• 정보보호학회논문지
• /
• 제32권3호
• /
• pp.555-564
• /
• 2022

최근 사이버 공격은 지능적이고 고도화된 악성코드를 활용한 해킹 기법을 활용하여 재택근무 및 원격의료, 자동산업설비를 공격하고 있어서 피해 규모가 커지고 있다. 안티바이러스와 같은 전통적인 정보보호체계는 시그니처 패턴 기반의 알려진 악성 URL을 탐지하는 방식이어서 알려지지 않은 악성 URL을 탐지할 수 없다. 그리고 종래의 정적 분석 기반의 악성 URL 분석 방식은 동적 로드와 암호화 공격에 취약하다. 본 연구에서는 악성 URL 데이터를 동적으로 학습하여 효율적으로 악성 URL 탐지하는 기법을 제안한다. 제안한 탐지 기법에서는 머신러닝 기반의 특징 선택 알고리즘을 사용해 악성 코드를 분류했고, 가중 유클리드 거리(Weighted Euclidean Distance, WED)를 활용하여 사전처리를 진행한 후 난독화 요소를 제거하여 정확도를 개선한다. 실험 결과에 따르면 본 연구에서 제안한 머신러닝 기반 악성 URL 탐지 기법은 종래의 방법 대비 2.82% 향상된 89.17%의 정확도를 보인다.

• Asian Journal of Business Environment
• /
• 제12권3호
• /
• pp.1-12
• /
• 2022

Purpose: This study aims to investigate whether AIS data can be used as a supporting indicator or as an initial signal to describe Indonesia's export-import conditions in real-time. Research design, data, and methodology: This study performs several stages of data selection to obtain indicators from AIS that truly reflect export-import activities in Indonesia. Also, investigate the potential of AIS indicators in producing forecasts of the value and volume of Indonesian export-import using conventional statistical methods and machine learning techniques. Results: The six preprocessing stages defined in this study filtered AIS data from 661.8 million messages to 73.5 million messages. Seven predictors were formed from the selected AIS data. The AIS indicator can be used to provide an initial signal about Indonesia's import-export activities. Each export or import activity has its own predictor. Conventional statistical methods and machine learning techniques have the same ability both in forecasting Indonesia's exports and imports. Conclusions: Big data AIS can be used as a supporting indicator as a signal of the condition of export-import values in Indonesia. The right method of building indicators can make the data valuable for the performance of the forecasting model.

• 한국수자원학회논문집
• /
• 제56권9호
• /
• pp.563-574
• /
• 2023

최근 기후변화로 인해 유역의 기상자료에 대한 반응이 달라지고 있어 강우-유출 모의에 대한 연구는 중요해지고 있다. 아울러 최근 기계학습 기법에 대한 높은 관심으로 이를 통한 강우-유출 모의 역시 활발하게 증가하고 있으나 기계학습 모형이 전통적으로 사용되어온 개념적 모형에 비해 활용성이 높은지는 아직 확실치 않다. 본 연구에서는 개념적 모형인 GR6J와 기계학습 모형인 Random Forest 성능을 한국 전역의 38개 계측 유역에 대해 계측 유역 예측기법과 미계측 유역 예측기법을 이용해 평가하였다. 먼저 계측 유역 적용기법 평가를 위해 각 모형을 관측 일 유량자료에 학습시키고 분리된 평가기간에 대한 모의성능을 비교하였다. 이후 미계측 유역 모의성능 평가를 위해 인접성 기반 지역화 방법을 Leave-One-Out Cross-Validation (LOOCV)을 이용해 평가하였다. 그 결과 계측 유역 평가에서는 Random Forest 기법이 GR6J 모형보다 일관되게 높은 성능을 보였다. 학습된 데이터를 출력 값으로 재생산하도록 구조화되어 있는 기계학습 기법이 개념적 이론을 통한 모형보다 높은 재현성을 갖기 때문으로 판단된다. 하지만 Random Forest 모형의 성능은 미계측 유역의 예측기법으로는 재현되지 않았고 GR6J 모형보다 성능이 더 낮은 것이 확인되었다. 본 연구는 기계학습 모형은 계측 유역의 유출예측에는 적용성이 높을 수 있으나 미계측 유역에 대한 적용가능성은 전통적인 개념적 모형보다 낮을 수 있음을 제시한다.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.342-347
• /
• 2022

On Cloud, the important data of the user that is protected on remote servers can be accessed via internet. Due to rapid shift in technology nowadays, there is a swift increase in the confidential and pivotal data. This comes up with the requirement of data security of the user's data. Data is of different type and each need discrete degree of conservation. The idea of data security data science permits building the computing procedure more applicable and bright as compared to conventional ones in the estate of data security. Our focus with this paper is to enhance the safety of data on the cloud and also to obliterate the problems associated with the data security. In our suggested plan, some basic solutions of security like cryptographic techniques and authentication are allotted in cloud computing world. This paper put your heads together about how machine learning techniques is used in data security in both offensive and defensive ventures, including analysis on cyber-attacks focused at machine learning techniques. The machine learning technique is based on the Supervised, UnSupervised, Semi-Supervised and Reinforcement Learning. Although numerous research has been done on this topic but in reference with the future scope a lot more investigation is required to be carried out in this field to determine how the data can be secured more firmly on cloud in respect with the Machine Learning Techniques and cryptographic methods.

• Journal of Korean Neurosurgical Society
• /
• 제67권1호
• /
• pp.103-114
• /
• 2024

Objective : Decompressive craniectomy (DC) with duroplasty is one of the common surgical treatments for life-threatening increased intracranial pressure (ICP). Once ICP is controlled, cranioplasty (CP) with reinsertion of the cryopreserved autologous bone flap or a synthetic implant is considered for protection and esthetics. Although with the risk of autologous bone flap resorption (BFR), cryopreserved autologous bone flap for CP is one of the important material due to its cost effectiveness. In this article, we performed conventional statistical analysis and the machine learning technique understand the risk factors for BFR. Methods : Patients aged >18 years who underwent autologous bone CP between January 2015 and December 2021 were reviewed. Demographic data, medical records, and volumetric measurements of the autologous bone flap volume from 94 patients were collected. BFR was defined with absolute quantitative method (BFR-A) and relative quantitative method (BFR%). Conventional statistical analysis and random forest with hyper-ensemble approach (RF with HEA) was performed. And overlapped partial dependence plots (PDP) were generated. Results : Conventional statistical analysis showed that only the initial autologous bone flap volume was statistically significant on BFR-A. RF with HEA showed that the initial autologous bone flap volume, interval between DC and CP, and bone quality were the factors with most contribution to BFR-A, while, trauma, bone quality, and initial autologous bone flap volume were the factors with most contribution to BFR%. Overlapped PDPs of the initial autologous bone flap volume on the BRF-A crossed at approximately 60 mL, and a relatively clear separation was found between the non-BFR and BFR groups. Therefore, the initial autologous bone flap of over 60 mL could be a possible risk factor for BFR. Conclusion : From the present study, BFR in patients who underwent CP with autologous bone flap might be inevitable. However, the degree of BFR may differ from one to another. Therefore, considering artificial bone flaps as implants for patients with large DC could be reasonable. Still, the risk factors for BFR are not clearly understood. Therefore, chronological analysis and pathophysiologic studies are needed.

• 한국항공운항학회지
• /
• 제26권4호
• /
• pp.101-109
• /
• 2018

In order to predict the future needs of the aircraft repair parts, each military group develops and applies various techniques to their characteristics. However, the aircraft and the equipped weapon systems are becoming increasingly advanced, and there is a problem in improving the hit rate by applying the existing demand prediction technique due to the change of the aircraft condition according to the long term operation of the aircraft. In this study, we propose a new prediction model based on the conventional time-series analysis technique to improve the prediction accuracy of aircraft repair parts by using machine learning model. And we show the most effective predictive method by demonstrating the change of hit rate based on actual data.

• 한국가시화정보학회지
• /
• 제19권3호
• /
• pp.31-38
• /
• 2021

The energy harvesting system using an inverted flag is analyzed by using an immersed boundary method to consider the fluid and solid interaction. The inverted flag flutters at a lower critical velocity than a conventional flag. A fluttering motion is classified into straight, symmetric, asymmetric, biased, and over flapping modes. The optimal energy harvesting efficiency is observed at the biased flapping mode. Using the three different machine learning algorithms, i.e., artificial neural network, random forest, support vector regression, the energy harvesting efficiency is predicted by taking bending rigidity, inclination angle, and flapping frequency as input variables. The R² value of the artificial neural network and random forest algorithms is observed to be more than 0.9.

• Earthquakes and Structures
• /
• 제22권4호
• /
• pp.401-419
• /
• 2022

A novel hybrid extreme machine learning-multiverse optimizer (ELM-MVO) framework is proposed to predict the liquefaction phenomenon in seismically excited tunnel lining inside the sand lens. The MVO is applied to optimize the input weights and biases of the ELM algorithm to improve its efficiency. The tunnel located inside the liquefied sand lens is also evaluated under various near- and far-field earthquakes. The results demonstrate the superiority of the proposed method to predict the liquefaction event against the conventional extreme machine learning (ELM) and artificial neural network (ANN) algorithms. The outcomes also indicate that the possibility of liquefaction in sand lenses under far-field seismic excitations is much less than the near-field excitations, even with a small magnitude. Hence, tunnels designed in geographical areas where seismic excitations are more likely to be generated in the near area should be specially prepared. The sand lens around the tunnel also has larger settlements due to liquefaction.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.29-29
• /
• 2023

To mitigate the damaging impacts of floods, accurate prediction of runoff, streamflow and flood inundation is needed. Conventional approach of simulating hydrology and hydraulics using loosely coupled models cannot capture the complex dynamics of surface and sub-surface processes. Additionally, the scarcity of data in ungauged basins and quality of data in gauged basins add uncertainty to model predictions, which need to be quantified. In this presentation, first the role of integrated modeling on creating accurate flood simulations and inundation maps will be presented with specific focus on urban environments. Next, the use of machine learning in producing streamflow predictions will be presented with specific focus on incorporating covariate shift and the application of theory guided machine learning. Finally, a framework to quantify the uncertainty in flood models using Hierarchical Bayesian Modeling Averaging will be presented. Overall, this presentation will highlight that creating accurate information on flood magnitude and extent requires innovation and advancement in different aspects related to hydrologic predictions.

• 방송공학회논문지
• /
• 제25권2호
• /
• pp.157-165
• /
• 2020

본 논문에서는 임베디드 시스템에서의 양자화 기계학습을 수행할 경우 발생하는 양자화 오차를 효과적으로 보상하기 위한 방법론을 제안한다. 경사 도함수(Gradient)를 사용하는 기계학습이나 비선형 신호처리 알고리즘에서 양자화 오차는 경사 도함수의 조기 소산(Early Vanishing Gradient)을 야기하여 전체적인 알고리즘의 성능 하락을 가져온다. 이를 보상하기 위하여 경사 도함수의 최대 성분에 대하여 직교하는 방향의 보상 탐색 벡터를 유도하여 양자화 오차로 인한 성능 하락을 보상하도록 한다. 또한, 기존의 고정 학습률 대신, 내부 순환(Inner Loop) 없는 비선형 최적화 알고리즘에 기반한 적응형 학습률 결정 알고리즘을 제안한다. 실험 결과 제안한 방식의 알고리즘을 로젠블록 함수를 통한 비선형 최적화 문제에 적용할 시 양자화 오차로 인한 성능 하락을 최소화시킬 수 있음을 확인하였다.