• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.80-96
• /
• 2022

Nowadays, artificial intelligence promotes the rapid development of skin cancer detection technology, and the federated skin cancer detection model (FSDM) and dual generative adversarial network model (DGANM) solves the fragmentation and privacy of data to a certain extent. To overcome the problem that the many-objective evolutionary algorithm (MaOEA) cannot guarantee the convergence and diversity of the population when solving the above models, a many-objective evolutionary algorithm based on integrated strategy (MaOEA-IS) is proposed. First, the idea of federated learning is introduced into population mutation, the new parents are generated through sub-populations employs different mating selection operators. Then, the distance between each solution to the ideal point (SID) and the Achievement Scalarizing Function (ASF) value of each solution are considered comprehensively for environment selection, meanwhile, the elimination mechanism is used to carry out the select offspring operation. Eventually, the FSDM and DGANM are solved through MaOEA-IS. The experimental results show that the MaOEA-IS has better convergence and diversity, and it has superior performance in solving the FSDM and DGANM. The proposed MaOEA-IS provides more reasonable solutions scheme for many scholars of skin cancer detection and promotes the progress of intelligent medicine.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.181-188
• /
• 2024

Traditional profanity detection methods have limitations in identifying intentionally altered profanities. This paper introduces a new method based on Named Entity Recognition, a subfield of Natural Language Processing. We developed a profanity detection technique using sequence labeling, for which we constructed a dataset by labeling some profanities in Korean malicious comments and conducted experiments. Additionally, to enhance the model's performance, we augmented the dataset by labeling parts of a Korean hate speech dataset using one of the large language models, ChatGPT, and conducted training. During this process, we confirmed that filtering the dataset created by the large language model by humans alone could improve performance. This suggests that human oversight is still necessary in the dataset augmentation process.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.11-23
• /
• 2024

Triage is a practice of accurately prioritizing patients in emergency department (ED) based on their medical condition to provide them with proper treatment service. The variation in triage assessment among medical staff can cause mis-triage which affect the patients negatively. Developing ED triage system based on machine learning (ML) techniques can lead to accurate and efficient triage outcomes. This study aspires to develop a triage system using machine learning techniques to predict ED triage levels using patients' information. We conducted a retrospective study using Security Forces Hospital ED data, from 2021 through 2023 during Hajj period in Saudia Arabi. Using demographics, vital signs, and chief complaints as predictors, two machine learning models were investigated, naming gradient boosted decision tree (XGB) and deep neural network (DNN). The models were trained to predict ED triage levels and their predictive performance was evaluated using area under the receiver operating characteristic curve (AUC) and confusion matrix. A total of 11,584 ED visits were collected and used in this study. XGB and DNN models exhibit high abilities in the predicting performance with AUC-ROC scores 0.85 and 0.82, respectively. Compared to the traditional approach, our proposed system demonstrated better performance and can be implemented in real-world clinical settings. Utilizing ML applications can power the triage decision-making, clinical care, and resource utilization.

• Journal of Platform Technology
• /
• v.12 no.1
• /
• pp.128-140
• /
• 2024

'Deepfake' refers to a video synthesis technique that utilizes various artificial intelligence technologies to create highly realistic fake content, causing serious confusion to individuals and society by being used for generating fake news, fraud, malicious impersonation, and more. To address this issue, there is a need for methods to detect malicious images generated by deepfake accurately. In this paper, we extract and analyze saliency features from deepfake and real images, and detect candidate synthesis regions on the images, and finally construct an automatic deepfake detection model by focusing on the extracted features. The proposed saliency feature-based model can be universally applied in situations where deepfake detection is required, such as synthesized images and videos. To demonstrate the performance of our approach, we conducted several experiments that have shown the effectiveness of the deepfake detection task.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2333-2345
• /
• 2024

Facial wrinkles are widely used to evaluate skin condition or aging for various fields such as skin diagnosis, plastic surgery consultations, and cosmetic recommendations. In order to effectively process facial wrinkles in facial image analysis, accurate wrinkle segmentation is required to identify wrinkled regions. Existing deep learning-based methods have difficulty segmenting fine wrinkles due to insufficient wrinkle data and the imbalance between wrinkle and non-wrinkle data. Therefore, in this paper, we propose a new facial wrinkle segmentation method based on a UNet++ model. Specifically, we construct a new facial wrinkle dataset by manually annotating fine wrinkles across the entire face. We then extract only the skin region from the facial image using a facial landmark point extractor. Lastly, we train the UNet++ model using both dice loss and focal loss to alleviate the class imbalance problem. To validate the effectiveness of the proposed method, we conduct comprehensive experiments using our facial wrinkle dataset. The experimental results showed that the proposed method was superior to the latest wrinkle segmentation method by 9.77%p and 10.04%p in IoU and F1 score, respectively.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.10
• /
• pp.513-519
• /
• 2024

Advancements in artificial intelligence(AI) have significantly improved deep learning-based audio deepfake technology, which has been exploited for criminal activities. To detect audio deepfake, we propose CoNSIST, an advanced audio deepfake detection model. CoNSIST builds on AASIST, which a graph-based end-to-end model, by integrating three key components: Squeeze and Excitation, Positional Encoding, and Reformulated HS-GAL. These additions aim to enhance feature extraction, eliminate unnecessary operations, and incorporate diverse information. Our experimental results demonstrate that CoNSIST significantly outperforms existing models in detecting audio deepfakes, offering a more robust solution to combat the misuse of this technology.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.11-16
• /
• 2022

As an interest in the development of artificial intelligence(AI) technology in the water supply sector increases, we have developed an AI algorithm that can predict improvement decision-making ratings through repetitive learning using the data of pipe condition evaluation results, and present the most reliable prediction model through a verification process. We have developed the algorithm that can predict pipe ratings by pre-processing 12 indirect evaluation items based on the 2020 Han River Basin's basic plan and applying the AI algorithm to update weighting factors through backpropagation. This method ensured that the concordance rate between the direct evaluation result value and the calculated result value through repetitive learning and verification was more than 90%. As a result of the algorithm accuracy verification process, it was confirmed that all water pipe type data were evenly distributed, and the more learning data, the higher prediction accuracy. If data from all across the country is collected, the reliability of the prediction technique for pipe ratings using AI algorithm will be improved, and therefore, it is expected that the AI algorithm will play a role in supporting decision-making in the objective evaluation of the condition of aging pipes.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.29 no.2
• /
• pp.101-115
• /
• 2024

The ocean heatwave is emerging as a major issue due to global warming, posing a direct threat to marine ecosystems and humanity through decreased food resources and reduced carbon absorption capacity of the oceans. Consequently, the prediction of ocean heatwaves in the vicinity of the Korean Peninsula is becoming increasingly important for marine environmental monitoring and management. In this study, an LSTM model was developed to improve the underestimated prediction of ocean heatwaves caused by the coarse vertical grid system of the Korean Peninsula Ocean Prediction System. Based on the results of ocean heatwave predictions for the Korean Peninsula conducted in 2023, as well as those generated by the LSTM model, the performance of heatwave predictions in the East Sea, Yellow Sea, and South Sea areas surrounding the Korean Peninsula was evaluated. The LSTM model developed in this study significantly improved the prediction performance of sea surface temperatures during periods of temperature increase in all three regions. However, its effectiveness in improving prediction performance during periods of temperature decrease or before temperature rise initiation was limited. This demonstrates the potential of the LSTM model to address the underestimated prediction of ocean heatwaves caused by the coarse vertical grid system during periods of enhanced stratification. It is anticipated that the utility of data-driven artificial intelligence models will expand in the future to improve the prediction performance of dynamical models or even replace them.