• 스마트미디어저널
• /
• 제7권4호
• /
• pp.79-89
• /
• 2018

In recent years, falls among elderly people have gained serious attention as a major cause of injuries. Falls often lead to fatal consequences due to lack of prompt response and rescue. Therefore, a more accurate fall detection system and an effective feature extraction technique are required to prevent and reduce the risk of such incidents. In this paper, we proposed an efficient feature extraction technique based on multiple sliding windows and validated it through a series of experiments using supervised learning algorithms. The experiments were conducted using the public datasets obtained from tri-axial accelerometers. The results depicted that extraction of the feature from adjacent sliding windows led to high accuracy in supervised machine learning-based fall detection. Also, the experiments conducted in this study suggested that the best accuracy can be achieved by keeping the window size as small as 2 seconds. With the kNN classifier and dataset from wearable sensors, the experiments achieved accuracy rates of 94%.

• 스마트미디어저널
• /
• 제10권3호
• /
• pp.9-22
• /
• 2021

Basically, machine learning models use input data to produce results. Sometimes, the input data is too complicated for the models to learn useful patterns. Therefore, feature engineering is a crucial data preprocessing step for constructing a proper feature set to improve the performance of such models. One of the most efficient methods for automating feature engineering is the autoencoder, which transforms the data from its original space into a latent space. However certain factors, including the datasets, the machine learning models, and the number of dimensions of the latent space (denoted by k), should be carefully considered when using the autoencoder. In this study, we design a framework to compare two data preprocessing approaches: with and without autoencoder and to observe the impact of these factors on autoencoder. We then conduct experiments using autoencoders with classifiers on popular datasets. The empirical results provide a perspective regarding the best suited autoencoder for these factors.

• International Journal of Advanced Culture Technology
• /
• 제10권2호
• /
• pp.98-105
• /
• 2022

This study's purpose is to suggest a pedagogical method based on using animated movie in liberal arts English classes and to examine the direction that using animated movie as learning material should take. To this end, in this study, the content understanding and expression concentration stages using animated movie are presented. After students learned in class through animated movie, two tests were conducted to investigate the change in learners' acquisition of English expressions. As a result, subjects' learning of English expressions showed a significant improvement over time. An open-ended questionnaire was also conducted to ascertain learners' satisfaction level and their perceptions of classes using animated movie, with learners' satisfaction found to be high overall (77.1%). Students identified the reasons for their high satisfaction rate as the following: "fun and a touching story", "beneficial composition of textbooks", "efficient teaching methods", "sympathetic topics", and "appropriate difficulty". When using video media in class, instructors should maximize and leverage the advantages of video media, which are rich both in context and in their linguistic aspects.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1049-1058
• /
• 2022

HAR(Human Action Recognition) such as anomaly and object detection has become a trend in research field(s) that focus on utilizing Artificial Intelligence (AI) methods to analyze patterns of human action in crime-ridden area(s), media services, and industrial facilities. Especially, in real-time system(s) using video streaming data, HAR has become a more important AI-based research field in application development and many different research fields using HAR have currently been developed and improved. In this paper, we propose and analyze a deep-learning-based HAR that provides more efficient scheme(s) using an intelligent AI models, such system can be applied to media services using RGB video streaming data usage without feature extraction pre-processing. For the method, we adopt Slowfast based on the Deep Neural Network(DNN) model under an open dataset(HMDB-51 or UCF101) for improvement in prediction accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.305-318
• /
• 2022

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.

• 스마트미디어저널
• /
• 제12권10호
• /
• pp.9-18
• /
• 2023

Harvest forecasting is the great demand of multiple aspects like temperature, rain, environment, and their relations. The existing study investigates the climate conditions and aids the cultivators to know the harvest yields before planting in farms. The proposed study uses federated learning. In addition, the additional widespread techniques such as bagging classifier, extra tees classifier, linear discriminant analysis classifier, quadratic discriminant analysis classifier, stochastic gradient boosting classifier, blending models, random forest regressor, and AdaBoost are utilized together. These presented nine algorithms achieved exemplary satisfactory accuracies. The powerful contributions of proposed algorithms can create exact harvest forecasting. Ultimately, we intend to compare our study with the earlier research's results.

• 한국멀티미디어학회논문지
• /
• 제19권5호
• /
• pp.932-938
• /
• 2016

Recently, interactive media which maximizes audience engagement by making the audience appeal on a stage in digital media environment has been distributed more widely. In fact, there has been active movement to develop and promote a new participatory media genre with higher immersion by applying this kind of interactive media concept to advertisement, film, game and e-learning. In the conventional interactive media, digital media had to be enjoyed in particular environment where diverse sensors were installed or through a certain device to recognize a user's motion and voice. This study attempted to design and implement an image creation system which ensures interactions between a user and media in popular distribution-enabled web environment and through PC and smart devices to minimize the image producer-user constraints.

• 한국항행학회논문지
• /
• 제24권3호
• /
• pp.238-244
• /
• 2020

스마트 시대를 살아가는 요즘 스마트폰을 전 국민이 사용하는 상황으로 봐도 무방할 정도로 빠른 발전과 보급이 진행되었으며, 스마트폰 사용으로 국내 미디어 콘텐츠 이용을 위한 필수 매체로 자리 잡아 성별, 연령, 지역 등에 상관없이 수많은 사람이 다양한 콘텐츠를 이용하고 있다. 최근 다양한 매체를 통해 온라인에서 학습을 위한 동영상 콘텐츠 소비가 이루어지고 있으며, 이는 학습자들이 온라인에서 동영상 콘텐츠를 활용하여 학습에 활용한다는 것을 알 수 있다. 기존 연구에서는 콘텐츠 유형에 따른 만족도 연구를 진행하였으며, 학습 콘텐츠 자체를 평가하여 학습자들에게 제공하는 방법에 대한 연구가 이루어 지지 않아 개선 방안이 필요하다고 판단하였다. 본 논문에서는 학습을 위한 동영상 콘텐츠 제공 방식 동향과 양질의 학습 콘텐츠를 제공하기 위한 개선 방안으로 학습 콘텐츠 자체의 평가와 리뷰를 통해 시스템을 제안하려고 한다.

• 스마트미디어저널
• /
• 제10권1호
• /
• pp.25-31
• /
• 2021

기계학습이 보편화되면서 기계학습을 활용한 응용 개발 또한 활발하게 이루어지고 있다. 또한 이러한 응용 개발을 지원하기 위한 기계학습 플랫폼 연구도 활발하게 진행되고 있다. 그러나 기계학습 플랫폼 연구가 활발하게 진행되고 있음에도 불구하고 기계학습 플랫폼에 적절한 부하 분산에 관한 연구는 아직 부족하다. 따라서 본 논문에서는 기계학습 분산 환경을 위한 부하 분산 기법을 제안한다. 제안하는 기법은 분산 서버를 레벨 해시 테이블 구조로 구성하고 각 서버의 성능을 고려하여 기계학습 작업을 서버에 할당한다. 이후 분산 서버를 구현하여 실험하고 기존 해싱 기법과 성능을 비교하였다. 제안하는 기법을 기존 해싱 기법과 비교하였을 때 평균 약 26%의 속도 향상을 보였고, 서버에 할당되지 못하고 대기하는 작업의 수가 약 38% 이상 감소함을 보였다.

• 스마트미디어저널
• /
• 제11권11호
• /
• pp.25-31
• /
• 2022

자율주행 자동차에서 딥러닝 기반 영상처리는 매우 중요하다. 자동차를 비롯한 SoC(System on Chip) 환경에서 실시간으로 도로 영상을 처리하기 위해서는 영상처리 모델을 딥러닝 연산에 특화된 NPU(Neural Processing Unit) 상에서 실행해야 한다. 본 연구에서는 GPU 서버 환경에서 개발된 7종의 오픈소스 딥러닝 영상처리 모델들을 TIDL (Texas Instrument Deep Learning) NPU 환경에 이식하였다. 성능 평가와 시각화를 통해 본 연구에서 이식한 모델들이 SoC 가상환경에서 정상 작동함을 확인하였다. 본 논문은 NPU 환경의 제약으로 인해 이식 과정에 발생한 문제들과 그 해결 방법을 소개함으로써 딥러닝 모델을 SoC 환경에 이식하려는 개발자 및 연구자가 참고할 만한 사례를 제시한다.