• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3336-3346
• /
• 2022

In general, a number of severe accident scenarios derived from Level 2 probabilistic safety assessment (PSA) are typically grouped into several categories to efficiently evaluate their potential impacts on the public with the assumption that scenarios within the same group have similar source term characteristics. To date, however, grouping by similar source terms has been completely reliant on qualitative methods such as logical trees or expert judgements. Recently, an exhaustive simulation approach has been developed to provide quantitative information on the source terms of a large number of severe accident scenarios. With this motivation, this paper proposes a machine learning-based categorization method based on exhaustive simulation for grouping scenarios with similar accident consequences. The proposed method employs clustering with an autoencoder for grouping unlabeled scenarios after dimensionality reductions and feature extractions from the source term data. To validate the suggested method, source term data for 658 severe accident scenarios were used. Results confirmed that the proposed method successfully characterized the severe accident scenarios with similar behavior more precisely than the conventional grouping method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.1
• /
• pp.109-126
• /
• 2014

The level of service (LOS) of the Highway Capacity Manual (KHCM) has been used as a basic criterion at decision making processes for signalized intersections in Korea. The KHCM provides five steps for the signalized intersection analysis. Among them, lane grouping, which is the third step, significantly influence the final LOS. The current method presented in the KHCM, however, classifies a shared lane as a de facto turning lane group, even though the turning traffic of the shared lane is few. Thus, this research was initiated to provide an alternative. To this end, three alternatives were suggested, including the method based on the lane grouping presented in the U.S. Highway Capacity Manual, the method using turning ratio of shared turning lane, and the method using a threshold traffic volume in lane grouping. The feasibilities of the three methods were evaluated using a calibrated CORSIM model. Conclusively, the method using a threshold traffic volume in lane grouping outperformed.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.3
• /
• pp.83-89
• /
• 2016

The group formation problem of the machine and part is a critical issue in the planning stage of cellular manufacturing systems. The machine-part grouping with alternative process plans means to form machine-part groupings in which a part may be processed not only by a specific process but by many alternative processes. For this problem, this study presents an algorithm based on self organizing neural networks, so called SOM (Self Organizing feature Map). The SOM, a special type of neural networks is an intelligent tool for grouping machines and parts in group formation problem of the machine and part. SOM can learn from complex, multi-dimensional data and transform them into visually decipherable clusters. In the proposed algorithm, output layer in SOM network had been set as one-dimensional structure and the number of output node has been set sufficiently large in order to spread out the input vectors in the order of similarity. In the first stage of the proposed algorithm, SOM has been applied twice to form an initial machine-process group. In the second stage, grouping efficacy is considered to transform the initial machine-process group into a final machine-process group and a final machine-part group. The proposed algorithm was tested on well-known machine-part grouping problems with alternative process plans. The results of this computational study demonstrate the superiority of the proposed algorithm. The proposed algorithm can be easily applied to the group formation problem compared to other meta-heuristic based algorithms. In addition, it can be used to solve large-scale group formation problems.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.701-708
• /
• 2005

Structuring mechanism, important to serve messages in post-office box structure, is to construct the hierarchy of classes according to the contents of message objects. This Paper Proposes $\alpha$-cut based genealogy grouping method to cluster a lot of structured objects in application domain. The proposed method decides the relationship first by semantic similarity relation and fuzzy relation, and then performs the grouping by operations of search( ), insert() and hierarchy(). This hierarchy structure makes it easy to process group-related processing tasks such as answering queries, discriminating objects, finding similarities among objects, etc. The proposed post-office box structure may be efficiently used to serve and manage message objects by the creation of groups. The Proposed method is tested for 5500 message objects and compared with other methods such as non-grouping, BGM, RGM, OGM.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.4
• /
• pp.15-24
• /
• 2005

The success of cooperative learning in small groups heavily depends on how the small groups are set up. When small groups are formed, the factors such as the objectives and characteristics of the work and the capabilities and interests of the group members should be considered to maximize the interaction among the group members. However, it is not easy for teachers to manually divide their class to small groups to satisfy such conditions. In this work, we developed and implemented a student grouping system that divides the class as appropriate as possible, when given multidimensional student data and a set of conditions for forming small groups. The grouping conditions can be heterogeneous, homogeneous, and both. The grouping system can easily be used by teachers since the system can be accessed by clicking a menu button embedded into Microsoft Excel. The system has also a wide range of application areas where object grouping by various conditions is needed.

• Journal of the Korean association of regional geographers
• /
• v.7 no.2
• /
• pp.97-119
• /
• 2001

The present education situations are rapidly changing to adapt to 'the Knowledge & Information-based Society'. Especially, the implementation of 'the 7th National Curriculum' put strong emphasis on the learner-centered education that refers to the ability grouping. Therefore, it is necessary that the change from a traditional teaching method to a learner-centered one in geography education will take place. This study will present a design of geography ability grouping through the Task-Solving Learning. This ability grouping method is suitable for the large class. And this study also presents a strategy by applying WBI, which make use of the advantage of computer and constructivism. This WBI model can be applied properly to many teaching-learning methods that includes Self-Directed Learning, Collaborate Learning, Ability Grouping, and Applying ICT Instruction. Actually they are demanded in the current education. A geography-classroom will have an accessible internet program as a precondition for this instruction.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.219-225
• /
• 2022

In this paper, we propose a CAC exploring a RA based dynamic spectrum hole grouping for secondary users' QoS enhancement in multi-classes cognitive radio networks. The RA based dynamic spectrum hole grouping uses SU multi-classes overlaying spectrum structure suggested here. Multiclass SUs are divided into real and non real, and real SUs have a priority for resource utilization against non real. The amount of resource required by real SUs is supported by Wiener prediction and the dynamic spectrum hole grouping, and that required by non real SU is supported by the remained available amount without prediction. In the simulations, we compare the proposed CAC performances using the dynamic spectrum hole grouping in terms of SU connection's blocking(dropping) rate and resource utilization efficiency according to multi-classes traffic characteristics, and then we show the proposed CAC can guarantee the desired QoS of multi-classes secondary users.

• Journal of The Korean Association of Information Education
• /
• v.14 no.3
• /
• pp.291-300
• /
• 2010

Group-based learning is known to be an effective means to improve scholastic achievement in online learning. Therefore, there are some previous researches for the group-based learning. A lot of previous researches define factors for grouping from the characteristics of classes, teacher's decision and students' preferences and then generate a group based on the defined factors. However, many algorithms proposed by previous researches depend on a specific class and is not a general approach since there exist several differences in terms of the need of courses, learners, and teachers. Moreover it is hard to find a automatic system for group generation. This paper proposes a grouping system which automatically generate a learner group according to characteristics of various classes. the proposed system automatically generates a learner group by using basic information for a class or additional factors inputted from a user. The proposed system defines a set of rules for learner grouping which enables automatic selection of a learner grouping algorithm tailored to the characteristics of a given class. This rule based approach allows the proposed system to accommodate various learner grouping algorithms for a later use. Also we show the usability of our system by serviceability evaluation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.85-88
• /
• 2000

본 논문은 Threshold Logic Unit(TLU)를 기본 뉴런으로 하여 최소화된 이진신경회로망을 합성하는 방법인 MSP Term Grouping(MTG) 알고리즘의 time complexity를 분석하고자 한다. 이를 전체 패턴 탐색을 통한 이진신경회로망 합성의 경우와 비교하여 MTG 알고리즘의 효용성을 보여준다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1987.04a
• /
• pp.46-48
• /
• 1987

In the difference picture(DP) which is obtatined from two subsequent images we detect edge intersection points(EIP) and estimate the directions in which edges disappear at those points, Then we group the DP regions which the motion of the object makes and we extract the moving object.