IBT Sense Pattern Recognition

IBT Sense Feature Image

Sense, from Infinite Biomedical Technologies (IBT), is an impressive myoelectric pattern recognition system. It is not just the technology that impresses but also the training and support systems that IBT has put into place.

A Quick Look at the Sense Pattern Recognition System

The following video provides a brief glimpse of the Sense pattern recognition system:

Before reading further, a little background information may be helpful. To obtain this, please see our master article Myoelectric Pattern Recognition for Bionic Arms & Hands, which includes a basic description of how pattern recognition systems work.

As that article indicates, there are a few key areas crucial to the success of any myoelectric pattern recognition system. These are:

  • basic technology;
  • evaluation support;
  • setup & calibration;
  • training;
  • recalibration by the end-user;

We will examine Sense in each of these areas.

Basic Technology

There is a spectrum of pattern recognition technologies:

Pattern Recognition Spectrum

A simple system may use some form of pattern recognition or artificial intelligence to clean up myoelectric signals but it still relies on the user to explicitly contract certain muscles to control a bionic device. This is not a true pattern recognition system. True pattern recognition systems allow the user to attempt to move a bionic device in the desired manner, which then triggers a pattern of muscle movements. It is this pattern that is translated into bionic device commands, not the movement of specific muscles.

Universal systems offer true pattern recognition. They are called “universal” because they are capable of interfacing with many different types of bionic components, including elbow and wrist components.

IBT’s Sense is a universal system. It is meant to be used with 3-8 sensors and can be combined with bionic components from different manufacturers to form an overall solution.

Because Sense must support the functionality common to these components, it does not attempt to match the advanced capabilities of some of the more experimental pattern recognition systems on the horizon, which may allow spontaneous control over individual bionic finger movements.

Instead, Sense supports the movements allowed by whatever components it is attempting to control.

How does Sense do this? Let’s walk you through the typical chronology of its evaluation, configuration, and subsequent use.

Evaluation Support

The first step for a prospective user is to evaluate whether he can benefit from Sense.

IBT supports this by providing loaner kits to prosthetists. These kits contain sensors, a control system, and software that allow prosthetists to test the suitability of prospective Sense users without having to fabricate complete physical test systems. Prosthetists can temporarily apply the sensors to a user’s residual limb and then use Sense’s calibration and training software to test the solution virtually.

There is no difference in the software setup, calibration, and training of a virtual user versus one who has an actual bionic prosthesis.

Setup & Calibration

We’re not going to cover the physical setup of Sense here. The prosthetist will take care of that. We’re going to start at the point where the physical setup is complete and the prosthetist is ready to use the software with a specific user.

Although this video was created for prosthetists, we urge end-users to watch it to get a better understanding of Sense’s capabilities:

The key takeaways from this video are:

  • The prosthetist has precise control over which sensors are used to detect specific patterns and which patterns are paired with specific movements by a bionic component.
  • The available actions for each bionic component are dictated by the components themselves (e.g. a TASKA hand will have different grip patterns than an i-Limb).
  • The pattern correlating to each movement can have multiple variations based on arm position. This helps address one of the main problems with any myoelectric device — that different arm positions can degrade signal detection.
  • Though not shown in the video, prosthetists can also change the sensitivity of myoelectric sensors and the speed at which the bionic hand or joint moves in response to commands.

TRAINING

IBT places a great deal of emphasis on user training. Because of this, they provide an excellent virtual, game-based training software called MyoTrain, as shown in this video:

What can we say about this software? It seems incredibly thorough and valuable to both the prosthetist and the end-user. However, as with most things, the more that you put into it, the more you will get out of it.

RECALIBRATION

After you have gone through an evaluation, had a socket built by your prosthetist, completed your training, and taken delivery of your complete bionic arm solution, you should be finished with Sense calibration, right?

Wrong. One of the challenges of myoelectric control systems, especially those dependent on skin-surface sensors, is that the state of a user’s residual limb is not constant. It can change with things like temperature (swells when hot, shrinks when cold), humidity (skin sweat), and muscle fatigue.

When this happens, users need the ability to quickly recalibrate their Sense system:

This type of user ability to adjust “on the fly” is critical to the success of any myoelectric pattern recognition system.

Note, however, that his recalibration process is not as convenient as Coapt Gen2‘s push-button recalibration for some situations.

User Feedback Survey & Results

Are you or have you previously been an IBT Sense user? If so, please share your insights with others looking at Sense as a possible pattern recognition system.

Survey

Results

We do not yet have a sufficient number of survey participants to publish fair and accurate results for the IBT Sense system.

As soon as we do, we’ll update this section.

Considerations Before Buying IBT’s Sense

Without sufficient feedback from independent users, we’re not yet able to form a complete opinion about IBT Sense.

However, we can say that IBT has checked all the boxes when it comes to delivering a complete myoelectric pattern recognition system.

Additionally, we can tell you that their staff have been exceptionally open and helpful with us in putting together this article. To us, that has been a consistent sign of a good company.

So, if you are shopping for this type of pattern recognition system, we believe that IBT Sense should at least go on your shortlist.

The real question for prospective users is whether to opt for proven pattern recognition systems like Sense, Coapt’s Gen2, or Ottobock’s Myo Plus now, or to wait to see if some of the advanced/experimental systems for the new devices coming from Atom Limbs, BrainRobotics, and Esper Bionics pan out.

As it stands now, it will likely be 2022 before those new devices get to market and another year or two after that before we get sufficient user feedback to know if they have delivered on their promises.

In other words, a lot of this will come down to each prospective user’s purchase window and risk tolerance.

Related Information

If you are considering a dual-site, direct-control myoelectric system, do not miss our article on Finding the Right Myoelectric Control System.

For a comprehensive description of all current upper-limb technologies, devices, and research, see A Complete Guide to Bionic Arms & Hands.

Click here for more information on Infinite Biomedical Technologies.