Human behavioral monitoring during sleep is essential for various medical applications. Majority ... more Human behavioral monitoring during sleep is essential for various medical applications. Majority of the contactless human pose estimation algorithms are based on RGB modality, causing ineffectiveness in in-bed pose estimation due to occlusions by blankets and varying illumination conditions. Long-wavelength infrared (LWIR) modality based pose estimation algorithms overcome the aforementioned challenges; however, ground truth pose generations by a human annotator under such conditions are not feasible. A feasible solution to address this issue is to transfer the knowledge learned from images with pose labels and no occlusions, and adapt it towards real world conditions (occlusions due to blankets). In this paper, we propose a novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images in real world conditions. Our experiments and analysis show the effectiveness of our a...
Topology optimization is the tool of choice for obtaining the initial design of structural compon... more Topology optimization is the tool of choice for obtaining the initial design of structural components. The resulting optimal design from topology optimization will be the input for subsequent structural optimizations with regard to shape, size, and layout. In reality, however, iterative solvers used in conventional SIMP (Simplified Isotropic Material with Penalization) based topology optimization schemes consume a very high computational power and therefore act as a bottleneck in the manufacturing process. In this work, an accelerated topology optimization technique based on deep learning is presented. Conditional Generative Adversarial Network (cGAN) architecture is used to predict the optimal topology of a given structure subject to a set of input parameters. This novel framework is showcased to generate initial truss designs for any combination of volume fractions and edge loading locations. Unlike prevalent topology optimization solvers, the proposed method obtains the accurate ...
A method for nonlinear material modeling and design using statistical learning is proposed to ass... more A method for nonlinear material modeling and design using statistical learning is proposed to assist in the mechanical analysis of structural materials. Conventional computational homogenization schemes are proven to underperform in analyzing the complex nonlinear behavior of such microstructures with finite deformations. Also, the higher computational cost of the existing homogenization schemes inspires the inception of a data-driven multiscale computational homogenization scheme. In this paper, a statistical nonlinear homogenization scheme is discussed to mitigate these issues using the Gaussian Process Regression technique. A data-driven model is trained for different strain states of microscale unit cells. In the macroscale, nonlinear response of the macroscopic structure is analyzed, for which the stresses and material responses are predicted by the trained surrogate model.
2021 IEEE International Symposium on Circuits and Systems (ISCAS), 2021
Diagnosing pre-existing heart diseases early in life is important as it helps prevent complicatio... more Diagnosing pre-existing heart diseases early in life is important as it helps prevent complications such as pulmonary hypertension, heart rhythm problems, blood clots, heart failure and sudden cardiac arrest. To identify such diseases, phonocardiogram (PCG) and electrocardiogram (ECG) waveforms convey important information. Therefore, effectively using these two modalities of data has the potential to improve the disease screening process. We evaluate this hypothesis on a subset of the PhysioNet Challenge 2016 Dataset which contains simultaneously acquired PCG and ECG recordings. Our novel dual-convolutional neural network based approach uses transfer learning to tackle the problem of having limited amounts of simultaneous PCG and ECG data that is publicly available, while having the potential to adapt to larger datasets. In addition, we introduce two main evaluation frameworks named record-wise and sample-wise evaluation which leads to a rich performance evaluation for the transfer...
Human behavioral monitoring during sleep is essential for various medical applications. Majority ... more Human behavioral monitoring during sleep is essential for various medical applications. Majority of the contactless human pose estimation algorithms are based on RGB modality, causing ineffectiveness in in-bed pose estimation due to occlusions by blankets and varying illumination conditions. Long-wavelength infrared (LWIR) modality based pose estimation algorithms overcome the aforementioned challenges; however, ground truth pose generations by a human annotator under such conditions are not feasible. A feasible solution to address this issue is to transfer the knowledge learned from images with pose labels and no occlusions, and adapt it towards real world conditions (occlusions due to blankets). In this paper, we propose a novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images in real world conditions. Our experiments and analysis show the effectiveness of our a...
Topology optimization is the tool of choice for obtaining the initial design of structural compon... more Topology optimization is the tool of choice for obtaining the initial design of structural components. The resulting optimal design from topology optimization will be the input for subsequent structural optimizations with regard to shape, size, and layout. In reality, however, iterative solvers used in conventional SIMP (Simplified Isotropic Material with Penalization) based topology optimization schemes consume a very high computational power and therefore act as a bottleneck in the manufacturing process. In this work, an accelerated topology optimization technique based on deep learning is presented. Conditional Generative Adversarial Network (cGAN) architecture is used to predict the optimal topology of a given structure subject to a set of input parameters. This novel framework is showcased to generate initial truss designs for any combination of volume fractions and edge loading locations. Unlike prevalent topology optimization solvers, the proposed method obtains the accurate ...
A method for nonlinear material modeling and design using statistical learning is proposed to ass... more A method for nonlinear material modeling and design using statistical learning is proposed to assist in the mechanical analysis of structural materials. Conventional computational homogenization schemes are proven to underperform in analyzing the complex nonlinear behavior of such microstructures with finite deformations. Also, the higher computational cost of the existing homogenization schemes inspires the inception of a data-driven multiscale computational homogenization scheme. In this paper, a statistical nonlinear homogenization scheme is discussed to mitigate these issues using the Gaussian Process Regression technique. A data-driven model is trained for different strain states of microscale unit cells. In the macroscale, nonlinear response of the macroscopic structure is analyzed, for which the stresses and material responses are predicted by the trained surrogate model.
2021 IEEE International Symposium on Circuits and Systems (ISCAS), 2021
Diagnosing pre-existing heart diseases early in life is important as it helps prevent complicatio... more Diagnosing pre-existing heart diseases early in life is important as it helps prevent complications such as pulmonary hypertension, heart rhythm problems, blood clots, heart failure and sudden cardiac arrest. To identify such diseases, phonocardiogram (PCG) and electrocardiogram (ECG) waveforms convey important information. Therefore, effectively using these two modalities of data has the potential to improve the disease screening process. We evaluate this hypothesis on a subset of the PhysioNet Challenge 2016 Dataset which contains simultaneously acquired PCG and ECG recordings. Our novel dual-convolutional neural network based approach uses transfer learning to tackle the problem of having limited amounts of simultaneous PCG and ECG data that is publicly available, while having the potential to adapt to larger datasets. In addition, we introduce two main evaluation frameworks named record-wise and sample-wise evaluation which leads to a rich performance evaluation for the transfer...
Uploads
Papers by Udith Haputhanthri