• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.411-413
• /
• 2010

The wireless AP positioning system is under active progress regarding research and commercialization due to its merit of being able to overcome the representing demerits of existing GPS positioning, which are signal distortion and poor signal reception. This system's feature is to collect AP information distributed throughout the real world, store it on database, and execute positioning by comparing with searched AP information. The positioning process uses collected data, whereas comparison of database data uses the fingerprinting method. The fingerprinting method is a probabilistic modeling method that acquires as much of the data collected from one location upon database composition, to store the value's average value and use it in positioning. Yet, using the average value may contain the probability of errors. Such errors are fatal weaknesses for services based on the background of accurate positioning. This paper deals with the characteristics and problems of the previously used wireless AP positioning system, and proposes measures of using AP information for outdoor positioning in order to solve the aforementioned problems.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.30-37
• /
• 2021

Recently, 3D contents used in various fields have been attracting people's attention due to the development of virtual reality and augmented reality technology. In order to produce 3D contents, it is necessary to model the objects as vertices. However, high-quality modeling is time-consuming and costly. In order to convert a 2D character into a 3D model, it is necessary to express it as line drawings through feature line extraction. The extraction of consistent line drawings from 2D cartoon cartoons is difficult because the styles and techniques differ depending on the designer who produces them. Therefore, it is necessary to extract the line drawings that show the geometrical characteristics well in 2D cartoon shapes of various styles. This study proposes a method of automatically extracting line drawings. The 2D Cartoon shading image and line drawings are learned by using adversarial network model, which is artificial intelligence technology and outputs 2D cartoon artwork of various styles. Experimental results show the proposed method in this research can be obtained as a result of the line drawings representing the geometric characteristics when a 2D cartoon painting as input.

• Journal of Information Science Theory and Practice
• /
• v.9 no.1
• /
• pp.24-34
• /
• 2021

The popularity of social networking sites (SNS) has facilitated communication between users. The usage of SNS helps users in their daily life in various ways such as sharing of opinions, keeping in touch with old friends, making new friends, and getting information. However, some users misuse SNS to belittle or hurt others using profanities, which is typical in cyberbullying incidents. Thus, in this study, we aim to identify profane words from the ASKfm corpus to analyze the profane word distribution across four different roles involved in cyberbullying based on lexicon dictionary. These four roles are: harasser, victim, bystander that assists the bully, and bystander that defends the victim. Evaluation in this study focused on occurrences of the profane word for each role from the corpus. The top 10 common words used in the corpus are also identified and represented in a graph. Results from the analysis show that these four roles used profane words in their conversation with different weightage and distribution, even though the profane words used are mostly similar. The harasser is the first ranked that used profane words in the conversation compared to other roles. The results can be further explored and considered as a potential feature in a cyberbullying detection model using a machine learning approach. Results in this work will contribute to formulate the suitable representation. It is also useful in modeling a cyberbullying detection model based on the identification of profane word distribution across different cyberbullying roles in social networks for future works.

• Nano
• /
• v.13 no.11
• /
• pp.1850126.1-1850126.10
• /
• 2018

Flexible strain sensors, as the core member of the family of smart electronic devices, along with reasonable sensing range and sensitivity plus low cost, have rose a huge consumer market and also immense interests in fundamental studies and technological applications, especially in the field of biomimetic robots movement detection and human health condition monitoring. In this paper, we propose a new flexible strain sensor based on thick CVD graphene film and its low-cost fabrication strategy by using the commercial adhesive tape as flexible substrate. The tensile tests in a strain range of ~30% were implemented, and a gage factor of 30 was achieved under high strain condition. The optical microscopic observation with different strains showed the evolution of cracks in graphene film. Together with commonly used platelet overlap theory and percolation network theory for sensor resistance modeling, we established an overlap destructive resistance model to analyze the sensing mechanism of our devices, which fitted the experimental data very well. The finding of difference of fitting parameters in small and large strain ranges revealed the multiple stage feature of graphene crack evolution. The resistance fallback phenomenon due to the viscoelasticity of flexible substrate was analyzed. Our flexible strain sensor with low cost and simple fabrication process exhibits great potential for commercial applications.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.451-456
• /
• 2018

UAVs (Unmanned Aerial Vehicles) are widely used for maintenance and monitoring of facilities. It is necessary to acquire a high-resolution image for evaluating the appearance state of the facility in safety inspection. In addition, it is essential to acquire the video data in order to acquire data over a wide area rapidly. In general, since video data does not include position information, it is difficult to analyze the actual size of the inspection object quantitatively. In this study, we evaluated the utilization of 3D point cloud data of bridges using a matching between video frames and reference photos. The drones were used to acquire video and photographs. And exterior orientations of the video frames were generated through feature point matching with reference photos. Experimental results showed that the accuracy of the video frame data is similar to that of the reference photos. Furthermore, the point cloud data generated by using video frames represented the shape and size of bridges with usable accuracy. If the stability of the product is verified through the matching test of various conditions in the future, it is expected that the video-based facility modeling and inspection will be effectively conducted.

• Wind and Structures
• /
• v.27 no.6
• /
• pp.381-397
• /
• 2018

Nonlinear behavior in fluid-structure interaction (FSI) of bridge decks becomes increasingly significant for modern bridges with increasing spans, larger flexibility and new aerodynamic deck configurations. Better understanding of the nonlinear aeroelasticity of bridge decks and further development of reduced-order nonlinear models for the aeroelastic forces become necessary. In this paper, the amplitude-dependent and neutral angle dependent nonlinearities of the motion-induced loads are further highlighted by series of computational fluid dynamics (CFD) simulations. An effort has been made to investigate a semi-analytical time-domain model of the nonlinear motion induced loads on the deck, which enables nonlinear time domain simulations of the aeroelastic responses of the bridge deck. First, the computational schemes used here are validated through theoretically well-known cases. Then, static aerodynamic coefficients of the Great Belt East Bridge (GBEB) cross section are evaluated at various angles of attack, leading to the so-called nonlinear backbone curves. Flutter derivatives of the bridge are identified by CFD simulations using forced harmonic motion of the cross-section with various frequencies. By varying the amplitude of the forced motion, it is observed that the identified flutter derivatives are amplitude-dependent, especially for $A^*_2$ and $H^*_2$ parameters. Another nonlinear feature is observed from the change of hysteresis loop (between angle of attack and lift/moment) when the neutral angles of the cross-section are changed. Based on the CFD results, a semi-analytical time-domain model for describing the nonlinear motion-induced loads is proposed and calibrated. This model is based on accounting for the delay effect with respect to the nonlinear backbone curve and is established in the state-space form. Reasonable agreement between the results from the semi-analytical model and CFD demonstrates the potential application of the proposed model for nonlinear aeroelastic analysis of bridge decks.

• Smart Structures and Systems
• /
• v.23 no.6
• /
• pp.565-577
• /
• 2019

One of the most effective countermeasures for mitigating cable vibration is to install mechanical dampers near the anchorage of the cable. Most of the dampers used in the field are so-called passive dampers where their parameters cannot be changed once designed. The parameters of passive dampers are usually determined based on the optimal damper force obtained from the universal design curve for linear dampers, which will provide a maximum additional damping for the cable. As the optimal damper force is chosen based on a predetermined principal vibration mode, passive dampers will be most effective if cable undergoes single-mode vibration where the vibration mode is the same as the principal mode used in the design. However, in the actual engineering practice, multi-mode vibrations are often observed for cables. Therefore, it is desirable to have dampers that can suppress different modes of cable vibrations simultaneously. In this paper, MR dampers are proposed for controlling multi-mode cable vibrations, because of its ability to change parameters and its adaptability of active control without inquiring large power resources. Although the highly nonlinear feature of the MR material leads to a relatively complex representation of its mathematical model, effective control strategies can still be derived for suppressing multi-mode cable vibrations based on nonlinear modelling, as proposed in this paper. Firstly, the nonlinear Bouc-wen model is employed to accurately portray the salient characteristics of the MR damper. Then, the desired optimal damper force is determined from the universal design curve of friction dampers. Finally, the input voltage (current) of MR damper corresponding to the desired optimal damper force is calculated from the nonlinear Bouc-wen model of the damper using a piecewise linear interpolation scheme. Numerical simulations are carried out to validate the effectiveness of the proposed control algorithm for mitigating multi-mode cable vibrations induced by different external excitations.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2022

Accurately measuring location is necessary to provide a variety of services. The data for indoor positioning measures the RSSI values from the WiFi device through an application of a smartphone. The measured data becomes the raw data of machine learning. The feature data is the measured RSSI value, and the label is the name of the space for the measured position. For this purpose, the machine learning technique is to study a technique that predicts the exact location only with the WiFi signal by applying an efficient technique to classification. Ensemble is a technique for obtaining more accurate predictions through various models than one model, including backing and boosting. Among them, Boosting is a technique for adjusting the weight of a model through a modeling result based on sampled data, and there are various algorithms. This study uses Xgboost among the above techniques and evaluates performance with other ensemble techniques.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.27-36
• /
• 2022

In this paper, to improve the conditions of the fish processing site, we propose a method to predict the cutting point of fish according to the target weight using AI machine vision. The proposed method performs image-based preprocessing by first photographing the top and front views of the input fish. Then, RANSAC(RANdom SAmple Consensus) is used to extract the fish contour line, and then 3D external information of the fish is obtained using 3D modeling. Next, machine learning is performed on the extracted three-dimensional feature information and measured weight information to generate a neural network model. Subsequently, the fish is cut at the cutting point predicted by the proposed technique, and then the weight of the cut piece is measured. We compared the measured weight with the target weight and evaluated the performance using evaluation methods such as MAE(Mean Absolute Error) and MRE(Mean Relative Error). The obtained results indicate that an average error rate of less than 3% was achieved in comparison to the target weight. The proposed technique is expected to contribute greatly to the development of the fishery industry in the future by being linked to the automation system.