• Journal of the Korean Institute of Gas
• /
• v.24 no.6
• /
• pp.91-97
• /
• 2020

Lithium-ion batteries (LIBs) have a longer lifespan, higher energy density, and lower self-discharge rates than other batteries, therefore, they are preferred as an Energy Storage System (ESS). However, during years 2017-2019, 28 ESS fire accidents occurred in Korea, and accurate capacity estimation of LIB is essential to ensure safety and reliability during operations. In this study, data-driven modeling that predicts capacity changes according to the charging cycle of LIB was conducted, and developed models were compared their performance for the selection of the optimal machine learning model, which includes the Decision Tree, Ensemble Learning Method, Support Vector Regression, and Gaussian Process Regression (GPR). For model training, lithium battery test data provided by NASA was used, and GPR showed the best prediction performance. Based on this study, we will develop an enhanced LIB capacity prediction and remaining useful life estimation model through additional data training, and improve the performance of anomaly detection and monitoring during operations, enabling safe and stable ESS operations.

• Journal of Advanced Navigation Technology
• /
• v.25 no.4
• /
• pp.293-298
• /
• 2021

In general, the guided weapon seeker and the guided control device process the target, search, recognition, and capture information to indicate the state of the guided missile, and play a role in controlling the operation and control of the guided weapon. The signals required for guided weapons are gaze change rate, visual signal, and end-stage fuselage orientation signal. In order to process the complex and difficult-to-process missile signals of recent missiles in real time, it is necessary to increase the data processing speed of the missiles. This study showed the processing speed after applying the stop and go and inverse enumeration algorithm among the parallel algorithm methods of PINQ and comparing the processing speed of the signal data required for the guided missile in real time using the guided missile inspection program. Based on the derived data processing results, we propose an effective method for processing missile data when applying a parallel processing algorithm by comparing the processing speed of the multi-core processing method and the single-core processing method, and the CPU core utilization rate.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.93-101
• /
• 2023

In this paper, we propose a method of creating a 3D bounding box for an object using a vanishing point to increase the accuracy of object recognition in an image when recognizing an traffic object using a video camera. Recently, when vehicles captured by a traffic video camera is to be detected using artificial intelligence, this 3D bounding box generation algorithm is applied. The vertical vanishing point (VP1) and horizontal vanishing point (VP2) are derived by analyzing the camera installation angle and the direction of the image captured by the camera, and based on this, the moving object in the video subject to analysis is specified. If this algorithm is applied, it is easy to detect object information such as the location, type, and size of the detected object, and when applied to a moving type such as a car, it is tracked to determine the location, coordinates, movement speed, and direction of each object by tracking it. Able to know. As a result of application to actual roads, tracking improved by 10%, in particular, the recognition rate and tracking of shaded areas (extremely small vehicle parts hidden by large cars) improved by 100%, and traffic data analysis accuracy was improved.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.154-154
• /
• 2023

수질모니터링은 수자원 보존과 공중 보건에 있어 매우 중요하다. 기후변화로 인한 이상강우와 산업화 등의 이유로 비점오염물질 및 오염원 배출량이 증가하여 하천과 호소에 영양염류가 증가하게 된다. 영얌염류의 증가로 하천에 부영양화 상태가 지속된다면 녹조발생 등으로 인해 생태계에 부정적 영향을 초래하게 된다. 또한 부영양화는 원수의 유기물량 증가로 인해 처리비용 증가, 이취미 문제 등 인간에게도 직접적인 문제를 유발한다. 특히 우리나라의 경우 하천 취수율이 높은 국가이며, 낙동강 중상류 지역에는 산업시설이 과도하게 밀집되어 있어 하천에 오염물질 유입이 되어 부영양화가 된다면 심각한 문제를 유발하게 된다. TN은 부영양화의 중요한 지표다. 우리나라의 TN 측정은 시료 채수 후 실험실에서 수질오염공정 시험기준에 따라 진행이 된다. 실험실 분석은 TN 농도를 분석하는 일반적인 방법이며, 정확한 검출 및 정량화를 목표로 한다. 하지만 이러한 방식은 정교한 장비를 갖춘 전문 실험실 및 전문 인력을 필요로 한다. 환경부에서 주요 하천에 수질측정망을 설치하여 수질현황에 대한 종합적인 조사를 통해 수질변화 추세를 파악하는 것이 가능하지만, 실시간 TN 농도를 감지하는데 매우 제한적이다. 현재 조사방식은 TN 농도 증가로 인한 문제에 대해 초기대응을 하기에는 한계가 있다. 최근 센서의 발전으로 다양한 항목을 신속하고 지속적으로 모니터링 할 수 있게 되었다. TN에 대한 직접적인 센서 모니터링은 불가능 하지만 여러 측정 항목이 TN과 상관관계가 있는 것이 여러 연구에서 입증되었다. 이러한 결과를 바탕으로 본 연구에서는 오염도가 높은 낙동강을 대상으로 TN 예측에 대한 기초 연구를 진행하였다. 과거 측정된 자료를 활용하여 센서로 측정 가능한 항목을 통해 TN 예측을 진행하며, 실제 활용을 위해 회귀식을 도출하고자 한다. 최근 환경부에서 실시간 수질 현황 및 오염도를 파악하기 위해 자동측정망 지점을 늘리는 추세인데, 본 연구의 결과를 활용한다면 실시간 TN 예측에 대한 기초자료 활용될 수 있을 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.78-78
• /
• 2021

영상유속분석법은 비접촉식으로 유속을 측정하는 방법으로 특히 홍수시 하천의 표면유속을 안전하게 계측할 수 있어서 경제적이고 안전한 하천유속 측정 방법 중 하나이다. STIV는 영상의 휘도 정보를 시간 방향으로 나열하여 작성된 STI(Space-Time Image)에 나타나는 패턴의 기울기를 이용하여 유속을 산정하는 방법이다. 특히 STIV(Space-Time Image Velocimetry)는 기존 입자군의 상호상관법에 기초한 입자영상유속계와 달리 표식자의 유무와 상관없이 유속을 측정할 수 있어 적용성과 안정성이 확보된다. 하지만 영상의 상태가 불량한 경우 정확한 유속 측정이 난해하며 야간에는 별도의 조명 추가 및 태풍과 같은 악기상에서는 빗방울이 카메라에 맺히거나 수면의 진동, 구조물의 진동에 의한 영상의 상태가 불량하게 되어 측정 정도가 떨어진다. 이처럼 영상을 이용한 유속 계측에 있어 다양한 연구 및 기술개발이 요구되는 시점이다. 따라서 본 연구에서는 영상을 이용한 정확한 유속측정을 위해 STIV와 인공지능을 융합하여 정확한 유속 평가를 목적으로 한다. 우선 기존 STI에 의한 기울기 추정방법을 확장하여 딥러닝(CNN)에 의한 기울기 추정방법을 도입하였다. CNN은 일반적으로 이미지의 특성을 추출하는데 유용한 방법으로서 STI의 2차원 Fourier변환 이미지를 사용하여 패턴의 기울기를 감지하도록 학습하였고 적용 결과 기울기에 대한 인식율은 매우 양호하였으며 이를 이용한 실제 관측 영상에 적용한 결과 유속에 대한 정밀도도 매우 양호하게 나타났다. 또한 딥러닝을 적용한 STIV는 노이즈(진동, 화면 불량 등)가 있는 영상에서도 안정적으로 유속을 산정할 수 있으며 전파유속계를 이용한 실제 하천의 표면유속 관측치와 비교 검토 결과 매우 양호하게 유속을 평가하고 있는 것으로 나타났다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.771-780
• /
• 2024

In this study, we implemented a real-time pest detection and prediction system for a strawberry farm using a computer vision model based on the YOLOv5 architecture and an Isolation Forest Classifier. The model performance evaluation showed that the YOLOv5 model achieved a mean average precision (mAP 0.5) of 78.7%, an accuracy of 92.8%, a recall of 90.0%, and an F1-score of 76%, indicating high predictive performance. This system was designed to be applicable not only to strawberry farms but also to other crops and various environments. Based on data collected from a tomato farm, a new AI model was trained, resulting in a prediction accuracy of over 85% for major diseases such as late blight and yellow leaf curl virus. Compared to the previous model, this represented an improvement of more than 10% in prediction accuracy.

• Journal of the Microelectronics and Packaging Society
• /
• v.23 no.3
• /
• pp.21-29
• /
• 2016

In this paper, we developed a flexible transparent capacitive pressure sensor which can recognize X and Y coordinates and the size of force simultaneously by sensing a change in electrical capacitance. The flexible transparent capacitive pressure sensor was composed of 3 layers which were top electrode, pressure sensing layer, and bottom electrode. Silver nanowire(Ag NW)/poly(3,4-ethylenedioxythiophene): poly(styrenesulfonate) (PEDOT:PSS) hybrid film was used for top and bottom flexible transparent electrode. The fabricated capacitive pressure sensor had a total size of 5 inch, and was composed of 11 driving line and 19 sensing line channels. The electrical, optical properties of the Ag NW/PEDOT:PSS and capacitive pressure sensor were investigated respectively. The mechanical flexibility was also investigated by bending tests. Ag NW/PEDOT:PSS exhibited the sheet resistance of $44.1{\Omega}/square$, transmittance of 91.1%, and haze of 1.35%. Notably, the Ag NW/PEDOT:PSS hybrid electrode had a constant resistance change within a bending radius of 3 mm. The bending fatigue tests showed that the Ag NW/PEDOT:PSS could withstand 200,000 bending cycles which indicated the superior flexibility and durability of the hybrid electrode. The flexible transparent capacitive pressure sensor showed the transmittance of 84.1%, and haze of 3.56%. When the capacitive pressure sensor was pressed with the multiple 2 mm-diameter tips, it can well detect the force depending on the applied pressure. This indicated that the capacitive pressure sensor is a promising scheme for next generation flexible transparent touch screens which can provide multi-tasking capabilities through simultaneous multi-touch and multi-force sensing.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.2
• /
• pp.144-149
• /
• 2018

The eggs are incubated for 18 days through the generator and incubated in the developing incubator. During the developmental period, the weight loss of the fetus is correlated with the ventricular formation, and the proper ventricular formation is also associated with the healthy embryonic hatching and the egg hatching rate. However, in the incubator period of the domestic hatchery, it is a reality to acquire the resultant side by the Iranian standard weight measurement with the experience of the hatchery and the person concerned and the development period without the apparatus for measuring the present weight. As a result, prevalence of early mortality, hunger and illness during hatching are frequent. Monitoring the reduction of weaning weight is crucial to obtaining chick quality and hatching performance with weight changes within the development machine. Water loss is different depending on the size of eggs, egg shell, and elder group. We can expect to increase the hatching rate by measuring the weight change in real time and optimizing the ventilation change accordingly. There is a need to develop a real-time measurement system that can control 10 to 13% reduction of the total weight during hatching. The system through this study is a way to check the one - time directly when moving the existing egg, and it is impossible to control the measurement of the fetal water evaporation within the development period. Unlike systems that do not affect the hatching rate, four load cells are connected in parallel on the Arduino sketch board and the AT-command command is used to connect the mobile phone and computer in real time. The communication speed of Bluetooth was set to 15200 to match the communication speed of Arduino and Hyper-terminal program. The real - time monitoring system was designed to visually check the change of the weight of the fetus in the artificial incubator. In this way, we aimed to improve the hatching rate and health condition of the hatching eggs.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.122-130
• /
• 2008

In many applications of wireless sensor networks, sensed data can be classified either normal or urgent data according to its time criticalness. Normal data such as periodic monitoring is loss and delay tolerant, but urgent data such as fire alarm is time critical and should be transferred to a sink with reliable. In this paper, by exploiting these data characteristics, we propose a novel energy-efficient data-aware routing protocol for wireless sensor networks, which provides a high reliability for urgent data and energy efficiency for normal data. In the proposed scheme, in order to enhance network survivability and reliability for urgent data, each sensor node forwards only urgent data when its residual battery level is below than a threshold. Also, the proposed scheme uses different data delivery mechanisms depending on the data type. The normal data is delivered to the sink using a single-path-based data forwarding mechanism to improve the energy-efficiency. Meanwhile, the urgent data is transmitted to the sink using a directional flooding mechanism to guarantee high reliability. Simulation results demonstrate that the proposed scheme could significantly improve the network lifetime, along with high reliability for urgent data delivery.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.249-254
• /
• 2007

A mobile robot with various types of sensors and wireless camera is introduced. We show this mobile robot can detect objects well by combining the results of active sensors and image processing algorithm. First, to detect objects, active sensors such as infrared rays sensors and supersonic waves sensors are employed together and calculates the distance in real time between the object and the robot using sensor's output. The difference between the measured value and calculated value is less than 5%. We focus on how to detect a object region well using image processing algorithm because it gives robots the ability of working for human. This paper suggests effective visual detecting system for moving objects with specified color and motion information. The proposed method includes the object extraction and definition process which uses color transformation and AWUPC computation to decide the existence of moving object. Shape information and signature algorithm are used to segment the objects from background regardless of shape changes. We add weighing values to each results from sensors and the camera. Final results are combined to only one value which represents the probability of an object in the limited distance. Sensor fusion technique improves the detection rate at least 7% higher than the technique using individual sensor.