Artificial intelligence capsule positioning system
An artificial intelligence capsule positioning system is provided. An artificial intelligence capsule positioner of the artificial intelligence capsule positioning system collects multiple pieces of measured data related to a capsule. The multiple pieces of measured data include a direction vector and a spatial coordinate of the capsule, frequencies and strengths of signals transmitted by a signal transmitter on the capsule, and strengths of the signals received by antennas. The artificial intelligence capsule positioner uses an artificial intelligence machine learning algorithm to learn the multiple pieces of measured data from a database to analyze rules for how a position of the capsule changes with the multiple pieces of measured data to establish a training model. When a new capsule flows in a human body, the artificial intelligence capsule positioner uses the training model to position the new capsule.
1 . An artificial intelligence capsule positioning system, comprising:
a signal transmitter disposed on a capsule, and configured to transmit a plurality of capsule signals when the capsule is placed into and flows in a body of a test subject;
a plurality of signal receivers being wirelessly connected to the signal transmitter, and configured to wirelessly receive the plurality of capsule signals from the signal transmitter; and
an artificial intelligence capsule positioner being wirelessly connected to the plurality of signal receivers, including:
a data collecting unit including at least one sensor configured to establish a database and to collect multiple pieces of measured data associated with the capsule to the database, wherein the multiple pieces of measured data include a direction vector and a spatial coordinate of the capsule on which the signal transmitter transmits each of the plurality of capsule signals, a frequency and a strength of each of the plurality of capsule signals transmitted by the signal transmitter, and the strength of each of the plurality of capsule signals respectively received by the plurality of signal receivers;
a training model establisher connected to the data collecting unit, configured to use an artificial intelligence machine learning algorithm to learn the multiple pieces of measured data from the database, and configured to analyze rules for how a position of the capsule changes with the multiple pieces of measured data, so as to establish a training model; and
a capsule positioner connected to the training model establisher, and configured to use the training model to instantly position the capsule flowing in a human body to obtain a position of the capsule in the human body,
wherein an error gain calculator is configured to substitute the position of the capsule that is positioned by the capsule positioner using the training model at a current time point, an estimated position of the capsule at the current time point and an estimated position of the capsule at a previous time point into following equation to calculate a gain:
S
=
K
×
Z
+
(
1
-
K
)
×
X
,
wherein S represents the estimated position of the capsule at the current time point, K represents the gain, Z represents the position of the capsule that is positioned at the current time point by the capsule positioner using the training model, and X represents the estimated position of the capsule at the previous time point.
2 . The artificial intelligence capsule positioning system according to claim 1 , wherein the artificial intelligence capsule positioner further includes:
a capsule flowing speed calculator connected to the capsule positioner, and configured to calculate a flow speed of the capsule in the human body according to a length of time that the capsule is placed into the human body and the position of the capsule in the human body from the capsule positioner.
3 . The artificial intelligence capsule positioning system according to claim 1 , wherein the artificial intelligence capsule positioner further includes:
the error gain calculator connected to the capsule positioner, and further configured to determine a ratio relationship between the estimated position of the capsule at the current time point and the position of the capsule that is positioned by the capsule positioner using the training model to calculate the gain.
4 . The artificial intelligence capsule positioning system according to claim 3 , wherein the training model establisher is connected to the error gain calculator, and configured to determine whether or not the training model is to be retrained according to the gain calculated by the error gain calculator.
5 . The artificial intelligence capsule positioning system according to claim 1 , wherein the plurality of signal receivers respectively receive the plurality of capsule signals via BLUETOOTH wireless transmission.
6 . The artificial intelligence capsule positioning system according to claim 1 , wherein the multiple pieces of measured data of the database further include data of a broadcast channel through which each of the plurality of capsule signals is transmitted by the signal transmitter.
7 . The artificial intelligence capsule positioning system according to claim 6 , wherein the broadcast channel includes a BLUETOOTH broadcast channel.
8 . The artificial intelligence capsule positioning system according to claim 1 , wherein each of the plurality of signal receivers includes one or more antennas.