Abstract: Various embodiments of the present disclosure provide methods, apparatuses, and computer program products for functional nonlinear Wiener-based signal filtering, with which an estimate of a target signal may be produced. Various embodiments involve generation and/or implementation of a functional Wiener filter for continuous time series data filtering, such as signal prediction or signal denoising. In various embodiments, the functional Wiener filter is configured through a reproducing kernel Hilbert space employing a similarity measure that embeds signal statistical information, such as the correntropy measure. With this, the functional Wiener filter is uniquely applicable to the space of nonlinear mappings.

Abstract: Various embodiments are directed to configuring or training deep neural network (DNN) machine learning models comprising one or more hidden layers and an output layer. Various embodiments provide technical advantages in training DNN machine learning models, including improved computational efficiency and guaranteed optimality. In one embodiment, an example method includes identifying a nonlinear-model-based representation for each hidden layer, which may be a Bank of Wiener Models, a nonlinear units of the hidden layer, and/or the like. The method further includes individually and sequentially configuring the hidden layers, each configured by determining a correlation measure (e.g., a correlation ratio) between the layer output and a target signal. Parameters of the particular hidden layer are modified by maximizing the correlation measure to yield maximal correlation over the space of functions.

Abstract: Various examples related to real time detection with recurrent networks are presented. These can be utilized in automatic insect recognition to provide accurate and rapid in situ identification. In one example, among others, a method includes training parameters of a kernel adaptive autoregressive-moving average (KAARMA) using a signal of an input space. The signal can include source information in its time varying structure. A surrogate embodiment of the trained KAARMA can be determined based upon clustering or digitizing of the input space, binarization of the trained KAARMA state and a transition table using the outputs of the trained KAARMA for each input in the training set. A recurrent network detector can then be implemented in processing circuitry (e.g., flip-flops, FPGA, ASIC, or dedicated VLSI) based upon the surrogate embodiment of the KAARMA The recurrent network detector can be configured to identify a signal class.

Abstract: Embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for training a machine learning model comprising a hidden module and an output module and configured for identifying one of a plurality of original labels for an input. In accordance with one embodiment, a method is provided that includes generating sufficiently-labeled data comprising example-pairs each associated with a sufficient label. The sufficient label of an example-pair indicates whether a first and a second input example have the same original label. The method further includes training the hidden module using the sufficiently-labeled data, and subsequently, training the output module using a plurality of input examples each having an original label. The plurality of input examples may be a plurality of fully-labeled data. The method further includes automatically providing the resulting trained machine learning model for use in prediction tasks.

Abstract: Systems and methods for monitoring uterus contraction activity and progress of labor. The system of the subject invention can comprises (1) a plurality of sensors; (2) an amplifying/filtering means; (3) a computing means; and (4) a graphical user interface. Accurate clinical data, which can be extracted and provided to the user in real-time using the system of the invention, include without limitation, progress of labor, prediction and monitoring of preterm labor, and intrauterine pressure prediction. In a preferred embodiment, the system of the invention includes an intelligence means, such as a neural network system, to analyze and interpret clinical data for use in clinical diagnosis as well as delivery strategy.

Abstract: A system and method for monitoring a patient's compliance with a medication regimen includes an electronic tag integral with or attached to a medicine delivery device such as a capsule, the tag haying an antenna and a receiver/transmitter, the system also including a reader positioned externally for detecting the presence and location of the delivery device in the patient.

Abstract: Various methods and systems are related to pulse-based automatic gain control. In one example, pulse-based automatic gain control (AGC) includes a variable gain amplifier (VGA) configured to amplify an analog input signal to generate an analog output signal based upon an amplification control signal; an integrate-and-fire (IF) sampler configured to generate a pulse train corresponding to the analog output signal; and a gain adjustment configured to generate the amplification control signal based upon a comparison of time between pulses of the pulse train to a reference time. In another example, a method includes determining time between pulses of a pulse train corresponding to an analog output signal from a VGA; generating an amplification control signal based upon a comparison of the time between pulses of the pulse train to a reference time; and adjusting amplification of the VGA in response to the amplification control signal.

Abstract: Various examples related to automatically composing universal filters are presented. In one example, among others, a system includes processing circuitry that can organize data received by the system into clusters or quasi-orthogonal regions, which are organized based upon a centroid threshold distance. The data can be organized by applying a cluster and retain operation, a cluster and merge operation or a split and retain operation. The system can then determine filter weights based at least in part upon centers of the clusters; update a content addressable filter bank (CAFB) based upon the filter weights; and filter subsequently received data based upon the CAFB. In another example, a method includes receiving and organizing initial data into clusters or quasi-orthogonal regions; determining filter weights based at least in part upon centers of the clusters; updating a CAFB based upon the filter weights; and receiving and filtering subsequent data based upon the CAFB.

Abstract: A system and method for monitoring a patient's compliance with a medication regimen includes an electronic tag integral with or attached to a medicine delivery device such as a capsule, the tag having an antenna and a receiver/transmitter, the system also including a reader positioned externally for detecting the presence and location of the delivery device in the patient.

Abstract: Various examples are provided related to speech recognition. In one example, a method includes converting an auditory signal into a pulse train, segmenting the pulse train into a series of frames having a predefined duration, and identifying a portion of the auditory signal by applying at least a portion of the series of frames segmented from the pulse train to a kernel adaptive autoregressive-moving-average (KAARMA) network. In another example, a speech recognition system includes processing circuitry configured to convert an auditory signal into a pulse train, segment the pulse train into a secured of frames, and identifying a portion of the auditory signal by applying at least a portion of the series of frames segmented from the pulse train to a KAARMA network. The series of frames segmented from the pulse train can be applied to a KAARMA chain including a plurality of KAARMA networks for identification.

Abstract: Various examples of devices, methods and systems related to pulse based arithmetic units. In one example, a pulse domain device includes an augend area calculator to provide an augend area output for an augend pulse train; an addend area calculator to provide an addend area output for an addend pulse train; a resultant sum area (RSA) decoder to provide a RSA output using the augend and addend area outputs; and a pulse timing calculator to provide RSA output pulse timing. In another example, a pulse domain device includes a multiplicand area calculator to provide an multiplicand area output for a multiplicand pulse train; a multiplier area calculator to provide a multiplier area output for a multiplier pulse train; a resultant product area (RPA) decoder to provide a RPA output using the multiplicand and multiplier area outputs; and a pulse timing calculator to provide RPA output pulse timing.

Abstract: A system and method for monitoring a patient's compliance with a medication regimen includes an electronic tag integral with or attached to a medicine delivery device such as a capsule, the tag having an antenna and a receiver/transmitter, the system also including a reader positioned externally for detecting the presence and location of the delivery device in the patient.

Abstract: A system and method for monitoring a patient's compliance with a medication regimen includes an electronic tag integral with or attached to a medicine delivery device such as a capsule, the tag having an antenna and a receiver/transmitter, the system also including a reader positioned externally for detecting the presence and location of the delivery device in the patient.

Abstract: Systems and methods for monitoring uterus contraction activity and progress of labor. The system of the subject invention can comprises (1) a plurality of sensors; (2) an amplifying/filtering means; (3) a computing means; and (4) a graphical user interface. Accurate clinical data, which can be extracted and provided to the user in real-time using the system of the invention, include without limitation, progress of labor, prediction and monitoring of preterm labor, and intrauterine pressure prediction. In a preferred embodiment, the system of the invention includes an intelligence means, such as a neural network system, to analyze and interpret clinical data for use in clinical diagnosis as well as delivery strategy.

Abstract: Various examples related to real time detection with recurrent networks are presented. These can be utilized in automatic insect recognition to provide accurate and rapid in situ identification. In one example, among others, a method includes training parameters of a kernel adaptive autoregressive-moving average (KAARMA) using a signal of an input space. The signal can include source information in its time varying structure. A surrogate embodiment of the trained KAARMA can be determined based upon clustering or digitizing of the input space, binarization of the trained KAARMA state and a transition table using the outputs of the trained KAARMA for each input in the training set. A recurrent network detector can then be implemented in processing circuitry (e.g., flip-flops, FPGA, ASIC, or dedicated VLSI) based upon the surrogate embodiment of the KAARMA The recurrent network detector can be configured to identify a signal class.

Abstract: Various examples related to automatically composing universal filters are presented. In one example, among others, a system includes processing circuitry that can organize data received by the system into clusters or quasi-orthogonal regions, which are organized based upon a centroid threshold distance. The data can be organized by applying a cluster and retain operation, a cluster and merge operation or a split and retain operation. The system can then determine filter weights based at least in part upon centers of the clusters; update a content addressable filter bank (CAFB) based upon the filter weights; and filter subsequently received data based upon the CAFB. In another example, a method includes receiving and organizing initial data into clusters or quasi-orthogonal regions; determining filter weights based at least in part upon centers of the clusters; updating a CAFB based upon the filter weights; and receiving and filtering subsequent data based upon the CAFB.

Abstract: Various methods and systems are related to pulse-based automatic gain control. In one example, pulse-based automatic gain control (AGC) includes a variable gain amplifier (VGA) configured to amplify an analog input signal to generate an analog output signal based upon an amplification control signal; an integrate-and-fire (IF) sampler configured to generate a pulse train corresponding to the analog output signal; and a gain adjustment configured to generate the amplification control signal based upon a comparison of time between pulses of the pulse train to a reference time. In another example, a method includes determining time between pulses of a pulse train corresponding to an analog output signal from a VGA; generating an amplification control signal based upon a comparison of the time between pulses of the pulse train to a reference time; and adjusting amplification of the VGA in response to the amplification control signal.

Abstract: Various examples are provided related to speech recognition. In one example, a method includes converting an auditory signal into a pulse train, segmenting the pulse train into a series of frames having a predefined duration, and identifying a portion of the auditory signal by applying at least a portion of the series of frames segmented from the pulse train to a kernel adaptive autoregressive-moving-average (KAARMA) network. In another example, a speech recognition system includes processing circuitry configured to convert an auditory signal into a pulse train, segment the pulse train into a secured of frames, and identifying a portion of the auditory signal by applying at least a portion of the series of frames segmented from the pulse train to a KAARMA network. The series of frames segmented from the pulse train can be applied to a KAARMA chain including a plurality of KAARMA networks for identification.

Abstract: Various examples of devices, methods and systems related to pulse based arithmetic units. In one example, a pulse domain device includes an augend area calculator to provide an augend area output for an augend pulse train; an addend area calculator to provide an addend area output for an addend pulse train; a resultant sum area (RSA) decoder to provide a RSA output using the augend and addend area outputs; and a pulse timing calculator to provide RSA output pulse timing. In another example, a pulse domain device includes a multiplicand area calculator to provide an multiplicand area output for a multiplicand pulse train; a multiplier area calculator to provide a multiplier area output for a multiplier pulse train; a resultant product area (RPA) decoder to provide a RPA output using the multiplicand and multiplier area outputs; and a pulse timing calculator to provide RPA output pulse timing.

Abstract: Systems and methods for monitoring uterus contraction activity and progress of labor. The system of the subject invention can comprises (1) a plurality of sensors; (2) an amplifying/filtering means; (3) a computing means; and (4) a graphical user interface. Accurate clinical data, which can be extracted and provided to the user in real-time using the system of the invention, include without limitation, progress of labor, prediction and monitoring of preterm labor, and intrauterine pressure prediction. In a preferred embodiment, the system of the invention includes an intelligence means, such as a neural network system, to analyze and interpret clinical data for use in clinical diagnosis as well as delivery strategy.