• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1222-1225
• /
• 2022

본 논문에서는 저조도 환경에서 촬영된 영상의 조도를 개선하여 얼굴 검증 정확도를 높이는 방법을 제안하였다. 입력 이미지의 조도 개선을 통해 얼굴 검출 정확도를 개선하며, 검출된 얼굴의 반복적인 조도 향상을 통해 생성된 다수의 특징 벡터를 이용하여 얼굴 검증에 이용하였다. 얼굴 검출 및 검증 정확도 측정을 위해 K-FACE 데이터셋을 이용하였다. 저조도 환경에서 촬영된 검증 이미지에 대하여, 제안하는 특징 벡터 합성 방법으로 인해, 동일인 쌍 및 타인 쌍의 유사도 점수 분포의 표준 편차가 줄어드는 경향을 확인했으며, 이로 인해 검증 성능이 높아지는 결과를 얻었다.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.18 no.6
• /
• pp.105-113
• /
• 2014

Most operating civil structures measure response data continuously by various types of sensors and evaluate their health conditions. Measurement control criteria for such civil structures are usually defined in the first operating stage by experts working at a construction or engineering company. However, a few studies have been carried to examine the adequacy of these measurement control criteria based on the actual measured data. The paper introduces a systematic way of resetting the measurement control criteria for the measured monitoring data based on the statistical aspects of the measured data. The proposed statistical approach has been examined with actually measured time-history data from a bridge structure.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.37-47
• /
• 2022

Autonomous delivery operation data is the key to driving a paradigm shift for last-mile delivery in the Corona era. To bridge the technological gap between domestic autonomous delivery robots and overseas technology-leading countries, large-scale data collection and verification that can be used for artificial intelligence training is required as the top priority. Therefore, overseas technology-leading countries are contributing to verification and technological development by opening AI training data in public data that anyone can use. In this paper, 326 objects were collected to trainn autonomous delivery robots, and artificial intelligence models such as Mask r-CNN and Yolo v3 were trained and verified. In addition, the two models were compared based on comparison and the elements required for future autonomous delivery robot research were considered.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.13-18
• /
• 2022

In this paper, we proposed VW-FedAVG(Validation based Weighted FedAVG) which updates the global model by weighting according to performance verification from the models of each device participating in the training. The first method is designed to validate each local client model through validation dataset before updating the global model with a server side validation structure. The second is a client-side validation structure, which is designed in such a way that the validation data set is evenly distributed to each client and the global model is after validation. MNIST, CIFAR-10 is used, and the IID, Non-IID distribution for image classification obtained higher accuracy than previous studies.

• Journal of Industrial Convergence
• /
• v.21 no.5
• /
• pp.133-142
• /
• 2023

In recent years, the problem of academic credential falsification is not simply the manipulation of certificates generated by educational institutions, but also the difficulty of trusting automated relationship verification and verification itself, such as falsely recording completion as graduation while still in school. This is due to the lack of sharing of educational background databases among university institutions and the establishment/operation of independent systems that make it difficult to track educational backgrounds. This study designs and implements an E-AV model for academic credential verification centered on university institutions. It summarizes and stores the linked information on the existing academic background in an encrypted database and implements it with web standard technology considering the compatibility and scalability of the existing system. The results of sample data verification show that it improves safety against forgery and complies with storage space and execution performance. This study aims to contribute to the improvement of online verification services such as academic records management in domestic universities.

• Journal of Aerospace System Engineering
• /
• v.17 no.5
• /
• pp.42-57
• /
• 2023

In this paper, to increase the research capability of flight missions and maintenance in operating military aircraft, we studied the requirements for additional mounting of flight video and data recorders and safety verification methods. The verification process of the recorder equipment itself, structural safety in the aircraft system, power and electrical safety, electromagnetic compatibility, and impact of airworthiness are described in accordance with military standards and operating environment requirements. In addition, through ground/flight tests, the results of functional operation suitable for the influence and demand of interference between the flight video and data recorder and other systems are also presented.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.101-109
• /
• 2013

Data quality management is extremely important. In this study, we proposed data standardization for effective quality management of enterprise-owned data about distributed goods and validated its effectiveness by case study. For the standardization of data, we designed data category and data dictionary. Additionally, we categorized data and identified its attributes for data category design, and we developed design process for data dictionary and built the dictionary of word, term, domain and code for data dictionary design. And then we proposed output documents which have to be written for data standardization. Proposed data standardization approach is validated its efficiency by quantitative and qualitative measurement. and as a result the data quality of the data standardization improved 24% and the data quality of the consistency of the data dictionary improved 7%.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.1
• /
• pp.103-109
• /
• 2006

In this paper, VDS(Vehicle Dynamics Simulator) and ACS(Attitude Control Simulator) are developed and are verified using PILS(Process In-the Loop Simulation) between VDS and ACS. VDS is including the AOCS(Attitude & Orbit Control Subsystem) hardware modeling of geosynchronous satellite and consists of modulation concept. ACS performs the attitude determination using sensor data and generates the attitude control commands. In order to transfer the data between VDS and PCDU(Power Control & Distribution Unit), data acquisition boards were mounted. VDS performance is verified using HILS(Hardware In-the Loop Simulation) between VDS and PCDU.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.649-655
• /
• 2021

This study purposes to cross-validate its performance by applying the optimal seismic vulnerability assessment model based on previous studies conducted in Gyeongju to other regions. The test area was Pohang City, the occurrence site for the 2017 Pohang Earthquake, and the dataset was built the same influencing factors and earthquake-damaged buildings as in the previous studies. The validation dataset was built via random sampling, and the prediction accuracy was derived by applying it to a model based on a random forest (RF) of Gyeongju. The accuracy of the model success and prediction in Gyeongju was 100% and 94.9%, respectively, and as a result of confirming the prediction accuracy by applying the Pohang validation dataset, it appeared as 70.4%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.5
• /
• pp.885-893
• /
• 2024

As deepfake technology advances, its increasing misuse has spurred extensive research into detection models. These models' performance evaluations, which include selecting train and test datasets, data preprocessing, and data augmentation, are often compromised by arbitrarily chosen validation methodologies in existing studies. This leads to biases under standardized conditions. This paper reviews these methodologies to pinpoint what diminishes evaluation reliability. Experiments in standardized environments reveal the difficulties in comparing performance absolutely. The findings highlighted the need for a consistent validation methodology to boost evaluation reliability and enable fair comparisons.