• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.845-853
• /
• 2020

In this paper, we propose a method for classifying environmental sound for selective noise cancellation in industrial sites. Noise in industrial sites causes hearing loss in workers, and researches on noise cancellation have been widely conducted. However, the conventional methods have a problem of blocking all sounds and cannot provide the optimal operation per noise type because of common cancellation method for all types of noise. In order to perform selective noise cancellation, therefore, we propose a method for environmental sound classification based on deep learning. The proposed method uses new sets of acoustic features consisting of temporal and statistical properties of Mel-spectrogram, which can overcome the limitation of Mel-spectrogram features, and uses convolutional neural network as a classifier. We apply the proposed method to five-class sound classification with three noise classes and two non-noise classes. We confirm that the proposed method provides improved classification accuracy by 6.6% point, compared with that using conventional Mel-spectrogram features.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.667-676
• /
• 2021

Recently, adolescents in Korea are exposed to the risk of postural imbalance due to overuse of smartphones and lack of physical activity due to the amount of learning. In addition, the need for effective non-face-to-face exercise services is increasing due to Corona 19. With this in mind, this study proposes an exercise service using an EMG sensor to overcome the limitations of non-face-to-face services while providing the effect of improving round shoulders for adolescents. An exercise program that can improve round shoulders was constructed, and an application in conjunction with an EMG sensor was implemented to exercise effectively. The exercise program was configured to alternately exercise the target muscle area for 4 weeks, and the function to provide feedback was added by measuring the EMG values that change accordingly. Through this study, we intend to provide the basis for exercise-based posture correction digital service, and improve the unbalanced body through this, thereby promoting the possibility of health promotion.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.339-345
• /
• 2021

With the development of online education due to COVID-19, the EduTech market, which combines new technologies such as AI and AR/VR in education is rapidly growing. In addition, the children's industry is steadily growing despite the decreasing birth rate every year as more and more families with one child per household are investing in their children. However, supply of contents to EduTech market is slow compared to demands that are increasing. Therefore, the purpose of this paper is to help solve these problems by developing and supporting AR kids contents with convenience, practicality, and efficiency using AR technology. AR content for supporting vocabulary learning for infants is not just an end to watching and listening, but an observation-driven model that can manipulate content directly, which attracts children's interest and helps children learn words. This paper is intended for infants from 15 months to 36 months old when full-fledged language development occurs.

• The Journal of Information Systems
• /
• v.31 no.1
• /
• pp.147-173
• /
• 2022

Purpose As the use of social network services has become common, it has become possible to freely communicate and establish relationships with other people anytime, anywhere for communication and information sharing. Influencers who have a strong influence on consumers' perceptions and attitudes through their own opinions and stories have appeared on various social media channels such as YouTube. Recently, companies utilize influencers with a large number of followers to check interactions with customers to understand customer attitudes and opinions about products in real time. Start-ups with insufficient resources need to quickly examine customer responses to reduce the probability of failure after product planning. The Lean process of creating an MVP and quickly confirming and learning the market response should be repeated over and over again. Findings In this paper, we try to suggest that the YouTube platform can play a sufficient role as a customer experiment space through examples. The case company is a company that has successfully commercialized products by continuously interacting with customers through the YouTube platform for the first four months of its founding. This paper is expected to be helpful in the experimental process for prospective founders and early founders to examine customer responses to reduce the probability of market failure before commercialization. Design/methodology/approach This paper analyzed the YouTube channel data of case companies based on the netnography methodology and presented the contents of the lean process management carried out in the experimental stage and the post-production stage through interview research.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.369-377
• /
• 2022

Recent deep learning-based face synthesis research shows the result of generating a realistic face including overall style or elements such as hair, glasses, and makeup. However, previous methods cannot create a face at a very detailed level, such as the microstructure of the skin. In this paper, to overcome this limitation, we propose a technique for synthesizing a more realistic facial image from a single face label image by controlling the types and intensity of skin microelements. The proposed technique uses Pix2PixHD, an Image-to-Image Translation method, to convert a label image showing the facial region and skin elements such as wrinkles, pores, and redness to create a facial image with added microelements. Experimental results show that it is possible to create various realistic face images reflecting fine skin elements corresponding to this by generating various label images with adjusted skin element regions.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.778-789
• /
• 2021

Recently, various lightweight methods for using Convolutional Neural Network(CNN) models in mobile devices have emerged. Weight quantization, which lowers bit precision of weights, is a lightweight method that enables a model to be used through integer calculation in a mobile environment where GPU acceleration is unable. Weight quantization has already been used in various models as a lightweight method to reduce computational complexity and model size with a small loss of accuracy. Considering the size of memory and computing speed as well as the storage size of the device and the limited network environment, this paper proposes a method of compressing integer weights after quantization using a video codec as a method. To verify the performance of the proposed method, experiments were conducted on VGG16, Resnet50, and Resnet18 models trained with ImageNet and Places365 datasets. As a result, loss of accuracy less than 2% and high compression efficiency were achieved in various models. In addition, as a result of comparison with similar compression methods, it was verified that the compression efficiency was more than doubled.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.812-815
• /
• 2022

Images displayed on a digital devices under the sunlight are generally perceived to be darker than the original images, which leads to a decrease in visibility. For better visibility, global luminance compensation or tone mapping adaptive to ambient lighting is required. However, the existing methods have limitations in chrominance compensation and are difficult to use in real world due to their heavy computational cost. To solve these problems, this paper propose a piece-wise linear curves (PLECs)-based image enhancement method to improve both luminance and chrominance. At this time, PLECs are regressed through deep learning and implemented in the form of a lookup table to real-time operation. Experimental results show that the proposed method has better visibility compared to the original image with low computational cost.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.738-750
• /
• 2022

In this study, we reviewed and discussed whether auditory stimuli with short length can evoke emotion-related neurological responses. The findings implicate that if personalized sound tracks are provided to XR users based on machine learning or probability network models, user experiences in XR environment can be enhanced. We also investigated that the arousal-relaxed factor evoked by short auditory sound can make distinct patterns in functional connectivity characterized from background EEG signals. We found that coherence in the right hemisphere increases in sound-evoked arousal state, and vice versa in relaxed state. Our findings can be practically utilized in developing XR sound bio-feedback system which can provide preference sound to users for highly immersive XR experiences.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.619-628
• /
• 2022

Although face recognition and face generation have been growing in popularity, the privacy issues of using facial images in the wild have been a concurrent topic. In this paper, we propose a face editing network that can reduce privacy issues by generating face images with various properties from a small number of real face images and facial mask information. Unlike the existing methods of learning face attributes using a lot of real face images, the proposed method generates new facial images using a facial segmentation mask and texture images from five parts as styles. The images are then trained with our network to learn the styles and locations of each reference image. Once the proposed framework is trained, we can generate various face images using only a small number of real face images and segmentation information. In our extensive experiments, we show that the proposed method can not only generate new faces, but also localize facial attribute editing, despite using very few real face images.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.341-348
• /
• 2021

This study identified learners' immersion, focusing on online video education platforms, Zoom and Webex, used in colleges after the 'Covid-19', and suggested design improvement measures to improve immersion. Through prior research and literature research, the components of immersion and screen components of the online distance education platform were identified, and measures to improve immersion were suggested through questionnaire surveys and in-depth interviews. The research method was conducted for 5 days from April 7 to 12, 2021 for 50 college students and graduate students in their 20s and 30s who are receiving online education through Zoom and Webex, and 6 people were interviewed in-depth. As a result of the experiment, the communication between learners and lecturers was deduced as the biggest factor, so a design plan to facilitate communication between learners and lecturers was proposed based on Gutenberg's diagram. As online video education is predicted to continue even after the Covid-19, continuous online video education immersion research is needed, and we hope that it can contribute to the direction of the research.