• Journal of Intelligence and Information Systems
• /
• v.13 no.4
• /
• pp.121-135
• /
• 2007

Constraint directed scheduling techniques, representing problem constraints explicitly and constructing schedules by constrained heuristic search, have been successfully applied to real world scheduling problems that require satisfying a wide variety of constraints. However, there has been little basic research on the representation and optimization of the objective value of a schedule in the constraint directed scheduling literature. In particular, the cost objective is very crucial for enterprise decision making to analyze the effects of alternative business plans not only from operational shop floor scheduling but also through strategic resource planning. This paper aims to explicitly represent and optimize the total cost of a schedule including the tardiness and inventory costs while satisfying non-relaxable constraints such as resource capacity and temporal constraints. Within the cost based scheduling framework, a cost propagation algorithm is presented to update cost information throughout temporal constraints within the same job.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.1
• /
• pp.225-234
• /
• 2019

Bitcoin is a cryptocurrency with characteristics such as de-centralization and distributed ledger, and these features are maintained through a mining system called "proof of work". In the mining system, mining difficulty is adjusted to keep the block generation time constant. However, Bitcoin's current method to update mining difficulty does not reflect the future hash power, so the block generation time can not be kept constant and the error occurs between designed time and real time. This increases the inconsistency between block generation and real world and causes problems such as not meeting deadlines of transaction and exposing the vulnerability to coin-hopping attack. Previous studies to keep the block generation time constant still have the error. In this paper, we propose a machine-learning based method to reduce the error. By training with the previous hash power, we predict the future hash power and adjust the mining difficulty. Our experimental result shows that the error rate can be reduced by about 36% compared with the current method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.4
• /
• pp.37-48
• /
• 2009

Household service robots should be able to provide their users with a variety of temporal reasoning services. In this paper, we propose an effective way of developing such temporal reasoning services using a domain-independent AI planner. Developing temporal reasoning services with a domain-independent AI planner, we have to address both the knowledge engineering problem of how to represent various real-world temporal constraints in a planning domain definition language, and the system design problem of how to realize the interface between the AI planner and the service consumer. In this paper, we introduce an example scenario and a set of typical temporal constraints for a household service robot, and then present how to represent them in the standard planning domain definition language. We also explain how to implement a service agent based on an AI planner in order to develop and provide new services efficiently.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.51-57
• /
• 2021

Quite a few elementary school teachers began to utilize AI technology in order to provide students with customized, intelligent information services in recent years. However, learning principles of AI may be as important as utilizing AI in everyday life because understanding principles of AI can empower them to buildup adaptability to changes in highly technological world. In the paper, 'Linear Regression Algorithm' is selected for teaching AI-based prediction system to solve real world problems suitable for elementary students. A simulation program written in Scratch was developed so that students can find a solution of linear regression model using the program. The paper shows that students have learned analyzing data as well as comparing the accuracy of the prediction model. Also, they have shown the ability to solve real world problems by finding suitable prediction models.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.287-294
• /
• 2007

Many classification algorithms for real world data suffer from a data class imbalance problem. To solve this problem, various methods have been proposed such as altering the training balance and designing better sampling strategies. The previous methods are not satisfy in the distribution of the input data and the constraint. In this paper, we propose a focused sampling method which is more superior than previous methods. To solve the problem, we must select some useful data set from all training sets. To get useful data set, the proposed method devide the region according to scores which are computed based on the distribution of SOM over the input data. The scores are sorted in ascending order. They represent the distribution or the input data, which may in turn represent the characteristics or the whole data. A new training dataset is obtained by eliminating unuseful data which are located in the region between an upper bound and a lower bound. The proposed method gives a better or at least similar performance compare to classification accuracy of previous approaches. Besides, it also gives several benefits : ratio reduction of class imbalance; size reduction of training sets; prevention of over-fitting. The proposed method has been tested with kNN classifier. An experimental result in ecoli data set shows that this method achieves the precision up to 2.27 times than the other methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1304-1311
• /
• 2003

Target tracking in a real world situation is difficult problem because of continuous variations in images, huge amounts of data, and high processing speed demands. The problem becomes even harder in the case of sea background. This paper presents an initial study of neural network based method for target detection and tracking in cluttering environment. The approach uses a combination of differential motion analysis, Kohonen self-organizing network and region growing method. The network is capable of detecting the mass-centers of moving objects within one frame. The history of neurons positions in the sequential frames approximates the traces of the targets. The experiments done with the network in simulated environment showed promising results.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.37 no.3
• /
• pp.247-256
• /
• 2011

Existing organic UV protection materials seem to be problematic due to their penetration and irritation to skin. Inorganic UV protection materials are also at issue for safety of their nano-type transformation. Therefore, the recent studies of UV protection materials have been focused not only on the effectiveness but also on their safety. One of the UV protection materials in study which have higher safety is the organic-inorganic conjugation type UV protection material. Previously, we have reported the manufacturing process, physical property and UV protection efficiency of methoxychinnamidoprophy poloysilsesquixan as a new cross-linked polymer type UV protection material. In this study, we have evaluated the effect of the methoxychinnamidoprophy poloysilsesquixan on embryo-fetal development in SD rats. This study is expected to show some definite information related to the effect on pregnancy or embryo-fetal abnormality in case of the clinical exposure of the methoxychinnamidoprophy poloysilsesquixan.

• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.41-51
• /
• 2018

Recently, in the field of video surveillance, deep learning based learning method is applied to intelligent video surveillance system, and various events such as crime, fire, and abnormal phenomenon can be robustly detected. However, since occlusion occurs due to the loss of 3d information generated by projecting the 3d real-world in 2d image, it is need to consider the occlusion problem in order to accurately detect the object and to estimate the pose. Therefore, in this paper, we detect moving objects by solving the occlusion problem of object detection process by adding depth information to existing RGB information. Then, using the convolution neural network in the detected region, the positions of the 14 keypoints of the human joint region can be predicted. Finally, in order to solve the self-occlusion problem occurring in the pose estimation process, the method for 3d human pose estimation is described by extending the range of estimation to the 3d space using the predicted result of 2d keypoint and the deep neural network. In the future, the result of 2d and 3d pose estimation of this research can be used as easy data for future human behavior recognition and contribute to the development of industrial technology.

• The Journal of Korean Association of Computer Education
• /
• v.5 no.3
• /
• pp.89-106
• /
• 2002

One of the key success factors for Computer Supported Collaborative Learning(CSCL) environments relies on collaborative reflection. Reflection refers to the active, intellectual thinking for monitoring one's own learning process and continuous internal activities of exploring oneself for new learning experiences. Also, reflective activities are closely related not only with the individual aspect of internal exploration but also with the social aspect of learner-learner interaction. This paper suggests four essential macro-level design strategies such as (1)facilitating collaborative awareness, (2)making thinking visualization, (3)negotiation-mediated knowledge construction, (4)providing metacognitive awareness cues or Questions for scaffolding collaborative reflection in the CSCL environments and made some implications for key functional features for the design and development of system components for CSCL.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.672-678
• /
• 2008

Entities in reality have direct relationships between each other. They also have new and indirect relationships through such direct relationships. An ontology gives explicit meaning of such relationships. Thus, we can discover new relationships between entities based on an ontology. Such new relationships are applied in indentifying new communities or constructing social networks. Measuring for the degree of relationships is an important problem in such domains. This paper proposes a measurement for the degree of relationships between entities based on an ontology. Most of researches are based on connected paths between entities. However, there are meaningful relationships between two entities through the schema in an ontology even through there are no connected paths between the entities. The proposed method measures for the degree of relationships between two entities not based on connected paths, but also relationships through the schema. The experiment result shows that the relationships through the schema are meaningful to measure the degree of relationships between entities.