• Journal of Biomedical Engineering Research
• /
• v.45 no.3
• /
• pp.118-127
• /
• 2024

Commonly deep learning methods for enhancing the quality of medical images use unpaired dataset due to the impracticality of acquiring paired dataset through commercial imaging system. In this paper, we propose a supervised learning method to enhance the quality of ultrasound images. The U-net model is designed by incorporating a divide-and-conquer approach that divides and processes an image into four parts to overcome data shortage and shorten the learning time. The proposed model is trained using paired dataset consisting of 828 pairs of low-quality and high-quality images with a resolution of 512x512 pixels obtained by varying the number of channels for the same subject. Out of a total of 828 pairs of images, 684 pairs are used as the training dataset, while the remaining 144 pairs served as the test dataset. In the test results, the average Mean Squared Error (MSE) was reduced from 87.6884 in the low-quality images to 45.5108 in the restored images. Additionally, the average Peak Signal-to-Noise Ratio (PSNR) was improved from 28.7550 to 31.8063, and the average Structural Similarity Index (SSIM) was increased from 0.4755 to 0.8511, demonstrating significant enhancements in image quality.

• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.177-188
• /
• 2022

The support vector machine (SVM) has been successfully applied to various classification areas with a high level of classification accuracy. However, it is infeasible to use the SVM in analyzing massive data because of its significant computational problems. When analyzing imbalanced data with different class sizes, furthermore, the classification accuracy of SVM in minority class may drop significantly because its classifier could be biased toward the majority class. To overcome such a problem, we propose the DOC-SVM method, which uses divide-oversampling and conquers techniques. The proposed DOC-SVM divides the majority class into a few subsets and applies an oversampling technique to the minority class in order to produce the balanced subsets. And then the DOC-SVM obtains the final classifier by aggregating all SVM classifiers obtained from the balanced subsets. Simulation studies are presented to demonstrate the satisfactory performance of the proposed method.

• ETRI Journal
• /
• v.35 no.5
• /
• pp.767-774
• /
• 2013

In this paper, a novel parallel Viterbi decoding scheme is proposed to decrease the decoding latency and power consumption for the software-defined radio (SDR) system. It implements a divide-and-conquer approach by first dividing a block into a series of subblocks, then performing independent Viterbi decoding for each subsequence, and finally merging the surviving subpaths into the final path. Moreover, a network-on-chip-based SDR platform is used to evaluate the performance of the proposed parallel Viterbi decoding scheme. The experiment results show that our scheme can speed up the Viterbi decoding process without increasing the BER, and it performs better than the current state-of-the-art methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.6
• /
• pp.863-870
• /
• 1993

A new methodology of multimedia data composition generated SRT(Synchronization Relation Tree) dynamically after user composing multimedia date by using high level user interface, and processes message passing protocols to adjust multimedia data temporal composition. In this paperl we propose SRT generating algorithm which transfer user defined timeline diagram to SRT dynamically. SRT generating algorithm is to use divide and conquer methodology and recurvise programming. And prove that it generates and type of multimedia date compositon to SRT.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1994.04a
• /
• pp.691-700
• /
• 1994

Voronoi diagram of a set of geometric entities on a plane such as points, line segments, or arcs is a collection of Voronoi polygons associated with each entity, where Voronoi polygon of an entity is a locus of point which is closer to the associated entity than any other entity. Voronoi diagram is one of the most fundamental geometrical construct and well-known for its theoretical elegance and the wealth of applications. Various geometric problems can be solved with the aid of Voronoi diagram. For example, the maximum tool diameter of a milling cutter for rough cutting in a pocket can be easily found, and the pocketing tool path can be efficiently generated from Voronoi diagram. In PCB design, the design rule checking can be easily done via Voronoi diagram, too. This paper discusses an algorithm to construct Voronoi diagram of a simple polygon which consists of simple curves such as line segments as well as arcs in a plane with O(nlogn) time complexity by employing the divide and conquer scheme.

• Speech Sciences
• /
• v.5 no.1
• /
• pp.89-103
• /
• 1999

It is relatively easy to develop a prototype of a Korean language processing system, but it is very difficult to make it an operational system. In this paper, we survey the current status and methodological issues of the Korean language processing systems such as morphological analyzer, parser and machine translator. In most cases, Korean language processing system easily comes to a dead-end state where its performance can not be improved any more. The reason is that it adopts a general algorithm covering similar problems as a whole because specific low-level problems are not clearly defined and their algorithms are unclear. So, when we add some restrictions to solve an individual linguistic problem, they are also applied to other linguistic phenomena as a side effect. It causes a critical problem that the improvement of the algorithm is very difficult. This paper proposes a 2-step paradigm, a divide-and-conquer method by the functional modularization, a simplification method, and an exception handling technique to develop an operational system that does not fall into a dead-end state.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.665-666
• /
• 2022

Differential evolution is an efficient algorithm for continuous optimization problems. However, applying differential evolution to solve large-scale optimization problems quickly degrades performance and exponentially increases runtime. To overcome this problem, a new cooperative coevolution differential evolution based on Spark (referred to as SparkDECC) is proposed. The divide-and-conquer strategy is used in SparkDECC.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.559-560
• /
• 2021

Differential evolution is an efficient algorithm for solving continuous optimization problems. However, applying differential evolution to solve large-scale optimization problems dramatically degrades performance and exponentially increases runtime. Therefore, a novel cooperative coevolution differential evolution based on Spark (known as SparkDECC) is proposed. The divide-and-conquer strategy is used in SparkDECC.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.197-201
• /
• 2005

When we want to find out the regulatory relationships between genes from gene expression data, dimensionality is one of the big problem. In general, the size of search space in modeling the regulatory relationships grows in O(n$^2$) while the number of genes is increasing. However, hopefully it can be reduced to O(kn) with selected k by applying divide and conquer heuristics which depend on some assumptions about genetic network. In this paper, we approach the modeling problem in divide-and-conquer manner. We applied clustering to make the problem into small sub-problems, then hierarchical model process is applied to those small sub-problems.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.215-222
• /
• 2002

This paper presents a reliable fully automatic labeling system which fits well with languages having well-developed syllables such as in Korean. The ASL System utilize DAC (Divide and Conquer), a control mechanism, based segmentation algorithm to use phonetic and acoustic information with greater efficiency. The segmentation algorithm is to devide speech signals into speechlets which is localized speech signal pieces and to segment each speechlet for speech boundaries. While HMM method has uniform and definite efficiencies, the suggested method gives framework to steadily develope and improve specified acoustic knowledges as a component. Without using statistical method such as HMM, this new method use only phonetic-acoustic information. Therefore, this method has high speed performance, is consistent extending the specific acoustic knowledge component, and can be applied in efficient way. we show experiment result to verify suggested method at the end.