• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.217-223
• /
• 2009

Vocabulary recognition system of Mobile terminal is executed statistical method for vocabulary recognition and used statistical grammar recognition system using N-gram. If limit arithmetic processing capacity in memory of vocabulary to grow then vocabulary recognition algorithm complicated and need a large scale search space and many processing time on account of impossible to process. This study suggest vocabulary recognition optimize using MLHF System. MLHF separate acoustic search and lexical search system using FLaVoR. Acoustic search feature vector of speech signal extract using HMM, lexical search recognition execution using Levenshtein distance algorithm. System performance as a result of represent vocabulary dependence recognition rate of 98.63%, vocabulary independence recognition rate of 97.91%, represent recognition speed of 1.61 second.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.667-669
• /
• 2021

본 논문에서는 벡터 기반 데이터 증강 기법(Data augmentation)을 제안하여 학습 데이터를 구축한 뒤, 이를 합성곱 신경망(Convolutional Neural Networks, CNN)으로 실제 균열과 가까운 패턴을 표현할 수 있는 프레임워크를 제안한다. 건축물의 균열은 인명 피해를 가져오는 건물 붕괴와 낙하 사고를 비롯한 큰 사고의 원인이다. 이를 인공지능으로 해결하기 위해서는 대량의 데이터 확보가 필수적이다. 하지만, 실제 균열 이미지는 복잡한 패턴을 가지고 있을 뿐만 아니라, 위험한 상황에 노출되기 때문에 대량의 데이터를 확보하기 어렵다. 이러한 데이터베이스 구축의 문제점은 인위적으로 특정 부분에 변형을 주어 데이터양을 늘리는 탄성왜곡(Elastic distortion) 기법으로 해결할 수 있지만, 본 논문에서는 이보다 향상된 균열 패턴 결과를 CNN을 활용하여 보여준다. 탄성왜곡 기법보다 CNN을 이용했을 때, 실제 균열 패턴과 유사하게 추출된 결과를 얻을 수 있었고, 일반적으로 사용되는 픽셀 기반 데이터가 아닌 벡터 기반으로 데이터 증강을 설계함으로써 균열의 변화량 측면에서 우수함을 보였다. 본 논문에서는 적은 개수의 균열 데이터를 입력으로 사용했음에도 불구하고 균열의 방향 및 패턴을 다양하게 생성하여 쉽게 균열 데이터베이스를 구축할 수 있었다. 이는 장기적으로 구조물의 안정성 평가에 이바지하여 안전사고에 대한 불안감에서 벗어나 더욱 안전하고 쾌적한 주거 환경을 조성할 것으로 기대된다.

• Steel and Composite Structures
• /
• v.46 no.6
• /
• pp.731-744
• /
• 2023

Vehicle load information is an important role in operating and ensuring the structural health of cable-stayed bridges. In this regard, an efficient and economic method is proposed for vehicle load detection based on the observed cable tension and vehicle position using a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), a robust program for modeling and considering both geometric and material nonlinearities of bridge structures subjected to vehicle load with low computational costs. With the superiority of GNN, the proposed model is demonstrated to precisely capture complex nonlinear correlations between the input features and vehicle load in the output. Four popular machine learning methods including artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machines (SVM) are refereed in a comparison. A case study of a cable-stayed bridge with the typical truck is considered to evaluate the model's performance. The results demonstrate that the GNN-based model provides high accuracy and efficiency in prediction with satisfactory correlation coefficients, efficient determination values, and very small errors; and is a novel approach for vehicle load detection with the input data of the existing monitoring system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.13-16
• /
• 2022

LSTM과 같은 딥러닝 기법을 이용해 언어모델을 얻는 과정에서 일종의 부산물로 학습 대상인 말뭉치를 구성하는 어휘의 단어벡터를 얻을 수 있다. 단어벡터의 차원을 2차원으로 감소시킨 후 이를 평면에 도시하면 대상 문장/문서의 핵심 어휘 사이의 상대적인 거리와 각도 등을 직관적으로 확인할 수 있다. 본 연구에서는 기형도의 시(詩)을 중심으로 특정 작품을 선정한 후 시를 구성하는 핵심 어휘들의 차원 감소된 단어벡터를 2D 평면에 도시하여, 단어벡터를 얻기 위한 텍스트 전처리 방식에 따라 그 거리/각도가 달라지는 양상을 분석해 보았다. 어휘 사이의 거리에 의해 군집/분류의 결과가 달라질 수 있고, 각도에 의해 유사도/유추 연산의 결과가 달라질 수 있으므로, 평면상에서 핵심 어휘들의 상대적인 거리/각도의 직관적 확인을 통해 군집/분류작업과 유사도 추천/유추 등의 작업 결과의 양상 변화를 확인할 수 있었다. 이상의 결과를 통해, 영화 추천/리뷰나 문학작품과 같이 단어 하나하나의 배치에 따라 그 분위기와 정동이 달라지는 분야의 경우 텍스트 전처리에 따른 거리/각도 변화를 미리 직관적으로 확인한다면 분류/유사도 추천과 같은 작업을 좀 더 정밀하게 수행할 수 있을 것으로 판단된다.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.300-305
• /
• 2023

Audience reactions in response to remote virtual performances must be compressed before being transmitted to the server. The server, which aggregates these data for group insights, requires a distribution code for the transfer. Recently, distributed learning algorithms such as federated learning have gained attention as alternatives that satisfy both the information security and efficiency requirements. In distributed learning, no individual user has access to complete information, and the objective is to achieve a learning effect similar to that achieved with the entire information. It is therefore important to distribute interdependent information among users and subsequently aggregate this information following training. In this paper, we present a new extension technique for minimal code that allows a new minimal code with a different length and Hamming weight to be generated through the product of any vector and a given minimal code. Thus, the proposed technique can generate minimal codes with previously unknown parameters. We also present a scenario wherein these combined methods can be applied.

• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.2
• /
• pp.138-142
• /
• 2007

This paper presents an algorithm which extends the rapidly-exploring random tree (RRT) framework to deal with change of the task environments. This algorithm called the Retrieval RRT Strategy (RRS) combines a support vector machine (SVM) and RRT and plans the robot motion in the presence of the change of the surrounding environment. This algorithm consists of two levels. At the first level, the SVM is built and selects a proper path from the bank of RRTs for a given environment. At the second level, a real path is planned by the RRT planners for the: given environment. The suggested method is applied to the control of $KUKA^{TM}$, a commercial 6 DOF robot manipulator, and its feasibility and efficiency are demonstrated via the cosimulatation of $MatLab^{TM}\;and\;RecurDyn^{TM}$.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.1
• /
• pp.45-55
• /
• 1993

In this paper, a two-stage block matching algorithm (BMA), which can reduce greatly the computational complexity of the conventional BMAs, is proposed, in which the onedimensional distortion measure based on the integral projection is introduced to determine the candidate motion vectors and then among them a final motion vector is detected based on the conventional two-dimensional distortion measure. Due to the one-dimensional calculation of a distortion measure, the proposed algorithm can reduce the computational complexity of the conventional BMA (full search method with a 16$\times$16 block) by a factor of 4, with its performance comparable to those of the conventional ones. Simulation results based on the original and noisy image sequences are shown. Also the simulation of the proposed method combined with the MPEG (Moving Picture Experts Group) SM3 (Simulation Model Three) is presented. Computer simulation shows that the proposed algorithm is fast with its performance comparable to those of the conventional ones.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.313-320
• /
• 1999

In this paper, a translation, rotation and scale invariant system for the classification of closed 2D images using the bispectrum of a contour sequence and the weighted fuzzy mean method is derived and compared with the classification process using one of the competitive neural algorithm, called a LVQ(Learning Vector Quantization). The bispectrun based on third order cumulants is applied to the contour sequences of the images to extract fifteen feature vectors for each planar image. These bispectral feature vectors, which are invariant to shape translation, rotation and scale transformation, can be used to represent two-dimensional planar images and are fed into an classifier using weighted fuzzy mean method. The experimental processes with eight different shapes of aircraft images are presented to illustrate the high performance of the proposed classifier.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.4
• /
• pp.277-282
• /
• 2015

Braincomputer interface (BCI) technology is making advances in the field of humancomputer interaction (HCI). To improve the BCI technology, we study the changes in the electroencephalogram (EEG) signals for six levels of grip strength: 10%, 20%, 40%, 50%, 70%, and 80% of the maximum voluntary contraction (MVC). The measured EEG data are categorized into three classes: Weak, Medium, and Strong. Features are then extracted using power spectrum analysis and multiclass-common spatial pattern (multiclass-CSP). Feature datasets are classified using a support vector machine (SVM). The accuracy rate is higher for the Strong class than the other classes.