The secondary growth model for Salmonella was developed based on the artificial neural network (ANN) with data collected from ComBase and FoodData Central. In addition to the existing secondary model variables (temperature, pH, Na+, and water contents), more input variables (sugar, carbohydrate, lipid, and protein contents) were considered. The output variables were microbial growth parameters (lag phase duration [l] and maximum growth rate [mmax]). A commercial ANN program (NeuralWorks Predict) was utilized with training at 80%, validation at 10%, and test data at 10%. ANN models were created using all data and cleansed data. Using the cleansed data, the training/testing root mean square error (RMSE) for mmax improved from 0.14/0.16 to 0.11/0.14, whereas the RMSE for l was still not acceptable, from 11.94/33.03 to 7.09/4.18. The l data were divided into two ranges with high and low goodness of fit, whereas the ANN model for each field was built, resulting in an optimally low RMSE.

This study deals with the application of an artificial neural network (ANN) model to predict power consumption for utilizing seawater source heat pumps of recirculating aquaculture system. An integrated dynamic simulation model was constructed using the TRNSYS program to obtain input and output data for the ANN model to predict the power consumption of the recirculating aquaculture system with a heat pump system. Data obtained from the TRNSYS program were analyzed using linear regression, and converted into optimal data necessary for the ANN model through normalization. To optimize the ANN-based power consumption prediction model, the hyper parameters of ANN were determined using the Bayesian optimization. ANN simulation results showed that ANN models with optimized hyper parameters exhibited acceptably high predictive accuracy conforming to ASHRAE standards.

최근에 선박을 안전하게 설계 및 운항하기 위해 인공지능으로 운동성능을 예측하는 연구가 늘고 있다. 하지만 일반적인 선박 에 비해 소형 어선에 대한 연구는 부족한 실정이다. 본 논문에서는 소형 어선의 운동성능 계산에 필수적인 운동응답을 심층신경망으로 추정하는 모델을 제안한다. 15척의 소형 어선에 대하여 유체동역학 해석을 수행하였으며 이를 통해 데이터베이스를 구축하였다. 환경 조 건과 주요 제원을 입력 데이터로, 단위 파고에 대한 운동응답(Response Amplitude Operator)을 출력 데이터로 설정하였다. 훈련된 심층신경 망 모델을 통해 예측된 운동응답은 유체동역학 해석 결과와 유사한 경향을 보이며 고주파 성분을 가진 운동응답 함수를 낮은 오차로 근 사하는 결과를 보여준다. 본 연구의 결과를 바탕으로 어선의 선형 특성 고려한 심층신경망 모델로 확장하여 연구 결과의 활용도를 넓히 고자 한다.

Tomato is one of the major widely cultivated crops around the world. The leaf area is directly related to the total amount of photosynthesis, which affects the yield and quality of the fruit. Traditional methods of measuring the leaf area are time-consuming and can cause damage to the leaves. To address these problems, various studies are being conducted for measuring the leaf area. In this study, we introduced a model to estimate the leaf area using images of tomatoes. Using images captured by a camera, we measured the leaf length and width and used linear regression analysis to derive the leaf area estimation formula. Furthermore, we used a Neural Network (NN) for additional analysis to compare the accuracy of the models. Initially, to verify the reliability of the image data, we conducted a correlation analysis between the actual measurement data and the image data, which showed a high positive correlation. The leaf area estimation model presented 23 estimation formulas. We used regression analysis to estimate the coefficients of each model and also used employed an artificial neural network analysis to derive high R-squared (R2) values and low Root Mean Square Error (RMSE) values. Among the estimation formulas, the ninth model showed the highest reliability with an R-squared value of 0.863. We conducted a verification experiment to confirm the accuracy of the selected model, and the R-squared value was 0.925. This study confirmed the reliability of data measured from images and the reliability of the leaf area estimation model using image data. These methods are expected to be an important tool in agriculture, using imaging equipment for measuring and monitoring the crop growth.

PURPOSES : This study aims to determine whether machine learning techniques based on the results of chemical analysis experiments can be rationally applied to evaluate the aging of various asphalt binders used throughout the country. METHODS : We conducted chemical experiments such as FT-IR, H-NMR, C- NMR, and GPC for the three-stage aging levels of eight types of asphalt binders used in the country and utilized two artificial neural network models to determine valid chemical experimentation and conditions for the use of neural modeling through predictions. RESULTS : The M-prop model, which combined the findings from each neural network model into a single artificial neural network model, demonstrated superior predictive performance compared with the M-base model, which assessed aging using two cluster layers. In addition, the minimum amount of data required to achieve 100% predictive accuracy for the target asphalt binders, regardless of the artificial neural network model, was 18, and the amount of training data decreased to less than 50%. CONCLUSIONS : The predictive accuracy of the aging of asphalt binders was significantly enhanced when GPC data was used, indicating that GPC should be prioritized in evaluating the aging of asphalt binders.

본 논문에서는 소형어선의 운동 응답을 예측하기 위해 딥러닝 모델을 구축하였다. 크기가 다른 두 소형어선을 대상으로 유체 동역학 성능을 평가하여 데이터세트를 확보하였다. 딥러닝 모델은 순환 신경망 기법의 하나인 장단기 메모리 기법(LSTM, Long Short-Term Memory)을 사용하였다. 딥러닝 모델의 입력 데이터는 6 자유도 운동 및 파고의 시계열 데이터를 사용하였으며, 출력 라벨로는 6 자유도 운동의 시계열 데이터로 선정하였다. 최적 LSTM 모델 구축을 위해 hyperparameter 및 입력창 길이의 영향을 평가하였다. 구축된 LSTM 모 델을 통해 입사파 방향에 따른 시계열 운동 응답을 예측하였다. 예측된 시계열 운동 응답은 해석 결과와 전반적으로 잘 일치함을 확인 할 수 있었다. 시계열의 길이가 길어짐에 따라서 예측값과 해석 결과의 차이가 발생하는데, 이는 장기 데이터에 따른 훈련 영향도가 감 소 됨에 따라 나타난 것으로 확인할 수 있다. 전체 예측 데이터의 오차는 약 85% 이상의 데이터가 10% 이내의 오차를 보였으며, 소형어 선의 시계열 운동 응답을 잘 예측함을 확인하였다. 구축된 LSTM 모델은 소형어선의 모니터링 및 경보 시스템에 활용될 수 있을 것으로 기대한다.

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

Image recognition is not very effective in the water environment due to multiple factors, such as high scattering and high scattering in the water column. This is why the relevant parameters in the Faster R-CNN network model need to adjust continuously to improve the effectiveness of water detection. The control variable method adjusts the program's learning rate by tuning the network model's parameters. Then, the number of training rounds is adjusted according to the loss function of each round, and finally, we can get the number of matches with the minimum loss function. Based on the experimental results on the dataset, it is shown that the proposed method not only selects the learning rate with the best detection results but also has the strongest robustness and achieves a 96%-99% recognition rate for passenger ships, cargo ships, warships, and bridges compared with other learning rates. Experiments show that the Faster R-CNN network model detects water targets with significant results, and the best network model learning rate parameter is 6×10-3.

기술 트렌드가 증가함에 따라, 엄청난 양의 데이터가 생성되고 있습니다. 많은 양의 데이터가 소비되는 기술 분야 중 하나는 컴퓨터 비전이다. 인간은 기계와 비교할 때 시각에 영향을 미치는 표정, 조명 또는 시야각과 같은 외부 조건에서도 얼굴이나 사물을 쉽게 감지하고 인식할 수 있다. 그 이유는 그것과 관련된 높은 차원 의 데이터 때문이다. 데이터 차원성은 모든 관측치에서 측정되는 변수의 총 수를 말합니다. 이번 사업은 안 면인식시스템에 적합한 다양한 차원감소 기법을 비교하고 조도가 다양한 안면이미지로 구성된 다양한 데이 터세트로 테스트해 모델의 정확도 향상에 도움이 되는 기법의 앙상블 모델을 제안하고 성능을 측정하는 것 이 목적이다.렉스 배경과 표현. 제안된 앙상블 모델은 주성분 분석(PCA)과 로컬 선형 임베딩(LLE)이라는 두 가지 차원 감소 기술의 혼합에서 벡터를 추출하고, 이를 밀도 높은 컨볼루션 신경망(CNN)을 통해 전달하여 야생 면(LFW) 데이터 세트의 얼굴을 예측한다. 이 모형은 0.95의 검정 정확도와 0.94의 검정 F1 점수로 수행 됩니다. 제안된 시스템은 시스템이 얼굴을 예측할 수 있는 제안된 앙상블 모델과 통합된 웹캠에서 라이브 비 디오 스트림을 캡처하는 플라스크를 사용하여 개발된 웹 앱을 포함한다.

이 논문에서는 공용중인 구조물의 상시 계측 자료를 사용한 온라인 유한요소 모델 업데이트 방법을 제안한다. 일반적인 최적화 방법에 기반한 기존의 방법은 최적해를 찾기까지 반복적으로 고유치 해석을 수행해야 하므로 상시 업데이트에 사용하기에는 효과적이지 못하다. 제안하는 방법은 별도의 오프라인 작업이나 사용자의 개입이 없이 자동화된 과정으로 계측과 동시에 온라인 유한요소모델 업데이트를 수행할 수 있는 새로운 방법이다. 자동화된 Cov-SSI 알고리즘을 통해 구조물의 진동 계측 신호로부터 고유진동수 및 모드 형상을 식별하고, 이를 다시 역 고유치 신경망에 입력하여 최종적으로 업데이트된 유한요소 모델의 파라미터를 추정한다. 풍하중을 받는 20층 전단 빌딩 구조 모형에 대한 수치예제를 통해 제시한 방법이 자동으로 연속적인 유한요소모델 업데이트를 할 수 있었음을 확인하였다. 또한, 계측 도중 구조물의 특성이 변화하는 시나리오에 대한 예제에서 구조물의 변화가 일어나는 시점과 변화 후 변동된 구조 모델 파라미터 값을 성공적으로 추정할 수 있음을 확인하였다.

Predicting the quality of materials after they are subjected to plasma sintering is a challenging task because of the non-linear relationships between the process variables and mechanical properties. Furthermore, the variables governing the sintering process affect the microstructure and the mechanical properties of the final product. Therefore, an artificial neural network modeling was carried out to correlate the parameters of the spark plasma sintering process with the densification and hardness values of Ti-6Al-4V alloys dispersed with nano-sized TiN particles. The relative density (%), effective density (g/cm3), and hardness (HV) were estimated as functions of sintering temperature (oC), time (min), and composition (change in % TiN). A total of 20 datasets were collected from the open literature to develop the model. The high-level accuracy in model predictions (>80%) discloses the complex relationships among the sintering process variables, product quality, and mechanical performance. Further, the effect of sintering temperature, time, and TiN percentage on the density and hardness values were quantitatively estimated with the help of the developed model.

The contemporary high-tech structures have become enlarged and their functions more diversified. Steel concrete structure and composite material structures are not exceptions. Therefore, there have been on-going studies on fiber reinforcement materials to improve the characteristics of brittleness, bending and tension stress and others, the short-comings of existing concrete. In this study, the purpose is to develop the estimated model with dynamic characteristics following the steel fiber mixture rate and formation ration by using the nerve network in mixed steel fiber reinforced concrete (SFRC). This study took a look at the tendency of studies by collecting and analyzing the data of the advanced studies on SFRC, and facilitated it on the learning data required in the model development. In addition, by applying the diverse nerve network model and various algorithms to develop the optimal nerve network model appropriate to the dynamic characteristics. The accuracy of the developed nerve network model was compared with the experiment data value of other researchers not utilized as the learning data, the experiment data value undertaken in this study, and comparison made with the formulas proposed by the researchers. And, by analyzing the influence of learning data of nerve network model on the estimation result, the sensitivity of the forecasting system on the learning data of the nerve network is analyzed.

Simultaneous modelling was carried out using the neural networks with three inputs including a distinguishing variable for the steam table. It covered whole steam tables including the compressed, saturated and superheated region of water. And relative errors of the thermodynamic properties such as specific volume, enthalpy, entropy were compared using the neural networks and the linear interpolation method. As a result of the analysis, The neural networks has proven to be powerful in modeling the steam table because it has slightly better results than the interpolation method.

The use of radar-based systems for vessel monitoring is not suitable in populated areas, due to the high electromagnetic emissions. In this paper, a camera based vessel recognition system for application in the context of Vessel Traffic Services (VTS) and Homeland Protection (HP) is proposed. Our approach is designed to extend the functionality of traditional VTS systems by permitting the classification of both cooperative and non-cooperative targets, using camera images only. This allows enhancing the surveillance function in populated areas, where public opinion is strongly concerned about electromagnetic emissions and therefore antennas are suspiciously observed and radars are not allowed. Experiments have been carried out on a publicly available data set of images coming from the ARGOS boat traffic monitoring system in the City of Venice (Italy). The obtained classification accuracy of 89.6% (with 11 different classes of boats) demonstrates the effectiveness of the proposed approach.