• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.513-520
• /
• 2020

Recently, the development of a vision inspection system using machine learning has become more active. This study seeks to develop a defect inspection model using machine learning. Defect detection problems for images correspond to classification problems, which are the method of supervised learning in machine learning. In this study, defect detection models are developed based on algorithms that automatically extract features and algorithms that do not extract features. One-dimensional CNN and two-dimensional CNN are used as algorithms for automatic extraction of features, and MLP and SVM are used as algorithms for non-extracting features. A defect detection model is developed based on four models and their accuracy and AUC compare based on AUC. Although image classification is common in the development of models using CNN, high accuracy and AUC is achieved when developing SVM models by converting pixels from images into RGB values in this study.

• Journal of Convergence for Information Technology
• /
• v.10 no.6
• /
• pp.41-48
• /
• 2020

The sensor nodes in underwater IoT networks have practical limitations in power supply. Thus, the reduction of power consumption is one of the most important issues in underwater environments. In this regard, AMC(Adaptive Modulation and Coding) techniques are used by using the relation between SNR and BER. However, according to our hands-on experience, we observed that the relation between SNR and BER is not that tight in underwater environments. Therefore, we propose a deep learning based MLP classification model to reflect multiple underwater channel parameters at the same time. It correctly predicts BER with a high accuracy of 85.2%. The proposed model can choose the best parameters to have the highest throughput. Simulation results show that the throughput can be enhanced by 4.4 times higher than the conventionally measured results.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1297-1307
• /
• 2013

Several multi-hop applications developed for vehicular ad hoc networks use broadcast as a means to either discover nearby neighbors or disseminate useful traffic information to othet vehicles located within a certain geographical area. However, the conventional broadcast mechanism may lead to the so-called broadcast storm problem, a scenario in which there is a high level of contention and collision at the link layer due to an excessive number of broadcast packets. To solve broadcast storm problem, we propose an RPB-MACn-based LV-CAST that is a vehicular broadcast algorithm for disseminating safety-related emergency message. The proposed LV-CAST identifies the last node within transmission range by computing the distance extending on 1 hop from the sending node of an emergency message to the next node of receiving node of the emergency message, and the last node only re-broadcasts the emergency message. The performance of LV-CAST is evaluated through simulation and compared with other message dissemination algorithms.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.1
• /
• pp.40-48
• /
• 2007

This paper presents a novel texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields in multiscale Bayesian framework. Multiscale wavelet coefficients are used as input for the neural networks. The output of the neural network is modeled as a posterior probability. Texture classification at each scale is performed by the posterior probabilities from MLP networks and MAP (maximum a posterior) classification. Then, in order to obtain the more improved segmentation result at the finest scale, our proposed method fuses the multiscale MAP classifications sequentially from coarse to fine scales. This process is done by computing the MAP classification given the classification at one scale and a priori knowledge regarding contextual information which is extracted from the adjacent coarser scale classification. In this fusion process, the MRF (Markov random field) prior distribution and Gibbs sampler are used, where the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier. The proposed segmentation method shows better performance than texture segmentation using the HMT (Hidden Markov trees) model and HMTseg.

• Structural Monitoring and Maintenance
• /
• v.1 no.3
• /
• pp.249-271
• /
• 2014

This paper presents a unique study of Structural Health Monitoring (SHM) for the maintenance decision making about a real life movable bridge. The mechanical components of movable bridges are maintained on a scheduled basis. However, it is desired to have a condition-based maintenance by taking advantage of SHM. The main objective is to track the operation of a gearbox and a rack-pinion/open gear assembly, which are critical parts of bascule type movable bridges. Maintenance needs that may lead to major damage to these components needs to be identified and diagnosed timely since an early detection of faults may help avoid unexpected bridge closures or costly repairs. The fault prediction of the gearbox and rack-pinion/open gear is carried out using two types of Artificial Neural Networks (ANNs): 1) Multi-Layer Perceptron Neural Networks (MLP-NNs) and 2) Fuzzy Neural Networks (FNNs). Monitoring data is collected during regular opening and closing of the bridge as well as during artificially induced reversible damage conditions. Several statistical parameters are extracted from the time-domain vibration signals as characteristic features to be fed to the ANNs for constructing the MLP-NNs and FNNs independently. The required training and testing sets are obtained by processing the acceleration data for both damaged and undamaged condition of the aforementioned mechanical components. The performances of the developed ANNs are first evaluated using unseen test sets. Second, the selected networks are used for long-term condition evaluation of the rack-pinion/open gear of the movable bridge. It is shown that the vibration monitoring data with selected statistical parameters and particular network architectures give successful results to predict the undamaged and damaged condition of the bridge. It is also observed that the MLP-NNs performed better than the FNNs in the presented case. The successful results indicate that ANNs are promising tools for maintenance monitoring of movable bridge components and it is also shown that the ANN results can be employed in simple approach for day-to-day operation and maintenance of movable bridges.

• Advances in materials Research
• /
• v.6 no.2
• /
• pp.169-184
• /
• 2017

Electro-Discharge machining (EDM) is a thermal process comprising a complex metal removal mechanism. This method works by forming of a plasma channel between the tool and the workpiece electrodes leading to the melting and evaporation of the material to be removed. EDM is considered especially suitable for machining complex contours with high accuracy, as well as for materials that are not amenable to conventional removal methods. However, several phenomena can arise and adversely affect the surface integrity of EDMed workpieces. These have to be taken into account and studied in order to optimize the process. Recently, artificial neural networks (ANN) have emerged as a novel modeling technique that can provide reliable results and readily, be integrated into several technological areas. In this paper, we use an ANN, namely, the multi-layer perceptron and the back propagation network (BPNN) to predict the mean surface roughness of electro-discharge machined surfaces. The comparison of the derived results with experimental findings demonstrates the promising potential of using back propagation neural networks (BPNNs) for getting a reliable and robust approximation of the Surface Roughness of Electro-discharge Machined Components.

• Advances in Computational Design
• /
• v.3 no.3
• /
• pp.269-288
• /
• 2018

180 different 2D numerical analyses have been carried out to estimate the factor of safety (FOS) for rooted slopes. Four different types of vegetated coverage and a variety of slope geometry considering three types of soil have been evaluated in this study. The highly influenced parameters on the slope's FOS are determined. They have been chosen as the input parameters for developing a new practical relationship to estimate the FOS with an emphasis on the roots effects. The dependency of sliding mode and shape considering the soil and roots-type has been evaluated by using the numerical finite element model. It is observed that the inclination and height of the slope and the coverage type are the most important effective factors in FOS. While the soil strength parameters and its physical properties would be considered as the second major group that affects the FOS. Achieved results from the developed relationship have shown the acceptable estimation for the roots slope. The extracted R square from the proposed relationship considering nonlinear estimation has been achieved up to 0.85. As a further cross check, the achieved R square from a multi-layer neural network has also been observed to be around 0.92. The numerical verification considering different scenarios has been done in the current evaluation.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.5-13
• /
• 1992

Taking devantage of the property that Korean digit is a mono-syllable word, we proposed a spoken Korean-digit recognition scheme using the multi-layer perceptron. The spoken Korean-digit is divided into three segments (initial sound, medial vowel, and final consonant) based on the voice starting / ending points and a peak point in the middle of vowel sound. The feature vectors such as cepstrum, reflection coefficients, ${\Delta}$cepstrum and ${\Delta}$energy are extracted from each segment. It has been shown that cepstrum, as an input vector to the neural network, gives higher recognition rate than reflection coefficients. Regression coefficients of cepstrum did not affect as much as we expected on the recognition rate. That is because, it is believed, we extracted features from the selected stationary segments of the input speech signal. With 150 ceptral coefficients obtained from each spoken digit, we achieved correct recognition rate of 97.8%.

• Journal of Advanced Navigation Technology
• /
• v.22 no.5
• /
• pp.472-477
• /
• 2018

In this paper, we develop interactive content services for preventing depression of users through an intelligent Internet of Things(IoT) mirror system. For interactive content services, an IoT mirror device measures attention and meditation data from an EEG headset device and also measures facial expression data such as "sad", "angery", "disgust", "neutral", " happy", and "surprise" classified by a multi-layer perceptron algorithm through an webcam. Then, it sends the measured data to an oneM2M-compliant IoT server. Based on the collected data in the IoT server, a machine learning model is built to classify three levels of depression (RED, YELLOW, and GREEN) given by a proposed merge labeling method. It was verified that the k-nearest neighbor (k-NN) model could achieve about 93% of accuracy by experimental results. In addition, according to the classified level, a social network service agent sent a corresponding alert message to the family, friends and social workers. Thus, we were able to provide an interactive content service between users and caregivers.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.137-148
• /
• 2017

Researches on the Artificial Intelligence has been explosively activated in various fields since the advent of AlphaGo. Particularly, researchers on the application of multi-layer neural network such as deep learning, and various machine learning algorithms are being focused actively. In this paper, we described a development of an artificial intelligence Janggi game based on reinforcement learning algorithm and MCTS (Monte Carlo Tree Search) algorithm with accumulated game data. The previous artificial intelligence games are mostly developed based on mini-max algorithm, which depends only on the results of the tree search algorithms. They cannot use of the real data from the games experts, nor cannot enhance the performance by learning. In this paper, we suggest our approach to overcome those limitations as follows. First, we collects Janggi expert's game data, which can reflect abundant real game results. Second, we create a graph structure by using the game data, which can remove redundant movement. And third, we apply the reinforcement learning algorithm and MCTS algorithm to select the best next move. In addition, the learned graph is stored by object serialization method to provide continuity of the game. The experiment of this study is done with two different types as follows. First, our system is confronted with other AI based system that is currently being served on the internet. Second, our system confronted with some Janggi experts who have winning records of more than 50%. Experimental results show that the rate of our system is significantly higher.