Abstract: Provided are various mechanisms and processes for automatic computer vision-based defect detection using a neural network. A system is configured for receiving historical datasets that include training images corresponding to one or more known defects. Each training image is converted into a corresponding matrix representation for training the neural network to adjust weighted parameters based on the known defects. Once sufficiently trained, a test image of an object that is not part of the historical dataset is obtained. Portions of the test image are extracted as input patches for input into the neural network as respective matrix representations. A probability score indicating the likelihood that the input patch includes a defect is automatically generated for each input patch using the weighted parameters. An overall defect score for the test image is then generated based on the probability scores to indicate the condition of the object.

Abstract: Disclosed are apparatus and methods for enhancing operation of an ultrasonic sensing device for determining the status of an object near such ultrasonic sensing device. From the ultrasonic sensing device, an emission signal having a current frequency or band in an ultrasonic frequency range is emitted. Ultrasonic signals are received and analyzed to detect an object. After a trigger occurs, a background noise signal emitted, reflected, or diffracted from the object in an environment outside of the ultrasonic sensing device is detected and background noise metrics are estimated based on the background noise signal after halting the emitting of the emission signal. It is then determined whether the current frequency of the emission signal is optimized based on the background noise metrics. A next frequency or band is selected and the emission signal is emitted at the next frequency or band if the current frequency or band is not optimum.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate calibrating a user activity model of a user device nodes are described. According to an embodiment, a method for calibrating a user activity model used by a mobile device can comprise receiving sensor data from a sensor of the mobile device. Further, applying a first weight to a first likelihood of a first occurrence of a first activity, wherein the first likelihood is determined by a first estimator of the user activity model by applying preconfigured criteria to the sensor data. The method can further comprise performing an action based on a determination of the first occurrence of the first activity, the determination being based on the first weight and the first likelihood of the first occurrence of the first activity.

Abstract: A method for semi-automated labeling of data for machine learning training. Data is collected via time-series sensors to form an unlabeled dataset. After receiving one or more event type labels for a subset of the dataset, thereby forming a labeled dataset, the remainder of the unlabeled dataset is automatically labeled. Potential new labels for the remainder of the unlabeled dataset are determined via cross correlation between the labeled dataset and unlabeled dataset. The potential new labels are presented as training data for a machine learning algorithm.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate calibrating a user activity model of a user device nodes are described. According to an embodiment, a method for calibrating a user activity model used by a mobile device can comprise receiving sensor data from a sensor of the mobile device. Further, applying a first weight to a first a first likelihood of a first occurrence of a first activity, wherein the first likelihood is determined by a first estimator of the user activity model by applying preconfigured criteria to the sensor data. The method can further comprise performing an action based on a determination of the first occurrence of the first activity, the determination being based on the first weight and the first likelihood of the first occurrence of the first activity.

Abstract: Provided are various mechanisms and processes for automatic computer vision-based defect detection using a neural network. A system is configured for receiving historical datasets that include training images corresponding to one or more known defects. Each training image is converted into a corresponding matrix representation for training the neural network to adjust weighted parameters based on the known defects. Once sufficiently trained, a test image of an object that is not part of the historical dataset is obtained. Portions of the test image are extracted as input patches for input into the neural network as respective matrix representations. A probability score indicating the likelihood that the input patch includes a defect is automatically generated for each input patch using the weighted parameters. An overall defect score for the test image is then generated based on the probability scores to indicate the condition of the object.

Abstract: Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. An indication is sent to the sensor node to initiate training by the sensor node to detect anomalies in object(s) in the environment based on sensor data generated by a sensor operable to detect signals from the one or more objects in the environment. After training is initiated, the sensor node automatically trains a model in communication with the sensor to detect anomalies in the one or more objects in the environment, wherein such training is based on the sensor data. After the model is trained, the model to detect anomalies in the object(s) in the environment is executed by the sensor node.

Abstract: Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. At the sensor node, an indication is received to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment. After training is initiated, the sensor node automatically trains a model that resides on the sensor to detect anomalies in the environment, and such training is based on the sensor data. After the model is trained, the model to detect anomalies in the environment is executed by the sensor node.

Abstract: Disclosed are apparatus and methods for enhancing operation of an ultrasonic sensing device for determining the status of an object near such ultrasonic sensing device. From the ultrasonic sensing device, an emission signal having a current frequency or band in an ultrasonic frequency range is emitted. Ultrasonic signals are received and analyzed to detect an object. After a trigger occurs, a background noise signal emitted, reflected, or diffracted from the object in an environment outside of the ultrasonic sensing device is detected and background noise metrics are estimated based on the background noise signal after halting the emitting of the emission signal. It is then determined whether the current frequency of the emission signal is optimized based on the background noise metrics. A next frequency or band is selected and the emission signal is emitted at the next frequency or band if the current frequency or band is not optimum.

Abstract: The disclosure facilitates fingerprint recognition, user authentication, and prevention of loss of control of personal information and identity theft. The disclosure also facilitates identifying spoofed fingerprint authentication attempts, and/or securing user touch sensitive devices against spoofed fingerprint authentication attempts.

Abstract: Provided are various mechanisms and processes for automatic computer vision-based defect detection using a neural network. A system is configured for receiving historical datasets that include training images corresponding to one or more known defects. Each training image is converted into a corresponding matrix representation for training the neural network to adjust weighted parameters based on the known defects. Once sufficiently trained, a test image of an object that is not part of the historical dataset is obtained. Portions of the test image are extracted as input patches for input into the neural network as respective matrix representations. A probability score indicating the likelihood that the input patch includes a defect is automatically generated for each input patch using the weighted parameters. An overall defect score for the test image is then generated based on the probability scores to indicate the condition of the object.

Abstract: A method and apparatus that resolve near touch ambiguities in a touch screen includes detecting a touch screen touch event and detecting a vibro-acoustic event. These events generate signals received respectively by two different sensors and/or processes. When the two events occur within a pre-defined window of time, they may be considered to be part of the same touch event and may signify a true touch.

Abstract: Disclosed are apparatus and methods for enhancing operation of an ultrasonic sensing device for determining the status of an object near such ultrasonic sensing device. From the ultrasonic sensing device, an emission signal having a current frequency or band in an ultrasonic frequency range is emitted. Ultrasonic signals are received and analyzed to detect one or more objects near or contacting the ultrasonic sensing device. After expiration of a predefined time period of emitting the emission signal, a background noise signal is detected from an environment of the ultrasonic device and background noise metrics are estimated based on the background noise signal. It is then determined whether the current frequency of the emission signal is optimized based on the background noise metrics. A next frequency or band is selected and the emission signal is emitted at the next frequency or band if it is determined that the current frequency or band is not optimum.

Abstract: Techniques enabling improved classification of touch or hover interactions of objects with a touch sensitive surface of a device are presented. A speaker of the device can emit an ultrasonic audio signal comprising a first frequency distribution. A microphone of the device can detect a reflected audio signal comprising a second frequency distribution. The audio signal can be reflected off of an object in proximity to the surface to produce the reflected audio signal. A classification component can determine movement status of the object, or classify the touch or hover interaction, in relation to the surface, based on analysis of the signals. The classification component also can classify the touch or hover interaction based on such ultrasound data and/or touch surface or other sensor data. The classification component can be trained, using machine learning, to perform classifications of touch or hover interactions of objects with the surface.

Abstract: Provided are various mechanisms and processes for automatic computer vision-based defect detection using a neural network. A system is configured for receiving historical datasets that include training images corresponding to one or more known defects. Each training image is converted into a corresponding matrix representation for training the neural network to adjust weighted parameters based on the known defects. Once sufficiently trained, a test image of an object that is not part of the historical dataset is obtained. Portions of the test image are extracted as input patches for input into the neural network as respective matrix representations. A probability score indicating the likelihood that the input patch includes a defect is automatically generated for each input patch using the weighted parameters. An overall defect score for the test image is then generated based on the probability scores to indicate the condition of the object.

Abstract: Provided are various mechanisms and processes for quantization of tree-based machine learning models. A method comprises determining one or more parameter values in a trained tree-based machine learning model. The one or more parameter values exist within a first number space encoded in a first data type and are quantized into a second number space. The second number space is encoded in a second data type having a smaller file storage size relative to the first data type. An array is encoded within the tree-based machine learning model. The array stores parameters for transforming a given quantized parameter value in the second number space to a corresponding parameter value in the first number space. The tree-based machine learning model may be transmitted to an embedded system of a client device. The one or more parameter values correspond to threshold values or leaf values of the tree-based machine learning model.

Abstract: Techniques enabling improved classification of touch or hover interactions of objects with a touch sensitive surface of a device are presented. A speaker of the device can emit an ultrasonic audio signal comprising a first frequency distribution. A microphone of the device can detect a reflected audio signal comprising a second frequency distribution. The audio signal can be reflected off of an object in proximity to the surface to produce the reflected audio signal. A classification component can determine movement status of the object, or classify the touch or hover interaction, in relation to the surface, based on analysis of the signals. The classification component also can classify the touch or hover interaction based on such ultrasound data and/or touch surface or other sensor data. The classification component can be trained, using machine learning, to perform classifications of touch or hover interactions of objects with the surface.

Abstract: Disclosed are apparatus and methods for automatically training a sensor node to detect anomalies in an environment. At the sensor node, an indication is received to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment. After training is initiated, the sensor node automatically trains a model that resides on the sensor to detect anomalies in the environment, and such training is based on the sensor data. After the model is trained, the model to detect anomalies in the environment is executed by the sensor node.

Abstract: The disclosure facilitates fingerprint recognition, user authentication, and prevention of loss of control of personal information and identity theft. The disclosure also facilitates identifying spoofed fingerprint authentication attempts, and/or securing user touch sensitive devices against spoofed fingerprint authentication attempts.

Abstract: A system for classifying touch events includes a touch screen configured to display an interactive element, one or more acoustic sensors coupled to the touch screen, a touch event detector configured to monitor the one or more acoustic sensors and to save acoustic signals sensed by the one or more acoustic sensors, wherein the touch event detector is further configured to detect touch events in which the interactive element is touched by a first or a second finger part of a user, and wherein the touch events result in generating the acoustic signals, and an acoustic classifier configured to classify the acoustic signals.