• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.1149-1152
• /
• 2005

Detecting faces in images with complex backgrounds is a difficult task. Our approach, which obtains state of the art results, is based on a generative neural network model: the Constrained Generative Model (CGM). To detect side view faces and to decrease the number of false alarms, a conditional mixture of networks is used. To decrease the computational time cost, a fast search algorithm is proposed. The level of performance reached, in terms of detection accuracy and processing time, allows to apply this detector to a real word application: the indexation of face images on the Web.

• Journal of KIISE:Information Networking
• /
• v.30 no.6
• /
• pp.755-763
• /
• 2003

To improve performance over noisy wireless channels, mobile wireless networks employ forward error correction(FEC) techniques. The performance of static FEC algorithms, however, degrades by poorly matching the overhead of their correction code to the degree of the fluctuating underlying channel error. This paper proposes an adaptive FEC technique called FECA(FEC-level Adaptation), which dynamically tunes FEC strength to the currently estimated channel error rate at the data link layer. FECA is suitable for wireless networks whose error rate is high and slowly changing compared to the round-trip time between two communicating nodes. One such example network would be a sensor network in which the average bit error rate is higher than $10^{-6}$ and the detected error rate at one time lasts a few hundred milliseconds on average. Our experiments show that FECA performs 15% in simulations with theoretically modeled wireless channels and in trace-driven simulations based on the data collected from real sensor networks better than any other static FEC algorithms.

• The KIPS Transactions:PartC
• /
• v.16C no.2
• /
• pp.183-188
• /
• 2009

Wireless sensor networks will be broadly deployed in the real world and widely utilized for various applications. A prerequisite for secure communication among the sensor nodes is that the nodes should share a session key to bootstrap their trust relationship. The open problems are how to verify the identity of communicating nodes and how to minimize any information about the keys disclosed to the other side during key agreement. At any rate, any one of the existing schemes cannot perfectly solve these problems due to some drawbacks. Accordingly, we propose a new pre-distribution scheme with the following merits. First, it supports authentication services. Second, each node can only find some indices of key spaces that are shared with the other side, without revealing unshared key information. Lastly, it substantially improves resilience of network against node capture. Performance and security analyses have proven that our scheme is suitable for sensor networks in terms of performance and security aspects.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2822-2831
• /
• 1997

A B-ISDN network based on ATM must support several kinds of transport services with different traffic characteristics and service requirements. There is neither link-by-link flow control nor error control in the ATM layer. For different services, different flow/error controls could be performed at the AAL layer or at a higher Iayer(e.g. transport layer). In traditional data networks, the window now control mechanism combined with error control was used prevalently. But, the window flow control mechanism might be useless in ATM networks because the propagation delay is too large compared with the transmission rate. In this paper, we propose a simple flow control mechanism, called RCT(Rate Control for end-to-end Transport), for end-to-end data transport. The RCT shows acceptable performance when the average overload period is bounded by a certain time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.3
• /
• pp.461-468
• /
• 2008

RFID technology is one of the core technologies for ubiquitous computing, and many research activities have been going on in this research area currently. Related with these researches, mobile RFID network services using mobile devices having a built-in RFID reader and mobile networks have been launched in Korea, for the first time in the world. In this paper, we propose a method to coulect ALE middleware suggested by EPCglobal and existing mobile RFID network services. Especially, a RFID code conversion method is proposed to process mobile RFID code systems within ALE middleware systems. Using the proposed method, application developers and(or) content business industries can acquire the information they want, which is filtered and refined in real-time or periodically, from mobile RFID users. So, they can Provide customized services to users by using the user preference information. In this war, the ALE middleware system can be easily extended to process mobile RFID code effectively.

• Journal of Convergence for Information Technology
• /
• v.9 no.3
• /
• pp.22-29
• /
• 2019

Due to the development of ICT technology, convergence reality contents are utilized as technology for providing services in various industrial fields by visualizing various information such as sensor information and shared information in a service platform showing only simple three-dimensional contents. Research is underway to reduce the weight of applications by transmitting the resources of the object to be enhanced to the network as the information and the contents to be provided increase. In order to provide resources through the network, servers for processing various information such as pattern information, content information, and sensor information must be constructed in a cloud environment. However, in order to authenticate data transmitted and received in real-time in a cloud environment, there is a problem in that the processing is delayed and a delay phenomenon occurs in the rendering process and QoS is lowered. In this paper, we propose a system to distribute cloud server which provides augmented contents of convergent reality service that provides various contents such as sensor information and three - dimensional model, and shorten the processing time of reliable data through distributed relay between servers Respectively.

• Plant Journal
• /
• v.17 no.3
• /
• pp.37-41
• /
• 2021

P&ID((Piping and Instrument Diagram) is a key drawing in the engineering industry because it contains information about the units and instrumentation of the plant. Until now, simple repetitive tasks like listing symbols in P&ID drawings have been done manually, consuming lots of time and manpower. Currently, a deep learning model based on CNN(Convolutional Neural Network) is studied for drawing object detection, but the detection time is about 30 minutes and the accuracy is about 90%, indicating performance that is not sufficient to be implemented in the real word. In this study, the detection of symbols in a drawing is performed using 1-stage object detection algorithms that process both region proposal and detection. Specifically, build the training data using the image labeling tool, and show the results of recognizing the symbol in the drawing which are trained in the deep learning model.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.1029-1037
• /
• 2020

The machine learning algorithm has been widely used in water-related fields such as water resources, water management, hydrology, atmospheric science, water quality, water level prediction, weather forecasting, water discharge prediction, water quality forecasting, etc. However, water quality prediction studies based on the machine learning algorithm are limited compared to other water-related applications because of the limited water quality data. Most of the previous water quality prediction studies have predicted monthly water quality, which is useful information but not enough from a practical aspect. In this study, we predicted the dissolved oxygen (DO) using recurrent neural network with long short-term memory model recurrent neural network long-short term memory (RNN-LSTM) algorithms with hourly- and daily-datasets. Bugok Bridge in Oncheoncheon, located in Busan, where the data was collected in real time, was selected as the target for the DO prediction. The 10-month (temperature, wind speed, and relative humidity) data were used as time prediction inputs, and the 5-year (temperature, wind speed, relative humidity, and rainfall) data were used as the daily forecast inputs. Missing data were filled by linear interpolation. The prediction model was coded based on TensorFlow, an open-source library developed by Google. The performance of the RNN-LSTM algorithm for the hourly- or daily-based water quality prediction was tested and analyzed. Research results showed that the hourly data for the water quality is useful for machine learning, and the RNN-LSTM algorithm has potential to be used for hourly- or daily-based water quality forecasting.

• Earthquakes and Structures
• /
• v.22 no.2
• /
• pp.185-201
• /
• 2022

Structural Health Monitoring (SHM) is used to provide reliable information about the structure's integrity in near realtime following extreme incidents such as earthquakes, considering the inevitable aging and degradation that occurs in operating environments. This paper experimentally investigates an integrated wireless sensor network (Wi-SN) based monitoring technique for damage detection in concrete structures. An effective SHM technique can be used to detect potential structural damage based on post-earthquake data. Two novel methods are proposed for damage detection in reinforced concrete (RC) building structures including: (i) Jerk Energy Method (JEM), which is based on time-domain analysis, and (ii) Modal Contributing Parameter (MCP), which is based on frequency-domain analysis. Wireless accelerometer sensors are installed at each story level to monitor the dynamic responses from the building structure. Prior knowledge of the initial state (immediately after construction) of the structure is not required in these methods. Proposed methods only use responses recorded during ambient vibration state (i.e., operational state) to estimate the damage index. Herein, the experimental studies serve as an illustration of the procedures. In particular, (i) a 3-story shear-type steel frame model is analyzed for several damage scenarios and (ii) 2-story RC scaled down (at 1/6th) building models, simulated and verified under experimental tests on a shaking table. As a result, in addition to the usual benefits like system adaptability, and cost-effectiveness, the proposed sensing system does not require a cluster of sensors. The spatial information in the real-time recorded data is used in global damage identification stage of SHM. Whereas in next stage of SHM, the damage is detected at the story level. Experimental results also show the efficiency and superior performance of the proposed measuring techniques.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.57-66
• /
• 2022

The aim of the article is to investigate socio-political processes in Ukraine on the basis of institutional and behavioral approaches, in particular their regulatory and informational support. Methodology. To determine the nature and content of sociopolitical processes, the following approaches have been used: 1. Institutional approach in order to analyze the development of Ukraine's political institutions. 2. The behavioral approach has been used for the analysis of socio-political processes in Ukraine in the context of political behavior of citizens, their political activity which forms the political culture of the country. Results. The general features of the socio-political situation in Ukraine are as follows: the formed model of government, which can be conditionally described as "presidential"; public demand for new leaders remains at a high level; the society has no common vision of further development; significant tendency of reduction of real incomes of a significant part of the society and strengthening of fiscal pressure on businessmen will get a public response after some time. Increasing levels of voice, accountability, efficiency of governance and the quality of the regulatory environment indicate a slow change in the political system, which will have a positive impact on public sentiment in the future. At the same time, there has been little change in the quality of Ukraine's institutions to ensure political stability, the rule of law and control of corruption. There are no cardinal changes in the development of the institution of property rights, protection of intellectual rights, changes in the sphere of ethics and control of corruption. Thus, Ukraine's political institutions have not been able to bring about any change in the social-political processes. Accordingly, an average level of trust and confidence of citizens in political institutions and negative public sentiment regarding their perception and future change can be traced in Ukraine.