FOLLOW
17 Reviews   |   1002 Views   |   4 Followers

Machine Learning and its Feedback

Patent

WO2016078788A1

Owner

Freie Universität Berlin

Filing Date

August 28, 2015

Priority Date

November 17, 2014

Portfolio

Sensors - FU Berlin

Intro

This patent application uses machine learning to recognize movements of the human body. The patent owner is looking for commercialization partners.

Claims

1. To see the amended claims filed after receipt of (European) search report go to: https://register.epo.org/application?number=EP15767429&lng=en&...

To see the amended claims filed after receipt of (European) search report go to: https://register.epo.org/application?number=EP15767429&lng=en&tab=doclist

read more

Abstract

The invention regards a method and a feedback system for the assessment of motions of a versatile system that use a wireless sensor network attached t...
The invention regards a method and a feedback system for the assessment of motions of a versatile system that use a wireless sensor network attached to the versatile system. The method comprises a training phase and a feedback phase. In the training phase, a defined motion is conducted by the versatile system, whereby sensor data are gathered by the sensor nodes (31, 32, 33). After segmentation (202) of the sensor data into separate segments and the extracting (203) of features, a symbol is assigned to each of the motion fragments. A symbol sequence is formed which represents the complete motion conducted by the versatile system at a sensor node. After repeating at least once the conducting step and/or the analysing step, a reference symbol sequence (207) is formed at each sensor node (31, 32, 33). In the feedback phase, the defined motion is conducted again, and the collected sensor data are analyzed in a similar manner as in the training phase, wherein at each sensor node at least one motion fragment of the present motion is assessed (404) at least by comparing the symbol assigned to the motion fragment with a to be expected symbol of the reference symbol sequence. A feedback (405, 409, 410) is provided to the versatile system depending on the result of the assessment. The feedback refers to a motion fragment and may be provided while the motion is still carried out.
read more
Write Review

Here are the reviews from the crowd!

Rating categories
WOW!
GOTCHA!
DEAL!
Where should the donation go to?
Akcharris
September 17, 2018


Applications: In clinic Physical therapy, and medical.
Companies: Physical Theripest and medical professionals

LIKE       COMMENT


Bastian September 17, 2018

Thank you for your review, Akcharris! Just wondering why you are giving 1 to 2 light bulbs for this invention?


Workshop Passau July 9
July 11, 2018

The machine learning based sensor network can be used in various applications covering several unmet customer demands.
Applications: Training of dogs, emergency preparedness, professional sports
Companies: Government

LIKE       COMMENT


Workshop Dresden July 6
July 06, 2018

The sensor network can be used to track and improve health conditions, such as back pain. It can also be used to alert elderly people about movements that tend to result in falls or tripping.
Applications: Medical monitoring
Companies: Health insurance providers

LIKE       COMMENT


Workshop Dresden July 6
July 06, 2018

The sensor network could be used in animal farming applications. You could reinforce certain beneficial movements and limit harmful movements. Cow or pig farms come to mind.
Applications: Free range cattle control
Companies: Farm equipment companies, farmers

LIKE       COMMENT


Workshop Dresden July 6
July 06, 2018

The sensor network could be used to increase first aid skills in the general community. This application has the potential to save thousands of lives. Instead of having to go to a first aid class every few years (if at all), you could hone your skills at home or even just activate the application in case of a real emergency and get immediate feedback from the sensor network!
Applications: CPR
Companies: CPR device makers, health insurance providers

LIKE       COMMENT


Workshop Berlin May 23
May 23, 2018

This invention could be used to train surgeons. Although this may be a tiny market, this could have a huge effect. A young surgeon could train the system with an experienced surgeon. In the feedback phase, the young surgeon can recap the correct movement anywhere and anytime.

LIKE       COMMENT


Workshop Berlin May 23
May 23, 2018

The system could be used to improve your body language but also to prevent back pain and postural defects.

LIKE       COMMENT


Workshop Berlin May 23
May 23, 2018

Potential applications in skills: keyboard typing, handwriting, knitting, tying knots etc. Just imagine how pupils could train the sensors with their teachers and get feedback from the sensors at home while doing their homework!

LIKE       COMMENT


Workshop Berlin May 23
May 23, 2018

Potential applications in music (learn, master & apply): playing an instrument, singing, dancing, ballet & choreography.

LIKE       COMMENT


Workshop Berlin May 23
May 23, 2018

Perfect for smart toothbrushes: train the sensors together with your dentist and off you go.

LIKE       COMMENT


Workshop Munich May 14
May 22, 2018

Efficiency 2.0 - this invention can be used to train factory workforces. In the training phase, the foreman instructs the workers equipped with the sensors. In the feedback phase, the workers get haptic or kinesthetic responses from the sensor if their movements are outside the best mode of operation.

LIKE       COMMENT


Workshop Munich May 14
May 22, 2018

This invention has real market potential with golf players: a professional golf coach can train the sensor network taking into account the player's physique and movements. The golf player can then use the feedback system at home, in a hotel room or at the driving range to work on his swing.

LIKE       COMMENT


Workshop Munich 14 May
May 22, 2018

This invention relates to "a feedback system for the assessment of motions of a versatile system". Such a versatile system could also be a pet (think dog or a cat). Just imagine how you could help your cat or dog to recover from an injury: the sensor would be trained to give the cat or dog haptic responses if the cat or dog moves incorrectly. With LED lighting you could even observe if your pet's movements are correct (green lighting) or incorrect (red lighting).

LIKE       COMMENT


Workshop Munich 14 May
May 21, 2018

This invention could be used in shooting ranges of police academies. After a short training phase with a professional instructor, the machine learns the perfect positioning, drills and movements for the cadet. Afterwards, the cadet can rely on the invention's sensor network and feedback system to repeat precise and personally adapted exercises at the shooting range or even use it for dry runs at home.

LIKE       COMMENT


Bernd
April 16, 2018

This patent application could be a stepping stone for a heath insurance provider: either they invest to bring this technology to life or they could profit as soon as this system becomes common-place in a few years down the road.

LIKE       COMMENT


New Guy
April 11, 2018

The new patent claims (November 2017) require that the system provides feedback while the motion of the versatile system (read human) is still ongoing. This makes the invention very interesting: the system is able to warn the user about wrong movements right away.

LIKE       COMMENT


Sports Pro
April 10, 2018

This patent application has real potential. You can use the sensor network at home when you recover from an injury. More importantly, it is location independent: you can wear it in the gym when you work out, when you run & when you swim. I do hope that I can buy such a product soon!

LIKE       COMMENT


Show more

Rate the patent & write your own review!

Rating categories
WOW!
GOTCHA!
DEAL!
Where should our donation go to?
Your review
Write about potential applications
Write about potentially interested companies
Choose a name

Convinced about the patent? Contact us!

Your bid
Your e-mail
Your message