• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.15-31
• /
• 2023

In this study, we propose a novel approach to analyze big data related to patents in the field of smart factories, utilizing the Latent Dirichlet Allocation (LDA) topic modeling method and the generative artificial intelligence technology, ChatGPT. Our method includes extracting valuable insights from a large data-set of associated patents using LDA to identify latent topics and their corresponding patent documents. Additionally, we validate the suitability of the topics generated using generative AI technology and review the results with domain experts. We also employ the powerful big data analysis tool, KNIME, to preprocess and visualize the patent data, facilitating a better understanding of the global patent landscape and enabling a comparative analysis with the domestic patent environment. In order to explore quantitative and qualitative comparative advantages at this juncture, we have selected six indicators for conducting a quantitative analysis. Consequently, our approach allows us to explore the distinctive characteristics and investment directions of individual countries in the context of research and development and commercialization, based on a global-scale patent analysis in the field of smart factories. We anticipate that our findings, based on the analysis of global patent data in the field of smart factories, will serve as vital guidance for determining individual countries' directions in research and development investment. Furthermore, we propose a novel utilization of GhatGPT as a tool for validating the suitability of selected topics for policy makers who must choose topics across various scientific and technological domains.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.18-26
• /
• 2023

The building energy management system (BEMS), a system designed to efficiently manage energy production and consumption, aims to address the variable nature of power consumption within buildings due to their physical characteristics, necessitating stable power supply. In this context, accurate prediction of building energy consumption becomes crucial for ensuring reliable power delivery. Recent research has explored various approaches, including time series analysis, statistical analysis, and artificial intelligence, to predict power consumption. This paper analyzes the strengths and weaknesses of the Prophet model, choosing to utilize its advantages such as growth, seasonality, and holiday patterns, while also addressing its limitations related to data complexity and external variables like climatic data. To overcome these challenges, the paper proposes an algorithm that combines the Prophet model's strengths with the gated recurrent unit (GRU) to forecast short-term (2 days) and medium-term (7 days, 15 days, 30 days) building energy consumption. Experimental results demonstrate the superior performance of the proposed approach compared to conventional GRU and Prophet models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.93-98
• /
• 2024

With the rapid advance in AI (artificial intelligence) and high-performance computing technologies, deep learning is being used in various fields. Deep learning proceeds training by randomly reading a large amount of data and repeats this process. A large number of files are randomly repeatedly referenced during deep learning, which shows different access characteristics from traditional workloads with temporal locality. In order to cope with the difficulty in caching caused by deep learning, we propose a new sampling method that aims at reducing the randomness of dataset reading and adaptively operating on existing buffer cache algorithms. We show that the proposed policy reduces the miss rate of the buffer cache by 16% on average and up to 33% compared to the existing method, and improves the execution time by up to 24%.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.4
• /
• pp.420-426
• /
• 2024

This study proposes an innovative methodology for developing flexible printed circuit boards (FPCBs) capable of conforming to three-dimensional shapes, meeting the increasing demand for electronic circuits in diverse and complex product designs. By integrating a traditional flat plate-based fabrication process with a subsequent three-dimensional thermal deformation technique, we have successfully demonstrated an FPCB that maintains stable electrical characteristics despite significant shape deformations. Using a modified polyimide substrate along with Ag flake-based conductive ink, we identified optimized process variables that enable substrate thermal deformation at lower temperatures (~130℃) and enhance the stretchability of the conductive ink (ε ~30%). The application of this novel FPCB in a prototype 3D-shaped sensor device, incorporating photosensors and temperature sensors, illustrates its potential for creating multifunctional, shape-adaptable electronic devices. The sensor can detect external light sources and measure ambient temperature, demonstrating stable operation even after transitioning from a planar to a three-dimensional configuration. This research lays the foundation for next-generation FPCBs that can be seamlessly integrated into various products, ushering in a new era of electronic device design and functionality.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.232-237
• /
• 2024

In this paper, a broadband double dipole quasi-Yagi antenna using a 4×2 meander line array structure for maintaining 8 dBi gain was studied. The 4×2 meanderline array structure consists of a unit cell in the shape of a meanderline conductor, and it was placed above the second dipole antenna of the double dipole quasi-Yagi antenna. A double dipole quasi-Yagi antenna with generally used multiple strip directors was designed on an FR4 substrate with the same size, and the input reflection coefficient and gain characteristics were compared. Comparison results showed that the impedance frequency bandwidth increased by 6.3% compared to when using the multiple strip directors, the frequency bandwidth with a gain of 8 dBi or more increased by 10.1%, and average gain also slightly increased. The frequency band of the fabricated antenna for a voltage standing wave ratio less than 2 was 1.548-2.846 GHz(59.1%), and gain was measured to be more than 8 dBi in the 1.6-2.8 GHz band.

• Journal of Information Technology Services
• /
• v.23 no.3
• /
• pp.103-118
• /
• 2024

Due to the advancement of virtual reality technology, virtual idols are widely used in industrial and cultural content industries. However, it is difficult to utilize virtual idols' social perceptions because they are not properly understood. Therefore, this paper collected and analyzed YouTube comments to identify differences about social perception through comparative analysis between virtual idols and general idols. The dataset was constructed by crawling comments from music videos with more than 10 million views of virtual idols and more than 10,000 comments. Keyword frequency and TF-IDF values were derived from the collected dataset, and the connection centrality CONCOR cluster was analyzed with a semantic network using the UCINET program. As a result of the analysis, it was found that virtual idols frequently used keywords such as "person," "quality," "character," "reality," "animation," while reactions and perceptions were derived from general idols. Based on the results of this analysis, it was found that while general idols are mainly evaluated with their appearance and cultural factors, social perceptions of virtual idols' values are mixed with evaluations of cultural factors such as "song," "voice," and "choreography," focusing on technical factors such as "people," "quality," "character," and "animation." However, keywords such as "song," "voice," "choreography," and "music" are included in the top 30 like regular idols and appear in the same cluster, suggesting that virtual idols are gradually shifting away from minority tastes to mainstream culture. This study aims to provide academic and practical implications for the future expansion of the industry and cultural content industry of virtual idols by grasping the social perception of virtual idols.

• Dementia and Neurocognitive Disorders
• /
• v.23 no.3
• /
• pp.146-160
• /
• 2024

Background and Purpose: The emotions of people at various stages of dementia need to be effectively utilized for prevention, early intervention, and care planning. With technology available for understanding and addressing the emotional needs of people, this study aims to develop speech emotion recognition (SER) technology to classify emotions for people at high risk of dementia. Methods: Speech samples from people at high risk of dementia were categorized into distinct emotions via human auditory assessment, the outcomes of which were annotated for guided deep-learning method. The architecture incorporated convolutional neural network, long short-term memory, attention layers, and Wav2Vec2, a novel feature extractor to develop automated speech-emotion recognition. Results: Twenty-seven kinds of Emotions were found in the speech of the participants. These emotions were grouped into 6 detailed emotions: happiness, interest, sadness, frustration, anger, and neutrality, and further into 3 basic emotions: positive, negative, and neutral. To improve algorithmic performance, multiple learning approaches were applied using different data sources-voice and text-and varying the number of emotions. Ultimately, a 2-stage algorithm-initial text-based classification followed by voice-based analysis-achieved the highest accuracy, reaching 70%. Conclusions: The diverse emotions identified in this study were attributed to the characteristics of the participants and the method of data collection. The speech of people at high risk of dementia to companion robots also explains the relatively low performance of the SER algorithm. Accordingly, this study suggests the systematic and comprehensive construction of a dataset from people with dementia.

• Journal of Animal Science and Technology
• /
• v.47 no.6
• /
• pp.925-936
• /
• 2005

The present study evaluated whether pentoxifylline added to the freezing extender could improve the sperm characteristics and function in canine frozen semen. Also the conception rate following AI with frozen-thawed semen was investigated. The beneficial effects of pentoxifylline supplementation were visible in motility, viability, acrosome reaction, and tail swelling patterns. Especially, highest sperm viability and function were obtained in the forzen semen supplemented with 1mM pentoxifylline. The follicle size measured by ultrasonography was 6.48 mm, 11.52 mm and 8.9 mm on 11, 13 and 15 days after the onset of natural estrus, respectively and ovulation occurred on 13 and 15 days. The pregnancy rates in bitches inseminated with frozen semen on natural and induced estrus were 71.4% and 75.0%, respectively. There was no significant difference between the pregnancy rates in bitches inseminated with frozen semen following natural and induced estrus, but the litter size was slightly increased in natural cycle.

• Korean Journal of Weed Science
• /
• v.14 no.3
• /
• pp.199-211
• /
• 1994

Butachlor applied pre-emergence at 3.6kg ai/ha inhibited the growth and developments of shoot of barnyardgrass under dry condition, whereas rice was unaffected. Growth of rice and barnyardgrass under water condition was severely inhibited by treatment of butachlor but that of transplanted rice was not affected. The inhibition rate was higher under water condition, in broadcast rice and direct seeded rice than under dry condition, drilled rice and transplanted rice, respectively. The major anatomical response of stem of barnyardgrass seedling to butachlor under dry condition were partial reduction in thickness and collapse of leaf sheath, while not in rice. Broadcast rice on soil under water condition appeared reduction and constriction of leaf primordia thickness, and barnyardgrass formed tubular-like leaves and showed inhibited elongation of apical meristem. On the other hand, transplanted rice did not show these responses.

• Journal of Korea Water Resources Association
• /
• v.56 no.5
• /
• pp.311-323
• /
• 2023

In order to reduce disaster damage by localized heavy rains, floods, and urban inundation, it is important to know in advance whether natural disasters occur. Currently, heavy rain watch and heavy rain warning by the criteria of the Korea Meteorological Administration are being issued in Korea. However, since this one criterion is applied to the whole country, we can not clearly recognize heavy rain damage for a specific region in advance. Therefore, in this paper, we tried to reset the current criteria for a special weather report which considers the regional characteristics and to predict the damage caused by rainfall after 1 hour. The study area was selected as Gyeonggi-province, where has more frequent heavy rain damage than other regions. Then, the rainfall inducing disaster or hazard-triggering rainfall was set by utilizing hourly rainfall and heavy rain damage data, considering the local characteristics. The heavy rain damage prediction model was developed by a decision tree model and a random forest model, which are machine learning technique and by rainfall inducing disaster and rainfall data. In addition, long short-term memory and deep neural network models were used for predicting rainfall after 1 hour. The predicted rainfall by a developed prediction model was applied to the trained classification model and we predicted whether the rain damage after 1 hour will be occurred or not and we called this as 1ST-Model. The 1ST-Model can be used for preventing and preparing heavy rain disaster and it is judged to be of great contribution in reducing damage caused by heavy rain.