• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1290-1295
• /
• 2017

Document classification, a task of classifying the category of each document based on text, is one of the fundamental areas for natural language processing. Document classification may be used in various fields such as topic classification and sentiment classification. Neural network models for document classification can be divided into two categories: word-level models and character-level models that treat words and characters as basic units respectively. In this study, we propose a neural network model that combines character-level and word-level models to improve performance of document classification. The proposed model extracts the feature vector of each word by combining information obtained from a word embedding matrix and information encoded by a character-level neural network. Based on feature vectors of words, the model classifies documents with a hierarchical structure wherein recurrent neural networks with attention mechanisms are used for both the word and the sentence levels. Experiments on real life datasets demonstrate effectiveness of our proposed model.

• Journal of Korea Water Resources Association
• /
• v.34 no.6
• /
• pp.701-711
• /
• 2001

Forecasting of water quality variation is not an easy process due to the complicated nature of various water quality factors and their interrelationships. The objective of this study is to test the applicability of neural network models to the forecasting of the water quality at Gongju station in Geum River. This is done by forecasting monthly water qualities such as DO, BOD, and TN, and comparing with those obtained by ARIMA model. The neural network models of this study use BP(Back Propagation) algorithm for training. In order to improve the performance of the training, the models are tested in three different styles ; MANN model which uses the Moment-Adaptive learning rate method, LMNN model which uses the Levenberg-Marquardt method, and MNN model which separates the hidden layers for judgement factors from the hidden layers for water quality data. the results show that the forecasted water qualities are reasonably close to the observed data. And the MNN model shows the best results among the three models tested

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.241-246
• /
• 2020

In this paper, we propose a neural network model to converge the marine electric propulsion system and deep learning algorithm to predict the DC/DC converter output current in the electric propulsion regeneration system and to predict the battery charge during regeneration. In order to experiment with the proposed neural network, the input voltage and current of the PCM were measured and the data set was secured on the prototype PCM board. In addition, in order to improve the learning results in the insufficient data set, the scale of the data set was increased through data fitting and its learning was executed further. After learning, the difference between the data prediction result of the neural network model and the actual measurement data was compared. The proposed neural network model effectively showed the prediction of battery charge according to changes in input voltage and current. In addition, by predicting the characteristic change of the analog circuit constituting the DC/DC converter through a neural network, it is determined that the characteristics of the analog circuit should be considered when designing the regeneration system.

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.39-44
• /
• 2018

The application of deep neural networks to finance has received a great deal of attention from researchers because no assumption about a suitable mathematical model has to be made prior to forecasting and they are capable of extracting useful information from large sets of data, which is required to describe nonlinear input-output relations of financial time series. The paper presents a new deep neural network model where single layered autoencoder and 4 layered neural network are serially coupled for stock price forecasting. The autoencoder extracts deep features, which are fed into multi-layer neural networks to predict the next day's stock closing prices. The proposed deep neural network is progressively learned layer by layer ahead of the final learning of the total network. The proposed model to predict daily close prices of KOrea composite Stock Price Index (KOSPI) is built, and its performance is demonstrated.

• Journal of the Korean Geotechnical Society
• /
• v.19 no.4
• /
• pp.287-298
• /
• 2003

The feasibility of using neural networks to model the complex relationship between piezocone measurements and the undrained shear strength of clays has been investigated. A three layered back propagation neural network model was developed based on actual undrained shear strengths, which were obtained from the isotrpoically and anisotrpoically consolidated triaxial compression test(CIUC and CAUC), and piezocone measurements compiled from various locations around the world. It was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was compared with conventional empirical method, direct correlation method, and theoretical method. It was found that the neural network model is not only capable of inferring a complex relationship between piezocone measurements and the undrained shear strength of clays but also gives a more precise and reliable undrained shear strength than theoretical and empirical approaches. Furthermore, neural network model has a possibility to be a generalized relationship between piezocone measurements and undrained shear strength over the various places and countries, while the present empirical correlations present the site specific relationship.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.11
• /
• pp.71-79
• /
• 2017

In this paper, we implemented the exchange rate forecasting neural network using heterogeneous computing. Exchange rate forecasting requires a large amount of data. We used a neural network that could leverage this data accordingly. Neural networks are largely divided into two processes: learning and verification. Learning took advantage of the CPU. For verification, RTL written in Verilog HDL was run on FPGA. The structure of the neural network has four input neurons, four hidden neurons, and one output neuron. The input neurons used the US $ 1, Japanese 100 Yen, EU 1 Euro, and UK £ 1. The input neurons predicted a Canadian dollar value of $ 1. The order of predicting the exchange rate is input, normalization, fixed-point conversion, neural network forward, floating-point conversion, denormalization, and outputting. As a result of forecasting the exchange rate in November 2016, there was an error amount between 0.9 won and 9.13 won. If we increase the number of neurons by adding data other than the exchange rate, it is expected that more precise exchange rate prediction will be possible.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.10
• /
• pp.935-943
• /
• 2017

CNN (Convolution neural network), which is used for image classification and speech recognition among neural networks learning based on positive data, has been continuously developed to have a high performance structure to date. There are many difficulties to utilize in an embedded system with limited resources. Therefore, we use GPU (General-Purpose Computing on Graphics Processing Units), which is used for general-purpose operation of GPU to solve the problem because we use pre-learned weights but there are still limitations. Since CNN performs simple and iterative operations, the computation speed varies greatly depending on the thread allocation and utilization method in the Single Instruction Multiple Thread (SIMT) based GPGPU. To solve this problem, there is a thread that needs to be relaxed when performing Convolution and Pooling operations with threads. The remaining threads have increased the operation speed by using the method used in the following feature maps and kernel calculations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.311-326
• /
• 2024

The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.65-71
• /
• 2024

This paper proposes a neural network that can reduce the number of parameters while reducing matching errors in occluded regions to increase the accuracy of depth maps in stereo matching. Stereo matching-based object recognition is utilized in many fields to more accurately recognize situations using images. When there are many objects in a complex image, an occluded area is generated due to overlap between objects and occlusion by background, thereby lowering the accuracy of the depth map. To solve this problem, existing research methods that create context information and combine it with the cost volume or RoIselect in the occluded area increase the complexity of neural networks, making it difficult to learn and expensive to implement. In this paper, we create a depthwise seperable neural network that enhances regional feature extraction before cost volume generation, reducing the number of parameters and proposing a neural network that is robust to occlusion errors. Compared to PSMNet, the proposed neural network reduced the number of parameters by 30%, improving 5.3% in color error and 3.6% in test loss.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.6
• /
• pp.1424-1432
• /
• 2009

For the efficient management of hospital sickbeds, it is important to predict the length of stay (LoS) of appendicitis patients. This study analyzed the patient data to find factors that show high positive correlation with LoS, build LoS prediction models using neural network and decision tree models, and compare their performance. In order to increase the prediction accuracy, we applied the ensemble techniques such as bagging and boosting. Experimental results show that decision tree model which was built with less number of variables shows prediction accuracy almost equal to that of neural network model, and that bagging is better than boosting. In conclusion, since the decision tree model which provides better explanation than neural network model can well predict the LoS of appendicitis patients and can also be used to select the input variables, it is recommended that hospitals make use of the decision tree techniques more actively.