• Smart Media Journal
• /
• v.12 no.5
• /
• pp.88-101
• /
• 2023

As the definition and role of design changes over time with the times and society, design education needs to update teaching methods to match it. The course design in this study began with an optimisation of the learning model based on previous research and analysis, followed by in-depth interviews, the application of the interview results to the final curriculum design, and finally a questionnaire to verify the positive effects of this teaching model. This teaching model has been applied to teach a pilot class in a university of applied sciences in China. The main characteristics of the course design are Project-Based Learning (PJBL) oriented, team cooperation centric, and an educational model developed based on peer assessment. In every stage of the UI design course, realistic project simulations are adopted, enhancing students' abilities through practical experience, teamwork, and peer assessment. The innovation lies in validating the effectiveness and advantages of this model at every stage of the UI design course, innovating existing teaching methods, optimizing learning models, and combining practice with evaluation. This research found that a project-oriented team course design based on PJBL has a high degree of effectiveness and relevance in each stage of the UI design course, significantly improving students' overall competence. It is expected that the results of this study can be applied in various ways to the course design of the courses that similar to design majors.

• Smart Media Journal
• /
• v.11 no.7
• /
• pp.94-103
• /
• 2022

Weeds bring disadvantages to crops since they can damage them, and a clean treatment with less pollution and contamination should be developed. Artificial intelligence gives new hope to agriculture to achieve smart farming. This study delivers an automated weeds growth point detection using deep learning. This study proposes a combination of semantic graphics for generating data annotation and U-Net with pre-trained deep learning as a backbone for locating the growth point of the weeds on the given field scene. The dataset was collected from an actual field. We measured the intersection over union, f1-score, precision, and recall to evaluate our method. Moreover, Mobilenet V2 was chosen as the backbone and compared with Resnet 34. The results showed that the proposed method was accurate enough to detect the growth point and handle the brightness variation. The best performance was achieved by Mobilenet V2 as a backbone with IoU 96.81%, precision 97.77%, recall 98.97%, and f1-score 97.30%.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.27-35
• /
• 2024

This study deals with a method of combining image generation using Semi Supervised Learning based on GAN (Generative Adversarial Network) and image classification using ResNet50. Through this, a new approach was proposed to obtain more accurate and diverse results by integrating image generation and classification. The generator and discriminator are trained to distinguish generated images from actual images, and image classification is performed using ResNet50. In the experimental results, it was confirmed that the quality of the generated images changes depending on the epoch, and through this, we aim to improve the accuracy of industrial accident prediction. In addition, we would like to present an efficient method to improve the quality of image generation and increase the accuracy of image classification through the combination of GAN and ResNet50.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.45-52
• /
• 2024

In today's growing threat environment, rapid and effective detection and response to security events is essential. To solve these problems, many companies and organizations respond to security threats by introducing security control systems. However, existing security control systems are experiencing difficulties due to the complexity and diverse characteristics of security events. In this study, we propose an automated integrated security control system model based on artificial intelligence. It is based on deep learning, an artificial intelligence technology, and provides effective detection and processing functions for various security events. To this end, the model applies various artificial intelligence algorithms and machine learning methods to overcome the limitations of existing security control systems. The proposed model reduces the operator's workload, ensures efficient operation, and supports rapid response to security threats.

• 중국학논총
• /
• no.63
• /
• pp.121-136
• /
• 2019

Graded reading is to match reading competency of readers with difficulty levels of text, based on the study of readability. This article discusses how to apply new media to develop Chinese graded reading materials which are more interesting, scientific and practical than traditional paper materials. The graded materials on the new media platform can be used for Chinese second language learners to self-study, and also for instructors to support reading and writing instruction in class or after class.

• Information Systems Review
• /
• v.10 no.3
• /
• pp.39-64
• /
• 2008

As digital convergence evolves, it is expected that the market of IP-based services like VoIP and IPTV will be expanded. In particular, IPTV market is expected to attract consumers' attention through various interactive services offering a variety of experiences to consumers. Interactivity sets apart old media from new one in terms of how to mediate effects of user satisfaction. The object of this study is to investigate (1) multi-dimensional Interactivities in an interactive medium based on IP and relationship among them, and (2) significant factors affecting cognitive absorption of interactive media users. This study aims to provide implications on how to develop strategies for IP-based media including e-learning system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.334-342
• /
• 2022

Nowadays, as we can notice on social media, most users choose to use more than one language in their online postings. Thus, social media analytics needs reviewing as code-switching analytics instead of traditional analytics. This paper aims to present evidence comparable to the accuracy of code-switching analytics techniques in analysing the mood state of social media users. We conducted a systematic literature review (SLR) to study the social media analytics that examined the effectiveness of code-switching analytics techniques. One primary question and three sub-questions have been raised for this purpose. The study investigates the computational models used to detect and measures emotional well-being. The study primarily focuses on online postings text, including the extended text analysis, analysing and predicting using past experiences, and classifying the mood upon analysis. We used thirty-two (32) papers for our evidence synthesis and identified four main task classifications that can be used potentially in code-switching analytics. The tasks include determining analytics algorithms, classification techniques, mood classes, and analytics flow. Results showed that CNN-BiLSTM was the machine learning algorithm that affected code-switching analytics accuracy the most with 83.21%. In addition, the analytics accuracy when using the code-mixing emotion corpus could enhance by about 20% compared to when performing with one language. Our meta-analyses showed that code-mixing emotion corpus was effective in improving the mood analytics accuracy level. This SLR result has pointed to two apparent gaps in the research field: i) lack of studies that focus on Malay-English code-mixing analytics and ii) lack of studies investigating various mood classes via the code-mixing approach.

• Journal of Engineering Education Research
• /
• v.15 no.4
• /
• pp.85-93
• /
• 2012

This paper is to explore the effects of Robot Based Instruction(RBI) on the learning attitude of elementary school students. According to this research, researcher found out that there is significant improvement in learning attitude score after RBI was applied. The result of verification on the learning attitude is difference by sex showed that male students' learning attitude score is more high better than another group. In particular, it showed that there is more significant improvement in science art discretionary activities subjects. The above-mentioned results are based on as follows two reasons. First, RBI is efficient to improve students' internal motivation and ownership about tasks, and that is related to environment of learning and instruction focused on authentic task and practice. Second, educational advantages of robot media was reflected appropriately in RBI, also appropriate instructional environment for RBI was supported.

• The Journal of the Korea Contents Association
• /
• v.7 no.4
• /
• pp.192-198
• /
• 2007

Due to the development of information telecommunication technology, e-learning industry is rapidly expanding its scope along with its production technology. The recent trend of e-learning program is likely converted from Wmv(Window Media Video) of Microsoft to Flv(Flash video), which has less capacity but better quality than other image file. It has successfully drawn the users attention since Flv can operate at most OS environments and browsers let alone with window and Lenux without extra players and codec setup. However, there is no accurate data on comparative analysis between Wmv and Flv regarding capacity, quality and production time. Therefore, the study shows the comparative data analysis on Wmv and Flv so as to set out production platform up to its idiosyncrasy.

• Smart Media Journal
• /
• v.5 no.3
• /
• pp.35-41
• /
• 2016

In this paper, we propose hand-gesture signal recognition based on EPS(Electronic Potential Sensor) using Deep learning model. Extracted signals which from Electronic field based sensor, EPS have much of the noise, so it must remove in pre-processing. After the noise are removed with filter using frequency feature, the signals are reconstructed with dimensional transformation to overcome limit which have just one-dimension feature with voltage value for using convolution operation. Then, the reconstructed signal data is finally classified and recognized using multiple learning layers model based on deep learning. Since the statistical model based on probability is sensitive to initial parameters, the result can change after training in modeling phase. Deep learning model can overcome this problem because of several layers in training phase. In experiment, we used two different deep learning structures, Convolutional neural networks and Recurrent Neural Network and compared with statistical model algorithm with four kinds of gestures. The recognition result of method using convolutional neural network is better than other algorithms in EPS gesture signal recognition.