Traffic prediction device and traffic prediction method using SHAP algorithm-based clustering
The SHAP-based clustering approach in the traffic prediction device effectively identifies important features for IoT traffic, reducing computational load and enhancing prediction accuracy and adaptability.
KR102999124B1Active Publication Date: 2026-08-03RES & BUSINESS FOUND SUNGKYUNKWAN UNIV
4 Cites 0 Cited by
Patent Information
- Application Number
- KR1020230187550
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2023-12-20
- Publication Date
- 2026-08-03
- Estimated Expiration
- 2043-12-20
AI Technical Summary
Technical Problem
Existing traffic prediction technologies for IoT devices fail to accurately identify diverse and dynamic patterns, leading to increased computational load and inefficiency.
Method used
A traffic prediction device using a deep learning model with a SHAP algorithm for clustering, specifically employing a Temporal Convolution Network (TCN) to cluster data based on feature contributions, identifying and predicting unique IoT traffic patterns.
Benefits of technology
Enables accurate traffic prediction with reduced computational complexity and cost, allowing flexibility in adapting to diverse IoT environments.
✦ Generated by Eureka AI based on patent content.
Abstract
The present specification relates to a traffic prediction device using artificial intelligence. A traffic prediction device using clustering according to one embodiment includes a memory and a processor. The processor may be configured to acquire traffic data separated by time units from IoT devices deployed in multiple separated regions, extract the contribution to traffic prediction of each of the traffic data using an algorithm, cluster the traffic data based on the contribution, and train a Temporal Convolution Network (TCN) using the clustered traffic data.
Need to check novelty before this filing date? Find Prior Art