This paper introduces TINA, a novel framework for implementing non Neural Network (NN) signal processing algorithms on NN accelerators such as GPUs, TPUs or FPGAs. The key to this approach is the concept of mapping mathematical and logic functions as a series of convolutional and fully connected layers. By mapping functions into such a small sub stack ofNN layers, it becomes possible to execute non-NN algorithms on NN hardware (HW) accelerators efficiently, as well as to ensure the portability of TINA implementations to any platform that supports such NN accelerators. Results show that TINA is highly competitive vs alternative frame-works, specifically for complex functions with iterations. For a Polyphase Filter Bank use case TINA shows GPU speedups of up to 80x vs a CPU baseline with NumPy compared to 8x speedup achieved by alternative frameworks. The frame-work is open source and publicly available at httPs://github.com/ChristiaanBoe/TINA.@en

This paper offers a systematic method for creating medical knowledge-grounded patient records for use in activities involving differential diagnosis. Additionally, an assessment of machine learning models that can differentiate between various conditions based on given symptoms is also provided. We use a public disease-symptom data source called SymCat in combination with Synthea to construct the patients records. In order to increase the expressive nature of the synthetic data, we use a medically-standardized symptom modeling method called NLICE to augment the synthetic data with additional contextual information for each condition. In addition, Naive Bayes and Random Forest models are evaluated and compared on the synthetic data. The paper shows how to successfully construct SymCat-based and NLICE-based datasets. We also show results for the effectiveness of using the datasets to train predictive disease models. The SymCat-based dataset is able to train a Naive Bayes and Random Forest model yielding a 58.8% and 57.1% Top-1 accuracy score, respectively. In contrast, the NLICE-based dataset improves the results, with a Top-1 accuracy of 82.0% and Top-5 accuracy values of more than 90% for both models. Our proposed data generation approach solves a major barrier to the application of artificial intelligence methods in the healthcare domain. Our novel NLICE symptom modeling approach addresses the incomplete and insufficient information problem in the current binary symptom representation approach.@en

Flexible ultrasound has emerged as the basis for wearable devices in healthcare. In this work, a flexible 1D phased transducer array has been proposed. This transducer array includes piezoelectric sensors underneath the transducer array, which detect its local curvature at different locations, corresponding to the positions of each piezoelectric sensor. Using FEA a simulation study was created, resulting in a deformed transducer array in which the number of curves and the number of sensors are varied. The piezoelectric sensors detect the local curvature resulting in a displacement map along the array. The sensing error of these sensors is calculated by taking the difference between the detected curvature from the sensors and the actual curvature the PCB was subjected to during the simulations. The results of these simulations show that, an increase of sensors results in a noticeable decrease in sensing error up to 9 sensors. Increasing the number of sensors after that point decreases the sensing error to a negligible value. The curvature information gathered from the piezoelectric sensors was then used to allow for the generation of focused ultrasound beams. To enable this, ultrasound beamforming algorithms were augmented to include curvature correction. These simulations showed that, despite a slight decrease in beam pressure of a curved transducer array compared to an uncurved array, the sensors can effectively detect and compensate for curvature in ultrasound transducer arrays.

@en