• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.547-560
• /
• 2023

Recently, research on predicting ground classification using machine learning techniques, TBM excavation data, and ground data is increasing. In this study, a multi-classification prediction study for uniaxial compressive strength (UCS) was conducted by applying random forest model based on a decision tree among machine learning techniques widely used in various fields to machine data and ground data acquired at three slurry shield TBM sites. For the classification prediction, the training and test data were divided into 7:3, and a grid search including 5-fold cross-validation was used to select the optimal parameter. As a result of classification learning for UCS using a random forest, the accuracy of the multi-classification prediction model was found to be high at both 0.983 and 0.982 in the training set and the test set, respectively. However, due to the imbalance in data distribution between classes, the recall was evaluated low in class 4. It is judged that additional research is needed to increase the amount of measured data of UCS acquired in various sites.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.32-40
• /
• 2008

Fuzzy rules are very useful and efficient to describe classification rules especially when the attribute values are continuous and fuzzy in nature. However, it is generally difficult to determine membership functions for generating efficient fuzzy classification rules. In this paper, we propose a method of automatic generation of efficient fuzzy classification rules using evolutionary algorithm. In our method we generate a set of initial membership functions for evolutionary algorithm by supervised clustering the training data set and we evolve the set of initial membership functions in order to generate fuzzy classification rules taking into consideration both classification accuracy and rule comprehensibility. To reduce time to evaluate an individual we also propose an evolutionary algorithm with data partition evaluation in which the training data set is partitioned into a number of subsets and individuals are evaluated using a randomly selected subset of data at a time instead of the whole training data set. We experimented our algorithm with the UCI learning data sets, the experiment results showed that our method was more efficient at average compared with the existing algorithms. For the evolutionary algorithm with data partition evaluation, we experimented with our method over the intrusion detection data of KDD'99 Cup, and confirmed that evaluation time was reduced by about 70%. Compared with the KDD'99 Cup winner, the accuracy was increased by 1.54% while the cost was reduced by 20.8%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.34-40
• /
• 2018

This paper presents a new method to estimate the pose of a moving object accurately using a monocular camera and a low-end GPS+IMU sensor system. For this goal, we adopted a deep neural network for the semantic segmentation of input images and compared the results with a semantic map of a neighborhood. In this map matching, we use weight tables to deal with label inconsistency effectively. Signals from a low-end GPS+IMU sensor system are used to limit search spaces and minimize the proposed function. For the evaluation, we added noise to the signals from a high-end GPS-IMU system. The results show that the pose can be recovered from the noisy signals. We also show that the proposed method is effective in handling non-open-sky situations.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.849-858
• /
• 2004

Most of supervised teaming algorithms could be applied after that continuous variables are transformed to categorical ones at the preprocessing stage in order to avoid the difficulty of processing continuous variables. This preprocessing stage is called global discretization, uses the class distribution list called bins. But, when data are large and the range of the variable to be discretized is very large, many sorting and merging should be performed to produce a single bin because most of global discretization methods need a single bin. Also, if new data are added, they have to perform discretization from scratch to construct categories influenced by the data because the existing methods perform discretization in batch mode. This paper proposes a method that extracts sample points and performs discretization from these sample points in order to solve these problems. Because the approach in this paper does not require merging for producing a single bin, it is efficient when large data are needed to be discretized. In this study, an experiment using real and synthetic datasets was made to compare the proposed method with an existing one.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.497-501
• /
• 2008

In this paper we present a method for continuous EEG classification, where we employ nonnegative tensor factorization (NTF) to determine discriminative spectral features and use the Viterbi algorithm to continuously classily multiple mental tasks. This is an extension of our previous work on the use of nonnegative matrix factorization (NMF) for EEG classification. Numerical experiments with two data sets in BCI competition, confirm the useful behavior of the method for continuous EEG classification.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.8B
• /
• pp.752-759
• /
• 2002

The capacity of the cell varies with the load of the home and neighboring cells. But most call admission control (CAC) algorithms do not consider the cell loading. In this paper a dynamic call admission control is proposed in a WCDMA system with traffic asymmetry. The proposed algorithm changes the CAC thresholds of new call and handoff call based on channel condition. The blocking and dropping probabilities can be controlled by adjusting these thresholds. The proposed algorithm guarantees the Qos of call class and priority between new call and handoff call. In addition, it can minimize the grade of service (GOS) value with the system throughput maintained.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.212-216
• /
• 2006

MLP는 뛰어난 학습능력으로 인하여 많은 분야에 성공적으로 적용되고 있다. 그러나, 학습 방법으로서 최급경사법에 근거한 오차역전파 알고리즘을 적용하기 때문에 학습시간이 오래 걸리는 단점이 있다. 또한 입력차원의 크기가 크거나 클래스간 학습데이터의 유사성이 클 경우 최적의 파라미터를 구하는데는 한계가 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 LDA와 local MLP을 이용한 새로운 얼굴인식시스템을 제안하고자 한다. 제안된 방법은 우선 LDA 기법에 의해 차원이 축소된 얼굴의 특징벡터를 계산한다. 다음 단계로서 전체 학습영상을 사용하기 보다는 그룹별로 분할된 얼굴영상에 대해 MLP를 수행하므로서 그룹별로 최적인 파라미터를 결정한다. 마지막 단계로 그룹별로 수행된 local MLP를 결합함으로써 전체 얼굴인식 시스템을 구성한다. 제안된 방법의 타당성을 보이기 위해 ORL 얼굴영상을 대상으로 실험한 결과 기존 방법인 PCA나 LDA에 비해 향상된 결과를 보임을 확인할 수 있었다.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1891-1892
• /
• 2008

본 논문에서는 부분방전 패턴인식을 위한 퍼지뉴럴네크워크(Fuzzy-Nueral Network를 설계한다. 퍼지뉴럴네트워크의 구조에서 규칙의 전반부는 개별적인 입력 공간을 분할하여 표현하고, 규칙의 후반부는 다항식으로서 표현되며 오류역전파 알고리즘을 이용하여 연결가중치인 후반부 다항식의 계수를 학습한다. 또한, 유전자 알고리즘을 이용하여 각 입력에 대한 전반부 멤버쉽함수의 정점과 학습률 및 모멤텀 계수를 최적으로 동조한다. 제안된 네트워크는 부분방전 패턴인식을 위해 다중 출력을 가지며, 초고압 XLPE 케이블 절연접속함의 모의결함에 대해 부분방전 신호를 패턴인식한다. 부분방전 신호는 PRPDA 방법을 통해 256개의 입력 벡터와 4개의 출력 벡터를 가지며, 보이드 방전, 코로나 방전, 표면 방전, 노이즈의 4개 클래스를 분류하며, 패턴인식률로서 결과를 분석한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.99-102
• /
• 1998

본 논문에서는 복잡하고 비선형적인 시스템의 최적 모델링을 우해서 지능형 퍼지-뉴럴네트워크의 최적 모델 구축을 위한 방법을 제안한다. 기본 모델은 퍼지 추론 시스템의 언어적인 규칙생성의 장점과 뉴럴 네트워크의 학습기능을 결합한 FNNs 모델을 사용한다. FNNs 모델의 퍼지 추론부는 간략추론이 사용되고, 학습은 요류 역전파 알고리즘을 사용하여 다른 모델들에 비해 학습속도가 빠르고 수렴능력이 우수하다. 그러나 기본 모델은 주어진 시스템에 대하여 퍼지 공간을 균등하게 분할하여 퍼지 소속을 정의한다. 이것은 비선형 시스템의 모델링에 있어어서 성능을 저하시켜 최적의 모델을 얻기가 어렵다. 논문에서는 주어진 데이터의 특성을 부여한 공간을 설정하기 위하여 클러스터링 알고리즘을 사용한다. 클러스터링 알고리즘은 주어진 시스템에 대하여 상호 연관성이 있는 데이터들끼리 특성을 나누어 몇 개의 클래스를 이룬다. 클러스터링 알고리즘을 사용하여 초기 FNNs 모델의 퍼지 공간을 나누고 소속함수를 정의한다. 또한, 최적화 기법중의 하나로 자연선택과 자연계의 유전자 메카니즘에 바탕을 둔 탐색 알고리즘인 유전자 알고리즘을 사용하여 주\ulcorner 진 모델에 대하여 최적화를 수행한다. 또한 본 연구에서는 학습 및 테스트 데이터의 성능 결과의 상호 균형을 얻기 위한 하중값을 가긴 성능지수가 제시된다.

• Journal of KIISE:Information Networking
• /
• v.35 no.6
• /
• pp.497-509
• /
• 2008

Various algorithms and architectures for efficient packet classification have been widely studied. Packet classification algorithms based on a decision tree structure such as HiCuts and HyperCuts are known to be the best by exploiting the geometrical representation of rules in a classifier. However, the algorithms are not practical since they involve complicated heuristics in selecting a dimension of cuts and determining the number of cuts at each node of the decision tree. Moreover, the cutting is not efficient enough since the cutting is based on regular interval which is not related to the actual range that each rule covers. In this paper, we proposed a new efficient packet classification algorithm using a range cutting. The proposed algorithm primarily finds out the ranges that each rule covers in 2-dimensional prefix plane and performs cutting according to the ranges. Hence, the proposed algorithm constructs a very efficient decision tree. The cutting applied to each node of the decision tree is optimal and deterministic not involving the complicated heuristics. Simulation results for rule sets generated using class-bench databases show that the proposed algorithm has better performance in average search speed and consumes up to 3-300 times less memory space compared with previous cutting algorithms.