• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.2
• /
• pp.385-391
• /
• 2001

In this study, we will develop the sea surface interpretation system that can aware the target in the bottom of the sea. we will setup the database whose records would be the signal patterns of formation about mud, sand, rock and sea shell achieved by using supersonic. then we will convert analog signal received in fish detector to digital one using A/D converter So we can process and analyze this signal pattern then compare it to the one in our Database at the real time to identify the target in the bottom of the sea. After enough times of experiments from the background of the results that have been achieved from many studies(including a water tank experiment and a field investigation), we can aware the exact information of the sediment and the sand in the sea. By analyzing the first, second and third signal of the supersonic characters reflected from the body of a fish categorized by its family and from the body of shellfish, muddy sand, sand and rocks, We will develop the sea surface decipherment system which abstracts the first signal that shows the target in the bottom of the sea and makes the second and third signals filtering.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.195-198
• /
• 2013

Recognition and Tracking of interesting object is the significant field in Computer Vision. Mean-Shift algorithm have chronic problems that some errors are occurred when histogram of tracking area is similar to another area. in this paper, we propose to solve the problem. Each algorithm blocks skin color filtering, face detect and Mean-Shift started consecutive order assists better operation of the next algorithm. Avoid to operations of the overhead of tracking area similar to a histogram distribution areas overlap only consider the number of white pixels by running the Viola-Jones algorithm, simple arithmetic increases the convergence of the Mean-Shift. The experimental results, it comes to 78% or more of white pixels in the Mean-Shift search area, only if the recognition of the face area when it is configured to perform a Viola-Jones algorithm is tracking the object, was 100 percent successful.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.3
• /
• pp.501-519
• /
• 2017

With the revolution of IT technology, cyber threats and crimes are also increasing. In the recent years, many large-scale APT attack executed domestically and internationally. Specially, many of the APT incidents were not recognized by internal organizations, were noticed by external entities. With fourth industrial revolution(4IR), advancement of IT technology produce large scale of sensitive data more than ever before; thus, organizations invest a mount of budget for various methods such as encrypting data, access control and even SIEM for analyzing any little sign of risks. However, enhanced intelligent APT it's getting hard to aware or detect. These APT threats are too much burden for SMB, Enterprise and Government Agencies to respond effectively and efficiently. This paper will research what's the limitation and weakness of current defense countermeasure base on Cyber Kill Chain process and will suggest effective and efficient APT defense operation model with considering of organization structure and human resources for operation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1608-1613
• /
• 2009

All kinds of equipment which used an embedded system is developed, and these are used as to an actual life in developments regarding an embedded field in a lot of sections. Also, we can collect data from all kinds of sensors through wireless sensor networks, look by real time data collected could be brought if only through embedded system. In this paper we present a plan which improve the capabilities of embedded system only act as a gateway by installing embedded database in an embedded system for the sensing data management that was transmitted by radio from sensor nodes. In other words, by installing an embedded database to store and manage data by sensing data can be reduced the transmission frequency to communicate with a host and by performing the filtering program in embedded system and then by transmitting only valid data to the host can be increase the reliability of the analysis results based on data collected.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.81-86
• /
• 2014

In this paper, we present an effective sound classification system for recognizing the real-time context of a smartphone user. Our system avoids unnecessary consumption of limited computational resource by filtering both silence and white noise out of input sound data in the pre-processing step. It also improves the classification performance on low energy-level sounds by amplifying them as pre-processing. Moreover, for efficient learning and application of HMM classification models, our system executes the dimension reduction and discretization on the feature vectors through k-means clustering. We collected a large amount of 8 different type sound data from daily life in a university research building and then conducted experiments using them. Through these experiments, our system showed high classification performance.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.4
• /
• pp.13-24
• /
• 2008

Real-time traffic data are readily obtainable by traffic surveillance systems of intelligent transportation systems (ITS). Such data greatly support further applications in the field of traffic operations, planning, and safety. However, traffic data should be appropriately processed to fully exploit the benefits of data collection capability. Rather than developing individual data processing techniques, which is major concern of existing studies, this study proposes a novel methodology for evaluating data processing techniques in an integrated manner. Also, a tool for implementing the proposed methodology is developed. Users can extract useful and more reliable traffic data based upon their ultimate purpose of data usage by the evaluation tool developed in this study. Actual freeway traffic data are, as an example, fed into the evaluation tool, and results are discussed.

• Journal of Convergence for Information Technology
• /
• v.11 no.9
• /
• pp.214-220
• /
• 2021

With the rapid spread of smartphones, it has become common to listen to music everywhere, just like background music in life, so it is necessary to create a music database that can make recommendations according to individual circumstances and conditions. This paper proposes a music recommendation model through social media. Since emotions, situations, time of day, weather, etc. are included in hashtags, it is possible to build a social media-based database that reflects the opinions of various people with collective intelligence. We use web crawling to collect and categorize different hashtags from posts with music title hashtags to use real listeners' opinions about music in a database. Data from social media is used to create a music database, and music is classified in a different way from collaborative filtering, which is mainly used by existing music platforms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.637-644
• /
• 2021

In general, in the fields of computer vision, robotics, and augmented reality, the importance of 3D space and 3D object detection and recognition technology has emerged. In particular, since it is possible to acquire RGB images and depth images in real time through an image sensor using Microsoft Kinect method, many changes have been made to object detection, tracking and recognition studies. In this paper, we propose a method to improve the quality of 3D reconstructed images by processing images acquired through a depth-based (RGB-Depth) camera on a multi-view camera system. In this paper, a method of removing noise outside an object by applying a mask acquired from a color image and a method of applying a combined filtering operation to obtain the difference in depth information between pixels inside the object is proposed. Through each experiment result, it was confirmed that the proposed method can effectively remove noise and improve the quality of 3D reconstructed image.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.9 no.1
• /
• pp.57-70
• /
• 1999

Since a hybrid firewall filters packets at a network layer along with providing gateway functionalities at an application layer, it has a better performance than an If filtering firewall. In addition, it provides both the various kinds of access control mechanisms and transparent services to users. However, the security policies of a network layer are different from those of an application layer. Thus, the user interfaces for managing a hybrid firewalls in a consistent manner are needed. In this paper, we implement a graphical user interface to provide access control mechanisms and management facilities for a hybrid firewall such as log analysis, a real-time monitor for network traffics, and the statisics on traffics. And we also propose a new rule script language for specifying access control rules. By using the script language, users can generate the various forma of access control rules which are adapted by the existing firewalls.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1545-1550
• /
• 2021

We propose an optimal variable step size adjustment method for the simplified subband affine projection algorithm (Simplified SAP; SSAP) in a subband structure based on a polyphase decomposition technique. The proposed method provides an optimal step size derived to minimize the mean square deviation(MSD) at the time of updating the coefficients of the subband adaptive filter. Application of the proposed optimal step size in the SSAP algorithm using colored input signals ensures fast convergence speed and small steady-state error. The results of computer simulations performed using AR(2) signals and real voices as input signals prove the validity of the proposed optimal step size for the SSAP algorithm. Also, the simulation results show that the proposed algorithm has a faster convergence rate and good steady-state error compared to the existing other adaptive algorithms.