• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.43-54
• /
• 2024

Recently, there has been a lot of research on utilizing Language Models, and Large Language Models have achieved innovative results in various tasks. However, the practical application faces limitations due to the constrained resources and costs required to utilize Large Language Models. Consequently, there has been recent attention towards methods to effectively utilize models within given resources. Curriculum Learning, a methodology that categorizes training data according to difficulty and learns sequentially, has been attracting attention, but it has the limitation that the method of measuring difficulty is complex or not universal. Therefore, in this study, we propose a methodology based on data heterogeneity-based Curriculum Learning that measures the difficulty of data using reliable prior information and facilitates easy utilization across various tasks. To evaluate the performance of the proposed methodology, experiments were conducted using 5,000 specialized documents in the field of information communication technology and 4,917 documents in the field of healthcare. The results confirm that the proposed methodology outperforms traditional fine-tuning in terms of classification accuracy in both LoRA fine-tuning and full fine-tuning.

• Journal of IKEEE
• /
• v.25 no.1
• /
• pp.193-200
• /
• 2021

In order to prevent illegal fishing and reduce lost fishing gear, it is necessary to develop a constant and continuous fishing gear monitoring system in the marine environment. In this paper, we design a long-term operational, reliable system model with communication coverage of more than 25Km considering the reality of gradually expanding fishing activity due to the depletion of fishery resources and marine environments. The design results are implemented to verify the operability of the system by separating the communication success rate of SKT and private LoRa networks and verifying the control function of each control system through the collected location information, respectively.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2018.11a
• /
• pp.55-56
• /
• 2018

In order to reduce the risk of accidents, we proposed a construction safety management system combined with wearable device and LoRa (Low-Range Wireless Network) communication method to apply the usefulness of Internet (IoT) technology which means "everything connected". to construction safety management Management system. The proposed wearable safety device is a device that relays information exchange between wearable safety device and safety management server by LoRa wireless communication method. The safety management server can store workers bio-data and perform big data analysis. If a risk factor is determined from the analysis result, a warning is sent to the wearable safety device and the manager's application. The goal of this system is to prevent construction workers from entering the dangerous area that is not suitable for work, and to prevent safety accidents caused by human cause by detecting abnormal condition during work.

• Journal of Korea Multimedia Society
• /
• v.24 no.9
• /
• pp.1211-1223
• /
• 2021

Internet of Things(IoT) services have increased the demand for connectivity among electronics devices. As a result, various types of novel wireless communication technologies have been standardized and developed. In this paper, we evaluate the performance of low power wireless communication technologies such as Bluetooth, IEEE 802.15.4, DASH 7, IEEE 802.15.4g, LoRa, and SigFox in various environments. This is the first experiment evaluating various low power wireless communication technologies in real testbed. We expect that the evaluation results will be useful data to other researchers in applying the IoT technology in the future.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.109-114
• /
• 2022

This paper proposes a 2D joystick and LoRa-based teleoperation system for the Ackermman steering mobile robot. The proposed joystick mapping algorithm reduces the linear speed of the robot when the joystick is steered in the direction of the maximum steering angle in the high-speed driving state of a mobile robot to reduce the risk of rollover. The LoRa-based remote operation system is designed for remote operation of mobile robots that require long range communication with relatively little data transmission and low power. The proposed system is implemented and the experimental results demonstrate the effectiveness of the teleoperation system with respect to the stability of communication strength and the robot motion.

• Journal of Advanced Navigation Technology
• /
• v.22 no.5
• /
• pp.485-489
• /
• 2018

For the construction of smart factory that are part of the Fourth Industrial Revolution, data from the production environments and production machines should be collected, analyzed, and feedback should be given to predict when failures take place or parts should be replaced. For this purpose, a system that monitors the production environments and the status of the production machines are required. In this paper, the monitoring system for mobile devices and PC is implemented by collecting environmental data from production sites and sensor data of production machine using LoRa, a low-power wireless communication technology. On the mobile devices, production environments and vibration data can be displayed in real time. In PC monitoring program, sensor data can be displayed graphically to check standard deviation and data variation. The implemented system is used to collect data such as temperature, humidity, and atmospheric pressure of the production environment, and vibration data of production machines.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.285-287
• /
• 2017

Currently, the world of data communication is not simply communication between server and user in a wired way, but using wireless environment, various devices communicate with each other in a wider and diverse environment to generate a large amount of data. In this environment, IoT is now located deep in our lives, and IoT technologies are used in many tasks, but the data used in IoT is exposed without sufficient protection from malicious behavior. Most of these devices do not have enough computing power to cope with malicious attacks. In this paper, we aim to make all devices that have sufficient computing power and safety from simple sensors to be able to have security according to the situation. The proposed technology is based on the importance of the device and computing power, and it is possible to select the encryption technology selectively and to improve security.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.1
• /
• pp.74-82
• /
• 2019

The revolution of industry 4.0 is enabling us to build an intelligent connection society called smart cities. The use of renewable energy in particular solar energy is extremely important for modern society due to the growing power demand in smart cities, but its difficult to monitor and manage in each buildings since need to be deploy low energy sensors and information need to be transfer via wireless sensor network (WSN). The Internet of Things (IoT) / low-power wide-area (LPWA) is an emerging WSN technology, to collect and monitor data about environmental and physical electrical / electronics devices conditions in real time. However, providing power to IoT sensor end devices and other public electrical loads such as street lights, etc is an important challenging role because the sensor are usually battery powered and have a limited life time. In this paper, we proposes an efficient solar energy-based power management scheme for smart city based on IoT technology using LoRa wide-area network (LoRaWAN). This approach facilitates to maintain and prevent errors of solar panel based energy systems. The proposed solution maximizing output the power generated from solar panels system to distribute the power to the load and the grid. In this paper, we proved the efficiency of the proposed system with Simulink based system modeling and real-time emulation.

• Journal of Platform Technology
• /
• v.9 no.1
• /
• pp.32-39
• /
• 2021

Existing environmental measuring devices mainly focus on electromagnetic wave and eco-friendly product certification and durability test, and sensor reliability verification and verification of measurement data are conducted mainly through sensor performance evaluation through type approval and registration, acceptance test, initial calibration, and periodic test. This platform has established an ICT-based environmental monitoring sensor reliability verification system that supports not only performance evaluation for each target sensor, but also a verification system for sensor data reliability. A sensor board to collect sensor data for environmental information was produced, and a sensor and data reliability evaluation and verification service system was standardized. In addition, to evaluate and verify the reliability of sensor data based on ICT, a sensor data platform monitoring prototype using LoRa communication was produced, and the test was conducted in smart cities. To analyze the data received through the system, an optimization algorithm was developed using machine learning. Through this, a sensor big data analysis system is established for reliability verification, and the foundation for an integrated evaluation and verification system is provide.

• Journal of Advanced Navigation Technology
• /
• v.24 no.6
• /
• pp.613-619
• /
• 2020

Hybrid media access control (MAC) is used in internet of things (IoT) network, because of communication feature concern with data capacity and communication interval between gateway and sensor nodes and the cost efficiency. Hybrid MAC consists of TDMA and CSMA generally. The distance between gateway and sensor node is openly changed in marine IoT network. Therefore, it is needed to control the period of timeslot of hybrid MAC used in marine IoT network. In this paper, the design rule of TDMA timeslot with the variable period depending on communication distance was proposed. It was confirmed from the analysis that 72 times communication between gateway and sensor nodes is possible in LoRa network by using the proposed TDMA variable timeslot scheme.