• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.429-430
• /
• 2023

본 논문에서는 사용자들의 면역력 향상과 체력 증진을 목적으로, 아침에 스트레칭을 실행하는 기능을 모닝콜 앱에 도입하였다. 이 앱은 사용자가 원하는 스트레칭과 횟수를 설정할 수 있으며, 모닝콜이 활성화되면 사용자가 알람을 강제로 종료할 수 없는 알고리즘을 적용했다. 해당 앱에 TTS를 적용하여 알람 활성화 시 안내 음성이 나오도록 설계하였다. 주 기능으로 설정된 목표 횟수만큼 적절한 자세로 스트레칭을 수행해야만 모닝콜이 종료되도록 구현하여, 사용자의 건강증진에 기여할 것이다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.115-122
• /
• 2022

With the outbreak of COVID-19 a few years ago, video conferencing and electronic document work have increased, and for this reason, the proportion of computer work among modern people's daily routines is increasing. However, as more and more people work on computers in the wrong posture for a long time, the number of patients with poor eyesight and text neck is increasing. Until recently, many studies have been published to correct posture, but most of them have limitations that users may experience discomfort because they have to correct posture by wearing equipment. A posture correction sensor algorithm is proposed to prevent access to the minimum distance between a computer monitor and a person using an ultrasonic sensor device. At this time, an algorithm for minimizing false alarms among warning alarms that sound at the minimum distance is also proposed. Because the ultrasonic sensor device is used, posture correction can be performed without attaching a device to the body, and the user can relieve discomfort. In addition, experimental results showed that accuracy can be improved by reducing false alarms by removing more than half of the noise generated during distance measurement.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.547-549
• /
• 2010

In this paper, we propose context-aware system for semiconductor equipment that acquires information from multiple sensors in indoor environment. This proposed system acquires information from acceleration, pressure, temperature and gas sensors then the acquired information send to server. The data transmitted to server generates an alarm via context-aware algorithm of unit event and multi event. From that result, high-quality real-time monitoring is possible because of the reduced unnecessary alarms, and the efficient management is possible because the surrounding information is recognized at once.

• Journal of Convergence Society for SMB
• /
• v.6 no.4
• /
• pp.25-30
• /
• 2016

This paper presents on the development of a compact anti-lost device requested recently. The proposed device consists of the master and slave modules based on Bluetooth4.1 technology. To implement a low-power characteristic, an algorithm has been also developed. The transmitting and receiving circuits are designed by using BoT CLE110 module supporting Bluetooth 4.1. The ATmega 328P-AU was used for the control and LP3874EMP was used as a linear regulator. Power consumption of the fabricated product in operating mode is only 10mAh and 35mAh for MCU operating state. Alarm operation distance is $10m{\pm}30%$, the effective radiated power is less than 10mW, the frequency band is designed to operate in the Bluetooth band with 26MHz bandwidth. And algorithms have been developed to extend the battery life. The size of the product was obtained as $45{\times}45{\times}15mm$ for master and $35{\times}35{\times}10mm$ fr slave. After the optimization process, it is expected to be commercialized as a wristwatch for anti-lost device.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.201-204
• /
• 2021

최근 전동 킥보드 사용량이 크게 늘었으나, 다른 이동수단 대비 낮은 안정성과 사용자들의 헬멧 착용에 대한 인식 부족으로 인해 사고의 위험성이 큰 상황이다. 이에 대하여 정부는 헬멧 착용을 강제하는 법률을 제정하였으나, 경찰력의 한계에 따른 단속 미비로 여전히 헬멧 착용율은 낮다. 본 연구는 YOLO v3 알고리즘을 통해 학습시킨 딥러닝 모델을 활용하여 도로 상황을 촬영한 동영상 내에서 헬멧 착용자와 미착용자를 구분하고 미착용자 탐지 시 알람을 제공하는 시스템을 제시한다. 기존 YOLO 알고리즘 및 신경망을 적용하되, 전동 킥보드 데이터를 새로 수집하고 클래스를 구분하여 학습시켰다. 소수의 탐지 및 분류 오류를 보정하기 위해, 히스토그램 간 유사도를 측정해 최종적으로 객체를 추적 및 확정하고, 객체에 대한 헬멧 착용 여부를 통계적으로 확인한다.

• Journal of Satellite, Information and Communications
• /
• v.12 no.2
• /
• pp.56-60
• /
• 2017

This paper describes the design and implementation of fall-down detection algorithm based on image processing. The fall-down detection algorithm separates objects by using background subtraction and binarization after grayscale conversion of the input image acquired by the camera, and recognizes the human body by using labeling operation. The recognized human body can be monitored on the display image, and an alarm is generated when fall-down is detected. By using computer simulation, the proposed algorithm has shown a detection rate of 90%. We verify the feasibility of the proposed system by verifying the function by using the prototype test implemented on the DSP image processing board.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.23-30
• /
• 2022

The failure of the reefer container causes a great loss of cost, but the current reefer container alarm system is inefficient. Existing studies using simulation data of refrigeration systems exist, but studies using actual operation data of refrigeration containers are lacking. Therefore, this study classified the causes of failure using actual refrigerated container operation data. Data imbalance occurred in the actual data, and the data imbalance problem was solved by comparing the logistic regression analysis with ENN-SMOTE and class weight with the 2-stage algorithm developed in this study. The 2-stage algorithm uses XGboost, LGBoost, and DNN to classify faults and normalities in the first step, and to classify the causes of faults in the second step. The model using LGBoost in the 2-stage algorithm was the best with 99.16% accuracy. This study proposes a final model using a two-stage algorithm to solve data imbalance, which is thought to be applicable to other industries.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.10
• /
• pp.95-102
• /
• 2016

Pipeline is making the most use of transportation of petroleum products on the land. But due to tremendous accident or environmental disaster by oil pipeline leak or pipeline stolen, leak detection systems have been used for preventing it. Leak detection method based on negative pressure wave has been used at the long distance pipeline. But even if it has showed good leak detection quality, due to making a lot of false alarm, it has weak point that disturbs concentration to system. This study suggests algorithm and method of using volume balance to decrease false-alarm of pipeline leak detection system based on negative pressure wave.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.1
• /
• pp.65-71
• /
• 2017

Since existing Internet of Things(IoT) is vulnerable, it may cause property damage due to the information leakage. Especially, the smart door lock system built on the IoT can cause more damage. To solve these problems, this paper classify the data generated by the sensor according to the condition and send an alarm message to the user's smartphone through Google Cloud Message (GCM). We made it possible to check the images in real time through the smartphone application and control the door lock using the TCP / IP protocol. Also, we applied OTP-Based Matrix SEED algorithm to door lock system to improve security.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.583-589
• /
• 2012

This Paper contained Managing the Memory With Virtual Server, building Database for Broadcast and statistics, architecture Can Easily Build up Each Analysis algorism and How to Broadcast Analysis outcome for Inteligent Vessel Navigation Analysis System. Also concrete Algorism and formula for each navigation analysis that we studed(Collision, Patten, Traffic separation, Danger Area So on).