• Current Optics and Photonics
• /
• v.7 no.5
• /
• pp.511-517
• /
• 2023

Pipelines play an important role in urban water supply and drainage, oil and gas transmission, etc. This paper presents a technique for pattern recognition of fiber optic vibration signals collected by a distributed vibration sensing (DVS) system using a deep learning residual network (ResNet). The optical fiber is laid on the pipeline, and the signal is collected by the DVS system and converted into a 64 × 64 single-channel grayscale image. The grayscale image is input into the ResNet to extract features, and finally the K-nearest-neighbors (KNN) algorithm is used to achieve the classification and recognition of pipeline damage.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.42-50
• /
• 2010

It is necessary to implementation of system contain intelligent decision making algorithm considering marine feature because existing vessel USN system is simply monitoring obtained data from vessel USN. In this paper, we designed inference system using case based reasoning method and implemented knowledge base that case for fire and demage of digital marine vessel. We used K-Nearest Neighbor algorithm for recommend best similar case and input 3.000 EA by case for fire and demage context case base. As a result, we obtained about 82.5% average accuracy for fire case and about 80.1% average accuracy for demage case. We implemented digital marine vessel monitoring system using inference result.

• Steel and Composite Structures
• /
• v.42 no.6
• /
• pp.733-745
• /
• 2022

This study proposed a robust artificial intelligence (AI) model based on the social behaviour of the imperialist competitive algorithm (ICA) and artificial neural network (ANN) for modelling the deflection of reinforced concrete beams, abbreviated as ICA-ANN model. Accordingly, the ICA was used to adjust and optimize the parameters of an ANN model (i.e., weights and biases) aiming to improve the accuracy of the ANN model in modelling the deflection reinforced concrete beams. A total of 120 experimental datasets of reinforced concrete beams were employed for this aim. Therein, applied load, tensile reinforcement strength and the reinforcement percentage were used to simulate the deflection of reinforced concrete beams. Besides, five other AI models, such as ANN, SVM (support vector machine), GLMNET (lasso and elastic-net regularized generalized linear models), CART (classification and regression tree) and KNN (k-nearest neighbours), were also used for the comprehensive assessment of the proposed model (i.e., ICA-ANN). The comparison of the derived results with the experimental findings demonstrates that among the developed models the ICA-ANN model is that can approximate the reinforced concrete beams deflection in a more reliable and robust manner.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.355-366
• /
• 2023

Although machine learning (ML) techniques have been widely used in various fields of engineering practice, their applications in the field of wind engineering are still at the initial stage. In order to evaluate the feasibility of machine learning algorithms for prediction of wind loads on high-rise buildings, this study took the exposure category type, wind direction and the height of local wind force as the input features and adopted four different machine learning algorithms including k-nearest neighbor (KNN), support vector machine (SVM), gradient boosting regression tree (GBRT) and extreme gradient (XG) boosting to predict wind force coefficients of CAARC standard tall building model. All the hyper-parameters of four ML algorithms are optimized by tree-structured Parzen estimator (TPE). The result shows that mean drag force coefficients and RMS lift force coefficients can be well predicted by the GBRT algorithm model while the RMS drag force coefficients can be forecasted preferably by the XG boosting algorithm model. The proposed machine learning based algorithms for wind loads prediction can be an alternative of traditional wind tunnel tests and computational fluid dynamic simulations.

• Geomechanics and Engineering
• /
• v.38 no.5
• /
• pp.507-515
• /
• 2024

An accurate estimation of the geotechnical parameters in front of tunnel faces is crucial for the safe construction of underground infrastructure using tunnel boring machines (TBMs). This study was aimed at developing a data-driven model for predicting the rock quality designation (RQD) of the ground formation ahead of tunnel faces. The dataset used for the machine learning (ML) model comprises seven geological and mechanical features and 564 RQD values, obtained from an earth pressure balance (EPB) shield TBM tunneling project beneath the Han River in the Republic of Korea. Four ML algorithms were employed in developing the RQD prediction model: k-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), and extreme gradient boosting (XGB). The grid search and five-fold cross-validation techniques were applied to optimize the prediction performance of the developed model by identifying the optimal hyperparameter combinations. The prediction results revealed that the RF algorithm-based model exhibited superior performance, achieving a root mean square error of 7.38% and coefficient of determination of 0.81. In addition, the Shapley additive explanations (SHAP) approach was adopted to determine the most relevant features, thereby enhancing the interpretability and reliability of the developed model with the RF algorithm. It was concluded that the developed model can successfully predict the RQD of the ground formation ahead of tunnel faces, contributing to safe and efficient tunnel excavation.

• Journal of Korea Water Resources Association
• /
• v.52 no.2
• /
• pp.141-148
• /
• 2019

When simulating the daily rainfall amount by existing Markov Chain model, it is general to simulate the rainfall occurrence and to estimate the rainfall amount randomly from the distribution which is similar to the daily rainfall distribution characteristic using Monte Carlo simulation. At this time, there is a limitation that the characteristics of rainfall intensity and distribution by time according to the rainfall duration are not reflected in the results. In this study, 1-day, 2-day, 3-day, 4-day rainfall event are classified, and the rainfall amount is estimated by rainfall duration. In other words, the distributions of the total amount of rainfall event by the duration are set using the Kernel Density Estimation (KDE), the daily rainfall in each day are estimated from the distribution of each duration. Total rainfall amount determined for each event are divided into each daily rainfall considering the type of daily distribution of the rainfall event which has most similar rainfall amount of the observed rainfall using the k-Nearest Neighbor algorithm (KNN). This study is to develop the limitation of the existing rainfall estimation method, and it is expected that this results can use for the future rainfall estimation and as the primary data in water resource design.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.371-376
• /
• 2003

In this paper, we proposes a method for recognizing the facial expressions using ICA(Independent Component Analysis)-factorial representation method. Facial expression recognition consists of two stages. First, a method of Feature extraction transforms the high dimensional face space into a low dimensional feature space using PCA(Principal Component Analysis). And then, the feature vectors are extracted by using ICA-factorial representation method. The second recognition stage is performed by using the Euclidean distance measure based KNN(K-Nearest Neighbor) algorithm. We constructed the facial expression database for six basic expressions(happiness, sadness, angry, surprise, fear, dislike) and obtained a better performance than previous works.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.162-165
• /
• 2017

The proposed paper extracts the region of interest from the x-lay input image and compares it with the reference image. The x-ray image has the same shape, but the size, direction and position of the object are photographed differently. In this way, we measure the erection difference of darkness and darkness using the similarity measurement method for the same object. Distance measurement also calculates the distance between two points with vector coordinates (x, y, z) of x-lay data. Experimental results show that the proposed method improves the accuracy of ROI extraction and the reference image matching time is more efficient than the conventional method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.361-361
• /
• 2019

기존의 Markov Chain 모형으로 일강우량 모의시에 강우의 발생여부를 모의하고 강우일의 강우량은 Monte Carlo 시뮬레이션을 통해 일강우 분포 특성에 맞는 분포형에서 랜덤으로 강우량을 추정하는 것이 일반적이다. 이때 강우 지속기간에 따른 강도 및 강우의 시간별 분포 등의 강우 사상의 특성을 반영할 수 없다는 한계가 있다. 본 연구에서는 이를 개선하기 위해 강우 사상을 지속기간에 따라 강우량을 추정하였다. 즉 강우 사상의 강우 지속일별로 총강우량의 분포형을 비매개변수 추정이 가능한 핵밀도추정(Kernel Density Estimation, KDE)를 적용하여 각각 추정하고, 강우가 지속될 경우에 지속일별로 해당하는 분포형에서 강우량을 구하였다. 각 강우사상에 대해 추정된 총 강우량은 k-최근접 이웃 알고리즘(k-Nearest Neighbor algorithm, KNN)을 통해 관측 강우자료에서 가장 유사한 강우량을 가지는 강우사상의 강우량 일분포 형태에 따라 각 일강우량으로 분배하였다. 본 연구는 기존의 강우량 추정 방법의 한계점을 개선하고자 하였으며, 연구 결과는 미래 강우에 대한 예측에도 활용될 수 있으며 수자원 설계에 있어서 기초자료로 활용될 수 있을 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1708-1727
• /
• 2021

In the advent of the twenty-first century, human beings began to closely interact with technology. Today, technology is developing, and as a result, the world wide web (www) has a very important place on the Internet and the significant task is fulfilled by Web services. A lot of Web services are available on the Internet and, therefore, it is difficult to find matching Web services among the available Web services. The recommendation systems can help in fixing this problem. In this paper, our observation was based on the recommended method such as the collaborative filtering (CF) technique which faces some failure from the data sparsity and the cold-start problems. To overcome these problems, we first applied an ontology-based clustering and then the k-nearest neighbor (KNN) algorithm for each separate cluster group that effectively increased the data density using the past user interests. Then, user ratings were predicted based on the model-based approach, such as singular value decomposition (SVD) and the predictions used for the recommendation. The evaluation results showed that our proposed approach has a less prediction error rate with high accuracy after analyzing the existing recommendation methods.