• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.23-30
• /
• 2020

In this study, the relationship between natural gas (NG) data and gas-related environmental elements was performed using machine learning algorithms to predict the level of gas leakage risk without directly measuring gas leakage data. The study was based on open data provided by the server using the IoT-based remote control Picarro gas sensor specification. The naturel gas leaks into the air, it is a big problem for air pollution, environment and the health. The proposed method is multivariate outlier removing method based Random Forest (RF) classification for predicting risk of NG leak. After, unsupervised k-means clustering, the experimental dataset has done imbalanced data. Therefore, we focusing our proposed models can predict medium and high risk so best. In this case, we compared the receiver operating characteristic (ROC) curve, accuracy, area under the ROC curve (AUC), and mean standard error (MSE) for each classification model. As a result of our experiments, the evaluation measurements include accuracy, area under the ROC curve (AUC), and MSE; 99.71%, 99.57%, and 0.0016 for MOL_RF respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1300-1305
• /
• 2020

Due to the simplicity of communication structure using RS-232 and RS-422, the majority ships have still adapted on these communication interfaces and have constructed their own communication network in the ship. NMEA-0183 is the one of standards for BNWAS(Bridge Navigational Watch Alarm System) and currently being used in many countries. BNWAS utilises diverse sensor devices, GPS, AIS and so on for monitoring the status of ships and their deployments and environmental information(temperature, humidity, wind speed/direction, water temperature/current etc…). This paper proposes the use of any image sensors in NMEA-0183 environment and verifies possibility with certain video qualities through the experiment results. Furthermore the paper gathers videos and monitors the change of their qualities depending on the number of NMEA messages on RS-232 communication link. Finally we make conclusion that our proposal is sufficiently appropriate for ship monitoring system in the NMEA-0183.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1624-1630
• /
• 2019

With the increase in there are smart devices penetration around the world, services related to exercise checks are attracting attention. However, there is existing exercise amount measurement service does not use the altitude information, or because the use of an algorithm that does not corrected the GPS altitude error is not accurate movement distance provided have a problem. Therefore, in this paper, to improve the existing problems, Kalman-filter-based user movement distance measurement algorithm is designed and implementation of improved by using the Kalman-filter based GPS and barometric altimeter sensor fusion algorithm to improve the altitude value the accuracy and of calculate the coordinate plane distance. As a result of comparing the designed and implementation of algorithm with the existing algorithms, it is confirmed that the proposed algorithm improves the accuracy by about 2.17%.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.2
• /
• pp.147-154
• /
• 2021

In this paper, the configuration and design of the test equipment are presented to examine the impact of rapid temperature change in cooling-air that may occur during the operation of the fixed wing aircraft Environmental Control System (ECS) on avionic electronic equipment. At the start of the ECS, the temperature of the air supplied by the aircraft ECS may be increased to 5.0℃ per second. In order to ensure operating of the avionic electronic equipment that is mounted on the aircraft and receives cooling-air from the ECS, testing equipment that can implement the cooling-air characteristic test environment is required. During design of test equipment was verified cooling-air rapid rate of temperature change by performing a thermal/flow analysis, performance of the test equipment implemented was verified by applying an avionic electronic equipment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.5
• /
• pp.13-24
• /
• 2005

Due to the changes in the wireless information environment, there has been an increased demand for various types of information. Accordingly, many wireless communication technologies have been studied and developed. In particular, studies on ubiquitous communications are well underway. Lately, the focus has been on the Bluetooth technology due to its applicability in various environments. Applying Bluetooth connectivity to new environments such as ubiquitous or sensor networks requires finding new wars of using it. Thus, this research analyzed the vulnerability on the limited number of slaves in a piconet configuration through the current Bluetooth communication and proposed an expanded Bluetooth piconet formation method, regardless of the number of slaves inside the piconet even if it is not configured in a scatternet. In the proposed method, we applied a security service and resolved the vulnerabilities of the current piconet by configuring an expanded form of the current tree-shaped structure.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.88-95
• /
• 2020

In this paper, we propose a new arm swing walking pattern-based walking safety system for safe walking of elderly pedestrians. The proposed system is a walking safety system for elderly pedestrians using haptic-based devices such as smart bands and smart watches, and arm swing-based walking patterns to solve the problem that it is difficult to recognize the fall situation of pedestrians with the existing walking patterns of lower limb movements. Use. The arm swing-based walking pattern recognizes the number of steps and the fall situation of pedestrians through the swing of the arm using the acceleration sensor of the device, and creates a database of the location of the fall situation to warn elderly pedestrians when walking near the expected fall location. It delivers a message to provide pedestrian safety to the elderly. This system is expected to improve the safe walking rights and environment of the elderly.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1325-1330
• /
• 2020

New-born babies who require special attention medically are admitted often to incubator. Incubators are well equipped to fulfill take care of infants, but they have to hospital and so expensive. This paper proposes a smart incubator that can solve the problem of convenience and cost aspect of these incubators. Developed incubator enables near-field monitoring using Arduino Uno as the main control device and Bluetooth communication. The environment in the incubator measures temperature and humidity using a DHT22 sensor and the sound using a P5510 microphone. If the temperature and humidity data set by the user are lower or higher than the reference value, it is designed to operate the heating pad using the controller or turn on the fan to allow air circulation. The measured values in the incubator are displayed in real time on the user's smartphone monitoring screen and are programmed using app inventor. Developed incubators can help take care of infants at low cost in the home.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.4
• /
• pp.95-105
• /
• 2021

Road surface damage detection is essential for a comfortable driving environment and the prevention of safety accidents. Road management institutes are using automated technology-based inspection equipment and systems. As one of these automation technologies, a sensor to detect road surface damage plays an important role. For this purpose, several studies on sensors using deep learning have been conducted in recent years. Road images and label images are needed to develop such deep learning algorithms. On the other hand, considerable time and labor will be needed to secure label images. In this paper, the adversarial learning method, one of the semi-supervised learning techniques, was proposed to solve this problem. For its implementation, a lightweight deep neural network model was trained using 5,327 road images and 1,327 label images. After experimenting with 400 road images, a model with a mean intersection over a union of 80.54% and an F1 score of 77.85% was developed. Through this, a technology that can improve recognition performance by adding only road images was developed to learning without label images and is expected to be used as a technology for road surface management in the future.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.3
• /
• pp.83-90
• /
• 2022

Diabetes is a common disease today, and there are also many cases of developing into serious complications called Diabetic Foot Ulcers(DFU). Diagnosis and prevention of DFU in advance is an important task, and this paper proposes the method. Based on existing studies introduced in the paper, it can be seen that foot pressure and temperature information are deeply correlated with DFU. Introduce the process and architecture of SmarTinsole, an IoT device that measures these indicators. Also, the paper describes the preprocessing process for AI-based diagnosis of DFU. Through the comparison of the measured pressure graph and the actual human step distribution, it presents the results that multiple information collected in real-time from SmarTinsole are more efficient and reliable than the previous study.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.397-404
• /
• 2022

Recently, in the industrial field, various studies are being conducted on converging IIoT devices that combine low-power processes and network cards into industrial sites to improve production efficiency and reduce costs. In this paper, we propose a processing model that can efficiently manage products produced by attaching IIoT sensor information to infrastructure built in industrial sites. The proposed model creates production data using IIoT data collection, preprocessing, characteristic generation, and labels to detect abnormally processed sensing information in real time by checking sensing information of products produced by IIoT at regular intervals. In particular, the proposed model can easily process IIoT data by performing tracking and monitoring so that product information produced in industrial sites can be processed in real time. In addition, since the proposed model is operated based on the existing production environment, the connection with the existing system is smooth.