• ETRI Journal
• /
• v.42 no.2
• /
• pp.230-238
• /
• 2020

Human-object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three-stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual-based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V-COCO and HICO-DET, and demonstrate its state-of-the-art performance.

• Journal of Advanced Navigation Technology
• /
• v.8 no.2
• /
• pp.155-162
• /
• 2004

Recently, significant interest is shown to creation rather inexpensive global systems communications on base of Low-Earth-Orbit Satellite Networks (LEOSN). One of problems of design and creation LEOSN is development of the stream control methods and estimation it's efficiency in such networks. The given problem is complicated, that the topology of the satellite networks varies in time. It essentially hinders the analytical decision of the given problem. An effective way of overcoming of these difficulties is simulation modeling. For realization of research experiments on learning the information streams routing algorithms in LEOSN a special program complex SANET was developed. In the given paper principles of development of LEOSN simulation models and architecture of the manager by the process of a simulation modeling of the unit are considered. Methods of promotion of modeling time and architecture of a simulator complex offered in the article allow to boost essentially efficiency of simulation analysis and to ensure simulation modeling of the satellite networks consisting of several hundreds space vehicles.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.7 no.2
• /
• pp.157-166
• /
• 1996

This paper presents the optimum termination method of a TEM Cell, which utilizes hybrid distributed termination resistor array networks. Current stream on the septum, and on the terminal end of a TEM Cell is analyzed by numerical analysis. By circuit analysis, the optimum resistor array network is designed based on the result of the analysis, which assures efficient power dissipation, and current stream traveling straight and uniform. Thermovision photos were taken for comparing the conventional termination network on which each resistor is arranged at regular intervals, with the suggested optimum termination network on which each resistor is arranged for current distribution. The comparison of the results of thermovision photos shows a good agreement with those obtained by numerical analysis.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1616-1640
• /
• 2006

In this paper, we deal with a network optimization problem arising from the deployment of Ethernet-based BcN access network. BcN convergence services require that access networks satisfy QoS measures. BcN services have two types of traffics: stream traffic and elastic traffic. Stream traffic uses blocking probability as a QoS measure, while elastic traffic uses delay factor as a QoS measure. Incorporating the QoS requirements, we formulate the problem as a nonlinear mixed-integer programming model. The proposed model seeks to find a minimum cost dimensioning solution, while satisfying the QoS requirement. We propose tabu search heuristic algorithms for solving the problem, and simulate tabu result. We demonstrate the computational efficacy of the proposed algorithm by solving a network design problem.

• Journal of information and communication convergence engineering
• /
• v.10 no.3
• /
• pp.231-236
• /
• 2012

For real-time wireless sensor network applications, it is essential to provide different levels of quality of service (QoS) such as reliability, low latency, and fault-tolerant traffic control. To meet these requirements, an (m,k)-firm based real-time routing protocol has been proposed in our prior work, including a novel local transmission status indicator called local DBP (L_DBP). In this paper, a fault recovery scheme for (m,k)-firm real-time streams is proposed to improve the performance of our prior work, by contributing a delay-aware forwarding candidates selection algorithm for providing restricted redundancy of packets on multipath with bounded delay in case of transmission failure. Each node can utilize the evaluated stream DBP (G_DBP) and L_DBP values as well as the deadline information of packets to dynamically define the forwarding candidate set. Simulation results show that for real-time service, it is possible to achieve both reliability and timeliness in the fault recovery process, which consequently avoids dynamic failure and guarantees meeting the end-to-end QoS requirement.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.137-145
• /
• 2010

Digital vessel have to accurate and efficient mange the digital data from various sensors in the digital vessel. But, In sensor network, it is difficult to transmit and analyze the entire stream data depending on limited networks, power and processor. Therefore it is suitable to use alternative stream data processing after classifying the continuous stream data. In this paper, We propose efficient processing method that arrange some sensors (temperature, humidity, lighting, voice) and process query based on sliding window for efficient input stream and pre-clustering using multiple Support Vector Machine(SVM) algorithm and manage hash table to summarized information. Processing performance improve as store and search and memory using hash table and usage reduced so maintain hash table in memory. We obtained to efficient result that accuracy rate and processing performance of proposal method using 35,912 data sets.

• Journal of Korea Multimedia Society
• /
• v.16 no.12
• /
• pp.1427-1438
• /
• 2013

We have developed a 128-bit stream cipher algorithm composed of the 5-stage pipeline, capable of real-time processing, confidentiality and integrity. The developed stream cipher is a stream cipher algorithm that makes the final 128-bit ciphers through a whitening process after making the ASR 277 bit and SHACAL-2 and applying them to the CFB mode. We have verified the hardware performance of the proposed stream cipher algorithm with Modelsim 6.5d and Quartus II 12.0, and the result shows that the hardware runs at 33.34Mhz(4.27Gbps) at worst case. According to the result, the new cipher algorithm has fully satisfied the speed requirement of wireless Internet and sensor networks, and DRM environment. Therefore, the proposed algorithm with satisfaction of both confidentiality and integrity provides a very useful ideas.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.9-18
• /
• 2024

Small streams, despite their rich ecosystems, face challenges in vegetation assessment due to the limitations of traditional, time-consuming methods. This study presents a groundbreaking approach, combining unmanned aerial vehicles(UAVs), convolutional neural networks(CNNs), and the vegetation differential vegetation index (VDVI), to revolutionize both assessment and management of stream vegetation. Focusing on Idong Stream in South Korea (2.7 km long, 2.34 km² basin area)with eight diverse revetment methods, we leveraged high-resolution RGB images captured by UAVs across five dates (July-December). These images trained a ResNeXt101 CNN model, achieving an impressive 89% accuracy in classifying vegetation cover(soil,water, and vegetation). This enabled detailed spatial and temporal analysis of vegetation distribution. Further, VDVI calculations on classified vegetation areas allowed assessment of vegetation vitality. Our key findings showcase the power of this approach:(a) TheCNN model generated highly accurate cover maps, facilitating precise monitoring of vegetation changes overtime and space. (b) August displayed the highest average VDVI(0.24), indicating peak vegetation growth crucial for stabilizing streambanks and resisting flow. (c) Different revetment methods impacted vegetation vitality. Fieldstone sections exhibited initial high vitality followed by decline due to leaf browning. Block-type sections and the control group showed a gradual decline after peak growth. Interestingly, the "H environment block" exhibited minimal change, suggesting potential benefits for specific ecological functions.(d) Despite initial differences, all sections converged in vegetation distribution trends after 15 years due to the influence of surrounding vegetation. This study demonstrates the immense potential of UAV-based remote sensing and CNNs for revolutionizing small-stream vegetation assessment and management. By providing high-resolution, temporally detailed data, this approach offers distinct advantages over traditional methods, ultimately benefiting both the environment and surrounding communities through informed decision-making for improved stream health and ecological conservation.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.74-77
• /
• 1998

We consider connection-oriented wireless cellular networks. These networks employ dedicated radio channels for the transmission of signaling information. A forward signaling channel is a common signaling channel assigned to carry the multiplexed stream of paging and channel allocation(virtual circuit allocation) packets from a base station to mobile stations. The delay levels experienced by paging and channel allocation packets have serious effect on the utilization level of the limited radio channel capacity. While a slotted mode operation is used to reduce the power consumption level at mobile stations, it may induce an increase in packet delay levels. In this paper, we thus consider a multiplexing scheme for paging and channel allocation packets under which slots are dynamically allocated for the paging packet transmission. For this dynamic scheme, we develop an analytical method for deriving the delay characteristics exhibited by paging and channel allocation packets, and investigate the effect of network parameters on the delay level by using this method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10d
• /
• pp.199-204
• /
• 2006

오버레이 멀티캐스트는 IP 멀티캐스트의 대안으로 많은 관심을 받아 왔다. 본 논문에서는 오버레이 멀티캐스트에서 각 단말의 특성에 따라 적응적으로 멀티미디어를 전송하는 기법을 연구하였다. 데이터 기반으로 컨텐츠를 전달하는 피어-투-피어 형태의 전송 구조를 사용하여 각 단말이 네트웍 특성에 따라 데이터를 요청하는 형태로 구성되었다. 이웃 노드 선택, 버퍼 맵 교환, 필요한 데이터를 전송 요청하는 과정으로 구성되는 피어-투-피어 형태의 전송 구조에서 적응적인 멀티미디어 전송을 지원하기 위하여 전략적 세그먼테이션을 통한 버퍼 맵 교환, Fine-grained 적응 스케줄러를 통한 데이터 교환을 제안하였다. 본 연구에서 적용된 기법의 특성을 분석하기 위하여 정성적인 분석 모델을 제시하고 이를 통해 결론을 도출하였다.