MODULAR ELECTRONIC LIE AND EMOTION DETECTION SYSTEMS, METHODS, AND DEVICES

• US 20180160959A1
• Filed: 12/09/2017
• Published: 06/14/2018
• Est. Priority Date: 12/12/2016
• Status: Active Application

• Current Assignee: Keyrsten Suzanne Wilde, Timothy James Wilde
• Original Assignee: Keyrsten Suzanne Wilde, Timothy James Wilde
• Inventors: Wilde, Timothy James, Wilde, Keyrsten Suzanne
• Application Number:
  US15/836,863
• Publication Number:
  US 20180160959A1
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/0533 Measuring galvanic skin response
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/164 Lie detection
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A modular, electronic lie and emotion detection system is disclosed. The modular, electronic lie and emotion detection system can include a computing unit programmed for multifactor dimensionality reduction, anomaly detection, and prediction of lies and emotions and may also be configured to communicate with the modular and/or remote unit(s) via an interface or port or connector to which the computing unit and the modular and/or remote unit(s) are coupled. The modular and/or remote unit(s) can supplement the functionality of the computing unit.

Claims

1. An electronic lie detection and emotional analysis system, comprising:

a computing system whereby the system facilitates the transfer of audio, visual, and physiological data from a subject through the utilization of an input/output system comprised of wired and/or wireless connections and at least one of the following components;

a processor;

a memory;

a sensor;

a signal converter;

a receiver configured to wirelessly communicate with at least one remote unit;

a transmitter configured to wirelessly communicate with at least one remote unit;

a transceiver configured to wirelessly communicate with at least one remote unit;

wherein the input/output systems of the lie detection unit and the extensible unit are configured to provide a wired electrical connection between the lie detection unit and the extensible unit when in a coupled configuration via the at least one wired connection the lie detection unit and the at least one wired connection of the extensible unit

2. An extensible system, per claim 1, wherein an extensible unit by which the usage of will allow for a or to supplement existing systems;

the here aforementioned system comprises at least one of the following components;

a processor;

a memory;

a sensor;

a signal converter;

a receiver configured to wirelessly communicate with at least one remote unit;

a transmitter configured to wirelessly communicate with at least one remote unit;

a transceiver configured to wirelessly communicate with at least one remote unit;

3. The electronic system according to any of claims 1-2, wherein the input/output system of the extensible unit comprises a first wired connection and a second wired connection, where at least one of the first and second wired connections are configured to couple a second extensible unit to the first extensible unit and to provide communication between the lie detection unit and the second unit extensible unit.

4. The electronic lie detection and emotional analysis system according to claim 1, wherein:

the extensible unit comprises the sensor, and the extensible unit comprises the receiver and the transmitter and is configured to serve as a node for wireless communication with multiple remote units.

5. The device as recited in claim 1, wherein said system is further operable to execute code for:

providing secure communications; and

providing selected encryption information items to said transmission systems.

6. The method of claim 5, further comprising:

sending, from the system in claim 1 to the extensible unit or remote unit or server, a request for encrypted communications, whereby sending the request to transmit includes;

sending the request to communicate via a Hypertext Transfer Protocol Secure (HTTPS) request or a Hypertext Transfer Protocol (HTTP) request, where sending the request for the encrypted communication includes;

receiving the request for encrypted communication via a HTTPS request or a HTTP request, where transmitting the encrypted communication includes;

transmitting the encrypted communication as a HTTPS response or a HTTP response.

7. A method of analyzing multiple sources of the subjects audio, visual, and physiological information regarding lie detection analysis and emotional analysis according to any of claims 1-4, comprising:

the system of claim 1, wherein the execution of code whereby the audio, visual, and physiological information will be evaluated to determine the validity, usefulness, and/or highest contribution to the appropriate system;

analysis of incoming audio, visual, and physiological data for indications of lying and the emotional state of the subject by comparing the audio, visual, and physiological attributes of the subject to previously stored expression and/or parameterized value;

wherein, the system of claim 1 predicts if the subject is being truthful or lying;

wherein, the system of claim 1 predicts the subjects emotional state;

the system of claim 1, generates a composite visual, audio, or haptic response to the user indicating if the subject is being truthful or lying;

the system of claim 1, generates a composite visual, audio, or haptic response to the user indicating the emotional state of the subject;

the system of claim 1, may provide a composite visual, audio, or haptic response to the subject indicating if the subject is being truthful or lying;

8. The systems and methods of claim 7, wherein the audio, visual, and physiological information are generated and presented in real-time.

9. The system of claim 1 contains an attribute extractor program for extracting an attribute weight vector, wherein the current attribute weight vector contains information related to audio, visual, and physiological data;

a machine learning model generation program for generating a classification model from the current attribute weight vector, a plurality of data functions and a certainty function vector;

wherein the classification model associates the information of the current attribute weight vector and the ideal state certainty function vector with patterns and each of the plurality of patterns is associated with a respective one of a plurality of attribute classifications;

a certainty function generating program for generating a certainty function based on the classification model and the current attribute weight vector, wherein the certainty function contains information representing a likelihood of each attribute belonging to a respective one of the plurality of classifications;

a contextual attribute extractor program for extracting the certainty function attribute vector from a previously generated certainty function, wherein the certainty function attribute vector contains information related to audio, visual, and physiological data of the certainty function, wherein the classification model is updated to iteratively improve the classification models based on the latest extracted certainty function attribute vector and further wherein both the certainty function attribute vector is extracted and the classification model is updated, for a threshold number of iterations;

a machine learning classification program for classifying attributes of a secondary audio, visual, and physiological attributes based on the classification model.

10. The method of claim 9, wherein extracting a plurality of contextual attribute vectors further comprises:

characterizing by the system a plurality of the audio, visual, and physiological data of a respective one of the plurality of the certainty functions with features based on the likelihood of previously captured audio, visual, and physiological data belonging to a respective one of the plurality of classifications associated with the respective one of the plurality of certainty functions.