• Journal of the Korea Society of Computer and Information
• /
• v.26 no.8
• /
• pp.39-46
• /
• 2021

When conducting social big data analysis for franchise stores, reviews of multiple branches of a franchise can be collected together, from which analysis results can be distorted significantly. To improve its accuracy, it should be possible to filter reviews of other branches properly which are not subject to the analysis. This paper presents a method for social big data analysis which reflects characteristics of franchise stores. The proposed method consists of search key configuration and review filtering. For the former, the open data provided by Small Business Promotion Agency is used to extract region names for collecting reviews more accurately. For the latter, open search APIs provided by Naver or Kakao are used to obtain franchise branch information for filtering reviews of other branches that are not subject to analysis. To verify performance of the proposed method, experiments were conducted based on real social reviews collected from online, where the results showed that the accuracy of the proposed review filtering was 93.6% on the average.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.1-7
• /
• 2022

It has been found through physiological experiments that the visual neurons constituting the human visual cortex do not respond to all visual stimuli, but to a visual stimuli with specific conditions. In order to interpret such physiological experiments, a model that can simulate the firing characteristics of neurons including a linear filter with random gain was proposed. It has been proven through experiments that subspaces are formed. To verify the validity of the implemented model, the distribution of values for two pixels randomly extracted from four different visual stimulus data was observed. The difference between the two distributions was confirmed by extracting the central coordinate value, that is, the coordinate value with the most values, from the distribution of the total stimulus data and the spike ignition stimulus data. In the case of the entire set, it was verified through experiments that the stimulus data generating spikes is a subset or subspace of the entire stimulus data. This study can be used as a basic study related to the mechanism of spikes in response to visual stimuli.

• Journal of Radiation Protection and Research
• /
• v.47 no.3
• /
• pp.134-142
• /
• 2022

Background: This study investigated the characteristics of optically stimulated luminescence dosimeters (OSLDs) with fully filled deep electron/hole traps in the kV energy ranges. Materials and Methods: The experimental group consisted of InLight nanoDots, whose deep electron/hole traps were fully filled with 5 kGy pre-irradiation (OSLD_exp), whereas the non-pre-irradiated OSLDs were arranged as a control group (OSLD_cont). Absorbed doses for 75, 80, 85, 90, 95, 100, and 105 kVp with 200 mA and 40 ms were measured and defined as the unit doses for each energy value. A bleaching device equipped with a 520-nm long-pass filter was used, and the strong beam mode was used to read out signal counts. The characteristics were investigated in terms of fading, dose sensitivities according to the accumulated doses, and dose linearity. Results and Discussion: In OSLD_exp, the average normalized counts (sensitivities) were 12.7%, 14.0%, 15.0%, 10.2%, 18.0%, 17.9%, and 17.3% higher compared with those in OSLD_cont for 75, 80, 90, 95, 100, and 105 kVp, respectively. The dose accumulation and bleaching time did not significantly alter the sensitivity, regardless of the filling of deep traps for all radiation qualities. Both OSLD_exp and OSLD_cont exhibited good linearity, by showing coefficients determination (R²) > 0.99. The OSL sensitivities can be increased by filling of deep electron/hole traps in the energy ranges between 75 and 105 kVp, and they exhibited no significant variations according to the bleaching time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.692-712
• /
• 2022

Buoys used for Aid to Navigation systems are widely used to guide the sea paths and are powered by batteries, requiring continuous battery replacement. However, since human labor is required to replace the batteries, humans can be exposed to dangerous situation, including even collision with shipping vessels. In addition, Maritime sensors are installed on the route signs, so that these are often damaged by collisions with small and medium-sized ships, resulting in significant financial loss. In order to prevent these accidents, maritime object detection technology is essential to alert ships approaching buoys. Existing studies apply a number of filters to eliminate noise and to detect objects within the sea image. For this process, most studies directly access the pixels and process the images. However, this approach typically takes a long time to process because of its complexity and the requirements of significant amounts of computational power. In an emergent situation, it is important to alarm the vessel's rapid approach to buoys in real time to avoid collisions between vessels and route signs, therefore minimizing computation and speeding up processes are critical operations. Therefore, we propose Fast Connected Component Labeling (FCCL) which can reduce computation to minimize the processing time of filter applications, while maintaining the detection performance of existing methods. The results show that the detection performance of the FCCL is close to 30 FPS - approximately 2-5 times faster, when compared to the existing methods - while the average throughput is the same as existing methods.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.357-365
• /
• 2022

Refrigerant mischarging is one of the most frequently occurring failure modes in air conditioners, and both undercharging and overcharging degrade cooling performance. Therefore, it is important to accurately determine the amount of charged refrigerant. In this study, a support vector machine (SVM) model was developed to multi-classify the refrigerant mischarge through steady-state identification via fuzzy clustering techniques. For steady-state identification, a fuzzy clustering algorithm was applied to the air conditioner operation data using the difference between moving averages. The identification results using the proposed method were compared with those using existing steady-state determination techniques studied through the inversed Fisher's discriminant ratio (IFDR). Subsequently, the main features were selected using minimum redundancy maximum relevance (mRMR) considering the correlation among candidate features, and an SVM multi-classification model was devised using the derived features. The proposed method achieves satisfactory accuracy and robustness from test data collected in the new domain.

• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.101-109
• /
• 2023

In order to improve the measurement accuracy of the 6-dimensional accelerometer, the cross coupling compensation method of the accelerometer needs to be studied. In this paper, the non-linear error caused by cross coupling of piezoelectric six-dimensional accelerometer is compensated online. The cross coupling filter is obtained by analyzing the cross coupling principle of a piezoelectric six-dimensional accelerometer. Linear and non-linear fitting methods are designed. A two-level calibration hybrid compensation algorithm is proposed. An experimental prototype of a piezoelectric six-dimensional accelerometer is fabricated. Calibration and test experiments of accelerometer were carried out. The measured results show that the average non-linearity of the proposed algorithm is 2.2628% lower than that of the least square method, the solution time is 0.019382 seconds, and the proposed algorithm can realize the real-time measurement in six dimensions while improving the measurement accuracy. The proposed algorithm combines real-time and high precision. The research results provide theoretical and technical support for the calibration method and online compensation technology of the 6-dimensional accelerometer.

• Atmosphere
• /
• v.33 no.3
• /
• pp.319-330
• /
• 2023

As the need for PM type observation increases, Surface Particulate Matter Network (SPARTAN), PM samplers analyzes aerosol samples for PM mass concentration and chemical composition, were recently installed at two sites: Yonsei University at Seoul and Ulsan Institute of Science and Technology (UNIST) at Ulsan. These SPARTAN filter samplers and nephelometers provide the PM_2.5 mass concentration and chemical speciation data with aerosol type information. We introduced the overall information and installation of SPARTAN at the field site in this study. After installation and observation, both Seoul and Ulsan sites showed a similar time series pattern with the daily PM_2.5 mass concentration of SPARTAN and the data of Airkorea. In particular, in the case of high concentrations of fine particles, daily average value of PM_2.5 was relatively well-matched. During the Yonsei University observation period, high concentrations were displayed in the order of sulfate, black carbon (BC), ammonium, and calcium ions on most measurement days. The case in which the concentration of nitrate ions showed significant value was confirmed as the period during which the fine dust alert was issued. From the data analysis, SPARTAN data can be analyzed in conjunction with the existing urban monitoring network, and it is expected to have a synergetic effect in the research field. Additionally, the possibility of being analyzed with optical data such as AERONET is presented. In addition, the method of installing and operating SPARTAN has been described in detail, which is expected to help set the stage for the observation system in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.115-117
• /
• 2021

Currently, as IoT technology develops, monitoring systems are being used in various fields, and image processing is being used in various forms. Image data causes noise due to various causes during the transmission and reception process, and if it is not removed, loss of image information or error propagation occurs. Therefore, denoising images is essential. Typical methods of eliminating Salt and Pepper noise in images include AF, MF, and A-TMF. However, existing methods have the disadvantage of being somewhat inadequate in high-density noise. Therefore, in this paper, we propose an algorithm for determining noise for Salt and Pepper denoising and replacing the central pixel with an original pixel if it is non-noise, and processing the filtering mask by segmenting and averaging it in eight directions. We evaluate the performance by comparing and analyzing the proposed algorithms with existing methods.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.19-27
• /
• 2023

In the process of collecting social reviews, a number of noise reviews irrelevant to a given search keyword can be included in the search results. To filter out such reviews, machine learning can be used. However, if the number of reviews is insufficient for a target place to be analyzed, filtering accuracy can be degraded due to the lack of training data. To resolve this issue, we propose a supervised learning method to improve accuracy of the noise review filtering for the places with insufficient reviews. In the proposed method, training is not performed by an individual place, but by a group including several places with similar characteristics. The classifier obtained through the training can be used for the noise review filtering of an arbitrary place belonging to the group, so the problem of insufficient training data can be resolved. To verify the proposed method, a noise review filtering model was implemented using LSTM and BERT, and filtering accuracy was checked through experiments using real data collected online. The experimental results show that the accuracy of the proposed method was 92.4% on the average, and it provided 87.5% accuracy when targeting places with less than 100 reviews.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3854-3859
• /
• 2023

Background: This study aims to develop an evaluator that can quickly and accurately evaluate the shielding of low-energy industrial radiation generators. Methods: We used PyQt to develop a graphical user interface (GUI)-based program and employed the calculation methodology reported in the National Council on Radiation Protection and Measurements (NCRP)-49 for shielding calculations. We gathered the necessary factors for shielding evaluation using two libraries designed for Python, pandas and NumPy, and processed them into a database. We verified the effectiveness of the proposed program by comparing the results with those from safety reports of six domestic facilities. Results: After verifying the effectiveness of the program using the NCRP-49 example, we obtained an average error rate of 1.73%. When comparing the facility safety report and results obtained using the program, we found that the error rate was between 1.09% and 6.51%. However, facilities that did not use a defined shielding methodology were underestimated by 31.82% compared with the program (the final barrier thickness satisfied the shielding standard). Conclusion: The developed program provides a fast and accurate shielding evaluation that can assist personnel that work in radiation generator facilities and government officials in reviewing safety.