• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.19-25
• /
• 2023

In this paper, we propose a method for improving raw images captured in a low light condition based on deep learning considering the image signal processing. In the case of a smart phone camera, compared to a DSLR camera, the size of a lens or sensor is limited, so the noise increases and the reduces the quality of images in low light conditions. Existing deep learning-based low-light image processing methods create unnatural images in some cases since they do not consider the lens shading effect and white balance, which are major factors in the image signal processing. In this paper, pixel distances from the image center and channel average values are used to consider the lens shading effect and white balance with a deep learning model. Experiments with low-light images taken with a smart phone demonstrate that the proposed method achieves a higher peak signal to noise ratio and structural similarity index measure than the existing method by creating high-quality low-light images.

• Journal of Aerospace System Engineering
• /
• v.16 no.6
• /
• pp.8-17
• /
• 2022

This paper presents a novel geometric modeling technique to predict the mechanical properties of an aircraft wing's skin-stringer integrated panel. Due to mechanical and adhesive fastening, this panel is vulnerable to stress concentration and debonding, so we designed it to integrate the skin and stringer using three-dimensional woven composites. Geometric modeling was conducted by measuring the geometric parameters of the specimen and defining the pattern of the yarns as functions. We used a weighted average model with iso-strain and iso-stress assumptions to predict the mechanical properties of the panel parts. We then compared the results of a finite element analysis with a compression test to verify the accuracy of our model. Our proposed technique proved to be more efficient than the traditional experimental method for predicting the mechanical properties of skin-stringer integrated panels.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.73-79
• /
• 2022

The Python language widely used in artificial intelligence (AI) projects is an interpreter language, and errors occur at runtime. In order to prevent project failure due to errors, it is necessary to handle exceptions in code that can cause exceptional situations in advance. In particular, in AI projects that require a lot of resources, exceptions that occur after long execution lead to a large waste of resources. However, since exception handling depends on the developer's experience, developers have difficulty determining the appropriate exception to catch. To solve this need, we propose an approach that recommends exceptions to catch to developers during development by learning the existing exception handling statements. The proposed method receives the source code of the try block as input and recommends exceptions to be handled in the except block. We evaluate our approach for a large project consisting of two frameworks. According to our evaluation results, the average AUPRC is 0.92 or higher when performing exception recommendation. The study results show that the proposed method can support the developer's exception handling with exception recommendation performance that outperforms the comparative models.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.13-20
• /
• 2022

It's proposed and analyzed ML(Machine Learning) models to predict vehicle FC(Fuel Consumption) in real-time. The test driving was done for a car to measure vehicle speed, acceleration, road gradient and FC for training dataset. The various ML models were trained with feature data of speed, acceleration and road-gradient for target FC. There are two kind of ML models and one is regression type of linear regression and k-nearest neighbors regression and the other is classification type of k-nearest neighbors classifier, logistic regression, decision tree, random forest and gradient boosting in the study. The prediction accuracy is low in range of 0.5 ~ 0.6 for real-time FC and the classification type is more accurate than the regression ones. The prediction error for total FC has very low value of about 0.2 ~ 2.0% and regression models are more accurate than classification ones. It's for the coefficient of determination (R²) of accuracy score distributing predicted values along mean of targets as the coefficient decreases. Therefore regression models are good for total FC and classification ones are proper for real-time FC prediction.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.267-275
• /
• 2022

This paper proposed a Deep Neural Network Model system utilizing Keras for predicting air pollution risk of the cardiovascular disease through the effect of each component of air on the harmful virus using past air information, with analyzing 18,000 data sets of the Seoul Open Data Plaza. By experiments, the model performed tasks with higher accuracy when using methods of sigmoid, binary_crossentropy, adam, and accuracy through 3 hidden layers with each 8 nodes, resulting in 88.92% accuracy. It is meaningful in that any respiratory disease can utilize the risk prediction system if there are data on the effects of each component of air pollution and fine dust on oil-borne diseases. It can be further developed to provide useful information to companies that produce masks and air purification products.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.6
• /
• pp.1171-1181
• /
• 2022

Front Collision-Avoidance Assist (FCA) or Smart Cruise Control (SCC) is installed in a modern vehicle, and the amount of data exchange between ECUs increases rapidly. Therefore, Automotive Ethernet, especially SOME/IP, which supports wide bandwidth and two-way communication, is widely adopted to overcome the bandwidth limitation of traditional CAN communication. SOME/IP is a standard protocol compatible with various automobile operating systems, and improves connectivity between components in the vehicle. However, no encryption or authentication process is defined in the SOME/IP protocol itself. Therefore, there is a need for a security study on the SOME/IP protocol. This paper proposes a deep learning-based intrusion detection system in SOME/IP and performs six attacks to confirm the performance of the intrusion detection system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.163-170
• /
• 2022

This paper introduces a method of extracting facial features due to unrefined inputs in real life and improving the problem of not guaranteeing the ideal performance and speed of the object recognition model through a storage algorithm through weight summation. Many facial recognition processes ensure accuracy in ideal situations, but the problem of not being able to cope with numerous biases that can occur in real life is drawing attention, which may soon lead to serious problems in the face recognition process closely related to security. This paper presents a method of quickly and accurately recognizing faces in real time by comparing feature points extracted as input with a small number of feature points that are not overfit to multiple biases, using that various variables such as picture composition eventually take an average form.

• The Journal of Engineering Geology
• /
• v.33 no.1
• /
• pp.1-13
• /
• 2023

Predicting earthquakes is difficult due to the complexity of the systems underlying tectonic phenomena and incomplete understanding of the interactions among tectonic settings, tectonic stress, and crustal components. The Korean Peninsula is located in a stable intraplate region with a low average seismicity of M 2.3. As public interest in the earthquake grows, we analyzed earthquakes on the Korean Peninsula by attempting to predict spatio-temporal earthquake patterns and magnitudes using Facebook's Prophet model based on deep learning, and here we discuss seismic distribution zones using DBSCAN, a cluster analysis method. The Prophet model predicts future earthquakes in Chungcheongbuk-do, Gyeonggi-do, Seoul, and Gyeongsangbuk-do.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.277-277
• /
• 2023

최근 기후변화의 영향으로 호우의 발생빈도가 증가하고 있는 추세이며, 도시지역의 호우는 돌발적이고 국지적인 특성을 가지고 있어 인명과 재산피해 역시 증가하고 있으며, 급격한 도시화로 인한 구조적으로 홍수에 취약한 실정이다. 국지성 도시호우는 저층(1 km 내외)에서 형성되는 강우가 지배적이며, 기존의 대형레이더는 높은 산 정상에 설치되어 1.5 km 이상의 강우관측을 중심으로 운영됨에 따라 저층강우의 탐지 및 변동성 관측에 취약하여, 이에 대형 레이더에서 뿐만 아니라 도시단위의 국지성 호우관측에 대응할 수 있는 소형 레이더 기반 고정밀 강우관측 마련 및 운영 기술이 필요하다. 현재 K-water는 부산 에코델타 스마트시티에 도시 물재해 플랫폼 구현의 일환으로 돌발강우사전 탐지 및 도시의 신속·정확한 강우 관측을 위하여 높은 시공간 해상도를 제공하는 이중편파X 밴드 소형 강우레이더를 설치하고, 효율적 운용을 위해 각 고도각에서의 빔 차폐율을 확인하고 이를 고려한 최적 관측전략을 수립하였다. 또한 Z-Phi 방법을 이용한 반사도 감쇠 보정 기술을 개발하였으며, 강우 추정을 위해 하이브리드 고도면 합성 기법(HSR) 기법을 적용하고 검증하였다. 이후 소형 레이더의 정량적 추정강수를 이용하여 강우예측 정보를 생산하기 위해 이류모델을 적용하고, 비슬산과 소형 합성 레이더 추정강수로 선행 10분에서 180분까지 예측할 수 있도록 개발하였다. 또한, 지상강우관측 자료와의 정확도 비교 평가를 수행하고, 행정구역 및 표준유역의 예측 평균강우량을 생산하여 부산 에코델타 스마트시티 도시 물재해 통합관리 시스템과 연계운영을 위한 후속 과업을 수행중에 있다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.5
• /
• pp.61-73
• /
• 2009

Many software reliability growth models(SRGM) have been proposed since the software reliability issue was raised in 1972. The technology to estimate and grow the reliability of developing S/W to target value during testing phase were developed using them. Most of these propositions assumed the S/W debugging testing efforts be constant or even did not consider them. A few papers were presented as the software reliability evaluation considering the testing effort was important afterwards. The testing effort forms which have been presented by this kind of papers were exponential, Rayleigh, Weibull, or Logistic functions, and one of these 4 types was used as a testing effort function depending on the S/W developing circumstances. I propose the methology to evaluate the SRGM using least square estimater and maximum likelihood estimater for those 4 functions, and then examine parameters applying actual data adopted from real field test of developing S/W.