Abstract: A method of machine learning network includes receiving one or more sound segments and one or more associated text labels indicating captions associated with the sound segments, generating, utilizing a large language model of the machine learning network, one or more counterfactual captions associated with the one or more sound segments, wherein the one or more counterfactual captions are adversarial captions, determining a loss associated with the one or more sound segments, one or more associated text labels, and one or more counterfactual captions, updating parameters associated with an audio encoder or text encoder of the machine learning network, in response to falling below a threshold, repeating steps list above, and in response to meeting the threshold and utilizing a ranking, updating final parameters associated with the machine learning network.

Abstract: A method data augmentation includes receiving audio stream data associated with at least one impulse event, receiving a label associated with the audio stream data, and detecting, using an onset detector, at least one peak of the at least one impulse event. The method also includes extracting at least one positive sample of the audio stream data associated with the at least one impulse event. The method also includes applying, to the at least one positive sample, the label associated with the audio stream data and extracting at least one negative sample of the audio stream data associated with the at least one impulse event. The method also includes augmenting training data based on the at least one positive sample and the at least one negative sample and training at least one machine-learning model using the augmented training data.

Abstract: Systems and methods for converting a primary one-dimensional signal into a secondary one-dimensional signal of another modality. The primary signal is spliced into a plurality of consecutive frames. A first linear transformation transforms the frames into corresponding vectors. Positional encodings are provided on the vectors to encode relative positional information associated with each sample within each frame. A multi-head self-attention machine-learning model compares relative importance of the samples within each vector to each other in that vector to yield high-level representation vectors. A second linear transformation transforms the high-level representation vectors into corresponding secondary signal frames. The secondary signal frames are concatenated into a reconstructed one-dimensional secondary signal having a different modality than the primary signal.

Abstract: Methods and systems for training an audio-based machine learning model to predict a health condition based on biological sounds emitted by a person. Audio data corresponding to biological sounds produced by the person is generated from a microphone. The audio data is segmented into a plurality of segments, each segment associated with a respective sound event. An audio-based machine learning model is executed on the plurality of segments. The audio-based machine learning model is configured to output, for each segment, a label of a medical condition and an associated a confidence score. The model is trained via active learning, in which a subset of the plurality of segments are selected based on their confidence score being below a threshold, and provided to a human for annotation.

Abstract: Methods and systems of processing audio data with a multi-stage audio front end model is provided. A one-dimensional audio waveform is received as input and processed using a multi-stage audio frontend model to convert the one-dimensional waveform into a two-dimensional matrix representing features of the audio waveform. The multi-stage learnable audio frontend model is configured to apply a first filterbank to the audio waveform to generate a first time-frequency representation of the audio waveform; apply a first decimation filter to the audio waveform to generate a first decimated audio input; apply a second filterbank to the first decimated audio input to generate a second time-frequency representation of the audio waveform; and stack the first time-frequency representation and the second time-frequency representation together to generate the two-dimensional matrix.

Abstract: A method of training a prototypical network for sound event detection includes receiving samples of an audio signal that include positive samples corresponding to sound events and negative samples that do not correspond to sound events, determining, based on the positive samples, respective positive prototypes of a plurality of classes of sound events, determining, based on the negative samples, respective negative prototypes for respective groups of the negative samples, each of the negative prototypes corresponding to a combination of a plurality of the negative samples, and generating, based on comparisons between a first sample and the respective positive prototypes and each of the negative prototypes, an output signal that indicates whether the first sample belongs to one of the plurality of classes of sound events.

Abstract: Systems and methods for detecting symptoms of occupant illness is disclosed herein. In embodiments, a storage is configured to maintain a visualization application and data from one or more sources, such as an image source. A processor is in communication with the storage and a user interface. The processor is programmed to receive data from the one or more sources, execute human-detection models based on the received data, execute activity-recognition models to recognize symptoms of illness based on the data from the one or more sources, determine a location of the recognized symptoms, and execute a visualization application to display information in the user interface. The visualization application can show a background image with an overlaid image that includes an indicator for each location of recognized symptom of illness. Additionally, data from the audio source, image source, and/or radar source can be fused.

Abstract: Systems and methods for detecting symptoms of occupant illness is disclosed herein. In embodiments, a storage is configured to maintain a visualization application and data from one or more sources, such as an image source. A processor is in communication with the storage and a user interface. The processor is programmed to receive data from the one or more sources, execute human-detection models based on the received data, execute activity-recognition models to recognize symptoms of illness based on the data from the one or more sources, determine a location of the recognized symptoms, and execute a visualization application to display information in the user interface. The visualization application can show a background image with an overlaid image that includes an indicator for each location of recognized symptom of illness. Additionally, data from the audio source, image source, and/or radar source can be fused.

Abstract: A system includes a first and second transceiver configured to emit and receive a wireless signal, a controller in communication with the first and second transceiver, the controller configured to send instructions to the transceivers to initiate a Fine Time Measurement (FTM) on a wireless channel to a body part associated with a user during a healthy state of the user, store an FTM measurement associated with the healthy state of the user, send instructions to the transceiver to initiate the FTM on the wireless channel during an infected state of the user, store an FTM measurement associated with the infected state of the user, compare the FTM measurement associated with the healthy state of the user with the FTM measurement associated with the infected state of the user, and in response to the comparison exceeding a threshold value, output a notification.

Abstract: A method of training a machine learning (ML) model includes obtaining a dataset that includes first training data obtained using two or more ground truth sensing systems and second training data obtained using a prediction sensing system configured to implement the ML model, determining a loss function based on the first training data, the loss function defining a region of zero loss based on a minimum and a maximum of the first training data, calculating, using the ML model, a prediction output based on the second training data, calculating, using the loss function, a loss of the ML model based on the prediction output, and updating the ML model based on the calculated loss.

Abstract: A vehicle system that includes a vehicle seat, wherein the vehicle seat includes a seat-back portion, a seat-bottom portion, a head rest portion, wherein the vehicle seat includes one or more acoustic sensors configured to retrieve an acoustic signal associated with a passenger seat, and a processor in communication with at least the one or more acoustic sensors, wherein the processor is programmed to identify an anomaly associated with the passenger utilizing the acoustic signal, wherein the anomaly is identified via pre-processing the acoustic signal and extracting one or more features associated with the acoustic signal in response to the pre-preprocessing and utilizing a classifier to classify one or more features associated with the acoustic signal as either a normal condition or the anomaly, and output a notification associated with the anomaly in response to identifying the anomaly.

Abstract: A system that includes one or more sensors installed in proximity to a machine configured to collect raw signals associated with an environment of the machine, are multi-layer spatial data that include time-stamp data. The system may include a processor in communication with the sensors and programmed to receive one or more raw signals, denoise the one or more raw signals to obtain a pre-processed signal, extract one or more features from the pre-processed signals, classify the one or more features to an associated class, wherein the associated class includes one or more of a normal class, abnormal class, or a potential-abnormal class, create fusion data by fusing the one or more features utilizing the associated class and the time-stamp data, and output a heat map on an overlaid image of the environment.

Abstract: A system that includes one or more sensors installed in proximity to a machine configured to collect raw signals associated with an environment of the machine, are multi-layer spatial data that include time-stamp data. The system may include a processor in communication with the sensors and programmed to receive one or more raw signals, denoise the one or more raw signals to obtain a pre-processed signal, extract one or more features from the pre-processed signals, classify the one or more features to an associated class, wherein the associated class includes one or more of a normal class, abnormal class, or a potential-abnormal class, create fusion data by fusing the one or more features utilizing the associated class and the time-stamp data, and output a heat map on an overlaid image of the environment.

Abstract: A method includes receiving audio stream data associated with a data capture environment, and receiving sensor data associated with the data capture environment. The method also includes identifying at least some events in the sensor data, and calculating at least one offset value for at least a portion of the audio stream data that corresponds to at least one event of the sensor data. The method also includes synchronizing at least a portion of the sensor data associated with the portion of the audio stream data that corresponds to the at least one event of the sensor data, and labeling at least the portion of the audio stream data that corresponds to the at least one event of the sensor data. The method also includes generating training data using at least some of the labeled portion of the audio stream data, and training a machine learning model using the training data.

Abstract: A system that includes one or more sensors installed in proximity to a machine configured to collect raw signals associated with an environment of the machine, are multi-layer spatial data that include time-stamp data. The system may include a processor in communication with the sensors and programmed to receive one or more raw signals, denoise the one or more raw signals to obtain a pre-processed signal, extract one or more features from the pre-processed signals, classify the one or more features to an associated class, wherein the associated class includes one or more of a normal class, abnormal class, or a potential-abnormal class, create fusion data by fusing the one or more features utilizing the associated class and the time-stamp data, and output a heat map on an overlaid image of the environment.

Abstract: Provided herein are methods of detecting a disease, condition, or disorder in a subject. In some embodiments, the methods include obtaining a set of ribonucleic acid (RNA) molecules from a population of exosomes in a biological sample obtained from the subject and detecting a plurality of target RNA molecules corresponding to a selected set of cell-specific exosomal RNA molecules in the set of RNA molecules to generate a target RNA molecular profile for the sample. In some of these embodiments, the methods also include determining that the target RNA molecular profile substantially matches a reference RNA molecular profile that correlates with the disease, condition, or disorder in a subject and/or using at least one algorithm that predicts a likelihood that the target RNA molecular profile correlates with the disease, condition, or disorder in a subject. Related biosensor devices, kits, and systems are also provided.

Abstract: An intelligent audio analytic apparatus (IAAA) and method for space system. The IAAA comprises a processor, a computer readable medium, and a communication module. The instructions include audio data processing algorithms configured to identify and predict impending anomalies associated with the space system using at least one neural network.

Abstract: Systems and methods for detecting symptoms of occupant illness is disclosed herein. In embodiments, a storage is configured to maintain a visualization application and data from one or more sources, such as an image source. A processor is in communication with the storage and a user interface. The processor is programmed to receive data from the one or more sources, execute human-detection models based on the received data, execute activity-recognition models to recognize symptoms of illness based on the data from the one or more sources, determine a location of the recognized symptoms, and execute a visualization application to display information in the user interface. The visualization application can show a background image with an overlaid image that includes an indicator for each location of recognized symptom of illness. Additionally, data from the audio source, image source, and/or radar source can be fused.

Abstract: A method includes receiving audio stream data associated with a data capture environment, and receiving sensor data associated with the data capture environment. The method also includes identifying at least some events in the sensor data, and calculating at least one offset value for at least a portion of the audio stream data that corresponds to at least one event of the sensor data. The method also includes synchronizing at least a portion of the sensor data associated with the portion of the audio stream data that corresponds to the at least one event of the sensor data, and labeling at least the portion of the audio stream data that corresponds to the at least one event of the sensor data. The method also includes generating training data using at least some of the labeled portion of the audio stream data, and training a machine learning model using the training data.

Abstract: A method data augmentation includes receiving audio stream data associated with at least one impulse event, receiving a label associated with the audio stream data, and detecting, using an onset detector, at least one peak of the at least one impulse event. The method also includes extracting at least one positive sample of the audio stream data associated with the at least one impulse event. The method also includes applying, to the at least one positive sample, the label associated with the audio stream data and extracting at least one negative sample of the audio stream data associated with the at least one impulse event. The method also includes augmenting training data based on the at least one positive sample and the at least one negative sample and training at least one machine-learning model using the augmented training data.