3D Joint Motion Assessment for Accurate Cognitive Classification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing cognitive function evaluation systems are low in accuracy due to relying on limited features for estimation.

Innovation Solution

A cognitive function evaluation system that includes a motion detector, answer detector, and evaluator, capturing three-dimensional joint coordinates and cognitive task answers to generate spatial and temporal motion features, and classifies cognitive function into predefined classes using a neural network optimized for sensitivity and specificity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If limited features are used for cognitive function estimation, then the evaluation system is simple, but the accuracy is low

Engineering Contradiction:
Improvecognitive function evaluation accuracyVSAvoidevaluation system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The evaluation system segments the cognitive function assessment into multiple independent measurement modules: motion detection module capturing spatial and temporal joint coordinates, answer detection module capturing cognitive task responses, and feature extraction module processing both types of data. This segmentation allows comprehensive data collection while maintaining modular system architecture that manages complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from traditional single-dimension cognitive assessment to multi-dimensional evaluation by incorporating both motion data (spatial coordinates, temporal variations, joint angles) and cognitive task data (answers, response time). This dimensional expansion enables the neural network to process rich, multi-aspect information for accurate cognitive function classification.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If multiple features are collected from motion and cognitive tasks, then the cognitive function evaluation accuracy is improved, but the data processing complexity increases

Engineering Contradiction:
Improvecognitive function evaluation accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system introduces an intermediary feature extraction module that acts as a mediator between raw data collection and cognitive function evaluation. This module processes motion data (joint coordinates, spatial relationships, temporal variations) and cognitive data (answers, response patterns) into meaningful features, reducing processing complexity while maintaining evaluation accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms raw measurement data into standardized feature parameters through parameter change operations. Motion coordinates are converted to spatial and temporal features, cognitive responses are transformed into performance metrics. This parameter transformation simplifies the data structure for the neural network while preserving the essential information for accurate cognitive function assessment.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If a neural network is used to classify cognitive function into multiple classes, then the evaluation precision is improved, but the computational resources required increase

Engineering Contradiction:
Improvecognitive function classification precisionVSAvoidcomputational resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary feature extraction and data preprocessing before feeding data to the neural network. By preparing and optimizing features in advance (extracting spatial relationships, temporal variations, motion patterns), the neural network receives pre-processed data that reduces computational burden during classification while maintaining high precision for multi-class cognitive function evaluation.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4424241B1Cognitive function assessment system and training method
Publication Date: 2026.04.22 OSAKA UNIVERSITY
  • EP4424241B1 patent drawingFigure 1
  • EP4424241B1 patent drawingFigure 2A~2D
  • EP4424241B1 patent drawingFigure 3~4

AI summary

Cognitive function evaluation system (100) includes motion detector (20), answer detector (30), and evaluator (40). Motion detector (20) generates frames representing three-dimensional coordinates of joints of subject (SJ) who is performing a predetermined task. The frames are a series of frames generated in time order. Answer detector (30) detects answers to questions on a predetermined cognitive examination by subject (SJ) performing the predetermined task. Evaluator (40) outputs motion features based on the frames and evaluates a cognitive function of subject (SJ) based on the motion features and the answers by subject (SJ). The motion features represent a feature of a spatial positional relationship and a feature of temporal variations, of the joints of subject (SJ) whose images have been captured. The predetermined task includes a physical task that requires subject (SJ) to perform a predetermined behavior, and a cognitive task that requires subject (SJ) to answer questions on a cognitive examination. Motion detector (20) captures the images of subject (SJ) performing the physical task to generate the frames.