• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.788-790
• /
• 2022

최근 자동차 패러다임이 스마트카의 개념으로 급격히 변화하면서 생체신호를, 기반으로 감정을 인식하는 기술은 졸음에 의한 각종 사고들을 예방하는데 적극 사용되고 있다. 자동차의 안전 시스템의 경우 운전자 주의 경고 기능을 이미 탑재하고 있으므로, 운전자 표정을 인식해 적절한 서비스를 제공하여 자동차의 엔터테인먼트 분야인 인포테이먼트 기술을 더욱 폭넓게 활용할 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제14권9호
• /
• pp.1979-1986
• /
• 2010

Biological early warning system detects toxicity by looking at behavior of organisms in water. The system uses classifier for judgement about existence and amount of toxicity in water. Boosting algorithm is one of possible application method for improving performance in a classifier. Boosting repetitively change training example set by focusing on difficult examples in basic classifier. As a result, prediction performance is improved for the events which are difficult to classify, but the information contained in the events which can be easily classified are discarded. In this paper, an incremental learning method to overcome this shortcoming is proposed by using the extended data expression. In this algorithm, decision tree classifier define class distribution information using the weight parameter in the extended data expression by exploiting the necessary information not only from the well classified, but also from the weakly classified events. Experimental results show that the new algorithm outperforms the former Learn++ method without using the weight parameter.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• 제63권4호
• /
• pp.526-533
• /
• 2014

In this study, we introduce design methodology to develop a guidance for issuing heavy rainfall warning by using both RBFNNs(Radial basis function neural networks) and SVR(Support vector regression) model, and then carry out the comparative studies between two pattern classifiers. Individual classifiers are designed as architecture realized with the aid of optimization and pre-processing algorithm. Because the predictive performance of the existing heavy rainfall forecast system is commonly affected from diverse processing techniques of meteorological data, under-sampling method as the pre-processing method of input data is used, and also data discretization and feature extraction method for SVR and FCM clustering and PSO method for RBFNNs are exploited respectively. The observed data, AWS(Automatic weather wtation), supplied from KMA(korea meteorological administration), is used for training and testing of the proposed classifiers. The proposed classifiers offer the related information to issue a heavy rain warning in advance before 1 to 3 hours by using the selected meteorological data and the cumulated precipitation amount accumulated for 1 to 12 hours from AWS data. For performance evaluation of each classifier, ETS(Equitable Threat Score) method is used as standard verification method for predictive ability. Through the comparative studies of two classifiers, neuro-fuzzy method is effectively used for improved performance and to show stable predictive result of guidance to issue heavy rainfall warning.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• 제45권6호
• /
• pp.481-489
• /
• 2017

Situation awareness means recognizing everything necessary to understand progress in a flight or aircraft maintenance work. Situation awareness is based on more than simply recognizing important about the environment, and it is important to provide the meaning of information in an integrated form. The KHP provides the pilot with integrated situation display for an integrated form of situation awareness and warning that synchronizes the priority based audible signal with the visual signal. Provide integrated display and warning to reduce operator error and enable operators to focus on mission critical tasks and events. This paper introduces the integrated situation display and warning design implemented in the KHP.

• Journal of agricultural medicine and community health
• /
• 제41권2호
• /
• pp.63-74
• /
• 2016

Objectives: We surveyed the awareness and current status of using fumigant carbon disulfide for exterminate Curculio sikkimensis among chestnut farmers in Chungnam Province to suggest directions for health education and public relations. Methods: We designed questionnaires to evaluate recognition of fumigant carbon disulfide. We conducted a questionnaire survey to assess recognition and recognition level of fumigant carbon disulfide by the study variables. Results: The recognition status for fumigant carbon disulfide was 74.5%, but the recognition level was low (know well 27.5%). The path of recognition was 45.1% and 15.7% for neighbor and rural technology center, respectively. The recognition status for warning label of fumigant carbon disulfide was 52.9%. Recognition for warning label of fumigant carbon disulfide was tended to increase with high educational attainment, bigger owning land area. Recognition on the content of warning label were 29.4%, 27.5%, 21.6%, and 21.6% for inflammability, toxicity, hazard, and explosiveness, respectively. Using personal protection equipment was tended to increase with the high status of awareness on fumigant carbon disulfide. Conclusions: Health education programs for using fumigant carbon disulfide are needed for chestnut farmers. In addition, publicity information activities about prevention and protection of carbon disulfide poisoning are needed for high risk farmers.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권9호
• /
• pp.3659-3665
• /
• 2015

Background: Waterpipe tobacco smoking has becoming popular especially among young people worldwide. Smokers are attracted by its sweeter, smoother smoke, social ambience and the misconception of reduced harm. The objective of this study was to systematically review the effects of waterpipe tobacco policies and practices in reducing its prevalence. Materials and Methods: A systematic review was conducted electronically using the PubMed, OVID, Science Direct, Proquest and Embase databases. All possible studies from 1980 to 2013 were initially screened based on titles and abstracts. The selected articles were subjected to data extraction and quality rating. Results: Three studies met the inclusion criteria and were eligible for this review. Almost all of the waterpipe tobacco products and its accessories did not comply with the regulations on health warning labelling practices as stipulated under Article 11 of WHO FCTC. In addition, the grisly new warning labels for cigarettes introduced by Food and Drug Administration did not affect hookah tobacco smoking generally. Indoor air quality in smoking lounges was found to be poor and some hookah lounges were operated without smoke shop certification. Conclusions: Our findings revealed the availability of minimal information on the practices in controlling waterpipe smoking in reducing its prevalence. The lack of comprehensive legislations or practices in controlling waterpipe smoking warrants further research and policy initiatives to curb this burgeoning global epidemic, especially among the vulnerable younger population.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제20권2호
• /
• pp.171-178
• /
• 2020

Many countries are establishing and operating blended learning that combines the advantages of online and offline education. However, online education lecture-based Mooc courses have a very low level, with a graduation rate of less than 5-10%. Therefore, in order to increase the graduation rate of students taking online Mooc distance education lectures that anyone can easily take lectures anytime, anywhere on the web-based basis, it is necessary to introduce automatic analysis of students' understanding level of lectures and an automatic academic warning system. Moreover, in order to enter an advanced education country, it is necessary to develop an automatic judgment SW for wrong answer rate, automatic summary SW for lectures, and automatic analysis SW education for lecture-based weak subjects based on mixed learning levels. In order to improve this problem, in this paper, we proposed and simulated an automatic summarization system for lecture contents, an automatic warning system for incorrect answers, and an automatic judgment algorithm for weak subjects.

• Journal of the Korean Institute of Gas
• /
• 제17권2호
• /
• pp.28-35
• /
• 2013

The number of large and complex buildings is growing and they are usually concentrated in metropolitan cities. There is a possibility in such buildings that a small accident can expand to a massive disaster since their scale and complexity. To deal with this issue, a research on gas sensors which can detect multiple gases and early-warning systems has been conducted. Proper criteria or standards are necessary for effective application and operation of such sensor-based disaster monitoring system. In this study, we have proposed the alarm criteria of concentration of hazardous gases for the detection and the alarm release. For each alarm level, systematic disaster response plans consist of responsive actions and information delivery have been prepared. These disaster monitoring criteria can help the detection of hazardous gas-related disaster in the early stage of accident and the provision of appropriate emergency responses.

• Transactions of the Korean Society of Automotive Engineers
• /
• 제13권2호
• /
• pp.149-156
• /
• 2005

In this paper, the VR(Virtual Reality) simulation system is developed to analyze driver's perceptive response on the ASV(Advanced Safety Vehicle). The ASV is the vehicle of next generation equipped with various warning systems. For the purpose, the VR simulation system consists of VR database, vehicle dynamic model, graphic/sound system, and driving system. The VR database which generates 3D graphic and sound information is organized for the driving reality. Mathematical models of vehicle dynamic analysis are constructed to represent the dynamic behavior of a vehicle. The driving system and the graphic/sound system provide a driver with the operation of a vehicle and the feedback of a driving situation. Also, the real-time simulation algorithm synchronizes the vehicle dynamic model with the VR database. To check the validity of the developed system, a simple scenario is applied to investigate driver's perceptive response time and vehicle acceleration on an emergency situation. It is confirmed that the proposed system is useful and helpful to design the FVCWS(Forward Vehicle Collision Warning System).

• Journal of Auto-vehicle Safety Association
• /
• 제7권1호
• /
• pp.33-39
• /
• 2015

This study examined the drivers' acceptance level of various active safety features with Korean drivers on Seoul urban and city roads. The test vehicle, 2013 Cadillac ATS, was equipped with FCA(Forward Collision Alert), LDW(Lane Departure Warning), SBZA(Side Blind Zone Alert), FRPA(Front/Rear Park Assist), RCTA(Rear Cross Traffic Alert), ACC(Adaptive Cruise Control), and AEB(Autonomous Emergency Braking). Participants had chances to run the tests on those systems in the parking lot accompanied by the 106km long stretch of predetermined route including local road and interurban highway in Seoul and Gyeonggi-do under normal traffic flowing environment. After the test, participants completed a series of questionnaires about the features they experienced. The results revealed that RCTA and SBZA systems received more favourable ratings compared to the other features in avoiding crashes. The respondents preferred sound alerts to haptic ones even though haptic warning methods were better in providing directional information.