• Computers and Concrete
• /
• v.32 no.3
• /
• pp.327-337
• /
• 2023

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.5
• /
• pp.1077-1088
• /
• 2013

High-dimensional data analysis arises from almost all scientific areas, evolving with development of computing skills, and has encouraged penalized estimations that play important roles in statistical learning. For the past years, various penalized estimations have been developed, and the least absolute shrinkage and selection operator (LASSO) proposed by Tibshirani (1996) has shown outstanding ability, earning the first place on the development of penalized estimation. In this paper, we first introduce a number of recent advances in high-dimensional data analysis using the LASSO. The topics include various statistical problems such as variable selection and grouped or structured variable selection under sparse high-dimensional linear regression models. Several unsupervised learning methods including inverse covariance matrix estimation are presented. In addition, we address further studies on new applications which may establish a guideline on how to use the LASSO for statistical challenges of high-dimensional data analysis.

• Korean Journal of Hydrosciences
• /
• v.4
• /
• pp.1-9
• /
• 1993

It is a major objective for the management and operation of water resources system to forecast streamflows. The applicability of artificial neural network model to hydrologic system is analyzed and the performance is compared by statistical method with observed. Multi-layered perception was used to model rainfall-runoff process at Pyung Chang River Basin in Korea. The neural network model has the function of learning the process which can be trained with the error backpropagation (EBP) algorithm in two phases; (1) learning phase permits to find the best parameters(weight matrix) between input and output. (2) adaptive phase use the EBP algorithm in order to learn from the provided data. The generalization results have been obtained on forecasting the daily and hourly streamflows by assuming them with the structure of ARMA model. The results show validities in applying to hydrologic forecasting system.

• Journal of the Korean School Mathematics Society
• /
• v.3 no.1
• /
• pp.59-67
• /
• 2000

This study has been done to help teach mathematics on the spot of education by providing the history of mathematics and illustrations concerning mathematics, which were rearranged for the level of the second grade students in highschool and intented to interest students in mathematics classes. The contents of teaching, according to each unit (Matrix, Sequence, Limit, Differentiation, Integration, Probability, Statistics) include the life of the representative mathematician, the historical background centered on episodes, questions linked with reality, questions making sensations in history and something for maxim in mathematics. If such contents are properly used, they are expected to be able to stimulate students' curiosity, and to be effective in improving students' learning ability in mathematics by causing them to show their active attitudes toward learning mathematics.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.3
• /
• pp.69-79
• /
• 2017

In this paper, we propose our four-phase life cycle of P2P botnet with corresponding detection methods and the future direction for more effective P2P botnet detection. Our proposals are based on the intensive analysis that compares existing P2P botnet detection schemes in different points of view such as life cycle of P2P botnet, machine learning methods for data mining based detection, composition of data sets, and performance matrix. Our proposed life cycle model composed of linear sequence stages suggests to utilize features in the vulnerable phase rather than the entire life cycle. In addition, we suggest the hybrid detection scheme with data mining based method and our proposed life cycle, and present the improved composition of experimental data sets through analysing the limitations of previous works.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.431-431
• /
• 2000

The modeling of 5-bar linkage robot manipulator dynamics by means of a mathematical and neural architecture is presented. Such a model is applicable to the design of a feedforward controller or adjustment of controller parameters. The inverse model consists of two parts: a mathematical part and a compensation part. In the mathematical part, the subsystems of a 5-bar linkage robot manipulator are constructed by applying Kawato's Feedback-Error-Learning method, and trained by given training data. In the compensation part, MLP backpropagation algorithm is used to compensate the unmodeled dynamics. The forward model is realized from the inverse model using the inverse of inertia matrix and the compensation torque is decoupled in the input torque of the forward model. This scheme can use tile mathematical knowledge of the robot manipulator and analogize the robot characteristics. It is shown that the model is reasonable to be used for design and initial gain tuning of a controller.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.2001-2004
• /
• 2003

비정상 행위의 탐지를 위한 침입탐지 시스템의 성능을 좌우하는 가장 큰 요인들은 패킷의 손실없는 수집과 해당 도메인에 알맞은 분류 기법이라 할 수 있다. 본 논문에서는 기존의 탐지엔진에 적용된 알고리즘의 부류에서 벗어나 Instance 기반의 알고리즘인 IBL(Instance Based Learning)을 선택하여 학습시간의 단축과 패턴생성에 따른 분류근거의 명확성을 고려였다. 또한, 기존 IBL에 포함되어 있는 Symbolic value 의 거리계산 방식에서 네트워크의 로우 데이터인 패킷을 처리하는데 따르는 문제를 해결하기 위해 VDM(Value Difference Matrix)을 사용함으로써 탐지률을 향상시킬 수 있었다. Symbolic value간의 거리계산에 따른 성능향상의 정도를 알아보기 위해 VDM 적용 유무에 따른 실험결과와 탐지엔진에 적용되었던 알고리즘들인 COWEB 과 C4.5를 이용한 결과를 비교분석 하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.3
• /
• pp.481-492
• /
• 1997

This paper presents an algorithm for recognizing surface mount device(SMD) IC pattern based on the error back propoagation(EBP) neural network and discrete cosine transform(DCT). In this approach, we chose such parameters as frequency, angle, translation and amplitude for the shape informantion of SMD IC, which are calculated from the coefficient matrix of DCT. These feature parameters are normalized and then used for the input vector of neural network which is capable of adapting the surroundings such as variation of illumination, arrangement of objects and translation. Learning of EBP neural network is carried out until maximum error of the output layer is less then 0.020 and consequently, after the learning of forty thousand times, the maximum error have got to this value. Experimental results show that the rate of recognition is 100% in case of the random pattern taken at a similar circumstance as well as normalized training pattern. It also show that proposed method is not only relatively relatively simple compare with the traditional space domain method in extracting the feature parameter but also able to re recognize the pattern's class, position, and existence.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.5
• /
• pp.64-72
• /
• 2004

An extension of interaction matrix formulation to the problem of system and disturbance identification for a plant that is corrupted by both process and output disturbances is presented. The teaming control develops controllers that learn to improve their performance at executing a given task, based on experience performing this task. The simplest forms of loaming control are based on the same concept as integral control, but operating in the domain of the repetitions of the task. This paper studies the use of such controllers in a decentralized system, such as a robot moving on the vertical plane with the controller for each link acting independently. The basic result of the paper is to show that stability and iterative precision of the learning controllers for all subsystems when the coupling between subsystems is turned off, assures stability of the decentralized teaming in the coupled system, provided that the sample time in the digital teaming controller is sufficiently short. The methods of teaming system are shown up for the iterative precision of each link.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.8
• /
• pp.87-93
• /
• 2019

These days, as interest in the recommendation system with deep learning is increasing, a number of related studies to develop a performance for collaborative filtering through autoencoder, a state-of-the-art deep learning neural network architecture has advanced considerably. The purpose of this study is to propose autoencoder which is used by the recommendation system to predict ratings, and we added more hidden layers to the original architecture of autoencoder so that we implemented deep autoencoder with 3 to 5 hidden layers for much deeper architecture. In this paper, therefore we make a comparison between the performance of them. In this research, we use 2-dimensional arrays and 3-dimensional tensor as the input dataset. As a result, we found a correlation between matrix entry of the 3-dimensional dataset such as item-time and user-time and also figured out that deep autoencoder with extra hidden layers generalized even better performance than autoencoder.