• Smart Media Journal
• /
• v.12 no.9
• /
• pp.89-94
• /
• 2023

Recommender systems provide users with the most favorable items by analyzing explicit or implicit feedback of users on items. Recently, as the size of deep-learning-based models employed in recommender systems has increased, many studies have focused on reducing inference time while maintaining high recommendation accuracy. As one of them, a study on recommender systems with a knowledge distillation (KD) technique is actively conducted. By KD, a small-sized model (i.e., student) is trained through knowledge extracted from a large-sized model (i.e., teacher), and then the trained student is used as a recommendation model. Existing studies on KD for recommender systems have been mainly performed only for implicit feedback settings. Thus, in this paper, we try to investigate the performance and accuracy when applied to explicit feedback settings. To this end, we leveraged a total of five state-of-the-art KD methods and three real-world datasets for recommender systems.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.28-37
• /
• 2023

The main factor affecting the decline in rice yield is damage caused by localized heavy rains or typhoons. The method of analyzing the rice lodging area is difficult to obtain objective results based on visual inspection and judgment based on field surveys visiting the affected area. it requires a lot of time and money. In this paper, we propose the method of estimation and diagnosis for rice lodging areas using a Vision Transformer-based Segformer for RGB images, which are captured by unmanned aerial vehicles. The proposed method estimates the lodging, normal, and background area using the Segformer model, and the lodging rate is diagnosed through the rice field inspection criteria in the seed industry Act. The diagnosis result can be used to find the distribution of the rice lodging areas, to show the trend of lodging, and to use the quality management of certified seed in government. The proposed method of rice lodging area estimation shows 98.33% of mean accuracy and 96.79% of mIoU.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.77-85
• /
• 2023

After COVID-19, communication through online platforms has increased, leading to an accumulation of massive amounts of conversational text data. With the growing importance of summarizing this text data to extract meaningful information, there has been active research on deep learning-based abstractive summarization. However, conversational data, compared to structured texts like news articles, often contains missing or transformed information, necessitating consideration from multiple perspectives due to its unique characteristics. In particular, vocabulary omissions and unrelated expressions in the conversation can hinder effective summarization. Therefore, in this study, we restructured by considering the characteristics of Korean conversational data, fine-tuning a pre-trained text summarization model based on KoBART, and improved conversation data summary perfomance through a refining operation to remove redundant elements from the summary. By restructuring the sentences based on the order of utterances and extracting a central speaker, we combined methods to restructure the conversation around them. As a result, there was about a 4 point improvement in the Rouge-1 score. This study has demonstrated the significance of our conversation restructuring approach, which considers the characteristics of dialogue, in enhancing Korean conversation summarization performance.

• Smart Media Journal
• /
• v.13 no.1
• /
• pp.9-17
• /
• 2024

This study aims to develop an integrated agricultural distribution network management system to improve the quality, profit, and decision-making efficiency of agricultural products. We adopt two key techniques: crop maturity detection based on the YOLOX target detection algorithm and market price prediction based on the Prophet model. By training the target detection model, it was possible to accurately identify crops of various maturity stages, thereby optimizing the shipment timing. At the same time, by collecting historical market price data and predicting prices using the Prophet model, we provided reliable price trend information to shipping decision makers. According to the results of the study, it was found that the performance of the model considering the holiday factor was significantly superior to that of the model that did not, proving that the effect of the holiday on the price was strong. The system provides strong tools and decision support to farmers and agricultural distribution managers, helping them make smart decisions during various seasons and holidays. In addition, it is possible to optimize the distribution network of agricultural products and improve the quality and profit of agricultural products.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.23-32
• /
• 2024

Large-scale fires and their consequential damages are becoming increasingly common, but confidence in fire detection systems is waning. Recently, widely-used chemical fire detectors frequently generate lots of false alarms, while video-based deep learning fire detection is hampered by its time-consuming and expensive nature. To tackle these issues, this study proposes a fire detection model utilizing an autoencoder approach. The objective is to minimize false alarms while achieving swift and precise fire detection. The proposed model, employing an autoencoder methodology, can exclusively learn from normal data without the need for fire-related data, thus enhancing its adaptability to diverse environments. By amalgamating data from five distinct sensors, it facilitates rapid and accurate fire detection. Through experiments with various hyperparameter combinations, the proposed model demonstrated that out of 14 scenarios, only one encountered false alarm issues. Experimental results underscore its potential to curtail fire-related losses and bolster the reliability of fire detection systems.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.48-56
• /
• 2024

In the livestock industry, detecting environmental outliers and predicting data are crucial tasks. Outliers in livestock environment data, typically gathered through time-series methods, can signal rapid changes in the environment and potential unexpected epidemics. Prompt detection and response to these outliers are essential to minimize stress in livestock and reduce economic losses for farmers by early detection of epidemic conditions. This study employs two methods to experiment and compare performances in setting thresholds that define outliers in livestock environment data outlier detection. The first method is an outlier detection using Mean Squared Error (MSE), and the second is an outlier detection using a Dynamic Threshold, which analyzes variability against the average value of previous data to identify outliers. The MSE-based method demonstrated a 94.98% accuracy rate, while the Dynamic Threshold method, which uses standard deviation, showed superior performance with 99.66% accuracy.

• Journal of Welding and Joining
• /
• v.32 no.4
• /
• pp.39-45
• /
• 2014

Today, the development of digitized information media and info-communications are bringing many changes. Due to the development of IT thechnology, we can learn wherever, whenever, regardless of time and place. Machine drawing subject is a very important in mechanical engineering course, but it's studyed only basic theory in a short period, average 1~2weeks. So that, students think that the mechanical drawing is of minor importance. Such ideas make them difficult to impove sense of space in isometric drawing and drawing skill. Therefore, in this paper, augmented reality-based contents through the system, Mechanical Drawing of education to meet the effectiveness and satisfaction, student learning can be spontaneously it was construct self-system. And, Theoretical part of the Mechanical Drawing is proposed ensure more efficient and easier training. In this paper, we were test operation for user effectualness of proposed service at Korea Polytechnics Colleges a industrial facilities management in Daegu. Target user are 66 students, and The students were divided into experimental group and comparison group. Experimental results, experimental group was able to do systematically experience many Projection Drawing and Pictorial Drawing in short schooltime. And, The test operation results showed that have the possibility to meet education effectiveness and user satisfaction in this augmented reality-based contents system.

• Korean Journal of Construction Engineering and Management
• /
• v.15 no.1
• /
• pp.20-27
• /
• 2014

Construction safety training has mostly relied on one-way transference of instructors' knowledge to trainees through traditional media such as textbooks and lecture slides. However, safety knowledge could be more effectively acquired in experiential situations. The authors proposed a serious game to provide a comprehensive safety training environment. Trainees who assume the roles of safety inspectors in the game explore a virtual construction site to identify potential hazards and learn from the contents of feedback created by the game as a result of trainees' input. The paper reports details of the game design and development process. The test results indicated that trainees were motivated to refresh their safety knowledge, increased their learning interests, and enjoyed the learning process. In addition, trainees showed positive attitudes towards using the game scoring as a way of evaluating their safety knowledge. The test results encouraged the continuous development of the game.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.78-84
• /
• 2005

The education system that based on objective data is needed for the beginning technologists in the department of radiology, development of the CAI system based on breast images is needed mammography field. So, in this study, we implemented CAI system based on mammography images for medical radiological technologists under Web using multimedia toolbook. This system is implemented under Web, more and more beginning technologists can have a remote-education beyond time and space, can save human power and time that needed due to hold in common of educational information, and cannot team mistaken breast images because of learning execution based on objective data. Also, implemented system brings a higher interest and a learning effect to medical radiological technologies because of hyper-media method that offered from toolbook. In the future, it will be needed a continuous acceptance of changing knowledge and it will be useful system for technologist in case of applying various examinations based mammography method of this study.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.1
• /
• pp.19-28
• /
• 2006

In this paper, we have developed electronic textbooks for social studies centering on contents of a public educational process so that primary schools can use them as a text book. Also, we conducted a survey to find out how teachers perceived electronic textbooks in respect to site accessibility and utility, instructional design, progress of lesson, validity and accuracy of learning content, interface design, and web-based multimedia. In this paper, we presented a new model for electronic textbooks development, which is expected to be useful in developing electronic textbooks as a main text book, unlike other existing models. We applied the navigation utilizing book metaphors to the user interface, on the basis of the results from the analysis of the existing electronic textbooks. In addition, we provided affluent multi-media materials as well as hyperlink, a strong point of on-lines. Experimental results show that the academic achievement was high in knowledge-understanding areas and functional areas in the perspective of academic achievements of the learners.