• Journal of Platform Technology
• /
• v.8 no.4
• /
• pp.11-19
• /
• 2020

In an autonomous driving environment, dynamic recognition of objects is essential as the situation changes in real time. In addition, as the number of sensors and control modules built into an autonomous vehicle increases, the amount of data the central control unit has to process also rapidly increases. By minimizing the output data from the sensor, the load on the central control unit can be reduced. This study proposes a dynamic object recognition algorithm solely using the embedded processor on a LiDAR sensor. While there are open source algorithms to process the point cloud output from LiDAR sensors, most require a separate high-performance processor. Since the embedded processors installed in LiDAR sensors often have resource constraints, it is essential to optimize the algorithm for efficiency. In this study, an embedded processor based object recognition algorithm was developed for autonomous vehicles, and the correlation between the size of the point clouds and processing time was analyzed. The proposed object recognition algorithm evaluated that the processing time directly increased with the size of the point cloud, with the processor stalling at a specific point if the point cloud size is beyond the threshold

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.850-858
• /
• 2022

To deploy Gate Recurrent Units (GRU) on resource-constrained embedded devices, this paper presents a reconfigurable FPGA-based GRU accelerator that enables structured compression. Firstly, a dense GRU model is significantly reduced in size by hybrid quantization and structured top-k pruning. Secondly, the energy consumption on external memory access is greatly reduced by the proposed reuse computing pattern. Finally, the accelerator can handle a structured sparse model that benefits from the algorithm-hardware co-design workflows. Moreover, inference tasks can be flexibly performed using all functional dimensions, sequence length, and number of layers. Implemented on the Intel DE1-SoC FPGA, the proposed accelerator achieves 45.01 GOPs in a structured sparse GRU network without batching. Compared to the implementation of CPU and GPU, low-cost FPGA accelerator achieves 57 and 30x improvements in latency, 300 and 23.44x improvements in energy efficiency, respectively. Thus, the proposed accelerator is utilized as an early study of real-time embedded applications, demonstrating the potential for further development in the future.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.427-432
• /
• 2023

In this study, MEC (: Multi-access Edge Computing) proposes a cloud service network configuration for various tests of autonomous vehicles to which V2X (: Vehicle to Everything) is applied in Wave, LTE, and 5G networks and MEC App (: Application) applied V2X service function test verification of two domains (operator (KT, SKT, LG U+), network type (Wave, LTE (including 3G), 5G)) in a specific region. In 4G networks of domestic operators (SKT, KT, LG U+ and Wave), MEC summarized the improvement effects through V2X function blocks and traffic offloading for the purpose of bringing independent network functions. And with a high level of QoS value in the V2X VNF of the 5G network, the traffic steering function scenario was demonstrated on the destination-specific traffic path.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.1-7
• /
• 2023

The advent of deep learning technologies has led to the development of various medical applications, making healthcare services more convenient and effective. Among these applications, heart rate estimation is considered a vital method for assessing an individual's health. Traditional methods, such as photoplethysmography through smart watches, have been widely used but are invasive and require additional hardware. Recent advancements allow for contactless heart rate estimation through facial image analysis, providing a more hygienic and convenient approach. In this paper, we propose a lightweight methodology capable of accurately estimating heart rate in mobile environments, using a specialized 2-channel network structure based on 2D convolution. Our method considers both subtle facial movements and color changes resulting from blood flow and muscle contractions. The approach comprises two major components: an Encoder for analyzing image features and a regression layer for evaluating Blood Volume Pulse. By incorporating both features simultaneously our methodology delivers more accurate results even in computing environments with limited resources. The proposed approach is expected to offer a more efficient way to monitor heart rate without invasive technology, particularly well-suited for mobile devices.

• Journal of Practical Engineering Education
• /
• v.16 no.1_spc
• /
• pp.95-103
• /
• 2024

With the rapid decline of the school-age population, the competition for admissions has increased and marketing through digital channels has become more important, so universities are investing more resources in online promotion and communication to recruit new students. This study uses Google Analytics, a web log analysis tool, to track the visitor behavior of a university admissions website and establish a digital marketing strategy based on it. The analysis period was set from July 1, 2023, when Google Analytics 4(GA4) was integrated, to January 10, 2024, when the college admissions process was completed. The analysis revealed interesting patterns such as geographical information based on visitors' access location, devices(operating systems) and browsers used by visitors, acquisition channels through visitors traffic, conversions on pages and screens that visitors engaged with and visitor flow. Based on this study, we expect universities to find ways to strengthen their admission promotion through digital marketing and effectively communicate with applicants to gain a competitive edge.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.3
• /
• pp.127-143
• /
• 2022

Recently, many attempts to run numerical ocean models in cloud computing environments have been tried actively. A cloud computing environment can be an effective means to implement numerical ocean models requiring a large-scale resource or quickly preparing modeling environment for global or large-scale grids. Many commercial and private cloud computing systems provide technologies such as virtualization, high-performance CPUs and instances, ether-net based high-performance-networking, and remote direct memory access for High Performance Computing (HPC). These new features facilitate ocean modeling experimentation on commercial cloud computing systems. Many scientists and engineers expect cloud computing to become mainstream in the near future. Analysis of the performance and features of commercial cloud services for numerical modeling is essential in order to select appropriate systems as this can help to minimize execution time and the amount of resources utilized. The effect of cache memory is large in the processing structure of the ocean numerical model, which processes input/output of data in a multidimensional array structure, and the speed of the network is important due to the communication characteristics through which a large amount of data moves. In this study, the performance of the Regional Ocean Modeling System (ROMS), the High Performance Linpack (HPL) benchmarking software package, and STREAM, the memory benchmark were evaluated and compared on commercial cloud systems to provide information for the transition of other ocean models into cloud computing. Through analysis of actual performance data and configuration settings obtained from virtualization-based commercial clouds, we evaluated the efficiency of the computer resources for the various model grid sizes in the virtualization-based cloud systems. We found that cache hierarchy and capacity are crucial in the performance of ROMS using huge memory. The memory latency time is also important in the performance. Increasing the number of cores to reduce the running time for numerical modeling is more effective with large grid sizes than with small grid sizes. Our analysis results will be helpful as a reference for constructing the best computing system in the cloud to minimize time and cost for numerical ocean modeling.

• The Journal of the Korea Contents Association
• /
• v.14 no.4
• /
• pp.513-521
• /
• 2014

The purpose of this research is to develope and implement a convergent educational contents based on theoretical background of integrated education using agent based modeling in the ubiquitous learning environment. The structure of this contents consists of three modules that were designed by trans-disciplinary concept and situated learning theory. These three modules are: convergent problem presenting module, resource of knowledge module and learning of agent based modeling and IT tools module. After the satisfaction survey of the implemented content, out of 5 total value, the average value was 3.86 for effectiveness, 4.13 for convenience and 3.86 for design. The result of the survey shows that the users are generally satisfied. By using this u-learning contents, learners can experience and learn how to solve the convergent problem by utilizing IT tools without any limitation of device, time and space. At the same time, the proposal of structural design of contents can be a good guideline to the researchers to develop the convergent educational contents in the future.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.139-145
• /
• 2016

On the ICT healing platform designed to issue early disease alerts, TOS connected between the provider of personal health-related data and the service provider and relayed personalized health data. In the previous study, TOS proposed how to monitor the retrieval and management of document/measurement resources by taking mobile devices into account. Recently the healthcare field, however, defined the standard items needed for communication and data exchanges with a mobile device through HL7 FHIR. This study designed a data grid model between TOS and FHIR to provide personal health resources relayed through TOS in FHIR bundle search sets. The proposed design was organized as follows: first, it stated similarities between the method of TOS resource request and that of FHIR observation request. Then, it designed an eventbus module to process a retrieval request for FHIR service based on the imdb and cluster technologies. The proposed design can be used to expand the old service terminals of ICT healing platform to mobile health devices capable of using FHIR resources.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.11
• /
• pp.675-690
• /
• 2003

In this paper, we present the virtual dancing studio for distributed virtual environment. In this system, geographically distributed user shares the virtual dancing hall and interacts with each other. The participating object can be a graphical avatar or a live video stream. It allows the coexistence of graphic objects and real images in the shared virtual space. One of the main technical challenges in developing the distributed virtual environment is to handle excessive network traffic. In an effort to effectively reduce the network traffic, we propose a scheme to adjust the QoS of each object with respect to the distance from the observer in the virtual space. The server maintains the QoS vector for each client's shared space and controls the packet traffic to individual clients based on its QoS vectors. We develop a proto-type virtual dancing environment. Java based development enables the client to be platform independent. The result of experiment shows that the adoption of hierarchical QoS management significantly reduces the overall network traffic.

• Journal of Life Science
• /
• v.14 no.6 s.67
• /
• pp.991-996
• /
• 2004

This paper deals with an integrated system that facilitates researchers to do motif and domain search effectively and systematically. The system we developed is constructed on the basis of the integration of various resources related to motif, domain, and protein family. Those resources that can be classified into databases and search programs are dispersed to be available in Internet. In order to develop this system, we extracted core contents of diverse databases, which are required to analyze the protein function in terms of motifs or domains, to construct local databases and installed motif or domain search programs on our server, which corresponding database has as its own search program. Diverse utilities and CGI (Common Gateway Interface) programs make the databases and the search programs interlocked and web-based graphical user interfaces integrate all the components of our system. Employing our integrated system, end-users can receive its one-stop service to do protein function analysis systematically and effectively, without surfing many sites in Internet and wasting time over integrating search results.