Abnormal Event Analysis Using LBSN Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormal event detection techniques face challenges in balancing sensitivity, leading to false positives and false negatives, particularly when dealing with diverse situations and conditions, and require appropriate threshold definitions.
Innovation Solution
The method employs location-based social network (LBSN) data to contextualize abnormal events by detecting occurrences, analyzing LBSN data to identify linked events, and associating them with abnormal events, thereby improving anomaly detection and classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional threshold-based detection is used, then detection simplicity is maintained, but detection accuracy deteriorates due to false positives and false negatives
Solution Approach 1:
The patent introduces LBSN data as an intermediary element that mediates between the abnormal event detection system and the context information. This intermediary data source provides additional contextual cues (social media posts, check-ins, photos) that help distinguish true anomalies from false positives, thereby improving detection accuracy without requiring complex threshold tuning mechanisms
Solution Approach 2:
The system implements feedback by using LBSN data to validate and contextualize detected anomalies. The social media data provides real-time feedback about actual conditions at the location, allowing the system to confirm or reject detected anomalies based on contextual evidence from the social network, thus reducing false positives and negatives
2Reliability
If high sensitivity detection is applied, then false negatives are reduced, but false positives increase
Solution Approach 1:
LBSN data serves as an intermediary validation layer that filters high-sensitivity detection results. Social media posts, user check-ins, and location data provide contextual evidence to verify whether detected anomalies are genuine, allowing the system to maintain high sensitivity while reducing false positives through social context verification
Solution Approach 2:
The patent adds another dimension of validation by incorporating social media data alongside traditional detection methods. This additional dimension (social context) provides a new perspective for verifying anomalies, transforming the detection process from single-dimensional threshold checking to multi-dimensional contextual analysis, thereby reducing false positives
3Measurement precision
If context information is added to improve understanding, then detection accuracy improves, but data processing complexity increases
Solution Approach 1:
The system leverages the multi-functionality of LBSN data, which simultaneously provides location information, temporal context, social activity patterns, and user-generated content. This universal data source serves multiple purposes: validating anomalies, providing context for classification, and enabling trend analysis, thereby improving classification accuracy without requiring separate specialized data collection systems for each function
Data Source
AI summary
An embodiment for contextualizing abnormal events which employ location-based social networks, LBSN, data to determine events that may be linked to the abnormal events is provided. The embodiment may include detecting an occurrence of an abnormal event within a geographic region, wherein the abnormal event occurs at an occurrence time. The embodiment may also include obtaining location-based social networks, LBSN, data relating to the geographic region for a time period including the occurrence time. The embodiment may further include analyzing the obtained LBSN data, wherein the analyzation determines a linked event within the geographic region for the time period. The embodiment may also include associating the linked event with the abnormal event.