• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.1070-1073
• /
• 2010

센서 네트워크 환경에서 센서 노드들은 무선 통신 능력을 이용하여 접근하기 어려운 시공간적 환경에서 센싱 데이터를 송수신하며 각종 데이터를 수집, 분석, 감시 및 처리를 용이하게 한다. 이러한 센서 노드들은 동적으로 변화하는 환경에 대한 적응력이 떨어지고, 센서 데이터의 과잉 및 중복 송수신으로 인한 전력이나 네트워크 대역폭 관련 등의 문제점을 가진다. 이에 본 논문에서는 센서 노드를 이주하며 중복 데이터를 제거하고, 사용자나 어플리케이션의 요구에 적합한 데이터만을 수집 및 전송하여 데이터의 과잉 송수신으로 인한 전력낭비와 네트워크 부하를 줄일 수 있는 이동 에이전트를 설계한다. 또한 기존 멀티 에이전트 시스템과의 연계를 통한 이동 에이전트의 이주 알고리즘을 제시하고, 실제 이동 에이전트의 통신 수행과정을 보임으로써 설계 방법의 유효성을 보인다.

• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.4
• /
• pp.19-28
• /
• 2016

최근 RFID와 같은 무선 센싱 네트워크 기술과 객체 추적을 위한 센싱 디바이스 및 다양한 컴퓨팅 자원들이 빠르게 발전함에 따라, 기존 웹의 형태는 소셜 웹에서 유비쿼터스 컴퓨팅 웹으로 자연스럽게 진화되고 있다. 유비쿼터스 컴퓨팅 웹에서 사물인터넷(IoT)은 기존의 컴퓨터를 대체할 수 있는데, 이것은 곧 한 사람과 주변 사물들 간에 연결되는 네트워크가 확장되는 것과 동시에 네트워크 안에서 생성되는 데이터의 수가 기하급수적으로 증가되는 것을 의미한다. 따라서 보다 지능적인 IoT 서비스를 위해서는, 수많은 미가공 데이터들 사이에서 사람의 의도와 상황을 실시간으로 정확히 파악할 수 있어야 한다. 이때 사물과의 상호작용을 위한 동작 인식 기술(Gesture recognition)은 집적적인 접촉을 필요로 하지 않기 때문에, 미래의 사람-사물 간 상호작용에 응용될 수 있는 잠재력을 갖고 있다. 한편, 기계학습 분야의 최신 알고리즘들은 다양한 문제에서 사람의 인지능력을 종종 뛰어넘는 성능을 보이고 있는데, 그 중에서도 의사결정나무(Decision Tree)를 기반으로 한 Decision Forest는 분류(Classification)와 회귀(Regression)를 포함한 전 영역에 걸쳐 우월한 성능을 보이고 있다. 따라서 본 논문에서는 지능형 IoT 서비스를 위한 다양한 동작 인식 기술들을 알아보고, 동작 인식을 위한 Decision Forest의 기본 개념과 구현을 위한 학습, 테스팅에 대해 구체적으로 소개한다. 특히 대표적으로 사용되는 3가지 학습방법인 배깅(Bagging), 부스팅(Boosting) 그리고 Random Forest에 대해 소개하고, 이것들이 동작 인식을 위해 어떠한 특징을 갖는지 기존의 연구결과를 토대로 알아보았다.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.46-53
• /
• 2009

This study aims to develop a mobile-based portable u-Health Monitoring System which provides a personal medical service on demand by processing patients' data intellectually achieved through sensing technique of non-restriction/non-consciousness oriented and deciding. To do this, we composed a USN-based portable monitoring unit. It is the one, that contains a somatometry sensor which is attached to patient's body and detects bio information, a portable wireless terminal which receives information from the sensor and transmits it to monitor server, and a monitor server which interprets received data through wireless network and processes. Also, it tries to develop a non-restriction /non-consciousness oriented sensing technique which is related to glycosuria and cardiovascular diseases.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8C
• /
• pp.655-662
• /
• 2012

In this work, we propose an airborne cognitive radio system that searches a new spectrum band to avoid a communication interruption due to the interference from many radar signals. We develop a method of fast spectrum sensing based on an effective frequency by recognizing the interfering radar as well as geographical information. This effective frequency is calculated by the free-space path loss between a base station and a fighter with the speed parameter. From our analysis, it is verified that the maximum frequency searching time is reduced by half by using our method.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1408-1414
• /
• 2019

Deep artificial neural network with transfer learning is applied to compressed sensing cardiovascular MRI. Transfer learning is a method that utilizes structure, filter kernels, and weights of the network used in prior learning for current learning or application. The transfer learning is useful in accelerating learning speed, and in generalization of the neural network when learning data is limited. From a cardiac MRI experiment, with 8 healthy volunteers, the neural network with transfer learning was able to reduce learning time by a factor of more than five compared to that with standalone learning. Using test data set, reconstructed images with transfer learning showed lower normalized mean square error and better image quality compared to those without transfer learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.141-145
• /
• 2012

In a Ubiquitous sensor network environment, the sensor node is in general small and low price, and operating with power limited battery. The reliable TCP/IP protocol is used for transmitting sensed data from the sensor node. A new method was proposed in order to overcome the limitation of small embedded memory, but it is difficult to use for the case of frame error. In this paper, a new algorithm is proposed to manage the receiving frame error or loss, and it is appropriate to the sensor network to send sensed data periodically.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.9
• /
• pp.1057-1059
• /
• 2016

A construction method of energy-efficient data aggregation tree is proposed by considering a tradeoff between acquisition time and energy consumption in wireless sensor networks. This proposed method constructs the data aggregation tree to minimize the link cost between the connected nodes for reducing energy consumption, while minimizing the maximum distance between sensor nodes and a sink node for rapid information gathering. Simulation results show that the proposed aggregation tree can be generated with low complexity and achieves high energy efficiency compared to conventional methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.155-162
• /
• 2013

The conventional block-based compressed sensing uses a fixed block size for signal reconstruction, and the reconstructed signal is degraded because the block size suitable to the signal characteristics is not used. To solve this problem, in this paper, a variable block size method for compressed sensing is proposed that estimates the signal characteristics and selects a proper block size for each frame, thereby improving the quality of the reconstructed signal. The proposed method reconstructs the signal with different block sizes, analyzes the signal characteristics using correlation coefficients for each frame, and select the block size for the frame. It is confirmed that, with the same acquired data, the proposed method reconstructs the signal of higher quality than the conventional fixed block size method.

• Journal of Satellite, Information and Communications
• /
• v.6 no.1
• /
• pp.75-79
• /
• 2011

Wireless devices can communicate between each other without existing infrastructure in mobile Ad-hod network. Ad hoc networks can be used under difficult conditions, where it is difficult to construct infrastructures, such as shadowing areas, disaster areas, war area, and so on. In order to support to considerable and various wireless services, more spectrum resources are needed. However, efficient utilization of the frequency resource is difficult because of spectrum scarcity and the conventional frequency regulation. Ad-hoc networks employing cognitive radio (CR) system that guarantee high spectrum utilization provide effective way to increase the network capacity. In this paper, we simulate and compare the performance of conventional single and cooperative spectrum sensing with CR system using ad-hoc networks in additive white Gaussian noise (AWGN) and Rayleigh channel model. And we demonstrate performance improvement by analyzing the system performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.2
• /
• pp.676-682
• /
• 2018

As the IoT world including WSNs develops, the number of sensor systems that sense information according to the environment based on the principle of IoT is increasing. In order to perform security for each sensor system in such a complicated environment, the security modules must be varied. These problems make hardware/software implementation difficult when considering the system efficiency and hacking/cracking. Therefore, to solve this problem, this paper proposes a pseudorandom number generator (FLT: Pseudo-random Number Generator with Fixed Length Tap unrelated to the variable sensing nodes) with a fixed-length tap that generates a pseudorandom number with a constant period, irrespective of the number of sensing nodes, and has the purpose of detecting anomalies. The proposed FLT-LFSR architecture allows the security level and overall data formatting to be kept constant for hardware/software implementations in an IoT environment. Therefore, the proposed FLT-LFSR architecture emphasizes the scalability of the network, regardless of the ease of implementation of the sensor system and the number of sensing nodes.