• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.93-102
• /
• 2023

Data processing through the cloud causes many problems, such as latency and increased communication costs in the communication process. Therefore, many researchers study edge computing in the IoT, and autonomous driving is a representative application. In indoor self-driving, unlike outdoor, GPS and traffic information cannot be used, so the surrounding environment must be recognized using sensors. An efficient autonomous driving system is required because it is a mobile environment with resource constraints. This paper proposes a machine-learning method using neural networks for autonomous driving in an indoor environment. The neural network model predicts the most appropriate driving command for the current location based on the distance data measured by the LiDAR sensor. We designed six learning models to evaluate according to the number of input data of the proposed neural networks. In addition, we made an autonomous vehicle based on Raspberry Pi for driving and learning and an indoor driving track produced for collecting data and evaluation. Finally, we compared six neural network models in terms of accuracy, response time, and battery consumption, and the effect of the number of input data on performance was confirmed.

• Journal of Power Electronics
• /
• v.5 no.2
• /
• pp.129-141
• /
• 2005

A high-performance robust hybrid speed controller for a permanent-magnet synchronous motor (PMSM) drive with an on-line trained neural-network model-following controller (NNMFC) is proposed. The robust hybrid controller is a two-degrees-of-freedom (2DOF) integral plus proportional & rate feedback (I-PD) with neural-network model-following (NNMF) speed controller (2DOF I-PD NNMFC). The robust controller combines the merits of the 2DOF I-PD controller and the NNMF controller to regulate the speed of a PMSM drive. First, a systematic mathematical procedure is derived to calculate the parameters of the synchronous d-q axes PI current controllers and the 2DOF I-PD speed controller according to the required specifications for the PMSM drive system. Then, the resulting closed loop transfer function of the PMSM drive system including the current control loop is used as the reference model. In addition to the 200F I-PD controller, a neural-network model-following controller whose weights are trained on-line is designed to realize high dynamic performance in disturbance rejection and tracking characteristics. According to the model-following error between the outputs of the reference model and the PMSM drive system, the NNMFC generates an adaptive control signal which is added to the 2DOF I-PD speed controller output to attain robust model-following characteristics under different operating conditions regardless of parameter variations and load disturbances. A computer simulation is developed to demonstrate the effectiveness of the proposed 200F I-PD NNMF controller. The results confirm that the proposed 2DOF I-PO NNMF speed controller produces rapid, robust performance and accurate response to the reference model regardless of load disturbances or PMSM parameter variations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.12C
• /
• pp.1250-1257
• /
• 2003

Generally images are classified into two regions: edge and flat region. While low frequency components are popular in the flat region, high frequency components are quite important in the edge region. Therefore, deinterlacing algorithm that considers the characteristic of each region can be more efficient. In this paper, an image is divided into edge region and flat region by the local variance. And then, for each region, frequency modularized neural network is assigned. Using this structure, each modularized neural network can learn only its region intensively and avoid the complexity of learning caused by the data of different region. Using the local AC data for the input of neural network can prevent the degradation of the performance of teaming due to the average intensity values of image that disturbs the effective learning. The proposed method shows the improved performance compared with previous algorithms in the simulation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.2
• /
• pp.88-95
• /
• 1996

It is inevitable for local systems to have deviations which represent interactions and modeling errors originated from the decomposition process of a large scale system. This paper presents a decentralized control scheme for interconnected systems using local linear models and a neuro-coordinator. In the proposed method, the local system is composed of a linear model and unknown deviations caused by linearizing the subsystems around operating points or by estimating parameters of the subsystems. Because the local system has unmeasurable deviations we define a local reference model which consists of a local linear model and a neural network to estimate the deviations indirectly. The reference model is reformed into a linear model which has no deviations through a transformation of input variables and we obtain an optimum feedback control law which minimizes a local performance index. Finally, we derive a decentralized feedback control law which consists of local linear states and neural network outputs. In the decentralized control, the neuro-coordinator generates a corrective control signal to cancel the effect of deviations through backpropagation learning with the errors obtained from the differences of the local system outputs and reference model outputs. Also, the stability of local system is proved by the degree of learning of the neural network under an assumption on a neural network learning index. It is shown by computer simulations that the proposed control scheme can be applied successfully to the control of a biased two-link planar robot manipulator.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.3
• /
• pp.252-262
• /
• 2020

In Remote Sensing, a machine learning based SVM model is typically utilized for land cover classification. And study using neural network models is also being carried out continuously. But study using high-resolution imagery of KOMPSAT is insufficient. Therefore, the purpose of this study is to assess the accuracy of land cover classification by neural network models using high-resolution KOMPSAT-3 satellite imagery. After acquiring satellite imagery of coastal areas near Gyeongju City, training data were produced. And land cover was classified with the SVM, ANN and DNN models for the three items of water, vegetation and land. Then, the accuracy of the classification results was quantitatively assessed through error matrix: the result using DNN model showed the best with 92.0% accuracy. It is necessary to supplement the training data through future multi-temporal satellite imagery, and to carry out classifications for various items.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.273-280
• /
• 2020

Automatic Static Analysis Tools help developers to quickly find potential defects in source code with less effort. However, the tools reports a large number of false positive warnings which do not have to fix. In our study, we proposed an artificial neural network-based warning classification method using topic models of source code blocks. We collect revisions for fixing bugs from software change management (SCM) system and extract code blocks modified by developers. In deep learning stage, topic distribution values of the code blocks and the binary data that present the warning removal in the blocks are used as input and target data in an simple artificial neural network, respectively. In our experimental results, our warning classification model based on neural network shows very high performance to predict label of warnings such as true or false positive.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.125-133
• /
• 2014

This paper develops a bankruptcy prediction model on an Artificial Neural Network for hotel management. A bankruptcy prediction model has a specific feature to predict a bankruptcy of the whole hotel business after evaluate bankruptcy possibility on the basis of business performance data of each branch. here are many traditional statistical models for bankruptcy prediction such as Multivariate Discriminant Analysis or Logit Analysis. However, we chose Artificial Neural Network because the method has accuracy rates of prediction better than those of other methods. We first selected 100 good enterprises and 100 bankrupt enterprises as experimental data and set up a bankruptcy prediction model by use of a tool for Artificial Neural Network, NeuroShell. The model and its experiments, which demonstrated high efficiency, can certainly provide great help in decision making in the field of hotel management and in deciding on the bankruptcy or financial solidity of each branch of serviced residence hotel.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.4
• /
• pp.763-773
• /
• 2017

In recent years, personal information leakage and technology leakage accidents are frequently occurring. According to the survey, the most important part of this spill is the 'insider' within the organization, and the leakage of technology by insiders is considered to be an increasingly important issue because it causes huge damage to the organization. In this paper, we try to learn the normal behavior of employees using machine learning to prevent insider threats, and to investigate how to detect abnormal behavior. Experiments on the detection of abnormal behavior by implementing an Autoencoder composed of Recurrent Neural Network suitable for learning time series data among the neural network models were conducted and the validity of this method was verified.

• KIISE Transactions on Computing Practices
• /
• v.24 no.2
• /
• pp.93-98
• /
• 2018

Recommendation systems are used to provide items of interests for users to maximize a company's profit. Matrix factorization is frequently used by recommendation systems, based on an incomplete user-item rating matrix. However, as the number of items and users increase, it becomes difficult to make accurate recommendations due to the sparsity of data. To overcome this drawback, the use of text data related to items was recently suggested for matrix factorization algorithms. Furthermore, a word-level convolutional neural network was shown to be effective in the process of extracting the word-level features from the text data among these kinds of matrix factorization algorithms. However, it involves a large number of parameters to learn in the word-level convolutional neural network. Thus, we propose a matrix factorization algorithm which utilizes a character-level convolutional neural network with which to extract the character-level features from the text data. We also conducted a performance study with real-life datasets to show the effectiveness of the proposed matrix factorization algorithm.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.23 no.1
• /
• pp.109-117
• /
• 2011

It was calculated using empirical formulas for the weight of Tetrapod, which was a representative armor unit in the rubble mound breakwater in Korea. As the formulas were evaluated from a curve-fitting with the result of hydraulic test, the uncertainty of experimental error was included. Therefore, the neural network and M5' model tree were used to minimize the uncertainty and predicted the stability number of armor block. The index of agreement between the predicted and measured stability number was calculated to assess the degree of uncertainty for each model. While the neural network with the highest index of agreement have an excellent prediction capability, a significant disadvantage exists that general designers can not easily handle the method. However, although M5' model tree has a lower prediction capability than the neural network, the model tree is easily used by the designers because it has a good prediction capability compared with the existing empirical formula and can be used to propose the formulas like an empirical formula.