Abstract: A machine learning model for stratification of early diabetic foot complication using thermogram images is provided that is operable to predictively diagnose a risk for diabetic foot ulceration formation via receiving a thermogram of a foot; identifying, via a machine learning model, a risk factor of diabetic foot ulceration on the foot; and outputting, from the machine learning model, the risk factor as a diagnosis.

Abstract: Systems, methods, apparatuses, and computer program products for real-time, personalized cardiac monitoring for early detection of heart-beat anomalies. One method may include a device selecting at least one set of clean ECG segments, and at least one set of corrupted ECG segments; transforming at least one of a one-dimensional or two-dimensional version cycle-CANs trained to transform ECG signals from at least one different dataset; and restoring the at least one set of corrupted ECG segments based upon a one- or two-dimensional operational cycle-GAN trained over the batches.

Abstract: Certain embodiments may generally relate to structural damage detection. An embodiment may be directed to method for identifying a presence and a location of structural damage. Such method may include training a convolutional neural network (CNN) for a joint of a structure, sending instructions to a modal shaker to induce an input to the structure, receiving, as a result of the induced input, a raw acceleration signal at the joint, computing, based on the trained CNN and the raw acceleration signal, an index value of the joint, and identifying, according to the index value, a presence of a location of structural damage of the structure. In a further embodiment, the index value represents a likelihood of damage at the joint.

Abstract: Systems, methods, apparatuses, and computer program products for neural networks. In accordance with some example embodiments, an operational neuron model may comprise an artificial neuron comprising a composite nodal operator, a pool-operator, and an activation function operator. The nodal operator may comprise a linear function or non-linear function. In accordance with certain example embodiments, a generative neuron model may include a composite nodal-operator generated during the training using Taylor polynomial approximation without restrictions. In accordance with various example embodiments, a self-organized operational neural network (Self-ONN) may include one or more layers of generative neurons.

Abstract: Systems, methods, apparatuses, and computer program products for a machine learning paradigm. In accordance with some example embodiments, a self-organizing network may include one or more super neuron models with non-localized kernel operations. A set of additional parameters may define a spatial bias as the deviation of a kernel from the pixel location towards x- and y-direction for a kth output neuron connection to an ith neuron input map at layer l+1. This spatial bias may either be randomly set or may be optimized during the BP training. In either case, the network may benefit from such “non-localized” kernels that improve the receptive field size.

Abstract: Certain embodiments may generally relate to various techniques for machine learning. Feed-forward, fully-connected Artificial Neural Networks (ANNs), or the so-called Multi-Layer Perceptrons (MLPs) are well-known universal approximators. However, their learning performance may vary significantly depending on the function or the solution space that they attempt to approximate for learning. This is because they are based on a loose and crude model of the biological neurons promising only a linear transformation followed by a nonlinear activation function. Therefore, while they learn very well those problems with a monotonous, relatively simple and linearly separable solution space, they may entirely fail to do so when the solution space is highly nonlinear and complex. In order to address this drawback and also to accomplish a more generalized model of biological neurons and learning systems, Generalized Operational Perceptrons (GOPs) may be formed and they may encapsulate many linear and nonlinear operators.

Abstract: A method of detecting abnormal heartbeats includes providing a library of abnormal beat synthesis (ABS) filters, wherein each ABS filter corresponds to a specific cause of a cardiac problem. The method further includes obtaining an ECG of a normal heartbeat of a person and applying an ABS filter from the library of ABS filters to the ECG of the normal heartbeat of the person to generate a potential abnormal ECG. The method further includes monitoring a heartbeat of the person and classifying each heartbeat as either normal or abnormal.

Abstract: A method and apparatus may include receiving a signal from a motor. The signal is received while the motor is operating. The method also includes performing a pre-processing of the signal. The method also includes inputting the signal to a 1D convolutional neural network. The method also includes detecting a fault of the motor based on the output of the neural network.

Abstract: Certain embodiments may generally relate to various techniques for machine learning. Feed-forward, fully-connected Artificial Neural Networks (ANNs), or the so-called Multi-Layer Perceptrons (MLPs) are well-known universal approximators. However, their learning performance may vary significantly depending on the function or the solution space that they attempt to approximate for learning. This is because they are based on a loose and crude model of the biological neurons promising only a linear transformation followed by a nonlinear activation function. Therefore, while they learn very well those problems with a monotonous, relatively simple and linearly separable solution space, they may entirely fail to do so when the solution space is highly nonlinear and complex. In order to address this drawback and also to accomplish a more generalized model of biological neurons and learning systems, Generalized Operational Perceptrons (GOPs) may be formed and they may encapsulate many linear and nonlinear operators.

Abstract: Certain embodiments may generally relate to structural damage detection. An embodiment may be directed to method for identifying a presence and a location of structural damage. Such method may include training a convolutional neural network (CNN) for a joint of a structure, sending instructions to a modal shaker to induce an input to the structure, receiving, as a result of the induced input, a raw acceleration signal at the joint, computing, based on the trained CNN and the raw acceleration signal, an index value of the joint, and identifying, according to the index value, a presence of a location of structural damage of the structure. In a further embodiment, the index value represents a likelihood of damage at the joint.

Abstract: A method and apparatus may include receiving patient-specific data of a patient. The method can also include inputting the patient-specific data into an input layer of a 1D convolutional neural network. The method can also include inputting labels corresponding to the patient-specific data into an output layer of the 1D convolutional neural network. The method can also include training the 1D convolutional neural network with the inputted patient-specific data and labels. The 1D convolutional neural network is configured to detect abnormality within patient-specific data.

Abstract: A method and apparatus may include receiving a signal from a motor. The signal is received while the motor is operating. The method also includes performing a pre-processing of the signal. The method also includes inputting the signal to a 1D convolutional neural network. The method also includes detecting a fault of the motor based on the output of the neural network.