• Journal of Platform Technology
• /
• v.11 no.4
• /
• pp.71-79
• /
• 2023

In this paper, we analyze the characteristics of machine learning workloads and, based on them, propose a distributed in-memory caching technique to improve the performance of machine learning workloads. The core of machine learning workload is model training, and model training is a computationally intensive task. Performing machine learning workloads in a Kubernetes-based cloud environment in which the computing framework and storage are separated can effectively allocate resources, but delays can occur because IO must be performed through network communication. In this paper, we propose a distributed in-memory caching technique to improve the performance of machine learning workloads performed in such an environment. In particular, we propose a new method of precaching data required for machine learning workloads into the distributed in-memory cache by considering Kubflow pipelines, a Kubernetes-based machine learning pipeline management tool.

• Journal of Platform Technology
• /
• v.12 no.2
• /
• pp.58-63
• /
• 2024

CNNs tend to take a long time to learn and consume a lot of power due to lack of system resources with many data processing units when there are repetitive handles that do not have high performance in the image field. In this paper, we propose a handling method based on a low-power bus that can increase the exchange rate of multipliers and multiplicands within the convolution mixer, which is a tendency activity that occurs when a convolution mixer has multiplication, which is the core element of combination. Convolutional neural networks have proprietary low-power shared processor support and the design was implemented on an Intel DE1-SoC FPGA board using Verilog-HDL. The experiments validated the performance by comparing it with the exchange rate of the multiplier originally proposed by Shen on MNIST's numeric image database.

• Journal of Aerospace System Engineering
• /
• v.9 no.2
• /
• pp.47-50
• /
• 2015

MSIP(Ministry of Science, ICT and Future Plaaning) established the 'space technology commercialization plan' at 2012. According to this plan, MSIP and KARI(Korea Aerospace Research Institute) are nuturing space-related venture companies so that those companies are increasing from 2013. In addition, MSIP and KARI held space-related idea festivals last two years, and will run start-up program (STAR-Exploration) this year.

• Journal of Platform Technology
• /
• v.11 no.5
• /
• pp.110-125
• /
• 2023

In this paper, we utilize time-series aircraft location data measured based on 2019 domestic airports to analyze Go-Around and UOC_D situations during the approach phase of domestic airports. Various clustering-based machine learning techniques are applied to determine the most appropriate analysis method for domestic aviation data through experimentation. The ADS-B sensor is solely employed to measure aircraft positions. We designed a model using clustering algorithms such as K-Means, GMM, and DBSCAN to classify abnormal situations. Among them, the RF model showed the best performance overseas, but through experiments, it was confirmed that the GMM showed the highest classification performance for domestic aviation data by reflecting the aspects specialized in domestic terrain.

• Composites Research
• /
• v.34 no.1
• /
• pp.8-15
• /
• 2021

In the shipbuilding and marine industry, as a technology for reducing the weight of parts to reduce energy and improve operational efficiency of ships is required, a method of applying fibers-reinforced composites which is high-strength lightweight materials, as part materials can be considered. In this study, the possibility of applying fibers-reinforced composites to the pipe support clamps was evaluated to reduce the weight of LNGC. The fibers-reinforced composites were manufactured using carbon fibers and glass fibers as reinforcing fibers. Through the computer simulation program, the properties of the reinforcing materials and the matrix materials of the composites were inversely calculated, and the performance prediction was performed according to the change in the properties of each fiber lamination pattern. In addition, the structural analysis of the clamps according to the thickness of the composites was performed through the finite element analysis program. As a result of the study, it was confirmed that attention is needed in selecting the thickness when applying the fibers-reinforced composites of the clamp for weight reduction. It is considered that it will be easy to change the shape of the structure and change the structure for weight reduction in future supplementary design.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.3
• /
• pp.97-103
• /
• 2019

Electronic contract systems are widely used to integrate and manage the contract management process based on the development of ICT technology. Recently, improvement methods using block chain technology are being studied. However, contract management systems have processing performance, security vulnerabilities, data entry, and service accessibility issues. In this paper, we propose a block - chain based contract management platform with block chain, smart contract, and Rest API. The suggested platform includes the RPBFT algorithm which solves the processing performance and security vulnerability of the existing consensus authentication algorithm, and the algorithm to prevent data entry and enhance transparency of participants. The block-chain-based contract management platform proposed in this paper provides a use environment with improved processing performance, security, reliability, and transparency, and can be used through API without burdening construction. Therefore, The effect can be expected.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.244-255
• /
• 2022

This study estimated and evaluated the high resolution (1km) gridded mountain meteorology data of daily mean, maximum and minimum temperature based on ASOS (Automated Surface Observing System), AWS (Automatic Weather Stations) and AMOS (Automatic Mountain Meteorology Observation System) in South Korea. The ASOS, AWS, and AMOS meteorology data which were located above 200m was classified as mountainous area. And the ASOS, AWS, and AMOS meteorology data which were located under 200m was classified as non-mountainous area. The bias-correction method was used for correct air temperature over complex mountainous area and the performance of enhanced daily coefficients based on the AMOS and mountainous area observing meteorology data was evaluated using the observed daily mean, maximum and minimum temperature. As a result, the evaluation results show that RMSE (Root Mean Square Error) of air temperature using the enhanced coefficients based on the mountainous area observed meteorology data is smaller as 30% (mean), 50% (minimum), and 37% (maximum) than that of using non-mountainous area observed meteorology data. It indicates that the enhanced weather coefficients based on the AMOS and mountain ASOS can estimate mean, maximum, and minimum temperature data reasonably and the temperature results can provide useful input data on several climatological and forest disaster prediction studies.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.3
• /
• pp.192-203
• /
• 2016

Uganda is a country blessed with the biggest number of mountain Gorillas in the whole world. These animals contribute at least 12% in revenue generation to the Tourism sector through tracking by both local and foreign tourists who pay for the tracking permits. However, Gorilla tracking is also a big challenge even in the presence of highly skilled and well-trained game rangers. Development and implementation of a secure Computer and Mobile based Gorilla Tracking (GT) system that uses GIS and GPS technologies would be the most ideal technology to use. Therefore, this study aimed to find out the critical factors that would affect the Behavioral Intention of the would-be users to successfully decide to use such GIS/GPS-GT system. We used the existing UTAUT model to integrate six factors such as Performance Expectancy, Effort Expectancy, Employee Peer Influence, Facilitating Conditions, Behavioral Intention and System Use. However, Infrastructure Availability and Non-Technical Facilitating Conditions were added to reflect Ugandan ICT context. This amended UTAUT model was used to carry out the survey. The questionnaire was emailed to 220 government employees in the fields of ICT, Tour and Travel, Environmental Groups officials and Farmers who garden near the game reserves. A total of 133 were obtained fully completed, whereas 127 were deemed usable thus yielding a response rate of 58%. The analysis results show that except for non-technical facilitating conditions, effort expectancy, peer influence, performance expectancy and infrastructure availability positively affects behavioral Intention to use GIS/GPS-GT. This indicates that people in Uganda don't bother about regulations and rules in regard to using information system. As long as the system does what they want it to, anything else does not matter. As an employee in an organization is told to use a system by their supervisor, they have no objection to otherwise they risk losing their job. This implies that, supervisors have a great responsibility in the process of developing, implementing and using the system in Uganda.

• Journal of Information Technology and Architecture
• /
• v.11 no.4
• /
• pp.393-407
• /
• 2014

The Government Informatization Policy Plan represents the government's technology policy vision and a set of ICT policy agenda and initiatives for the tenure of the government. The Policy Plan, however, normally produces an excess of disconcerted and superfluous ICT policy proposals from various policy units in the government. To cope with the superficiality of the ICT policy set in the Policy Plan, this paper proposes an analysis of the epistemology of the policy set. A policy is constructed as an argument and the structure of the policy argument is analysed using a model of argumentation. The findings show that the present informatization policy is driven by three epistemological motives - the production, consumption, and performance of the ICT Technology. The various assumptions and premises that underlie and direct the generation of ICT policy arguments with different motives are idenfied and then are exposed to strong rebuttal arguments to evaluate their epistemological tenability. The policy implications of the epistemological analysis are discussed in the end.

• Journal of Animal Science and Technology
• /
• v.65 no.3
• /
• pp.627-637
• /
• 2023

As the population and income levels rise, meat consumption steadily increases annually. However, the number of farms and farmers producing meat decrease during the same period, reducing meat sufficiency. Information and Communications Technology (ICT) has begun to be applied to reduce labor and production costs of livestock farms and improve productivity. This technology can be used for rapid pregnancy diagnosis of sows; the location and size of the gestation sacs of sows are directly related to the productivity of the farm. In this study, a system proposes to determine the number of gestation sacs of sows from ultrasound images. The system used the YOLOv7-E6E model, changing the activation function from sigmoid-weighted linear unit (SiLU) to a multi-activation function (SiLU + Mish). Also, the upsampling method was modified from nearest to bicubic to improve performance. The model trained with the original model using the original data achieved mean average precision of 86.3%. When the proposed multi-activation function, upsampling, and AutoAugment were applied, the performance improved by 0.3%, 0.9%, and 0.9%, respectively. When all three proposed methods were simultaneously applied, a significant performance improvement of 3.5% to 89.8% was achieved.