• Title/Summary/Keyword: AI 모델

Search Result 1,189, Processing Time 0.032 seconds

Neuro PID Control for Ultra-Compact Binary Power Generation Plant (초소형 바이너리 발전 플랜트를 위한 Neuro PID 제어)

  • Han, Kun-Young
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.25 no.11
    • /
    • pp.1495-1504
    • /
    • 2021
  • An ultra-compact binary power generation plant converts thermal energy into electric power using temperature difference between heat source and cooling source. In the actual power generation environment, the characteristic value of the plant changes due to any negative effects such as environmental condition or corrosion of related equipment. If the characteristic value of the plant changes, it may lead to unstable output of the turbine in a conventional PID control system with fixed PID parameters. A Neuro PID control system based on Neural Network adaptively to adjust the PID parameters according to the change in the characteristic value of the plant is proposed in this paper. Discrete-time transfer function models to represent the dynamic characteristics near the operating point of the investigated plant are deduced, and a design strategy of the proposed control system is described. The proposed Neuro PID control system is compared with the conventional PID control system, and its effectiveness is demonstrated through the simulation results.

An Enhancement Method of Document Restoration Capability using Encryption and DnCNN (암호화와 DnCNN을 활용한 문서 복원능력 향상에 관한 연구)

  • Jang, Hyun-Hee;Ha, Sung-Jae;Cho, Gi-Hwan
    • Journal of Internet of Things and Convergence
    • /
    • v.8 no.2
    • /
    • pp.79-84
    • /
    • 2022
  • This paper presents an enhancement method of document restoration capability which is robust for security, loss, and contamination, It is based on two methods, that is, encryption and DnCNN(DeNoise Convolution Neural Network). In order to implement this encryption method, a mathematical model is applied as a spatial frequency transfer function used in optics of 2D image information. Then a method is proposed with optical interference patterns as encryption using spatial frequency transfer functions and using mathematical variables of spatial frequency transfer functions as ciphers. In addition, by applying the DnCNN method which is bsed on deep learning technique, the restoration capability is enhanced by removing noise. With an experimental evaluation, with 65% information loss, by applying Pre-Training DnCNN Deep Learning, the peak signal-to-noise ratio (PSNR) shows 11% or more superior in compared to that of the spatial frequency transfer function only. In addition, it is confirmed that the characteristic of CC(Correlation Coefficient) is enhanced by 16% or more.

A Study on the Optimization of a Contracted Power Prediction Model for Convenience Store using XGBoost Regression (XGBoost 회귀를 활용한 편의점 계약전력 예측 모델의 최적화에 대한 연구)

  • Kim, Sang Min;Park, Chankwon;Lee, Ji-Eun
    • Journal of Information Technology Services
    • /
    • v.21 no.4
    • /
    • pp.91-103
    • /
    • 2022
  • This study proposes a model for predicting contracted power using electric power data collected in real time from convenience stores nationwide. By optimizing the prediction model using machine learning, it will be possible to predict the contracted power required to renew the contract of the existing convenience store. Contracted power is predicted through the XGBoost regression model. For the learning of XGBoost model, the electric power data collected for 16 months through a real-time monitoring system for convenience stores nationwide were used. The hyperparameters of the XGBoost model were tuned using the GridesearchCV, and the main features of the prediction model were identified using the xgb.importance function. In addition, it was also confirmed whether the preprocessing method of missing values and outliers affects the prediction of reduced power. As a result of hyperparameter tuning, an optimal model with improved predictive performance was obtained. It was found that the features of power.2020.09, power.2021.02, area, and operating time had an effect on the prediction of contracted power. As a result of the analysis, it was found that the preprocessing policy of missing values and outliers did not affect the prediction result. The proposed XGBoost regression model showed high predictive performance for contract power. Even if the preprocessing method for missing values and outliers was changed, there was no significant difference in the prediction results through hyperparameters tuning.

The Methodology of the Golf Swing Similarity Measurement Using Deep Learning-Based 2D Pose Estimation

  • Jonghyuk, Park
    • Journal of the Korea Society of Computer and Information
    • /
    • v.28 no.1
    • /
    • pp.39-47
    • /
    • 2023
  • In this paper, we propose a method to measure the similarity between golf swings in videos. As it is known that deep learning-based artificial intelligence technology is effective in the field of computer vision, attempts to utilize artificial intelligence in video-based sports data analysis are increasing. In this study, the joint coordinates of a person in a golf swing video were obtained using a deep learning-based pose estimation model, and based on this, the similarity of each swing segment was measured. For the evaluation of the proposed method, driver swing videos from the GolfDB dataset were used. As a result of measuring swing similarity by pairing swing videos of a total of 36 players, 26 players evaluated that their other swing sequence was the most similar, and the average ranking of similarity was confirmed to be about 5th. This ensured that the similarity could be measured in detail even when the motion was performed similarly.

An Accuracy Assessment Scheme through Entropy Analysis in BLE-based Indoor Positioning Systems (BLE 기반 실내 측위 시스템에서 엔트로피 분석을 통한 정확도 평가 기법)

  • Pi, Kyung-Joon;Min, Hong;Han, Kyoungho
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.22 no.3
    • /
    • pp.117-123
    • /
    • 2022
  • Unlike the satellite-based outdoor positioning system, the indoor positioning system utilizes various wireless technologies such as BLE, Wi-Fi, and UWB. BLE-based beacon technology can measure the user's location by periodically broadcasting predefined device ID and location information and using RSSI from the receiving device. Existing BLE-based indoor positioning system studies have many studies comparing the error between the user's actual location and the estimated location at a single point. In this paper, we propose a technique to evaluate the positioning accuracy according to the movement path or area by applying the entropy analysis model. In addition, simulation results show that calculated entropy results for different paths can be compared to assess which path is more accurate.

Predicting lane speeds from link speeds by using neural networks

  • Pyun, Dong hyun;Pyo, Changwoo
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.8
    • /
    • pp.69-75
    • /
    • 2022
  • In this paper, a method for predicting the speed for each lane from the link speed using an artificial neural network is presented to increase the accuracy of predicting the required time of a driving route. The time required for passing through a link is observed differently depending on the direction of going straight, turning right, or turning left at the intersection of the end of the link. Therefore, it is necessary to predict the speed according to the vehicle's traveling direction. Data required for learning and verification were constructed by refining the data measured at the Gongpyeong intersection of Gukchaebosang-ro in Daegu Metropolitan City and four adjacent intersections around it. Five neural network models were used. In addition, error analysis of the prediction was performed to select a neural network experimentally suitable for the research purpose. Experimental results showed that the error in the estimation of the time required for each lane decreased by 17.4% for the straight lane, 4.4% for the right-turn lane, and 3.9% for the left-turn lane. This experiment is the result of analyzing only one link. If the entire pathway is tested, the effect is expected to be greater.

Escape Route Prediction and Tracking System using Artificial Intelligence (인공지능을 활용한 도주경로 예측 및 추적 시스템)

  • Yang, Bum-Suk;Park, Dea-Woo
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.8
    • /
    • pp.1130-1135
    • /
    • 2022
  • In Seoul, about 75,000 CCTVs are installed in 25 district offices. Each ward office has built a control center for CCTV control and is performing 24-hour CCTV video control for the safety of citizens. Seoul Metropolitan Government is building a smart city integrated platform that is safe for citizens by providing CCTV images of the ward office to enable rapid response to emergency/emergency situations by signing an MOU with related organizations. In this paper, when an incident occurs at the Seoul Metropolitan Government Office, the escape route is predicted by discriminating people and vehicles using the AI DNN-based Template Matching technology, MLP algorithm and CNN-based YOLO SPP DNN model for CCTV images. In addition, it is designed to automatically disseminate image information and situation information to adjacent ward offices when vehicles and people escape from the competent ward office. The escape route prediction and tracking system using artificial intelligence can expand the smart city integrated platform nationwide.

Valid Data Conditions and Discrimination for Machine Learning: Case study on Dataset in the Public Data Portal (기계학습에 유효한 데이터 요건 및 선별: 공공데이터포털 제공 데이터 사례를 통해)

  • Oh, Hyo-Jung;Yun, Bo-Hyun
    • Journal of Internet of Things and Convergence
    • /
    • v.8 no.1
    • /
    • pp.37-43
    • /
    • 2022
  • The fundamental basis of AI technology is learningable data. Recently, the types and amounts of data collected and produced by the government or private companies are increasing exponentially, however, verified data that can be used for actual machine learning has not yet led to it. This study discusses the conditions that data actually can be used for machine learning should meet, and identifies factors that degrade data quality through case studies. To this end, two representative cases of developing a prediction model using public big data was selected, and data for actual problem solving was collected from the public data portal. Through this, there is a difference from the results of applying valid data screening criteria and post-processing. The ultimate purpose of this study is to argue the importance of data quality management that must be most fundamentally preceded before the development of machine learning technology, which is the core of artificial intelligence, and accumulating valid data.

An Analysis of Educational Capacity Prediction according to Pre-survey of Satisfaction using Random Forest (랜덤 포레스트를 활용한 만족도 사전조사에 따른 교육 역량 예측 분석)

  • Nam, Kihun
    • The Journal of the Convergence on Culture Technology
    • /
    • v.8 no.6
    • /
    • pp.487-492
    • /
    • 2022
  • Universities are looking for various methods to enhance educational competence level suitable for the rapidly changing social environment. This study suggests a method to promote academic and educational achievements by reducing drop-out rate from their majors through implementation of pre-survey of satisfaction that revised and complemented survey items. To supplement the CQI method implemented after a general satisfaction survey, a pre-survey of satisfaction was carried out. To consolidate students' competences, this study made prediction and analysis of data with more importance possible using the Random Forest of the machine learning technique that can be applied to AI Medici platform, whose design is underway. By pre-processing the pre-survey of satisfaction, the students information enrolled in classes were defined as an explanatory variable, and they were classified, and a model was created and learning was conducted. For the experimental environment, the algorithms and sklearn library related in Jupyter notebook 3.7.7, Python 3.7 were used together. This study carried out a comparative analysis of change in educational satisfaction survey, carried out after classes, and trends in the drop-out students by reflecting the results of the suggested method in the classes.

Groundwater Resources Management with ChatGPT: Harnessing AI for Quantitative and Qualitative Approaches (지하수 수량 및 수질 관리를 위한 ChatGPT의 활용)

  • Eungyu Park
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2023.05a
    • /
    • pp.12-12
    • /
    • 2023
  • 지하수자원 관리의 정량적 및 정성적 측면에 있어, 최첨단 인공지능 언어 모델인 ChatGPT의 혁신적인 기능이 활용될 수 있다. 본 발표에서는 지하수 자료에 대한 분석과 도출된 문제의 중요도에 따른 목표를 설정, 그리고 지하수 관리 전략 개발에 있어서의 ChatGPT 활용 방법을 논의할 것이다. 이를 위한 구체적 사례로, 지하수자원 관리에 활용될 수 있는 다양한 도구들의 개발과 고도화에 ChatGPT가 기여하는 방식을 살펴볼 것이다. 이러한 개별 도구들은 지하수자원 관리 결정에 있어 더 나은 예측 및 평가를 제공하여, 지하수 자원 관리의 효율성을 도모할 수 있다. 또한, ChatGPT의 문제 발견 및 해결책 제안 능력에 대해서도 다룰 것이다. 이를 통해 지하수 관리에 있어서의 다양한 문제를 식별하고, 이해당사자들이 보다 효과적으로 대응할 수 있는 방안을 찾아낼 수 있을 것이다. 또한 ChatGPT가 제공하는 다양한 정보 및 문제에 대한 솔루션 접근 방식을 활용한 브레인스토밍 방법을 설명할 것이다. 추가적으로, 일반 인공지능(AGI)의 개발에 근접하면서 지하수 관리의 자동화 및 가속화 그리고 산업 및 환경에 미칠 수 있는 영향에 대해 고찰해 볼 것이다. 이를 위하여, ChatGPT와 같은 인공지능 기술이 더욱 고도화되고 향상되면서, 지하수 관리 및 관련 분야에서의 의사결정, 계획 수립, 그리고 모니터링과 같은 작업들이 어떻게 변화할지에 대하여 토의할 것이다. 본 발표는 지하수 자원 관리 분야에서 ChatGPT와 같은 인공지능 기반 접근법의 가치를 보여주며, 복잡한 지하수 환경 문제를 해결하는 데 있어 첨단 기술의 활용 가능성을 강조할 것이다. 또한, AGI가 등장할 때까지 여전히 요구되는 지하수 분야 도메인 지식과 전문기술의 중요성을 강조할 것이다. 지하수 관리자들의 도메인 지식과 전문적 기술은 인공지능 기반 도구와 결합되어 보다 정확한 분석, 예측 및 해결책 도출을 가속화하며 정교화할 것이다. 결론적으로, 지하수 관리에 대한 종합적인 이해와 전문성을 갖춘 전문가들의 인공지능 기술활용은 지속가능한 지하수의 첨단 관리 효과적 달성에 중요한 계기가 될 것으로 판단한다.

  • PDF