• ETRI Journal
• /
• v.44 no.5
• /
• pp.733-745
• /
• 2022

In software-defined wireless networking (SDWN), the optimal routing technique is one of the effective solutions to improve its performance. This routing technique is done by many different methods, with the most common using integer linear programming problem (ILP), building optimal routing metrics. These methods often only focus on one routing objective, such as minimizing the packet blocking probability, minimizing end-to-end delay (EED), and maximizing network throughput. It is difficult to consider multiple objectives concurrently in a routing algorithm. In this paper, we investigate the application of machine learning to control routing in the SDWN. An intelligent routing algorithm is then proposed based on the machine learning to improve the network performance. The proposed algorithm can optimize multiple routing objectives. Our idea is to combine supervised learning (SL) and reinforcement learning (RL) methods to discover new routes. The SL is used to predict the performance metrics of the links, including EED quality of transmission (QoT), and packet blocking probability (PBP). The routing is done by the RL method. We use the Q-value in the fundamental equation of the RL to store the PBP, which is used for the aim of route selection. Concurrently, the learning rate coefficient is flexibly changed to determine the constraints of routing during learning. These constraints include QoT and EED. Our performance evaluations based on OMNeT++ have shown that the proposed algorithm has significantly improved the network performance in terms of the QoT, EED, packet delivery ratio, and network throughput compared with other well-known routing algorithms.

• Journal of Oriental Neuropsychiatry
• /
• v.20 no.2
• /
• pp.217-227
• /
• 2009

Objectives : Multiple sclerosis (MS) is a demyelination disease of central nervous system, presenting a various neurological disorders depending on the lesion. In the view of oriental medicine, MS is similar to Flaccidity-syndrome(痿證). Also, since MS is a chronic disease which repeats the recurrences with periods of remission of the symptoms in between, it may usually be accompanied by depression. However, the etiology, treatment, and cause of recurrence of MS remain unknown, and also, as the recurrences of MS have been repeated, disease burden has been accumulated, which aggravates disorder. This case of MS experienced depression after the patient had been diagnosed as bad consequence based on the past 5 times recurrences of multiple sclerosis. Methods : We saw the causes as vicera and bowels functional disorder which might have come from a poor diet. Thus, we diagnosed this case as dual deficiency of spleen and kidney(脾腎兩虛), stagnant qi transforming into fire(氣鬱化火) and liver-kidney deficiency(肝腎不足) and treated it with Herb medication, acupuncture therapy, and supportive therapy, making the patient better. Results : We have improved the patient's condition to the time before 5th recurrence. Conclusions : This result suggests that our oriental medical treatments was effective on multiple sclerosis with depression.

• Journal of Korean Traditional Oncology
• /
• v.22 no.2
• /
• pp.13-24
• /
• 2017

Objectives: The purpose of this study is to report the effect of Korean Herbal Medicine (KHM) on a Renal Cell Carcinoma with multiple liver metastases patient. Methods: One renal cell carcinoma with multiple liver metastases patient was treated by KHM in conjunction with targeted anticancer agent (Afinitor). The effect of KHM was measured by scanning with Computed Tomography (CT), Blood Test, Visual Analogue Scale (VAS) and Eastern Cooperative Oncology Group scale. Results: Multiple hepatic tumors were reduced after the treatment during 5 months (Partial Remission, PR). As treatment was performed, complications induced by targeted anticancer agent (Afinitor) were alleviated. Conclusions: This case provides us a possibility that Korean Herbal Medicine offers potential benefits for renal cell carcinoma with multiple liver metastases patient.

• Journal of the military operations research society of Korea
• /
• v.17 no.1
• /
• pp.84-104
• /
• 1991

Up to the present, the evaluation measures in the production and inventory management have been studied under the pre-condition that the costs for major factors(e.g,. cost of carrying inventory, cost of demand shortage) are given easily, although in practice, it is difficult. The case in which multiple participants have a different viewpoints in production and inventory management has not been studied, in spite of its frequent occurrence. This study suggests a production and inventory model with multiple objectives corresponding to major factors and the related interactive algorithm based on the preference structures of participants. The problem can be solved through a weighting vector generated by an interaction with participants. The concept of equity is also used in order to guarantee the reasonable distribution of group utility in determining the individual relative weights of participants. This study includes the reality of the model and the decision process in the production and inventory management.

• Journal of Environmental Health Sciences
• /
• v.38 no.6
• /
• pp.550-560
• /
• 2012

Objectives: QSAR methodology was applied to explain two different sets of acceptable daily intake (ADI) data of 74 pesticides proposed by both the USEPA and WHO in terms of setting guidelines for food and drinking water. Methods: A subset of calculated descriptors was selected from Dragon$^{(R)}$ software. QSARs were then developed utilizing a statistical technique, genetic algorithm-multiple linear regression (GA-MLR). The differences in each specific model in the prediction of the ADI of the pesticides were discussed. Results: The stepwise multiple linear regression analysis resulted in a statistically significant QSAR model with five descriptors. Resultant QSAR models were robust, showing good utility across multiple classes of pesticide compounds. The applicability domain was also defined. The proposed models were robust and satisfactory. Conclusions: The QSAR model could be a feasible and effective tool for predicting ADI and for the comparison of logADIEPA to logADIWHO. The statistical results agree with the fact that USEPA focuses on more subtle endpoints than does WHO.

• The Journal of the Korean dental association
• /
• v.58 no.8
• /
• pp.486-494
• /
• 2020

Objectives: Management of a horizontal root fracture of an anterior teeth is challenging and often requires multiple approaches for improving the functional and esthetic outcomes. This case report describes the treatment and 2-yr follow up of 3 maxillary incisors with horizontal root fracture. Two maxillary central incisors were treated with Mineral Trioxide Aggregate (ProRoot MTA, Dentsply, Tulsa, OK, USA). Left maxillary lateral incisors were treated with endodontic treatment and submerged. During 2-yr of follow-up evaluation, the root-fractured teeth of the present patients were well retained in the arch, showing periodontal healing even after endodontic treatment.

• Journal of Intelligence and Information Systems
• /
• v.2 no.2
• /
• pp.69-83
• /
• 1996

The objective of this research is to develop a knowledge acquisition and refinement method for a multi-objective and multi-decision FMS scheduling problem. A competitive neural network and an inductive learning algorithm are integrated to extract and refine necessary scheduling knowledge from simulation outputs. The obtained scheduling knowledge can assist the FMS operator in real-time to decide multiple decisions simultaneously, while maximally meeting multiple objective desired by the FMS operator. The acquired scheduling knowledge for an FMS scheduling problem is tested by comparing the desired and the simulated values of the multiple objectives. The result show that the knowledge acquisition and refinement method is effective for the multi-objective and multi-decision FMS scheduling problems.

• Korean Journal of Hydrosciences
• /
• v.5
• /
• pp.57-70
• /
• 1994

For the system benefit optimization by considering risk or reliability from a multiple reservoir system using the Monte Carlo Technique, Many stochastically generated inflow series have to be used for the system analysis. In this study, the stochastically generated inflow series for the multiple reservoir system operation are preprocessed according to the considering system objectives and operating time periods. Through this procedure, several representative inflow series which have discrate probability levels and operation horizons are selected among the thousands of generated inflows. Then a deterministic optimization technique is applied to the hydropower energy estimation from the Han River Reservoir System which considers five reservoirs in this study. It took much less computational requirements than using the original Morite Carlo Technique, even though estimated result was almost similar.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.30 no.3
• /
• pp.88-99
• /
• 2019

Objectives: With increasing concerns for the rapidly growing minority population in South Korea, this literature review addressed a range of mental health risks among multiethnic youths (MY) in South Korea by 1) comparing mental health outcomes with those of native-born youths and 2) identifying multiple layers of relevant environmental factors, from family and school relationships to culture. Methods: We reviewed 54 studies that fulfilled specific inclusion criteria. Results: Multiple common risk/protective factors, including family separation, family relationship quality, parental socioeconomic and mental health status, social relationships at school, and cultural acceptance, were noted. Conclusion: In general, empirical evidence indicates that minority youths have relatively heightened risks for emotional and behavioral problems. Future studies must elucidate the complex interplay between multiple risk and protective factors and the long-term adaptation and mental health service utilization of MY.

• Journal of the Korean earth science society
• /
• v.26 no.5
• /
• pp.387-394
• /
• 2005

We have analyzed the science-gifted educational program (year 2002) at the Seoul National University in terms of its educational objectives, scientific models, and cognitive processes in scientific inquiry in order to provide insights into developing and improving science-gifted educational program. We assumed the following items as important factors for teaching scientifically gifted students: higher-order thinking skills involving synthesis domain in the educational objectives, highly abstract nature and complexity in the scientific models, cognitive processes of planning experiments in the cognitive processes in scientific inquiry. According to the analyzed results, the program has the following characteristics: (1) the rates of both higher and lower-order thinking skill domain in the educational objectives are similarly high, but the rate of synthesis domain is relatively low; (2) in the case of the scientific models, the rate of the multiple concepts and/or processes model is relatively low, while the level of the abstractness is relatively on average (3) cognitive processes of authentic scientific inquiry is not thoroughly reflected in the scientific inquiry activities, and very few cognitive processes of planning experiments factor is reflected. Therefore, we conclude in the synthesis domain in the educational objectives, multiple concepts and/or processes model, and cognitive processes of planning experiments should be especially reflected more on the science-gifted educational program in order to serve the needs of scientifically gifted students.