires were analyzed. The mean age of the patients was 51 years and the mean age of spouses was 55 years. The mean marital period was 28 years. The average duration since diagnosis was 9.1 years. Education level was varied from primary school to graduate school, and average income/month was 1,517,300 won. Method 2: Initial questionnaire studies on the burden of husbands were performed. Among 183 responding husbands, 23 consented to participate for a qualitative research. Data was obtained by direct and telephone interviews. The mean age of participants was 58 years, and the educational level and socioeconomic status also varied. Result: 1. Husbands′ burden: The average burden was 57.68 with a range of 6-96. 2. Burden and general characteristics: The husband′s burden correlated with the age of the patients, numbers in the family, therapy methods, patient′s level of discomfort, patient′s disease severity, patient′s level of dependence and the husband′s understanding of the level of severity. 3. Linear correlation analysis on burden: The husbands′ burden is explained in 22.5% by husband′s recognition of level of severity and husbands′ age. 4. There were four patterns of the burden on husbands: both objectve burden and subjective burden were high(pattern I), both of objectve burden and subjective burden were low(pattern II), objective burden was high but subjective burden was low(pattern III), objective burden was low but subjective burden was high(pattern IV). The pattern was correlated with the family income, educational level of the patients and their husbands, therapy methods, patient′s level of discomfort, patient′s disease severity, patient′s level of dependence and husband′s understanding of level of severity. 5. The core category of the caring experience of the husbands with arthritis patients was "companionship". The causal factor was the patients′ experience due to symptoms : physical disfigurement, pain, immobility, limitation of house chores, and limitation of social activities. Contextural factors are husbands′ identification of housework and husbands′ concern about the disease. The mediating factors are economic problems, fear of aging, feeling of limitation and family support. The strategy for interaction is mind control and how to solve emotional stress. The "companionship" resulted from caring activities, participation of household activities, helping patients′ to coping with emotional experience. 6. Companionship is established through the process of entering intervention, and caring state of mind. Entering intervention is the phase of participation of therapy and involvement of houseworks. The caring phase consists of decision on therapy, providing therapy, providing direct care, and taking over the household role of wife. Through caring phase, the changing phase set a stage in which husbands consolidate the relationship with their wives, and are reminded of the meaning of marriage. As a result, in changing phase, husbands′ companionship is enhanced. In conclusion, nursing care of chronic illnesses should include a family member especially the spouse. All information on disease shoud be provided to patients and whole family member. Strong support should also be provided to overcome difficulties in taking over role of other sex. Then the quality of life of patients and families will be much improved.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3366-3374
• /
• 2010

By identifying the patterns of diabetes and high blood pressure with elderly people in a certain region, this study was intented to obtain the basic information for the improvement of the elderly health. In this analysis, CART was used for studying the pattern for chronic illness, - with the basis on survival factor by each sex, marital status, occupation, methods of health management and age. Occupation related to agriculture showed the highest cases of diabetes. But in the occupations related to fishing industry and public service, number of diabetics were minimal. With occupations related to trades and others, the cases of diabetes increased as the age increased in 80's and 90's. In recent years, the elderly population is ever increasing. In addition, elderly health situation is surfacing as a significant social issue - this is especially the cases as their allowed activities are becoming even more limited. Therefore it is important to improve the functions for their livelihood and increase their satisfaction of life by considering their quality of life, so they could live the rest of their lives happily and comfortably.

• Asian-Australasian Journal of Animal Sciences
• /
• v.21 no.2
• /
• pp.167-176
• /
• 2008

Galectins are a group of animal lectins consisting of galectin-type carbohydrate recognition domains (CRD) with relatively minor domains. The biological properties of galectins include the regulation of inflammation, intercellular adhesion, cell differentiation and cell death. The diverse kinds of galectin suggest variety in their biological roles. Galectin-1 is released during adipocyte differentiation and is associated with fat which is one of the important factors for meat quality. To verify expression level, a 0.5 kb clone of galectin-1 was obtained from cDNA prepared from back fat tissue of a Sancheong Berkshire pig with good quality meat, and the galectin-1 gene identified. The deduced amino acid sequence of the galectin-1 gene was compared with those obtained from other species. By using RT-PCR and Real time-PCR, an attempt was made to determine the expression level of galectin-1 and to compare with various tissues (tenderloin and back fat) taken from pigs in different groups. Grouping of pigs was based on growth-stage (weighing 60, 80, and 110 kg) and the sub-speciation (Yorkshire and Sancheong Berkshire pigs). We attempted to determine influences of pig species, growth stages and tissue variations on the expression level of the galectin-l gene and it was revealed that the expression pattern of the galectin-1 gene was significantly different (p<0.01 or p<0.05). Galectin-1 genes were expressed more highly in the back fat tissues of pigs weighing 110 kg than in those weighing 60 kg or 80 kg. However, the lowest expression was seen in the tenderloin tissues of pigs weighing 110 kg. Sancheong Berkshire pigs showed higher expression of the galectin-1 gene compared to Yorkshire pigs. Accordingly, it is considered that the expression pattern of the galectin-1 gene influences the growth of back fat tissues and the pig speciation relationship. Previous studies suggested that different expression of galectin-1 genes represents variety among the breeds and is closely related to fat tissue growth, conjugation and catabolism. Further, this study suggests that the expression of galectin-1 at a specific growth stage and tissue contributes significantly to the overall meat quality of Sancheong Berkshire pigs.

• Korean Journal of Food Science and Technology
• /
• v.25 no.4
• /
• pp.373-378
• /
• 1993

A rapid gas chromatographic profiling method for the simultaneous analysis of free fatty and other acids was applied to vegetable oils. Oil samples were dissolved in dichloromethane and the free acids were extracted with saturated $NaHCO_3$ solution. The aqueous extract was acidified and then loaded onto the Chromosorb P column for the extraction. The acids were eluted with diethyl ether selectively from Chromosorb P column and were treated with triethylamine to prevent the losses of volatile acids. Several long chain fatty acids were detected from soybean oil, rice-bran oil, sesame oil and perilla oil. Various organic acids including odd number fatty acids were detected in crude oil, especially sesame oil. Arachidic acid from perilla oil and vanillic acid from sesame oil, which were not reported before were detected. The content ratio of free linoleic acid to oleic acid was $1.02{\sim}1.18$, which was similar to the reported data. When the GC profile of organic acids were simplified to their corresponding retention index spectra of bar graphical forms, they presented characteristic pattern of each vegetable oil that can be quickly recognized.

• Journal of Biosystems Engineering
• /
• v.29 no.4
• /
• pp.341-346
• /
• 2004

Recent livestock people concern not only increase of production, but also superior quality of animal-breeding environment. So far, the optimization of the breeding and air environment has been focused on the production increase. In the very near future, the optimization will be emphasized on the environment for the animal welfare and health. Especially, cattle farming demands the precision livestock farming and special attention has to be given to the management of feeding, animal health and fertility. The management of individual animal is the first step for precision livestock farming and animal welfare, and recognizing each individual is important for that. Though electronic identification of a cattle such as RFID(Radio Frequency Identification) has many advantages, RFID implementations practically involve several problems such as the reading speed and distance. In that sense, computer vision might be more effective than RFID for the identification of an individual animal. The researches on the identification of cattle via image processing were mostly performed with the cows having black-white patterns of the Holstein. But, the native Korean and Japanese cattle do not have any definite pattern on the body. The purpose of this research is to identify the Japanese black cattle that does not have a body pattern using computer vision technology and neural network algorithm. Twelve heads of Japanese black cattle have been tested to verify the proposed scheme. The values of input parameters were specified and then computed using the face images of cattle. The images of cattle faces were trained using associate neural network algorithm, and the algorithm was verified by the face images that were transformed using brightness, distortion, and noise factors. As a result, there was difference due to transform ratio of the brightness, distortion, and noise. And, the proposed algorithm could identify 100% in the range from -3 to +3 degrees of the brightness, from -2 to +4 degrees of the distortion, and from 0% to 60% of the noise transformed images. It is concluded that our system can not be applied in real time recognition of the moving cows, but can be used for the cattle being at a standstill.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.19 no.1
• /
• pp.12-16
• /
• 2015

Purpose Principal component analysis (PCA) is a method often used in the neuroimagre analysis as a multivariate analysis technique for describing the structure of high dimensional correlation as the structure of lower dimensional space. PCA is a statistical procedure that uses an orthogonal transformation to convert a set of observations of correlated variables into a set of values of linearly independent variables called principal components. In this study, in order to investigate the usefulness of PCA in the brain PET image analysis, we tried to analyze C[11]-PIB PET image as a representative case. Materials and Methods Nineteen subjects were included in this study (normal = 9, AD/MCI = 10). For C[11]-PIB, PET scan were acquired for 20 min starting 40 min after intravenous injection of 9.6 MBq/kg C[11]-PIB. All emission recordings were acquired with the Biograph 6 Hi-Rez (Siemens-CTI, Knoxville, TN) in three-dimensional acquisition mode. Transmission map for attenuation-correction was acquired using the CT emission scans (130 kVp, 240 mA). Standardized uptake values (SUVs) of C[11]-PIB calculated from PET/CT. In normal subjects, 3T MRI T1-weighted images were obtained to create a C[11]-PIB template. Spatial normalization and smoothing were conducted as a pre-processing for PCA using SPM8 and PCA was conducted using Matlab2012b. Results Through the PCA, we obtained linearly uncorrelated independent principal component images. Principal component images obtained through the PCA can simplify the variation of whole C[11]-PIB images into several principal components including the variation of neocortex and white matter and the variation of deep brain structure such as pons. Conclusion PCA is useful to analyze and extract the main pattern of C[11]-PIB image. PCA, as a method of multivariate analysis, might be useful for pattern recognition of neuroimages such as FDG-PET or fMRI as well as C[11]-PIB image.

• Cartoon and Animation Studies
• /
• s.50
• /
• pp.349-382
• /
• 2018

China is a great civilization which is a combination of various ethnic groups with long history change. As one of these important components of traditional culture, the lucky shape has been going through the ideological upheaval of the history change of China. Up to now, it has become the important parts which can stimulate the emotion of Chinese nation. The lucky shape becomes the basis of the rich traditional culture by long history of the Chinese nation. Even say it is the centre of this traditional culture resource. The lucky shape is a way of expressing the Chinese history and national emotions. It is the important part of people's living habits, emotion, as well as the cultural background. What's more, it has the value of beliefs of Surname totem. Meanwhile, it also has the function of passing on information. The symbol of information finally was created by the being of lucky shape to indicate its conceptual content. There are various kinds of lucky shapes. It will have its limitations when researching all kinds of them professionally. So, here the lucky shape of FISH will be researched. The shape of fish is the first good shape created by the Chinese nation. It is about 6000 years. Its special shape and lucky meaning embody the peculiar inherent culture and intension of the Chinese nation. It's the important component of the Chinese traditional culture. The traditional shape of fish was focused on the continuation of history and the patterns recognition, etc. It seldom indicated the meaning of the shape into the using of the modern design. So by searching the lucky meaning & the way of fish shape, the purpose of the search is to explore the real analysis of value of the fish shape in the modern enterprise identity design. The way of search is through the development of the history, the evolvement and the meaning of lucky of the traditional fish shape to analyse the symbolic meaning and the cultural meaning from all levels in nation, culture, art and life, etc. And by using the huge living example of the enterprise identity design of the traditional shape of the fish to analyse that how it works in positive way by those enterprise which is based on the trust with good image. In the modern Chinese enterprise identity design, the lucky image will be reinterpreted in the modern way. It will be proofed by the national perceptual knowledge of the consumer and the way of enlarge the goodwill of corporate image. It will be the conclusion. The traditional fish shape is the important core of modern design.So this search is taken through the instance of the design of enterprise image of the traditional fish shape to analysis the idea of the majority Chinese people of the traditional luck and the influence of corporation which based on trust and credibility. In modern image design of Chinese corporation, the auspicious sign reappear. The question survey is taken by people through the perceptual knowledge of the consumer and the cognition the enterprise image. According the result, people can speculate the improvement of consumer's recognition and the possibility of development of traditional concept.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.519-527
• /
• 2003

Speech is much influenced by the existence of outliers which are introduced by such an unexpected happenings as additive background noise, change of speaker's utterance pattern and voice detection errors. These kinds of outliers may result in severe degradation of speaker recognition performance. In this paper, we proposed the GMM based on robust principal component analysis (RPCA-GMM) using M-estimation to solve the problems of both ouliers and high dimensionality of training feature vectors in speaker identification. Firstly, a new feature vector with reduced dimension is obtained by robust PCA obtained from M-estimation. The robust PCA transforms the original dimensional feature vector onto the reduced dimensional linear subspace that is spanned by the leading eigenvectors of the covariance matrix of feature vector. Secondly, the GMM with diagonal covariance matrix is obtained from these transformed feature vectors. We peformed speaker identification experiments to show the effectiveness of the proposed method. We compared the proposed method (RPCA-GMM) with transformed feature vectors to the PCA and the conventional GMM with diagonal matrix. Whenever the portion of outliers increases by every 2%, the proposed method maintains almost same speaker identification rate with 0.03% of little degradation, while the conventional GMM and the PCA shows much degradation of that by 0.65% and 0.55%, respectively This means that our method is more robust to the existence of outlier.