• 한국측량학회지
• /
• 제35권5호
• /
• pp.423-430
• /
• 2017

Recently, data analysis research has been carried out using the deep learning technique in various fields such as image interpretation and/or classification. Various types of algorithms are being developed for many applications. In this paper, we propose a precipitation prediction algorithm based on deep learning with high accuracy in order to take care of the possible severe damage caused by climate change. Since the geographical and seasonal characteristics of Korea are clearly distinct, the meteorological factors have repetitive patterns in a time series. Since the LSTM (Long Short-Term Memory) is a powerful algorithm for consecutive data, it was used to predict precipitation in this study. For the numerical test, we calculated the PWV (Precipitable Water Vapor) based on the tropospheric delay of the GNSS (Global Navigation Satellite System) signals, and then applied the deep learning technique to the precipitation prediction. The GNSS data was processed by scientific software with the troposphere model of Saastamoinen and the Niell mapping function. The RMSE (Root Mean Squared Error) of the precipitation prediction based on LSTM performs better than that of ANN (Artificial Neural Network). By adding GNSS-based PWV as a feature, the over-fitting that is a latent problem of deep learning was prevented considerably as discussed in this study.

• 패션비즈니스
• /
• 제26권1호
• /
• pp.105-118
• /
• 2022

This study investigated the effective pedagogical strategies for sewing by examining the efficacy of sewing videos as supplemental learning materials and demonstration tools. Sewing videos were created for face-to-face apparel construction courses, and students' opinions on sewing videos as an educational tool were collected. Videos with subtitles were offered to Apparel Construction Course 1, whereas videos with narration and subtitles were offered to Apparel Construction Course 2. As "supplemental learning materials," students rated videos as more effective for learning and satisfying than "documents with text and images." The effectiveness and satisfaction scores for Apparel Construction Course 2 were significantly higher than those for Apparel Construction Course 1. Furthermore, videos were utilized significantly more than documents, and most students preferred videos over documents. The main benefits of videos as supplemental learning materials were repetitive learning at the learner's convenience and the detailed presentation of the sewing process. Students regarded narration as more effective and satisfying than subtitles. Narrations were expected to be offered along with subtitles. As "demonstration tools," students rated videos as more effective for learning and satisfying than traditional "sewing samples." Students preferred "demonstration with videos" to "demonstration with sewing samples." The main benefits of video demonstration were a close-up view, presentation of the entire sewing process, and shorter wait time without the need for group teaching. Students wanted more sewing videos and narrations to be offered, and various sewing machine feet to be used in the videos. Educational methods for sewing were suggested based on student opinions.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.299-302
• /
• 1996

A control algorithm is proposed for nonlinear multi-input multi-output(MIMO) batch processes by combining quadratic iterative learning control(Q-ILC) with model predictive control(MPC). Both controls are designed based on output feedback and Kalman filter is incorporated for state estimation. Novelty of the proposed algorithm lies in the facts that, unlike feedback-only control, unknown sustained disturbances which are repeated over batches can be completely rejected and asymptotically perfect tracking is possible for zero random disturbance case even with uncertain process model.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.96-100
• /
• 2003

In this paper, a DLC method is proposed for linear feedback systems to improve the tracking performance when the task of the system is repetitive. DLC can generate the desired control input directly from the previously learned control inputs corresponding to other output trajectories. It is assumed that all the desired output functions considered in this paper have some relations called proportionality and it is shown by mathematical analysis that DLC can be utilized to generate additional control efforts for the perfect tracking. To show the validity and tracking performance of the proposed method, some simulations are performed for the tracking control of a linear system with a PI controller.

• 한국실내디자인학회논문집
• /
• 제14권2호
• /
• pp.206-216
• /
• 2005

The purpose of this study is a development of $teaching{\cdot}learning$ program based on interior design WBI. WBI's meaning is Web Based Instruction. There can be several procedures that should be designed at the first step: Analyzing, Designing, Building, Testing, Recycling. These stages are constructed based on the theory of procedure about the computer and the $teaching{\cdot}learning$. Each stage is presented the contents of development, the contents of main, the method advantages and problem solving. These procedures and contents of development are the research method simultaneously with the result. Upon the completion of the system, it should undergo the same process continuously so that it can improve over a period of time, contribute to the interior design of students. In addition continuously repetitive requirements pop up in the phase. And it is necessary for this program try to map out a strategy developing and a policy support from university. It's very important that develop the contents of interior design from professor, students and field professor.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.1039-1042
• /
• 1995

In real time application such as motion control, it is hard to find the application of non-causal filtering due to its need for future position data, even though it shows wide usage in off-line digital signal processing. Recently, some of motion control areas such as learning and repetitive control use non-causal filtering technique in their application. these kinds of zero-lag non-causal filter application are very usful not only to reduce the machine vibration, but also to increase control accuracy with comparatively less work. In this paper, genuine method to implement zero-lag non-causal filter in a CNC is introduced. Also the variation of this implementation for the learning operation is suggested to give the NC better control performance for a specific job. By adopting the new NC architecture call Soft-NC, all these implementions are made possible here, and especially large memory requirement which hinders their usage for many years is no longer barrier in their real world application.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.58-62
• /
• 1988

Recently many adaptive control schemes for the industrial robot manipulator have been developed. Especially, learning control utilizing the repetitive motion of robot and based on iterative signal synthesis attracts much interests. However, since most of these approaches excludes the boundness of the input torque supplied to the manipulator, its effectiveness may be limited and also the full dynamic capacity of the robot manipulator can not be utilized. To overcome the above-mentioned difficulties and meet the desired performance, we propose an approach which yields the effective learning control schemes in this paper. In this study, some stability conditions derived from applying the Lyapunov theory to the discrete linear time-varying dynamic system are established and also an optimization scheme considering the bounded input torque is introduced. These results are simulated on a digital computer using a three-joint revolute manipulator to show their effectiveness.

• 제어로봇시스템학회논문지
• /
• 제12권10호
• /
• pp.1029-1034
• /
• 2006

In this paper, the tracking control of an automatic pipe cutting robot, called APCROM, with a magnetic binder is studied. Using magnetic force APCROM, a wheeled robot, binds itself to the pipe and executes unmanned cutting process. The gravity effect on the movement of APCROM varies as it rotates around the pipe laid in the gravitational field. In addition to the varying gravity effect other types of nonlinear disturbances including backlash in the driving system and the slip between the wheels of APCROM and the pipe also cause degradation in the cutting process. To maintain a constant velocity and consistent cutting performance, the authors adopt a repetitive learning controller (MRLC), which learns the required effort to cancel the tracking errors. An angular-position estimation method based on the MEMS-type accelerometer is also used in conjunction with MRLC to compensate the tracking error caused by slip at the wheels. Experimental results verify the effectiveness of the proposed control scheme.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.357-366
• /
• 2022

Artificial intelligence (AI) is the replication of human intelligence by computer systems and machines using tools like machine learning, deep learning, expert systems, and natural language processing. AI can be applied in administrative settings to automate repetitive processes, analyze and forecast data, foster social communication skills among staff, reduce costs, and boost overall operational effectiveness. In order to understand how AI is being used for administrative duties in various organizations, this paper gives a critical dialogue on the topic and proposed a framework for using artificial intelligence in organizations. Additionally, it offers a list of specifications, attributes, and requirements that organizations planning to use AI should consider.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.146.2-146
• /
• 2001

Recently, a need of non-industrial robot, such as service, medical, entertainment and house-keeping robot, has been increased. Therefore, the capability of robot which can do intelligent behavior like interaction with men and its environment become more prominent than the capability of executing simple repetitive task. To implement an intelligent robot which provides intelligent behavior, an effective system architecture including perception, learning, reasoning and action part is necessary. Control architectures for intelligent robot can be divided into two different classes. One is deliberative type controller which is applicate to high level intelligence like environment ...