Traffic Management Apparatus Using Adaptive Thresholds for Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current traffic abnormality detection methods based on fixed threshold values often lead to errors, misclassifying normal traffic fluctuations as abnormal and vice versa, especially due to events like software updates or rapid changes in network traffic.
Innovation Solution
A traffic management apparatus that generates a traffic model using historical data to predict traffic patterns and detect abnormalities by comparing predicted values with actual measurements, enhancing detection precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If fixed threshold values are used for traffic abnormality detection, then the detection method is simple and easy to implement, but the detection accuracy deteriorates leading to false positives and negatives
Solution Approach 1:
The patent applies dynamics by transitioning from static fixed threshold values to dynamic adaptive thresholds. The system continuously learns historical traffic patterns and adjusts detection thresholds based on actual traffic conditions, enabling the detection mechanism to adapt to changing network environments while maintaining high accuracy in abnormality detection
Solution Approach 2:
The patent changes the parameter of detection thresholds from fixed constants to dynamically adjusted values based on learned traffic patterns. By modifying the threshold parameter adaptively according to historical data and current traffic conditions, the system resolves the contradiction between simple implementation and accurate detection
2Device complexity
If fixed threshold values are used for traffic abnormality detection, then the system structure remains simple, but detection precision deteriorates due to inability to distinguish normal fluctuations from actual abnormalities
Solution Approach 1:
The patent applies preliminary action by pre-learning historical traffic patterns and establishing baseline models before actual abnormality detection occurs. This preparatory phase enables the system to distinguish between normal traffic fluctuations and true abnormalities more effectively, improving detection precision without requiring complex real-time analysis
Solution Approach 2:
The patent introduces an intermediary learning model that mediates between raw traffic data and abnormality detection. This intermediate layer processes and interprets traffic patterns, enabling more precise detection while keeping the overall system architecture relatively simple and manageable
3Measurement precision
If historical data is used to generate predictive traffic models, then detection accuracy improves, but computational complexity and processing time increase
Solution Approach 1:
The patent applies partial action by focusing computational resources on learning and analyzing only the most relevant historical traffic patterns and features. Rather than processing all possible data, the system selectively learns key patterns that contribute most to detection accuracy, reducing computational complexity while maintaining high detection performance
Data Source
AI summary
There is provided a traffic management apparatus including a memory, and a processor coupled to the memory and the processor configured to select a base model based on history information stored in the memory so as to generate a traffic model, obtain a predicted value of the traffic according to the traffic model, and detect traffic abnormality based on the predicted value and an actual measurement value of the traffic.