• Membrane and Water Treatment
• /
• 제9권2호
• /
• pp.115-121
• /
• 2018

Artificial neural network (ANN) simulation is used to predict the dynamic change of permeate flux during wheat starch industry wastewater microfiltration with and without static turbulence promoter. The experimental program spans range of a sedimentation times from 2 to 4 h, for feed flow rates 50 to 150 L/h, at transmembrane pressures covering the range of $1{\times}10^5$ to $3{\times}10^5Pa$. ANN predictions of the wastewater microfiltration are compared with experimental results obtained using two different set of microfiltration experiments, with and without static turbulence promoter. The effects of the training algorithm, neural network architectures on the ANN performance are discussed. For the most of the cases considered, the ANN proved to be an adequate interpolation tool, where an excellent prediction was obtained using automated Bayesian regularization as training algorithm. The optimal ANN architecture was determined as 4-10-1 with hyperbolic tangent sigmoid transfer function transfer function for hidden and output layers. The error distributions of data revealed that experimental results are in very good agreement with computed ones with only 2% data points had absolute relative error greater than 20% for the microfiltration without static turbulence promoter whereas for the microfiltration with static turbulence promoter it was 1%. The contribution of filtration time variable to flux values provided by ANNs was determined in an important level at the range of 52-66% due to increased membrane fouling by the time. In the case of microfiltration with static turbulence promoter, relative importance of transmembrane pressure and feed flow rate increased for about 30%.

• 정보처리학회논문지B
• /
• 제11B권6호
• /
• pp.667-674
• /
• 2004

이미지에서 문자 추출은 영상을 이해하기 위한 가장 기초적이고 중요한 문제이다. 본 논문에서는 문자의 획 특징을 이용하는 통계적인 방법으로 문자 영역을 검증하는 방법을 제안한다. 제안하는 방법은 $16\times16$ 크기의 텍스트와 비텍스트 이미지를 웨이블릿(wavelet) 변환하여 문자의 획과 방향성을 표현하는 35차원의 특징을 추출한다. 추출된 특징 중 변별력이 높은 특징만을 선택하여 SVM(Support Vector Machine) 분류기를 구성한다. 분류기론 이용하여 $16\times16$크기의 윈도우로 검증 영역을 스캔하면서, 각각의 윈도우를 텍스트와 비텍스트로 분류하고 최종적으로 검증 영역의 텍스트 여부를 결정한다. 제안한 방법을 적용함으로써 텍스트와 유사하여 구별하기 어려운 비텍스트 영역을 검증할 수 있었다.

• Journal of Positioning, Navigation, and Timing
• /
• 제6권4호
• /
• pp.167-179
• /
• 2017

In this paper, a simplified Cubature Kalman Filter (SCKF) is proposed to reduce the computation load of CKF, which is then used as a filter for transfer alignment of shipboard INS. CKF is an approximate Bayesian filter that can be applied to non-linear systems. When an initial estimation error is large, convergence characteristic of the CKF is more stable than that of the Extended Kalman Filter (EKF), and the reliability of the filter operation is more ensured than that of the Unscented Kalman Filter (UKF). However, when a system degree is large, the computation amount of CKF is also increased significantly, becoming a burden on real-time implementation in embedded systems. A simplified CKF is proposed to address this problem. This filter is applied to shipboard inertial navigation system (INS) transfer alignment. In the filter design for transfer alignment, measurement type and measurement update rate should be determined first, and if an application target is a ship, lever-arm problem, flexure of the hull, and asynchronous time problem between Master Inertial Navigation System (MINS) and Slave Inertial Navigation System (SINS) should be taken into consideration. In this paper, a transfer alignment filter based on SCKF is designed by considering these problems, and its performance is validated based on simulations.

• 수산해양기술연구
• /
• 제55권2호
• /
• pp.95-104
• /
• 2019

This study is aimed to take a stock assessment of blackthroat seaperch Doederleinia seaperch regarding the fishing effort of large-powered Danish Seine Fishery and Southwest Sea Danish Seine Fishery. For the assessment, the state-space model was implemented and the standardized catch per unit effort (CPUE) of large powered Danish Seine Fishery and Southwest Sea Danish Seine Fishery which is necessary for the model was estimated with generalized linear model (GLM). The model was adequate for stock assessment because its r-square value was 0.99 and root mean square error (RMSE) value was 0.003. According to the model with 95% confidence interval, maximum sustainable yield (MSY) of Blackthroat seaperch is from 2,634 to 6,765 ton and carrying capacity (K) is between 33,180 and 62,820. Also, the catchability coefficient (q) is between 2.14E-06 and 3.95E-06 and intrinsic growth rate (r) is between 0.31 and 0.72.

• Animal Bioscience
• /
• 제35권5호
• /
• pp.648-658
• /
• 2022

Objective: The identification of nonlinear mixed models that describe the growth trajectory of New Zealand rabbits was performed based on weight records and carcass measures obtained using ultrasonography. Methods: Phenotypic records of body weight (BW) and loin eye area (LEA) were collected from 66 animals raised in a didactic-productive module of cuniculture located in the southern Piaui state, Brazil. The following nonlinear models were tested considering fixed parameters: Brody, Gompertz, Logistic, Richards, Meloun 1, modified Michaelis-Menten, Santana, and von Bertalanffy. The coefficient of determination (R²), mean squared error, percentage of convergence of each model (%C), mean absolute deviation of residuals, Akaike information criterion (AIC), and Bayesian information criterion (BIC) were used to determine the best model. The model that best described the growth trajectory for each trait was also used under the context of mixed models, considering two parameters that admit biological interpretation (A and k) with random effects. Results: The von Bertalanffy model was the best fitting model for BW according to the highest value of R² (0.98) and lowest values of AIC (6,675.30) and BIC (6,691.90). For LEA, the Logistic model was the most appropriate due to the results of R² (0.52), AIC (783.90), and BIC (798.40) obtained using this model. The absolute growth rates estimated using the von Bertalanffy and Logistic models for BW and LEA were 21.51g/d and 3.16 cm², respectively. The relative growth rates at the inflection point were 0.028 for BW (von Bertalanffy) and 0.014 for LEA (Logistic). Conclusion: The von Bertalanffy and Logistic models with random effect at the asymptotic weight are recommended for analysis of ponderal and carcass growth trajectories in New Zealand rabbits. The inclusion of random effects in the asymptotic weight and maturity rate improves the quality of fit in comparison to fixed models.

• 지능정보연구
• /
• 제29권1호
• /
• pp.107-119
• /
• 2023

군인의 동작 및 운동 상태를 인식하는 기술은 웨어러블 테크놀로지와 인공지능의 결합으로 최근 대두되어 병력 관리의 패러다임을 바꿀 기술로 주목받고 있다. 이때 훈련 상황에서의 평가 및 솔루션 제공, 전투 상황에서의 효율적 모니터링 기능을 의도한대로 제공하기 위해서는 상태 판별의 정확도가 매우 높은 수준으로 유지되어야만 한다. 하지만 입력 데이터가 시계열 또는 시퀀스로 주어지는 경우, 기존의 피드포워드 신경망으로는 분류 성능을 극대화하는데 한계가 발생한다. 전장에서의 군사 동작 인식을 위해 다뤄지는 인간의 행동양식 데이터(3축 가속도 및 3축 각속도)는 시의존적 특성의 분석이 요구되기 때문에, 본 논문은 순환 신경망인 LSTM(Long-short Term Memory) 네트워크를 활용하여 취득 데이터의 이동 양상 및 순서 의존성을 파악하고 여덟 가지의 대표적 군사 동작(Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, High Crawl)을 분류하는 고성능 인공지능 모델을 제안한다. 이때, 학습 조건 및 모델 변수는 그 정확도에 결정적인 영향을 끼치지만 인간의 수동적 조정이 필요해 비용 비효율적이고 최적의 값을 보장하지 못한다. 본 논문은 기계 스스로 일반화 성능이 극대화된 조건들을 취득할 수 있도록 베이지안 최적화를 활용해 하이퍼파라미터를 최적화한다. 그 결과, 최종 아키텍쳐는 학습 가능한 파라미터의 개수가 유사한 기존의 인공 신경망과 비교해서 오차율이 62.56% 감소할 수 있었으며, 최종적으로 98.39%의 정확도로 군사 동작 인식 기능을 구현할 수 있었다.