• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1149-1155
• /
• 2012

In this paper, we propose cause diagnosis method of semiconductor defects from semiconductor industrial images. Our method constructs feature database (DB) of defect images. Then, defect and input images are subdivided by uniform block. And the block similarity is measured using histogram kai-square distance after color histogram calculation. Then, searched blocks in each image are merged into connected objects using clustering. Finally, the most similar defect image from feature DB is searched with the defect cause by measuring cluster similarity based on features of each cluster. Our method was validated by calculating the search accuracy of n output images having high similarity. With n = 1, 2, 3, the search accuracy was measured to be 100% regardless of defect categories. Our method could be used for the industrial applications.

• Journal of KIISE
• /
• v.45 no.3
• /
• pp.224-233
• /
• 2018

Recently, there are many of studies on SWRL reasoning engine based on user-defined rules in a distributed environment using a large-scale ontology. Unlike the schema based axiom rules, efficient inference orders cannot be defined in SWRL rules. There is also a large volumet of network shuffled data produced by unnecessary iterative processes. To solve these problems, in this study, we propose a method that uses Map-Reduce algorithm and distributed in-memory framework to deduce multiple rules simultaneously and minimizes the volume data shuffling occurring between distributed machines in the cluster. For the experiment, we use WiseKB ontology composed of 200 million triples and 36 user-defined rules. We found that the proposed reasoner makes inferences in 16 minutes and is 2.7 times faster than previous reasoning systems that used LUBM benchmark dataset.

• Journal of the Korean Society for information Management
• /
• v.25 no.4
• /
• pp.227-243
• /
• 2008

This study investigates an event detection method with the aim of generating an event-focused news summary from a set of news articles on a certain event using a multi-document summarization technique. The event detection method first classifies news articles into the event related topic categories by employing a SVM classifier and then creates event clusters containing news articles on an event by a modified single pass clustering algorithm. The clustering algorithm applies a time penalty function as well as cluster partitioning to enhance the clustering performance. It was found that the event detection method proposed in this study showed a satisfactory performance in terms of both the F-measure and the detection cost.

• Journal of Digital Convergence
• /
• v.12 no.11
• /
• pp.379-386
• /
• 2014

In this paper, the processing speed of Grabcut algorithm in order to efficiently improve the GPU (Graphics Processing Unit) for processing the data from the method. Grabcut algorithm has excellent performance object detection algorithm. Grabcut existing algorithms to split the foreground area and the background area, and then background and foreground K-cluster is assigned a cluster. And assigned to gradually improve the results, until the process is repeated. But Drawback of Grabcut algorithm is the time consumption caused by the repetition of clustering. Thus GPGPU (General-Purpose computing on Graphics Processing Unit) using the repeated operations in parallel by processing Grabcut algorithm to effectively improve the processing speed of the method. We proposed method of execution time of the algorithm reduced the average of about 95.58%.

• Progress in Medical Physics
• /
• v.14 no.2
• /
• pp.141-148
• /
• 2003

The purpose of this study is to evaluate the distribution of clusters and blood flow rate in ADHD SPECT brain blood flow images of children using statistical parametric mapping (SPM99). We studied 64 ADHD children (4-15 y, $8.03{\pm}2.57$ y. male/female:52/12) and compared them with a control group of 12 children (6-l7 y, $9.42{\pm}3.37$ y, male/female:8/4). We injected blood flow tracer $^{99m}Tc$-ethylcysteinate dimer (ECD) as a rCBF agent and took blood flow images after 30 min. by SPECT camera. In the case of hyperperfusion of rCBF in the ADHD group, we found 3 clusters clearly separated at the cingulate gyrus, Rt.cerebral occipital lobe and Lt.cerebellar post. lobe, on probability level 0.05 (P<0.05). Thirty-six ADHD patients with average hyperfusion rates between 18.72-19.30% in each cluster had more increase in blood flow than the average perfusion rate at the Rt. cerebral occipital lobe. These levels were influenced by P-value. In the case of hypoperfusion in the ADHD children, 4 decreased clusters on Lt. and Rt. cerebral frontal lobe, Lt. cerebral claustrum and Rt. cerebral, sup. temporal gyrus at P<0.01 can be seen. The average hypoperfusion rates for the ADHD children were 18.41-18.69% in each cluster, which showed more hypopefusion than the average perfusion rate at the Lt. Cerebrum inf. Frontal gyrus. The perfusion rates and the number of patients were not affected by P-value. The result of this study shows significant hyperpefusion clusters at the probability level of P:0.05 and hypoperfusion clusters at P:0.01. The number of ADHD patients in each clusters and the perfusion rate were not affected by P-value.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.181-187
• /
• 2020

In this paper, we proposed a register allocation algorithm and resource allocation algorithm in the high level synthesis process for the SoC design synthesis system of high performance vehicles We have analyzed to the operator characteristics and structure of datapath in the most important high-level synthesis. We also introduced the concept of virtual operator for the scheduling of multi-cycle operations. Thus, we demonstrated the complexity to implement a multi-cycle operation of the operator, regardless of the type of operation that can be applied for commonly use in the resources allocation algorithm. The algorithm assigns the functional operators so that the number of connecting signal lines which are repeatedly used between the operators would be minimum. This algorithm provides regional graphs with priority depending on connected structure when the registers are allocated. The registers with connecting structure are allocated to the maximum cluster which is generated by the minimum cluster partition algorithm. Also, it minimize the connecting structure by removing the duplicate inputs for the multiplexor in connecting structure and arranging the inputs for the multiplexor which is connected to the operators. In order to evaluate the scheduling performance of the described algorithm, we demonstrate the utility of the proposed algorithm by executing scheduling on the fifth digital wave filter, a standard bench mark model.

• Journal of Broadcast Engineering
• /
• v.21 no.3
• /
• pp.425-435
• /
• 2016

In this paper, we propose a classification model by analyzing raw material images recorded using a color CCD camera to automatically classify good and defective agricultural products such as rice, coffee, and green tea, and raw materials. The current classifying agricultural products mainly depends on visual selection by skilled laborers. However, classification ability may drop owing to repeated labor for a long period of time. To resolve the problems of existing human dependant commercial products, we propose a vision based automatic raw material classification combining mean shift clustering and stepwise region merging algorithm. In this paper, the image is divided into N cluster regions by applying the mean-shift clustering algorithm to the foreground map image. Second, the representative regions among the N cluster regions are selected and stepwise region-merging method is applied to integrate similar cluster regions by comparing both color and positional proximity to neighboring regions. The merged raw material objects thereby are expressed in a 2D color distribution of RG, GB, and BR. Third, a threshold is used to detect good and defective products based on color distribution ellipse for merged material objects. From the results of carrying out an experiment with diverse raw material images using the proposed method, less artificial manipulation by the user is required compared to existing clustering and commercial methods, and classification accuracy on raw materials is improved.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.1 s.307
• /
• pp.53-66
• /
• 2006

This paper proposes the combined image retrieval system that gives the same relevance as exhaustive search method while its performance can be considerably improved. This system is combined with two different retrieval methods and each gives the same results that full exhaustive search method does. Both of them are two-stage method. One uses condensation of feature vectors, and the other uses binary-tree clustering. These two methods extract the candidate images that always include correct answers at the first stage, and then filter out the incorrect images at the second stage. Inasmuch as these methods use equal algorithm, they can get the same result as full exhaustive search. The first method condenses the dimension of feature vectors, and it uses these condensed feature vectors to compute similarity of query and images in database. It can be found that there is an optimal condensation ratio which minimizes the overall retrieval time. The optimal ratio is applied to first stage of this method. Binary-tree clustering method, searching with recursive 2-means clustering, classifies each cluster dynamically with the same radius. For preserving relevance, its range of query has to be compensated at first stage. After candidate clusters were selected, final results are retrieved by computing similarities again at second stage. The proposed method is combined with above two methods. Because they are not dependent on each other, combined retrieval system can make a remarkable progress in performance.

• The KIPS Transactions:PartD
• /
• v.14D no.7
• /
• pp.733-742
• /
• 2007

A data stream is a massive unbounded sequence of data elements continuously generated at a rapid rate. Due to this reason, memory usage for data stream analysis should be confined finitely although new data elements are continuously generated in a data stream. To satisfy this requirement, data stream processing sacrifices the correctness of its analysis result by allowing some errors. The old distribution statistics are diminished by a predefined decay rate as time goes by, so that the effect of the obsolete information on the current result of clustering can be eliminated without maintaining any data element physically. This paper proposes a grid based clustering algorithm for a data stream. Given a set of initial grid cells, the dense range of a grid cell is recursively partitioned into a smaller cell based on the distribution statistics of data elements by a top down manner until the smallest cell, called a unit cell, is identified. Since only the distribution statistics of data elements are maintained by dynamically partitioned grid cells, the clusters of a data stream can be effectively found without maintaining the data elements physically. Furthermore, the memory usage of the proposed algorithm is adjusted adaptively to the size of confined memory space by flexibly resizing the size of a unit cell. As a result, the confined memory space can be fully utilized to generate the result of clustering as accurately as possible. The proposed algorithm is analyzed by a series of experiments to identify its various characteristics

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.7
• /
• pp.760-764
• /
• 2015

Wireless sensors, installed on machinery, and Time Division Multiple Access (TDMA) transmission make an ideal system for monitoring machine conditions in industrial plants because there is no need for electronic wiring. However, there has not yet been a successful field application of such a system, capable of continuously transmitting data at sample rates greater than 100 Hz. In this research, a TDMA network protocol capable of acquiring data from multiple sensors at sample rates greater than 100 Hz was developed for field application. The protocol was implemented in a single cluster-star topology network, and the system was evaluated based on the node number and transmission distance. Network simulator 2 (ns-2) was used for a real field simulation. Non-TDMA and TDMA protocol cases were compared using four sensor nodes. In the cases of 20-s and 40-s transmission times, there was little difference between the reception rates of the non-TDMA and TDMA systems. However, the difference was much greater when using a 60-s transmission time.