• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1722-1737
• /
• 2019

We developed an insider threat detection model to be used by organizations that repeat tasks at regular intervals. The model identifies the best combination of different feature selection algorithms, unsupervised learning algorithms, and standard scores. We derive a model specifically optimized for the organization by evaluating each combination in terms of accuracy, AUC (Area Under the Curve), and TPR (True Positive Rate). In order to validate this model, a four-year log was applied to the system handling sensitive information from public institutions. In the research target system, the user log was analyzed monthly based on the fact that the business process is processed at a cycle of one year, and the roles are determined for each person in charge. In order to classify the behavior of a user as abnormal, the standard scores of each organization were calculated and classified as abnormal when they exceeded certain thresholds. Using this method, we proposed an optimized model for the organization and verified it.

• 동의신경정신과학회지
• /
• 제30권4호
• /
• pp.327-340
• /
• 2019

Objectives: Alzheimer's disease (AD) is a complex disease accompanied by slow impairment of memory and coordination leading to behavioral changes. To date, the only treatment option is to delay the progress of the disease. The purpose of this study was to investigate the synergistic effects of combination treatment with donepezil and three herbal extracts SIP-3 in the AD mouse model induced by amyloid-β (Aβ). Methods: We tested SIP-3 extracts for the cytotoxicity on Aβ-treated SH-SY5Y cells. Then the synergistic effects of SIP-3 and donepezil were evaluated in the AD mouse model using animal experiments and the next generation sequencing (NGS) study. Results: We found that co-treatment with SIP-3 extracts and donepezil increased the viability in Aβ-treated SH-SY5Y cells. The beneficial effects of the co-treatment were also observed in the Aβ-induced AD mouse model. The NGS study was performed to show that the co-treatment of SIP-3 and donepezil restored the disease phenotype closely to the normal level in the AD mouse model in terms of mRNA expression. However, the phenotypes were only partially restored. Conclusions: This study suggests that the combination treatment has a potential to be used for the treatment of AD. However, longer periods of treatment may be required.

• 전자공학회논문지B
• /
• 제28B권10호
• /
• pp.831-841
• /
• 1991

A combined model of probabilistic and MLP(multi layer perceptron) model is proposed for the pattern classification of EMG( electromyogram) signals. The MLP model has a problem of not guaranteeing the global minima of error and different quality of approximations to Bayesian probabilities. The probabilistic model is, however, closely related to the estimation error of model parameters and the fidelity of assumptions. A proper combination of these will reduce the effects of the problems and be robust to input variations. Proposed model is able to get the MAP(maximum a posteriori probability) in the probabilistic model by estimating a priori probability distribution using the MLP model adaptively. This method minimize the error probability of the probabilistic model as long as the realization of the MLP model is optimal, and this is a good combination of the probabilistic model and the MLP model for the usage of MLP model reliability. Simulation results show the benefit of the proposed model compared to use the Mlp and the probabilistic model seperately and the average calculation time fro classification is about 50ms in the case of combined motion using an IBM PC 25 MHz 386model.

• Water Engineering Research
• /
• 제5권2호
• /
• pp.101-109
• /
• 2004

Aggregating information by combining forecasts from two or more forecasting methods is an alternative to using forecasts from just a single method to improve forecast accuracy. This paper describes the development and use of a monthly inflow forecast model based on an optimal linear combination (OLC) of forecasts derived from naive, persistence, and Ensemble Streamflow Prediction (ESP) forecasts. Using the cross-validation technique, the OLC model made 1-month ahead probabilistic forecasts for the Chungju multi-purpose dam inflows for 15 years. For most of the verification months, the skill associated with the OLC forecast was superior to those drawn from the individual forecast techniques. Therefore this study demonstrates that OLC can improve the accuracy of the ESP forecast, especially during the dry season. This study also examined the value of the OLC forecasts in reservoir operations. Stochastic Dynamic Programming (SDP) derived the optimal operating policy for the Chungju multi-purpose dam operation and the derived policy was simulated using the 15-year observed inflows. The simulation results showed the SDP model that updated its probability from the new OLC forecast provided more efficient operation decisions than the conventional SDP model.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권2호
• /
• pp.61-68
• /
• 2020

e-sports는 최근 꾸준한 성장을 이루면서 세계적인 인기 스포츠 종목이 되었다. 본 논문에서는 e-sports의 대표적인 게임인 리그오브레전드 경기 시작 단계에서의 승패 예측 모델을 제안한다. 리그오브레전드에서는 챔피언이라고 불리는 게임 상의 유닛을 플레이어가 선택하여 플레이하게 되는데, 각 플레이어의 선택을 통하여 구성된 팀의 챔피언 능력치 조합은 승패에 영향을 미친다. 제안 모델은 별다른 도메인 지식 없이 플레이어 단위 챔피언 능력치를 팀 단위 챔피언 능력치로 임베딩한 Bidirectional LSTM 임베딩 기반 딥러닝 모델이다. 기존 분류 모델들과 비교 결과 팀 단위 챔피언 능력치 조합을 고려한 제안 모델에서 58.07%의 가장 높은 예측 정확도를 보였다.

• 정보처리학회논문지B
• /
• 제17B권3호
• /
• pp.233-238
• /
• 2010

본 논문에서는 화질 저하 모델에 기반한 다중 인식기 결합을 이용하여 저화질 영상에 대한 인식 성능을 개선하기 위한 방법을 제안한다. 제안하는 방법은 화질 저하 모델을 이용해 특정 화질에 각각 특화된 복수의 인식기들을 생성한다. 인식 과정에서는 인식기들의 결과를 가중 평균에 의해 결합함으로써 최종 결과를 결정한다. 이 때, 각 인식기의 가중치는 입력 영상의 화질 추정 결과에 따라 동적으로 결정된다. 입력 영상의 화질에 특화된 인식기에는 큰 가중치를, 그렇지 않은 인식기에는 작은 가중치를 지정한다. 그 결과, 입력 영상의 화질 변이에 효과적으로 적응할 수 있다. 뿐만 아니라, 복수의 인식기를 사용하기 때문에 저화질 영상에 대하여 단일 인식 시스템보다 더욱 안정적인 성능을 나타낸다. 제안하는 다중 인식기 결합 방법은 화질을 고려하지 않은 다중 인식기 결합 방법이나, 화질을 고려한 단일 인식 방법과 비교하여 더 높은 인식률을 보였다.

• Korean Journal of Acupuncture
• /
• 제35권4호
• /
• pp.187-202
• /
• 2018

Objectives : Non-invasive transcranial electrical stimulation is one of therapeutic interventions to change in neural excitability of the cortex. Transcranial electro-acupuncture (TEA) can modulate brain functions through changes in cortical excitability as a model of non-invasive transcranial electrical stimulation. Some composites of fermented Scutellaria baicalenis (FSB) can activate intercellular signaling pathways for activation of brain-derived neurotrophic factor that is critical for formation of neural plasticity in stroke patients. This study was aimed at evaluation of combinatory treatment of TEA and FSB on behavior recovery and cortical neural excitability in rodent focal stroke model. Methods : Focal ischemic stroke was induced by photothrombotic injury to the motor cortex of adult rats. Application of TEA with 20 Hz and $200{\mu}A$ in combination with daily oral treatment of FBS was given to stroke animals for 3 weeks. Motor recovery was evaluated by rotating bean test and ladder working test. Electrical activity of cortical pyramidal neurons of stroke model was evaluated by using multi-channel extracellular recording technique and thallium autometallography. Results : Compared with control stroke group who did not receive any treatment, Combination of TEA and FSB treatment resulted in more rapid recovery of forelimb movement following focal stroke. This combination treatment also elicited increase in spontaneous firing rate of putative pyramidal neurons. Furthermore expression of metabolic marker for neural excitability was upregulated in peri-infract area under thallium autometallography. Conclusions : These results suggest that combination treatment of TEA and FSB can be a possible remedy for motor recovery in focal stroke.

• Asian-Australasian Journal of Animal Sciences
• /
• 제10권1호
• /
• pp.70-74
• /
• 1997

Data on 2,571 lactation records of Nili-Ravi buffaloes from four institutional herds and four field recording centers were analyzed under an animal model to see the effect of season definition on the error variance of the fitted model. Herd-year-season(HYS) was the main fixed effect along with permanent environment, breeding value and residuals as the random effects. All known relationships among the animals were considered. The error variance differed for various HYS combinations. It was minimum when then months were not grouped into seasons. The four or Five season scenarios were better than the two season scenarios. The average number of lactations represented in a HYS combination varied widely from 6 to 28. Very few subclasses for a given HYS combination warrants the use of fewer seasons for animal model evaluation of buffaloes.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2008년도 학술발표회 논문집
• /
• pp.500-504
• /
• 2008

The objective of this paper is to evaluate the feasibility of using an optimization model as a effective way to search conjunctive operation scheme to meet two conditions; one is to minimize the electric cost for pumping and another is to meet the water demand for satisfying customers. The feasibility is confirmed as comparing the best combinations of pumps between multi-regional water supply networks from multiple sources which are obtained through an optimization modeling and EPAnet modeling. KModsim model, a network optimization model, was used to determine conjunctive operation scheme in the pipe system. KModsim, based on Lagrangian Relaxation algorithm, is useful for modeling network system and obtaining simultaneously pump combination and water allocation with given input option such as energy unit cost supplying from a source into a consumer, operating pumping combination. This study develops the procedure of determining optimal conjunctive operation scheme with using KModsim model. As a study region, the water supplying systems of the Geojae-city in the Geongsang Namdo Province was selected and investigated. The EPAnet hydraulic simulation result(Ryu et al, 2007, KSWW) gave input data for optimization model; energy unit price(won/$m^3$), water service available area etc.. It was assured that the combination of pump operation through optimum conjunctive operation is to be optimum scheme to obtain the best economic water allocation with comparison to the hydraulic simulation result such as electric cost and pump combination cases. The results obtained through the study are as follows. First, It was found that a well-allocated water supply scheme, the best combination of pump operation through optimum joint operation, promises to save the electric cost and satisfy all operational goals such as stability and revenues during the period. Second, an application of KModSim, a network model, gave the amount of water allocation from each source to a consumer with consideration of economic supply. Finally, in a service area available to supply through conjunctive operation of existing inter-regional water supply networks within short distance, a conjunctive operation is useful for determining each transmission pipeline's service area and maximizing the effectiveness of optimizations in pumping operation time.

• 대한교통학회:학술대회논문집
• /
• 대한교통학회 1995년도 제27회 학술발표회
• /
• pp.84-98
• /
• 1995

Network-based model were developed to predict short term future traffic volume based on current traffic, historical average, and upstream traffic. It is presumed that upstream traffic volume can be used to predict the downstream traffic in a specific time period. Three models were developed for traffic flow prediction; a combination of historical average and upstream traffic, a combination of current traffic and upstream traffic, and a combination of all three variables. The three models were evaluated using regression analysis. The third model is found to provide the best prediction for the analyzed data. In order to balance the variables appropriately according to the present traffic condition, a heuristic adaptive weighting system is devised based on the relationships between the beginning period of prediction and the previous periods. The developed models were applied to 15-minute freeway data obtained by regular induction loop detectors. The prediction models were shown to be capable of producing reliable and accurate forecasts under congested traffic condition. The prediction systems perform better in the 15-minute range than in the ranges of 30-to 45-minute. It is also found that the combined models usually produce more consistent forecasts than the historical average.