• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.57-65
• /
• 2021

A hyper-connected intelligence information society is emerging that creates new value by converging IoT, AI, and Bigdata, which are new technologies of the fourth industrial revolution, in all industrial fields. Everything is connected to the network and data is exploding, and artificial intelligence can learn on its own and even intellectual judgment functions are possible. In particular, the Internet of Things provides a new communication environment that can be connected to anything, anytime, anywhere, enabling super-connections where everything is connected. Artificial intelligence technology is implemented so that computers can execute human perceptions, learning, reasoning, and natural language processing. Artificial intelligence is developing advanced technologies such as machine learning, deep learning, natural language processing, voice recognition, and visual recognition, and includes software, machine learning, and cloud technologies specialized in various applications such as safety, medical, defense, finance, and welfare. Through this, it is utilized in various fields throughout the industry to provide human convenience and new values. However, on the contrary, it is time to respond as intelligent and sophisticated cyber threats are increasing and accompanied by potential adverse functions such as securing the technical safety of new technologies. In this paper, we propose a new data modeling method to enable IoT integrated security control by utilizing artificial intelligence technology as a way to solve these adverse functions.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.411-417
• /
• 2022

This study aimed to learn and evaluate the effectiveness of VGGNet in the detection of pulmonary emphysema using low-dose chest computed tomography images. In total, 8000 images with normal findings and 3189 images showing pulmonary emphysema were used. Furthermore, 60%, 24%, and 16% of the normal and emphysema data were randomly assigned to training, validation, and test datasets, respectively, in model learning. VGG16 and VGG19 were used for learning, and the accuracy, loss, confusion matrix, precision, recall, specificity, and F1-score were evaluated. The accuracy and loss for pulmonary emphysema detection of the low-dose chest CT test dataset were 92.35% and 0.21% for VGG16 and 95.88% and 0.09% for VGG19, respectively. The precision, recall, and specificity were 91.60%, 98.36%, and 77.08% for VGG16 and 96.55%, 97.39%, and 92.72% for VGG19, respectively. The F1-scores were 94.86% and 96.97% for VGG16 and VGG19, respectively. Through the above evaluation index, VGG19 is judged to be more useful in detecting pulmonary emphysema. The findings of this study would be useful as basic data for the research on pulmonary emphysema detection models using VGGNet and artificial neural networks.

• Journal of the Korean Burn Society
• /
• v.22 no.1
• /
• pp.1-9
• /
• 2019

Purpose: The aim of this study was to investigate the characteristics of Acute Kidney Injury Network (AKIN)-defined nephrotoxicity in patients undergoing intravenous colistimethate sodium (CMS) therapy for major burns. Methods: This retrospective study included burn patients who received more than 48 h of intravenous CMS between September 2009 and December 2015. Data collection was performed using the institution's electronic medical record system. Patients assigned to the developed nephrotoxic group experienced aggravation of current AKIN stage during CMS treatment; those assigned to the non-nephrotoxic group experienced no change in current or exhibited improved AKIN stage during CMS therapy. Results: A total of 306 patients were included in this study. All patients were grouped according to AKIN stage: AKIN 0 (n=152); AKIN 1 (n=6); AKIN 2 (n=9); AKIN 3 (n=139). The baseline creatinine (Cr) level was 0.73 mg/dL. The incidence of nephrotoxicity was 50.3% according to AKIN stage; overall mortality was 45.8%. The non-nephrotoxic group consisted of 127 (74.7%) patients and 43 (25.3%) were in the developed nephrotoxic group. In patients requiring continuous renal replacement therapy (CRRT), baseline Cr level was 0.83 mg/dL, pre-CMS Cr level was 1.17 mg/dL, and post-CMS Cr level was 1.34 mg/dL. Conclusion: CMS can be administered without signs of nephrotoxicity for a certain period (approximately 1 week), it can be used relatively safely for 2 weeks. Application of CMS is a reasonable option for treating infections caused by multi-drug resistant gram-negative bacteria in patients with major burns. The caution should be exercised nevertheless.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• Journal of the Korean Society for information Management
• /
• v.41 no.1
• /
• pp.411-438
• /
• 2024

This study aims to identify and comprehensively view health information-related research trends using a bibliometric analysis. To this end, 1,193 papers from 2002 to 2023 related to "health information" were collected through the Korea Citation Index (KCI) database and analyzed in diverse aspects: research trends by period, academic fields, intellectual structure, and keyword changes. Results indicated that the number of papers related to health information continued to increase and has been decreasing since 2021. The main academic fields of health information-related research included "biomedical engineering," "preventive medicine/occupational environmental medicine," "law," "nursing," "library and information science," and "interdisciplinary research." Moreover, a co-word analysis was performed to understand the intellectual structure of research related to health information. As a result of applying the parallel nearest neighbor clustering (PNNC) algorithm to identify the structure and cluster of the derived network, four clusters and 17 subgroups belonging to them could be identified, centering on two conglomerates: "medical engineering perspective on health information" and "social science perspective on health information." An inflection point analysis was attempted to track the timing of change in the academic field and keywords, and common changes were observed between 2010 and 2011. Finally, a strategy diagram was derived through the average publication year and word frequency, and high-frequency keywords were presented by dividing them into "promising," "growth," and "mature." Unlike previous studies that mainly focused on content analysis, this study is meaningful in that it viewed the research area related to health information from an integrated perspective using various bibliometric methods.

• Korean Journal of Health Education and Promotion
• /
• v.12 no.1
• /
• pp.83-110
• /
• 1995

The purpose of this study was to investigate the status of the problematic behavior for the demented elderly and the stress among family members, and the effects of the problematic behavior upon the stress in order to offer the basic data for the adult and the elderly health education about dementia. For this purpose, 70 families who were resident in Seoul and Inchon were surveyed by quetionnaires. This was carried out from 26 July, 1994 to 11 September, 1994. Datum was analysed by using SPSS\PC+ including percentage, mean, t - test, ANOVA, Pearson correlation. So, the results of this study were as follows: 1. In view of socia-demographic characteristics, female were 82.9%, and of the female daughters-in-law of the demented elderly were 44.9%. 40th years old were 32.9% and 88.6% wase married. The christian were 34.8%, those who graduated university 47.1%, and those who had a job 32.9%. 2. Of the demented elderly, female were 74.3%, 80 years old were 37.1%, and their average age was seventy-seven point one years old. 66.2% of the elderly has been lived alone and the christian were 27.5%. In addition, those who graduated elementary school were 66.5%. 3. Of the behavior problem for the demented elderly, Activities of the Daily Living(ADL) was the most severe problem. The 2nd was cognitive function problem, the 3th, change of personality, the 4th, emotional disturbance, and the last, misconduct behavior. 4. For the status of behavior problems, females were more severe than male, and 80th years elderly ware the most severe groups. The longer disease period was, the severe problematic behaviors were, and in 4-6 years of the disease period the status was the highest(p＜0.05). Those who diagnosed the disease had more severe problems(p＜0.001). 5. The orders of the stress among family members caring for the demented elderly in this study were as follows : 1. The deficiency of supporting network 2. Decrease of elderly's cognitive activities 3. Assistance of BADL(Basic Activities of Daily Living) 6. Elderly's abnormal behavior 5. Assistance of IADL(Instrumental Activities of Daily Living), 6. As for the status of the stress among family members, female respondants were higher than male. On the ages, 20th years' stress score were the highest. Daughters-in-law were stressed more than other family members. The longer the time of caring per day was, the highest the status of the stress(p＜0.05), 7. Those who caring for female elderly and more than 80 years had more stressed. When the elderly was received the diagnosis, the family members were more stressed. On the disease period, 1-2 years was the highest and after 2 years the status of the stress was decreased and more than 6 years was the lowest(p＜0.05). 8. Behavior problems of the demented elderly were closely associated to the stress for family members. Of the problems, change of personality was the most related factor(r = 0.6552). The factors of Basic Activities of the Daily Living(BADL) was most correlated on assistance of Basic Activities of Daily Living (BADL), emotional disturbance the assistance of IADL(Instrumental Activities of Daily Living). Change of personality was most related to the stress of the decrease of cognitive activities and elderly's abnormal behavior. The deficiency of supporting network was most related to misconduct behavior.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.15
• /
• pp.6521-6526
• /
• 2015

Background: This study aimed toanalyze the risk behavior for cervical cancer (CC) and the human papillomavirus (HPV) prevalence and resolution among women who received care through the private healthcare network of a municipality in southern Brazil. Materials and Methods: This descriptive and retrospective study was conducted with 25 women aged 20 to 59 years who received care through the private healthcare network and were treated at a specialty clinic in the period from January to December 2012 in a municipality in Northwest Parana, Southern Brazil. Data from medical records with cytological and HPV results were used. Following treatment, these women were followed-up and reassessed after 6 months. Data were statistically analyzed using the t-test and chi-squared test at a 5% significance level. Results: The mean age of the studied women was $27.8{\pm}7.75$ years old, and the majority were married, with paid employment and were non-smokers. The mean age at menarche was $13.0{\pm}0.50$ years old, and the mean age at first intercourse was $17.5{\pm}1.78$ years, with only 8.0% (2) initiating sexual activity at an age ${\leq}15$ years old. The majority had 1 to 2 children (60.0%), while 88.0% reported having had one sexual partner in their lifetime, and all the women were sexually active. A total of 68.0% used a hormonal contraceptive method. All the women had leukorrhea and pain and were infected by a single HPV type. Regarding the lesion grade, 80.0% showed high risk and 20.0% low risk. The most prevalent high-risk HPV strain was 16. Conclusions: These findings provide relevant information on HPV risk factors and infection, as well as the treatment and 6-month follow-up results, in economically and socially advantaged women with no traditional risk factors, corroborating previous reports that different risk factors may be described in different populations. Thus, this study reinforces the fact that even women without the traditional risk factors should undergo HPVmonitoring and assessment to determine the persistence of infection, promoting early diagnosis of the lesions presented and appropriate treatment to thus prevent the occurrence of CC.

• Journal of Hospice and Palliative Care
• /
• v.16 no.4
• /
• pp.205-215
• /
• 2013

Most terminally ill cancer patients experience various physical and psychological symptoms during their illness. In addition to pain, they commonly suffer from fatigue, anorexia-cachexia syndrome, nausea, vomiting and dyspnea. In this paper, I reviewed some of the common non-pain symptoms in terminally ill cancer patients, based on the National Comprehensive Cancer Network (NCCN) guidelines to better understand and treat cancer patients. Cancer-related fatigue (CRF) is a common symptom in terminally ill cancer patients. There are reversible causes of fatigue, which include anemia, sleep disturbance, malnutrition, pain, depression and anxiety, medical comorbidities, hyperthyroidism and hypogonadism. Energy conservation and education are recommended as central management for CRF. Corticosteroid and psychostimulants can be used as well. The anorexia and cachexia syndrome has reversible causes and should be managed. It includes stomatitis, constipation and uncontrolled severe symptoms such as pain or dyspnea, delirium, nausea/vomiting, depression and gastroparesis. To manage the syndrome, it is important to provide emotional support and inform the patient and family of the natural history of the disease. Megesteol acetate, dronabinol and corticosteroid can be helpful. Nausea and vomiting will occur by potentially reversible causes including drug consumption, uremia, infection, anxiety, constipation, gastric irritation and proximal gastrointestinal obstruction. Metoclopramide, haloperidol, olanzapine and ondansetron can be used to manage nausea and vomiting. Dyspnea is common even in terminally ill cancer patients without lung disease. Opioids are effective for symptomatic management of dyspnea. To improve the quality of life for terminally ill cancer patients, we should try to ameliorate these symptoms by paying more attention to patients and understanding of management principles.

• Journal of Biomedical Engineering Research
• /
• v.25 no.5
• /
• pp.421-430
• /
• 2004

Clinically, it is almost impossible for a physician to distinguish subtle changes of frequency spectrum by using a stethoscope alone especially in the early stage of thrombus formation. Considering that reliability of mechanical valve is paramount because the failure might end up with patient death, early detection of valve thrombus using noninvasive technique is important. Thus the study was designed to provide a tool for early noninvasive detection of valve thrombus by observing shift of frequency spectrum of acoustic signals with computer aid diagnosis system. A thrombus model was constructed on commercialized mechanical valves using polyurethane or silicon. Polyurethane coating was made on the valve surface, and silicon coating on the sewing ring of the valve. To simulate pannus formation, which is fibrous tissue overgrowth obstructing the valve orifice, the degree of silicone coating on the sewing ring varied from 20％, 40％, 60％ of orifice obstruction. In experiment system, acoustic signals from the valve were measured using microphone and amplifier. The microphone was attached to a coupler to remove environmental noise. Acoustic signals were sampled by an AID converter, frequency spectrum was obtained by the algorithm of spectral analysis. To quantitatively distinguish the frequency peak of the normal valve from that of the thrombosed valves, analysis using a neural network was employed. A return map was applied to evaluate continuous monitoring of valve motion cycle. The in-vivo data also obtained from animals with mechanical valves in circulatory devices as well as patients with mechanical valve replacement for 1 year or longer before. Each spectrum wave showed a primary and secondary peak. The secondary peak showed changes according to the thrombus model. In the mock as well as the animal study, both spectral analysis and 3-layer neural network could differentiate the normal valves from thrombosed valves. In the human study, one of 10 patients showed shift of frequency spectrum, however the presence of valve thrombus was yet to be determined. Conclusively, acoustic signal measurement can be of suggestive as a noninvasive diagnostic tool in early detection of mechanical valve thrombosis.

• Journal of Hospice and Palliative Care
• /
• v.1 no.1
• /
• pp.56-64
• /
• 1998

Purpose : Seoul National University Hospital developed a group counseling program for the terminal cancer patients and their family members. This program consists of each of doctor, nutritionist, nurse, pharmacist, and social worker to provide them with the information and to enhance their ability to cope with terminal cancer. This research aims to introduce this new program per se, and to appreciate its validity and applicability to the terminal cancer patients and their family members by analyzing the concerns and specific questions of the participants. Methods : The methodological approach employed in this research is 1996 content analysis of the group counseling reports, and interview of the 312 participants. The analysis includes the general characteristics of the subjects, family relationship to the patients, times of attendance to the group session, source of information to the program. Results : The participants consist of 261 family members(84%) and 51 patients(16%). Majority responded to the program with a single-attendance. Diagnosis are mainly lung cancer, stomach cancer, liver cancer. The ratio of participants by family members is decreased in the order of spouse, children, daughter-in-law, brothers and sisters, and parents. The source of information to the program is largely through medical staff(69%) as compared with posters in the hospital (26%). The participants are interested primarily in the medical information. Their interests are various, such as pain control, patient care, nutrition, psychosocial problem and etc. Conclusion : This program is characterized largely as a family-supporting program which primarily offers information for terminal cancer. This program is a sort of a hospice program, which maximizes the present quality of living of the terminal cancer patients as long as life continues by encouraging them to live with terminal cancer. Thus, this group program can be employed as an active support network for the patients and their family. In order to develop comprehensive care-giving services, it is required to have 24-hour telephone service, hospice facilities, home care service, and communication between the referral hospitals and the primary care physicians, in particular. Such a development of services is the ultimate goal for improving care. But the immediate goal of the program is to make possible better education for the patients and their family to live with terminal cancer.