• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.199-208
• /
• 2017

Lithium polymer batteries are used in energy storage systems (ESS), electric vehicles (EVs), etc. due to their high safety, fast charging and long lifecycle, and now they are used in agricultural drones. However, when overcharging and overdischarging, the lithium-polymer battery is destroyed in the gap structure in the lithium-ion battery and the battery life is reduced. In order to prevent overcharge and overdischarge, uneven cell voltage Cell balancing system is needed. In this paper, a fuzzy controller suitable for nonlinear systems is proposed by detecting the unbalanced cells by detecting the voltage difference between charging and discharging of each cell, and suggesting the applied cell balancing algorithm. In this paper, we have designed the cell balancing of the battery pack of agricultural drones by fuzzy control and it is designed for equal control between cells. As a final result, we checked whether cell balancing is good, and when there are two cells, Cell balancing was confirmed. We tested whether it could be used for other products. As a result, we confirmed that cell balancing is good regardless of the number of cells used.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.97-102
• /
• 2017

Recently deep learning techniques such as convolutional neural networks (CNN) have been introduced to classify high-resolution remote sensing data. In this paper, we investigated the possibility of applying CNN to crop classification of farmland images captured by drones. The farming area was divided into seven classes: rice field, sweet potato, red pepper, corn, sesame leaf, fruit tree, and vinyl greenhouse. We performed image pre-processing and normalization to apply CNN, and the accuracy of image classification was more than 98%. With the output of this study, it is expected that the transition from the existing image classification methods to the deep learning based image classification methods will be facilitated in a fast manner, and the possibility of success can be confirmed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.283-284
• /
• 2018

최근 4차 산업 혁명의 시대가 시작되면서 IT, 사물 인터넷(IOT), 자율 주행 자동차, 드론 등 많은 분야에 있어서 일상생활의 편리함이 증가 하고 있는 추세이다. 하지만 긴박한 상황 시 사고 현장에 대한 빠른 출동 등과 같은 응급 상황에 필요한 분야의 개발은 제한적이다. 본 과제는 이러한 문제점들을 해결하기 위해 드론과 구급차를 결합하여 수직이착륙이 가능한 구급차를 제작할 것이다. 수직 이착륙이 가능한 구급차를 도입함으로써 도로 위 교통에 대한 문제점과 차로 이동이 어려운 환경에서 보다 빠르게 사고현장에 투입하여 인명 구조와 사고 현장을 수습하여 피해를 감소시키고자 한다.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.493-498
• /
• 2020

The fourth industrial revolution is the first topic thrown by Klaus Schwab at the Davos World Economic Forum in January 2016, meaning the next industrial revolution led by the Internet of Things (IOT), artificial intelligence (AI), robot technology and life sciences. In addition, in our lives, humans, computers and machines are connected organically, and organic relationships are evolving and developing at a furious rate in all areas of life. Since the 1953 armistice agreement, South Korea has remained in a state of confrontation with North Korea, and there have been continued fighting by the North, including naval skirmishes in the West Sea, artillery attacks on Yeonpyeong Island, the sinking of the Cheonan warship, and unmanned aerial vehicles and ankle mines. To prepare for such a local initiative, our military is constantly preparing and will have to strengthen its combat capabilities by developing and introducing advanced military equipment. After all, the military drone industry linked to the Fourth Industrial Revolution following the development of new war should continue its research on military drones in line with accurate diagnosis and the rapid development of future science and technology and IT technologies.

• Journal of the Korean Institute of Gas
• /
• v.25 no.5
• /
• pp.88-96
• /
• 2021

Advanced Internet of Things (IoT) technology is being used in various ways for the safety of the energy industry. At the center of safety measures, drones play various roles on behalf of humans. Drones are playing a role in reaching places that are difficult to reach due to large-scale facilities and space restrictions that are difficult for humans to inspect. In this study, the accuracy and completeness of movement of dangerous facilities were tested using drone images, and it was confirmed that the movement recognition accuracy was 100%, the average data analysis accuracy was 95.8699%, and the average completeness was 100%. Based on the experimental results, a future-oriented facility risk analysis system combined with ICT technology was implemented and presented. Additional experiments with diversified conditions are required in the future, and ICT convergence analysis system implementation is required.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.44-51
• /
• 2018

The purpose of this research is to collect atmospheric environmental information at specific altitudes in a range of 0 to 1 km above the surface and to monitor it using drones. The corresponding temperature and humidity were measured with the meteorological factors, and the amounts of fine dust and $CO_2$ were observed by the environmental factors so that they could receive the normal values. Monitoring the status of atmospheric gas emission in specific enterprises, industrial complexes and regions through the measurement is meant to help establish policies to reduce pollution factors. In conventional means previously practiced, exhaust gas detection accompanies a great deal of risks in terms of safety because the surveyor is directly exposed to the source of contamination such as the holes installed in the chimney. However, in our proposed method, the drone can collect information in a wide range under safe circumstances, which can be utilized through wide industrial areas.

• Annual Conference of KIPS
• /
• 2016.04a
• /
• pp.289-291
• /
• 2016

최근 정보통신기술의 눈부신 발전으로 사람-사람, 사람-사물, 사물-사물 각각을 연결하여 최대한의 시너지를 발휘하려는 움직임이 활발해지고 있다. 즉 일상생활에서 사용되는 자동차, 가전제품, 드론 등의 제품도 연결되어 통신하는 사물인터넷 시대가 도래 하고 있다. 머지않아 모든 기기가 연결되는 시대가 오면 물리적 보안 보다 논리적 보안이 중요해 질 것이다. 또한 사물인터넷 해킹은 정보보호라는 단위를 넘어 사람의 생명과 직결되는 해킹 피해가 발생할 위험이 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.697-700
• /
• 2020

고위험의 재난 상황에서 사람이 상황을 판단하고, 요구조자를 탐색하며, 구조하는 것은 추가 피해를 발생시킬 수 있다. 따라서 재난 상황에서도 이동과 접근이 용이한 무인항공에 관한 연구와 개발이 활발히 이루어지고 있다. 재난 상황에서 신속하게 대처하기 위해서는 선제적 상황인지 기술이 필요하다. 이에 본 논문은 구조 및 대피를 위해 사람, 자동차, 자전거 등의 객체를 인식하고 중복 인식을 피하기 위해 추적하는 딥러닝 기반 다중 객체 추적 시스템을 제안한다. 2019 인공지능 R&D 그랜드 챌린지 상황인지 부문에서의 대회 결과로 실험 성능을 증명한다.

• Convergence Security Journal
• /
• v.16 no.3_2
• /
• pp.25-32
• /
• 2016

Drone refers to an unmanned flying system according to the remote control. That is a remote control systems on the ground or a system that automatically or semi auto-piloted system without pilot on board. Drones have been used and developed before for military purposes. However there are currently utilized in a variety of areas such as logistics and distribution of relief supplies disaster areas, wireless Internet connection, TV, video shooting and disaster observation, tracking criminals etc. Especially it can be actively used in activities such as search or the structure of the disaster site, and may be able to detect the movement of people and an attacker using an infrared camera at night. Drones are very effective for private security.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.342-350
• /
• 2022

In this paper, actual drone noise samples are collected for speech processing in disaster environments to build noise-corrupted speech database, and speech enhancement performance is evaluated by applying spectrum subtraction and mask-based speech enhancement techniques. To improve the performance of VoiceFilter (VF), an existing deep neural network-based speech enhancement model, we apply the Self-Attention operation and use the estimated noise information as input to the Attention model. Compared to existing VF model techniques, the experimental results show 3.77%, 1.66% and 0.32% improvements for Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligence (STOI), respectively. When trained with a 75% mix of speech data with drone sounds collected from the Internet, the relative performance drop rates for SDR, PESQ, and STOI are 3.18%, 2.79% and 0.96%, respectively, compared to using only actual drone noise. This confirms that data similar to real data can be collected and effectively used for model training for speech enhancement in environments where real data is difficult to obtain.