• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.90-94
• /
• 2007

Location tracking automation of resources in construction industry is one of the most important procedures to improve construction project performance and reduce the period of construction. Recently, location tracking technologies have proven to be effective in tracking construction materials and equipment in real time through the instrumentality of RFID (Radio Frequency Identification). By using wireless communication and inter-working system between RFID and USN, it is possible that construction engineers receive the location information of construction resources without additional efforts that move the RFID reader to read tags periodically. In the inter-working system, RFID reader delivers the acquired materials information to sensor node which is connected by serial interface. Then sensor node transmits the received data to the data aggregation terminal that is a sink node. The data aggregation terminal can transmit collected data to construction manager who is out of construction site using infrastructure such as CDMA(Code Division Multiple Access) network. The combination model of the two system and field test scenarios are presented in this paper.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.4
• /
• pp.253-263
• /
• 2021

Concrete structures are damaged by aging and external environmental factors. This type of damage is to appear in the form of cracks, to proceed in the form of spalling. Such concrete damage can act as the main cause of reducing the original design bearing capacity of the structure, and negatively affect the stability of the structure. If such damage continues, it may lead to a safety accident in the future, thus proper repair and reinforcement are required. To this end, an accurate and objective condition inspection of the structure must be performed, and for this inspection, a sensor technology capable of detecting damage area is required. For this reason, we propose a deep learning-based image processing algorithm that can detect spalling. To develop this, 298 spalling images were obtained, of which 253 images were used for training, and the remaining 45 images were used for testing. In addition, an improved loss function and data augmentation technique were applied to improve the detection performance. As a result, the detection performance of concrete spalling showed a mean intersection over union of 80.19%. In conclusion, we developed an algorithm to detect concrete spalling through a deep learning-based image processing technique, with an improved loss function and data augmentation technique. This technology is expected to be utilized for accurate inspection and diagnosis of structures in the future.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.31-39
• /
• 2018

Recently, there has been active studies to provide a user-friendly interface in a virtual reality environment by recognizing user hand gestures based on deep learning. However, most studies use separate sensors to obtain hand information or go through pre-process for efficient learning. It also fails to take into account changes in the external environment, such as changes in lighting or some of its hands being obscured. This paper proposes a hand gesture recognition method based on deep learning that is strong in external environments without the need for pre-process of RGB images obtained from general webcam. In this paper we improve the VGGNet and the GoogLeNet structures and compared the performance of each structure. The VGGNet and the GoogLeNet structures presented in this paper showed a recognition rate of 93.88% and 93.75%, respectively, based on data containing dim, partially obscured, or partially out-of-sight hand images. In terms of memory and speed, the GoogLeNet used about 3 times less memory than the VGGNet, and its processing speed was 10 times better. The results of this paper can be processed in real-time and used as a hand gesture interface in various areas such as games, education, and medical services in a virtual reality environment.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.1001-1006
• /
• 2023

Globally, rising energy costs and increased energy demand are important issues for the food processing and manufacturing industries, which consume significant amounts of energy throughout the supply chain. Accordingly, there is a need for the development of a real-time energy monitoring and analysis system that can optimize energy use. In this study, a food factory energy monitoring system was proposed based on IoT installed in a food factory, including monitoring of each facility, energy supply and usage monitoring for the heat treatment process, and search functions. The system is based on the IoT sensor of the food processing plant and consists of PLC, database server, OPC-UA server, UI server, API server, and CIMON's HMI. The proposed system builds big data for food factories and provides facility-specific monitoring through collection functions, as well as energy supply and usage monitoring and search service functions for the heat treatment process. This data collection-based energy monitoring system will serve as a guide for the development of a small and medium-sized factory energy monitoring and management system for energy savings. In the future, this system can be used to identify and analyze energy usage to create quantitative energy saving measures that optimize process work.

• Journal of the Society of Disaster Information
• /
• v.10 no.4
• /
• pp.518-527
• /
• 2014

Our society is changed and diversified rapidly and such tendency is accelerated day after day and has made a lot of problems in the many fields. The important thing we have to recognize is such tendency has a bad effect recently on the safety system in Korea. So it is time to enhance the national safety system and moreover recently Sewol-ho(passenger ship) went down in the sea, it made people remind the importance of national safety system. With this incident, Korean government decided to establish the national safety communication network against the disaster. At this time, I will propose several ideas about the national safety communication network. 1. It must to be established an unified network to contact people who is on a disaster site anytime and anywhere. This is most important element on all disaster sites. 2. PS-LTE technology must to be adopted to the network because it has many advantages including various multimedia services compared to the TETRA in the past. 3. 700MHz is the most efficient band for the network because it has wide cell sites coverage compared to 1.8GHz. 4. Satellite communication system is needed to the network for back-up. 5. It will be effective to adopt Social Media to the communication network system like a Twitter or Facebook for sharing many kinds of information and notifying people of warning message. 6. It can make the network more useful to introduce the latest technology like a sensor network. And Korean government has to improve the system related to the disaster including law and operating organization.

• Journal of Bio-Environment Control
• /
• v.25 no.4
• /
• pp.277-282
• /
• 2016

This study was aimed to investigate the effect of air-circulation fans on air temperature and relative humidity in a single-span tomato greenhouse (W: 7m, L: 25m, H: 3.2m). According to standard of fan layout by ASAE (1997), a total of 10 fans were bilaterally arranged in 2 rows in the experimental greenhouse. The distributions of air temperature and relative humidity were measured from 6 pm to 8 am under different conditions, with and without fans. The measurement heights were 0.7m, 1.7m and 2.7m. Under the condition of "fans off", the spatial differences of air temperature and relative humidity between upper and lower sides were $1.7^{\circ}C$ and 10.8%, respectively. The operation of 10 fans showed their differences to $0.1^{\circ}C$ and 3.2%. The number of fans and installation direction were evaluated their performance on reducing the spatial variation of air temperature and relative humidity. The experimental layouts were 5 and fans in 2 rows (bilaterally) and 10 fans in the one (same) direction. Under the condition of "6 fans on" and "5 fans on", the spatial differences of air temperature and relative humidity between upper and lower side were $0.3^{\circ}C$, 3.4% and $0.3^{\circ}C$ and 4.0%. The operation of 10 fans in the one direction reduced their differences to $0.5^{\circ}C$ and 4.9%. The overall findings of this study showed that there was no significant differences under each condition. Therefore, this study suggested that it is more economic and effective to install five fans in 2 rows (bilaterally) in the greenhouse (W: 7m, L: 25m, H: 3.2m).

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.18 no.4
• /
• pp.163-177
• /
• 2013

An instrumented ferry made two transects per day across two current systems which are the North Korean Cold Current and the East Korean Warm Current over the years 2012-2013 from Gangneung to Ulleungdo in the southwestern East Sea. Seawater properties of these transects were measured with high spatial and temporal resolution for an extended period of time. Here the salinity records from the transects with the oceanographic observation data from East Sea Fisheries Institute of NFRDI, AVISO daily current chart and GOCI Chlorophyll-a image in 2012 and 2013 are used to study the time-series variation of salinity at the surface. The high salinity section with the range of 33.15~34.12 occurred on the transect mainly in the middle of eddy, and western boundary of strong northward current from June to October. We can found low salinity waters in both sides of the high salinity section. It is estimated that the western low salinity waters with the range of 30.58~33.20 accompanied by southward current were derived from the NKCC and the eastern waters with the range of 31.30~33.24 accompanied by northward current were derived from the Tsushima Surface Water. The lowest salinity of NKCC is confirmed in this study as 30.36. It is found that the western waters below 33.00 extended extremely toward the east about 110 km area from Gangneung and toward the south around Jukbyon coastal area as a 5~10 m layer. We can find its volume of low saline waters transport is not neglectable compared with that of Tsushima Current region in the western part of the East Sea. In this study we named it as the North Korean Low Saline Surface Water in summer.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.1
• /
• pp.67-76
• /
• 2024

In this paper, we present a DIP-MLS testing method that combines digital image processing with a rigid body-based MLS differencing approach to measure mechanical variables and analyze the impact of target location and image resolution. This method assesses the displacement of the target attached to the sample through digital image processing and allocates this displacement to the node displacement of the MLS differencing method, which solely employs nodes to calculate mechanical variables such as stress and strain of the studied object. We propose an effective method to measure the displacement of the target's center of gravity using digital image processing. The calculation of mechanical variables through the MLS differencing method, incorporating image-based target displacement, facilitates easy computation of mechanical variables at arbitrary positions without constraints from meshes or grids. This is achieved by acquiring the accurate displacement history of the test specimen and utilizing the displacement of tracking points with low rigidity. The developed testing method was validated by comparing the measurement results of the sensor with those of the DIP-MLS testing method in a three-point bending test of a rubber beam. Additionally, numerical analysis results simulated only by the MLS differencing method were compared, confirming that the developed method accurately reproduces the actual test and shows good agreement with numerical analysis results before significant deformation. Furthermore, we analyzed the effects of boundary points by applying 46 tracking points, including corner points, to the DIP-MLS testing method. This was compared with using only the internal points of the target, determining the optimal image resolution for this testing method. Through this, we demonstrated that the developed method efficiently addresses the limitations of direct experiments or existing mesh-based simulations. It also suggests that digitalization of the experimental-simulation process is achievable to a considerable extent.