Started from the study of

Aerospace Medicine

Human motion and the distinct characteristics in its movements are a result of an interaction between the body and constant gravity.


As human motion is closely related to the brain, a deterioration in brain results in impairment of human motion. It’s difficult to detect the deterioration visually nor are we able to measure how far the deterioration is from the norm.

MOTIONCORE was initially developed to create a solution that support the diagnoses of Parkinson’s disease by detecting and analyzing dynamic characteristics of human motion.

We have acquired Orthopedics, Otorhinolaryngology, Neurology, and Cardiology patient’s motion data, 15,000 healthy and 15,000 diagnosed and labeled by medical doctors, and approved by the IRB (Institutional Review Board) to create a mathematical model of human motion. Then, using simulation based AI we were able to quantify and standardize motion data for different health conditions.

Key Competencies of MOTIONCORE Analytics Include

Data Capture and Sensor Fusion

Gait motion analytics requires advanced sensor fusion technology to capture precise and accurate data related to human movement. This involves wearable sensors, motion capture systems, and specialized footwear that can capture various parameters.

Signal Processing and Data Analysis

Gait motion analytics involves processing large volumes of data collected from sensors and transforming it into meaningful information. This requires advanced signal processing techniques, data visualization, and statistical analysis to extract relevant features, identify patterns, and detect anomalies or deviations from the norm.

Biomechanical-Computational Neuroscience Expertise

Analyzing gait patterns as manifestations of normal brain activity requires a deep understanding of human anatomy, physiology, biomechanics, neuroscience, and mathematics. This expertise allows for the identification and interpretation of specific gait parameters, assessing their significance, and recognizing information distance from normal patterns that may indicate underlying health conditions or potential risks.

Simulation and Artificial Intelligence

Gait motion analytics can benefit from the application of simulation and artificial intelligence (AI) algorithms. These techniques can assist in automating the analysis process, improving accuracy, and enabling predictive modeling for personalized clinical support and health assessments. Unlike the image-based AI where massive data set is required to create each model, simulation- based AI deals with mathematical models, biomechanical simulations which is a machine learning process guided by real-time motion feedback. In other words, our AI process is way more efficient than the image-based AI.

Clinical Integration with real-time Decision Support

Gait motion analytics should be designed to integrate seamlessly into clinical workflows and decision-making processes. The core competency lies in providing healthcare professionals with actionable insights and do it in real-time. In addition to clinical applications, our expertise in human motion analysis extends to the realm of health assessment. By capturing and interpreting an individual's movement patterns, we can uncover subtle indicators of overall health and well-being. Our solutions go beyond traditional assessments by providing a holistic view of an individual's physical fitness, helping them optimize their performance, prevent injuries, and achieve their wellness goals.

fundamental image

Business Conventions and Technology Transfer

Busan Metropolitan City

Health Data Clinical Support Project Official IRB Registered for 30,000 persons (18-89 yrs.)

Ministry of Culture, Sports and Tourism

Development of Physical Factors for the Elderly Official IRB Registered for 1,800 seniors

National Institute for Mathematical Sciences

Deriving Mathematical Equations for Healthy and Non-Healthy people

Agency for Defense Development

Development of Computational Brain Science Model Based on Virtualized Learning Model


Journal of NeuroEngineering and Rehabilitation (2018)

Validity of shoe-type inertial measurement units for Parkinson’s disease patients during treadmill walking • Real-time ultra-precise medical analysis

PLOS ONE (2019)

Quantitative analysis of the bilateral coordination and gait asymmetry using inertial measurement unit-based gait analysis • Real-time human motion characteristics extraction

npj parkinson’s disease (2021)

The effect of levodopa on bilateral coordination and gait asymmetry in Parkinson’s disease using inertial sensor • Real-time analysis of Parkinson’s Disease medicine effects

The main papers out of 23 published papers (Include AI-related)