Abstract: An exemplary virtual IMU extraction system and method are disclosed for human activity recognition (HAR) or classifier system that can estimate inertial measurement units (IMU) of a person in video data extracted from public repositories of video data having weakly labeled video content. The exemplary virtual IMU extraction system and method of the human activity recognition (HAR) or classifier system employ an automated processing pipeline (also referred to herein as “IMUTube”) that integrates computer vision and signal processing operations to convert video data of human activity into virtual streams of IMU data that represents accelerometer, gyroscope, or other inertial measurement unit estimation that can measure acceleration, inertia, motion, orientation, force, velocity, etc. at a different location on the body. In other embodiments, the automated processing pipeline can be used to generate high-quality virtual accelerometer data from a camera sensor.

Abstract: Disclosed herein is a flexible sensing interface, comprising: a sensor, comprising: a core; an inner electrode in the form of a conductive material in contact with the core; an inner dielectric material substantially encasing the inner electrode; an outer electrode in the form of a conductive material in contact with the inner dielectric material and in electrical communication with the inner electrode; and an outer dielectric material substantially encasing the outer electrode; wherein the inner dielectric material and the outer dielectric material comprise an elastic material. Also disclosed herein are systems and methods for making and using the same.

Abstract: A method including receiving sound data captured by a wearable device of the user, the sound data indicative of contact between a first portion of the user wearing the wearable device and a second portion of the user wearing the wearable device; receiving motion data captured by the wearable device of the user, the motion data indicative of at least a movement of the first portion of the user wearing the wearable device; and determining, by a processor, based at least in part on the sound data and the motion data, a user input associated with the contact between a first portion of the user wearing the wearable device and a second portion of the user wearing the wearable device and the movement of the first portion of the user wearing the wearable device.

Abstract: A vibration transducer for sensing vibrations includes a first flexible triboelectric member, a second flexible triboelectric member, a plurality of attachment points, a first electrode and a second electrode. The first flexible triboelectric member includes a first triboelectric layer and a material being on a first position on a triboelectric series. A conductive layer is deposited on the second side thereof. The second flexible triboelectric member includes a second triboelectric layer and a material being on a second position on the triboelectric series that is different from the first position on the triboelectric series. The second triboelectric member is adjacent to the first flexible triboelectric member. When the first triboelectric member comes into and out of contact with the second triboelectric member as a result of the vibrations, a triboelectric potential difference having a variable intensity corresponding to the vibrations can be sensed between the first and second triboelectric members.

Abstract: A portable electronic device including: a plurality of sensors configured to generate, in response to a first contact with a body of a user in a vicinity of the portable electronic device, one or more first input signals; a microprocessor; and a memory having stored thereon instructions that, when executed by the microprocessor, control the microprocessor to execute, in response to an analysis of the one or more first input signals indicating that the first contact corresponds to a first gesture, and by the microprocessor, a first command corresponding to the first gesture.

Abstract: An exemplary virtual IMU extraction system and method are disclosed for human activity recognition (HAR) or classifier system that can estimate inertial measurement units (IMU) of a person in video data extracted from public repositories of video data having weakly labeled video content. The exemplary virtual IMU extraction system and method of the human activity recognition (HAR) or classifier system employ an automated processing pipeline (also referred to herein as “IMUTube”) that integrates computer vision and signal processing operations to convert video data of human activity into virtual streams of IMU data that represents accelerometer, gyroscope, or other inertial measurement unit estimation that can measure acceleration, inertia, motion, orientation, force, velocity, etc. at a different location on the body. In other embodiments, the automated processing pipeline can be used to generate high-quality virtual accelerometer data from a camera sensor.

Abstract: Disclosed herein is a flexible sensing interface, comprising: a sensor, comprising: a core; an inner electrode in the form of a conductive material in contact with the core; an inner dielectric material substantially encasing the inner electrode; an outer electrode in the form of a conductive material in contact with the inner dielectric material and in electrical communication with the inner electrode; and an outer dielectric material substantially encasing the outer electrode; wherein the inner dielectric material and the outer dielectric material comprise an elastic material. Also disclosed herein are systems and methods for making and using the same.

Abstract: Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

Abstract: A vibration transducer for sensing vibrations includes a first flexible triboelectric member, a second flexible triboelectric member, a plurality of attachment points, a first electrode and a second electrode. The first flexible triboelectric member includes a first triboelectric layer and a material being on a first position on a triboelectric series. A conductive layer is deposited on the second side thereof. The second flexible triboelectric member includes a second triboelectric layer and a material being on a second position on the triboelectric series that is different from the first position on the triboelectric series. The second triboelectric member is adjacent to the first flexible triboelectric member. When the first triboelectric member comes into and out of contact with the second triboelectric member as a result of the vibrations, a triboelectric potential difference having a variable intensity corresponding to the vibrations can be sensed between the first and second triboelectric members.

Abstract: A method including receiving sound data captured by a wearable device of the user, the sound data indicative of contact between a first portion of the user wearing the wearable device and a second portion of the user wearing the wearable device; receiving motion data captured by the wearable device of the user, the motion data indicative of at least a movement of the first portion of the user wearing the wearable device; and determining, by a processor, based at least in part on the sound data and the motion data, a user input associated with the contact between a first portion of the user wearing the wearable device and a second portion of the user wearing the wearable device and the movement of the first portion of the user wearing the wearable device.

Abstract: A vibration transducer for sensing vibrations includes a first flexible triboelectric member, a second flexible triboelectric member, a plurality of attachment points, a first electrode and a second electrode. The first flexible triboelectric member includes a first triboelectric layer and a material being on a first position on a triboelectric series. A conductive layer is deposited on the second side thereof. The second flexible triboelectric member includes a second triboelectric layer and a material being on a second position on the triboelectric series that is different from the first position on the triboelectric series. The second triboelectric member is adjacent to the first flexible triboelectric member. When the first triboelectric member comes into and out of contact with the second triboelectric member as a result of the vibrations, a triboelectric potential difference having a variable intensity corresponding to the vibrations can be sensed between the first and second triboelectric members.

Abstract: A portable electronic device having improved user input capabilities and methods for controlling the same are provided. The device includes sensors capable of detecting and classifying user inputs provided as gestures performed on a surface of the device, wherein the surface does not include the sensors for detection of the gesture, nor is the surface in direct communication with the sensors for detection of the gesture. The device includes a microprocessor that performs instructions in response to the provided user input gestures.

Abstract: A vibration transducer for sensing vibrations includes a first flexible triboelectric member, a second flexible triboelectric member, a plurality of attachment points, a first electrode and a second electrode. The first flexible triboelectric member includes a first triboelectric layer and a material being on a first position on a triboelectric series. A conductive layer is deposited on the second side thereof. The second flexible triboelectric member includes a second triboelectric layer and a material being on a second position on the triboelectric series that is different from the first position on the triboelectric series. The second triboelectric member is adjacent to the first flexible triboelectric member. When the first triboelectric member comes into and out of contact with the second triboelectric member as a result of the vibrations, a triboelectric potential difference having a variable intensity corresponding to the vibrations can be sensed between the first and second triboelectric members.

Abstract: A portable electronic device having improved user input capabilities and methods for controlling the same are provided. The device includes sensors capable of detecting and classifying user inputs provided as gestures performed on a surface of the device, wherein the surface does not include the sensors for detection of the gesture, nor is the surface in direct communication with the sensors for detection of the gesture. The device includes a microprocessor that performs instructions in response to the provided user input gestures.

Abstract: Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

Abstract: A portable electronic device including: a plurality of sensors configured to generate, in response to a first contact with a body of a user in a vicinity of the portable electronic device, one or more first input signals; a microprocessor; and a memory having stored thereon instructions that, when executed by the microprocessor, control the microprocessor to execute, in response to an analysis of the one or more first input signals indicating that the first contact corresponds to a first gesture, and by the microprocessor, a first command corresponding to the first gesture.

Abstract: Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

Abstract: Disclosed is a system that uses existing power line infrastructure in a building as a distributed reception antenna capable of receiving signals from very low-power wireless sensors, thus allowing these sensors to be detected at ranges that are otherwise impractical with over-the-air reception. Also disclosed is a wireless sensor platform that is able to be sensed throughout a building with very low current draw. The disclosed technique may also be utilized to extend the range of mid-frequency consumer electronic devices by leveraging the power line as a reception antenna.

Abstract: Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

Abstract: Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power lines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.