• Journal of Korea Foundry Society
• /
• v.42 no.6
• /
• pp.369-376
• /
• 2022

The die-casting process is an important process for various industries, but there are limitations in the profitability and productivity of related companies due to the high defect rate. In order to overcome this, this study has developed die-casting fault detection modules based on industrial AI technologies. The developed module is constructed from three-stage models depending on the characteristics of the dataset. The first-stage model conducts fault detection based on supervised learning from the dataset without labels. The second-stage model realizes one-class classification based on semi-supervised learning, where the dataset only has production success labels. The third-stage model corresponds to fault detection based on supervised learning, where the dataset includes a small amount of production failure cases. The developed fault detection module exhibited outstanding performance with roughly 96% accuracy for actual process data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.621-631
• /
• 2023

Adversarial training improves the robustness of deep neural networks for adversarial examples. However, the previous adversarial training method focuses only on the adversarial loss function, ignoring that even a small perturbation of the input layer causes a significant change in the hidden layer features. Consequently, the accuracy of a defended model is reduced for various untrained situations such as clean samples or other attack techniques. Therefore, an architectural perspective is necessary to improve feature representation power to solve this problem. In this paper, we apply an attention module that generates an attention map of an input image to a general model and performs PGD adversarial training upon the augmented model. In our experiments on the CIFAR-10 dataset, the attention augmented model showed higher accuracy than the general model regardless of the network structure. In particular, the robust accuracy of our approach was consistently higher for various attacks such as PGD, FGSM, and BIM and more powerful adversaries. By visualizing the attention map, we further confirmed that the attention module extracts features of the correct class even for adversarial examples.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.155-164
• /
• 2023

Machine learning with its high precision algorithms, Precision agriculture (PA) is a new emerging concept nowadays. Many researchers have worked on the quality and quantity of PA by using sensors, networking, machine learning (ML) techniques, and big data. However, there has been no attempt to work on trends of artificial intelligence (AI) techniques, dataset and crop type on precision agriculture using internet of things (IoT). This research aims to systematically analyze the domains of AI techniques and datasets that have been used in IoT based prediction in the area of PA. A systematic literature review is performed on AI based techniques and datasets for crop management, weather, irrigation, plant, soil and pest prediction. We took the papers on precision agriculture published in the last six years (2013-2019). We considered 42 primary studies related to the research objectives. After critical analysis of the studies, we found that crop management; soil and temperature areas of PA have been commonly used with the help of IoT devices and AI techniques. Moreover, different artificial intelligence techniques like ANN, CNN, SVM, Decision Tree, RF, etc. have been utilized in different fields of Precision agriculture. Image processing with supervised and unsupervised learning practice for prediction and monitoring the PA are also used. In addition, most of the studies are forfaiting sensory dataset to measure different properties of soil, weather, irrigation and crop. To this end, at the end, we provide future directions for researchers and guidelines for practitioners based on the findings of this review.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.44-51
• /
• 2024

The construction of a stress measurement detaset plays a curcial role in various modern applications. In particular, for the efficient training of artificial intelligence models for stress measurement, it is essential to compare various biases and construct a quality-controlled dataset. In this paper, we propose the construction of a stress measurement dataset with quality management through the comparison of various biases. To achieve this, we introduce strss definitions and measurement tools, the process of building an artificial intelligence stress dataset, strategies to overcome biases for quality improvement, and considerations for stress data collection. Specifically, to manage dataset quality, we discuss various biases such as selection bias, measurement bias, causal bias, confirmation bias, and artificial intelligence bias that may arise during stress data collection. Through this paper, we aim to systematically understand considerations for stress data collection and various biases that may occur during the construction of a stress dataset, contributing to the construction of a dataset with guaranteed quality by overcoming these biases.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.1
• /
• pp.99-107
• /
• 2023

Recently, the rate of death and safety accidents at construction sites is the highest among all kinds of industries. In order to apply artificial intelligence technology to construction sites, it is essential to secure a dataset which can be used as a basic training data. In this paper, a number of image data were collected through actual construction site, for which major construction equipment objects mainly operated in civil engineering sites were defined. The optimal training dataset construction was completed by annotation process of about 90,000 image dataset. Reliability of the dataset was verified with the mAP of over 90 % in use of YOLO, a representative model in the field of object detection. The construction equipment training dataset built in this study has been released which is currently available on the public data portal of the Ministry of Public Administration and Security. This dataset is expected to be freely used for any application of object detection technology on construction sites especially in the field of construction safety in the future.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.232-237
• /
• 2020

Given the recent pace of development and expansion of Artificial Intelligence (AI) technology, the influence and ripple effects of AI technology on the whole of our lives will be very large and spread rapidly. The National Artificial Intelligence R&D Strategy, published in 2019, emphasizes the importance of artificial intelligence education for K-12 students. It also mentions STEM education, AI convergence curriculum, and budget for supporting the development of teaching materials and tools. However, it is necessary to create a new type of curriculum at a time when artificial intelligence curriculum has never existed before. With many attempts and discussions going very fast in all countries on almost the same starting line. Also, there is no suitable professor for K-12 students, and it is difficult to make K-12 students understand the concept of AI. In particular, it is difficult to teach elementary school students through professional programming in AI education. It is also difficult to learn tools that can teach AI concepts. In this paper, we propose an educational model for elementary school students to improve their understanding of AI through play or experience. This an experiential education model that combineds exploratory learning and discovery learning using multi-intelligence and the PLAY teaching-learning model to undertand the importance of data training or data required for AI education. This educational model is designed to learn how a computer that knows only binary numbers through UA recognizes images. Through code.org, students were trained to learn AI robots and configured to understand data bias like play. In addition, by learning images directly on a computer through TeachableMachine, a tool capable of supervised learning, to understand the concept of dataset, learning process, and accuracy, and proposed the process of AI inference.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3943-3948
• /
• 2022

Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 × 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.83-88
• /
• 2023

This study investigates the fine-tuning of large-scale Automatic Speech Recognition (ASR) models, specifically OpenAI's Whisper model, for domain-specific applications using the KsponSpeech dataset. The primary research questions address the effectiveness of targeted lexical item emphasis during fine-tuning, its impact on domain-specific performance, and whether the fine-tuned model can maintain generalization capabilities across different languages and environments. Experiments were conducted using two fine-tuning datasets: Set A, a small subset emphasizing specific lexical items, and Set B, consisting of the entire KsponSpeech dataset. Results showed that fine-tuning with targeted lexical items increased recognition accuracy and improved domain-specific performance, with generalization capabilities maintained when fine-tuned with a smaller dataset. For noisier environments, a trade-off between specificity and generalization capabilities was observed. This study highlights the potential of fine-tuning using minimal domain-specific data to achieve satisfactory results, emphasizing the importance of balancing specialization and generalization for ASR models. Future research could explore different fine-tuning strategies and novel technologies such as prompting to further enhance large-scale ASR models' domain-specific performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.167-176
• /
• 2024

Lip-reading is the task of inferring the speaker's utterance from silent video based on learning of lip movements. It is very challenging due to the inherent ambiguities present in the lip movement such as different characters that produce the same lip appearances. Recent advances in deep learning models such as Transformer and Temporal Convolutional Network have led to improve the performance of lip-reading. However, most previous works deal with English lip-reading which has limitations in directly applying to Korean lip-reading, and moreover, there is no a large scale Korean lip-reading dataset. In this paper, we introduce the first large-scale Korean lip-reading dataset with more than 120 k utterances collected from TV broadcasts containing news, documentary and drama. We also present a preprocessing method which uniformly extracts a facial region of interest and propose a transformer-based model based on grapheme unit for sentence-level Korean lip-reading. We demonstrate that our dataset and model are appropriate for Korean lip-reading through statistics of the dataset and experimental results.

• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.11-19
• /
• 2024

This paper was studied abouta technology for detecting damage to temporary works equipment used in construction sites with explainable artificial intelligence (XAI). Temporary works equipment is mostly composed of steel or aluminum, and it is reused several times due to the characters of the materials in temporary works equipment. However, it sometimes causes accidents at construction sites by using low or decreased quality of temporary works equipment because the regulation and restriction of reuse in them is not strict. Currently, safety rules such as related government laws, standards, and regulations for quality control of temporary works equipment have not been established. Additionally, the inspection results were often different according to the inspector's level of training. To overcome these limitations, a method based with AI and image processing technology was developed. In addition, it was devised by applying explainableartificial intelligence (XAI) technology so that the inspector makes more exact decision with resultsin damage detect with image analysis by the XAI which is a developed AI model for analysis of temporary works equipment. In the experiments, temporary works equipment was photographed with a 4k-quality camera, and the learned artificial intelligence model was trained with 610 labelingdata, and the accuracy was tested by analyzing the image recording data of temporary works equipment. As a result, the accuracy of damage detect by the XAI was 95.0% for the training dataset, 92.0% for the validation dataset, and 90.0% for the test dataset. This was shown aboutthe reliability of the performance of the developed artificial intelligence. It was verified for usability of explainable artificial intelligence to detect damage in temporary works equipment by the experiments. However, to improve the level of commercial software, the XAI need to be trained more by real data set and the ability to detect damage has to be kept or increased when the real data set is applied.