• ETRI Journal
• /
• v.45 no.6
• /
• pp.1022-1034
• /
• 2023

In this study, the impact of varying lighting conditions on recognition and decision-making was considered. The luminosity approach was presented to increase gesture recognition performance under varied lighting. An efficient framework was proposed for sensor-based sign language gesture identification, including picture acquisition, preparing data, obtaining features, and recognition. The depth images were collected using multiple Microsoft Kinect devices, and data were acquired by varying resolutions to demonstrate the idea. A case study was designed to attain acceptable accuracy in gesture recognition under variant lighting. Using American Sign Language (ASL), the dataset was created and analyzed under various lighting conditions. In ASL-based images, significant feature points were selected using the scale-invariant feature transformation (SIFT). Finally, an artificial neural network (ANN) classified hand gestures using specified characteristics for validation. The suggested method was successful across a variety of illumination conditions and different image sizes. The total effectiveness of NN architecture was shown by the 97.6% recognition accuracy rate of 26 alphabets dataset with just a 2.4% error rate.

• Journal of Korean Society of Water and Wastewater
• /
• v.38 no.1
• /
• pp.1-15
• /
• 2024

Occurrence of process environment changes, such as influent load variances and process condition changes, can reduce treatment efficiency, increasing effluent water quality. In order to prevent exceeding effluent standards, it is necessary to manage effluent water quality based on process operation data including influent and process condition before exceeding occur. Accordingly, the development of the effluent water quality prediction system and the application of technology to wastewater treatment processes are getting attention. Therefore, in this study, through the multi-channel measuring instruments in the bio-reactor and smart multi-item water quality sensors (location in bio-reactor influent/effluent) were installed in The Seonam water recycling center #2 treatment plant series 3, it was collected water quality data centering around COD, T-N. Using the collected data, the artificial intelligence-based effluent quality prediction model was developed, and relative errors were compared with effluent TMS measurement data. Through relative error comparison, the applicability of the artificial intelligence-based effluent water quality prediction model in wastewater treatment process was reviewed.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.125-141
• /
• 2012

These days, the malicious attacks and hacks on the networked systems are dramatically increasing, and the patterns of them are changing rapidly. Consequently, it becomes more important to appropriately handle these malicious attacks and hacks, and there exist sufficient interests and demand in effective network security systems just like intrusion detection systems. Intrusion detection systems are the network security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. Conventional intrusion detection systems have generally been designed using the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. However, they cannot handle new or unknown patterns of the network attacks, although they perform very well under the normal situation. As a result, recent studies on intrusion detection systems use artificial intelligence techniques, which can proactively respond to the unknown threats. For a long time, researchers have adopted and tested various kinds of artificial intelligence techniques such as artificial neural networks, decision trees, and support vector machines to detect intrusions on the network. However, most of them have just applied these techniques singularly, even though combining the techniques may lead to better detection. With this reason, we propose a new integrated model for intrusion detection. Our model is designed to combine prediction results of four different binary classification models-logistic regression (LOGIT), decision trees (DT), artificial neural networks (ANN), and support vector machines (SVM), which may be complementary to each other. As a tool for finding optimal combining weights, genetic algorithms (GA) are used. Our proposed model is designed to be built in two steps. At the first step, the optimal integration model whose prediction error (i.e. erroneous classification rate) is the least is generated. After that, in the second step, it explores the optimal classification threshold for determining intrusions, which minimizes the total misclassification cost. To calculate the total misclassification cost of intrusion detection system, we need to understand its asymmetric error cost scheme. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, total misclassification cost is more affected by FNE rather than FPE. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 10,000 samples from them by using random sampling method. Also, we compared the results from our model with the results from single techniques to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell R4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on GA outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that the proposed model outperformed all the other comparative models in the total misclassification cost perspective. Consequently, it is expected that our study may contribute to build cost-effective intelligent intrusion detection systems.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.893-906
• /
• 2020

This paper reports on the analysis of the location accuracy of a precision image generation system manufactured for CAS 500. The planned launch date of the CAS 500 is 2021, and since it has not yet been launched, the analysis was performed using KOMPSAT-3A satellite images having similar specifications to the CAS 500. In this paper, we have checked the geolocation accuracy of initial sensor model, the model point geolocation accuracy of the precise sensor model, the geolocation accuracy of the precise sensor model using the check point, and the geolocation accuracy of the precise orthoimage using 30 images of the Korean Peninsula. In this study, the target geolocation accuracy is to have an RMSE within 2 pixels when an accurate ground control point is secured. As a result, it was confirmed that the geolocation accuracy of the precision sensor model using the checkpoint was about 1.85 pixels in South Korea and about 2.04 pixels in North Korea, and the geolocation accuracy of the precise orthoimage was about 1.15 m in South Korea and about 3.23 m in North Korea. Overall, it was confirmed that the accuracy of North Korea was low compared to that of South Korea, and this was confirmed to have affected the measured accuracy because the GCP (Ground Control Point) quality of the North Korea images was poor compared to that of South Korea. In addition, it was confirmed that the accuracy of the precision orthoimage was slightly lower than that of precision sensor medel, especially in North Korea. It was judged that this occurred from the error of the DTM (Digital Terrain Model) used for orthogonal correction. In addition to the causes suggested by this paper, additional studies should be conducted on factors that may affect the position accuracy.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1631-1645
• /
• 2021

This research aims to provide the characteristics of the world's first active lidar sensor Atmospheric Laser Doppler Instrument (ALADIN) wind data and Geostationary Korea Multi Purpose Satellite 2A (GK2A) Atmospheric Motion Vector (AMV) data by comparing two wind data. As a result of comparing the data from September 2019 to August 1, 2020, The total number of collocated data for the AMV (using IR channel) and Mie channel ALADIN data is 177,681 which gives the Root Mean Square Error (RMSE) of 3.73 m/s and the correlation coefficient is 0.98. For a more detailed analysis, Comparison result considering altitude and latitude, the Normalized Root Mean Squared Error (NRMSE) is 0.2-0.3 at most latitude bands. However, the upper and middle layers in the lower latitudes and the lower layer in the southern hemispheric are larger than 0.4 at specific latitudes. These results are the same for the water vapor channel and the visible channel regardless of the season, and the channel-specific and seasonal characteristics do not appear prominently. Furthermore, as a result of analyzing the distribution of clouds in the latitude band with a large difference between the two wind data, Cirrus or cumulus clouds, which can lower the accuracy of height assignment of AMV, are distributed more than at other latitude bands. Accordingly, it is suggested that ALADIN wind data in the southern hemisphere and low latitude band, where the error of the AMV is large, can have a positive effect on the numerical forecast model.

• Korean Journal of Optics and Photonics
• /
• v.28 no.3
• /
• pp.108-115
• /
• 2017

We report the assembly procedure and performance evaluation of a visible and near-infrared spectrometer in the wavelength region of 400-900 nm, which is later to be combined with fore-optics (a telescope) to form a f/2.5 imaging spectrometer with a field of view of ${\pm}7.68^{\circ}$. The detector at the final image plane is a $640{\times}480$ charge-coupled device with a $24{\mu}m$ pixel size. The spectrometer is in an Offner relay configuration consisting of two concentric, spherical mirrors, the secondary of which is replaced by a convex grating mirror. A double-pass test method with an interferometer is often applied in the assembly process of precision optics, but was excluded from our study due to a large residual wavefront error (WFE) in optical design of 210 nm ($0.35{\lambda}$ at 600 nm) root-mean-square (RMS). This results in a single-path test method with a Shack-Hartmann sensor. The final assembly was tested to have a RMS WFE increase of less than 90 nm over the entire field of view, a keystone of 0.08 pixels, a smile of 1.13 pixels and a spectral resolution of 4.32 nm. During the procedure, we confirmed the validity of using a Shack-Hartmann wavefront sensor to monitor alignment in the assembly of an Offner-like spectrometer.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.409-415
• /
• 2022

Plant growth and development are also affected by root-zone environment. Therefore, it is important to consider the variables of the root-zone environment when establishing an irrigation strategy. The purpose of this study is to analyze the relationship between the volumetric moisture content (VWC), Bulk EC (ECb), and Pore EC (ECp) used by plant roots using FDR sensors in two types of rockwool media with different water transmission characteristics, using the method above this was used to establish a method for collecting and correcting available root-zone environmental data. For the experiment, two types of rockwool medium (RW1, RW2) with different physical characteristics were used. The moisture content (MC) and ECb were measured using an FDR sensor, ECp was measured after extracting the residual nutrient solution from the medium using a disposable syringe in the center of the medium at a volumetric moisture content (VWC) of 10-100%. Then, ECb and ECp are measured by supplying nutrient solution having different concentration (distilled water, 0.5-5.0) to two types of media (RW1, RW2) in each volume water content range (0 to 100%). The relationship between ECb and ECp in RW1 and RW2 media is best suited for cubic polynomial. The relationship between ECb and ECp according to volume moisture content (VWC) range showed a large error rate in the low volume moisture content (VWC) range of 10-60%. The correlation between the sensor measured value (ECb) and the ECp used by plant roots according to the volumetric water content (VWC) range was the most suitable for the Paraboloid equation in both media (RW1, RW2). The coefficient of determination the calibration equation for RW1 and RW2 media were 0.936, 0.947, respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1061-1068
• /
• 2017

A RVDT is a sensor that measures angular displacement and the output signal of RVDT is a DSBSC-AM signal. For this reason, a DSBSC-AM demodulation processor is required to determine the angular displacement from the output signal. In this paper, DADC(Digital Angle to DC) which extracts the angular displacement from the output signal of a RVDT is implemented based-on modified Costas Loop usually used in the demodulation of DSBSC-AM signal by using FPGA. DADC can used with both 4-wire and 5-wire RVDTs and can exactly compensate the phase difference between the input excitation and output signals of a RVDT unlike the conventional analog RVDT signal conditioners which require external components. Since digital signal processing technique that can enhance the linearity is exploited, DADC shows 0.035% linearity error, which is smaller than 0.005% that of a conventional analog signal conditioner. The DADC are tested in an integrated experimental environment which includes a commercial RVDT sensor, ADC and an analog output block.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.6
• /
• pp.527-534
• /
• 2017

The purpose of this study is to develop unmanned equipment that can automatically move to the desired point and measure water quality at the correct depth. For this purpose, we constructed a water sampling lift and water sampling container, an unmanned vessel equipped with a VRS-GPS, an acoustic echo sounder, and a water quality sensor. Also, we developed an automatic navigation algorithm and program, an automatic water sampling program, and a water quality map generation program. As a result of the experiment in the detention pond, the unmanned vessel sailed along the planned route with an accuracy of about 93% within the error range of 3m. In addition, the water quality sensor installed in the lift was able to acquire the water quality of the target area in real time and transmit it to the server via wireless Internet, and it was possible to monitor the water quality of each site in real time. Through field experiments, the water sampling lift was able to control the desired length with an accuracy of about 94%. The stretch length accuracy experiment of the water sampling lift was impossible to measure directly in the water, so it was replaced land-based experiment. We also found some unstable problems due to the weight of the water sampling lift and the weight of the air compressor to operate the water container. Except these two problems, we accomplished purpose of this study. An automated water quality measurement method using an unmanned vessel can be used to measure the quality of water in a difficult to access area and to secure the safety of the worker.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.6
• /
• pp.47-53
• /
• 2003

In this paper, we described the laboratory layout of the optical CT in connection with the measurement of large current based on Magneto-Optic Effects. It was used He-Ne laser for light source and was used PIN-Photodiode for light receiver. The sensing section was organized by winding optical fiber around conductor on the concept that the rotation angle of polarizing axis by Faraday Effect is proportional to the applied current in to conduction. The optical signal passed through optical fiber sensor was induced to analyzer arranged in the direction of $\theta$ for input polarization, and then analyzed its rotation angle and researched on operating characteristics of optical CT for 60[Hz] AC current measurement from l00[A] to 1000[A] was carried out. In this results, the output signals induced linearly with the current and proved that the intensity is increased with increasing turns of fiber through output differences which in accordance with turns of fiber and we verified that there is not only difference of the output with the medium between electric field and optical fiber, but also the lineality. Measuring the references and output intensities of the optical CT, ratio errors were within $\pm$7%. This confirmed that error rate will be improved by each medium and turns.