Method and system for shipping container loading and unloading estimation

1. A method at a computing device, the method comprising:

receiving, at the computing device, sensor data for a vehicle providing vibration frequency and magnitude for a plurality of tests, along with a loading status for the sensor data for each of the plurality of tests;

calculating an energy (E L ) for a low frequency passband and calculating an energy (E H ) for a high frequency passband of a bandpass filter pair for each of the plurality of tests;

finding an energy ratio based on the energy for the low frequency passband and the energy for the high frequency passband for each of the plurality of tests, wherein the energy ratio (eRatio) comprises:

eRatio

=

E

L

E

L

+

E

H

;

deriving weighting constants for a type of chassis of a vehicle; and

sending the weighting constants to a sensor apparatus at the vehicle for finding whether the vehicle is loaded or unloaded.

2. The method of claim 1 , further comprising repeating the calculating and finding for a plurality of bandpass filter pairs.

3. The method of claim 1 , wherein the deriving comprises applying a machine learning algorithm to E L and E H and the energy ratio, along with a known loading status, for each of the plurality of tests.

4. The method of claim 3 , wherein the machine learning algorithm is a minimum-mean squared error algorithm.

5. The method of claim 4 , wherein E L , E H and the energy ratio, along with the known loading status, for each of the plurality of tests, are represented as

y n =w 0 +w 1 x n1 +w 2 x n2 +. . . +w j x nj

and wherein the plurality of equations may be solved for:

y

=

Xw

⁢

where

⁢

X

=

[

1

…

x

1

⁢

j

⋮

⋱

⋮

1

…

x

n

⁢

j

]

⁢

and

⁢

y

=

[

y

1

y

2

…

y

n

]

T

⁢

and

⁢

w

=

[

w

1

w

2

…

w

j

]

T

.

6. The method of claim 3 , wherein the machine learning algorithm is a support-vector machine algorithm.

7. The method of claim 1 , wherein sensor data for each of the plurality of tests is filtered through multiple bandpass filter pairs, and wherein weighting coefficients are derived for an energy (E k,L ) for low frequency passband, an energy (E k,H ) for a high frequency passband, and an energy ratio of each bandpass filter pair (k).

8. The method of claim 1 , wherein the computing device is a server remote from the vehicle.

9. A computing device comprising:

a processor; and

a communications subsystem,

wherein the computing device is configured to:

receive sensor data for a vehicle providing vibration frequency and magnitude for a plurality of tests, along with a loading status for the sensor data for each of the plurality of tests;

calculate an energy (E L ) for a low frequency passband and calculating an energy (E H ) for a high frequency passband of a bandpass filter pair for each of the plurality of tests;

find an energy ratio based on the energy for the low frequency passband and the energy for the high frequency passband for each of the plurality of tests, wherein the energy ratio (eRatio) comprises:

eRatio

⁢

=

E

L

E

L

+

E

H

;

derive weighting constants for a type of chassis of a vehicle; and

send the weighting constants to a sensor apparatus at the vehicle for finding whether the vehicle is loaded or unloaded.

10. The computing device of claim 9 , wherein the computing device is further configured to repeat the calculating and finding for a plurality of bandpass filter pairs.

11. The computing device of claim 9 , wherein the computing device is configured to derive by applying a machine learning algorithm to E L and E H and the energy ratio, along with a known loading status, for each of the plurality of tests.

12. The computing device of claim 11 , wherein the machine learning algorithm is a minimum-mean squared error algorithm.

13. The computing device of claim 12 , wherein E L , E H and the energy ratio, along with the known loading status, for each of the plurality of tests, are represented as

y n =w 0 +w 1 x n1 +w 2 x n2 +. . . +w j x nj

and wherein the plurality of equations may be solved for:

y

=

Xw

⁢

where

⁢

X

=

[

1

…

x

1

⁢

j

⋮

⋱

⋮

1

…

x

nj

]

⁢

and

⁢

y

=

[

y

1

y

2

…

y

n

]

T

⁢

and

⁢

w

=

[

w

1

w

2

…

w

j

]

T

.

14. The computing device of claim 11 , wherein the machine learning algorithm is a support-vector machine algorithm.

15. The computing device of claim 9 , wherein sensor data for each of the plurality of tests is filtered through multiple bandpass filter pairs, and wherein weighting coefficients are derived for an energy (E k,L ) for low frequency passband, an energy (E k,H ) for a high frequency passband, and an energy ratio of each bandpass filter pair (k).

16. The computing device of claim 9 , wherein the computing device is a server remote from the vehicle.

17. A non-transitory computer readable medium for storing instruction code, which, when executed by a processor on a computing device cause the computing device to:

receive sensor data for a vehicle providing vibration frequency and magnitude for a plurality of tests, along with a loading status for the sensor data for each of the plurality of tests;

calculate an energy (E L ) for a low frequency passband and calculating an energy (E H ) for a high frequency passband of a bandpass filter pair for each of the plurality of tests;

find an energy ratio based on the energy for the low frequency passband and the energy for the high frequency passband for each of the plurality of tests, wherein the energy ratio (eRatio) comprises:

eRatio

=

E

L

E

L

+

E

H

;

derive weighting constants for a type of chassis of a vehicle; and

send the weighting constants to a sensor apparatus at the vehicle for finding whether the vehicle is loaded or unloaded.