18504214. APPARATUS FOR NON-DETERMINISTIC FUTURE STATE PREDICTION USING TIME SERIES DATA AND OPERATION METHOD THEREOF simplified abstract (ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE)
APPARATUS FOR NON-DETERMINISTIC FUTURE STATE PREDICTION USING TIME SERIES DATA AND OPERATION METHOD THEREOF
Organization Name
ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
Inventor(s)
APPARATUS FOR NON-DETERMINISTIC FUTURE STATE PREDICTION USING TIME SERIES DATA AND OPERATION METHOD THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 18504214 titled 'APPARATUS FOR NON-DETERMINISTIC FUTURE STATE PREDICTION USING TIME SERIES DATA AND OPERATION METHOD THEREOF
The patent application describes an apparatus that includes a preprocessor and a learner to predict future states of time series data.
- The preprocessor generates raw data, preprocesses it into time series data, and further preprocesses it into learning data.
- The learner uses the preprocessed learning data to train a prediction model that increases the similarity between predicted future states within the same cluster and decreases the similarity between predicted future states in different clusters.
- The prediction model is a machine learning model for predicting future states of time series data at any time point.
Potential Applications: - Predictive maintenance in industrial machinery - Forecasting stock prices in financial markets - Predicting patient outcomes in healthcare settings
Problems Solved: - Improving accuracy of future state predictions - Enhancing clustering of similar data points - Optimizing machine learning models for time series data
Benefits: - Increased efficiency in decision-making processes - Enhanced predictive capabilities for various industries - Improved resource allocation based on future state predictions
Commercial Applications: Title: "Enhanced Predictive Modeling for Time Series Data" This technology can be utilized in industries such as manufacturing, finance, and healthcare to improve forecasting accuracy and optimize operations.
Prior Art: Researchers have explored similar approaches in predictive modeling for time series data, focusing on clustering techniques and machine learning algorithms.
Frequently Updated Research: Ongoing research in machine learning and time series analysis continues to refine predictive modeling techniques for various applications.
Questions about Enhanced Predictive Modeling for Time Series Data: 1. How does this technology compare to traditional forecasting methods? 2. What are the key challenges in implementing this predictive modeling approach in real-world scenarios?
Original Abstract Submitted
Disclosed is an apparatus, which includes a preprocessor that generates raw data, generates preprocessed time series data, and generates preprocessed learning data, and a learner that receives the preprocessed learning data as input data and trains a prediction model such that the similarity between a first future state predicted using the input data and a second future state predicted using data included in the same cluster as the input data increases and such that the similarity between the first future state and a third future state predicted using data included in a different cluster from the input data decreases, and the prediction model is a machine learning model for predicting a future state of the time series data at an arbitrary time point.
