• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• Phonetics and Speech Sciences
• /
• v.11 no.4
• /
• pp.89-96
• /
• 2019

In this paper, we propose a deep learning architecture that can effectively detect speech segmentation in broadcast contents. We also propose a multi-scale time-dilated layer for learning the temporal changes of feature vectors. We implement several comparison models to verify the performance of proposed model and calculated the frame-by-frame F-score, precision, and recall. Both the proposed model and the comparison model are trained with the same training data, and we train the model using 32 hours of Korean broadcast data which is composed of various genres (drama, news, documentary, and so on). Our proposed model shows the best performance with F-score 91.7% in Korean broadcast data. The British and Spanish broadcast data also show the highest performance with F-score 87.9% and 92.6%. As a result, our proposed model can contribute to the improvement of performance of speech detection by learning the temporal changes of the feature vectors.

• Journal of Korean Library and Information Science Society
• /
• v.34 no.1
• /
• pp.261-286
• /
• 2003

This paper is to emphasize on important of reading books and leading instruction at the age of multi-media. And this paper observes the promotion of reading books fer children in all the world. Especially the role of public library is important for the promotion of reading books fur children. According]y this paper present plans for the promotion of reading books for children successfully. The role of public library is a mediator for book and children. We have to restore storytelling culture for forming cooperative culture and healing heart pain in the public library. And We have to found a children's library around the children's life, especially in the local government. We have to train children's librarian Immediately In educational institution. We have to enhance the specialization of children's room librarian in the public library.

• Journal of Communications and Networks
• /
• v.7 no.2
• /
• pp.157-170
• /
• 2005

The combination of multiple antennas and multi-carrier code division multiple-access (MC-CDMA) is a strong candidate for the downlink of the next generation mobile communications. The study of such systems in scenarios that model real-life trans-missions is an additional step towards an optimized achievement. We consider a realistic MIMO channel with two or four transmit antennas and up to two receive antennas, and channel state information (CSI) mismatches. Depending on the mobile terminal (MT) class, its number of antennas or complexity allowed, different data-rates are proposed with turbo-coding and asymptotic spectral efficiencies from 1 to 4.5 bit/s/Hz, using three algorithms developed within the European IST-MATRICE project. These algorithms can be classified according to the degree of CSI at base-station (BS): i) Transmit space-frequency prefiltering based on constrained zero-forcing algorithm with complete CSI at BS; ii) transmit beamforming based on spatial correlation matrix estimation from partial CSI at BS; iii) orthogonal space-time block coding based on Alamouti scheme without CSI at BS. All presented schemes require a reasonable complexity at MT, and are compatible with a single-antenna receiver. A choice between these algorithms is proposed in order to significantly improve the performance of MC-CDMA and to cover the different environments considered for the next generation cellular systems. For beyond-3G, we propose prefiltering for indoor and pedestrian microcell environments, beamforming for suburban macrocells including high-speed train, and space-time coding for urban conditions with moderate to high speeds.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.3
• /
• pp.115-120
• /
• 2019

Hemiplegic patients who suffered from a stroke struggle with a deterioration in upper limb functions, which can both be psychologically and physically discomforting; this can also limit patients' daily tasks involving any upper limb motions. In this study, we developed an assistive device for hemiplegic patients to improve their upper limb functions. It was manufactured to train patients by using their grip strength and the range of motion of the arm. Furthermore, we produced game contents in virtual reality to induce users' immersion and interaction. It was configured as a multi-player game to help ease the mental burden of receiving the training alone, hence allowing the patient and the caregiver to join the rehabilitation training simultaneously. The assistive device and game contents developed in this study enables patients and caregivers to easily check the degree of improvements in upper limb function by viewing quantitative analysis and visualized results.

• Structural Engineering and Mechanics
• /
• v.91 no.6
• /
• pp.643-656
• /
• 2024

The prediction of the moment rotation behavior of semi-rigid connections has been the subject of extensive research. However, to improve the accuracy of these predictions, there is a growing interest in employing machine learning algorithms. This paper investigates the effectiveness of using Multi-gene genetic programming (MGGP) to predict the moment-rotation behavior of flush-end plate connections compared to that of artificial neural networks (ANN) and previous studies. It aims to automate the process of determining the most suitable equations to accurately describe the behavior of these types of connections. Experimental data was used to train ANN and MGGP. The performance of the models was assessed by comparing the values of coefficient of determination (R²), maximum absolute error (MAE), and root-mean-square error (RMSE). The results showed that MGGP produced more accurate, reliable, and general predictions compared to ANN and previous studies with an R² exceeding 0.99, an RMSE of 6.97, and an MAE of 38.68, highlighting its advantages over other models. The use of MGGP can lead to better modeling and more precise predictions in structural design. Additionally, an experimentally-based regression analysis was conducted to obtain the rotational capacity of FECs. A new equation was proposed and compared to previous ones, showing significant improvement in accuracy with an R² score of 0.738, an RMSE of 0.014, and an MAE of 0.024.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1966-1972
• /
• 2011

Optical flow estimation based on multi constraint approaches is frequently used for recognition of moving objects. This paper proposed the method to monitor passenger boarding using image processing when a train is operated based on Automatic Train Operation(ATO). The movement of passenger can be detected to compare two images, one is a basic image and another is immediately captured by CCTV. Optical Flow helps to find the movement of passenger when two images are compared. The movement of passenger is one of important informations for ATO system because it needs to decide door status.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.372-377
• /
• 2007

For more than 2,500 years, surgical teaching has been based on the so called "see one, do one, teach one" paradigm, in which the surgical trainee learns by operating on patients under close supervision of peers and superiors. However, higher demands on the quality of patient care and rising malpractice costs have made it increasingly risky to train on patients. Minimally invasive surgery, in particular, has made it more difficult for an instructor to demonstrate the required manual skills. It has been recognized that, similar to flight simulators for pilots, virtual reality (VR) based surgical simulators promise a safer and more comprehensive way to train manual skills of medical personnel in general and surgeons in particular. One of the major challenges in the development of VR-based surgical trainers is the real-time and realistic simulation of interactions between surgical instruments and biological tissues. It involves multi-disciplinary research areas including soft tissue mechanical behavior, tool-tissue contact mechanics, computer haptics, computer graphics and robotics integrated into VR-based training systems. The research described in this paper addresses the problem of characterizing soft tissue properties for medical virtual environments. A system to measure in vivo mechanical properties of soft tissues was designed, and eleven sets of animal experiments were performed to measure in vivo and in vitro biomechanical properties of porcine intra-abdominal organs. Viscoelastic tissue parameters were then extracted by matching finite element model predictions with the empirical data. Finally, the tissue parameters were combined with geometric organ models segmented from the Visible Human Dataset and integrated into a minimally invasive surgical simulation system consisting of haptic interface devices and a graphic display.

• Journal of Korean Society of Transportation
• /
• v.33 no.5
• /
• pp.431-440
• /
• 2015

This study aims to quantify the railway freight performance using various indicators, to compare it over many countries, and to evaluate efficiency of railway freight in Korea. The indicators developed in this study was classified into two categories; country-specific and company-specific indicator. The former includes freight train density, average gross train load and average haul while the latter contains revenue/ton-km, ratio of operating costs to revenue, revenue per employee, ton-km per employee, costs per ton-km and ratio of labor costs to total operating costs. The results of this study shows that Korail performance is in low efficiency due to multi-frequency small amounts transport. The productivity of railway freight in Korea represented as ton-km per employee appears to be lower than that of other oversea companies considered in this study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.9
• /
• pp.1718-1724
• /
• 2017

Recently, Smart plugs for real time monitoring of household appliances based on IoT(Internet of Things) have been activated. Through this, consumers are able to save energy by monitoring real-time energy consumption at all times, and reduce power consumption through alarm function based on consumer setting. In this paper, we measure the alternating current from a wall power outlet for real-time monitoring. At this time, the current pattern for each household appliance was classified and it was experimented with deep learning to determine which product works. As a result, we used a cross validation method and a bootstrap verification method in order to the classification performance according to the type of appliances. Also, it is confirmed that the cost function and the learning success rate are the same as the train data and test data.