• Smart Media Journal
• /
• v.11 no.9
• /
• pp.64-74
• /
• 2022

A number of studies related to underwater robots are being conducted to utilize marine resources. However, unlike ordinary drones, underwater robots have a problem that it is not easy to locate because the medium is water, not air. The monitoring and positioning program of underwater robots, an existing study for identifying underwater locations, has difficulty in locating and monitoring in small spaces because it aims to be utilized in large spaces. Therefore, in this paper, we propose a three-dimensional positioning program for continuous monitoring and command delivery in small spaces. The proposed program consists of a multi-dimensional positioning monitoring function and a ability to control the path of travel through a three-dimensional screen so that the depth of the underwater robot can be identified. Through the performance evaluation, a robot underwater could be monitored and verified from various angles with a 3D screen, and an error within the assumed range was verified as the difference between the set path and the actual position is within 6.44 m on average.

• Smart Media Journal
• /
• v.11 no.9
• /
• pp.9-20
• /
• 2022

Deep reinforcement learning(RL) is an end-to-end data-driven control method that is widely used in the autonomous driving domain. However, conventional RL approaches have difficulties in applying it to autonomous driving tasks due to problems such as inefficiency, instability, and uncertainty. These issues play an important role in the autonomous driving domain. Although recent studies have attempted to solve these problems, they are computationally expensive and rely on special assumptions. In this paper, we propose a new algorithm MCDT that considers inefficiency, instability, and uncertainty by introducing a method called uncertainty sequence modeling to autonomous driving domain. The sequence modeling method, which views reinforcement learning as a decision making generation problem to obtain high rewards, avoids the disadvantages of exiting studies and guarantees efficiency, stability and also considers safety by integrating uncertainty estimation techniques. The proposed method was tested in the OpenAI Gym CarRacing environment, and the experimental results show that the MCDT algorithm provides efficient, stable and safe performance compared to the existing reinforcement learning method.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.35-43
• /
• 2022

This paper studies how to improve the identification rate of laryngeal disability speech data by convolutional neural network (CNN) and machine learning ensemble learning methods. In general, the number of laryngeal dysfunction speech data is small, so even if identifiers are constructed by statistical methods, the phenomenon caused by overfitting depending on the training method can lead to a decrease the identification rate when exposed to external data. In this work, we try to combine results derived from CNN models and machine learning models with various accuracy in a multi-voting manner to ensure improved classification efficiency compared to the original trained models. The Pusan National University Hospital (PNUH) dataset was used to train and validate algorithms. The dataset contains normal voice and voice data of benign and malignant tumors. In the experiment, an attempt was made to distinguish between normal and benign tumors and malignant tumors. As a result of the experiment, the random forest method was found to be the best ensemble method and showed an identification rate of 85%.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.167-172
• /
• 2023

The P-3C maritime patrol aircraft operated by the Republic of Korea Navy is equipped with various sensor devices (LRUs, line replace units) for tactical data collection. Depending on the characteristics of the sensor device, it operates with various communication protocols such as IEEE 802.3, MIL-STD-1553A/B, and ARINC-429. In addition, the collected tactical data is processed in the tactical station for mission operators, and this tactical station constitutes a clustering network on Gigabit Ethernet and operates in a distributed processing method. For communication with the sensor device, a specific tactical station mounts a peripheral device (eg. ARINC-429 interface card). The problem is that the performance of the entire distributed processing according to the peripheral device control and communication relay of this specific device is degraded, and even the operation stop of the tactical station has a problem of disconnecting the communication with the related sensor device. In this paper, we propose a method to mount a separate gateway to solve this problem, and the validity of the proposed application is demonstrated through the operation result of this gateway.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.483-494
• /
• 2023

Recently, gas turbine generators are widely used for frequency control of power systems. Although the inlet temperature of a gas turbine is a key factor related to the performance and lifespan of the device, the inlet temperature is not measured directly for reasons such as the turbine structure and operating environment. In particular, the inlet temperature of the reheating gas turbine is very important for stable operation management, but field workers are experiencing a lot of difficulties because the manufacturer does not provide information on the calculation formula. Therefore, in this study, we propose a method for estimating the inlet temperature of a gas turbine using a machine learning-based linear regression analysis method based on a polytropic process equation. In addition, by proposing an inlet temperature calculation algorithm through the usefulness analysis and verification of the inlet temperature calculation model obtained through linear regression analysis, it is intended to help to improve the level of reheat gas turbine combustion tuning technology.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.6
• /
• pp.51-57
• /
• 2009

Wireless sensor networks consist of numerous sensor nodes that have inexpensive and limited resources. Generally, most of the sensors are assigned to the hazardous or uncontrollable environments. If the sensor nodes are randomly assigned to the wide target area, it is very hard to see the accurate locations of sensor nodes. Therefore, this study provides an efficient key distribution scheme to solve these problems. Based on the provided scheme, the study enabled the closely neighboring nodes to exchange information with each other after securing safe links by using the pre-distributed keys. At the same time, the provided scheme could increase the probability of multiparty key detection among nodes by using the location information of sensor node. Lastly, the study intended to show the superiority of the limitation method through a performance test.

• Journal of Internet of Things and Convergence
• /
• v.9 no.3
• /
• pp.1-6
• /
• 2023

One of the economical ways to satisfy the quality of service desired by the user in a web service environment is to adjust the size of the object. To this end, this study finds the maximum size of objects that satisfy this constraint when the mean response time is given below an arbitrary threshold for quality of service. It can be inferred that in the steady state of system, the mean response time in the deterministic model by using the round-robin will be the same as that of the queueing model following the general distribution. Based on this, analytical formulas and procedures for finding the maximum object size are obtained. As a service distribution of web traffic, the Pareto distribution is appropriate, so the maximum object size is computed by applying the M/G(Pareto)/1 model and the M/G/1/PS model using exponential distribution as computational experience. Performance evaluation through numerical calculation shows that as the shape parameter in the Pareto distribution increases, the M/G(Pareto)/1 model and M/G/1/PS model have the same maximum object size. The results of this study can be used to environments where objects can be sized for economical web service control.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.65-70
• /
• 2023

In recent years, the digital media environment has begun to diversify, with a greater focus being placed on user-centric design. With the development of digital technology, the digital media environment has formed a vast network of information, which supports interactive communication between people, creating a need for user-centric research. Mobile displays, as a representation of the digital media environment, have the advantage of mobility through the use of thin screen displays and low-performance image sensors, which allow for miniaturization and power saving. However, this results in reduced colour accuracy compared to large displays. This study investigates users' colour perception when using dark and light mode mobile displays. Colour perception was measured using a psycho-physical experiment, which controls each colour attribute based on the 12 colours of KS. The results were analysed to determine whether there is a difference in colour perception between dark mode and light mode, and if the difference was statistically significant. Future research directions based on the results are then discussed.

• Journal of IKEEE
• /
• v.26 no.1
• /
• pp.95-103
• /
• 2022

In this paper, the efficiency of a sensorless method with square-wave injection for a low-cost inverter, so called B4 inverter is presented. This inverter comprises only 4 switches to reduce system cost. It is distinguished from the conventional B6 inverter that has 6 of switching elements. The B4 inverter, injected a 1 kHz of harmonic wave, has been modelled using the functions and library in Matlab/Simulink. This paper described each component of sensorless algorithm. Among them, the Notch Filter is used to extract the harmonic component of the phase current and a second-order low-pass filter was used to reduce the ripple of the estimated speed. It is shown through simulation that the rotor angle of a permanent magnet synchronous motor is detected by multiplying the current waveform extracted using the notch filter by the harmonic voltage. The feasibility of the proposed method is shown through Simulink simulation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.61-61
• /
• 2021

온도 성층화는 많은 저수지와 댐에서 흔히 발생하는 현상으로 호수나 저수지의 표면 온도가 바닥보다 상대적으로 높아 깊이에 따른 열 구배를 나타낸다. 이러한 온도 성층화 현상은 여름철과 같이 상부와 하부의 온도 차가 클수록 안정적이게 나타나며 이러한 층화 현상으로 수직 확산이 제어되어 수질에 영향을 미친다고 알려져 있다. 따라서 댐이나 호수 등 층화 현상이 심한 유체 내부 바닥에 물순환장치를 설치하여 외부로부터 공기를 끌어와 하부에서 공기를 분출하여 온도 성층을 약화시키기도 한다. 물순환 장치를 설비하면 수체의 혼합이 용이해지며 물질전달이 개선되어 수질이 향상된다. 국내의 경우 대청댐, 보령댐, 영주 댐 등 많은 국내 댐 내부에 물순환장치가 설비되어있다. 본 연구에서 댐의 물순환장치의 성능을 파악하기 위해 산기식 물순환 장비가 설치되어있는 영주댐을 연구 대상 지역으로 잡았다. 연구지역의 계절별 성층구조 및 특성을 조사하기 위해, 봄, 여름, 가을 영주댐에 방문하여 관측 자료를 취득하였으며 물순환 장치는 봄철의 경우만 가동하였다. 봄철의 물순환 장치 가동 전후 관측 데이터를 바탕으로 수치모형실험을 실행하여 관측 결과와 비교 및 검증하였다. 이를 바탕으로 여름, 가을에 물순환장치를 가동하였을 경우 댐 내부 수체의 혼합과정을 살펴보는 연구를 진행하였다. 본 연구는 CFD (Computational Fluid Dynamic) 시뮬레이션을 수행하기 위해 오픈 소스 소프트웨어 OpenFOAM(version 4.0)에서 열 전달이 포함되어있는 비압축성 VOF 솔버를 사용하였다. 본 솔버는 물과 공기를 동시에 나타낼 수 있으며 온도의 확산 방정식을 포함하고 있다. 또한 유동해석 수행 시 사용한 물순환장치의 효울은 실제 장치의 효율과 동일하다. 본 연구의 목표는 다음과 같다. (1) 관측만으로 파악하기 어려운 수체의 혼합거동을 유동해석 자료를 통해 면밀히 살펴보고 (2) 봄철 물순환 장치가 작동하기 전후 자료를 바탕으로 여름 및 가을철 물순환장치 가동 전후 데이터를 유동해석 자료로 취득한다. (3) 또한 물순환장치 가동 전후 데이터를 통해 계절별 혼합 효율을 취득한다.