• Smart Media Journal
• /
• v.9 no.4
• /
• pp.126-133
• /
• 2020

The treatment policy and prognosis are determined based on the final stage of lung cancer patients. The final stage of lung cancer patients is determined based on the T, N, and M stage classification table provided by the American Cancer Society (AJCC). However, the final stage of AJCC has limitations in its use for various fields such as patient treatment, prognosis and survival days prediction. In this paper, clustering algorithm which is one of non-supervised learning algorithms was assessed in order to check whether using only T, N, M stages with a data science method is effective for classifying the group of patients in the aspect of survival days. The final stage groups and T, N, M stage clustering groups of lung cancer patients were compared by using the cox proportional hazard model. It is confirmed that the accuracy of prediction of survival days with only T, N, M stages becomes higher than the accuracy with the final stages of patients. Especially, the accuracy of prediction of survival days with clustering of T, N, M stages improves when more or less clusters are analyzed than the seven clusters which is same to the number of final stage of AJCC.

• 전기의세계
• /
• v.59 no.11
• /
• pp.27-31
• /
• 2010

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.1 no.1
• /
• pp.55-64
• /
• 1990

The purpose of the present study is to investigate cognitive characteristics of ADHD children by comparing their performances on KEDI-WISC according to age and EEG variables. Subjects were 56 ADHD children who visited Seoul National University Children's Hospital during the period from January, 1988 to March, 1989. Group differences on age and EEG variables were tested by ANOVA, and Hierarchical Cluster Analysis was performed to investigate how ADHD children were classified based on their performances on KEDI-WISC. The results Indicated that ADHD children showed low scores on Coding, Digit Span, and Comprehension subtests, suggesting their attention deficits and impulsivity. ADHD children were clustered Into three groups based on only FSIQ. In post-hoc tests three groups showed different cognitive strengths and weaknesses on KEDI-WISC. Group differences on age were not significant, and abnormal EEG group showed lower PIQ than normal EEG group, suggesting the possibility that their attention deficits were related to neurological factors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.2
• /
• pp.44-57
• /
• 1995

In this paper GFI (Generalized Fuzzy Isodata) and FI (Fuzzy Isodata) algorithms are studied and applied to the tire tread pattern classification problem. GFI algorithm which repeatedly grouping the partitioned cluster depending on the fuzzy partition matrix is general form of GI algorithm. In the constructing the binary tree using GFI algorithm cluster validity, namely, whether partitioned cluster is feasible or not is checked and construction of the binary tree is obtained by FDH clustering algorithm. These algorithms show the good performance in selecting the prototypes of each patterns and classifying patterns. Directions of edge in the preprocessed image of tire tread pattern are selected as features of pattern. These features are thought to have useful information which well represents the characteristics of patterns.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.72-78
• /
• 2006

It is essential for robot to have the sensing and communication abilities in the swarm robot system. In general, as the number of robot goes on increasing, the limitation of communication capacity and information overflow occur in global communication system. Therefore a local communication is more effective than global one. In this paper, we propose the novel method for determining the optimal communication radius through the analyzing of the information propagation based on local communication. And we also propose a method of cooperative strategies and group behavior of swarm robot based on artificial immune system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.660-666
• /
• 2011

In this paper, we proposed a Particle Swarm Optimization(PSO) to search the optimal link lengths for legged walking robot. In order to apply the PSO algorithm for the proposed, its walking robot kinematic analysis is needed. A crab robot based on four-bar linkage mechanism and Jansen mechanism is implemented in H/W. For the performance index of PSO, the stride length of the legged walking robot is defined, based on the propose kinematic analysis. Comparative simulation results present to illustrate the viability and effectiveness of the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.212-215
• /
• 2008

In this paper, we develop the optimal path planning algorithm using the improved Dijkstra algorithm and the particle swarm optimization. To get the optimal path, at first we construct the MAKLINK on the world environment and then make a graph associated with the MAKLINK. The MAKLINK is a set of edges which consist of the convex set. Some of the edges come from the edges of the obstacles. From the graph, we obtain the Dijkstra path between the starting point and the destination point. From the optimal path, we search the improved Dijkstra path using the graph. Finally, applying the particle swarm optimization to the improved Dijkstra path, we obtain the optimal path for the mobile robot. It turns out that the proposed method has better performance than the result in [1] through the experiment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.316-321
• /
• 2007

We propose a quatitative annotation method for edges in Bayesian networks using given sets of condition-specific data. Bayesian network model has been used widely in various fields to infer probabilistic dependency relationships between entities in target systems. Besides the need for identifying dependency relationships, the annotation of edges in Bayesian networks is required to analyze the meaning of learned Bayesian networks. We assume the training data is composed of several condition-specific data sets. The contribution of each condition-specific data set to each edge in the learned Bayesian network is measured using the ratio of likelihoods between network structures of including and missing the specific edge. The proposed method can be a good approach to make quantitative annotation for learned Bayesian network structures while previous annotation approaches only give qualitative one.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.100-105
• /
• 2011

Needs of intelligent system has risen continuously to solve given problem optimally using learning and reasoning. This system has performed important roles in diverse fields for improving the human-life quality in past, present, and future. So, it is important to analyze the trend of technology forecasting for the intelligent system. In this paper, we propose a patent analysis method for technology forecasting of the intelligent system using objective patent data. To verify our study, we use the patent data applied and registered until now.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.121-124
• /
• 2007

본 논문에서는 적응분할에 바탕을 둔 신호의 상호정보 추출에 의한 효율적인 얼굴인식 방법을 제안하였다. 여기서 적응분할의 상호정보 수출은 영상신호의 확률밀도를 보다 간단하게 계산할 수 있도록 함으로써 신호 상호간의 종속성을 좀 더 빠르고 정확하게 측정하기 위함이다. 또한 상호정보는 학습 얼굴영상과 인식을 위해 입력되는 시험 얼굴영상 상호간의 상관관계를 나타내는 정보로 유사성을 나타내는 군집화 척도이다. 제안된 방법을 256*192 픽셀의 5개 얼굴들을 대상으로 실험한 결과, 우수한 인식성능이 있음을 확인하였다.