• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.56-63
• /
• 2016

In this study, we introduce a design of Fuzzy RBFNNs-based digit recognition system using the incremental-PCA in order to recognize the handwritten digits. The Principal Component Analysis (PCA) is a widely-adopted dimensional reduction algorithm, but it needs high computing overhead for feature extraction in case of using high dimensional images or a large amount of training data. To alleviate such problem, the incremental-PCA is proposed for the computationally efficient processing as well as the incremental learning of high dimensional data in the feature extraction stage. The architecture of Fuzzy Radial Basis Function Neural Networks (RBFNN) consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means (FCM) algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, connection weights are used as the extended diverse types in polynomial expression such as constant, linear, quadratic and modified quadratic. Experimental results conducted on the benchmarking MNIST handwritten digit database demonstrate the effectiveness and efficiency of the proposed digit recognition system when compared with other studies.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.167-174
• /
• 2009

Music evokes human emotions or creates music moods through various low-level musical features. Typical music clip consists of one or more moods and this can be used as an important criteria for determining the similarity between music clips. In this paper, we propose a new music retrieval scheme based on the mood change patterns of music clips. For this, we first divide music clips into segments based on low level musical features. Then, we apply K-means clustering algorithm for grouping them into clusters with similar features. By assigning a unique mood symbol for each cluster, we can represent each music clip by a sequence of mood symbols. Finally, to estimate the similarity of music clips, we measure the similarity of their musical mood sequence using the Longest Common Subsequence (LCS) algorithm. To evaluate the performance of our scheme, we carried out various experiments and measured the user evaluation. We report some of the results.

• Journal of KIISE:Software and Applications
• /
• v.35 no.10
• /
• pp.589-599
• /
• 2008

Accurate software effort estimation has always been a challenge for the software industrial and academic software engineering communities. Many studies have focused on effort estimation methods to improve the estimation accuracy of software effort. Although data quality is one of important factors for accurate effort estimation, most of the work has not considered it. In this paper, we investigate the influence of outlier elimination on the accuracy of software effort estimation through empirical studies applying two outlier elimination methods(Least trimmed square regression and K-means clustering) and three effort estimation methods(Least squares regression, Neural network and Bayesian network) associatively. The empirical studies are performed using two industry data sets(the ISBSG Release 9 and the Bank data set which consists of the project data collected from a bank in Korea) with or without outlier elimination.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.23-32
• /
• 2006

This paper describes the optimization of a language model and an acoustic model to improve speech recognition using Korean unit digits. Since the model is composed of a finite state network (FSN) with a disyllable, recognition errors of the language model were reduced by analyzing the grammatical features of Korean unit digits. Acoustic models utilize a demisyllable pair to decrease recognition errors caused by inaccurate division of a phone or monosyllable due to short pronunciation time and articulation. We have used the K-means clustering algorithm with the transformed successive state splitting in the feature level for the efficient modelling of feature of the recognition unit. As a result of experiments, 10.5% recognition rate is raised in the case of the proposed language model. The demi-syllable fair with an acoustic model increased 12.5% recognition rate and 1.5% recognition rate is improved in transformed successive state splitting.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.8
• /
• pp.1625-1631
• /
• 2005

This paper describes an optimization of a language model and an acoustic model that improve the ability of speech recognition with Korean nit digit. Recognition errors of the language model are decreasing by analysis of the grammatical feature of korean unit digits, and then is made up of fsn-node with a disyllable. Acoustic model make use of demi-syllable pair to decrease recognition errors by inaccuracy division of a phone, a syllable because of a monosyllable, a short pronunciation and an articulation. we have used the k-means clustering algorithm with the transformed successive state splining in feature level for the efficient modelling of the feature of recognition unit . As a result of experimentations, $10.5\%$ recognition rate is raised in the case of the proposed language model. The demi-syllable pair with an acoustic model increased $12.5\%$ recognition rate and $1.5\%$ recognition rate is improved in transformed successive state splitting.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.859-868
• /
• 2004

We propose a method of selecting initial training examples for active learning so that it can reach high accuracy faster with fewer further queries. Our method is based on the assumption that an active learner can reach higher performance when given an initial training set consisting of diverse and typical examples rather than similar and special ones. To obtain a good initial training set, we first cluster examples by using k-means clustering algorithm to find groups of similar examples. Then, a representative example, which is the closest example to the cluster's centroid, is selected from each cluster. After these representative examples are labeled by querying to the user for their categories, they can be used as initial training examples. We also suggest a method of using the centroids as initial training examples by labeling them with categories of corresponding representative examples. Experiments with various text data sets have shown that the active learner starting from the initial training set selected by our method reaches higher accuracy faster than that starting from randomly generated initial training set.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.114-114
• /
• 2017

하천의 유사량 자료는 하상변동 예측, 저수지 퇴사량 추정, 유사조절 계획 수립 등 유역과 하천관리 그리고 하천 시설물 관리를 위해 필요하다. 최근 4대강 사업구간에 대한 담수용 보로 유입되는 유사량과 하천 유사의 종횡단적 분포와 하상변동량 등의 산정에 기초자료로 활용하고자 유사량 관측망이 구축되어 있다. 본 연구에서는 하천 유사량에 영향을 미치는 유역특성인자에 대한 군집분석을 통해 유사 발생 유역을 분류하고자 한다. 체계화된 유량 및 유사량 측정 방법에 의해 신뢰할만한 유량-총유사량 관계식을 갖는 유량조사사업단의 35개 유역을 대상으로 한다. 유역 군집분석을 수행하고자 유역과 하천에 대한 지형인자, 토양인자, 토지이용 등의 유역특성 매개변수 자료를 수집하였고, 매개변수별 유사도거리 산정에 오류를 줄이기 위해 매개변수를 무차원화 하였다. 유역의 비유사량은 유역면적, 유역경사, 토성, 토지이용 등에 영향을 받았다. K-means 기법에 의해 군집분석을 수행한 결과 유사량 측정 유역은 A, B, C, D 4개의 그룹으로 분류되었다. B그룹 유역은 첨두홍수량이 크고 발생시간이 짧은 유역 및 하천 조건을 가지고 있었으며, 직접유출이 증가하는 지표조건과 침식이 활발한 토양조건을 갖는 것으로 파악되었다. 그룹별로 실측 비유사량을 검토한 결과 B그룹에 포함된 유역의 유사량이 다른 유역에 비해 상대적으로 크게 발생하였다. 이러한 결과는 유역특성 매개변수의 군집분석을 통한 유역의 군집분류가 유역과 하천의 유사관리 측면에서 유용한 관리방안으로 활용될 수 있음을 의미한다.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.580-591
• /
• 2019

This paper focuses on to improving object detection performance using the camera and LiDAR on autonomous vehicle platforms by fusing detected objects from individual sensors through a late fusion approach. In the case of object detection using camera sensor, YOLOv3 model was employed as a one-stage detection process. Furthermore, the distance estimation of the detected objects is based on the formulations of Perspective matrix. On the other hand, the object detection using LiDAR is based on K-means clustering method. The camera and LiDAR calibration was carried out by PnP-Ransac in order to calculate the rotation and translation matrix between two sensors. For Sensor fusion, intersection over union(IoU) on the image plane with respective to the distance and angle on world coordinate were estimated. Additionally, all the three attributes i.e; IoU, distance and angle were fused using logistic regression. The performance evaluation in the sensor fusion scenario has shown an effective 5% improvement in object detection performance compared to the usage of single sensor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.342-345
• /
• 2014

Network intrusion detection system based on machine learning methods is quite dependent on the selected features in terms of accuracy and efficiency. Nevertheless, choosing the optimal combination of features from generally used features to detect network intrusion requires extensive computing resources. For instance, the number of possible feature combinations from given n features is $2^n-1$. In this paper, to tackle this problem we propose a optimal feature selection algorithm. Proposed algorithm is based on the local search algorithm, one of representative meta-heuristic algorithm for solving optimization problem. In addition, the accuracy of clusters which obtained using selected feature components and k-means clustering algorithm is adopted to evaluate a feature assembly. In order to estimate the performance of our proposed algorithm, comparing with a method where all features are used on NSL-KDD data set and multi-layer perceptron.

• The Korean Journal of Applied Statistics
• /
• v.32 no.3
• /
• pp.331-348
• /
• 2019

Understanding the tumor heterogeneity due to differences in the growth pattern of metastatic tumors and rate of change is important for understanding the sensitivity of tumor cells to drugs and finding appropriate therapies. It is often possible to test for differences in population means using t-test or ANOVA when the group of N samples is distinct. However, these statistical methods can not be used unless the groups are distinguished as the data covered in this paper. Statistical methods have been studied to test heterogeneity between samples. The minimum combination t-test method is one of them. In this paper, we propose a maximum combinatorial t-test method that takes into account combinations that bisect data at different ratios. Also we propose a method based on the idea that examining the heterogeneity of a sample is equivalent to testing whether the number of optimal clusters is one in the cluster analysis. We verified that the proposed methods, maximum combination t-test method and gap statistic, have better type-I error and power than the previously proposed method based on simulation study and obtained the results through real data analysis.