• Smart Media Journal
• /
• v.8 no.2
• /
• pp.39-45
• /
• 2019

As deep learning has become popular, researches which can help explaining the prediction results also become important. Superpixel based multi-scale combining technique, which provides the advantage of visual pleasing by maintaining the shape of the object, has been recently proposed. Based on the principle of prediction difference, this technique computes the saliency map from the difference between the predicted result excluding the superpixel and the original predicted result. In this paper, we propose a new technique of both excluding and including super pixels. Experimental results show 3.3% improvement in IoU evaluation.

• Knowledge Management Research
• /
• v.20 no.3
• /
• pp.119-137
• /
• 2019

With the recent spread of digital content, more people have been watching the digital content of TV programs on their PCs or mobile devices, rather than on TVs. With the change in such media use pattern, genres(types) of broadcast programs change in the flow of the times and viewers' trends. The programs that were broadcast on TVs have been released in digital content, and thereby people watching such content change their perception. For this reason, it is necessary to newly and differently classify genres(types) of broadcast programs on the basis of digital content, from the conventional classification of program genres(types) in broadcasting companies or relevant industries. Therefore, this study suggests a plan for newly classifying broadcast programs through using machine learning with the log data of people watching the programs in online media and for applying the new classification. This study is academically meaningful in the point that it analyzes and classifies program types on the basis of digital content. In addition, it is meaningful in the point that it makes use of the program classification algorithm developed in relevant industries, and especially suggests the strategy and plan for applying it.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.22-29
• /
• 2021

In the past decade, deep learning has been applied to various medical image analysis tasks. Skeletal bone age estimation is clinically important as it can help prevent age-related illness and pave the way for new anti-aging therapies. Recent research has applied deep learning techniques to the task of bone age assessment and achieved positive results. In this paper, we propose a bone age prediction method using a deep convolutional neural network. Specifically, we first train a classification model that automatically localizes the most discriminative region of an image and crops it from the original image. The regions of interest are then used as input for a regression model to estimate the age of the patient. The experiments are conducted on a whole-body scintigraphy dataset that was collected by Chonnam National University Hwasun Hospital. The experimental results illustrate the potential of our proposed method, which has a mean absolute error of 3.35 years. Our proposed framework can be used as a robust supporting tool for clinicians to prevent age-related diseases.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.46-57
• /
• 2019

In recent research, deep learning-based methods have achieved state-of-the-art performance in various computer vision tasks. However, these methods are commonly supervised, and require huge amounts of annotated data to train. Acquisition of data demands an additional costly effort, particularly for the tasks where it becomes challenging to obtain large amounts of data considering the time constraints and the requirement of professional human diligence. In this paper, we present a data level synthetic sampling solution to learn from small and imbalanced data sets using Generative Adversarial Networks (GANs). The reason for using GANs are the challenges posed in various fields to manage with the small datasets and fluctuating amounts of samples per class. As a result, we present an approach that can improve learning with respect to data distributions, reducing the partiality introduced by class imbalance and hence shifting the classification decision boundary towards more accurate results. Our novel method is demonstrated on a small dataset of 2789 tomato plant disease images, highly corrupted with class imbalance in 9 disease categories. Moreover, we evaluate our results in terms of different metrics and compare the quality of these results for distinct classes.

• Journal of Korea Game Society
• /
• v.21 no.6
• /
• pp.75-86
• /
• 2021

Brand image refers to how customers, stakeholders and the market see and recognize the brand. A positive brand image leads to continuous purchases, but a negative brand image is directly linked to consumers' buying behavior, such as stopping purchases, so from the corporate perspective, it needs to be quickly and accurately identified. Currently, methods of investigating brand images include surveys and SNS surveys, which have limited number of samples and are time-consuming and costly. Therefore, in this study, we are going to conduct an emotional analysis of text data on social media by utilizing the machine learning based KoBERT model, and then suggest how to use it for game corporate brand image analysis and verify its performance. The result has proved some degree of usability showing the same ranking within five brands when compared with the BRI Korea's brand reputation ranking.

• Smart Media Journal
• /
• v.10 no.4
• /
• pp.80-90
• /
• 2021

Using optical music recognition technology based on deep learning, we propose to apply the results derived to VR games. To detect the music objects in the music sheet, the deep learning model used YOLO v5, and Hough transform was employed to detect undetected objects, modifying the size of the staff. It analyzes and uses BPM, maximum number of combos, and musical notes in VR games using output result files, and prevents the backlog of notes through Object Pooling technology for resource management. In this paper, VR games can be produced with music elements derived from optical music recognition technology to expand the utilization of optical music recognition along with providing VR contents.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1213-1220
• /
• 2022

This study was conducted to understand how to derive educational methods to efficiently improve class satisfaction for 130 college students who experienced non-face-to-face classes during the last Covid-19. The appropriateness of class time, improvement of learning effect, continuity of non-face-to-face classes, and use of educational media were set as items corresponding to class satisfaction. Research was attempted to derive an educational method for efficient class satisfaction improvement by grasping the difference and relationship between variables.

• Smart Media Journal
• /
• v.12 no.2
• /
• pp.36-41
• /
• 2023

With the advent of applicant tracking systems, online recruitment has become more popular, and recruitment fraud has become a serious problem. This research aims to develop a reliable model to detect recruitment fraud in online recruitment environments to reduce cost losses and enhance privacy. The main contribution of this paper is to provide an automated methodology that leverages insights gained from exploratory analysis of data to distinguish which job postings are fraudulent and which are legitimate. Using EMSCAD, a recruitment fraud dataset provided by Kaggle, we trained and evaluated various single-classifier and ensemble-classifier-based machine learning models, and found that the ensemble classifier, the random forest classifier, performed best with an accuracy of 98.67% and an F1 score of 0.81.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• Journal of Animal Science and Technology
• /
• v.66 no.4
• /
• pp.846-858
• /
• 2024

In a duck cage, ducks are placed in various states. In particular, if a duck is overturned and falls or dies, it will adversely affect the growing environment. In order to prevent the foregoing, it was necessary to continuously manage the cage for duck growth. This study proposes a method using an object detection algorithm to improve the foregoing. Object detection refers to the work to perform classification and localization of all objects present in the image when an input image is given. To use an object detection algorithm in a duck cage, data to be used for learning should be made and the data should be augmented to secure enough data to learn from. In addition, the time required for object detection and the accuracy of object detection are important. The study collected, processed, and augmented image data for a total of two years in 2021 and 2022 from the duck cage. Based on the objects that must be detected, the data collected as such were divided at a ratio of 9 : 1, and learning and verification were performed. The final results were visually confirmed using images different from the images used for learning. The proposed method is expected to be used for minimizing human resources in the growing process in duck cages and making the duck cages into smart farms.