• Korean Chemical Engineering Research
• /
• v.57 no.3
• /
• pp.338-343
• /
• 2019

The water transport and water content of the electrolyte membrane greatly affect the performance of the membrane in PEMFC(Proton Exchange Membrane Fuel Cell). In this study, the parameters (electroosmotic coefficient, water diffusion coefficient) of polymer membranes for water transport were measured by a simple method, and water flux and ion conductivity were simulated by using a model equation. One dimensional steady state model equation was constructed by using only the electro-osmosis and diffusion as the driving force of water transport. The governing equations were simulated with MATLAB. The electro-osmotic coefficient of $144{\mu}m$ thick polymer membranes was measured in hydrogen pumping cell, the value was 1.11. The water diffusion coefficient was expressed as a function of relative humidity and the activation energy for water diffusion was $2,889kJ/mol{\cdot}K$. The water flux and ion conductivity results simulated by applying these coefficients showed good agreement with the experimental data.

• Database Research
• /
• v.34 no.3
• /
• pp.45-57
• /
• 2018

The drowsiness that occurs in the driving is a very dangerous driver condition that can be directly linked to a major accident. In order to prevent drowsiness, there are traditional drowsiness detection methods to grasp the driver's condition, but there is a limit to the generalized driver's condition recognition that reflects the individual characteristics of drivers. In recent years, deep learning based state recognition studies have been proposed to recognize drivers' condition. Deep learning has the advantage of extracting features from a non-human machine and deriving a more generalized recognition model. In this study, we propose a more accurate state recognition model than the existing deep learning method by learning image and PPG at the same time to grasp driver's condition. This paper confirms the effect of driver's image and PPG data on drowsiness detection and experiment to see if it improves the performance of learning model when used together. We confirmed the accuracy improvement of around 3% when using image and PPG together than using image alone. In addition, the multimodal deep learning based model that classifies the driver's condition into three categories showed a classification accuracy of 96%.

• Korean Journal of Materials Research
• /
• v.31 no.1
• /
• pp.38-42
• /
• 2021

In this study, high temperature wetting analysis and AZ80/Ti interfacial structure observation are performed for the mixture of AZ80 and Ti, and the effect of Al on wetting in Mg alloy is examined. Both molten AZ80 and pure Mg have excellent wettability because the wet angle between molten droplets and the Ti substrate is about 10° from initial contact. Wetting angle decreases with time, and wetting phenomenon continues between droplets and substrate; the change in wetting angle does not show a significant difference when comparing AZ80-Ti and Mg-Ti. As a result of XRD of the lower surface of the AZ80-Ti sample, in addition to the Ti peak of the substrate, the peak of TiAl3, which is a Ti-Al intermetallic compound, is confirmed, and TiAl3 is generated in the Al enrichment region of the Ti substrate surface. EDS analysis is performed on the droplet tip portion of the sample section in which pure Mg droplets are dropped on the Ti substrate. Concentration of oxygen by the natural oxide film is not confirmed on the Ti surface, but oxygen is distributed at the tip of the droplet on the Mg side. Molten AZ80 and Ti-based compound phases are produced by thickening of Al in the vicinity of Ti after wetting is completed, and Al in the Mg alloy does not affect the wetting. The driving force of wetting progression is a thermite reaction that occurs between Mg and TiO2, and then Al in AZ80 thickens on the Ti substrate interface to form an intermetallic compound.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.75-80
• /
• 2021

Positioning technology is performing important functions in augmented reality, smart factory, and autonomous driving. Among the positioning techniques, the positioning method using beacons has been considered a challenging task due to the deviation of the RSSI value. In this study, the position of a moving object is predicted by training a neural network that takes the RSSI value of the receiver as an input and the distance as the target value. To do this, the measured distance versus RSSI was collected. A neural network was introduced to create synthetic data from the collected actual data. Based on this neural network, the RSSI value versus distance was predicted. The real value of RSSI was obtained as a neural network for generating synthetic data, and based on this value, the coordinates of the object were estimated by learning a neural network that tracks the location of a terminal in a virtual environment.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.6
• /
• pp.1154-1162
• /
• 2020

In this study, the soft textile actuator is produced for a smart wearable with the shape memory effects from linear shape memory alloys of Nickel and Titanium using the driving force through the fabrication process. The measurement model was designed to measure dynamic characteristics. The heating method, and memory shape of the linear shape memory alloy were set to measure the operating temperature. A shape memory alloy at 40.13℃, was used to heat the alloy with a power supply for the selective operation and rapid reaction speed. The required amount of current was obtained by calculating the amount of heat and (considering the prevention of overheating) set to 1.3 A. The fabrication process produced a soft textile actuator using a stitching technique for linear shape memory alloys at 0.5 mm intervals in the general fabric. The dynamic characteristics of linear shape memory alloys and actuators were measured and compared. For manufactured soft textile actuators, up to 0.8 N, twice the force of the single linear shape memory alloy, 0.38 N, and the response time was measured at 50 s.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.152-162
• /
• 2020

In the urban and rural complex, taxis move from downtown to rural areas for business purposes, and operate a combined surcharge system that preserves losses when they back to downtown. However, complaints related to the abolition of the compound surcharge system are increasing due to deformed operation that does not fit the purpose of the system. When the combinedsurcharge system is abolished, the taxi industry can be hit hard by the decrease in profits, and local governments are inevitable to support it. However, it is difficult to set the size of the subsidy considering the decrease of actual income. This study is to estimate the income reduction in the abolition of the combined surcharge system by scientific and objective method by analyzing the DTG data and the sales data collected from the digital driving recorder installed in the corporate taxi of the urban and rural complex area (e.g., Tongyeong city). This study is meaningful in that it used DTG data to solve the current issues in the real region and suggested the use of new DTG data.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.213-218
• /
• 2021

In this paper, we detect and track vehicles by type based on highway daytime driving videos taken with black boxes for vehicles. In addition, we design a real-time MR contents production method that can be newly created by placing substitute videos of each type of detected vehicles in the same location as the new background video. To detect and track vehicles by type, we use the YOLO algorithm. And we also use the mask technique based on RGB color for substitute videos of each type of vehicles detected. The size of the vehicle substitute videos to be used for MR content are substituted by the same size as the area size of the detected vehicles. In this paper, we confirm that real-time MR contents design is possible as a result of experiments and simulations and believe that It will be usefully utilized in the field of VR contents.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.175-179
• /
• 2021

With the recent increase in the proportion of single-person households, the demand for reasonable personal mobility has increased, and the "Personal Mobility" industry that can be used conveniently and concisely has grown rapidly. In fact, according to data from the Korea Transport Institute, the scale of the electric kickboards rental industry, one of the personal mobility industry sectors, is expected to expand to 200,000 units in 2022. Due to the characteristics of electric kickboards that are powered by electricity, stable and efficient battery supply is the most basic and important issue. According to recent reviews from users who have used the electric kickboard, there were cases where the use of the electric kickboard is attempted, but the battery is in a discharged state or the battery charge level is low and thus cannot be used. Therefore, this paper proposes a solar charging system for stable battery use of electric kickboards. When this system is applied, it is expected that it will not only be an eco-friendly charging method for electric kickboards, but also stably supply and demand batteries while driving.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.514-521
• /
• 2021

When calculating an intersection collision speed using a formula, it is very difficult to grasp the degree of deceleration of a vehicle after the collision unless there is road surface trace in the entire section where each vehicle moved from the point of collision to their final positions after the collision. A vehicle's motion trajectory shows an irregular curve after a collision due to the effects of inertia based on the driving characteristics of the vehicle, the eccentric force according to the collision site, and the collision speed. Therefore, it is very important to set the appropriate departure angle after a collision for accurate collision speed analysis. In this study, based on experimental collision data using a computer simulation (PC-Crash), the correlation between an appropriate vehicle departure angle and the post-collision speed was analyzed, and then, a regression analysis model was derived. Through this, we propose a method to calculate collision speed by applying only the vehicle departure angle in some types of collisions for traffic accidents at intersections.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.20-29
• /
• 2021

In the Industry 4.0 era, artificial intelligence has attracted considerable interest for learning mass data to improve the accuracy of forecasting and classification. On the other hand, the current method of detecting anomalies relies on traditional statistical methods for a limited amount of data, making it difficult to detect accurate anomalies. Therefore, this paper proposes an artificial intelligence-based anomaly detection methodology to improve the prediction accuracy and identify new data patterns. In particular, data were collected and analyzed from the point of view that sensor data collected at vehicle idle could be used to detect abnormalities. To this end, a sensor was designed to determine the appropriate time length of the data entered into the forecast model, compare the results of idling data with the overall driving data utilization, and make optimal predictions through a combination of various sensor data. In addition, the predictive accuracy of artificial intelligence techniques was presented by comparing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) as the predictive methodologies. According to the analysis, using idle data, using 1.5 times of the data for the idling periods, and using CNN over LSTM showed better prediction results.