• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.540-548
• /
• 2012

The Weapon Target Allocation(WTA) problem is the NP-Complete problem. The WTA problem is that the threatful air targets are assigned by weapon of allies for killing the targets. A good solution of NP-complete problem is heuristic algorithms. Genetic algorithms are commonly used heuristic for global optimization, and it is good solution on the diverse problem domain. But there has been very little research done on the generation of their initial population. The initialization of population is one of the GA step, and it decide to initial value of individuals. In this paper, we propose to the population initialization method to improve a Genetic Algorithm. When it initializes population, the proposed algorithm reflects the characteristics of the WTA problem domain, and inherits the dominant gene. In addition, the search space widely spread in the problem space to find efficiently the good quality solution. In this paper, the proposed algorithm to verify performance examine that an analysis of various properties and the experimental results by analyzing the performance compare to other algorithms. The proposed algorithm compared to the other initialization methods and a general genetic algorithm. As a result, the proposed algorithm showed better performance in WTA problem than the other algorithms. In particular, the proposed algorithm is a good way to apply to the variety of situation WTA problem domain, because the proposed algorithm can be applied flexibly to WTA problem by the adjustment of RMI.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.380-389
• /
• 2007

In Korea, undoubtedly, the cancer is one of the most common reasons of death, and hepatoma is the second highest fatal cancer regardless of the gender only next to the stomach cancer In the middle and prime-aged between 40 and 60 years, the incidence of hepatoma is the highest in the world, and the death rate due to hepatoma is the highest among OECD countries. In this paper, we propose a novel method for automatic identification of hepatoma from a contrast enhanced CT images, which is used in an expert system that helps medical specialists. First, consecutive $40{\sim}50$ contrail enhanced CT images are photographed by every 5mm from the upper part of the chest, and using position information on the rib, we classify the internal area including only internal organs and the external one that consists of the rib, subcutaneous fat layers, and the background from the CT images. Then, the region of the liver is extracted from the classified internal area by using information on the intensity, the distribution of brightness, and using the regions extracted from consecutive images, we restore information on the 5 mm space occurred between the consecutive two slides tty applying a shape-based interpolation method. Lastly, using the characteristics such as the brightness and the morphology, we are able to extract the regions of hepatoma. The expert system based on our method is sufficiently competitive when it is compared with the diagnoses by specialists in the diagnostic radiology.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.12 no.2
• /
• pp.62-65
• /
• 1983

As a new practical method for preserving freshness of fish, partially frozen storage has been reported to be useful in terms of K-value, TBA value, sensory evaluation etc. In order to develop a storage procedure to be used in place of cooled or frozen storage for the preservation of precooked fish food, partial freezing for up to two to three weeks was examined using baked mackerel. The criteria for evaluation were made according to the changes in volatile basic nitrogen (VBN), thiobarbituric acid (TBA) value, viable bacterial number, pH, color difference and sensory evaluation in fish muscle. The changes in TBA value of baked muscle during storage at $-3^{\circ}C$ differed slightly from those obserbed during cooled ($5^{\circ}C$) and frozen storage ($-20^{\circ}C$). Partial frozen storage ($-3^{\circ}C$) was effective in prolong an induction period of lipid oxidation during early storage. VBN of baked muscle tends to increase slowly while pH value was decrease during storage and there was no observed significant differences among three different storage condition. Viable bacterial number of the baked mackerel muscle stored at $-3^{\circ}C$ showed significantly less than that stored at $5^{\circ}C$, and similar to that stored at $-20^{\circ}C$ (the levels of $10^2/g$). Judging from the results of sensory evaluation and experimental data, partial frozen storage at $-3^{\circ}C$ seems to be effective as means of short-period preserving baked mackerel.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.46-54
• /
• 2006

Recently, the important of a personal identification is increasing according to expansion using each on-line commercial transaction and personal ID-card. Although a personal ID-card embedded RFID(Radio Frequency Identification) tag is gradually increased, the way for a person's identification is deficiency. So we need automatic methods. Because RFID tag is vary small storage capacity of memory, it needs effective feature extraction method to store personal biometrics information. We need new recognition method to compare each feature. In this paper, we studied the face verification system using Hippocampal neuron modeling algorithm which can remodel the hippocampal neuron as a principle of a man's brain in engineering, then it can learn the feature vector of the face images very fast. and construct the optimized feature each image. The system is composed of two parts mainly. One is feature extraction using NMF(Non-negative Matrix Factorization) and LDA(Linear Discriminants Analysis) mixture algorithm and the other is hippocampal neuron modeling and recognition simulation experiments confirm the each recognition rate, that are face changes, pose changes and low-level quality image. The results of experiments, we can compare a feature extraction and learning method proposed in this paper of any other methods, and we can confirm that the proposed method is superior to the existing method.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.302-310
• /
• 2020

In this paper, we have implemented the living waste analysis system based on IoT and AI(Artificial Intelligence), and proposed effective waste process and management method. The Jeju location have the strong point to devise a stratagem and estimate waste quantization, rather than others. Especially, we can recognized the amount variation of waste to the residence people compare to the sightseer number, and the good example a specific waste duty. Thus this paper have developed the IoT device for interconnecting the existed CCTV camera, and use the AI algorithm to analysis the waste image. By using these decision of image analysis, we can inform their deal commend and a decided information to the map of the waste cars. In order to evaluate the performance of IoT, we have experimented the electromagnetic compatibility under a national official authorization KN-32, KN61000-4-2~6, and obtained the stable experimental results. In the further experimental results, we can applicable for an data structure for precise definition command by using the simulated several waste image with artificial intelligence algorithm.

• Journal of the Korean Geographical Society
• /
• v.48 no.6
• /
• pp.803-818
• /
• 2013

In this study, a total of 80 rock formations in the romantic road(Nangmangado) were investigated and analyzed and the results are as follows. The area in where the rock formations landscape is seen the most is Yangyang(43 formations), and the formations are most densely concentrated in Jukdo beach when seen from the site group. The most observed landform is weathering landform(61%) and the rest is comprised of coastal landform(24%) and structural landform(15%). For weathering landform, Tafoni takes up the largest portion (33%) and is followed by Corestone(27%), Tor(22%), Gnamma(10%), Groove(4%) and Exfoliation(4%). Considering academic value, rarity and accessibility overall, the 35 landforms are expected to have high utility value as tourism resources and topography filed course. And out of these 35 landforms, 11 are concentrated in Dongsan beach in Yangyang. Therefore, it seems worthy to consider developing Dongsan beach under the name of "Dongsan Coast Rock Park(Tentative Name)" to be actively utilized as tourism resources. The landforms which are evaluated as highly valuable for geomorphology filed course are a total of 16 areas including Fan rock and Op rock formations. In these areas, typical weathering landforms are concentrated in one spot and two or three other types of landform can also be additionally observed, allowing the place to be highly efficient for field education.

• Journal of the Korean Geotechnical Society
• /
• v.32 no.11
• /
• pp.61-72
• /
• 2016

For the construction of high-rise structures and the optimized foundation design, the use of the large-diameter PHC pile has increased. Especially, the use of the 600 mm diameter PHC pile has significantly increased. In this study, for the evaluation of the suitability of the current design practice, the 46 dynamic pile load tests, which were carried out in the 600 mm diameter preboring PHC pile, are analyzed. The end bearing capacity is obtained from the end of initial driving test and the shaft capacity is estimated from the restrike test. The allowable capacities estimated by the dynamic load test are compared with those based on the current design practice. The analyses show that the allowable end bearing capacity evaluated by the dynamic pile load test is greater than the design practice in most piles. The allowable shaft capacity, however, is smaller than the design practice in many piles. The higher end bearing capacity and the smaller shaft capacity may result from the improvement of the drilling equipment and the increase in the penetration depth. Thus, the portion of the end bearing capacity in the total capacity increases.

• Korea Journal of Hospital Management
• /
• v.16 no.4
• /
• pp.35-66
• /
• 2011

This study analyzed efficiency by utilizing DEA analytical technique centering on materials for 2009 of 20 major university hospitals in capital area. Input variables were utilized professor & full-time doctor, resident, nurse & number of bed hospitals. Output variables were analyzed by dividing number of annual outpatients & number of annual inpatients, and annually total outpatient profit & inpatient profit into a model of the standard for number of patients and the standard for medical profit. DEA analysis was elicited efficiency score by applying CCR, BCC, BFG, scale profit, and SE model. Through t-test after eliciting efficiency score, the implications were suggested by comparing efficiency between DMU in Seoul and DMU in capital area, by comparing between high-class general hospitals and general hospitals, and by comparing between high-class general hospitals in Seoul and 5 big hospitals. As a result of analysis, the major university hospitals in capital area showed high efficiency as a whole close to "1," but indicated low efficiency relatively in CCR field. Thus, the expansion in scale within capital area was indicated to reach the limit. Second, in a model of analyzing the standard for number of patients, the medical institutions, which are being operated efficiently, were indicated to be 10 DMUs. In the standard for medical profit, 12 DMUs were analyzed to be operated efficiently. Third, the efficiency in general hospital was higher than high-class general hospital. Thus, the efficiency of operation was indicated to be more important than scale. Also, large high-class hospitals(big 5) where are located in downtown Seoul showed the higher efficiency than other general high-class general hospitals, but were indicating very low efficiency in some DMUs. Fourth, as a result of generalizing and evaluating the number of patients and the medical profit, the efficient DMU was indicated to be more when analyzing on the basis of medical profit than the standard for number of patients. Thus, major university hospitals in capital area were indicated to make more effort for section in medical profit. Based on the analytical results of efficiency, a strategy for reinforcing efficiency in inefficient DMU was indicated to be needed a strategy of creating customers for promoting number of patients and a strategy for making operation efficient for increasing profitability.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.550-554
• /
• 2002

In this paper, we design the CORBA-based Mobile-Agent Model (CMAM) which has the capability of the efficient work processing in distributed environment through sensing network traffic and searching the optimal path for migration nodes of mobile agent. In case existing mobile agent model is given various works from user, the network overhead and traffic are increased by increasing of execution module size. Also, if it happens a large quantity of traffics due to migration of nodes according to appointment of the passive host(node) muting schedule by user, it needs much cost for node search time by traffic. Therefore, in this paper, we design a new mobile agent model that assures the reliability of agent's migration through dynamic act on the specific situation according to appointment of the active routing schedule and can minimize agent's work processing time through optimal path search. The proposed model assigns routing schedule of the migration nodes actively using an extended MAFFinder. Also, for decreasing overhead of network by agent's size, it separated by mobile agent including oかy agent calling module and push agent with work executing module based on distributed object type of CORBA. Also, it can reduce the required time for round works of mobile agent through the optimal path search of migration nodes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.1023-1031
• /
• 2010

With recent advances in hardware and wireless communication techniques, wireless multimedia sensor network which collects multimedia data through wireless sensor network has started to receive a lot of attentions from many researchers. Wireless multimedia sensor network requires a research of efficient compression and transmission to process the multimedia data which has large size, in the wireless sensor network that has very low network bandwidth. In this paper, we propose PIT protocol for the transmission based on the priority that classified by the DPCM compression. The PIT protocol sets different priority to the each subbands which are divided by the wavelet transform. The PIT protocol transmits the data with higher priority to guarantee the high image quality. The PIT protocol uses the characteristic of wavelet transform that the transformed image is very insensible to the data loss. In PIT protocol, each subbands of wavelet transformed image has fair weight in the compressed image to utilize the prioriy based transmission. The experiment results show that the PIT protocol improves the quality of image in spite of data loss.