• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.5
• /
• pp.915-920
• /
• 2007

Using the existing algorithms that estimate the background noise, the detection probability for the week tonals is low and for the even week tonals, there is a limit not detected. Therefore it is required to algorithms which can improve the performance of the tonal extraction. Recently, many researches using artificial neural networks in sonar signal processing are performed. We propose a neural network with double feedback that can remove automatically the background noise and detect the even week tonals buried in background noise, therefore not detected by growing the week tonals lastingly for a certain time. For the real underwater target, experiments for the tonal extraction are performed by using the existing algorithms that estimate the background noise and the proposed neural network. As a result of the experiment, a method using the proposed neural network showed the better performance of the tonal extraction in comparison with the existing algorithms.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.205-210
• /
• 2022

To achieve the higher network capacity and mass connectivity in the forthcoming mobile network, revolutionary technologies have been considered. Recently, an upper bound on capacity of intelligent reflecting surface (IRS) transmissions towards the sixth generation (6G) mobile systems has been proposed. In this paper, we consider a tighter upper bound on capacity of IRS transmissions than the existing upper bound. First, using integration by parts, we derive an upper bound on capacity of IRS transmissions under Rician fading channels and a Rayleigh fading channel. Then, we show numerically that the proposed upper bound is closer to Monte Carlo simulations than the existing upper bound. Furthermore, we also demonstrate that the bounding error of the proposed upper bound is much smaller than that of the existing upper bound, and the superiority of the proposed upper bound over the existing upper bound becomes more significant as the signal-to-noise ratio (SNR) increases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.3
• /
• pp.838-856
• /
• 2014

Enhanced network speed and the appearance of various applications have recently resulted in the rapid increase of Internet users and the explosive growth of network traffic. Under this circumstance, Internet users are eager to receive reliable and Quality of Service (QoS)-guaranteed services. To provide reliable network services, network managers need to perform control measures involving dropping or blocking each traffic type. To manage a traffic type, it is necessary to rapidly measure and correctly analyze Internet traffic as well as classify network traffic according to applications. Such traffic classification result provides basic information for ensuring service-specific QoS. Several traffic classification methodologies have been introduced; however, there has been no favorable method in achieving optimal performance in terms of accuracy, completeness, and applicability in a real network environment. In this paper, we propose a method to classify Internet traffic as the first step to provide stable network services. We integrate the existing methodologies to compensate their weaknesses and to improve the overall accuracy and completeness of the classification. We prioritize the existing methodologies, which complement each other, in our integrated classification system.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.9
• /
• pp.425-430
• /
• 2015

The Sensor Registry System(SRS) provides sensor metadata to a user for instant use and seamless interpretation of sensor data in a heterogeneous sensor network environment. The existing sensor registry system cannot provide sensor metadata in case that the network connection is not available or is unstable. To resolve the problem, this paper proposes an extension of sensor registry system using network coverage information. The extended system sends a set of sensor metadata to the user by using network coverage open data (mobile vendors, signal strength, communication type). The extended SRS proposed in this paper supports a safer sensor metadata provision than the existing SRS, and it thus improves the quality of application services.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.27 no.4
• /
• pp.29-38
• /
• 1999

Present green space planning of Korea pay little attention to biodiversity conservation in urban areas. The quality of urban wildlife habitat has been deteriorated severely due to fragmentation and isolation of urban open spaces. The application of ecological corridors to urban green space planning and management can greatly enhance the bird habitat of Seoul. The objectives of this study were to evaluate bird habitat potential of existing urban parks of Seoul, and to investigate methods to develop ecological corridors for wild birds. This study consists of three parts. The first part is to construct bird species/habitat relationship model. The second part is to evaluate 207 urban parks of Seoul with the model. Based on the relative potential for bird habitat, urban parks of Seoul can be classified into cores, nodes, and points of the network. Outcomes of this part can also be used to enhance the quality of bird habitats by identifying limits or weakness of existing green spaces for bird habitat. The final part is to develop three green network plans; north-south network, the Han river network, and a district network for Kangnam-Gu.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.8
• /
• pp.1683-1690
• /
• 2005

This study examines dynamic flow control method in UDP, analyzes packet loss which is frequently used element in measuring existing dynamic flow control and characteristics of round trip time, and proposes a new method of measurement, RSST. The algorithm that uses the proposed RSST enables accurate measurement of network status by considering both the currently measured network status and the past history of network status in controlling the transmission rate. For comparison study, a network status measurement software program that displays detailed information about volume of transmission generation of network status, and flow pattern of network was developed. The performance test shows that the proposed algorithm can better adjust to network condition in terms of low pack loss rate over existing algorithms.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.109-118
• /
• 2023

Data-based analysis methods have become used more for estimating or predicting housing prices, and neural network models and decision trees in the field of big data are also widely used more and more. Neural network models are often evaluated to be superior to existing statistical models in terms of estimation or prediction accuracy. However, there is ambiguity in determining the input feature of the input layer of the neural network model, that is, the type and number of input features, and decision trees are sometimes used to overcome these disadvantages. In this paper, we evaluate the existing methods of using decision trees and propose the method of using decision trees to prioritize input feature selection in neural network models. This can be a complementary or combined analysis method of the neural network model and decision tree, and the validity was confirmed by applying the proposed method to house price estimation. Through several comparisons, it has been summarized that the selection of appropriate input characteristics according to priority can increase the estimation power of the model.

• International Journal of Contents
• /
• v.2 no.4
• /
• pp.12-18
• /
• 2006

The number of wireless public network user is increasing rapidly. Security problem for user authentication has been increased on existing wireless network such as IEEE802.11 based Wireless LAN. As a solution, IEEE802.1x (EAP-MD5, EAP-TLS, EAP-TTLS), X.509, protocol or security system was suggested as a new disposal plan on this problem. In this study, we overview main problem on existing EAP-MD5 authentication mechanism on Wireless LAN and propose a SMS(Short Message Service) based secure authentication and accounting mechanism for providing security enhanced wireless network transactions.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.64 no.4
• /
• pp.315-320
• /
• 2015

Proposal algorithm in this paper introduced cells, units of router group, for distributed processing of previous genetic algorithm. This paper presented ways to reduce search delay time of overall network through cell-based genetic algorithm. As a result of performance analysis comparing with existing genetic algorithm through experiments, the proposal algorithm was verified superior in terms of costs and delay time. Furthermore, time for routing an alternative path was reduced in proposal algorithm, in case that a network was damaged in existing optimal path algorithm, Dijkstra algorithm, and the proposal algorithm was designed to route an alternative path faster than Dijkstra algorithm, as it has a 2nd shortest path in cells of the damaged network. The study showed that the proposal algorithm can support routing of alternative path, if Dijkstra algorithm is damaged in a network.

• Journal of Korea Multimedia Society
• /
• v.23 no.6
• /
• pp.756-764
• /
• 2020

A typical algorithm used for image analysis is the Convolutional Neural Network(CNN). R-CNN, Fast R-CNN, Faster R-CNN, etc. have been studied to improve the performance of the CNN, but they essentially require large amounts of data and high algorithmic complexity., making them inappropriate for small and medium-sized services. Therefore, in this paper, the image label prediction algorithm based on CNN with collaborative layer with low complexity, high accuracy, and small amount of data was proposed. The proposed algorithm was designed to replace the part of the neural network that is performed to predict the final label in the existing deep learning algorithm by implementing collaborative filtering as a layer. It is expected that the proposed algorithm can contribute greatly to small and medium-sized content services that is unsuitable to apply the existing deep learning algorithm with high complexity and high server cost.