• ETRI Journal
• /
• v.46 no.2
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.85-94
• /
• 2024

Artificial Intelligence of Things (AIoT), which combines AI and the Internet of Things (IoT), has recently gained popularity. Deep neural networks (DNNs) have achieved great success in many applications. Deploying complex AI models on embedded boards, nevertheless, may be challenging due to computational limitations or intelligent model complexity. This paper focuses on an AIoT-based system for smart sewing automation using edge devices. Our technique included developing a detection model and a decision tree for a sufficient testing scenario. YOLOv5 set the stage for our defective sewing stitches detection model, to detect anomalies and classify the sewing patterns. According to the experimental testing, the proposed approach achieved a perfect score with accuracy and F1score of 1.0, False Positive Rate (FPR), False Negative Rate (FNR) of 0, and a speed of 0.07 seconds with file size 2.43MB.

• Journal of Information Technology Applications and Management
• /
• v.30 no.4
• /
• pp.11-28
• /
• 2023

This paper proposes a method of integrating ChatGPT with traditional chatbot systems to enhance conversational artificial intelligence(AI) and create more efficient conversational systems. Traditional chatbot systems are primarily based on classification models and are limited to intent classification and simple response generation. In contrast, ChatGPT is a state-of-the-art AI technology for natural language generation, which can generate more natural and fluent conversations. In this paper, we analyze the business service areas that can be integrated with ChatGPT and traditional chatbots, and present methods for conducting conversational scenarios through case studies of service types. Additionally, we suggest ways to integrate ChatGPT with traditional chatbot systems for intent recognition, conversation flow control, and response generation. We provide a practical implementation example of how to integrate ChatGPT with traditional chatbots, making it easier to understand and build integration methods and actively utilize ChatGPT with existing chatbots.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.51 no.1
• /
• pp.1-10
• /
• 2024

Deep learning algorithms are becoming more prevalent in dental research because they are utilized in everyday activities. However, dental researchers and clinicians find it challenging to interpret deep learning studies. This review aimed to provide an overview of the general concept of deep learning and current deep learning research in dental radiographic image analysis. In addition, the process of implementing deep learning research is described. Deep-learning-based algorithmic models perform well in classification, object detection, and segmentation tasks, making it possible to automatically diagnose oral lesions and anatomical structures. The deep learning model can enhance the decision-making process for researchers and clinicians. This review may be useful to dental researchers who are currently evaluating and assessing deep learning studies in the field of dentistry.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.11a
• /
• pp.237-238
• /
• 2023

Urbanization and the increase in building scale have amplified the complexity of M.E.P design. Traditional design methods face limitations when considering intricate pathways and variables, leading to an emergent need for research in automated design. Initial algorithmic approaches encountered challenges in addressing complex architectural structures and the diversity of M.E.P types. However, with the launch of OpenAI's ChatGPT-3.5 beta version in 2022, new opportunities in the automated design sector were unlocked. ChatGPT, based on the Large Language Model (LLM), has the capability to deeply comprehend the logical structures and meanings within training data. This study analyzed the potential application and latent value of LLMs in M.E.P design. Ultimately, the implementation of LLM in M.E.P design will make genuine automated design feasible, which is anticipated to drive advancements across designs in the construction sector.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.658-661
• /
• 2024

퍼블릭 클라우드 시장이 성장하면서 퍼블릭 클라우드에서 호스팅하는 컴퓨팅 자원으로 구축된 거대하고 복잡한 IT 시스템이 점차 많아지고 있다. 이러한 시스템의 증가는 서비스 장애 발생 확률을 높이므로, 장애 관리 및 선제 감지를 위한 퍼블릭 클라우드 자원의 이상 감지 연구에 대한 수요 또한 증가하고 있다. 그러나 연구에 활용할 수 있는 벤치마크 데이터셋이 없다는 점과, 실제 자원에서 추출할 수 있는 데이터는 레이블링이 되어 있지 않은 불균형 데이터라는 점 때문에 관련 연구가 부족한 상황이다. 이러한 문제를 해결하고자 본 논문은 비지도 방식의 표현 학습 기반 딥러닝 모델을 활용한 이상 감지 시스템을 제안한다. 시스템의 이상 감지 성능을 유지하고자 일정 주기마다 다수의 딥러닝 모델을 재학습하고 비교하여 최적의 모델로 업데이트 하는 방식을 고안하였다. 해당 시스템의 평가에는 실제 퍼블릭 클라우드 자원에서 발생한 메트릭 데이터가 활용됐으며, 그 결과 준수한 이상 감지 성능을 보인다는 것을 확인하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.1-6
• /
• 2016

A.I. has being developed from the technology for Big data analysis to the technology like a human being. The sensing technology of IOT will make A.I. have the more delicate sense than human's five senses. The computer resource is going to be able to support A.I. by clouding networking technology wherever and whenever. Like this A.I. is getting developed as a golden boy of the latest technologies At the same time, many experts have the anxiety and bleak outlook about A.I. Most of dystopian images of the future come out when the contemplative view is lost or it is not possible to view the phenomena objectively. Or it is because of the absence of confidence and ability to convert from the visions of technology development to the subject visions of human will. This study is not about the mass dismissal, unemployment or the end of mankind by machinery according to the development of A.I. technology and service, but more about the occurrent issue like the personal information invasion in daily life. Also the ethical and institutional models are considered to develop A.I. industry protecting the personal information.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.19-27
• /
• 2020

In this paper, we propose a machine learning method for diagnosing the failure of a gas pressure regulator. Originally, when implementing a machine learning model for detecting abnormal operation of a facility, it is common to install sensors to collect data. However, failure of a gas pressure regulator can lead to fatal safety problems, so that installing an additional sensor on a gas pressure regulator is not simple. In this paper, we propose various machine learning approach for diagnosing the abnormal operation of a gas pressure regulator with only the flow rate and gas pressure data collected from a gas pressure regulator itself. Since the fault data of a gas pressure regulator is not enough, the model is trained in all classes by applying the over-sampling method. The classification model was implemented using Gradient boosting, 1D Convolutional Neural Networks, and LSTM algorithm, and gradient boosting model showed the best performance among classification models with 99.975% accuracy.

• Journal of Gastric Cancer
• /
• v.21 no.3
• /
• pp.279-297
• /
• 2021

Purpose: Various changes in nutrition, metabolism, immunity, and psychological status occur through multiple mechanisms after gastrectomy. The purpose of this study was to predict disease status after gastrectomy by analyzing diseases pattern that occur or change after gastrectomy. Materials and Methods: A retrospective cohort study was conducted using nationwide claims data. Patients with gastric cancer who underwent gastrectomy or endoscopic resection were included in the study. Eighteen target diseases were selected and categorized based on their underlying mechanism. The incidence of each target disease was compared by dividing the study sample into those who underwent gastrectomy (cases) and those who underwent endoscopic resection for early gastric cancer (controls). The cases were matched with controls using propensity score matching. Thereafter, Cox proportional hazard models were used to evaluate intergroup differences in disease incidence after gastrectomy. Results: A total of 97,634 patients who underwent gastrectomy (84,830) or endoscopic resection (12,804) were included. The incidence of cholecystitis (P<0.0001), pancreatitis (P=0.034), acute kidney injury (P=0.0083), anemia (P<0.0001), and inguinal hernia (P=0.0007) were higher after gastrectomy, while incidence of dyslipidemia (P<0.0001), vascular diseases (ischemic heart disease, stroke, and atherosclerosis; P<0.0001, P<0.0001, and P=0.0005), and Parkinson's disease (P=0.0093) were lower after gastrectomy. Conclusions: This study identifies diseases that may occur after gastrectomy in patients with gastric cancer.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.70-75
• /
• 2021

Grouping and classifying similar designs in design increase efficiency in terms of management and provide convenience in terms of use. Using artificial intelligence algorithms, this study attempted to classify textile designs into four categories: dots, flower patterns, stripes, and geometry. In particular, we explored whether it is possible to find and explain the regions of interest underlying classification from the perspective of artificial intelligence. We randomly extracted a total of 4,536 designs at a ratio of 8:2, comprising 3,629 for training and 907 for testing. The models used in the classification were VGG-16 and ResNet-34, both of which showed excellent classification performance with precision on flower pattern designs of 0.79%, 0.89% and recall of 0.95% and 0.38%. Analysis using the Local Interpretable Model-agnostic Explanation (LIME) technique has shown that geometry and flower-patterned designs derived shapes and petals from the region of interest on which classification was based.