Abstract: A disclosed example includes providing vibration information to a model, the vibration information corresponding to a first vibration measured at a first mobile device when the first mobile device is in a state of non-use by a user, the model based on a plurality of vibration patterns that correspond to second vibrations measured by second mobile devices in different environments; identifying, using the model, one of the vibration patterns that corresponds to the vibration information; determining an environment of the first mobile device based on the one of the vibration patterns; and instructing the first mobile device to modify a functionality of the first mobile device based on the environment.

Abstract: In some embodiments, a method calculates a first color metric value from a detection window in a first image that is detected by a visual system. A second image of pixels is generated where the pixels include one or more second color metric values that meet the first color metric value within a threshold. The method compares the second image to an object. When the comparison meets a criterion, the method transitions from a first mode to a second mode. When the comparison does not meet the criterion, the method continues to operate in the first mode.

Abstract: Methods and apparatuses for identifying food chewed or beverage drank are disclosed herein. In embodiments, a device may comprise one or more sensors to provide vibration signal data representative of vibrations sensed from a nasal bridge of a user wearing the device, a chewing analyzer to extract from the vibration signal data a first plurality of features associated with chewing activities, and/or a drinking analyzer is to extract from the vibration signal data a second plurality of features associated with drinking activities. The extracted first and/or second plurality of features, in turn, may be used to determine a category of food the user was chewing, or a category of beverage the user was drinking. In embodiments, the methods and apparatuses may use personalized models.

Abstract: An example apparatus for hearing protection and communication includes safety glasses including a vibration sensor to capture speech from a user. The apparatus also includes hearing protectors communicatively coupled to the safety glasses and one or more other devices. The hearing protectors are to reduce a volume of an ambient sound and play back captured speech from the one or more other devices. The apparatus also further includes a number of wireless communication elements to communicatively couple the safety glasses, the hearing protectors, and at least a second apparatus for hearing protection and communication.

Abstract: Technologies for emotion prediction based on breathing patterns include a wearable device. The wearable device includes a breathing sensor to generate breathing data, one or more processors, and one or more memory devices having stored therein a plurality of instructions that, when executed, cause the wearable device to calibrate a personalized emotion predictive model associated with the user, collect breathing data of the user of the wearable device, analyze the breathing data to determine a breathing pattern, predict, in response to an analysis of the breathing data, the emotional state of the user using the personalized emotion predictive model, and output the emotional state of the user.

Abstract: An apparatus to facilitate unsupervised incremental clustering learning for multiple modalities is disclosed. The apparatus includes one or more processors to perform first unsupervised clustering on a first input descriptor vector corresponding to a first modality, the first unsupervised clustering to associate the first input descriptor vector with a first identifier; perform second unsupervised clustering on a second input descriptor vector corresponding to a second modality, the second unsupervised clustering to associate the second input descriptor vector with a second identifier; and compare the first identifier of the first unsupervised clustering and the second identifier of the second unsupervised clustering to determine labeling for the first input descriptor vector and the second input descriptor vector.

Abstract: An apparatus to facilitate fractional convolutional kernels is disclosed. The apparatus includes one or more processors comprising a convolution circuit of a neural network, the convolution circuit to initialize a set of parameters of a fractional convolutional kernel, the set of parameters comprising at least a fractional derivative parameter that is initialized with a fractional value, and apply the fractional convolutional kernel to input data to convolve the input data to obtain output data.

Abstract: Technology for a mobile device is described. The mobile device can include a vibration motor operable to generate a vibration, and a sensor operable to capture a plurality of vibration signals that result from the vibration. The mobile device can provide the plurality of vibration signals to a model running on the mobile device. The model can include a plurality of predefined patterns that correspond to vibration signals produced by mobile devices residing on different surfaces. The mobile device can identify, using the model, a predefined pattern in the plurality of predefined patterns that substantially corresponds to the plurality of vibration signals based on a confidence level that exceeds a threshold. The mobile device can determine a type of surface on which the mobile device resides based on the predefined pattern identified using the model.

Abstract: A component of an Autonomous Vehicle (AV) system, the component having at least one processor; and a non-transitory computer-readable storage medium including instructions that, when executed by the at least one processor, cause the at least one processor to decode data encoded in a signal, wherein the data identifies a pattern of protrusions embedded in a driving surface, the signal being received from at least one vehicle sensor resulting from a vehicle driving over the pattern of protrusions in the driving surface.

Abstract: Apparatuses and methods for selecting, for communicating, between signals provided by various pickups on the basis of a calculated signal to noise ratio (SNR) are disclosed. The various pickups may include a microphone and a vibration sensor. Signals from the microphone may be compared with signals from the vibration sensor by extracting a root-mean-square (RMS) profile for each, and comparing the RMS profiles to determine an SNR estimate for the microphone signal. The microphone signal may be selected if the SNR estimate is below a predetermined threshold, otherwise the vibration sensor signal may be selected. The vibration sensor signal may be subject to further processing if selected to approximate the microphone signal.

Abstract: Apparatuses and methods for transforming a signal from a vibration sensor into an approximation of a signal from a microphone are disclosed. The vibration sensor signal may be transformed by first obtaining a smooth average spectrum and corresponding deviation data for the vibration sensor signal. The smooth average spectrum may be passed through a mapping neural network to obtain a transformed smooth average spectrum that approximates a smooth average spectrum that would be obtained from a microphone. The transformed signal is then obtained by recombining the transformed smooth average spectrum with the deviation data.

Abstract: Methods, apparatus, systems, and articles of manufacture to detect the location of sound sources external to computing devices are disclosed. An apparatus, to determine a direction of a source of a sound relative to a computing device, includes a cross-correlation analyzer to generate a vector of values corresponding to a cross-correlation of first and second audio signals corresponding to the sound. The first audio signal is received from a first microphone of the computing device. The second audio signal is received from a second microphone of the computing device. The apparatus also includes a location analyzer to use a machine learning model and a set of the values of the vector to determine the direction of the source of the sound.

Abstract: Systems, apparatuses and methods may provide for origination camera technology that extracts data from multimodal sensor signals associated with a scene and generates a five-dimensional (5D) representation of the scene, wherein the 5D representation includes a three-dimensional (3D) visual representation, a one-dimensional (1D) temporal representation, and a 1D branch representation. The technology may also store the 5D representation as a set of abstract descriptors.

Abstract: Systems, apparatuses and methods may provide for technology that establishes a point of intersection based on a rate of change in a logarithmic function and generates a first linear estimation of the logarithmic function, wherein the first linear estimation has the point of intersection as an upper bound. Additionally, a second linear estimation of the logarithmic function may be generated, wherein the second linear estimation has the point of intersection as a lower bound. In one example, linear estimations of an antilogarithmic function may be similarly generated based on the rate of change of the antilogarithmic function.

Abstract: An apparatus for autonomous vehicles includes a perception pipeline having independent classification processes operating in parallel to respectively identify objects belonging to a specific object type based on sensor data flows from multiple ones of a plurality of different types of sensors. The apparatus also includes a sensor monitoring stage to operate in parallel with the perception pipeline and to use the sensor data flows to estimate and track a confidence level of each of the plurality of different types of sensors, and nullify a deficient sensor when the confidence level associated with the deficient sensor fails to meet a confidence threshold.

Abstract: Technologies for using a shifted neural network include a compute device to determine a shift-based activation function of the shifted neural network. The shift-based activation function is a piecewise linear approximation of a transcendental activation function and is defined by a plurality of line segments such that a corresponding slope of each line segment is a power of two. The compute device further trains the shifted neural network based on shift-based input weights and the determined shift-based activation function.

Abstract: Techniques are disclosed to use existing vehicle speakers alone or in conjunction with other sensors (e.g. SRS sensors and/or microphones) that may already be implemented as part of the vehicle to identify acoustic signatures. Suitable low-cost and widely available hardware components (e.g., relays) may be used to modify the vehicle's existing speakers for a bi-directional mode of operation. Moreover, the vehicle's existing of audio amplifiers may be used to amplify signals collected by the speakers when operating in “reverse,” and process these collected signals to determine vehicle state information.

Abstract: Technology for a mobile device is described. The mobile device can include a vibration motor operable to generate a vibration, and a sensor operable to capture a plurality of vibration signals that result from the vibration. The mobile device can provide the plurality of vibration signals to a model running on the mobile device. The model can include a plurality of predefined patterns that correspond to vibration signals produced by mobile devices residing on different surfaces. The mobile device can identify, using the model, a predefined pattern in the plurality of predefined patterns that substantially corresponds to the plurality of vibration signals based on a confidence level that exceeds a threshold. The mobile device can determine a type of surface on which the mobile device resides based on the predefined pattern identified using the model.

Abstract: Methods, systems, and apparatus for audio noise reduction from a drone are disclosed. An example apparatus includes an acoustic sensor to gather acoustic data and at least one rotational motion sensor to gather rotational motion data of a first rotor and second rotational motion data of a second rotor. The example apparatus also includes an analyzer to identify a first filter that matches the first rotational motion data and identify a second filter that matches the second rotational motion data. The analyzer also is to filter the acoustic data into filtered acoustic data with the first identified filter and the second identified filter and generate an audio signal based on the filtered acoustic data.

Abstract: Technology for a mobile device is described. The mobile device can include a vibration motor operable to generate a vibration, and a sensor operable to capture a plurality of vibration signals that result from the vibration. The mobile device can provide the plurality of vibration signals to a model running on the mobile device. The model can include a plurality of predefined patterns that correspond to vibration signals produced by mobile devices residing on different surfaces. The mobile device can identify, using the model, a predefined pattern in the plurality of predefined patterns that substantially corresponds to the plurality of vibration signals based on a confidence level that exceeds a threshold. The mobile device can determine a type of surface on which the mobile device resides based on the predefined pattern identified using the model.