WO-2026090909-A1 - METHODS AND APPARATUS FOR PEST DETECTION USING A SENSED CAPACITANCE PROFILE AND MACHINE LEARNING

Abstract

Various examples are directed to apparatus and methods for detecting and identifying pests using capacitance profiles and machine learning. A method includes receiving sensor data from one or more capacitive sensors configured to detect motion and generating feature data for a plurality of pests from the sensor data. The feature data is used to generate profiles for the plurality of pests, and a processor is trained using the generated profiles for the plurality of pests. The trained processor and the generated profiles are used to classify a pest of the plurality of pests based on the received sensor data, and an output is provided including the classification of the pest.

Inventors

• ZHANG, LUJUN
• WEI, Qiling
• ZHOU, Ziwei
• CHEN, KAI
• XIAO, YI
• SCHWARTZ, DANIEL RONALD

Assignees

• ECOLAB USA INC.

Dates

Publication Date

20260507

Application Date

20241030

Claims (20)

1. A computer-implemented method comprising: receiving sensor data from one or more capacitive sensors configured to detect motion; generating feature data for a plurality of pests from the sensor data; using the feature data to generate profiles for the plurality of pests; training a processor using the generated profiles for the plurality of pests; using the trained processor and the generated profiles to classify a pest of the plurality of pests based on the received sensor data; providing an output including a classification of the pest; and updating the generated profiles using at least in part one or more of past sensor data, feature data, and classifications.
2. The method of claim 1, wherein receiving sensor data from one or more capacitive sensors includes receiving sensor data from a pest control device.
3. The method of claim 1, wherein receiving sensor data from one or more capacitive sensors includes receiving sensor data from an internet of things (IoT) device.
4. The method of claim 1, further comprising: using the trained processor and the generated profiles to identify a pest of the plurality of pests based on the received sensor data.
5. The method of claim 4, further comprising: providing an output including an identification of the pest.
6. The method of claim 1, wherein generating feature data for a plurality of pests from the sensor data includes generating frequency domain feature data.
7. The method of claim 1, wherein generating feature data for a plurality of pests from the sensor data includes generating statistical feature data.
8. The method of claim 1, wherein generating feature data for a plurality of pests from the sensor data includes generating time-based feature data.
9. The method of claim 1, wherein using the trained processor and the generated profiles to classify a pest of the plurality of pests based on the received sensor data includes classifying the pest based on a peak amplitude of the sensor data.
10. The method of claim 1, wherein using the trained processor and the generated profiles to classify a pest of the plurality of pests based on the received sensor data includes classifying the pest based on a peak interval of the sensor data.
11. The method of claim 1, wherein providing an output including the classification of the pest includes providing an output on a mobile device of a user.
12. A system comprising: a computer system comprising one or more processors and a data storage system in communication with the one or more processors, wherein the data storage system comprises instructions thereon that, when executed by the one or more processors, causes the one or more processors to: receiving sensor data from one or more capacitive sensors configured to detect motion; generating feature data for a plurality of pests from the sensor data; using the feature data to generate profiles for the plurality of pests; training a processor using the generated profiles for the plurality of pests; using the trained processor and the generated profiles to classify a pest of the plurality of pests based on the received sensor data; providing an output including a classification of the pest; and updating the system based at least in part on at least some or all past sensor data, feature data, and classifications.
13. The system of claim 12, wherein training the processor including using a machine learning model.
14. The system of claim 13, wherein using the machine learning model includes using a machine learning model including a neural network.
15. The system of claim 13, wherein using the machine learning model includes using a machine learning model including a long short-term memory (LSTM) network.
16. The system of claim 13, wherein using the machine learning model includes using a machine learning model including bidirectional encoder representations from transformers (BERT) .
17. The system of claim 13, wherein using the machine learning model includes using a machine learning model including natural language processing (NLP) .
18. The system of claim 13, wherein using the machine learning model includes using a machine learning model including an artificial intelligence (AI) -based knowledge tree.
19. The system of claim 12, wherein at least a portion of the computer system includes a network-based storage device.
20. The system of claim 12, wherein at least a portion of the computer system includes a mobile computing device.

Description

METHODS AND APPARATUS FOR PEST DETECTION USING A SENSED CAPACITANCE PROFILE AND MACHINE LEARNING TECHNICAL FIELD This disclosure relates generally to pest detection and control, and more particularly to methods and apparatus for detecting and identifying pests using capacitance profiles and machine learning. BACKGROUND Pest control systems may include sensors in pest control devices to detect and identify pests captured or observed by the pest control devices. Data from sensors may be used to determine presence of the pests. However, pest control devices that use capacitive sensors to detect specific pests, such as rodents or insects, may generate false positive results from the presence of other pest species and from the environment. The false positive results waste service efforts for the pest control devices and lead to decreased efficiency, including causing a less accurate and more time consuming calculation. There is a need in the art for methods and apparatus for a pest detection and classification methodology for a capacitive sensor-based pest control system that provides more reliable, faster and more accurate detection and classification and avoids false alarms due to environmental effects. SUMMARY The present apparatus and methods provide a system for detecting and identifying pests using capacitance profiles and machine learning. Various examples are directed to a computer system comprising one or more processors and a data storage system in communication with the one or more processors. The data storage system comprises instructions thereon that, when executed by the one or more processors, causes the one or more processors to receive sensor data from one or more capacitive sensors configured to detect motion, and generate feature data for a plurality of pests from the sensor data. The feature data is used by the computer system to generate profiles for the plurality of pests, and a processor is trained using the generated profiles for the plurality of pests. The trained  processor and the generated profiles are used to classify a pest of the plurality of pests based on the received sensor data, and an output is provided by the computer system including the classification of the pest. Various examples are directed to apparatus and methods for detecting and identifying pests using capacitance profiles and machine learning. A method includes receiving sensor data from one or more capacitive sensors configured to detect motion and generating feature data for a plurality of pests from the sensor data. The feature data is used to generate profiles for the plurality of pests, and a processor is trained using the generated profiles for the plurality of pests. The trained processor and the generated profiles are used to classify a pest of the plurality of pests based on the received sensor data, and an output is provided including the classification of the pest. The trained processor and generated profiles also serve to reduce environmental effects, which may cause false positive senses. This Summary is an overview of some of the teachings of the present application and not intended to be an exclusive or exhaustive treatment of the present subject matter. Further details about the present subject matter are found in the detailed description and appended claims. The scope of the present invention is defined by the appended claims and their legal equivalents. BRIEF DESCRIPTION OF THE DRAWINGS The drawings illustrate generally, by way of example, various embodiments discussed in the present document. The drawings are for illustrative purposes only and may not be to scale. FIGS. 1A-1B illustrate example embodiments of a system for detecting and identifying pests using capacitance profiles. FIG. 2 illustrates an example embodiment of a method for detecting and identifying pests using capacitance profiles and machine learning. FIG. 3 illustrates an example machine learning module for detecting and identifying pests using capacitance profiles. FIG. 4 is a flowchart of a method of training a model for detecting and identifying pests using capacitance profiles. FIG. 5 illustrates an example embodiment of a system for detecting and identifying pests using capacitance profiles. FIGS. 6A-6B illustrate example embodiments of a pest sensing or control device for obtaining sensor data for detecting and identifying pests using capacitance profiles. FIGS. 7A-7E are graphical illustrations of features used for detecting and identifying pests using capacitance profiles, according to various embodiments. FIG. 8 is a block diagram of a machine in the example form of a computer system within which a set of instructions may be executed, for causing the machine to perform any one or more of the methodologies discussed herein. DETAILED DESCRIPTION The following detailed description of the present subject matter refers to subject matter in the accompanying drawings which show, by way of illustration, specific aspects a