• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.355-358
• /
• 2008

미국, 일본 등 해외 선진국에서는 교통사고를 과학적으로 분석하기 위해서 많은 연구가 활발히 이루어지고 있다. 특히 교통사고가 발생하면 어느 차량이 가해차량 이고 피해 차량인지 판단하기가 매우 어려운 실정이다. 본 논문에서는 이러한 문제점을 해결하기 위해서. 교통사고 발생 전후 일정 시간 동안 진행차량의 주변 상황을 자동 녹화하고, 특히 충돌방향으로 카메라의 방향을 이동시켜서 충돌 시에 차체의 방향이 변경되더라도 그에 따라 카메라의 촬영 각도를 변경시켜 충돌전후의 상황을 정확하게 녹화할 수 있는 시스템을 제안하였다.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.13-22
• /
• 2021

The clinical decision support system uses accumulated medical data to apply an AI model learned by machine learning to patient diagnosis and treatment prediction. However, the existing black box-based AI application does not provide a valid reason for the result predicted by the system, so there is a limitation in that it lacks explanation. To compensate for these problems, this paper proposes a system model that applies XAI that can be explained in the development stage of the clinical decision support system. The proposed model can supplement the limitations of the black box by additionally applying a specific XAI technology that can be explained to the existing AI model. To show the application of the proposed model, we present an example of XAI application using LIME and SHAP. Through testing, it is possible to explain how data affects the prediction results of the model from various perspectives. The proposed model has the advantage of increasing the user's trust by presenting a specific reason to the user. In addition, it is expected that the active use of XAI will overcome the limitations of the existing clinical decision support system and enable better diagnosis and decision support.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.6
• /
• pp.273-278
• /
• 2012

Wired communication signals that are generated in a wheelchair and using GPS to gather speed in this study. And occupants in the helmet, and save your current location information in a wheelchair and speed information that is passed by smartphone to take advantage of the Black Box App and radio feature multi-Communications App S/W development.The results of this study can be utilized effectively a pseudo-real-time information can be shared in each other's wheelchair with many people moving. Limitations of the study at the Institute of Experimental concrete measures for the commercial approach to the development of operational models as required.

• The KIPS Transactions:PartD
• /
• v.13D no.4 s.107
• /
• pp.573-582
• /
• 2006

Black-box testing needs to prepare fitting test data, execute software, and examine the result. If we test software effectively, not only selecting test cases but also representing test cases are important. In static testing effectiveness of testing activities also depends on how to represent test cases and checklist to validate. This paper suggests a method for finding ineffective critical test cases and reengineering them. An experiment of reengineering digital set-top box software shows the process and results of checking effectiveness and conformance of current test cases and patching test cases. The result shows how much save the test time and improve test coverage by reengineering test cases. Methods of reuse and restructuring test cases are also studied to fit into embedded product-line software.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.5
• /
• pp.9-15
• /
• 2013

In this paper, automatic recognition of an accident and whether service delivery and risk driving through the giving of the driver to correct driving habits before and after the accident to reproduce highly scalable video Smart Mobile Blackbox DVR (SMBD, Smart Mobile Blackbox DVR) Computer of the model was designed. SMBD on embedded systems equipped with wireless capabilities to sleep in the car accident point and the image information by wireless communications, by notification in the control center, 24-hour emergency rescue service and traffic information can be provided. The vehicle ECU (Electronic Control Unit) of the vehicle information and sensor data in conjunction with wireless eCall (Emergency Call) services can be realized.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.576-580
• /
• 2010

Generally, due to the strong coherence between embedded software and hardware or peripheral software, embedded software is tested by using black-box test based on user scenario for the whole system. This paper suggests the method to coordinate between testing and debugging under consideration for difficulties on solving out the defects detected from black-box test. First of all, from test result analysis, it builds up the debugging strategies enable to trace the locations of the defect's causes. And along with the strategies, it implements the generator of test scripts to be performed on the emulator environment. Through these steps, it can coordinate embedded software testing and debugging activities.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1348-1351
• /
• 2012

본 연구는 오토바이에서 생성되는 유선통신 신호와 GPS를 이용한 속도를 수집하여 헬멧에 전송하여 스마트폰을 이용해 현재 위치정보와 오토바이에서 전달되는 속도 정보 등을 저장한 블랙박스 App과 무전 기능인 멀티통신 App을 개발했다. 또한 오토바이에서 생성된 속도 데이터나 신호 데이터값을 거치대를 통해 헬멧으로 전달되어 헬멧에 Headup Display를 통해 운전자에 전달하는 Headup Display를 탑재한 헬멧을 연구개발 하였다. 본 연구의 결과물은 오토바이 등 여러 사람이 함께 이동하면서 서로의 정보를 실시간으로 공유할 수 있어서 효과적으로 활용할 수 있다. 연구의 한계점은 연구소에서 실험적으로 개발 운용한 모델로서 상업적인 접근에 대한 구체적인 방안이 필요하다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.279-280
• /
• 2024

본 논문에서는 주행 중 차량의 상태를 실시간으로 모니터링함과 동시에, 페달 조작 여부를 확인할 수 있는 영상 촬영 및 저장 시스템을 제안한다. 개발된 차량 운행 정보 블랙박스는 블루투스 OBD2 커넥터를 통해 차량의 PID 값을 식별하고 수집한다. 이 데이터는 비동기 방식으로 처리되며, 라즈베리파이와 7인치 터치 디스플레이를 이용해 운전자에게 한눈에 보일 수 있는 형태로 정보를 제공한다. 특히, 멀티스레드를 활용하여 ECU 정보를 페달 조작 여부 영상에 표시하는 동시에 녹화하고, CSV 파일로 SD 카드에 실시간으로 저장한다. 수집된 차량 데이터와 영상 데이터는 예기치 못한 사고 발생 시 운전자의 과실 비율 측정과 대처행동을 입증하는 데 중요한 역할을 할 것으로 기대되며, 차량 정비 시 참고 자료로 활용될 수 있다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.49-54
• /
• 2024

Data imbalance is a common issue encountered in classification problems, stemming from a significant disparity in the number of samples between classes within the dataset. Such data imbalance typically leads to problems in classification models, including overfitting, underfitting, and misinterpretation of performance metrics. Methods to address this issue include resampling, augmentation, regularization techniques, and adjustment of loss functions. In this paper, we focus on loss function adjustment, particularly comparing the performance of various configurations of loss functions (Cross Entropy, Balanced Cross Entropy, two settings of Focal Loss: 𝛼 = 1 and 𝛼 = Balanced, Asymmetric Loss) on Multi-Class black-box video data with imbalance issues. The comparison is conducted using the I3D, and R3D_18 models.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.1
• /
• pp.10-17
• /
• 2016

GPS location information storage included in the HD black box is using a unique manner for each manufacturer does not have a specific standard. In this paper, in order to overcome the limitations of the storage space and thereby the image quality according to store GPS position information deteriorate to solve the problems that cause, we propose the location information concealment method included in the HDTV video content using a essential hidden region. HDTV video content is a Border Extender of 8 lines in the frame to the bottom of the compression will be required. This was inserted into the image of a gray scale used in block form in order to space the current position information is concealed to prevent image degradation. The proposed method was confirmed using real HD black box, there are more difficult to interpret the format of the ASCII code re-edit the location information when the compression effect disappears with the existing security zones added. Therefore, the proposed method is suitable for location-based services, such as Facebook or Youtube videos.