لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
یازدهمین کنفرانس بین المللی کنترل ، ابزار دقیق و اتوماسیون
FACTS : Feedback-Adaptive Learning for Cluster-Based Time Series Forecasting
نویسندگان :
Alireza Jahani
1
Ali Mehrabi
2
S. Ahmad Khalilpour
3
Hamed Seyedi
4
Hamid D. Taghirad
5
1- K.N. Toosi University of Technology Tehran, Iran
2- K.N. Toosi University of Technology Tehran, Iran
3- K.N. Toosi University of Technology Tehran, Iran
4- K.N. Toosi University of Technology Tehran, Iran
5- K.N. Toosi University of Technology Tehran, Iran
کلمات کلیدی :
time series forecasting،feedback error
چکیده :
Despite the emergence of global models as a solution, their inability to achieve optimal performance in time series forecasting remains a significant challenge. Clustering methods proposed in the literature to deal with these complications are ineffective when faced with complex and large datasets. This study introduces a robust solution based on feedback from the predictive model. In the proposed three-step algorithm, hidden relationships between time series are firstly extracted through feedback from a global model trained on the entire dataset. Then, using the created vector space, the dataset is clustered. Finally, an adaptive learning algorithm is employed to train a separate model on each cluster. The integration of the feedback mechanism in the proposed method enhances the clustering process, enabling it to capture patterns that are not only structurally and temporally similar but also exhibit similar forecasting behaviors. This, in turn, enhances the process of fitting a model to each cluster, boosting its effectiveness. The proposed model is assessed using a real-world dataset collected locally, showcasing its overall capability. Evaluation results show that the proposed model significantly reduces forecasting errors and eliminates the reliance on existing methods.
لیست مقالات
لیست مقالات بایگانی شده
Design of Tube model predictive controller to control human heart rate by treadmill velocity
Fatemeh Rahmati - Sama Nikanfar - Amirhossein Nikoofard
Dissipativity-based Stability Analysis of Power Networks with Uncertain Interconnections
Narges Rezaei Kookhdan - Hamid Reza Koofigar
A comparison study on the dynamic control of OpenMANIPULATOR-X by PD with gravity compensation tuned by oscillation damping based on the phase-trajectory-length concept
Amirhossein Dadbin - Ahmad Kalhor - Mehdi Tale Masouleh
Integrating Vision and Robotics: Automated Object Localization and Fault Detection with a 6-DoF Manipulator
Masoumeh Azadegan - Alaleh Vafaei
Wearable sensing smart solutions for workers' remote control in health-risk activities
Paolo Visconti - Roberto De Fazio - Ramiro Velazquez - Bassam Al-Naami - Amir Aminzadeh Ghavifekr
Optimal control based on reinforcement learning for a class of nonlinear singularly perturbed systems
Mohammad Saleh Rouhi - Roya Amjadifard
Improved Unscented Kalman Filter Algorithm to Increase the SLAM Accuracy
Hasan Enami Eraghi - Mohammadreza Taban - Sayed Farzad Bahreinian
A Model Reference Adaptive Control System for Phase- Locked Loop (PLL) in Grid-Connected Power Systems
Mostafa Khavaninzadeh - Ramin Nahavandi - Mjtaba Moeti
Application of NSGA-II in Channel Selection of Motor Imagery EEG Signals with Common Spatio-Spectral Patterns in BCI Systems
M. Moein Esfahani - Hossein Sadati
The Effect of Observer Position on Networked Control Systems with Random Transmission Delays and Packet Dropouts
Elaheh Mohammadi-Asl - Farzad Hashemzadeh - Mahdi Baradarannia - Peyman Bagheri
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.9.5