• Information Systems Review
• /
• v.22 no.1
• /
• pp.113-124
• /
• 2020

In the operation of farms, it is very important to evaluate the quality of harvested crops and to classify defective products. However, farmers have difficulty coping with the cost and time required for quality assessment due to insufficient capital and manpower. This study thus aims to detect defects by analyzing the epidermis of fruit using deep learning algorithm. We developed a model that can analyze the epidermis by applying YOLOv3 algorithm based on Region Convolutional Neural Network to video images of peach. A total of four classes were selected and trained. Through 97,600 epochs, a high performance detection model was obtained. The crop failure detection model proposed in this study can be used to automate the process of data collection, quality evaluation through analyzed data, and defect detection. In particular, we have developed an analytical model for peach, which is the most vulnerable to external wounds among crops, so it is expected to be applicable to other crops in farming.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.465-470
• /
• 2024

The advancement of AI-based image generation technology has resulted in the creation of various images, emphasizing the need for technology capable of accurately discerning them. The amount of generated image data is limited, and to achieve high performance with a limited dataset, this study proposes a model for discriminating generated images using transfer learning. Applying pre-trained models from the ImageNet dataset directly to the CIFAKE input dataset, we reduce training time cost followed by adding three hidden layers and one output layer to fine-tune the model. The modeling results revealed an improvement in the performance of the model when adjusting the final layer. Using transfer learning and then adjusting layers close to the output layer, small image data-related accuracy issues can be reduced and generated images can be classified.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.517-524
• /
• 2024

Generative AI, exemplified by models like ChatGPT, has revolutionized human-machine interactions in the 21st century. As these advancements permeate various sectors, their intersection with the arts is both promising and challenging. Despite the arts' historical resistance to AI replacement, recent developments have sparked active research in AI's role in artistry. This study delves into the potential of AI in visual arts education, highlighting the necessity of swift adaptation amidst the Fourth Industrial Revolution. This research, conducted at a 4-year global higher education institution located in Gyeongbuk, involved 70 participants who took part in a creative convergence module course project. The study aimed to examine the influence of AI collaboration in visual arts, analyzing distinctions across majors, grades, and genders. The results indicate that creative activities with AI positively influence students' creativity and digital media literacy. Based on these findings, there is a need to further develop effective educational strategies and directions that incorporate AI.

• Journal of Platform Technology
• /
• v.12 no.2
• /
• pp.12-22
• /
• 2024

With the rapid increase in digital data in modern society, digital forensics plays a crucial role, and file type identification is one of its integral components. Research on the development of identification models utilizing artificial intelligence is underway to identify file types swiftly and accurately. However, existing studies do not support the identification of file types with high domestic usage rates, making them unsuitable for use within the country. Therefore, this paper proposes a more accurate file type identification model using Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). To overcome limitations of existing methods, the proposed model demonstrates superior performance on the FFT-75 dataset, effectively identifying file types with high domestic usage rates such as HWP, ALZ, and EGG. The model's performance is validated by comparing it with three existing research models (CNN-CO, FiFTy, CNN-LSTM). Ultimately, the CNN and GRU based file type identification and classification model achieved 68.2% accuracy on 512-byte file fragments and 81.4% accuracy on 4096-byte file fragments.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.751-757
• /
• 2024

This study evaluates the effectiveness of advertising copywriting using the artificial intelligence language model, ChatGPT, and explores its potential applications and limitations within the advertising industry. We established five key research questions and conducted in-depth focus group interviews (FGI) with university students in Busan. The findings reveal that there was no significant preference difference between copies written by ChatGPT and human copywriters. However, ChatGPT's copies were particularly effective in age-targeted advertising but showed limitations in gender targeting and reflecting cultural contexts. Additionally, consumer acceptance of AI copywriting was generally positive, though concerns were raised about the creativity and naturalness of AI-generated copies. This research provides practical insights into how AI can be utilized in advertising content creation and stimulates discussion on the appropriate use of AI technology and ethical considerations within the industry. These results offer important implications for both advertising professionals and the academic community.

• Smart Media Journal
• /
• v.11 no.10
• /
• pp.89-96
• /
• 2022

An open domain machine reading comprehension is a model that adds a function to search paragraphs as there are no paragraphs related to a given question. Document searches have an issue of lower performance with a lot of documents despite abundant research with word frequency based TF-IDF. Paragraph selections also have an issue of not extracting paragraph contexts, including sentence characteristics accurately despite a lot of research with word-based embedding. Document reading comprehension has an issue of slow learning due to the growing number of parameters despite a lot of research on BERT. Trying to solve these three issues, this study used BM25 which considered even sentence length and InferSent to get sentence contexts, and proposed an open domain machine reading comprehension with ALBERT to reduce the number of parameters. An experiment was conducted with SQuAD1.1 datasets. BM25 recorded a higher performance of document research than TF-IDF by 3.2%. InferSent showed a higher performance in paragraph selection than Transformer by 0.9%. Finally, as the number of paragraphs increased in document comprehension, ALBERT was 0.4% higher in EM and 0.2% higher in F1.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.122-129
• /
• 2022

In this paper, we propose a method to improve the performance of Transformer-based speech recognizers using data augmentation that locally adjusts the frame rate. First, the start time and length of the part to be augmented in the original voice data are randomly selected. Then, the frame rate of the selected part is changed to a new frame rate by using linear interpolation. Experimental results using the Wall Street Journal and LibriSpeech speech databases showed that the convergence time took longer than the baseline, but the recognition accuracy was improved in most cases. In order to further improve the performance, various parameters such as the length and the speed of the selected parts were optimized. The proposed method was shown to achieve relative performance improvement of 11.8 % and 14.9 % compared with the baseline in the Wall Street Journal and LibriSpeech speech databases, respectively.

• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.

• Journal of the Korean Society of Radiology
• /
• v.14 no.2
• /
• pp.121-127
• /
• 2020

The era of the Fourth Industrial Revolution is increasingly demanding mathematical competencies for virtual reality (VR), artificial intelligence (AI) and the like. In this context, this study intended to identify the basic mathematical competency levels of university freshman students in radiology department and to provide basic data thereon. For this, the diagnostic assessment of basic learning competencies for the domain of mathematics was conducted from June 17, 2019 to June 28, 2019 among 78 freshman students of radiology department at S university and D university. As a result, the university students' overall basic mathematical competency levels were diagnosed to be excellent. However, their levels in the sectors of the geometry and vector and the probability and statistics were diagnosed to be moderate, with the mean scores of 2.61 points and 2.64 points, respectively, which were found to be lower than those of the other sections. As for basic mathematical competency levels according to genders, the levels of male students and female students were diagnosed to be excellent, with the mean scores of 17.48 points and 16.29 points, respectively, showing no statistically significant difference (p>0.05). Given the small number of subjects and regional restriction, there might be some limitations in the generalization of the findings of the present study to all university freshman students and all departments. The above results suggest that it is necessary to implement various programs such as student level-based special lectures for enhancing basic mathematical competencies relating to major in order to improve the basic mathematical competencies of freshman students in radiology department, and that it is necessary to increase the students' mathematical competencies by offering major math courses in the curriculum and applying teaching-learning methods matching students' levels.

• The Journal of the Korea Contents Association
• /
• v.19 no.6
• /
• pp.47-57
• /
• 2019

The purpose of this study is to explore how college students aware of the 4th industrial revolution and prepare to adjust it. The subjects of the study were 317 college students in Busan city and analyzed by gender, major and grades. Results are as follows. First, students who are male, higher grade and major in engineering area showed greater recognition compared to students who are female, lower grade and studying other areas for the new era. Also for big changes of the era most students agreed with convenience of life but decrease of job opportunities. Second, most students showed nothing special work yet but students in engineering area make an effort to foster their competence. Third, most students had lower, below average level of competence that are required in the new era. Fourth, the difficulties students encounter are lack of educational opportunities and financial problem. Male students responded lack of time and laboratory work and female students are lack of concerns. The study suggests that colleges should provide various method such as regular and irregular and extra curriculum to enhance students creativity and competence for the new era.