• Animal Bioscience
• /
• v.34 no.4
• /
• pp.770-782
• /
• 2021

Objective: The aim of the present study was to compare the effectiveness of three approaches (the seasonal auto-regressive integrated moving average [SARIMA] model, the nonlinear autoregressive exogenous [NARX] artificial neural networks and Wood's model) to the prediction of milk yield during lactation. Methods: The dataset comprised monthly test-day records from 965 Polish Holstein-Friesian Black-and-White primiparous cows. The milk yields from cows in their first lactation (from 5 to 305 days in milk) were used. Each lactation was divided into ten lactation stages of approximately 30 days. Two age groups and four calving seasons were distinguished. The records collected between 2009 and 2015 were used for model fitting and those from 2016 for the verification of predictive performance. Results: No significant differences between the predicted and the real values were found. The predictions generated by SARIMA were slightly more accurate, although they did not differ significantly from those produced by the NARX and Wood's models. SARIMA had a slightly better performance, especially in the initial periods, whereas the NARX and Wood's models in the later ones. Conclusion: The use of SARIMA was more time-consuming than that of NARX and Wood's model. The application of the SARIMA, NARX and Wood's models (after their implementation in a user-friendly software) may allow farmers to estimate milk yield of cows that begin production for the first time.

• Communications for Statistical Applications and Methods
• /
• v.30 no.2
• /
• pp.119-133
• /
• 2023

With the rapid growth of the economy and fossil fuel consumption, the concentration of air pollutants has increased significantly and the air pollution problem is no longer limited to small areas. We conduct statistical analysis with the actual data related to air quality that covers the entire of South Korea using R and Python. Some factors such as SO₂, CO, O₃, NO₂, PM₁₀, precipitation, wind speed, wind direction, vapor pressure, local pressure, sea level pressure, temperature, humidity, and others are used as covariates. The main goal of this paper is to predict air quality index (AQI) spatio-temporal data. The observations of spatio-temporal big datasets like AQI data are correlated both spatially and temporally, and computation of the prediction or forecasting with dependence structure is often infeasible. As such, the likelihood function based on the spatio-temporal model may be complicated and some special modelings are useful for statistically reliable predictions. In this paper, we propose several methods for this big spatio-temporal AQI data. First, random effects with spatio-temporal basis functions model, a classical statistical analysis, is proposed. Next, neural networks model, a deep learning method based on artificial neural networks, is applied. Finally, random forest model, a machine learning method that is closer to computational science, will be introduced. Then we compare the forecasting performance of each other in terms of predictive diagnostics. As a result of the analysis, all three methods predicted the normal level of PM_2.5 well, but the performance seems to be poor at the extreme value.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2821-2823
• /
• 2002

In this paper we propose the Multi-FNN (Fuzzy-Neural Networks) for optimal identification modeling of complex system. The proposed Multi-FNNs is based on a concept of FNNs and exploit linear inference being treated as generic inference mechanisms. In the networks learning, backpropagation(BP) algorithm of neural networks is used to updata the parameters of the network in order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM(Hard C-Means)clustering algorithm which carry out the input-output dat a preprocessing function and Genetic Algorithm which carry out optimization of model The HCM clustering method is utilized to determine the structure of Multi-FNNs. The parameters of Multi-FNN model such as apexes of membership function, learning rates, and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization abilities of the model. NOx emission process data of gas turbine power plant is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• Journal of Korean Society of Transportation
• /
• v.18 no.1
• /
• pp.47-59
• /
• 2000

The purpose of this study is to develop travel-time estimation model using neural networks and prediction model using neural networks and kalman-filtering technique. The data used in this study are travel speed collected from inductive loop vehicle detection systems(VDS) and travel time collected from the toll collection system (TCS) between Seoul and Osan toll Plaza on the Seoul-Pusan Expressway. Two models, one for travel-time estimation and the other for travel-time Prediction were developed. Application cases of each model were divided into two cases, so-called, a single-region and a multiple-region. because of the different characteristics of travel behavior shown on each region. For the evaluation of the travel time estimation and Prediction models, two Parameters. i.e. mode and mean were compared using five-minute interval data sets. The test results show that mode was superior to mean in representing the relationship between speed and travel time. It is, however shown that mean value gives better results in case of insufficient data. It should be noted that the estimation and the Prediction of travel times based on the VDS data have been improved by using neural networks, because the waiting time at exit toll gates can be included for the estimation of travel time based on the VDS data by considering differences between VDS and TCS travel time Patterns in the models. In conclusion, the results show that the developed models decrease estimation and prediction errors. As a result of comparing the developed model with the existing model using the observed data, the equality coefficients of the developed model was average 88% and the existing model was average 68%. Thus, the developed model was improved minimum 17% and maximum 23% rather then existing model .

• Journal of Integrative Natural Science
• /
• v.14 no.4
• /
• pp.183-188
• /
• 2021

Collaborative filtering is one of the commonly used methods in the web recommendation system. Numerous researches on the collaborative filtering proposed the numbers of measures for enhancing the accuracy. This study suggests the movie recommendation system applied with Word2Vec and ensemble convolutional neural networks. First, user sentences and movie sentences are made from the user, movie, and rating information. Then, the user sentences and movie sentences are input into Word2Vec to figure out the user vector and movie vector. The user vector is input on the user convolutional model while the movie vector is input on the movie convolutional model. These user and movie convolutional models are connected to the fully-connected neural network model. Ultimately, the output layer of the fully-connected neural network model outputs the forecasts for user, movie, and rating. The test result showed that the system proposed in this study showed higher accuracy than the conventional cooperative filtering system and Word2Vec and deep neural network-based system suggested in the similar researches. The Word2Vec and deep neural network-based recommendation system is expected to help in enhancing the satisfaction while considering about the characteristics of users.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.51-56
• /
• 2006

Biases embedded in numerical weather precipitation forecasts by the RDAPS model was determined, quantified and corrected. The ultimate objective is to eventually enhance the reliability of reservoir operation by Korean Water Resources Corporation (KOWACO), which is based on precipitation-driven forecasts of stream flow. Statistical post-processing, so called MOS (Model Output Statistics) was applied to RDAPS to improve their performance. The Artificial Neural Nwetwork (ANN) model was applied for 4 cases of 'Probability of Precipitation (PoP) for wet and dry season' and 'Quantitative Precipitation Forecasts (QPF) for wet and dry season'. The reduction on the large systematic bias was especially remarkable. The performance of both networks may be improved by retraining, probably every month. In addition, it is expected that performance of the networks will improve once atmospheric profile data are incorporated in the analysis. The key to the optimal performance of ANN is to have a large data set relevant to the predictand variable. The more complex the process to be modeled by the ANN, the larger the data set needs to be.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.64-71
• /
• 2002

This research developed construction cost forecasting model using Building Construction Cost Index, time series analysis and Artificial Neural Networks. By this model, we could calculate the forecasted values of construction cost precisely and efficiently. And we also could find out that the standard deviation of forecasted values is 0.375 and it is a very exact result, so the standard deviation is just 0.33 percent of 112.28, the average of Building Construction Cost Index. And it show more exact forecasting result in comparison with Time Series Analysis.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.7-11
• /
• 2022

Object detection technology is one of the main research topics in the field of computer vision and has established itself as an essential base technology for implementing various vision systems. Recent DNN (Deep Neural Networks)-based algorithms achieve much higher recognition accuracy than traditional algorithms. However, it is well-known that the DNN model inference operation requires a relatively high computational power. In this paper, we analyze the inference time complexity of the state-of-the-art object detection architecture Yolov7 in various environments. Specifically, we compare and analyze the time complexity of four types of the Yolov7 model, YOLOv7-tiny, YOLOv7, YOLOv7-X, and YOLOv7-E6 when performing inference operations using CPU and GPU. Furthermore, we analyze the time complexity variation when inferring the same models using the Pytorch framework and the Onnxruntime engine.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.21-26
• /
• 2006

This paper focuses on modeling and predicting differential GPS corrections transmitted by marine radio-beacon systems using artificial neural networks. Various neural network structures with various training algorithms were examined, including Linear, Radial Biases, and Feedforward. Matlab Neural Network toolbox is used for this purpose. Data sets used in building the model are the transmitted pseudorange corrections and broadcast navigation message. Model design is passed through several stages, namely data collection, preprocessing, model building, and finally model validation. It is found that feedforward neural network with automated regularization is the most suitable for our data. In training the neural network, different approaches are used to take advantage of the pseudorange corrections history while taking into account the required time for prediction and storage limitations. Three data structures are considered in training the neural network, namely all round, compound, and average. Of the various data structures examined, it is found that the average data structure is the most suitable. It is shown that the developed model is capable of predicting the differential correction with an accuracy level comparable to that of beacon-transmitted real-time DGPS correction.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.4
• /
• pp.511-523
• /
• 2023

Research on the integration of unmanned aerial vehicles and deep learning for reinforced concrete damage detection is actively underway. Convolutional neural networks have a high impact on the performance of image classification, detection, and segmentation as backbones. The MobileNet, a pre-trained convolutional neural network, is efficient as a backbone for an unmanned aerial vehicle-based damage detection model because it can achieve sufficient accuracy with low computational complexity. Analyzing vanilla convolutional neural networks and MobileNet under various conditions, MobileNet was evaluated to have a verification accuracy 6.0~9.0% higher than vanilla convolutional neural networks with 15.9~22.9% lower computational complexity. MobileNetV2, MobileNetV3Large and MobileNetV3Small showed almost identical maximum verification accuracy, and the optimal conditions for MobileNet's reinforced concrete damage image feature extraction were analyzed to be the optimizer RMSprop, no dropout, and average pooling. The maximum validation accuracy of 75.49% for 7 types of damage detection based on MobilenetV2 derived in this study can be improved by image accumulation and continuous learning.