• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.14-27
• /
• 2021

Strong earthquakes have caused substantial losses in recent years, and earthquake risk prevention has aroused a significant amount of attention. Earthquake risk prevention products can help improve the self and mutual-rescue abilities of people, and can create convenient conditions for earthquake relief and reconstruction work. At present, it is difficult for earthquake risk prevention information systems to meet the information requirements of multiple scenarios, as they are highly specialized. Aiming at mitigating this shortcoming, this study investigates and analyzes four user roles (government users, public users, social force users, insurance market users), and summarizes their requirements for earthquake risk prevention products in the whole disaster chain, which comprises three scenarios (pre-quake preparedness, in-quake warning, and post-quake relief). A targeted recommendation rule base is then constructed based on the case analysis method. Considering the user's location, the earthquake magnitude, and the time that has passed since the earthquake occurred, a targeted recommendation model is built. Finally, an Android APP is implemented to realize the developed model. The APP can recommend multi-form earthquake risk prevention products to users according to their requirements under the three scenarios. Taking the 2019 Lushan earthquake as an example, the APP exhibits that the model can transfer real-time information to everyone to reduce the damage caused by an earthquake.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.557-569
• /
• 2022

Vibration-based structural health monitoring (SHM) is crucial for the dynamic maintenance of civil building structures to protect property security and the lives of the public. Analyzing these vibrations with modern artificial intelligence and deep learning (DL) methods is a new trend. This paper proposed an unsupervised deep learning method based on a convolutional autoencoder (CAE), which can overcome the limitations of conventional supervised deep learning. With the convolutional core applied to the DL network, the method can extract features self-adaptively and efficiently. The effectiveness of the method in detecting damage is then tested using a benchmark model. Thereafter, this method is used to detect damage and instant disaster events in a rubber bearing-isolated gymnasium structure. The results indicate that the method enables the CAE network to learn the intact vibrations, so as to distinguish between different damage states of the benchmark model, and the outcome meets the high-dimensional data distribution characteristics visualized by the t-SNE method. Besides, the CAE-based network trained with daily vibrations of the isolating layer in the gymnasium can precisely recover newly collected vibration and detect the occurrence of the ground motion. The proposed method is effective at identifying nonlinear variations in the dynamic responses and has the potential to be used for structural condition assessment and safety warning.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.142-148
• /
• 2023

In Modern days, Self-driving for modern people is an absolute necessity for transportation and many other reasons. Additionally, after the outbreak of COVID-19, driving by oneself is preferred over other means of transportation for the prevention of infection. However, due to the constant exposure to stressful situations and chronic fatigue one experiences from the work or the traffic to and from it, modern drivers often drive under drowsiness which can lead to serious accidents and fatality. To address this problem, we propose a drowsy driving prevention learning model which detects a driver's state of drowsiness. Furthermore, a method to sound a warning message after drowsiness detection is also presented. This is to use MoveNet to quickly and accurately extract the keypoints of the body of the driver and Dense Neural Network(DNN) to train on real-time driving behaviors, which then immediately warns if an abnormal drowsy posture is detected. With this method, we expect reduction in traffic accident and enhancement in overall traffic safety.

• The Journal of the Korea Contents Association
• /
• v.21 no.9
• /
• pp.176-183
• /
• 2021

Digital medical technology is very effective and at the same time faces the challenge of protecting privacy. However, for contact tracking and exposure notification apps in COVID-19 environment, there is always a trade-off between privacy measures and the effectiveness of the app's use. Today, many countries have developed and used contact tracking and exposure notification apps in various forms to prevent the spread of COVID-19, but the suspicion of digital surveillance (digital panopticon) is unavoidable. Therefore, this study aims to identify the factors of personal information infringement and dissatisfaction through text mining analysis by extracting user reviews of "Self-Quarantine Safety Protection" in Korea. As a result of the text mining analysis, we derived four groups, 'Address recognition error', 'Exit warning error', 'Access error', and 'App. program error'. Since 'Address recognition error' and 'Exit warning error' can give the app users a strong perception that they are keeping under surveillanc by the app, transparent management of personal information protection and consent procedures related to personal information collection are required. In addition, if the other two groups are not corrected immediately due to an error in an app function or a program bug, the complaints of users can be maximized and a protest against the monitor can be raised.

• Journal of Industrial Convergence
• /
• v.19 no.6
• /
• pp.101-108
• /
• 2021

This descriptive study was conducted to identify the relationship between knowledge of stroke and stroke-related health promoting lifestyle among nursing students. Data were collected from September 21 to 26, 2020, from 182 nursing students. Data were self-reported using a structured questionnaire. Data were analyzed using independent t-test, one-way ANOVA, and Kruskal-Wallis test. The mean stroke knowledge score of the participants was 14.97±3.13. The mean score on knowledge of stroke risk factors was 8.69±1.98, and that for knowledge of stroke warning signs was 5.43±1.31. The mean health promoting lifestyle score was 2.93±0.47. Knowledge of risk factors according to general and health-related characteristics showed significant differences in age and money on hand. Knowledge of warning signs according to general and health-related characteristics showed significant differences in the family history of stroke. Health promoting lifestyle to general and health-related characteristics showed significant differences in religion, satisfaction with major, subjective health status, and body mass index. In conclusion, nursing students had high knowledge of stroke, but stroke-related health promoting were not.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.839-850
• /
• 2018

The flood damage in urban areas due to torrential rain is increasing with urbanization. For this reason, accurate and rapid flooding forecasting and expected inundation maps are needed. Predicting the extent of flooding for certain rainfalls is a very important issue in preparing flood in advance. Recently, government agencies are trying to provide expected inundation maps to the public. However, there is a lack of quantifying the extent of inundation caused by a particular rainfall scenario and the real-time prediction method for flood extent within a short time. Therefore the real-time prediction of flood extent is needed based on rainfall-runoff-inundation analysis. One/two dimensional model are continued to analyize drainage network, manhole overflow and inundation propagation by rainfall condition. By applying the various rainfall scenarios considering rainfall duration/distribution and return periods, the inundation volume and depth can be estimated and stored on a database. The Rainfall-Duration-Flooding Quantity (RDF) relationship curve based on the hydraulic analysis results and the Self-Organizing Map (SOM) that conducts unsupervised learning are applied to predict flooded area with particular rainfall condition. The validity of the proposed methodology was examined by comparing the results of the expected flood map with the 2-dimensional hydraulic model. Based on the result of the study, it is judged that this methodology will be useful to provide an unknown flood map according to medium-sized rainfall or frequency scenario. Furthermore, it will be used as a fundamental data for flood forecast by establishing the RDF curve which the relationship of rainfall-outflow-flood is considered and the database of expected inundation maps.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.3
• /
• pp.42-51
• /
• 2017

Snowfall is an important natural hazard in Korea. In recent years, the socioeconomic importance of impact-based forecasts of meteorological phenomena have been highlighted. To further develop forecasts, we first need to analyze the climatic characteristics of each region. In this study, homogeneous regions for snowfall analysis were classified using a self-organizing map for impact-based forecast and warning services. Homogeneous regions of snowfall were analyzed into seven clusters and the characteristics of each group were investigated using snowfall, observation days, and maximum snowfall. Daegwallyeong, Gangneung-si, and Jeongeup-si were classified as areas with high snowfall and Gyeongsangdo was classified as an area with low snowfall. Comparison with previous studies showed that representative areas were well distinguished, but snowfall characteristics were found to be different. The results of this study are of relevance to future policy decisions that use impact-based forecasting in each region.

• Archives of Plastic Surgery
• /
• v.36 no.3
• /
• pp.277-282
• /
• 2009

Purpose: The vegetative state is a clinical condition with complete unawareness of self and environment, but with preservation of brain - stem functions. Vegetative patients may have nosocomial infections in their wounds, like pressure sores and infected craniums after cranioplasties. Usually flap surgery is necessary for those wounds, but decision of undergoing surgery is difficult because of various adverse conditions of vegetative patients. We share our experience of several successful flap surgeries in vegetative patients, and evaluate obstacles and requirements to get satisfactory results. Methods: From December 2005 to September 2008, a total of 4 vegetative patients underwent surgeries. In 2 patients with infected artificial craniums, scalp reconstructions with free flaps were performed. In other 2 patients with huge pressure sores with sepsis, island flap coverage of wounds was done. Retrospective study was done on hospital day, vegetative period, number of surgeries done, underlying diseases, causative bacteria, and contents of informed consent. Results: Mean hospital day was 14 months and mean vegetative period was 17.5 months. Patients underwent average of 4.5 surgeries under general anesthesia. There were several underlying diseases like hypertension, DM, CHF and chronic anemia. MRSA(Methicilin - resistant Staphylococcus Aureus) was cultured from every patient's wounds. Informed consent included a warning for high mortality and a need of attentive familial cooperation. Conclusion: There are three requirements for doing flap surgeries in vegetative patients. First, to prevent aggravation of brain damage and underlying diseases by general anesthesia, multidisciplinary team approach is needed. Second, operation should be beneficial for prolonging patient's lifespan. Third, because postoperative care is very difficult and long hospitalization is needed, detailed informed consent and highly cooperative attitude of family should be confirmed before operation.

• Journal of the Korean Society of Safety
• /
• v.32 no.3
• /
• pp.151-159
• /
• 2017

This study deals with characteristics and risk of a PM based on user survey result, road driving test and data analysis of PM accident. Text mining method is applied to extract PM accident data from Big Data, which are claim data of private insurance company. Road driving test and survey on safety, convenience, noise, overtake ability, steering ability, and climbing ability of PM are performed to evaluate user's safety and convenience considering domestic road condition. As the result of claim data analysis, annual average increase rate of PM accident is 47.4% and average compensation of personal mobility is higher than that of bicycle by maximum 1.5 times. 79.8% of PM accident is self-caused accident due to unskilled driving and age-specific diagnosis rate of driver over 60 is higher than that of under 60. Diagnosis rate of over 60 at lower limb, foot, rib and spine is especially higher than that of under 60. As the result of road driving test and user survey, satisfaction level on safety and convenience of PM is evaluated as close to that of bicycle and satisfaction level of PM is increased after boarding. Overtake ability, steering ability, and climbing ability of PM are evaluated as same or better than that of bicycle but warning equipment to pedestrian or bike such as horn is required because noise level of PM during driving is too low. Finally, user survey result shows that bicycle road is suitable for PM and safety standard, advance-education and insurance are required for PM. It is suggested that drivers' license for PM can be replaced by advance-education. Results of this study can be used to prepare safety measures and legal basis for PM operation.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.1
• /
• pp.565-570
• /
• 2013

Objectives: To describe the development and validation of a cancer awareness questionnaire (CAQ) based on a literature review of previous studies, focusing on cancer awareness and prevention. Materials and Methods: A total of 388 Chinese undergraduate students in a private university in Kuala Lumpur, Malaysia, were recruited to evaluate the developed self-administered questionnaire. The CAQ consisted of four sections: awareness of cancer warning signs and screening tests; knowledge of cancer risk factors; barriers in seeking medical advice; and attitudes towards cancer and cancer prevention. The questionnaire was evaluated for construct validity using principal component analysis and internal consistency using Cronbach's alpha (${\alpha}$) coefficient. Test-retest reliability was assessed with a 10-14 days interval and measured using Pearson product-moment correlation. Results: The initial 77-item CAQ was reduced to 63 items, with satisfactory construct validity, and a high total internal consistency (Cronbach's ${\alpha}$=0.77). A total of 143 students completed the questionnaire for the test-retest reliability obtaining a correlation of 0.72 (p<0.001) overall. Conclusions: The CAQ could provide a reliable and valid measure that can be used to assess cancer awareness among local Chinese undergraduate students. However, further studies among students from different backgrounds (e.g. ethnicity) are required in order to facilitate the use of the cancer awareness questionnaire among all university students.