• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.475-478
• /
• 2014

This paper proposed the position tracking and recognition method of workers and cars in construction field. The reason why the position of workers and cars has to be tracked is to prevent the safety accident, emergency rescue, and theft of building materials by unauthorized people and car, etc. To realize the tracking, it needs to adopt the Information Telecommunication technology to the construction field as an integrated support system. In this paper, we proposed the continuous positioning tracking algorithm for workers and moving cars using the selected wireless communication network. And we proposed the virtual gateway method to detect the entrance status of moving workers and cars. All of these proposed methods are evaluated in real construction field using the prototype of support system made by ourselves.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.293-296
• /
• 2016

In case of an emergency on a busy road of a city, drivers should make way for special vehicles such as police cars, fire engines, or ambulance as soon as possible. If road infrastructures recognize the movements of special vehicles, and transfer alert message to traffic signal controllers and normal cars through wireless network such as WAVE or TPEG, normal cars can prepare to make way in advance. As a result, it help special vehicles move faster. In this paper, we install a roof mark on the roof of a special vehicle, detect the mark through a mark recognition algorithm which includes perspective transformation, and get the inner information by decoding the digital pattern on it. The experiment results show that mark can be recognized 100% and 93.3% of inner digital data of the mark can be recognized, when the size of a mark is larger than $88cm{\times}88cm$ and the mark moves at a speed of 50km/s.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.45-48
• /
• 2019

Detection of crosswalk is an important issue for the blind to walk without the help of others. There is a braille block on the sidewalk, which helps the blind to walk. On the other hand, crosswalk is more dangerous due to the moving vehicles. However, there is no appropriate means to induce the blind. In this paper, we propose a method to detect crosswalk in front of a blind and estimate its direction using an image sensor. We adopt multi-ROIs and make their binary versions. In order to determine whether it is a crosswalk, two features are extracted; one is the number of crossing in the binary image and the other is the ratio of white area. We can also estimate the direction of the crosswalk through the slope of the projection data. We evaluated the performance using experimental dataset and the proposed algorithm showed 80% accuracy of detection.

• Journal of Aerospace System Engineering
• /
• v.13 no.2
• /
• pp.26-33
• /
• 2019

Control moment gyro (CMG) employed as satellite actuators, generates a large torque through the steering of its gimbals. Although each gimbal holds a high-speed rotating wheel, the wheel imbalances induces disturbance and degrades the satellite control quality. Therefore, the disturbances ought to be detected and identified as a precaution against actuator faults. Among the method used in detecting disturbances is the state observers. In this paper, we apply a continuous second order sliding mode observer to detect single disturbances/faults in CMGs. Verification of the algorithm is also done on the hardware satellite simulator where four CMGs are installed.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.9
• /
• pp.13-24
• /
• 2021

Recently, attempts have been made to detect fouling patterns in the ground using Ground Penetrating Radar (GPR) during the maintenance of gravel ballast railway tracks. However, dealing with GPR signal data obtained with a large amount of noise in a site where complex ground conditions are mixed, often depends on the experience of experts, and there are many difficulties in precise analysis. Therefore, in this study, a numerical modeling technique that can quantitatively simulate the GPR signal characteristics according to the degree of fouling of the gravel ballast material was proposed using python-based open-source code gprMax and RSA (Random sequential Absorption) algorithm. To confirm the accuracy of the simulation model, model tests were manufactured and the results were compared to each other. In addition, the identification of the fouling layer in the model test and analysis by various test conditions was evaluated and the results were analyzed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.50-56
• /
• 2020

With the rapid development of deep neural network theory and application research, the effect of face detection has been improved. However, due to the complexity of deep neural network calculation and the high complexity of the detection environment, how to detect face quickly and accurately becomes the main problem. This paper is based on the relatively simple model of the MTCNN model, using FDDB (Face Detection Dataset and Benchmark Homepage), LFW (Field Label Face) and FaceScrub public datasets as training samples. At the same time of sorting out and introducing MTCNN(Multi-Task Cascaded Convolutional Neural Network) model, it explores how to improve training speed and Increase performance at the same time. In this paper, the dynamic image pyramid technology is used to replace the traditional image pyramid technology to segment samples, and OHEM (the online hard example mine) function in MTCNN model is deleted in training, so as to improve the training speed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1618-1624
• /
• 2020

Intestinal obstruction diagnosis method based on X-ray can affect objective diagnosis because it includes subjective factors of the examiner. Therefore, in this paper, a detection method of Intestinal Obstruction from X-Ray image using Hough transform and PCM is proposed. The proposed method uses Hough transform to detect straight lines from the extracted ROI of the intestinal obstruction X-Ray image and bowel obstruction is extracted by using air fluid level's morphological characteristic detected by the straight lines. Then, ROI is quantized by applying PCM clustering algorithm to the extracted ROI. From the quantized ROI, cluster group that includes bowel obstruction's characteristic is selected and small bowel regions are extracted by using object search from the selected cluster group. The proposed method of using PCM is applied to 30 X-Ray images of intestinal obstruction patients and setting the initial cluster number of PCM to 4 showed excellent performance in detection and the TPR was 81.47%.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.34 no.2
• /
• pp.136-141
• /
• 2021

Heating cables, widely used in office buildings, factories, streets and railways, deteriorate in electrical insulation during operation. The insulation deterioration of heating cables leads to electric discharges that can cause electrical fires. With this background, this paper dealt with a condition monitoring technique for heating cables by the analysis of discharge signals to prevent electrical fires. Insulation deterioration was simulated using an arc generator specified in UL1699 under AC operation, and the characteristic and propagation of discharge signals were analyzed on a 100 meter-long heating cable. Discharge signals produced by insulation deterioration were detected as a voltage pulse because they are as small as a few mV and they are attenuated through propagation path. The frequency spectrum of discharge signals mainly existed in the range from 70 kHz to 110 kHz, and the maximum attenuation of the signal was 84.8% at 100 meters away from the discharge point. Based on the experimental results, a monitoring device, which is composed of a high pass filter with the cut-off frequency of 70 kHz, a comparator, a wave shaper and a microprocessor, was designed and fabricated. Also, an algorithm was designed to discriminate the discharge signal in the presence of noise, compared with the pulse repetition period and the number of pulse counts per 100ms. In the experiment, the result showed that the prototype monitoring device could detect and discriminate the discharge signals produced at every discharge point on a heating cable.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.4
• /
• pp.374-381
• /
• 2021

Raman spectrometers are studied and developed for the military purposes because of their nondestructive inspection capability to capture unique spectral features induced by molecular structures of colorless and odorless chemical warfare agents(CWAs) in any phase. Raman spectrometers often suffer from random noise caused by their detector inherent noise, background signal, etc. Thus, reducing the random noise in a measured Raman spectrum can help detection algorithms to find spectral features of CWAs and effectively detect them. In this paper, we propose a denoising autoencoder for Raman spectra with a loss function for sample efficient learning using noisy dataset. We conduct experiments to compare its effect on the measured spectra and detection performance with several existing noise reduction algorithms. The experimental results show that the denoising autoencoder is the most effective noise reduction algorithm among existing noise reduction algorithms for Raman spectrum based standoff detection of CWAs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2168-2187
• /
• 2021

The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.