• Title/Summary/Keyword: machine learning

Search Result 5,100, Processing Time 0.026 seconds

Formal Model of Extended Reinforcement Learning (E-RL) System (확장된 강화학습 시스템의 정형모델)

  • Jeon, Do Yeong;Song, Myeong Ho;Kim, Soo Dong
    • Journal of Internet Computing and Services
    • /
    • v.22 no.4
    • /
    • pp.13-28
    • /
    • 2021
  • Reinforcement Learning (RL) is a machine learning algorithm that repeat the closed-loop process that agents perform actions specified by the policy, the action is evaluated with a reward function, and the policy gets updated accordingly. The key benefit of RL is the ability to optimze the policy with action evaluation. Hence, it can effectively be applied to developing advanced intelligent systems and autonomous systems. Conventional RL incoporates a single policy, a reward function, and relatively simple policy update, and hence its utilization was limited. In this paper, we propose an extended RL model that considers multiple instances of RL elements. We define a formal model of the key elements and their computing model of the extended RL. Then, we propose design methods for applying to system development. As a case stud of applying the proposed formal model and the design methods, we present the design and implementation of an advanced car navigator system that guides multiple cars to reaching their destinations efficiently.

A Case Study on an Artificial Intelligence Fashion Curation Practice Subject through Industrial-academic Project-based Learning (산학 연계 프로젝트 기반 학습(PBL)을 활용한 AI 패션 큐레이션 실습 교과목 운영 사례 연구)

  • An, Hyosun;Park, Minjung
    • Fashion & Textile Research Journal
    • /
    • v.23 no.3
    • /
    • pp.337-346
    • /
    • 2021
  • In the fourth industrial revolution, fashion students are expected to work with various technologies to show creativity. This study aimed to conduct project-based learning(PBL) in collaboration with industry experts to design and operate artificial intelligence(AI) in the practice subject of fashion curation through the industrial academic teaching method. We first looked at teaching methods and strategies incorporating PBL in various academic fields. Next, we analyzed fashion projects and fashion curation services applying AI. Then through the question-and-answer method and by consulting with industry experts, we developed a curriculum for AI fashion curation, applying PBL(fashion market and trend analysis; new styles and time, place, and occasion planning; AI machine learning data set production; curation model development; and evaluation) suitable for the university's educational environment, information technology company conditions, and fashion students. As part of a close cooperation system with the industry, we conducted a 15-week Fashion Project II (Capstone Design) course and evaluated the outcomes and student satisfaction with the course. Students were able to develop new style, and time, place, and occasion categories and to utilize strategies for AI fashion curation services reflecting the unique needs of Millennials and Generation Z. Students showed high satisfaction with the curriculum. Further, it was confirmed that the study successfully applied PBL in class using AI technology in fashion education.

Design and Implementation of Hand Gesture Recognizer Based on Artificial Neural Network (인공신경망 기반 손동작 인식기의 설계 및 구현)

  • Kim, Minwoo;Jeong, Woojae;Cho, Jaechan;Jung, Yunho
    • Journal of Advanced Navigation Technology
    • /
    • v.22 no.6
    • /
    • pp.675-680
    • /
    • 2018
  • In this paper, we propose a hand gesture recognizer using restricted coulomb energy (RCE) neural network, and present hardware implementation results for real-time learning and recognition. Since RCE-NN has a flexible network architecture and real-time learning process with low complexity, it is suitable for hand recognition applications. The 3D number dataset was created using an FPGA-based test platform and the designed hand gesture recognizer showed 98.8% recognition accuracy for the 3D number dataset. The proposed hand gesture recognizer is implemented in Intel-Altera cyclone IV FPGA and confirmed that it can be implemented with 26,702 logic elements and 258Kbit memory. In addition, real-time learning and recognition verification were performed at an operating frequency of 70MHz.

Comparison of Fine Grained Classification of Pet Images Using Image Processing and CNN (영상 처리와 CNN을 이용한 애완동물 영상 세부 분류 비교)

  • Kim, Jihae;Go, Jeonghwan;Kwon, Cheolhee
    • Journal of Broadcast Engineering
    • /
    • v.26 no.2
    • /
    • pp.175-183
    • /
    • 2021
  • The study of the fine grained classification of images continues to develop, but the study of object recognition for animals with polymorphic properties is proceeding slowly. Using only pet images corresponding to dogs and cats, this paper aims to compare methods using image processing and methods using deep learning among methods of classifying species of animals, which are fine grained classifications. In this paper, Grab-cut algorithm is used for object segmentation by method using image processing, and method using Fisher Vector for image encoding is proposed. Other methods used deep learning, which has achieved good results in various fields through machine learning, and among them, Convolutional Neural Network (CNN), which showed outstanding performance in image recognition, and Tensorflow, an open-source-based deep learning framework provided by Google. For each method proposed, 37 kinds of pet images, a total of 7,390 pages, were tested to verify and compare their effects.

The prediction of appearance of jellyfish through Deep Neural Network (심층신경망을 통한 해파리 출현 예측)

  • HWANG, CHEOLHUN;Han, Myung-Mook
    • Journal of Internet Computing and Services
    • /
    • v.20 no.5
    • /
    • pp.1-8
    • /
    • 2019
  • This paper carried out a study to reduce damage from jellyfish whose population has increased due to global warming. The emergence of jellyfish on the beach could result in casualties from jellyfish stings and economic losses from closures. This paper confirmed from the preceding studies that the pattern of jellyfish's appearance is predictable through machine learning. This paper is an extension of The prediction model of emergence of Busan coastal jellyfish using SVM. In this paper, we used deep neural network to expand from the existing methods of predicting the existence of jellyfish to the classification by index. Due to the limitations of the small amount of data collected, the 84.57% prediction accuracy limit was sought to be resolved through data expansion using bootstraping. The expanded data showed about 7% higher performance than the original data, and about 6% better performance compared to the transfer learning. Finally, we used the test data to confirm the prediction performance of jellyfish appearance. As a result, although it has been confirmed that jellyfish emergence binary classification can be predicted with high accuracy, predictions through indexation have not produced meaningful results.

An Empirical Study on Prediction of the Art Price using Multivariate Long Short Term Memory Recurrent Neural Network Deep Learning Model (다변수 LSTM 순환신경망 딥러닝 모형을 이용한 미술품 가격 예측에 관한 실증연구)

  • Lee, Jiin;Song, Jeongseok
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.6
    • /
    • pp.552-560
    • /
    • 2021
  • With the recent development of the art distribution system, interest in art investment is increasing rather than seeing art as an object of aesthetic utility. Unlike stocks and bonds, the price of artworks has a heterogeneous characteristic that is determined by reflecting both objective and subjective factors, so the uncertainty in price prediction is high. In this study, we used LSTM Recurrent Neural Network deep learning model to predict the auction winning price by inputting the artist, physical and sales charateristics of the Korean artist. According to the result, the RMSE value, which explains the difference between the predicted and actual price by model, was 0.064. Painter Lee Dae Won had the highest predictive power, and Lee Joong Seop had the lowest. The results suggest the art market becomes more active as investment goods and demand for auction winning price increases.

Design and Implementation of A Smart Crosswalk System based on Vehicle Detection and Speed Estimation using Deep Learning on Edge Devices (엣지 디바이스에서의 딥러닝 기반 차량 인식 및 속도 추정을 통한 스마트 횡단보도 시스템의 설계 및 구현)

  • Jang, Sun-Hye;Cho, Hee-Eun;Jeong, Jin-Woo
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.24 no.4
    • /
    • pp.467-473
    • /
    • 2020
  • Recently, the number of traffic accidents has also increased with the increase in the penetration rate of cars in Korea. In particular, not only inter-vehicle accidents but also human accidents near crosswalks are increasing, so that more attention to traffic safety around crosswalks are required. In this paper, we propose a system for predicting the safety level around the crosswalk by recognizing an approaching vehicle and estimating the speed of the vehicle using NVIDIA Jetson Nano-class edge devices. To this end, various machine learning models are trained with the information obtained from deep learning-based vehicle detection to predict the degree of risk according to the speed of an approaching vehicle. Finally, based on experiments using actual driving images and web simulation, the performance and the feasibility of the proposed system are validated.

Development of a Severity Level Decision Making Process of Road Problems and Its Application Analysis using Deep Learning (딥러닝을 이용한 도로 문제점의 심각도 판단기법 개발 및 적용사례 분석)

  • Jeon, Woo Hoon;Yang, Inchul;Lee, Joyoung
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.10
    • /
    • pp.535-545
    • /
    • 2022
  • The purpose of this study is to classify the various problems in surface road according to their severity and to propose a priority decision making process for road policy makers. For this purpose, the road problems reported by Cheok-cheok app were classified, and the EPDO was adopted and calculated as an index of their severity. To test applicability of the proposed process, some images of road problems reported by the app were classified and annotated, and the Deep Learning was used for machine learning of the curated images, and then the other images of road problems were used for verification. The detecting success rate of the road problems with high severity such as road kills, obstacles in a lane, road surface cracks was over 90%, which shows the applicability of the proposed process. It is expected that the proposed process will make the app possible to be used in the filed to make a priority decision making by classifying the level of severity of the reported road problems automatically.

Efficient distributed consensus optimization based on patterns and groups for federated learning (연합학습을 위한 패턴 및 그룹 기반 효율적인 분산 합의 최적화)

  • Kang, Seung Ju;Chun, Ji Young;Noh, Geontae;Jeong, Ik Rae
    • Journal of Internet Computing and Services
    • /
    • v.23 no.4
    • /
    • pp.73-85
    • /
    • 2022
  • In the era of the 4th industrial revolution, where automation and connectivity are maximized with artificial intelligence, the importance of data collection and utilization for model update is increasing. In order to create a model using artificial intelligence technology, it is usually necessary to gather data in one place so that it can be updated, but this can infringe users' privacy. In this paper, we introduce federated learning, a distributed machine learning method that can update models in cooperation without directly sharing distributed stored data, and introduce a study to optimize distributed consensus among participants without an existing server. In addition, we propose a pattern and group-based distributed consensus optimization algorithm that uses an algorithm for generating patterns and groups based on the Kirkman Triple System, and performs parallel updates and communication. This algorithm guarantees more privacy than the existing distributed consensus optimization algorithm and reduces the communication time until the model converges.

Deep Learning for Classification of High-End Fashion Brand Sensibility (딥러닝을 통한 하이엔드 패션 브랜드 감성 학습)

  • Jang, Seyoon;Kim, Ha Youn;Lee, Yuri;Seol, Jinseok;Kim, Seongjae;Lee, Sang-goo
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.46 no.1
    • /
    • pp.165-181
    • /
    • 2022
  • The fashion industry is creating innovative business models using artificial intelligence. To efficiently utilize artificial intelligence (AI), fashion data must be classified. Until now, such data have been classified focusing only on the objective properties of fashion products. Their subjective attributes, such as fashion brand sensibilities, are holistic and heuristic intuitions created by a combination of design elements. This study aims to improve the performance of collaborative filtering in the fashion industry by extracting fashion brand sensibility using computer vision technology. The image data set of fashion brand sensibility consists of high-end fashion brand photos that share sensibilities and communicate well in fashion. About 26,000 fashion photos of 11 high-end fashion brand sensibility labels have been collected from the 16FW to 21SS runway and 50 years of US Vogue magazines beginning from 1971. We use EfficientNet-B1 to establish the main architecture and fine-tune the network with ImageNet-ILSVRC. After training fashion brand sensibilities through deep learning, the proposed model achieved an F-1 score of 74% on accuracy tests. Furthermore, as a result of comparing AI machine and human experts, the proposed model is expected to be expanded to mass fashion brands.