Pest detector to identify a type of pest using machine learning

1. A detector comprising:

one or more sensors;

one or more external indicators;

one or more processors; and

one or more non-transitory computer-readable media to store instructions executable by the one or more processors to perform operations comprising:

receiving sensor data from a first sensor of the one or more sensors;

determining, by a machine learning algorithm, that the sensor data indicates a presence of a pest;

sending a notification message to a computing device, the notification message including at least a portion of the sensor data; and

visually indicating, using a pest detected indicator of the one or more external indicators that the pest was detected;

a sensor plugin comprising:

an additional sensor; and

a plug to mate with a receptacle in a housing of the detector, the plug to provide:

a mechanical linkage between the sensor plugin and the detector; and

an electrical linkage to carry additional sensor data from the additional sensor to the one or more processors in the detector.

2. The detector of claim 1 , the operations further comprising:

detecting, by a motion sensor, movement associated with the pest; and

capturing, by an imaging sensor of the detector, one or more digital images of the pest, wherein:

the first sensor comprises the motion sensor and the additional sensor comprises the imaging sensor; or

the first sensor comprises the imaging sensor and the additional sensor comprises the motion sensor.

3. The detector of claim 1 , the operations further comprising:

detecting, using a wireless networking protocol, a presence of one or more additional detectors; and

creating a mesh network with the one or more additional detectors, wherein the detector uses the mesh network to communicate with at least one of a computing device or a server that is wirelessly connected to the detector.

4. The detector of claim 1 , the operations further comprising:

receiving ambient light data from an ambient light sensor of the detector;

determining that the ambient light data satisfies a predetermined threshold; and

transitioning the detector from an active mode to a low-power mode.

5. The detector of claim 1 , wherein indicating that the pest was detected comprises at least one of:

visually indicating, using an external indicator light of the detector, that the pest was detected; or

causing an indicator to be displayed on a software application executing on a computing device that is wirelessly connected to the detector, wherein the computing device comprises one of a smartphone, a tablet, or a virtual assistant enabled device.

6. The detector of claim 1 , wherein the one or more external indicators comprise one or more of:

a power indicator to indicate that the detector is either powered on or powered off;

a mode indicator to indicate that the detector is either in a low power mode or in a pest detection mode;

a network connection status indicator to indicate that the detector is either connected to a wireless network or not connected to the wireless network; and

a pest detected status indicator to indicate that the detector has detected the pest or has not detected the pest.

7. The detector of claim 1 , the operations further comprising:

comparing the sensor data with previously stored sensor data; and

determining a number of pests detected by the detector.

8. A detector comprising:

one or more sensors;

a sensor plugin comprising:

a plugin housing that includes an additional sensor of the one or more sensors;

a plug to mate with a receptacle in a housing of the detector; and

a telescoping extender that is extendable to position the additional sensor at a particular distance from the detector;

one or more external indicators;

one or more processors; and

one or more non-transitory computer readable media storing instructions executable by the one or more processors to perform operations comprising:

receiving sensor data from the one or more sensors;

determining, by a machine learning algorithm, that the sensor data indicates a presence of a pest;

sending a notification message to a computing device, the notification message including at least a portion of the sensor data; and

visually indicating, using a pest indicator of the one or more external indicators, that the pest was detected.

9. The detector of claim 8 , wherein:

the sensor plugin rotates at least 180 degrees to position the additional sensor to detect pests in a pest detection zone that is about 180 degrees relative to a front surface of the detector.

10. The detector of claim 9 , wherein:

a second sensor of the one or more sensors creates a second pest detection zone that is about 180 degrees relative to a rear surface of the detector;

wherein the additional sensor and the second sensor provide about 360 degrees of pest detection.

11. The detector of claim 8 , wherein:

the additional sensor is positioned to detect pests where a floor meets a wall or where the wall meets a ceiling.

12. The detector of claim 11 , wherein the additional sensor is backward facing to detect pest movement within a wall.

13. The detector of claim 8 , wherein the one or more sensors comprise at least one of:

a motion sensor, an imaging sensor, a microphone, a structured light sensor, an ultrasound sensor, a temperature sensor, an ultrasonic sensor, a capacitive sensor, or a micropower impulse radar sensor.

14. A detector comprising:

one or more processors; and

one or more non-transitory computer readable media to store instructions executable by the one or more processors to perform operations comprising:

receiving sensor data from one or more sensors;

determining, by a machine learning algorithm, that the sensor data indicates a presence of a pest;

sending a notification message to a computing device, the notification message including at least a portion of the sensor data;

visually indicating, using an external indicator light of the detector, that the pest was detected;

receiving second sensor data from the one or more sensors;

determining that the machine learning algorithm does not recognize a second pest in the second sensor data; and

sending a message to a server indicating that the machine learning algorithm does not recognize the second pest, the message including the second sensor data.

15. The detector of claim 14 , wherein the operations further comprise:

receiving an update to the machine learning algorithm from a server;

installing the update to create an updated machine learning algorithm; and

determining, by the updated machine learning algorithm, that the second sensor data indicates the presence of the second pest.

16. The detector of claim 15 , wherein:

the updated machine learning algorithm is trained to detect pests in a geographic area in which the detector is located.

17. The detector of claim 14 , wherein the sensor data comprises at least one of:

a set of one or more digital images; or

a digital audio recording.

18. The detector of claim 14 , wherein the operations further comprise:

detecting, by a motion sensor of the detector, movement associated with the pest; and

in response to detecting the movement, capturing, by an imaging sensor of the detector, one or more digital images of the pest.

19. The detector of claim 14 , the operations further comprising:

receiving ambient light data from an ambient light sensor of the detector;

determining that the ambient light data does not satisfies a predetermined threshold; and

transitioning the detector from an active mode to a low-power mode.

20. The detector of claim 14 , wherein the one or more sensors comprise at least one of:

a motion sensor, an imaging sensor, a microphone, a structured light sensor, an ultrasound sensor, a temperature sensor, an ultrasonic sensor, a capacitive sensor, or a micropower impulse radar sensor.