• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• Journal of Korean Academy of Nursing
• /
• v.27 no.2
• /
• pp.411-422
• /
• 1997

The purpose of this study is twofold : (i) to investigate how much effort the married couples are making for the good health of both the pregnant woman and her unborn child from the time of their marriage to and during the period of conception : and (ii) to comprehensive investigate socio-cultural back-grounds which affect prenatal effort. Result of this study provide a basis for the prenatal care program which will be appropriate to our culture. This study has been done by the ethnographic research method. The subjects of this study are 53 people in all consisting of 33 pregnant women and 20 husbands. In order to investigate socio-cultural factors which influence Taegyo, producers of Taegyo music were interviewed. In addition the researcher surveyed the markets of Taegyo music, participated in special courses of prenatal education, analyzed the content of the books and periodicals dealing with Taegyo, and collected the concept of Taegyo distributed by the mass media. The full-fledged study continued for eight months from February to August.1996. The data were analyzed as soon as they were collected. Spradly's(1979, 1980) developmental, sequential method of domain analysis. taxonomic analysis, componential analysis, and theme analysis in this order was adopted as the procedure of analyzing the data. To obtain the exactness of study, Sandelowski's (1986) four criteria, that is, Credibility, Fittingness, Auditability, and Confirmability were applied to all stages of data collection, data analysis, the interpretation of the result, and the description of the result. The following are the result : 1. The couples' Taegyo at the stage of preconception was related to their physical, psychological, spiritual conditions under which a healthy baby will be born. Specific methods they prefer are : "the choice of one's spouse." "physical check-up," "physical good health, " "praying, " and so on. 2. When the marriod couple have sex in order to conceive, their Taegyo was related to the imposition of their physical, psychological, and environmental conditions. Specific methods they prefer are : "having sex at specific time, " "having sex in nice place." "to purify their minds while having sex," and so on. 3. The married couples' Taegyo while they are in pregnancy was related to the imposition of their physical. psychological, emotionmental. environmental, social and spiritual conditions. Specific methods they prefer are : "listening to music. " "reading," "looking at beautiful things only," "to avoid looking at or listening to bad things." "to eat food in good shape, " "to avoid drugs," "eating Korean herbal medicine." "sexual abstinence," "to avoid dangerous places," "to keep emotional tranquility," "moderate exercises and rest." "leading a pure life." "praying." "being aware of their words and behavior." "for the couple to keep a good relationship." "interaction with their unborn child," "to support Taegyo for pregnant women," and so on. 4. The married couple put Taegyo into practice on the basis of the following principles : the principle of respecting an unborn child, the principle of forming a good disposition. the principle of top-down parental love, the principle of synergy between a pregnant woman and her unborn child, the principle of expecting a good child, the principle of forming a good habit, and the principle of acquiring a parental role. 5. The practice of Taegyo is influenced by such factors as the married couple, the supporting system, and the mass media. As the husband -and-wife factor, their information of Taegyo, the degree of importance is assigned to their characters, their time to spare, their healthiness, the age of pregnant woman, their conception plan, their religion, their belief of the Taegyo effects, and the birth of a baby in this order. The factor of the supporting system consists of her husband's support, her family support, and her neighbor's support. The mass media factors include the broadcasting media, books specialized in Taegyo, periodicals for pregnant women, booklets for advertizing powdered milk, Taegyo music of record manufacturing companies, and the teaching materials for gifted children. Among these the mass media is especially taking advantage of Taegyo as its main source of economic profits are leading the public behavior pattern to a prodigal one. Taegyo is a self-control behavior which requires practice for the following : the physical and psychological good health of the pregnant woman and her unborn child, the development of the unborn child's good character, the development of the unborn child's intelligence and talents, the expectation of the unborn child's good features. shape a good habit, the expectation of the unborn child's bright future, and the learning of a parental role, the expectation of male birth. Above all it is a type of our good cultural tradition which pursues a value higher than the one that the prenatal care does. The principles of pregnancy care inherent in the habit of Taegyo will provide us a guideline for the development of the prenatal care.

• Journal of the Korean Society of Radiology
• /
• v.9 no.7
• /
• pp.529-533
• /
• 2015

VCUG(Voiding Cystourethrography) study is being performed to check urinary reflex symptom from bladder to ureter or kidney in the method of filling the bladder with radiation opaque contrast agent. However, VCUG study have been performed impersonally, patients have to be naked and open their legs and then void. This method is so impersonal that it is immediately needed to improve the way of testing and crete new aid. Therefore, this study through producing underwear for VCUG, analysis and compares the test time of VCUG, patient radiation dose and patient satisfaction. The target of this study was 79 Male and Female patients who visited genitourinary clinic of PNUYH for their VCUG tests AXIUM Iconos R200(Siemens Medical System : Germany) and self-produced plastic underwears made by vinyl and plasic molding machine were used. The 79 patient were divided into two groups : experiment of patient and comparison group of we patient (using aid) in order to compare, testing time, DAP (dose area product) and patient satisfaction. There was time reduction, from 35.3min of comparison group to 27.8min experimentation group by 7.5min decrease. And comparison group of $4566.6{\mu}Gym^2$(DAP) decreased experimental group (using aid) of $3411.9{\mu}Gym^2$ by $1154.7{\mu}Gym^2$. In the case of patients satisfaction study, anxiety had a drop by 3.45 of comparison group to 2.51 experimentation group by 0.94 decrease. in experimental group. And shame had a drop by 4.02 of comparison group to 3.08 experimentation group by 0.94 increase. in experimental group. Difference of the smooth voiding had a drop by 1.90 of comparison group to 2.84 experimentation group by 0.94 increase. in experimental group. In addition satisfaction had a rise by 1.19 in experimental group. There were also other opinions of uncomfortableness on it and troublesome to wear. VCUG is one of the sensitive care required test. Therefore staff and the aid can give patients such comfortable and the aid can consentive on voiding. As a result test time and DAP can be reduced. It is needed to make testing at more comfortable for patients.

• Journal of Preventive Medicine and Public Health
• /
• v.27 no.2 s.46
• /
• pp.200-216
• /
• 1994

In present study, the authors investigated the possible effect of coffee consumption on serum cholesterol level in 1017 men between the ages of 40 and 59 years, who were randomly selected from the members of Seoul Cohort Study. Serum total cholesterol data was collected with other serologic indices (e.g. systolic blood pressure, diastolic blood pressure, hight, weight, etc.) through the program of biennial health check-up offered by Korean Medical Insurance Corporation (KMIC). The amount of coffee consumption was assessed by a self-administered questionnaire through mailing. Other confounding factors, such as age, body mass index, cigarette smoking, alcohol consumption, physical activity, and other dietary intake pattern were also determined by the questionnaire. The differences in means of serum total cholesterol in compared to non consumers were $-0.4{\pm}3.56mg/dl$ for those drinking less than 1 cup a day, $-0.6{\pm}3.60mg/dl$ for those drinking 1 cup a day, and $7.1{\pm}3.41mg/dl$ for those drinking more than 2 cups a day. Since smoking interacted the relationship between coffee consumption and serum total choleaterol, we re-analyzed those relationship in smokers and non-smokers separately Other atherogenic behaviors were well correlated with total cholesterol, so we adjusted the mean values of serum total cholesterol through multivariate model selection with age(r=0.12), total cigarette index (cigarette-years; r=0.10), Quetelet's index ($Kg/m^2$, r=0.16), daily calory expenditure (kcal/day, r=0.06), weekly meat and poultry consumption(g/week, r=0.05), weekly fish consumption (g/week, r=0.08), other caffeinated beverage intake (cups/week), and the amount of sugar and prim added to the coffee. Among those variables only age, Quetelet's index, fish consumption, and total cigarette index (in smokers) were remained in the models. After adjustment, the corresponing differences of total cholesterol in smokers were changed to $0.4{\pm}5.24mg/dl,\;-0.5{\pm}4.97mg/dl,\;and\;8.9{\pm}4.78mg/dl$, which were significantly different among themselves (P=0.011). In non-smokers, however, the differences were not statistically significant (P=0.76). Adjusted mean values of systolic blood pressure and diastolic blood pressure were also determined to evaluate the direct effect of coffee to cardiovascular system, but their means were not significantly different by coffee consumption(p=0.18 for SBP, p=0.48 for DBP). Asuming instant coffee in the most popular type of coffee in Korea, the association observed in our study between coffee and serum total cholesterol, especially in smokers, is very interesting finding for the connection between coffee and serum total cholesterol, because only 'boiled coffee' tend to show significant lipid raising effect rather than to other types of coffee, like filtered or espresso, in most of the western countries. We concluded that people who drink coffee more than 2 cups a day have significantly higher serum total cholesterol level than those who never drink coffee, especially in smokers.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.61-83
• /
• 2012

A knowledge map describes the network of related knowledge into the form of a diagram, and therefore underpins the structure of knowledge categorizing and archiving by defining the relationship of the referential navigation between knowledge. The referential navigation between knowledge means the relationship of cross-referencing exhibited when a piece of knowledge is utilized by a user. To understand the contents of the knowledge, a user usually requires additionally information or knowledge related with each other in the relation of cause and effect. This relation can be expanded as the effective connection between knowledge increases, and finally forms the network of knowledge. A network display of knowledge using nodes and links to arrange and to represent the relationship between concepts can provide a more complex knowledge structure than a hierarchical display. Moreover, it can facilitate a user to infer through the links shown on the network. For this reason, building a knowledge map based on the ontology technology has been emphasized to formally as well as objectively describe the knowledge and its relationships. As the necessity to build a knowledge map based on the structure of the ontology has been emphasized, not a few researches have been proposed to fulfill the needs. However, most of those researches to apply the ontology to build the knowledge map just focused on formally expressing knowledge and its relationships with other knowledge to promote the possibility of knowledge reuse. Although many types of knowledge maps based on the structure of the ontology were proposed, no researches have tried to design and implement the referential navigation-enabled knowledge map. This paper addresses a methodology to build the ontology-based knowledge map enabling the referential navigation between knowledge. The ontology-based knowledge map resulted from the proposed methodology can not only express the referential navigation between knowledge but also infer additional relationships among knowledge based on the referential relationships. The most highlighted benefits that can be delivered by applying the ontology technology to the knowledge map include; formal expression about knowledge and its relationships with others, automatic identification of the knowledge network based on the function of self-inference on the referential relationships, and automatic expansion of the knowledge-base designed to categorize and store knowledge according to the network between knowledge. To enable the referential navigation between knowledge included in the knowledge map, and therefore to form the knowledge map in the format of a network, the ontology must describe knowledge according to the relation with the process and task. A process is composed of component tasks, while a task is activated after any required knowledge is inputted. Since the relation of cause and effect between knowledge can be inherently determined by the sequence of tasks, the referential relationship between knowledge can be circuitously implemented if the knowledge is modeled to be one of input or output of each task. To describe the knowledge with respect to related process and task, the Protege-OWL, an editor that enables users to build ontologies for the Semantic Web, is used. An OWL ontology-based knowledge map includes descriptions of classes (process, task, and knowledge), properties (relationships between process and task, task and knowledge), and their instances. Given such an ontology, the OWL formal semantics specifies how to derive its logical consequences, i.e. facts not literally present in the ontology, but entailed by the semantics. Therefore a knowledge network can be automatically formulated based on the defined relationships, and the referential navigation between knowledge is enabled. To verify the validity of the proposed concepts, two real business process-oriented knowledge maps are exemplified: the knowledge map of the process of 'Business Trip Application' and 'Purchase Management'. By applying the 'DL-Query' provided by the Protege-OWL as a plug-in module, the performance of the implemented ontology-based knowledge map has been examined. Two kinds of queries to check whether the knowledge is networked with respect to the referential relations as well as the ontology-based knowledge network can infer further facts that are not literally described were tested. The test results show that not only the referential navigation between knowledge has been correctly realized, but also the additional inference has been accurately performed.