• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.53-60
• /
• 2022

YouTube realistically shows fake news and biased content based on facts that have not been verified due to low entry barriers and ambiguity in video regulation standards. Therefore, this study aims to analyze the influence of the media and YouTube on individual behavior and their relationship. Data from YouTube and Twitter are randomly imported with selenium, beautiful soup, and Twitter APIs to classify the 31 most frequently mentioned keywords. Based on 31 keywords classified, data were collected from YouTube, Twitter, and Naver News, and positive, negative, and neutral emotions were classified and quantified with NLTK's Natural Language Toolkit (NLTK) Vader model and used as analysis data. As a result of analyzing the correlation of data, it was confirmed that the higher the negative value of news, the more positive content on YouTube, and the positive index of YouTube content is proportional to the positive and negative values on Twitter. As a result of this study, YouTube is not consistent with the emotion index shown in the news due to its secondary processing and affected characteristics. In other words, processed YouTube content intuitively affects Twitter's positive and negative figures, which are channels of communication. The results of this study analyzed that YouTube plays a role in assisting individual discrimination in the current situation where accurate judgment of information has become difficult due to the emergence of yellow media that stimulates people's interests and instincts.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.4
• /
• pp.148-163
• /
• 2021

The diversification of the New Deal urban regeneration projects, that started in 2017 in accordance with the "Special Act on Urban Regeneration Activation and Support", generated the increased demand for the accuracy of data-driven diagnosis and project type forecast. Thus, this research was conducted to develop an application model able to identify the most appropriate New Deal project type for "eup", "myeon" and "dong" across the country. Data for application model development were collected through Statistical geographic information service(SGIS) and the 'Urban Regeneration Comprehensive Information Open System' of the Urban Regeneration Information System, and data for the analysis model was constructed through data pre-processing. Four models were derived and simulations were performed through polynomial regression analysis and multinomial logistic regression analysis for the application of the appropriate New Deal project type. I verified the applicability and validity of the four models by the comparative analysis of spatial distribution of the previously selected New Deal projects by targeting the sites located in Seoul by each model and the result showed that the DI-54 model had the highest concordance rate.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.6
• /
• pp.71-80
• /
• 2021

This study is aimed at analyzing the characteristics of each service quality and the requirements of the customers followed by the classification of service quality factors of youth sports clubs by using Kano model. For this purpose, a survey was conducted by targeting on 257 subjects in 10 youth sports clubs in Seoul and Gyeonggi areas and for data processing, Microsoft Office Excel 2016 and SPSS 22.0 were used to carry out Frequency Analysis, Factor Analysis, Reliability Analysis, Kano model Quality Classification, Timko's Customer Satisfaction Coefficient, and the computation and analysis of Public-service Customer Satisfaction Index. The following shows the research findings. First, as a result of using Kano model to classify each item of the service quality factors of the youth sports club through Dualistic Quality Theory Attribution, one-dimensional quality elements resulted in all 22 items of service quality factors of youth sports club. Second, the customer satisfaction coefficient computation result showed that satisfaction coefficient appeared by the order of 'kind response of the instructor,'(0.81), 'attitude of the instructor'(0.80), 'systematic lecture program'(0.76), and 'variety of program)'(0.76) and dissatisfaction coefficient appeared by the order of 'clean and pleasant facility'(-0.79), 'attitude of the instructor'(-0.76), 'kind response of the instructor'(-0.76), 'convenience of parking facility'(-0.73), and 'promptness of business process'(-0.73). Third, the public-service customer satisfaction index placing appeared by the order of the 'attitude of the instructor', 'kind response of the instructor', 'clean and pleasant facility' and 'systematic lecture program'.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.729-735
• /
• 2021

Recently Artificial Intelligence(AI) has been developed and used in various fields. Especially AI recognition technology can perceive and distinguish images so it should plays a significant role in quality inspection process. For stability of autonomous driving technology, semiconductors inside automobiles must be protected from external electromagnetic wave(EM wave). As a shield film, a thin polymeric material with hole shaped micro-patterns created by a laser processing could be used for the protection. The shielding efficiency of the film can be increased by the hole structure with appropriate pitch and size. However, since the sensitivity of micro-machining for some parameters, the shape of every single hole can not be same, even it is possible to make defective patterns during process. And it is absolutely time consuming way to inspect all patterns by just using optical microscope. In this paper, we introduce a AI inspection system which is based on web site AI tool. And we evaluate the usefulness of AI model by calculate Area Under ROC curve(Receiver Operating Characteristics). The AI system can classify the micro-patterns into normal or abnormal ones displaying the text of the result on real-time images and save them as image files respectively. Furthermore, pressing the running button, the Hardware of robot arm with two Arduino motors move the film on the optical microscopy stage in order for raster scanning. So this AI system can inspect the entire micro-patterns of a film automatically. If our system could collect much more identified data, it is believed that this system should be a more precise and accurate process for the efficiency of the AI inspection. Also this one could be applied to image-based inspection process of other products.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.35-43
• /
• 2021

Recently, there has been a growing interest in zero-shot cross-lingual transfer, which leverages cross-lingual language models (CLLMs) to perform downstream tasks that are not trained in a specific language. In this paper, we point out the limitations of the data-centric aspect of quality estimation (QE), and perform zero-shot cross-lingual transfer even in environments where it is difficult to construct QE data. Few studies have dealt with zero-shots in QE, and after fine-tuning the English-German QE dataset, we perform zero-shot transfer leveraging CLLMs. We conduct comparative analysis between various CLLMs. We also perform zero-shot transfer on language pairs with different sized resources and analyze results based on the linguistic characteristics of each language. Experimental results showed the highest performance in multilingual BART and multillingual BERT, and we induced QE to be performed even when QE learning for a specific language pair was not performed at all.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.77-89
• /
• 2022

It has been proven through many previous researches that the pretrained language model with a large corpus helps improve performance in various natural language processing tasks. However, there is a limit to building a large-capacity corpus for training in a language environment where resources are scarce. Using the Cross-lingual Post-Training (XPT) method, we analyze the method's efficiency in Korean, which is a low resource language. XPT selectively reuses the English pretrained language model parameters, which is a high resource and uses an adaptation layer to learn the relationship between the two languages. This confirmed that only a small amount of the target language dataset in the relationship extraction shows better performance than the target pretrained language model. In addition, we analyze the characteristics of each model on the Korean language model and the Korean multilingual model disclosed by domestic and foreign researchers and companies.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.3
• /
• pp.79-88
• /
• 2022

Cable-supported bridges, as important large infrastructures, require a long-term and systematic maintenance strategy. In particular, various methods have been proposed to secure safety for the bridges, such as installing various types of sensor on members in the bridges, and setting management thresholds. It is evidently necessary to propose a strategic plan to efficiently manage increasing number of cable-supported bridges and data collected from a number of sensors. This study aims to develop an analysis tool that can automatically remove abnormal signals and calculate statistical results for the purpose of efficiently analyzing a wide range of data collected from a long span bridge measurement system. To develop the tool, basic information such as the types and quantity of sensors installed in long span bridges and signal characteristics of the collected data were analyzed. Thereafter, the Humpel filtering method was used to determine the presence or absence of an abnormality in the signal and then filtered. The statistical results with filtered data were shown. Finally, one cable-stayed bridge and one suspension bridge currently in use were chosen as the target bridges to verify the performance of the developed tool. Signal processing and statistical analysis with the tool were performed. The results are similar to the results reported in the existing work.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.331-338
• /
• 2022

Successor representation (SR) is a model of human reinforcement learning (RL) mimicking the underlying mechanism of hippocampal cells constructing cognitive maps. SR utilizes these learned features to adaptively respond to the frequent reward changes. In this paper, we evaluated the performance of SR under the context where changes in latent variables of environments trigger the reward structure changes. For a benchmark test, we adopted SR-Dyna, an integration of SR into goal-driven Dyna RL algorithm in the 2-stage Markov Decision Task (MDT) in which we can intentionally manipulate the latent variables - state transition uncertainty and goal-condition. To precisely investigate the characteristics of SR, we conducted the experiments while controlling each latent variable that affects the changes in reward structure. Evaluation results showed that SR-Dyna could learn to respond to the reward changes in relation to the changes in latent variables, but could not learn rapidly in that situation. This brings about the necessity to build more robust RL models that can rapidly learn to respond to the frequent changes in the environment in which latent variables and reward structure change at the same time.

• Journal of Ecology and Environment
• /
• v.46 no.2
• /
• pp.136-143
• /
• 2022

Background: In northern Thailand, the longan flower is the principal nectar source for honey production. Microorganisms play a critical function in the agricultural ecology. The morphological characteristics of fungal species found in longan pollen were studied. Aspergillus spp. were found to be invertase-producing strains and were employed in the longan syrup production process. The purpose of this study was to evaluate the effects of invertase-added longan syrup on the adult honey bee population numbers that were fed by this syrup for 16 weeks. Results: Different fungal species were found in longan pollen samples. Aspergillus was the main genus, with three predominant sections: Nigri, Flavi, and Terrei. Other isolated species were Trichoderma spp., Rhizopus spp., Neurospora spp., Chaetomium spp., Fusarium spp. and Penicillium spp. However, Aspergillus spp. is the only fungal species that produces the enzyme invertase. The invertase-producing strains belonging to the Aspergillus section Nigri were found to be A. niger LP5 with an optimum activity at pH 6.0 and 60℃. When A. niger LP5 invertase was used for longan syrup processing, the highest levels of glucose (3.45%) and fructose (2.08%) were found in invertase added longan syrup (C), while fresh (A) and boiled longan syrup (B) had lower contents of both sugars. The sucrose content was detected in (A) at 4.25%, while (B) and (C) were at 4.02% and 3.08%, respectively. An appropriate amount of sugar to feed and maintain the honey bee population was considered. The data showed no statistically significant differences between the two selected forms of longan syrup compared to the sugar syrup examined by the adult honey bee population. Conclusions: The main species of isolated fungi from longan pollen were Aspergillus spp. The discovery of an invertase-producing strain of A. niger LP5 has enabled its application for enzyme utilization in the invert sugar preparation process. The adult worker bee populations fed by longan syrup from both boiled and invertase-added sources showed an increasing trend. Artificial syrup made from longan fruit to feed honey bees when natural food sources are limited can be applied.