• Title/Summary/Keyword: Artificial Intelligence

Search Result 5,113, Processing Time 0.028 seconds

Assessment of Visual Landscape Image Analysis Method Using CNN Deep Learning - Focused on Healing Place - (CNN 딥러닝을 활용한 경관 이미지 분석 방법 평가 - 힐링장소를 대상으로 -)

  • Sung, Jung-Han;Lee, Kyung-Jin
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.51 no.3
    • /
    • pp.166-178
    • /
    • 2023
  • This study aims to introduce and assess CNN Deep Learning methods to analyze visual landscape images on social media with embedded user perceptions and experiences. This study analyzed visual landscape images by focusing on a healing place. For the study, seven adjectives related to healing were selected through text mining and consideration of previous studies. Subsequently, 50 evaluators were recruited to build a Deep Learning image. Evaluators were asked to collect three images most suitable for 'healing', 'healing landscape', and 'healing place' on portal sites. The collected images were refined and a data augmentation process was applied to build a CNN model. After that, 15,097 images of 'healing' and 'healing landscape' on portal sites were collected and classified to analyze the visual landscape of a healing place. As a result of the study, 'quiet' was the highest in the category except 'other' and 'indoor' with 2,093 (22%), followed by 'open', 'joyful', 'comfortable', 'clean', 'natural', and 'beautiful'. It was found through research that CNN Deep Learning is an analysis method that can derive results from visual landscape image analysis. It also suggested that it is one way to supplement the existing visual landscape analysis method, and suggests in-depth and diverse visual landscape analysis in the future by establishing a landscape image learning dataset.

Research on optimal safety ship-route based on artificial intelligence analysis using marine environment prediction (해양환경 예측정보를 활용한 인공지능 분석 기반의 최적 안전항로 연구)

  • Dae-yaoung Eeom;Bang-hee Lee
    • Proceedings of the Korean Institute of Navigation and Port Research Conference
    • /
    • 2023.05a
    • /
    • pp.100-103
    • /
    • 2023
  • Recently, development of maritime autonomoust surface ships and eco-friendly ships, production and evaluation research considering various marine environments is needed in the field of optimal routes as the demand for accurate and detailed real-time marine environment prediction information expands. An algorithm that can calculate the optimal route while reducing the risk of the marine environment and uncertainty in energy consumption in smart ships was developed in 2 stages. In the first stage, a profile was created by combining marine environmental information with ship location and status information within the Automatic Ship Identification System(AIS). In the second stage, a model was developed that could define the marine environment energy map using the configured profile results, A regression equation was generated by applying Random Forest among machine learning techniques to reflect about 600,000 data. The Random Forest coefficient of determination (R2) was 0.89, showing very high reliability. The Dijikstra shortest path algorithm was applied to the marine environment prediction at June 1 to 3, 2021, and to calculate the optimal safety route and express it on the map. The route calculated by the random forest regression model was streamlined, and the route was derived considering the state of the marine environment prediction information. The concept of route calculation based on real-time marine environment prediction information in this study is expected to be able to calculate a realistic and safe route that reflects the movement tendency of ships, and to be expanded to a range of economic, safety, and eco-friendliness evaluation models in the future.

  • PDF

The Meta-Analysis on Effects of Living Lab-Based Education (리빙랩 기반 교육 프로그램의 효과에 대한 메타분석)

  • So Hee Yoon
    • Journal of Practical Engineering Education
    • /
    • v.14 no.3
    • /
    • pp.505-512
    • /
    • 2022
  • The purpose of this study is to synthesize effects of the living lab-based education through meta-analysis. Seven primary studies reporting the effect of living lab-based education were carefully selected for data analysis. Research questions are as follows. First, what is the overall effect size of the living lab-based education? The overall effect size refers to the effect on the cognitive and affective domains. Second, what is the effect size of the living lab-based education according to categorical variables? Categorical variables are outcome characteristics, study characteristics, and design characteristics. Results are summarized as follows. First, the overall effect size of living lab-based education was 0.347. Second, the effect size according to the cognitive domain was 1.244 for information process, 0.593 for communication, 0.261 for problem solving, and 0.26 for creativity. Third, the effect size according to subject area was shown in the order of electrical and electronic engineering 1.146, technology and home economics 0.489, artificial intelligence 0.379, and practical arts 0.168. Fourth, the effect size according to school level was 1.058 for high school, 0.312 for middle school, and 0.217 for elementary school. Fifth, the effect size by grade level was 0.295 when two or more grades were integrated and 0.294 for a single grade.

The Perception Analysis of Autonomous Vehicles using Network Graph (네트워크 그래프를 활용한 자율주행차에 대한 인식 분석)

  • Hyo-gyeong Park;Yeon-hwi You;Sung-jung Yong;Seo-young Lee;Il-young Moon
    • Journal of Practical Engineering Education
    • /
    • v.15 no.1
    • /
    • pp.97-105
    • /
    • 2023
  • Recently, with the development of artificial intelligence technology, many technologies for user convenience are being developed. Among them, interest in autonomous vehicles is increasing day by day. Currently, many automobile companies are aiming to commercialize autonomous vehicles. In order to lay the foundation for the government's new and reasonable policy establishment to support commercialization, we tried to analyze changes and perceptions of public opinion through news article data. Therefore, in this paper, 35,891 news article data mentioning terms similar to 'autonomous vehicles' over the past three years were collected and network analyzed. As a result of the analysis, major keywords such as 'autonomous driving', 'AI', 'future', 'Hyundai Motor', 'autonomous driving vehicle', 'automobile', 'industrial', and 'electric vehicle' were derived. In addition, the autonomous vehicle industry is developing into a faster and more diverse platform and service industry by converging with various industries such as semiconductor companies and big tech companies as well as automobile companies and is paying attention to the convergence of industries. To continuously confirm changes and perceptions in public opinion, it is necessary to analyze perceptions through continuous analysis of SNS data or technology trends.

A Study on the Depression Relief Effect of Visual Psychological Stabilization Image Using EEG Analysis (뇌파 분석을 이용한 시각 심리 안정 영상의 우울감 완화 효과에 대한 연구)

  • Gurim Kang;Sooyeon Lim
    • The Journal of the Convergence on Culture Technology
    • /
    • v.9 no.5
    • /
    • pp.563-568
    • /
    • 2023
  • The government's strengthening of the standards for mentally ill patients and expanding the scope of examinations to the entire nation reflects the changing times. According to the OECD's announcement (2021), the incidence of depression and anxiety has more than doubled since the prolonged COVID-19 pandemic in countries around the world, with Korea's prevalence ranking first. However, only 12.1% of those who have been diagnosed with mental disorders received counseling and treatment from experts. The difference between depression and simple depression is significant depending on whether it is medically treated or temporary, but it can be seen that the continuation of depression is depression. In order to reduce this depression, Kandinsky's work was visualized and created. In a study conducted by changing the playback speed of the produced Kandinsky image, beta and gamma values, which showed the largest deviation when compared to depressive patients and normal people, increased significantly when viewed at 90fps, which was most effective in relieving depression. Artistic creations are bound to be accepted differently depending on the individual's perspective, but it is hoped that research that can improve the phenomenon of individuals suffering from depression by integrating artificial intelligence and traditional mental health approaches will be further developed and widely used for treatment.

Development of smart car intelligent wheel hub bearing embedded system using predictive diagnosis algorithm

  • Sam-Taek Kim
    • Journal of the Korea Society of Computer and Information
    • /
    • v.28 no.10
    • /
    • pp.1-8
    • /
    • 2023
  • If there is a defect in the wheel bearing, which is a major part of the car, it can cause problems such as traffic accidents. In order to solve this problem, big data is collected and monitoring is conducted to provide early information on the presence or absence of wheel bearing failure and type of failure through predictive diagnosis and management technology. System development is needed. In this paper, to implement such an intelligent wheel hub bearing maintenance system, we develop an embedded system equipped with sensors for monitoring reliability and soundness and algorithms for predictive diagnosis. The algorithm used acquires vibration signals from acceleration sensors installed in wheel bearings and can predict and diagnose failures through big data technology through signal processing techniques, fault frequency analysis, and health characteristic parameter definition. The implemented algorithm applies a stable signal extraction algorithm that can minimize vibration frequency components and maximize vibration components occurring in wheel bearings. In noise removal using a filter, an artificial intelligence-based soundness extraction algorithm is applied, and FFT is applied. The fault frequency was analyzed and the fault was diagnosed by extracting fault characteristic factors. The performance target of this system was over 12,800 ODR, and the target was met through test results.

Methods for Quantitative Disassembly and Code Establishment of CBS in BIM for Program and Payment Management (BIM의 공정과 기성 관리 적용을 위한 CBS 수량 분개 및 코드 정립 방안)

  • Hando Kim;Jeongyong Nam;Yongju Kim;Inhye Ryu
    • Journal of the Computational Structural Engineering Institute of Korea
    • /
    • v.36 no.6
    • /
    • pp.381-389
    • /
    • 2023
  • One of the crucial components in building information modeling (BIM) is data. To systematically manage these data, various research studies have focused on the creation of object breakdown structures and property sets. Specifically, crucial data for managing programs and payments involves work breakdown structures (WBSs) and cost breakdown structures (CBSs), which are indispensable for mapping BIM objects. Achieving this requires disassembling CBS quantities based on 3D objects and WBS. However, this task is highly tedious owing to the large volume of CBS and divergent coding practices employed by different organizations. Manual processes, such as those based on Excel, become nearly impossible for such extensive tasks. In response to the challenge of computing quantities that are difficult to derive from BIM objects, this study presents methods for disassembling length-based quantities, incorporating significant portions of the bill of quantities (BOQs). The proposed approach recommends suitable CBS by leveraging the accumulated history of WBS-CBS mapping databases. Additionally, it establishes a unified CBS code, facilitating the effective operation of CBS databases.

An Exploratory Study of Generative AI Service Quality using LDA Topic Modeling and Comparison with Existing Dimensions (LDA토픽 모델링을 활용한 생성형 AI 챗봇의 탐색적 연구 : 기존 AI 챗봇 서비스 품질 요인과의 비교)

  • YaeEun Ahn;Jungsuk Oh
    • 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.

Optimization-based Deep Learning Model to Localize L3 Slice in Whole Body Computerized Tomography Images (컴퓨터 단층촬영 영상에서 3번 요추부 슬라이스 검출을 위한 최적화 기반 딥러닝 모델)

  • Seongwon Chae;Jae-Hyun Jo;Ye-Eun Park;Jin-Hyoung, Jeong;Sung Jin Kim;Ahnryul Choi
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.16 no.5
    • /
    • pp.331-337
    • /
    • 2023
  • In this paper, we propose a deep learning model to detect lumbar 3 (L3) CT images to determine the occurrence and degree of sarcopenia. In addition, we would like to propose an optimization technique that uses oversampling ratio and class weight as design parameters to address the problem of performance degradation due to data imbalance between L3 level and non-L3 level portions of CT data. In order to train and test the model, a total of 150 whole-body CT images of 104 prostate cancer patients and 46 bladder cancer patients who visited Gangneung Asan Medical Center were used. The deep learning model used ResNet50, and the design parameters of the optimization technique were selected as six types of model hyperparameters, data augmentation ratio, and class weight. It was confirmed that the proposed optimization-based L3 level extraction model reduced the median L3 error by about 1.0 slices compared to the control model (a model that optimized only 5 types of hyperparameters). Through the results of this study, accurate L3 slice detection was possible, and additionally, we were able to present the possibility of effectively solving the data imbalance problem through oversampling through data augmentation and class weight adjustment.

Detection Fastener Defect using Semi Supervised Learning and Transfer Learning (준지도 학습과 전이 학습을 이용한 선로 체결 장치 결함 검출)

  • Sangmin Lee;Seokmin Han
    • Journal of Internet Computing and Services
    • /
    • v.24 no.6
    • /
    • pp.91-98
    • /
    • 2023
  • Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.