• 한국통신학회논문지
• /
• 제40권5호
• /
• pp.809-811
• /
• 2015

In this paper, for the purpose of providing high data rate services, the multi-hop frame structure is designed for the underwater acoustic (UWA) short-range system which is proposed as a part of ocean surveillance and tracking network (OSTN). Under the measured underwater channel environment, the link-level system performance are also evaluated. Simulation results show not only the packet error rate (PER) comparisons, but the optimal modulation and coding scheme (MCS) levels for the orthogonal frequency division multiplexing (OFDM) based short-range UWA communications network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• 한국IT서비스학회지
• /
• 제8권2호
• /
• pp.147-156
• /
• 2009

As the result of the rapid development of IT technology, an on-line diagnostic system using the field bus communication network coupled with a smart sensor module will be widely used at the nuclear power plant in the near future. The smart sensor system is very useful for the prompt understanding of abnormal state of the key equipments installed in the nuclear power plant. In this paper, it is assumed that a smart sensor system based on the fieldbus communication network for the surveillance and diagnostics of safety-critical equipments will be installed in the harsh-environment of the nuclear power plant. It means that the key components of fieldbus communication system including microprocessor, FPGA, and ASIC devices, are to be installed in the RPV (reactor pressure vessel) and the RCS (reactor coolant system) area, which is the area of a high dose-rate gamma irradiation fields. Gamma radiation constraints for the DBA (design basis accident) qualification of the RTD sensor installed in the harsh environment of nuclear power plant, are typically on the order of 4 kGy/h. In order to use a field bus communication network as an ad-hoc diagnostics sensor network in the vicinity of the RCS pump area of the nuclear power plant, the robust survivability of IT-based micro-electronic components in such intense gamma-radiation fields therefore should be verified. An intelligent CCD camera system, which are composed of advanced micro-electronics devices based on IT technology, have been gamma irradiated at the dose rate of about 4.2kGy/h during an hour UP to a total dose of 4kGy. The degradation performance of the gamma irradiated CCD camera system is explained.

• 한국군사과학기술학회지
• /
• 제20권5호
• /
• pp.708-716
• /
• 2017

We deal with the target selection in seeker-detection image through network, using the detection information from aerial vehicle and the target information from surveillance and reconnaissance system. Especially, we constrain the sea battle environment, where it is difficult to perform scene-matching rather than land. In this paper, we suggest the target selection algorithm based on the confidence estimation with respect to distance and size. In detail, we propose the generation method of reference point for distance evaluation, and we investigate the effect of pixel margin and target course for size evaluation. Finally, the proposed algorithm is simulated and analyzed through several scenarios.

• 로봇학회논문지
• /
• 제2권1호
• /
• pp.21-28
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. And the article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguity conditions. We propose to track the moving objects by generating hypotheses not in the image plan but on the top-view reconstruction of the scene. Comparative results on real video sequences show the advantage of our method for multi-object tracking. Also, the method is applied to the intelligent environment and its performance is verified by the experiments.

• 해양환경안전학회지
• /
• 제21권3호
• /
• pp.234-239
• /
• 2015

This paper focuses on analyzing the modern warfare and weapon systems supported by improved GPS informations. The GPS capability was investigated through the real experimental test for verifying the most recent GPS features under its modernization processing. And then it was verified that such capabilities, accuracy and availability, of a typical L1, C/A code GPS receiver are equivalent to the military receiver's ones. It was also sure that the influence of GPS improved informations on NCW(Network-Centric Warfare), PGM(Precision Guided Munition) and C4SIR(Command, Control, Communications, Computers, Intelligence, Surveillance and Reconnaissance) should be increased and the modern warfare may be strongly dependent on GNSS informations.

• 한국군사과학기술학회지
• /
• 제17권5호
• /
• pp.591-603
• /
• 2014

In this paper, we have described the characteristics of the Underwater Distributed Sensor Network (UDSN) and proposed the conceptual design guideline by an effectiveness analysis. To perform the effectiveness analysis, we defined an battlefield environment, and then analyzed principal components which compose the UDSN to find out simulation parameters and system constraints. We have chosen a measure of effectiveness based on a target trajectory, which could enhance intuitive understanding about current status, and performed various simulations to reveal critical design parameters in terms of sensor node types, arrangement, cost and combination of detection information.

• 한국멀티미디어학회논문지
• /
• 제23권11호
• /
• pp.1372-1382
• /
• 2020

This paper proposes a core technology for a micro river monitoring terminal device suitable for flood monitoring in small rivers and valleys. Our proposed device is basically equipped with a 77GHz radar, gyro and accelerometer sensors. To measure the flow velocity and water level, we proposed a signal processing technique that extracts pure water energy components from the observed Doppler velocity and reflection intensity from the radar. And to determine the stability of the river structure equipped with our device, we constantly monitor the displacement of the measured values of the gyro and accelerometer sensors. Experimental result verified that our method detects pure water energy in various river environments and distinguishes between flow velocity and water level well. And we verified that vibration and position change of structures can be determined through a gyro sensor. In future research, we will work to build a secure digital twin river network by lowering the cost of supplying RF-WAV devices. Also we expect our device to contribute to securing a preventive golden time in rivers.

• 한국물환경학회지
• /
• 제23권5호
• /
• pp.697-704
• /
• 2007

This study proposes an integrated technique of Genetic Algorishim (GA) and Geographic Information System (GIS) for designing the water quality monitoring networks. To develop solution scheme of the integrated system, fitness functions are defined by the linear combination of five criteria which stand for the operation objectives of water quality monitoring stations. The criteria include representativeness of a river system, compliance with water quality standards, supervision of water use, surveillance of pollution sources and examination of water quality changes. The fitness level is obtained through calculations of the fitness functions and input data from GIS. To find the most appropriate parameters for the problems, the sensitivity analysis is performed for four parameters such as number of generations, population sizes, probability of crossover, and probability of mutation. Using the parameters resulted from the sensitivity analysis, the developed system proposed 110 water quality monitoring stations in the Nakdong River. This study demonstrates that the integrated technique of GA and GIS can be utilized as a decision supporting tool in optimized design for a water quality monitoring network.

• 융합보안논문지
• /
• 제7권2호
• /
• pp.107-118
• /
• 2007

센서 네트워크는 다양한 환경에 배치되어 환경요소 감시 및 군사적으로 유용한 정보를 제공하는데 사용될 수 있다는 특징을 가지고 있지만, 여러 가지 보안상의 취약점을 갖고 있는 단점이 있다. 따라서 이러한 센서 네트워크의 안전성을 위해서는 반드시 보안 서비스가 요구되며, 센서 네트워크 노드간의 안전한 통신을 위해 보다 안전하고 효과적인 노드 관리 기법이 요구된다. 본 논문에서는 센서 네트워크에서의 센서 노드의 보안성이 요구되는 환경 및 그룹 키 관리기법에 적합한 효과적인 CH 및 클러스터링 기법을 제안한다. 먼저 각각의 노드들은 매 라운드 설정단계에서 BS와의 통신을 통하여 잔류 전력 및 암호 키를 이용한 인증 메시지를 전송하고 BS는 유효인증비율 및 잔류전력량을 반영하여 이 값들이 높은 노드를 CH로 선발한다. 이후 BS는 매 라운드 마다 이전라운드의 유효인증비율을 반영/누적 하여 적은 양의 에너지 소비로 안전한 클러스터 노드를 선발할 수 있는 기법을 제안한다.