• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.11-19
• /
• 2014

In this paper, we design an intelligent agent system with the data mining module and information fusion module as the core components of the system and investigate the possibility for the medical expert system. In the data mining module, fuzzy neural network, OFUN-NET analyzes multi-view data and produces fuzzy cluster knowledge base. In the information fusion module and application module, they serve the diagnosis result with possibility degree and useful information for diagnosis, such as uncertainty decision status or detection of asymmetry. We also present the experiment results on the BI-RADS-based feature data set selected form DDSM benchmark database. They show higher classification accuracy than conventional methods and the feasibility of the system as a computer aided diagnosis system.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.5
• /
• pp.82-89
• /
• 1993

In this paper, we proposed the autonomous algorithm of pseudo-exhaustive testing for the multi-level combinational logic circuits. For the processing of shared-circuit that existed in each cone-circuit when it backtracked the path from PO to PI of CUT at the conventional verification testing, the dependent relation of PI-P0 is presented by a dependence matrix so it easily partitioned the sub-circuits for the pseudo-exhaustive testing. The test pattern of sub-circuit's C-inputs is generated using a binary counter and the test pattern of I-inputs is synthesized using a singular cover and consistency operation. Thus, according to the test patterns presented with the recipe cube, the number of test pattrens are reduced and it is possible to test concurrently each other subcircuits. The proposed algorithm treated CUT's net-list to the source file and was batch processed from the sub-circuit partitioning to the test pattern generation. It is shown that the range of reduced ration of generated pseudo-exhaustive test pattern exhibits from 85.4% to 95.8% when the average PI-dependency of ISACS bench mark circuits is 69.4%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.201-202
• /
• 2018

In this paper, a dog breed image provided by Dataset of existing ImageNet and Oxford-IIIT Pet Image is combined with a dog breed image obtained through data mining on Internet and a random-label is added. this paper introduces to recognize 122 classes of dog breeds and 1 class that is not dog breeds. The recognition rate of dog breeds using both conventional DB and collection DB was improved 1.5% over Top-1 compared to recognition rate of dog breeds using only existing DB. The image recognition rate about non-dog image, was 93% recognition rate in case of 10000 random DBs.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.165-172
• /
• 2009

According to the American Cancer Society, breast cancer is the second largest cause of cancer deaths and most frequently diagnosed cancer in women. The currently most popular method for early detection of breast cancer is the digital mammography. A mass or calcification lesion has been known as the most important clue for the diagnosis. In this paper, we propose a diagnosis approach based on fuzzy cluster knowledge base. We combine different two sources of feature data in duel OFUN-NET and produce the diagnosis result with possibility degree. We also present the experimental results on the dataset of mass and calcification lesions extracted from the public real world mammogram database DDSM. These results show higher classification accuracy than conventional methods and the feasibility as a decision supporting tool for diagnosis of digital mammogram.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.173-179
• /
• 1998

This paper proposes a new call admission control scheme utilizing an inverse fuzzy vector quantizer(IFVQ) and neural net, which combines benefits of IFVQ and flexibilities of FCM(Fuzzy-C-Menas) arithmatics, to decide whether a requested call that is not trained in learning phase to be connected or not. The system generates the estimated traffic pattern of the cell stream of a new call, using feasible/infeasible patterns in codebook, fuzzy membership values that represent the degree to which each pattern of codebook matches input pattern, and FCM arithmatics. The input to the NN is the vector consisted of traffic parameters which is the means and variances of the number of cells arriving inthe interval. After training(using error back propagation algorithm), when the NN is used for decision making, the decision as to whether to accept or reject a new call depends on whether the output is greater or less then decision threshold(+0.5). This method is a new technique for call admi sion control using the membership values as traffic parameter which declared to CAC at the call set up stage, and is valid for a very general traffic model in which the calls of a stream can belong to an unlimited number of traffic classes. Through the simmulation. it is founded the performance of the suggested method outforms compared to the conventional NN method.

• Journal of information and communication convergence engineering
• /
• v.11 no.1
• /
• pp.1-6
• /
• 2013

Suppressing or mitigating signal distortion due to group velocity dispersion and optical Kerr effects is necessary in ultra-high speed and long-haul wavelength division multiplexing (WDM) transmission systems. Dispersion management (DM), optical phase conjugation (OPC), and the combination of these two are promising techniques to compensate for signal distortion. In this paper, to implement a flexible optical WDM network, a new optical link configuration with a randomly distributed single-mode fiber (SMF) length and fixed residual dispersion per span in the combination of DM and OPC is proposed and investigated. The simulation results show that the best net residual dispersion (NRD) in the proposed optical links is +10 ps/nm, which is independent of pre- and postcompensation. The effective launch power of the WDM channel is increased more in the optical links with NRD = +10 ps/nm controlled by only precompensation. Furthermore, the system performance difference between the proposed optical link configuration with the best NRD and the conventional optical link with uniform distribution of the SMF length had little significance. Consequently, it is confirmed that the proposed optical link configuration with the best NRD is effective and useful for implementing a reconfigurable long-haul WDM network.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.416-422
• /
• 2021

Due to the large differences in human activity within classes, the large similarity between classes, and the problems of visual angle and occlusion, it is difficult to extract features manually, and the detection rate of human behavior is low. In order to better solve these problems, an improved Faster R-CNN-based detection algorithm is proposed in this paper. It achieves multi-object recognition and localization through a second-order detection network, and replaces the original feature extraction module with Dense-Net, which can fuse multi-level feature information, increase network depth and avoid disappearance of network gradients. Meanwhile, the proposal merging strategy is improved with Soft-NMS, where an attenuation function is designed to replace the conventional NMS algorithm, thereby avoiding missed detection of adjacent or overlapping objects, and enhancing the network detection accuracy under multiple objects. During the experiment, the improved Faster R-CNN method in this article has 84.7% target detection result, which is improved compared to other methods, which proves that the target recognition method has significant advantages and potential.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.252-255
• /
• 2020

Unsupervised deep learning methods have shown impressive results for the challenging monocular depth estimation task, a field of study that has gained attention in recent years. A common approach for this task is to train a deep convolutional neural network (DCNN) via an image synthesis sub-task, where additional views are utilized during training to minimize a photometric reconstruction error. Previous unsupervised depth estimation networks are trained within a fixed depth estimation range, irrespective of its possible range for a given image, leading to suboptimal estimates. To overcome this suboptimal limitation, we first propose an unsupervised adaptive depth estimation method guided by minimum and maximum (min-max) depth priors for a given input image. The incorporation of min-max depth priors can drastically reduce the depth estimation complexity and produce depth estimates with higher accuracy. Moreover, we propose a novel network architecture for adaptive depth estimation, called the AdaMM-DepthNet, which adopts the min-max depth estimation in its front side. Intensive experimental results demonstrate that the adaptive depth estimation can significantly boost up the accuracy with a fewer number of parameters over the conventional approaches with a fixed minimum and maximum depth range.

• Journal of KIISE:Software and Applications
• /
• v.31 no.8
• /
• pp.1101-1112
• /
• 2004

In this paper, we propose a Web page weighting scheme using the user preference in each sense of query word to improve the performance of Web search. Generally search engines assign weights to a web page by using relevancy only, which is obtained by comparing the query word and the words in a web page. In the information retrieval from huge data such as the Web, simple word comparison cannot distinguish important documents because there exist too many documents with similar relevancy In this paper we implement a WordNet-based user interface that helps to distinguish different senses of query word, and constructed a search engine in which the implicit evaluations by multiple users are reflected in ranking by accumulating the number of clicks. In accumulating click counts, they are stored separately according to senses, so that more accurate search is possible. The experimental results with several keywords show that the precision of proposed system is improved compared to conventional search engines.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.2
• /
• pp.35-41
• /
• 1993

The height differences in Mean Sea Level is an important factor in geodetic leveling net, because MSL is the reference datum for height. Geodesists and Oceanographers agree on the height differences in MSL in the east-west direction, but they disagree almost always on the north-south slope, each suspecting systematic errors in the leveling methods of the others. A promising method for determining this slope is comparison of MSL at the tidal station connected by geodetic leveling. The slopes of the sea surface along the coast of Korean Peninsular is estimated from conventional local MSL at the tidal station and bench mark height of first order leveling net in Korea. As a reference level surface, MSL at Inchon is chosen. The results indicate that sea level rises along coast of Korean Peninsular from south to north about 5.5 cm/latitude. In the east-west direction, sea level along East Sea coast stands about 5 cm higher than that along Yellow Sea coast. These are not invariable but provisional phenomena. It may become certain provided that the exact MSL is estimated.