• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.206-207
• /
• 2023

Intelligent maritime traffic information services provide services for maritime traffic safety, but due to the difference in ship specifications and loading condition, the method of determining abnormalities in ship stability has not been generalized. In this study, we established a method for collecting and preprocessing Accelerometer and GPS data for calculating ship stability. In addition, we have researched a model that can determine the real-time ship stability through data science algorithms that can reflect each vessel specifications and external forces, breaking away from approximate calculations that cannot reflect weather factors in the real ocean.

• Information Systems Review
• /
• v.25 no.3
• /
• pp.1-26
• /
• 2023

A theoretical model of information overload (Jackson and Farzaneh, 2012) with its three influential components (i.e., time, technology, and social networks) was empirically tested in the context of news consumption behavior considered as a communicative outcome. Using a national sample of South Korean adults (N = 1166), data analyses identified perceived information overload and large/diverse social networks positively associated with active and passive news consumption. Findings may imply the existence of individually varying cognitive threshold (i.e., tipping point), if crossed individuals cannot process information any further. News consumers may keep searching and receiving information to verify factuality of news even when they feel overloaded.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.97-104
• /
• 2010

In this paper, ICT (in circuit tester) inspection system and inspection algorithm is proposed and detects whether inferiority exists or not in the mounted device on the flexible PCB in cell phones or mobile display devices. The system is composed of PD (pin-driver) and GGM (ground guarding method). The structural characteristics of these flexible PCB are analyzed, which is needed to input or output the test signal. Test signal to investigate the characteristics of passive components is generated using modified circuit diagram and proposed inspection algorithm. PM (pin-map) is decided on the basis of circuit diagram and has the information about the kind of test signal to be applied and the pad number for the test signal to be connected. PD is designed to load a proper test signal for a specific pad and is adjusted according to PM so that the reconstructed circuit has minimum node and mash. The proposed ICT inspection system is realized using PD and GGM. Using the system, an experiment for each passive component is done to investigate the measurement accuracy of the developed system and an experiment for real flexible PCB model is done to verity the effectiveness of the system.

• Journal of Korea Water Resources Association
• /
• v.44 no.12
• /
• pp.975-990
• /
• 2011

In this study, to develop an assessment method for spatio-temporal riverbed changes, a 1-dimensional model (HEC-RAS) and a 2-dimensional model (CCHE2D) were built and applied. As for the analysis of a riverbed's long-term change in a real stream, three new assessment methods were developed, which are called the "Sediment section cumulative curve", "Sediment section moment", and "Sediment probability distribution function." These methods were used to assess the characteristics of riverbed changes using a consistent valuation standard and to understand changes in quantities intuitively. From the results of this study, sediment characteristics of cross sections can be detected effectively by applying the "Sediment section cumulative curve" method to determine whether there is any sedimentation or erosion in total emission. The amount of sedimentation or erosion occurring in the right or left banks, which divided by center column, could be presented as one criterion by applying the "Sediment section moment" method. This approach could be utilized as an indicator for sediment predictions. Spatio-temporal sediment variables can be presented quantitatively by determining the mean and uncertain boundaries through the "Sediment probability distribution function", and finally, the results can be illustrated for each cross section to provide intuitive recognition.

• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.318-326
• /
• 2005

This paper presents the image feature extraction method and the image classification technique to select the harmful image flowed from the Internet by grade of image contents such as harmlessness, sex-appealing, harmfulness (nude), serious harmfulness (adult) by the characteristic of the image. In this paper, we suggest skin area detection technique to recognize whether an input image is harmful or not. We also propose the ROI detection algorithm that establishes region of interest to reduce some noise and extracts harmful degree effectively and defines the characteristics in the ROI area inside. And this paper suggests the multiple-SVM training method that creates the image classification model to select as 4 types of class defined above. This paper presents the multiple-SVM classification algorithm that categorizes harmful grade of input data with suggested classification model. We suggest the skin likelihood image made of the shape information of the skin area image and the color information of the skin ratio image specially. And we propose the image feature vector to use in the characteristic category at a course of traininB resizing the skin likelihood image. Finally, this paper presents the performance evaluation of experiment result, and proves the suitability of grading image using image feature classification algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.3
• /
• pp.600-611
• /
• 1996

Recently, neural network-based speech recognition has been studied to utilize the adaptivity and learnability of neural network models. However, conventional neural network models have difficulty in the co-articulation processing and the boundary detection of similar phonmes of the Korean speech. Also, in case of using one phonotopic map, learning speed may dramatically increase and inaccuracies may be caused because homogeneous learning and recognition method should be applied for heterogenous data. Hence, in this paper, a neural net typewriter has been designed using a hierarchical self-organizing classifier(HSOC), and related algorithms are presented. This HSOC, during its learing stage, distributed phoneme data on hierarchically structured multiple phonotopic maps, using Kohonen's self-organizing feature maps(SOFM). Presented and experimented in this paper were the algorithms for deciding the number of maps, map sizes, the selection of phonemes and their placement per map, an approapriate learning and preprocessing method per map. If maps are divided according to a priorlinguistic knowledge, we would have difficulty in acquiring linguistic knowledge and how to alpply it(e.g., processing extended phonemes). Contrarily, our HSOC has an advantage that multiple phonotopic maps suitable for given input data are self-organizable. The resulting three korean phonotopic maps are optimally labelled and have their own optimal preprocessing schemes, and also confirm to the conventional linguistic knowledge.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2008.10a
• /
• pp.173-178
• /
• 2008

In this paper, we will introduce rock physics modeling technique, which interrelate reservoir properties with seismic properties, and apply the technique to the Donghae-1 gas reservoir. From well-log data analysis, we obtained velocityporosity (Vp-$\phi$) relations for each formation. These relations can used to predict porosity from seismic data. In addition, we analyzed permeability data, which were obtained from core measurements and computational rock physics simulations. We then obtained permeability-porosity ($\kappa-\phi$) relations. Combining $\kappa-\phi$ with Vp-$\phi$ relations, we finally present quantitative Vp-$\kappa$ relations. As to Vp-$\phi$ modeling, we found that the degree of diagenesis and clay contents increase with depth. As to Vp-$\kappa$ relations, though \kappa-\phi relations are almost identical for all formations, we could obtain distinct Vp-$\kappa$ relations due to Vp-$\phi$ variations. In conclusion, the rock physics modeling, which bridges between seismic properties and reservoir properties, can be a very robust tool for quantitative reservoir characterization with less uncertainty.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.255-257
• /
• 2017

These days automotive markets are launching models that include a variety of IT technologies. Tesla's Tesla model S and Google's unmanned automobiles are emerging one after another. This type of automobile with IT technology provides various convenience to the driver and the driver is getting benefit by various conveience services. on the contrary, it is also true that defects for errors in electronic components cause accidents that threaten the safety of drivers. There is a sudden unintended acceleration among these accidents. The cause of the accident is not clear yet, but the claim that the ECU device caused by the magnetic field causes accident of the car due is the most reliable. But, in Korea, when occur a car sudden unintended acceleration accident, the char maker often claims that an accident occurred due to driver's pedal malfunction. Also most drivers are responsible for the lack of grounds to refute. In this paper, the pedal operation image of the driver is acquired and the sensor is attached to the control part such as the excel and brake so as to discriminate whether the vehicle sudden unintended acceleration accident is the driver's pedal operation error or the fault of. i have implemented a system that can do this.

• Korean Chemical Engineering Research
• /
• v.45 no.1
• /
• pp.32-38
• /
• 2007

A batch Process has a multi-way data structure that consists of batch-time-variable axis, so the statistical modeling of a batch process is a difficult and challenging issue to the process engineers. In this study, We applied a statistical process control technique to the general batch process data, and implemented a fault-detection and Statistical process control system that was able to detect, identify and diagnose the fault. Semiconductor etch process and semi-batch styrene-butadiene rubber process data are used to case study. Before the modeling, we pre-processed the data using the multi-way unfolding technique to decompose the data structure. Multivariate regression techniques like support vector regression and partial least squares were used to identify the relation between the process variables and process condition. Finally, we constructed the root mean squared error chart and variable contribution chart to diagnose the faults.