• Smart Media Journal
• /
• v.11 no.1
• /
• pp.58-66
• /
• 2022

As Internet technology develops, SNS users are increasing. As SNS becomes popular, SNS-type crimes using the influence and anonymity of social networks are increasing day by day. In this paper, we propose a fake account classification method that applies machine learning and deep learning to statistical and image data for fake accounts classification. SNS account data used for training was collected by itself, and the collected data is based on statistical data and image data. In the case of statistical data, machine learning and multi-layer perceptron were employed to train. Furthermore in the case of image data, a convolutional neural network (CNN) was utilized. Accordingly, it was confirmed that the overall performance of account classification was significantly meaningful.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.55.3-55.3
• /
• 2019

We present a pipeline to estimate baryonic properties of a galaxy inside a dark matter (DM) halo in DM-only simulations using a machine trained on high-resolution hydrodynamic simulations. As an example, we use the IllustrisTNG hydrodynamic simulation of a (75 h^-1 Mpc)³ volume to train our machine to predict e.g., stellar mass and star formation rate in a galaxy-sized halo based purely on its DM content. An extremely randomized tree (ERT) algorithm is used together with multiple novel improvements we introduce here such as a refined error function in machine training and two-stage learning. Aided by these improvements, our model demonstrates a significantly increased accuracy in predicting baryonic properties compared to prior attempts --- in other words, the machine better mimics IllustrisTNG's galaxy-halo correlation. By applying our machine to the MultiDark-Planck DM-only simulation of a large (1 h^-1 Gpc)³ volume, we then validate the pipeline that rapidly generates a galaxy catalogue from a DM halo catalogue using the correlations the machine found in IllustrisTNG. We also compare our galaxy catalogue with the ones produced by popular semi-analytic models (SAMs). Our so-called machine-assisted semi-simulation model (MSSM) is shown to be largely compatible with SAMs, and may become a promising method to transplant the baryon physics of galaxy-scale hydrodynamic calculations onto a larger-volume DM-only run. We discuss the benefits that machine-based approaches like this entail, as well as suggestions to raise the scientific potential of such approaches.

• Journal of Animal Reproduction and Biotechnology
• /
• v.38 no.2
• /
• pp.84-88
• /
• 2023

Because multiple ovulation embryo transfer (MOET) in cattle includes several benefits such as wide spreading of genetically superior offspring for long distance, this biotechnological method has been widely applied to Hanwoo. When the recipients are not stayed close after embryo recovery from donor, the embryos are moved to other farms via several vehicles (car, train, and airplane). However, air travel induces lesser oxygen level, increased vibration, lower air pressure, higher noise, and increased exposure of cosmic radiation to living things than ground level. It was still unknown that fresh embryos obtained from multiple ovulation of Hanwoo could maintain their fertility after being transported via air plane, the present case report introduced a clinical case of MOET in Hanwoo after shipping fresh embryos via air transportation. The donor was multi-ovulated via follicle-stimulating hormone series of injection, which was followed by a gonadotrophin-releasing hormone injection and artificial insemination twice. The embryos were recovered by the uterine flushing, packed in ministraws, transported to recipients for 6 h including 1 h air flight, and then transferred to the synchronized recipients. During pregnancy diagnosis of early gestation period, 5 of 7 recipients (71.4%) presented no heat signs and showed fetal sacs with fluid under transrectal ultrasonography. After normal gestation period, all recipients naturally delivered healthy calves (male n = 2 and female n = 3) without abortion, stillbirth, and premature birth. The present case report indicated that transportation of fresh embryos for MOET via domestic flight in Korea did not affect to their fertility.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.51-59
• /
• 2024

Collecting a dataset with a corresponding labeled gaze vector requires a high cost in the gaze estimation field. In this paper, we suggest a data augmentation of manipulating the gaze of an original image, which improves the accuracy of the gaze estimation model when the number of given gaze labels is restricted. By conducting multi-class gaze bin classification as an auxiliary task and adjusting the latent variable of the diffusion model, the model semantically edits the gaze from the original image. We manipulate a non-binary attribute, pitch and yaw of gaze vector to a desired range and uses the edited image as an augmented train data. The improved gaze accuracy of the gaze estimation network in the semi-supervised learning validates the effectiveness of our data augmentation, especially when the number of gaze labels is 50k or less.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.3220-3226
• /
• 2011

In order to monitor internal risk factors such as fire, terror, etc. on the subway station, the surveillance systems using CCTV and various kinds of sensors have been implemented and recently, introduction of surveillance systems using an advanced IT technology, sensor network technology is tried on several areas. Since 2007, Korean government has made an effort to develop the intelligent surveillance and monitoring system, which can monitor fire, intrusion, passenger congestion, health-state of structure, etc., by using wireless sensor network technology and intelligent video analytic technique. For that purpose, this study carried out field wireless communication environment test on Chungmuro Station of Seoul Metro on the basis of ZigBee that is considered as a representative wireless sensor network before field application of the intelligent integrated surveillance system being developed, arranged and analyzed and ZigBee based wireless communication environment test results on the platform and waiting room of Chungmuro Station on this paper. Results of wireless spectrum analysis on the platform and waiting room showed that there is no radio frequency overlapped with that of ZigBee based sensor network and no frequency interference with adjacent frequencies separated 10MHz or more. As results of wireless data transmission test using ZigBee showed that data transmission is influenced by multi-path fading effect from the number and flow rate of passengers on the platform or the waiting room rather than effects from entrance and exit of the train to/from the platform, it should be considered when implementing the intelligent integrated surveillance system on the station.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.483-488
• /
• 2018

Far field input utterance is one of the major causes of performance degradation of speaker verification systems. In this study, we used teacher student learning framework to compensate for the performance degradation caused by far field utterances. Teacher student learning refers to training the student deep neural network in possible performance degradation condition using the teacher deep neural network trained without such condition. In this study, we use the teacher network trained with near distance utterances to train the student network with far distance utterances. However, through experiments, it was found that performance of near distance utterances were deteriorated. To avoid such phenomenon, we proposed techniques that use trained teacher network as initialization of student network and training the student network using both near and far field utterances. Experiments were conducted using deep neural networks that input raw waveforms of 4-channel utterances recorded in both near and far distance. Results show the equal error rate of near and far-field utterances respectively, 2.55 % / 2.8 % without teacher student learning, 9.75 % / 1.8 % for conventional teacher student learning, and 2.5 % / 2.7 % with proposed techniques.

• Steel and Composite Structures
• /
• v.49 no.1
• /
• pp.81-89
• /
• 2023

A simplified calculation method of natural vibration characteristics of high-speed railway multi-span bridge-longitudinal ballastless track system is proposed. The rail, track slab, base slab, main beam, bearing, pier, cap and pile foundation are taken into account, and the multi-span longitudinal ballastless track-beam-bearing-pier-cap-pile foundation integrated model (MBTIM) is established. The energy equation of each component of the MBTIM based on Timoshenko beam theory is constructed. Using the improved Fourier series, and the Rayleigh-Ritz method and Hamilton principle are combined to obtain the extremum of the total energy function. The simplified calculation formula of the natural vibration frequency of the MBTIM under the influence of vertical and longitudinal vibration is derived and verified by numerical methods. The influence law of the natural vibration frequency of the MBTIM is analyzed considering and not considering the participation of each component of the MBTIM, the damage of the track interlayer component and the stiffness change of each layer component. The results show that the error between the calculation results of the formula and the numerical method in this paper is less than 3%, which verifies the correctness of the method in this paper. The high-order frequency of the MBTIM is significantly affected considering the track, bridge pier, pile soil and pile cap, while considering the influence of pile cap on the low-order and high-order frequency of the MBTIM is large. The influence of component damage such as void beneath slab, mortar debonding and fastener failure on each order frequency of the MBTIM is basically the same, and the influence of component damage less than 10m on the first fourteen order frequency of the MBTIM is small. The bending stiffness of track slab and rail has no obvious influence on the natural frequency of the MBTIM, and the bending stiffness of main beam has influence on the natural frequency of the MBTIM. The bending stiffness of pier and base slab only has obvious influence on the high-order frequency of the MBTIM. The natural vibration characteristics of the MBTIM play an important guiding role in the safety analysis of high-speed train running, the damage detection of track-bridge structure and the seismic design of railway bridge.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Journal of radiological science and technology
• /
• v.31 no.2
• /
• pp.149-159
• /
• 2008

The purposes of this study are to analyze abnormal dilatation of the extrahepatic bile ducts by using transabdominal ultrasound, to confirm the existence of bile ducts diseases and their interrelationship, and for it to give a new theoretical basis for the technical access to extrahepatic bile ducts, upon which to analyze the ripple effects of the scan training. After teaching technical access process based on the new theory about extrahepatic bile duct to the thirty students who are studying ultrasonography, we allocated three hours per one student (30 mins ${\times}$ 6 times) to focus on the training of scanning skill. Training has been performed by one-to-one method. For evaluation, all the students have to perform the scans on (1) confluence of the right and left hepatic ducts (extrahepatic bile ducts and cystic duct), (2) the suprapancreatic bile duct, (3) the intrapancreatic bile duct, (4) intrapapilla Duct, based on the clearly divided concept. The existing training and methods have had low confidency about transabdominal ultrasonography of the extrahepatic bile duct and had limitation with which they could image only the suprapancreatic bile duct. The evaluation after finishing the train based on the new theory, however, all the students (30students) can access to (1) confluence of the right and left hepatic ducts(extrahepatic bile ducts and cystic duct), (2) the suprapancreatic bile duct objectively. 24 students can access to (3) the intrapancreatic bile duct and only one student can even make an image for (4) the intrapapilla Duct Though the evaluation on extrahepatic bile duct has to be performed with multi-sided method considering intrahepatic cause, bile duct cause and pathophysiological cause, only if we can image the extrahepatic bile duct to ampular of Vater objectively and confidently, we can greatly reduce invasive procedure such as ERCP, which is for the purpose of simple differential diagnosis and painful to the patients. Therefore if we concentrate on the scanning train based on the new theory to raise the confidency about ultrasonography, the effect will be doubled.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1701-1708
• /
• 2011

A typical day in the subway transportation is used by hundreds of thousands are also concerned about the safety of the various workrooms with high underground fire or other less than in the subway users could be damaging even to be raised and there. In 2010, in fact, room air through vents in the fire because smoke and toxic gas accident victims, and train service suspended until such cases are often reported. In response to these incidents in subway stations, even if the latest IT technology, wireless sensor network technology and intelligent video surveillance technology by integrating fire and structural integrity, such as a comprehensive integrated surveillance system to monitor the development of intelligent urban transit system and are under study. In this study, prior to the application of the monitoring system into the field stations, authors carried out the ZigBee-based wireless sensor networks performance analyzation in the Chungmuro station. The test results at a communications room and ventilation room of the station are summarized and analyzed.