• Korean Journal of Radiology
• /
• v.23 no.3
• /
• pp.343-354
• /
• 2022

Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.189-198
• /
• 2024

AI is accepted not only in the private sector but also in the defense sector as a cutting-edge technology that must be introduced for the development of national defense. In particular, artificial intelligence has been selected as a key task in defense science and technology innovation, and the importance of data is increasing. As the national defense department shifts from a closed data policy to data sharing and activation, efforts are being made to secure high-quality data necessary for the development of national defense. In particular, we are promoting a review of the business budget system to secure data so that related procedures can be improved to reflect the unique characteristics of AI and big data, and research and development can begin with sufficient large quantities and high-quality data. However, there is a need to establish standardization and quality standards for structured data and unstructured data at the national defense level, but the defense department is still proposing standardization and quality standards for structured data, so this needs to be supplemented. In this paper, we propose an unstructured data set standard format for defense unstructured data sets, which are most needed in defense artificial intelligence, and based on this, we propose a standardization method for defense unstructured data sets.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• Journal of Veterinary Science
• /
• v.23 no.1
• /
• pp.17.1-17.10
• /
• 2022

Background: Inspection of livestock farms using surveillance cameras is emerging as a means of early detection of transboundary animal disease such as African swine fever (ASF). Object tracking, a developing technology derived from object detection aims to the consistent identification of individual objects in farms. Objectives: This study was conducted as a preliminary investigation for practical application to livestock farms. With the use of a high-performance artificial intelligence (AI)-based 3D depth camera, the aim is to establish a pathway for utilizing AI models to perform advanced object tracking. Methods: Multiple crossovers by two humans will be simulated to investigate the potential of object tracking. Inspection of consistent identification will be the evidence of object tracking after crossing over. Two AI models, a fast model and an accurate model, were tested and compared with regard to their object tracking performance in 3D. Finally, the recording of pig pen was also processed with aforementioned AI model to test the possibility of 3D object detection. Results: Both AI successfully processed and provided a 3D bounding box, identification number, and distance away from camera for each individual human. The accurate detection model had better evidence than the fast detection model on 3D object tracking and showed the potential application onto pigs as a livestock. Conclusions: Preparing a custom dataset to train AI models in an appropriate farm is required for proper 3D object detection to operate object tracking for pigs at an ideal level. This will allow the farm to smoothly transit traditional methods to ASF-preventing precision livestock farming.

• Convergence Security Journal
• /
• v.22 no.3
• /
• pp.101-110
• /
• 2022

As the cases of using artificial intelligence in various fields increase, attempts to solve various issues through artificial intelligence in the intrusion detection field are also increasing. However, the black box basis, which cannot explain or trace the reasons for the predicted results through machine learning, presents difficulties for security professionals who must use it. To solve this problem, research on explainable AI(XAI), which helps interpret and understand decisions in machine learning, is increasing in various fields. Therefore, in this paper, we propose an explanatory AI to enhance the reliability of machine learning-based intrusion detection prediction results. First, the intrusion detection model is implemented through XGBoost, and the description of the model is implemented using SHAP. And it provides reliability for security experts to make decisions by comparing and analyzing the existing feature importance and the results using SHAP. For this experiment, PKDD2007 dataset was used, and the association between existing feature importance and SHAP Value was analyzed, and it was verified that SHAP-based explainable AI was valid to give security experts the reliability of the prediction results of intrusion detection models.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.25-36
• /
• 2023

Today, as AI (Artificial Intelligence) technology is introduced in various fields, including security, the development of technology is accelerating. However, with the development of AI technology, attack techniques that cleverly bypass malicious behavior detection are also developing. In the classification process of AI models, an Adversarial attack has emerged that induces misclassification and a decrease in reliability through fine adjustment of input values. The attacks that will appear in the future are not new attacks created by an attacker but rather a method of avoiding the detection system by slightly modifying existing attacks, such as Adversarial attacks. Developing a robust model that can respond to these malware variants is necessary. In this paper, we propose two methods of generating Adversarial attacks as efficient Adversarial attack generation techniques for improving Robustness in AI models. The proposed technique is the XAI-based attack technique using the XAI technique and the Reference based attack through the model's decision boundary search. After that, a classification model was constructed through a malicious code dataset to compare performance with the PGD attack, one of the existing Adversarial attacks. In terms of generation speed, XAI-based attack, and reference-based attack take 0.35 seconds and 0.47 seconds, respectively, compared to the existing PGD attack, which takes 20 minutes, showing a very high speed, especially in the case of reference-based attack, 97.7%, which is higher than the existing PGD attack's generation rate of 75.5%. Therefore, the proposed technique enables more efficient Adversarial attacks and is expected to contribute to research to build a robust AI model in the future.

• Journal of Service Research and Studies
• /
• v.13 no.4
• /
• pp.191-205
• /
• 2023

Artificial Intelligence (AI), especially in the domain of text-generative services, has witnessed a significant surge, with forecasts indicating the AI-as-a-Service (AIaaS) market reaching a valuation of $55.0 Billion by 2028. This research set out to explore the quality dimensions characterizing synthetic text media software, with a focus on four key players in the industry: ChatGPT, Writesonic, Jasper, and Anyword. Drawing from a comprehensive dataset of over 4,000 reviews sourced from a software evaluation platform, the study employed the Latent Dirichlet Allocation (LDA) topic modeling technique using the Gensim library. This process resulted the data into 11 distinct topics. Subsequent analysis involved comparing these topics against established AI service quality dimensions, specifically AICSQ and AISAQUAL. Notably, the reviews predominantly emphasized dimensions like availability and efficiency, while others, such as anthropomorphism, which have been underscored in prior literature, were absent. This observation is attributed to the inherent nature of the reviews of AI services examined, which lean more towards semantic understanding rather than direct user interaction. The study acknowledges inherent limitations, mainly potential biases stemming from the singular review source and the specific nature of the reviewer demographic. Possible future research includes gauging the real-world implications of these quality dimensions on user satisfaction and to discuss deeper into how individual dimensions might impact overall ratings.

• Asia Pacific Journal of Corpus Research
• /
• v.1 no.1
• /
• pp.95-125
• /
• 2020

This paper aims to inform people how to support each other on social media. It alludes to an architecture for social media discourse and proposes a novel theory of support in social media discourse. It makes a methodological contribution. It combines predominately artificial intelligence with corpus linguistics analysis. It is on a large-scale dataset of anonymised diabetes-related user's posts from the Facebook platform. Log-likelihood and precision measures help with validation. A multi-method approach with Discourse Analysis helps in understanding any potential patterns. People living with Diabetes are found to employ sophisticated high-frequency patterns of device-enabled categories of purpose and content. It is with, for example, linguistic forms of Advice with stance-taking and targets such as Diabetes amongst other interactional ways. There can be uncertainty and variation of effect displayed when sharing information for support. The implications of the new theory aim at healthcare communicators, corpus linguists and with preliminary work for AI support-bots. These bots may be programmed to utilise the language patterns to support people who need them automatically.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• pp.300-310
• /
• 2022

A vast amount of labeled data is required for deep neural network training. A typical strategy to improve the performance of a neural network given a training data set is to use data augmentation technique. The goal of this work is to offer a novel image augmentation method for improving object detection accuracy. An object in an image is removed, and a similar object from the training data set is placed in its area. An in-painting algorithm fills the space that is eliminated but not filled by a similar object. Our technique shows at most 2.32 percent improvements on mAP in our testing on a military vehicle dataset using the YOLOv4 object detector.

• Journal of the Korean Society of Systems Engineering
• /
• v.17 no.2
• /
• pp.91-97
• /
• 2021

User interface for cancer classification system is a software application with clinician's friendly tools and functions to diagnose cancer from pathology images. Pathology evolved from manual diagnosis to computer-aided diagnosis with the help of Artificial Intelligence tools and algorithms. In this paper, we explained each block of the project life cycle for the implementation of automated breast cancer classification software using AI and machine learning algorithms to classify normal and invasive breast histology images. The system was designed to help the pathologists in an automatic and efficient diagnosis of breast cancer. To design the classification model, Hematoxylin and Eosin (H&E) stained breast histology images were obtained from the ICIAR Breast Cancer challenge. These images are stain normalized to minimize the error that can occur during model training due to pathological stains. The normalized dataset was fed into the ResNet-34 for the classification of normal and invasive breast cancer images. ResNet-34 gave 94% accuracy, 93% F Score, 95% of model Recall, and 91% precision.