Menü
“We use a combination of computer vision and supervised machine learning techniques to analyze the quality of movements and identify musculoskeletal imbalances. Thereby, the feedback from our users and experts is used to make the artificial intelligence more and more precise.”
Prof. Dr. Welf Löwe
Chief Research Officer
The largest movement deviation isn't necessarily where you are having pain, but where an imbalance has been detected.
Movement deviations can be caused by an unequal use of certain muscle groups. It's not about having a stronger and a weaker side of your body. It's about an unequal response between those muscle groups that work together in a movement.
An imbalance occurs when one muscle group is over-activated while the other remains under-active.
Ideal Score
If you achieve a score of 100%, your movement does not deviate from the golden standard which represents an ideal movement performance.
Average
The average marker shows how you compare to all other AIMO users.
Low Score
A low score means that your movement performance deviates significantly from the golden movement standard.
[1] Basics for the automated assessment of insufficiencies of the musculoskeletal system
Dressler D., Liapota P, Löwe W. Towards an Automated Assessment of Musculoskeletal Insufficiencies. In: Czarnowski I., Howlett R., Jain L. (eds) Intelligent Decision Technologies 2019. Smart Innovation, Systems and Technologies, 2019. Singapore. Springer; 2019 vol. 142 p. 251-61. Doi: 10.1007/978-981-13-8311-3_22
[2] Data-supported automated assessment of insufficiencies of the musculoskeletal system
Dressler D, Liapota P, Löwe W. Data Driven Human Movement Assessment. In: Czarnowski I, Howlett R, Jain L (eds.). Proceedings of the 11th KES International Conference on Intelligent Decision Technologies (IDT): Smart Innovation, Systems and Technologies Series. Singapore. Springer: 2019 vol. 143. doi: 10.1007/978-981-13-8303- 8_29
[3] The effect of choosing different machine learning approaches on the assessment of human movements
Hagelbäck J, Liapota P, Lincke A, Löwe W. The Performance of some Machine Learning Approaches in Human Movement Assessment. In: Macedo M, Rodrigues L (eds.). Proceedings of the 13th Multi Conference on Computer Science and Information systems (MCCSIS). Porto, Portugal. IADIS Press; 2019 p. 35-42. ISBN: 978-989-8533-89-0
[4] Varianten der dynamischen Zeitphasenanpassung (Time Warping) und ihr Effekt auf die Beurteilung menschlicher Bewegungen
Hagelbäck, J., P. Liapota, A. Lincke and W. Löwe (2019b). Variants of Dynamic Time Warping and their Performance in Human Movement Assessment. The 21st Int’l Conf on Artificial Intelligence co-located with The 2019 World Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE’19). Las Vegas, Nevada, USA.
[5] Introduction of quality models based on multidimensional probabilities; mathematical foundations for the Aimo™–Score
Ulan, M., W. Löwe, M. Ericsson and A. Wingkvist (2018a). Introducing quality models based on joint probabilities. 40th International Conference on Software Engineering: Companion Proceedings, ICSE 2018, Gothenburg, Sweden: pp 216-217.
[6] Interactive visualization of score calculation models based on multidimensional probability distribution; mathematical foundations for the Aimo™–Score
Ulan, M., S. Hönel, R. M. Martins, M. Ericsson, W. Löwe, A. Wingkvist and A. Kerren (2018b). Quality Models Inside Out: Interactive Visualization of Software Metrics by Means of Joint Probabilities. 2018 IEEE Working Conference on Software Visualization (VISSOFT): pp 65-75.
[7] For the compatibility of different 3D camera technologies
Hagelbäck, J., A. Lincke, W. Löwe and E. Rall (2019c). On the Agreement of Commodity 3D Cameras. The 23rd Int’l Conference on Image Processing, Computer Vision, and Pattern Recognition co-located with The 2019 World Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE’19). Las Vegas, Nevada, USA.
[8] Application of the Aimo™–Score in elderly care
Backåberg, Sofia, Amanda Hellström, Cecilia Fagerström, Anders Halling, Alisa Lincke, Welf Löwe and Mirjam Ekstedt (2020). Evaluation of the skeleton avatar technique for easy assessment of mobility and balance among older adults. Frontiers in Computer Science, section Digital Public Health; 12/2020
[9] Advanced quality models based on multidimensional probabilities; mathematical foundations for the Aimo™–Score
Ulan, M., W. Löwe, M. Ericsson and A. Wingkvist (2021). Copula-based Software Metrics Aggregation. Software Quality Journal (Springer), 8/2021
[10] Pre-processing of motion captures for visualization and Aimo™ scoring
Gauss, Joela, Ch. Brandin, A. Heberle and W. Löwe (2021). Smoothing Skeleton Avatar Videos using Signal Processing Technology. Springer Nature Computer Science, 2(429)
[11] Weighted quality models based on multidimensional probabilities; mathematical foundations for the Aimo™–Score
Ulan, M., W. Löwe, M. Ericsson and A. Wingkvist (2021). Weighted Software Quality Scoring and its Application to Defect Prediction. Empirical Software Engineering (Springer), 26(86)
[12] Application of the Aimo™ score as a measurement tool for physical activity in older people
Alisa Lincke, Cecilia Fagerström, Mirjam Ekstedt, Welf Löwe, and Sofia Backåerg (2021). Skeleton avatar technology as a way to measure physical activity in healthy older adults, Informatics in Medicine Unlocked (Elsevier), 24(100609)