• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.6
• /
• pp.44-51
• /
• 1999

The HMM-Net is a neural network architecture that implements the computation of output probabilities of a hidden Markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria of maximum likehood(ML) and minimization of mean squared error(MMSE) are used for learning HMM-Net classifiers. The criterion MMSE is better than ML when initial learning condition is well established. However Ml is more useful one when the condition is incomplete[3]. Therefore we propose an efficient learning method of HMM-Net classifiers using a hybrid criterion(ML/MMSE). In the method, we begin a learning with ML in order to get a stable start-point. After then, we continue the learning with MMSE to search an optimal or near-optimal solution. Experimental results for the isolated numeric digits from /0/ to /9/, a training and testing time-series pattern set, show that the performance of the proposed method is better than the others in the respects of learning and recognition rates.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.18 no.6
• /
• pp.506-510
• /
• 1985

It is an important work to determine the mesh size of gill net for efficient catch. For investigating the suitable mesh size, the gill net for anchovy, Engraulis japonica was made and operated in the bay of Ulsan in July. 1983. The gill net for anchovy was composed of six different mesh size, 23.1mm (H=0.65), 21.6mm (H=0.65), 20.0mm (H=0.65), 23.1mm (H=0.55), 21.6mm (H=0.55) and 20.0mm(H=0.55). The parts of body caught by the gill net was examined, and the selectivity curves (for reference Ishida's method) with respect to the each mesh size were estimated using the data obtained through the operation of research gill net. The main results of this study are as follows: 1. The number of anchovy whose neck was in net was 148, more than $90\%$ of all, 161 2. The coefficient of relationship between the circumference of neck and the fork length were 0.70. 3. Fork length that the relative fishing efficiency of 23.1 mm mesh size (H=0.55) was maximum value was about 11.1 centimeter.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.169-178
• /
• 2009

There are various approaches that retrieve information from video. However, previous approaches have considered just object information and relationship between objects without story information to retrieve contents. To retrieve exact information at video, we need analyzing approach based on characters and community since these are body of story proceeding. Therefore, this paper describes video information retrieval methodology based on character information. Characters progress story to form relationship through conversations. We can analyze the relationship between characters in a story with the methods that classifies role grades and clusters communities of characters. In this paper, for these, we propose the Character-net and describe how to classify role grades and cluster communities at Character-net. And we show this method to be efficient.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.4
• /
• pp.511-523
• /
• 2023

Research on the integration of unmanned aerial vehicles and deep learning for reinforced concrete damage detection is actively underway. Convolutional neural networks have a high impact on the performance of image classification, detection, and segmentation as backbones. The MobileNet, a pre-trained convolutional neural network, is efficient as a backbone for an unmanned aerial vehicle-based damage detection model because it can achieve sufficient accuracy with low computational complexity. Analyzing vanilla convolutional neural networks and MobileNet under various conditions, MobileNet was evaluated to have a verification accuracy 6.0~9.0% higher than vanilla convolutional neural networks with 15.9~22.9% lower computational complexity. MobileNetV2, MobileNetV3Large and MobileNetV3Small showed almost identical maximum verification accuracy, and the optimal conditions for MobileNet's reinforced concrete damage image feature extraction were analyzed to be the optimizer RMSprop, no dropout, and average pooling. The maximum validation accuracy of 75.49% for 7 types of damage detection based on MobilenetV2 derived in this study can be improved by image accumulation and continuous learning.

• Journal of Korea Multimedia Society
• /
• v.9 no.11
• /
• pp.1503-1514
• /
• 2006

Today, consumers can access Internet from everywhere, therefore most commercial and other organizations provide their services on the Web. As the result, countless Web service systems are already on the Internet and more systems are under construction. Therefore, many researches of verifying that the system to be constructed will not have any deadlock and will run successfully without any problem at the early stage of design have been performed. Several Petri net based verification methods have also been published. However, they have focused on building Petri net models of Web service systems and none of them introduces efficient analysis methods. As a mathematical technique with which we can find the minimum duration time needed to fire all the transitions at least once and coming back to the initial marking in a timed net, the minimum cycle time method has been widely used in computer system analysis. A timed net is a modified version of a Petri net where a transition is associated with a delay time. A delay time used in a timed net is a constant even though the duration time associated with an event in the real world is a stochastic number in general. Therefore, this paper proposes 'Mixedly Distributed Stochastic Timed Net' where a transition can be associated with a stochastic number and introduce a minimum cycle time analysis method for 'Mixedly Distributed Stochastic Timed Net'. We also introduce a method of analysing a Web service system's response time with the minimum cycle time analysis method for 'Mixedly Distributed Stochastic Timed Net.'.

• Journal of the Korean Society for Heat Treatment
• /
• v.22 no.1
• /
• pp.16-22
• /
• 2009

The rolling process is an efficient and economical approach for the manufacturing of plate metals. In the rolling process, the temperature variation is very critical for plate thickness accuracy. The main cause of thickness variation in hot plate mills is the non-uniform temperature distribution along the length of the slab. Also the exit plate thickness is mainly affected by the rolling conditions such as mill modulus, plate thickness and plate width. Hence the thickness variation in top-end is also dependent on these factors. Therefore this study has concentrated on determining the correct amounts of thickness variation due to top-end temperature drop and process parameters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.5
• /
• pp.1129-1133
• /
• 2004

The MIC-NET of 3,010 circuits to process on-line business on post, insurance, finance, electromagnetic wave, and so forth has the problems on spending of bandwidth for the lack of flexibility of leased-line service band. In this paper, it is suggested to establish the efficient 3 steps conversion plan through analysis and comparison with economical efficiency on MIC-NET. The promoting policy proposed in this paper, both MIC and local post office will raise image as financial institute and provide high level service with reliability and security as distinguished government organization.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.10 no.4
• /
• pp.121-127
• /
• 2011

Many peer-to-peer (p2p) systems have been studied in distributed, ubiquitous computing environments. Distributed hash table (DHT)-based p2p systems can improve load-balancing even though locality utilization and user mobility are not guaranteed. We propose a mobile locality-based hierarchical p2p overlay network (MLH-Net) to address locality problems without any other services. MLH-Net utilizes mobility features in a mobile environment. MLH-Net is constructed as two layers, an upper layer formed with super-nodes and a lower layer formed with normal-nodes. Because super-nodes can share advertisements, we can guarantee physical locality utilization between a requestor and a target during any discovery process. To overcome a node failure, we propose a simple recovery mechanism. The simulation results demonstrate that MLH-Net can decrease discovery routing hops by 15% compared with JXTA and 66% compared with Chord.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.655-657
• /
• 2021

It is challenging to find breast ultrasound image training dataset to develop an accurate machine learning model due to various regulations, personal information issues, and expensiveness of acquiring the images. However, studies targeting transfer learning for ultrasound breast cancer images classification have not been able to achieve high performance compared to radiologists. Here, we propose an improved transfer learning model for ultrasound breast cancer classification using publicly available dataset. We argue that with a proper combination of ImageNet pre-trained model and optimizer, a better performing model for ultrasound breast cancer image classification can be achieved. The proposed model provided a preliminary test accuracy of 99.5%. With more experiments involving various hyperparameters, the model is expected to achieve higher performance when subjected to new instances.