• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.859-872
• /
• 2016

Land cover classification is an important tool for preventing natural disasters, collecting environmental information, and monitoring natural resources. Hyperspectral imaging is widely used for this task thanks to sufficient spectral information. However, the curse of dimensionality, spatiotemporal variability, and lack of labeled data make it difficult to classify the land cover correctly. We propose a novel classification framework for land cover classification of hyperspectral data based on convolutional neural networks. The proposed framework naturally incorporates full spectral features with the information from neighboring pixels and has advantages over existing methods that require additional feature extraction or pre-processing steps. Empirical evaluation results show that the proposed framework provides good generalization power with classification accuracies better than (or comparable to) the most advanced existing classifiers.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.81-86
• /
• 2020

With the development of the intelligent Internet of Things AIoT that goes beyond the IoT of the Internet of Things, the industry is changing overall. In addition, with the advent of the 4th Industrial Revolution, revolutionary changes and developments are also taking place in the automobile industry. A representative example is "autonomous driving vehicle". Because the domestic and foreign interests in autonomous vehicles have increased, many developments have been made, and although limited, they have developed into the commercialization stage. However, the structure of the autonomous vehicle that collects, analyzes, and controls data using various sensors installed in the vehicle, not the driver, is often insufficiently exposed to hacking due to the lack of multiplexed devices for security. In this case, as this can be a threat not only to the driver, but also to the surrounding environment, this paper proposes a new data processing function to improve the system security of autonomous vehicles.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.433-440
• /
• 2016

Railway point machines act as actuators that provide different routes to trains by driving switchblades from the current position to the opposite one. Since point failure can significantly affect railway operations with potentially disastrous consequences, early stress detection of point machine is critical for monitoring and managing the condition of rail infrastructure. In this paper, we propose a stress detection method for point machine in railway condition monitoring systems using sound data. The system enables extracting sound feature vector subset from audio data with reduced feature dimensions using feature subset selection, and employs support vector machines (SVMs) for early detection of stress anomalies. Experimental results show that the system enables cost-effective detection of stress using a low-cost microphone, with accuracy exceeding 98%.

• Journal of the Korean Institute of Gas
• /
• v.22 no.1
• /
• pp.53-59
• /
• 2018

In Korea, The number of installed LPG Charging stations is about 2000, increasing by 26 every year. In these, about 500 charging stations are older above 15 year, accounting about 25% of total stations. About 86% of them are located in the city, which is causing serious damage if accident occurs. In this paper, we developed a duel gas sensor module and integrated control system software that can prevent and correspondence to gas leaks and fire accidents at LPG/CNG charging stations. The dual type sensor module has the function of collecting and transmitting the measured data to the sensors of methane, butane and hydrogen through RF433Mhz communication. In addition, each sensor is attached with two to improve stability and accuracy. The integrated control system software detects real-time data of the devices measured by the sensors and it send to the PC and smart phone of manager. Therefore, if accident occurs, the manager can check the status of the charging station regardless of time and place.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1195-1200
• /
• 2007

This paper describes indoor location estimation intelligent robot. Indoor location estimation function using RSSI based indoor location estimation system and wireless sensor networks were implemented in the robot. Spartan III(Xilinx, U.S.A.) was used as a main control device in the mobile robot and the current direction data was collected in the indoor location estimation system. The data was transferred to the wireless sensor network node attached to the mobile robot through Zigbee/IEEE 802.15.4, a wireless communication. After receiving it, with the data of magnetic compass the node is aware of and senses the direction the robot head for and the robot moves to its destination. Indoor location estimation intelligent robot is can be moved efficiently and actively without obstacle on flat ground to the appointment position by user.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.789-798
• /
• 2021

In this study, for the purpose of collecting and analyzing target-specific RCS data of target signals simulator for verification/improvement of radar system performance, VHF band monostatic/bistatic RCS of civil aircraft(B-747, B-737) and fighter(F-16) models were analyzed by EM simulation tool. In order to reduce the RCS analysis time, the analysis time and RCS data were compared and cross-verified. Also, the analysis range was selected by examining the interpolation error according to the analysis angle resolution. The RCS data obtained for each model were analyzed separately by the incident/reflection elevation angle and frequency. The RCS characteristics according to the shape of the aircraft and the incident/reflection azimuth angle were described. Finally, the statistical RCS distribution value of each model is presented through RCS distribution histogram analysis. In the future, the RCS database obtained by this study will be used for the target signals simulator of the VHF band radar system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.147-151
• /
• 2014

With the advent of tiny and inexpensive computer systems like Raspberry Pi, it has become possible to construct an experimental environment of MANETs (Mobile Ad hoc Networks) at a relatively low cost. In this paper, we implement a node of MANETs with a Raspberry Pi equipped with two 802.11 wireless LAN cards and dynamic routing software running on it. In an outdoor MANETs environment with moving mobile nodes automatically rebuilding broken routes, we conducted a real-time video streaming experiment over the MANET. The video stream is transmitted from a node with a video camera installed on it to another node through the route established dynamically. Each node is equipped with a display device, with which the current status of the node can be checked out. We also implemented software that automatically collects data stored in each node and analyzes the performance of the MANETs. Through this experiment, we could evaluate the performance of realistic video streaming service in a MANETs environment.

• 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.

• Smart Media Journal
• /
• v.12 no.3
• /
• pp.49-59
• /
• 2023

Optical Camera Communication (OCC), known as the next-generation wireless communication technology, is currently under extensive research. The performance of OCC technology is affected by the communication environment, and various strategies are being studied to improve it. Among them, the most prominent method is applying convolutional neural networks (CNN) to the receiver of OCC using deep learning technology. However, in most studies, CNN is simply used to detect the transmitter. In this paper, we experiment with applying the convolutional neural network not only for transmitter detection but also for the Rx demodulation system. We hypothesize that, since the data images of the OCC system are relatively simple to classify compared to other image datasets, high accuracy results will appear in most CNN models. To prove this hypothesis, we designed and implemented an OCC system to collect data and applied it to 12 different CNN models for experimentation. The experimental results showed that not only high-performance CNN models with many parameters but also lightweight CNN models achieved an accuracy of over 99%. Through this, we confirmed the feasibility of applying the OCC system in real-time on mobile devices such as smartphones.

• Annual Conference of KIPS
• /
• 2010.11a
• /
• pp.913-916
• /
• 2010

Wireless sensor networks consist of small battery powered devices with limited energy resources. Once deployed, the small sensor nodes are usually inaccessible to the user, and thus replacement of the energy source is not feasible. Hence, energy efficiency is a key design issue that needs to be enhanced in order to improve the life span of the network. In BCDCP, all sensors send data from CH (Cluster Head) and then to BS (Base Station). BCDCP works well in small-scale network but in large scale network it is not appropriated since it uses much energy for long distance wireless communication. We propose a routing protocol - Triangular Clustering Routing Protocol (TCRP) - to prolong network life time through the balanced energy consumption. TCRP selects cluster head of triangular shape. The sensor field is divided into energy level and in every level we choose one node as a gate node. This gate node collects data and sends it to the leader node. Finally the leader node sends the aggregated data to the BS. We show TCRP outperforms BCDCP with several experiments.