• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.285-288
• /
• 2006

Most previous studies on improving the effectiveness of CBR have focused on the similarity function aspect or optimization of case features and their weights. However, according to some of the prior research, finding the optimal k parameter for the k-nearest neighbor (k-NN) is also crucial for improving the performance of the CBR system. Nonetheless, there have been few attempts to optimize the number of neighbors, especially using artificial intelligence (AI) techniques. In this study, we introduce a genetic algorithm (GA) to optimize the number of neighbors that combine, as well as the weight of each feature. The new model is applied to the real-world case of a major telecommunication company in Korea in order to build the prediction model for the customer profitability level. Experimental results show that our GA-optimized CBR approach outperforms other AI techniques for this mulriclass classification problem.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.177-183
• /
• 2022

To measure the size and weight of the fish, we developed an automatic fish size measurement system using a deep neural network, where the YOLO (You Only Look Once)v3 model was used. To detect fish, an IP camera with infrared function was installed over the fish pool to acquire image data and used as input data for the deep neural network. Using the bounding box information generated as a result of detecting the fish and the structure for which the actual length is known, the size of the fish can be obtained. A GUI (Graphical User Interface) program was implemented using LabVIEW and RTSP (Real-Time Streaming protocol). The automatic fish size measurement system shows the results and stores them in a database for future work.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.769-779
• /
• 2022

Spectral clustering has become a typical and efficient clustering method used in a variety of applications. The critical step of spectral clustering is the similarity measurement, which largely determines the performance of the spectral clustering method. In this paper, we propose a novel spectral clustering algorithm based on the local similarity measure of shared neighbors. This similarity measurement exploits the local density information between data points based on the weight of the shared neighbors in a directed k-nearest neighbor graph with only one parameter k, that is, the number of nearest neighbors. Numerical experiments on synthetic and real-world datasets demonstrate that our proposed algorithm outperforms other existing spectral clustering algorithms in terms of the clustering performance measured via the normalized mutual information, clustering accuracy, and F-measure. As an example, the proposed method can provide an improvement of 15.82% in the clustering performance for the Soybean dataset.

• Journal of Korean Port Research
• /
• v.11 no.1
• /
• pp.75-83
• /
• 1997

In this paper, we codify the objective function that should be optimized by using Genetic Algorithm instead of Heuristic method to solve these problems. So, each bit that constitutes one structure can signify each commodity. Therefore, we can exchange customers without restriction if the traveling distance diminishes among the districts. Furthermore, even though the capacity of a customer's commodities exceeds that of a vehicle, the following vehicle can be allocated. Also, we obtained good result by testing with real data. To be brief, we can effectively allocate innumerable commodities, that have various magnitudes and weight, into restricted capacity of the vehicle by applying genetic algorithm that is useful in solving the problems of optimization.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.8 no.2
• /
• pp.123-136
• /
• 2004

Terzaghi's one-dimensional consolidation theory has some important assumption, which can't be applicable to predict the behavior of soft clay ground. Especially, predictions using infinitesimal strain and linear material function related with permeability can give rise to mistake in comparison with the result of real behavior in site. For this reason, Gibson et al. established a rigorous formulation for the one-dimensional nonlinear finite strain consolidation theory, which can consider non-linearity of material function. But it is difficult to apply this theory to predict the behavior of common soft clay ground with vertical drain. In this study, consolidation model which can consider the vertical and horizontal flow of a fully saturated clay layer, self-weight of soil and nonlinear characteristics of compressibility and permeability are derived. Numerical analysis scheme, which can be applied to consolidation analysis by derived consolidation model in this study was developed. The characteristics of material function were examined using laboratory testing such as standard consolidation test, Rowe-cell test and modified consolidation test.

• Journal of Korean Society of Steel Construction
• /
• v.18 no.2
• /
• pp.213-223
• /
• 2006

Conventional truss optimization approaches, while often sophisticated and computationally intensive, have been applied to simple, minimum weight-cost models. These approaches do not perform well when applied to real-world trusses, which have costmodels that are complex and which often involve multiple objectives. Thus, this paper describes the optimization strategies that a clustering technique, which identifies members that are likely to have the same product type, uses for the optimal design of truss structures with real- world cost functions that consider the costs on the weight of the truss, the number of products in the design, the number of joints in the structures, and the costs required in the site.At first, the clustering technique is applied to identify the members and to generate a proper initial solution. A simple taboo search technique is then used, which attempts to generate the optimal solution by starting with the solution from the previous technique. For example, the proposed approach is a plied to a typical problem and to a problem similar to relative performances. The results show that this algorithm generates not only better-quality solutions but also more efficient ones

• Journal of Navigation and Port Research
• /
• v.32 no.3
• /
• pp.223-228
• /
• 2008

As most of small fishing boats made of FRP have been constructed by experience in Korea, some structural safety problems have been occurred occasionally. To improve the structural strength and reduce the costs for construction and operation, optimum design for small fishing boat was carried out in this study. The weight of fishing boat and the main dimensions of structural members are chosen as objective function and design variables, respectively. By the combination of global and local search methods, a hybrid optimization algorithm was developed to escape the local minima and reduce CPU time in analysis procedure, and finite element analysis was performed to determine the constraint parameters at each iteration step in optimization loop. Optimization results were compared with the real existing fishing boat, and the effects of optimum design were examined from points of view; structural strength, material cost, etc.

• Journal of Internet Computing and Services
• /
• v.11 no.4
• /
• pp.59-72
• /
• 2010

WIM(Weigh-In-Motion) is the system measuring the weight of the vehicle with a high-speed. In the existing WIM system, vehicle weight is measured based on the constant speed and the error ratio has 10%. However, because of measuring the driving pattern, that is abnormal driving pattern which is like the acceleration and down-shift of the drivers, it has the error ratio which is bigger than the real. In order to it reduces the error ratio of WIM system, the improved WIM system needs to find the abnormal driving pattern. In order to reducing the error ratio of these WIM systems, the improved WIM system can find abnormal driving patterns. In this paper, the improved WIM system which analyzes the abnormality driving pattern influencing on the error ratio of WIM system of an existing and minimizes the error span is designed. The improved WIM system has the multi step loop structure of adding the loop sensor to an existing system. In addition, the measure function defined as an intrinsic is improved and the weight measured by the abnormal driving pattern is amended. The analysis of experiment result improved WIM system can know the fact that the error span reduces by 8% less than in the existing the maximum average sampling error 22.98%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11C
• /
• pp.10-23
• /
• 2001

It is difficult to satisfy the QoS(Quality of Service) guarantee which is required by real-time application services only with the Best-Effort(BE) service adopted in the current Internet. Therefore, worldwide research is being made on the method of QoS provisioning. Among them, the QoS guarantee mechanism using the Diffserv(Differentiated Service) was discussed in this paper. First we analyzed how the DiffServ performance was affected by traffic models. For this, we performed the research for the random, bursts, and self-similar traffic modeling method. We then designed and implemented an OPNET simulator, and performed the simulation 7d performance evaluation for diverse input parameters. Based on the results of performance evaluation, it was confirmed that QoS guarantee is possible for the EF(Expedited Forwarding) class with the DiffServ function under every environments considered and the service separation between EF and BE(Best Effort) classes is also possible. We also analyzed the performance variation and dynamic behavior of DiffServ mechanism based on the resource allocation between E? and BE classes in WFQ(Weighted Fair Queueing).

• The Journal of Internal Korean Medicine
• /
• v.35 no.4
• /
• pp.519-531
• /
• 2014

Objectives: Diabetic nephropathy is the most common cause of end stage renal disease. Transforming growth factor (TGF)-${\beta}1$, type IV collagen, advanced glycation end-products (AGEs), and angiotensin II type 1 receptor (AT1) are the main factors of diabetic nephropathy. We investigated the effects of Prunus on renal function and histopathological changes of diabetic nephropathy rat model induced by unilateral nephrectomy and streptozotocin. Methods: Diabetes was induced in male Sprague-Dawley rats ($290{\pm}10g$) by injecting streptozotocin (55 mg/kg) into the tail vein after unilateral nephrectomy. Rats were divided into 3 groups (n=6): normal, control, and Prunus. After 8 weeks of oral administration of Prunus extract on the Prunus group from 3 days after streptozotocin injection, we checked weight, 24 hrs urine, blood biochemistry and renal tissue to evaluate renal function and histopathological changes by examining parameters including albuminuria, BUN, creatinine, cholesterol, low density lipoprotein (LDL), triglyceride, TGF-${\beta}1$, type IV collagen, AGEs, and AT1. We also measured mRNA expression of TGF-${\beta}1$, type IV collagen, AGEs, and AT1 by Real Time polymerase chain reaction (RT-PCR). Results: Prunus decreased the amount of 24 hrs proteinuria, and inhibited histopathological changes of diabetic nephropathy including the expression and accumulation of TGF-${\beta}1$, type IV collagen and AGEs which could promote development of diabetic nephropathy. Prunus also inhibited mRNA expression of TGF-${\beta}1$, type IV collagen. Conclusions: These findings suggest that Prunus might protect the renal function and inhibit the development of renal injury by regulating factors including TGF-${\beta}1$, type IV collagen, AGEs, except AT1, so Prunus can be used for diabetic patients to prevent the progression of diabetic nephropathy.