• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.5
• /
• pp.555-563
• /
• 2009

When a mobile mapping system or a robot is equipped with only a GPS (Global Positioning System) and multiple stereo camera system, a transformation from a local camera coordinate system to GPS coordinate system is required to link camera poses and 3D data by V-SLAM (Vision based Simultaneous Localization And Mapping) to GIS data or remove the accumulation error of those camera poses. In order to satisfy the requirements, this paper proposed a novel method that calculates a camera rotation in the GPS coordinate system using the three pairs of camera positions by GPS and V-SLAM, respectively. The propose method is composed of four simple steps; 1) calculate a quaternion for two plane's normal vectors based on each three camera positions to be parallel, 2) transfer the three camera positions by V-SLAM with the calculated quaternion 3) calculate an additional quaternion for mapping the second or third point among the transferred positions to a camera position by GPS, and 4) determine a final quaternion by multiplying the two quaternions. The final quaternion can directly transfer from a local camera coordinate system to the GPS coordinate system. Additionally, an update of the 3D data of captured objects based on view angles from the object to cameras is proposed. This paper demonstrated the proposed method through a simulation and an experiment.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.184-192
• /
• 2022

Valve internal leakage is caused by damage to the internal parts of the valve, resulting in accidents and shutdowns of the piping system. This study investigated the possibility of a real-time leak detection method using the acoustic emission (AE) signal generated from the piping system during the internal leakage of a butterfly valve. Datasets of raw time-domain AE signals were collected and postprocessed for each operation mode of the valve in a systematic manner to develop a data-driven model for the detection and classification of internal leakage, by applying machine learning algorithms. The aim of this study was to determine whether it is possible to treat leak detection as a classification problem by applying two classification algorithms: support vector machine (SVM) and convolutional neural network (CNN). The results showed different performances for the algorithms and datasets used. The SVM-based binary classification models, based on feature extraction of data, achieved an overall accuracy of 83% to 90%, while in the case of a multiple classification model, the accuracy was reduced to 66%. By contrast, the CNN-based classification model achieved an accuracy of 99.85%, which is superior to those of any other models based on the SVM algorithm. The results revealed that the SVM classification model requires effective feature extraction of the AE signals to improve the accuracy of multi-class classification. Moreover, the CNN-based classification can be a promising approach to detect both leakage and valve opening as long as the performance of the processor does not degrade.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.21-39
• /
• 2020

Recently, deep learning has shown high performance in various applications such as pattern analysis and image classification. Especially known as a difficult task in the field of machine learning research, stock market forecasting is an area where the effectiveness of deep learning techniques is being verified by many researchers. This study proposed a deep learning Convolutional Neural Network (CNN) model to predict the direction of stock prices. We then used the feature selection method to improve the performance of the model. We compared the performance of machine learning classifiers against CNN. The classifiers used in this study are as follows: Logistic Regression, Decision Tree, Neural Network, Support Vector Machine, Adaboost, Bagging, and Random Forest. The results of this study confirmed that the CNN showed higher performancecompared with other classifiers in the case of feature selection. The results show that the CNN model effectively predicted the stock price direction by analyzing the embedded values of the financial data

• The Journal of Korean Society for Radiation Therapy
• /
• v.25 no.2
• /
• pp.159-165
• /
• 2013

Purpose: Abdominal compressor is used to control breathing in stereotactic body radiotherapy for lung tumors frequently. We evaluated the dynamic variation aspect of internal tumor volume by breathing. Materials and Methods: We reviewed 20 lung cancer patients (7 upper lung patients, 4 middle lung patients, 9 lower lung patients) who received stereotactic body radiotherapy using abdominal compressor between April 2012 to April 2013. Coordinate shift values were obtained by using four-dimensional cone-beam CT (4D-CBCT) to investigate treatment set-up error and moving tumor position error. To investigate how much difference of each part, we compared 95% confidence interval, maximum values and minimum values of three-dimensional vector value and analyzed conformity degree through the Pearson square correlation coefficient. Results: 95% confidence interval of three-dimensional vector value of each part is 1.8~2.9 mm in upper lobe, 2.3~5.4 mm in middle lobe and 2.2~4.0 mm in lower lobe. Conformity degree was the result that respectively is LR direction 0.75, SI direction 0.68 and AP direction 0.63 in upper lobe, LR direction 0.82, SI direction 0.51 and AP direction 0.92 in middle lobe and LR direction 0.63, SI direction 0.50 and AP direction 0.34 in lower lobe. Conclusion: We showed difference by each site in lung tumor due to respiration by using abdominal compressor. Therefore, we must correct treatment set-up error as well as moving tumor position error by breathing. It is also considered to be useful that it is the use of 4D-CBCT when correcting the error due to various dynamic variation.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.51-56
• /
• 2003

The structuring of Web information supports a strong user side viewpoint that a user wants his/her own needs on snooping a specific Web site. Not only the depth first algorithm or the breadth-first algorithm, but also the Web information is abstracted to a hierarchical structure. A prototype system is suggested in order to visualize and to represent a semantic significance. As a motivating example, the Web test site is suggested and analyzed with respect to several keywords. As a future research, the Web site model should be extended to the whole WWW and an accurate assessment function needs to be devised by which several suggested models should be evaluated.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.