• 한국재난정보학회 논문집
• /
• 제17권4호
• /
• pp.802-816
• /
• 2021

연구목적: 본 논문에서는 개선된 특허 검색식을 제안하고 이에 기반 한 특허분석을 통해 Passive Tracking 기술분야의 잠재적 유망분야에 해당하는 공백기술을 도출하여 향후 수행해야 할 연구개발의 방향성을 제시한다. 연구방법: 본 논문에서는 기존의 검색식 구성 방식을 개선하여 유사어 DB, 최근 발표 논문의 Keyword, AI 검색 등의 다양한 Tool과 방법을 복합적으로 적용하는 기법을 제안하고, Passive Tracking 기술분야를 대상으로 광범위한 특허조사 및 분석을 통해, 기술 변화의 방향성 및 흐름을 확인하고, 해결하고자 하는 목적과 수단을 매트릭스화 하는 방법으로 공백기술을 도출한다. 연구결과: 제안하는 방법을 통해 Passive Tracking 기술분야 공백기술은 인공지능,적응형/복합형 측위기술 및 레이더/안테나를 활용한 '멀티 타깃 측위·추적기술'과 '3D 측위 기술'이 공백기술로 도출되었으며, 도출 결과의 타당성을 검토하기 위한 검색 결과 상용화 서비스 또는 제품이 부재함을 확인하였다. 결론: 본 논문에서 도출한 공백기술은 특허출원이 활발하지 않고 선점되어 있는 선행특허가 많지 않은 분야이므로, 보다 적극적인 연구개발과 특허출원 활동을 통해 기술에 대한 권리를 확보할 필요가 있다.

• Journal of Information Technology Applications and Management
• /
• 제28권6호
• /
• pp.145-161
• /
• 2021

Recently, as personal information utilization devices such as IoT, artificial intelligence, and wearable devices that focus on the individual have spread, privacy violations are also increasing. However, the privacy paradox of providing personal information to enjoy services while worrying is getting stronger. However, there are still preliminary studies on this. In this study, an intelligent home camera based on IoT technology was selected as a research object, and whether privacy paradox exists in the IoT environment, including smart home camera, was studied. To this end, the effect of perceived usefulness, a benefit factor of smart home camera use, and privacy concern, a risk factor, on intention to use was verified. In addition, it was investigated whether the relationship between privacy concerns and intention to use differs according to the presence or absence of use experience. In order to verify the research model, a survey was conducted with people with and without experience in using smart home cameras, and a total of 298 data samples were used for statistical analysis. As a result of the analysis, it was found that both perceived usefulness and privacy concerns had a positive effect on the intention to use, proving that privacy paradox exists in the IoT-based smart home camera environment. In addition, by analyzing the fact that privacy concerns have different effects on usage intentions depending on the user experience, it was verified that those with experience have a strong privacy paradox and those without experience have a weak privacy paradox. This study is meaningful because it seeks strategic implications to improve service and business performance by understanding the relationship between privacy attitudes and behaviors of IoT service providers, including smart home cameras.

• Journal of Information Technology Applications and Management
• /
• 제30권2호
• /
• pp.1-18
• /
• 2023

Recently, as technology development has accelerated and product life cycles have been shortened, it is necessary to derive key product features from customers in the R&D planning and evaluation stage. More companies want differentiated competitiveness by providing consumer-tailored products based on big data and artificial intelligence technology. To achieve this, the need to correctly grasp the required quality, which is a requirement of consumers, is increasing. However, the existing methods are centered on suppliers or domain experts, so there is a gap from the actual perspective of consumers. In other words, product attributes were defined by suppliers or field experts, but this may not consider consumers' actual perspective. Accordingly, the demand for deriving the product's main attributes through reviews containing consumers' perspectives has recently increased. Therefore, we propose a review data analysis-based required quality methodology containing customer requirements. Specifically, a pre-training language model with a good understanding of Korean reviews was established, consumer intent was correctly identified, and key contents were extracted from the review through a combination of KeyBERT and topic modeling to derive the required quality for each product. RevBERT, a Korean review domain-specific pre-training language model, was established through further pre-training. By comparing the existing pre-training language model KcBERT, we confirmed that RevBERT had a deeper understanding of customer reviews. In addition, all processes other than that of selecting the required quality were linked to the automation process, resulting in the automation of deriving the required quality based on data.

• 소성∙가공
• /
• 제32권3호
• /
• pp.153-159
• /
• 2023

This paper presents the optimal design of a heating system using radiant heating elements for application in smart farms. Smart farming, an advanced agricultural technology, is based on artificial intelligence and the internet of things and promotes crop production. Temperature and humidity regulation is critical in smart farms, and thus, a heating system is essential. Radiant heating elements are devices that generate heat using electrical energy. Among other applications, radiant heating elements are used for environmental control and heating in smart farm greenhouses. The performance of these elements is directly related to their electrical energy consumption. Therefore, achieving a balance between efficient electrical energy consumption and maximum heating performance in smart farms is crucial for the optimal design of radiant heating elements. In this study, the size, electrical energy supply, heat generation efficiency, and heating performance of radiant heating elements used in these heating systems were investigated. The effects of the size and electrical energy supply of radiant heating elements on the heating performance were experimentally analyzed. As the radiant heating element size increased, the heat generation efficiency improved, but the electrical energy consumption also increased. In addition, increasing the electrical energy supply improved both the heat generation efficiency and heating performance of the radiant heating elements. Based on these results, a method for determining the optimal size and electrical energy supply of radiant heating elements was proposed, and it reduced the electrical energy consumption while maintaining an appropriate heating performance in smart farms. These research findings are expected to contribute to energy conservation and performance improvement in smart farming.

• 대한임베디드공학회논문지
• /
• 제18권3호
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.17-25
• /
• 2023

The alarming global prevalence of Type 2 Diabetes Mellitus (T2DM) has catalyzed an urgent need for robust, early diagnostic methodologies. This study unveils a pioneering approach to predicting T2DM, employing the Extreme Gradient Boosting (XGBoost) algorithm, renowned for its predictive accuracy and computational efficiency. The investigation harnesses a meticulously curated dataset of 4303 samples, extracted from a comprehensive Chinese research study, scrupulously aligned with the World Health Organization's indicators and standards. The dataset encapsulates a multifaceted spectrum of clinical, demographic, and lifestyle attributes. Through an intricate process of hyperparameter optimization, the XGBoost model exhibited an unparalleled best score, elucidating a distinctive combination of parameters such as a learning rate of 0.1, max depth of 3, 150 estimators, and specific colsample strategies. The model's validation accuracy of 0.957, coupled with a sensitivity of 0.9898 and specificity of 0.8897, underlines its robustness in classifying T2DM. A detailed analysis of the confusion matrix further substantiated the model's diagnostic prowess, with an F1-score of 0.9308, illustrating its balanced performance in true positive and negative classifications. The precision and recall metrics provided nuanced insights into the model's ability to minimize false predictions, thereby enhancing its clinical applicability. The research findings not only underline the remarkable efficacy of XGBoost in T2DM prediction but also contribute to the burgeoning field of machine learning applications in personalized healthcare. By elucidating a novel paradigm that accentuates the synergistic integration of multifaceted clinical parameters, this study fosters a promising avenue for precise early detection, risk stratification, and patient-centric intervention in diabetes care. The research serves as a beacon, inspiring further exploration and innovation in leveraging advanced analytical techniques for transformative impacts on predictive diagnostics and chronic disease management.

• 인터넷정보학회논문지
• /
• 제24권4호
• /
• pp.85-92
• /
• 2023

X-ray, Computed Tomography (CT), Magnetic Resonance Imaging (MRI)과 같은 의료데이터에서 딥러닝을 활용해 질병 유무 판별 태스크와 같은 문제를 해결하려는 시도가 활발하다. 대부분의 데이터 기반 딥러닝 문제들은 높은 정확도 달성과 정답과 비교하는 성능평가의 활용을 위해 지도학습기법을 사용해야 한다. 지도학습에는 다량의 이미지와 레이블 세트가 필요하지만, 학습에 충분한 양의 의료 이미지 데이터를 얻기는 어렵다. 다양한 데이터 증강 기법을 통해 적은 양의 의료이미지와 레이블 세트로 지도학습 기반 모델의 과소적합 문제를 극복할 수 있다. 본 연구는 딥러닝 기반 갈비뼈 골절 세그멘테이션 모델의 성능 향상과 효과적인 좌우 반전, 회전, 스케일링 등의 데이터 증강 기법을 탐색한다. 좌우 반전과 30° 회전, 60° 회전으로 증강한 데이터셋은 모델 성능 향상에 기여하지만, 90° 회전 및 ⨯0.5 스케일링은 모델 성능을 저하한다. 이는 데이터셋 및 태스크에 따라 적절한 데이터 증강 기법의 사용이 필요함을 나타낸다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.431-433
• /
• 2022

IoT 기술의 발달에 따라 인공지능과 자동화와 같이 다양한 기술들이 산업현장에 접목되고 있으며, 이에 따라 데이터처리의 중요성이 높아지고 있다. 영상의 잡음제거는 영상처리의 기본적인 과정 중 하나로서, 수많은 어플리케이션에서 전처리 단계로 사용된다. 잡음제거를 위해 다양한 연구가 진행되었지만, 잡음제거 과정에서 영상의 디테일 보존, 질감 복원과 특수한 영역의 잡음 제거와 같이 다양한 문제가 발생한다. 본 논문에서는 임펄스 잡음제거 과정에서 영상의 디테일 보존을 위해 확장된 컨벌루션 마스크를 사용한 디지털 필터를 제안한다. 제안한 알고리즘은 필터링 마스크로 확장된 컨벌루션 마스크를 사용하며, 잡음수준에 따라 확장수준을 스위칭하여 최종출력을 구한다. 제안한 알고리즘의 성능을 평가하기 위해 시뮬레이션을 진행하였으며, 기존 방법과 비교하여 성능을 분석하였다.

• 실천공학교육논문지
• /
• 제15권2호
• /
• pp.357-364
• /
• 2023

인공지능 기술의 급속한 발전으로 인해 생성형 인공지능 플랫폼은 다양한 분야에서 혁신적인 활용이 이루어지고 있다. 본 논문에서는 인공지능을 교육에 활용한 연구사례, 생성형 인공지능 플랫폼이 컴퓨터그래픽 영역에 활용된 사례를 살펴보고, 생성형 인공지능 교육 방향성에 대해 논의하였다. 컴퓨터그래픽에서 이미지 생성과 편집, 영상편집에 활용 가능한 생성형 인공지능 플랫폼을 소개하고, 영상편집 제작과정에 적용할 수 있도록 활용방법을 제안하였다. 이러한 생성형 인공지능 플랫폼은 제작공정에서 창작자의 수고를 덜고, 시간을 단축시킨다는 효율성 측면에서도 장점뿐만 아니라 개인의 역량을 증진할 수 있다. 컴퓨터그래픽 제작에 있어 생성형 인공지능 플랫폼은 다양한 변화를 가져다 주었다. 그런 변화를 살펴보고 생성형 인공지능 플랫폼을 활용한 창작 교육에 방향성을 제시하고자 한다.

• 전기전자학회논문지
• /
• 제27권4호
• /
• pp.518-523
• /
• 2023

고정자 권선단락은 미세한 턴이 단락되어 급격히 고장이 심각해짐에 따라 ITSC의 진단이 중요시되고 있다. 그러나, 3상 유도전동기의 노이즈 및 손실등과 유사한 특징을 가짐에 따라 ITSC진단에 많은 어려움이 있다. 이를 효율적으로 진단하기 위해서 인공지능 기법으로 연구되고 있으나, 현장에서는 모델기반 기법이 두루 활용되고 있음에 따라 모델기반 기법에 대한 진단 성능개선 연구가 필요한 실정이다. 이에 본 논문에서는 회전하고 있는 자속에 변화를 무시하며, 전류 성분만을 이용할 수 있도록 Clarke변환 방법을 응용하여 진단방법을 제안하였다. 이에 30분간의 정상 및 ITSC 상태의 측정 결과, 정상상태를 ITSC 상태로 오인식하는 경우 0.2[%], ITSC상태를 정상상태로 오거부하는 경우 0.26[%]로 효율적인 진단 방법임을 실험을 통해 알 수 있었다.