• International Journal of Computer Science & Network Security
• /
• 제21권12spc호
• /
• pp.526-538
• /
• 2021

Machine and deep learning-based models are emerging techniques that are being used to address prediction problems in biomedical data analysis. DNA sequence prediction is a critical problem that has attracted a great deal of attention in the biomedical domain. Machine and deep learning-based models have been shown to provide more accurate results when compared to conventional regression-based models. The prediction of the gene sequence that leads to cancerous diseases, such as prostate cancer, is crucial. Identifying the most important features in a gene sequence is a challenging task. Extracting the components of the gene sequence that can provide an insight into the types of mutation in the gene is of great importance as it will lead to effective drug design and the promotion of the new concept of personalised medicine. In this work, we extracted the exons in the prostate gene sequences that were used in the experiment. We built a Deep Neural Network (DNN) and Bi-directional Long-Short Term Memory (Bi-LSTM) model using a k-mer encoding for the DNA sequence and one-hot encoding for the class label. The models were evaluated using different classification metrics. Our experimental results show that DNN model prediction offers a training accuracy of 99 percent and validation accuracy of 96 percent. The bi-LSTM model also has a training accuracy of 95 percent and validation accuracy of 91 percent.

• 한국지반공학회논문집
• /
• 제38권12호
• /
• pp.103-112
• /
• 2022

본 연구에서는 시간-침하량 계측 데이터를 기반으로 한 기존 침하 예측 이론식을 확인하였다. 기존 계측 기반 침하 예측 이론식 중 쌍곡선법 및 Asaoka법이 정확도가 높게 나타났으며, 이외 방법은 정확도가 낮은 것으로 확인되었다. 이러한 분석 결과를 토대로 기존 침하 예측 방법의 한계점을 도출하였으며, 이러한 한계점을 보완할 수 있는 개선방안으로써 가중 비선형 회귀분석을 통한 침하 예측 방법을 제시하였다.

• 한국통신학회논문지
• /
• 제25권6A호
• /
• pp.782-793
• /
• 2000

본 논문은 10GHz이상의 주파수 대역을 사용하는 위성 통신 링크에서 강우에 의해 감쇠된 신호 레벨을 동적으로 예측하기 위한 비교적 간단한 예측 기법을 제시한다. 예측 기법은 이산시간 저역 통과 필터링, 기울기에 근거한 예측, 평균 오차 보정, 고정 및 가변 혼합 예측 여유 할당의 4가지 기능 블록을 갖는다. Ku 대역의 측정 데이터로부터 주파수 스케일링에 의해 얻어진 Ka 대역 강우 감쇠 데이터를 이용하여 시뮬레이션을 수행하였다. 평균 오차 보정을 갖는 기울기 예측 기법은 1dB 이하의 표준 편차를 가지며, 평균 오차 보정에 의해 약 1.5~2.5 배의 예측 오차 감소를 보인다. 요구되는 평균 여유 면에서, 혼합 예측 여유 할당은 고정 여유 방법과 가변 여유 방법에 비해 더 적은 평균 여유를 요구한다.

• 한국IT서비스학회지
• /
• 제11권1호
• /
• pp.211-221
• /
• 2012

Many metric-based classification models have been proposed to predict fault-proneness of software module. This paper presents two prediction models using Bayesian classifier which is one of the most popular modern classification algorithms. Bayesian model based on Bayesian probability theory can be a promising technique for software quality prediction. This is due to the ability to represent uncertainty using probabilities and the ability to partly incorporate expert's knowledge into training data. The two models, Na$\ddot{i}$veBayes(NB) and Bayesian Belief Network(BBN), are constructed and dimensionality reduction of training data and test data are performed before model evaluation. Prediction accuracy of the model is evaluated using two prediction error measures, Type I error and Type II error, and compared with well-known prediction models, backpropagation neural network model and support vector machine model. The results show that the prediction performance of BBN model is slightly better than that of NB. For the data set with ambiguity, although the BBN model's prediction accuracy is not as good as the compared models, it achieves better performance than the compared models for the data set without ambiguity.

• Geomechanics and Engineering
• /
• 제23권1호
• /
• pp.51-59
• /
• 2020

In this paper, the WEKA platform was used to mine and analyze measured data of floor failure depth and a prediction system of floor failure depth was developed with Java. Based on the standardization and discretization of 35-set measured data of floor failure depth in China, the grey correlation degree analysis on five factors affecting the floor failure depth was carried out. The correlation order from big to small is: mining depth, working face length, floor failure resistance, mining thickness, dip angle of coal seams. Naive Bayes model, neural network model and decision tree model were used for learning and training, and the accuracy of the confusion matrix, detailed accuracy and node error rate were analyzed. Finally, artificial neural network was concluded to be the optimal model. Based on Java language, a prediction system of floor failure depth was developed. With the easy operation in the system, the prediction from measured data and error analyses were performed for nine sets of data. The results show that the WEKA prediction formula has the smallest relative error and the best prediction effect. Besides, the applicability of WEKA prediction formula was analyzed. The results show that WEKA prediction has a better applicability under the coal seam mining depth of 110 m~550 m, dip angle of coal seams of 0°~15° and working face length of 30 m~135 m.

• 한국콘텐츠학회논문지
• /
• 제8권10호
• /
• pp.76-87
• /
• 2008

동적 경로 안내 시스템과 같은 첨단 여행 정보 시스템(ATIS)의 발전에 따라 도로 네트워크 상에서 보다 정확한 주행 시간 예측 기법에 대한 연구가 활발히 진행되고 있다. 그러나 기존 대부분의 연구들은 주어진 경로 상의 평균 주행 속도만을 기반으로 주행 시간을 예측한다. 이는 러시아워 시간대의 혼잡한 도로, 주말에 교외로 나가는 대규모의 차량 등과 같은 일별 혹은 주별 도로 교통 상황을 반영하지 못하기 때문에, 주행 시간 예측의 정확도가 저하된다. 이를 해결하기 위해 본 연구에서는 규칙-기반 분류화 기법을 이용한 주행 시간 예측 알고리즘을 제안한다. 제안된 알고리즘은 데이터마이닝 기법인 규칙-기반 분류화 기법을 사용하여, 과거 차량의 궤적 데이터로부터 하루의 시간대별 교통량과 주별 차량의 운행 양식 등 도로 교통 상황을 추출하고, 이를 통해 차량의 주행 시간을 보다 정확하게 예측한다. 제안된 알고리즘 기존의 링크-기반 예측(link-based prediction) 알고리즘, Micro T* 알고리즘[3], 그리고 스위칭 (switching) 알고리즘[10]과 예측 정확도 측면에서 성능 비교를 수행한다. 예측 정확도 성능 비교 결과, 제안된 기법이 타 예측 기법에 비해 MARE (mean absolute relative error) 가 크게 감소하여 성능이 향상됨을 보인다. 그 밖에 다른 기법들과 장단점을 비교하여, 제안된 기법의 유용성을 나타낸다.

• 품질경영학회지
• /
• 제47권1호
• /
• pp.187-198
• /
• 2019

Purpose: In this study, a reliability prediction based reliability growth management is suggested especially for the early development phase of a system and the case study of surveillance system is given. Methods: The proposed reliability prediction based reliability growth management procedures consists of 7 Steps. In Step 1, the stages for reliability growth management are classified according to the major design changes. From Step 2 to Step 5, system reliability is predicted based on reliability structures and the predicted reliabilities of subsystems (Level 2) and modules (Level 3). At each stage, by comparing the predicted system reliability with that of the previous stage, the reliability growth of the system is checked in Step 6. In Step 7, when the predicted value of sustem reliability does not satisfy the reliability goal, some design alternatives are considered and suggested to improve the system reliability. Results: The proposed reliability prediction based reliability growth management can be an efficient alternative for managing reliability growth of a system in its early development phase. The case study shows that it is applicable to weapon system such as a surveillance system. Conclusion: In this study, the procedures for a reliability prediction based reliability growth management are proposed to satisfy the reliability goal of the system efficiently. And it is expected that the use of the proposed procedures would reduce, in the test and evaluation phase, the number of corrective actions and its cost as well.

• Journal of Advanced Marine Engineering and Technology
• /
• 제41권1호
• /
• pp.56-61
• /
• 2017

본 논문은 시간지연이 있는 데이터의 예측기법과 햅틱기반의 원격조작시스템에서의 응용방법을 다룬다. 일반적으로 네트워크 환경은 데이터 전송에 따른 시간지연이 필수적으로 동반되며, 햅틱기반의 원격조작시스템이 이러한 네트워크 환경에 구현되는 경우 시간지연으로 인해 전체 시스템의 성능저하를 피할 수 없다. 이러한 상황을 고려하여, 본 논문은 ARMA모델을 기반으로 모델파라미터의 학습방법과 실시간 예측을 위한 재귀적 알고리즘을 제안한다. 제안된 방법은 가상공간에 놓인 물체에 대하여 양방향 햅틱 상호작용의 상황에서 5ms의 샘플링 주기로 획득한 햅틱데이터에 적용되며, 그 결과로서 100ms 이후의 값을 예측함에 있어 위치수준 오차 1mm이내의 예측성능을 보였다.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1997년도 춘계학술발표회논문집(1)
• /
• pp.362-367
• /
• 1997

To assess the coolability of particle bed, which is formed in reactor cavity, it is important to assess the prediction capabilities of Dryout Heat flux correlations. The existing DHF correlations (Sowa et al., Dhir-Catton (a), Dhir-Catton (b), Hardee-Nilson, Ostesen, Shires-Stevens, Lipinski, Jones et al., Dhir-Barleon, Theofanous-Saito, Henry-Fauske) for particle beds are assessed using developed DHF database. Eleven DHF correlations are chosen for assessment based on literature survey. Among them, five are based on flooding correlation, which are used for chemical engineering and others are based on conservation equations. The parameters in DHF correlations are directly substituted into correlations. Totally 202 data are classified into 6 groups based on bed thickness and particle diameter. In each group, prediction capabilities of correlations are assessed and shown by standard deviation and root mean square (RMS) error. Prediction capability of each correlation depends on the data group and none of correlations shows best prediction capability on entire groups. According to present study, even if those correlations show poor prediction capability, Lipinski correlation is best correlation considering entire groups.

• 약학회지
• /
• 제59권1호
• /
• pp.29-39
• /
• 2015

In recent years, physiologically based pharmacokinetic (PBPK) modeling has been widely used in pharmaceutical industries as well as regulatory health authorities for drug discovery and development. Several application areas of PBPK have been introduced so far including drug-drug interaction prediction, transporter-mediated interaction prediction, and pediatric PK prediction. The purpose of this review is to introduce PBPK and illustrates one of its application areas, particularly pediatric PK prediction by utilizing existing adult PK data and in vitro data. The evaluation of the initial PBPK for adult was done by comparing with experimental PK profiles and the scaling from adult to pediatric was conducted using age-related changes in size such as tissue compartments, and protein binding etc. Sotalol and lorazepam were selected in this review as model drugs for this purpose and were re-evaluated using the PBPK models by GastroPlus$^{(R)}$. The challenges and strategies of PBPK models using adult PK data as well as appropriate in vitro assay data for extrapolating pediatric PK at various ages were also discussed in this paper.