• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.646-648
• /
• 2004

기계학습의 군집화(clustering) 기법은 예제들 간의 유사성에 근거하여 주어진 예제들을 무리 짓는 방법이다. 준감독(semi-supervised) 군집화는 카테고리가 부여된(labeled) 소수의 예제들을 적극적으로 활용하여 군집형태가 보다 자연스럽게 형성되도록 유도하는 군집화 방법이다. 준감독 군집화 문제에서 예제에 카테고리를 부여하는 작업은 현실적으로 극히 제한적이거나 카테고리를 부여하는데 소요되는 비용이 상당하므로, 제한된 자원 내에서 군집화에 효용성이 높을 예제들을 선정하여 카테고리를 부여하는 것이 필요하다. 본 논문에서는 기존 연구에서 능동적 학습의 초기 훈련예제 선정을 위해 제안된 군집기반 훈련예제 선정 방법을 준감독 군집화에 적용하여 군집 결과의 질을 향상시키고자 한다. 군집화를 이용한 예제 선정 방법은 유사한 예제들은 동일한 카테고리에 속할 가능성이 높다는 가정하에 전체 예제를 활용하여 선정하고자 하는 예제 수만큼 군집을 생성 한 후. 각 군집의 중심점에 가장 가까운 예제들을 대표 예제로 선정하여 훈련 집합을 구성하는 방법이다 본 논문에서는 문서를 대상으로 하는 준감독 군집화 실험을 통해, 카테고리를 부여할 예제를 임의로 선정한 경우에 비해 군집화를 이용한 훈련 예제들로 준감독 군집화를 수행한 경우가 보다 좋은 군집을 형성함을 확인하였다.

• Journal of Information Science Theory and Practice
• /
• v.6 no.4
• /
• pp.28-38
• /
• 2018

Wikipedia is composed of millions of articles, each of which explains a particular entity with various languages in the real world. Since the articles are contributed and edited by a large population of diverse experts with no specific authority, Wikipedia can be seen as a naturally occurring body of human knowledge. In this paper, we propose a method to automatically identify key entities and relations in Wikipedia articles, which can be used for automatic ontology construction. Compared to previous approaches to entity and relation extraction and/or identification from text, our goal is to capture naturally occurring entities and relations from Wikipedia while minimizing artificiality often introduced at the stages of constructing training and testing data. The titles of the articles and anchored phrases in their text are regarded as entities, and their types are automatically classified with minimal training. We attempt to automatically detect and identify possible relations among the entities based on clustering without training data, as opposed to the relation extraction approach that focuses on improvement of accuracy in selecting one of the several target relations for a given pair of entities. While the relation extraction approach with supervised learning requires a significant amount of annotation efforts for a predefined set of relations, our approach attempts to discover relations as they occur naturally. Unlike other unsupervised relation identification work where evaluation of automatically identified relations is done with the correct relations determined a priori by human judges, we attempted to evaluate appropriateness of the naturally occurring clusters of relations involving person-artifact and person-organization entities and their relation names.

• Geomechanics and Engineering
• /
• v.30 no.2
• /
• pp.107-121
• /
• 2022

Coal pillar assessment is of broad importance to underground engineering structure, as the pillar failure can lead to enormous disasters. Because of the highly non-linear correlation between the pillar failure and its influential attributes, conventional forecasting techniques cannot generate accurate outcomes. To approximate the complex behavior of coal pillar, this paper elucidates a new idea to forecast the underground coal pillar stability using combined unsupervised-supervised learning. In order to build a database of the study, a total of 90 patterns of pillar cases were collected from authentic engineering structures. A state-of-the art feature depletion method, t-distribution symmetric neighbor embedding (t-SNE) has been employed to reduce significance of actual data features. Consequently, an unsupervised machine learning technique K-mean clustering was followed to reassign the t-SNE dimensionality reduced data in order to compute the relative class of coal pillar cases. Following that, the reassign dataset was divided into two parts: 70 percent for training dataset and 30 percent for testing dataset, respectively. The accuracy of the predicted data was then examined using support vector classifier (SVC) model performance measures such as precision, recall, and f₁-score. As a result, the proposed model can be employed for properly predicting the pillar failure class in a variety of underground rock engineering projects.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.3
• /
• pp.21-28
• /
• 2024

Unsupervised learning is a type of machine learning, and unlike supervised learning or reinforcement learning, a target value for input value is not given. Clustering is mainly used for such unsupervised learning. One of the representative methods of such clustering is K-means clustering. Since K-means clustering is a method of determining the number of clusters and continuing to find the central point of the data allocated to the cluster, there is a problem that the clustered group may not be the optimal cluster. In this study, particle swarm optimization algorithm, which determines the motion vector by adding various variables as well as the center point, is applied to K-means clustering. The improved K-means clustering makes it possible to move toward better outcome values even when the center of cluster no longer change. In the conventional clustering method, the center of the cluster moves to the center of the data belonging to the cluster, and clustering ends when the cluster does not change, so other characteristics other than the center value are excluded. Unlike the conventional clustering method, the improved clustering method uses a central value, an average value, and a random value as variables, and a particle swarm optimization algorithm that modifies the vector for each iteration is applied. As a result, improved clustering method derived a better result value than the existing clustering method in the group's fitness index, silhouette score.

• MALSORI
• /
• no.66
• /
• pp.87-103
• /
• 2008

We describe a new active learning method in conditional random fields (CRFs) framework for keyphrase extraction. To save elaboration in annotation, we use diversity and representative measure. We select high diversity training candidates by sentence confidence value. We also select high representative candidates by clustering the part-of-speech patterns of contexts. In the experiments using dialog corpus, our method achieves 86.80% and saves 88% training corpus compared with those of supervised method. From the results of experiment, we can see that the proposed method shows improved performance over the previous methods. Additionally, the proposed method can be applied to other applications easily since its implementation is independent on applications.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.870-876
• /
• 1993

This paper presents a binary clustering network (BCN) and a heuristic algorithm to detect pitch for recognition of keywords in continuous speech. In order to classify nonlinear patterns, BCN separates patterns into binary clusters hierarchically and links same patterns at root level by using the supervised learning and the unsupervised learning. BCN has many desirable properties such as flexibility of dynamic structure, high classification accuracy, short learning time, and short recall time. Pitch Detection algorithm is a heuristic model that can solve the difficulties such as scaling invariance, time warping, time-shift invariance, and redundance. This recognition algorithm has shown recognition rates as high as 95% for speaker-dependent as well as multispeaker-dependent tests.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.269-270
• /
• 2013

퍼지 클러스터링은 유사도가 높은 데이터 포인트들이 동일한 클러스터에 포함되도록 하는 대표적인 비교사 학습 방법 중 하나이다. 이 논문에서는 클러스터링을 분류기의 전처리 단계에서 활용할 수 있도록 클러스터 내에서 분류 오류가 최소가 될 수 있도록 클러스터를 생성할 수 있는 새로운 퍼지 클러스터링 방법을 제안한다. 제안하는 클러스터링은 특징 벡터와 함께 클래스 라벨을 활용하므로 분류기와 결합하여 사용할 경우 기존 분류기와 함께 사용할 경우 보다 우수한 성능을 기대할 수 있다.

• The Journal of Korean Association of Computer Education
• /
• v.13 no.1
• /
• pp.65-73
• /
• 2010

This study offered lexical knowledge acquisition model of unsupervised learning method in order to overcome limitation of lexical knowledge hand building manual of supervised learning method for research of natural language processing. The offered model obtains the lexical knowledge from the lexical entry which was given by inputting through the process of vectorization, clustering, lexical knowledge acquisition automatically. In the process of obtaining the lexical knowledge acquisition of model, some parts of lexical knowledge dictionary which changes in the number of lexical knowledge and characteristics of lexical knowledge appeared by parameter changes were shown. The experimental results show that is possibility of automatic building of Machine-readable dictionary, because observed to the number of lexical class information cluster collected constant. also building of lexical ditionary including left-morphosyntactic information and right-morphosyntactic information is reflected korean characteristic.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.57-64
• /
• 2014

Most previous studies of software fault prediction model which determines the fault-proneness of input modules have focused on supervised learning model using training data set. However, Unsupervised learning model is needed in case supervised learning model cannot be applied: either past training data set is not present or even though there exists data set, current project type is changed. Building an unsupervised learning model is extremely difficult that is why only a few studies exist. In this paper, we build unsupervised models using representative clustering algorithms, EM and DBSCAN, that have not been used in prior studies and compare these models with the previous model using K-means algorithm. The results of our study show that the EM model performs slightly better than the K-means model in terms of error rate and these two models significantly outperform the DBSCAN model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.