• Journal of Korea Multimedia Society
• /
• v.13 no.1
• /
• pp.10-16
• /
• 2010

As the study of ubiquitous computing environment has been very active in recent years, the senor network technology is considered to be a core technology of it. This wireless sensor network is enabled to sense and gather data of interest from its surroundings by sensor nodes applied in physical space. Each sensor node structuring the sensor network is demanded to execute the required service using limited resources. This limited usage of resources requires the sensor node to energy-efficiently perform in building wireless sensor network, which enables to extend the entire network life. This study structures a system able to monitor changing environment data on a real-time basis using a computer remotely as it energy-efficiently gathers and sends environment data of specific areas.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.3
• /
• pp.556-560
• /
• 2013

Recently, solutions to accommodate explosively growing mobile data traffic have attracted intensive attentions since the emergence of high-performance smartphones. Spectrum which can be exploited for mobile communications is very limited. Thus, femto cell is considered as an alternative because it can efficiently offload mobile data traffic from macro cells without using additional spectrum. In this paper, we mathematically analyzed the coverage of femto cell when it is deployed in an area where there exists signals from existing macro base stations. Our numerical results indicate that the coverage of femto cell increases as the total power of femto cell increases or the ratio of power allocated to pilot channel increases. However, it is also shown that the coverage of femto cell is very limited despite its high power when interference signals from macro base stations are strong.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3211-3230
• /
• 2014

Recently, sparse coding has achieved remarkable success in image representation tasks. In practice, the performance of clustering can be significantly improved if limited label information is incorporated into sparse coding. To this end, in this paper, a novel semi-supervised algorithm, called constrained sparse concept coding (CSCC), is proposed for image representation. CSCC considers limited label information into graph embedding as additional hard constraints, and hence obtains embedding results that are consistent with label information and manifold structure information of the original data. Therefore, CSCC can provide a sparse representation which explicitly utilizes the prior knowledge of the data to improve the discriminative power in clustering. Besides, a kernelized version of our proposed CSCC, namely kernel constrained sparse concept coding (KCSCC), is developed to deal with nonlinear data, which leads to more effective clustering performance. The experimental evaluations on the MNIST, PIE and Yale image sets show the effectiveness of our proposed algorithms.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.2
• /
• pp.1-9
• /
• 2020

A smart factory is a key industrial application introduced by the 4^th industrial revolution. The automatic guided vehicle (AGV) is one of the technology realizing smart factory, but the development cost is high due to its early stage of technology. Although developing a low-cost AGV requires a lot of data, it has limited data acquisition capability because of the limited storage and the AGV movement. Hence, we propose a development environment using Bluetooth to collect data and design a lane detector. The proposed lane detector shows a high lane detection ratio regardless of light variation and a shade.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.724-736
• /
• 2019

Dynamic thermal rating technology can effectively improve the thermal load capacity of transmission lines. However, its availability is limited by the quantity and high cost of the hardware facilities. This paper proposes a new dynamic thermal rating technology based on global/regional assimilation and prediction system (GRAPES) and geographic information system (GIS). The paper will also explore the method of obtaining any point meteorological data along the transmission line by using GRAPES and GIS, and provide the strategy of extracting and decoding meteorological data. In this paper, the accuracy of numerical weather prediction was verified from the perspective of time and space. Also, the 750-kV transmission line in Shaanxi Province is considered as an example to analyze. The results of the study indicate that dynamic thermal rating based on GRAPES and GIS can fully excavate the line power potential without additional cost on hardware, which saves a lot of investment.

• Food Science and Industry
• /
• v.50 no.1
• /
• pp.16-25
• /
• 2017

There is no doubt that accumulation of big data using multi-omics technologies will be useful to solve human's long-standing problems such as development of personalized diet and medicine, overcoming diseases, and longevity. However, in the food industry, big data based on omics is scarcely accumulated. In particular, comprehensive analysis of molecular lipid metabolites directly associated with food quality, such as taste, flavor, and texture has been very limited. Moreover, most of food lipidomics studies are applied to analyze lipid components and discriminate authenticity and freshness of limited foods including vegetable and fish oil. However, if lipid big data through food lipidomics research of various foods and materials can be accumulated, lipidomics can be used in the optimization of food processing, production, delivery system, food safety, and storage as well as functional food.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.1
• /
• pp.17-24
• /
• 2023

With the continuous growth in the amount of data collected and analyzed, deep learning has become increasingly popular for extracting meaningful insights from various fields. However, hardware limitations pose a challenge for achieving meaningful results with limited data. To address this challenge, this paper proposes an algorithm that leverages the characteristics of convolutional neural networks (CNNs) to reduce the size of image datasets by 20% through smoothing and shrinking the size of images using color elements. The proposed algorithm reduces the learning time and, as a result, the computational load on hardware. The experiments conducted in this study show that the proposed method achieves effective learning with similar or slightly higher accuracy than the original dataset while reducing computational and time costs. This color-centric dataset construction method using image smoothing techniques can lead to more efficient learning on CNNs. This method can be applied in various applications, such as image classification and recognition, and can contribute to more efficient and cost-effective deep learning. This paper presents a promising approach to reducing the computational load and time costs associated with deep learning and provides meaningful results with limited data, enabling them to apply deep learning to a broader range of applications.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.94-97
• /
• 2022

The emerging energy harvesting technology, which has been successfully integrated into Wireless Sensor Networks, enables sensor batteries to be charged using renewable energy sources. In the meantime, the problem of Minimum Latency Aggregation Scheduling (MLAS) in battery-powered WSNs has been well studied. However, because sensors have limited energy harvesting capabilities, captured energy is limited and varies greatly between nodes. As a result, all previous MLAS algorithms are incompatible with Battery-Free Wireless Sensor Networks (BF-WSNs). We investigate the MLAS problem in BF-WSNs in this paper. To make the best use of the harvested energy, we build an aggregation tree that leverages the energy harvesting rates of the sensor nodes with an intuitive explanation. The aggregation tree, which determines sender-receiver pairs for data transmission, is one of the two important phases to obtain a low data aggregation latency in the BF-WSNs.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.608-615
• /
• 2022

Construction projects are large-scale projects that require extensive construction costs and resources. Especially, scheduling is considered as one of the essential issues for project success. However, the schedule and resource management are challenging to conduct in high-tech construction projects including complex design of MEP and architectural finishing which has to be constructed within a limited workspace and duration. In order to deal with such a problem, this study suggests resource and sequence optimization using constraint programming in construction projects. The optimization model consists of two modules. The first module is the data structure of the schedule model, which consists of parameters for optimization such as labor, task, workspace, and the work interference rate. The second module is the optimization module, which is for optimizing resources and sequences based on Constraint Programming (CP) methodology. For model validation, actual data of plumbing works were collected from a construction project using a five-minute rate (FMR) method. By comparing actual data and optimized results, this study shows the possibility of reducing the duration of plumbing works in construction projects. This study shows decreased overall project duration by eliminating work interference by optimizing resources and sequences within limited workspaces.

• Journal of Animal Science and Technology
• /
• v.65 no.6
• /
• pp.1254-1269
• /
• 2023

This study aims to predict the change in corn share according to the grazing of 20 gestational sows in a mature corn field by taking images with a camera-equipped unmanned air vehicle (UAV). Deep learning based on convolutional neural networks (CNNs) has been verified for its performance in various areas. It has also demonstrated high recognition accuracy and detection time in agricultural applications such as pest and disease diagnosis and prediction. A large amount of data is required to train CNNs effectively. Still, since UAVs capture only a limited number of images, we propose a data augmentation method that can effectively increase data. And most occupancy prediction predicts occupancy by designing a CNN-based object detector for an image and counting the number of recognized objects or calculating the number of pixels occupied by an object. These methods require complex occupancy rate calculations; the accuracy depends on whether the object features of interest are visible in the image. However, in this study, CNN is not approached as a corn object detection and classification problem but as a function approximation and regression problem so that the occupancy rate of corn objects in an image can be represented as the CNN output. The proposed method effectively estimates occupancy for a limited number of cornfield photos, shows excellent prediction accuracy, and confirms the potential and scalability of deep learning.