An official website of the United States government
Abstract Robotic assistive or rehabilitative devices are promising aids for people with neurological disorders as they help regain normative functions for both upper and lower limbs. However, it remains challenging to accurately estimate human intent or residual efforts non-invasively when using these robotic devices. In this article, we propose a deep learning approach that uses a brightness mode, that is, B-mode, of ultrasound (US) imaging from skeletal muscles to predict the ankle joint net plantarflexion moment while walking. The designed structure of customized deep convolutional neural networks (CNNs) guarantees the convergence and robustness of the deep learning approach. We investigated the influence of the US imaging’s region of interest (ROI) on the net plantarflexion moment prediction performance. We also compared the CNN-based moment prediction performance utilizing B-mode US and sEMG spectrum imaging with the same ROI size. Experimental results from eight young participants walking on a treadmill at multiple speeds verified an improved accuracy by using the proposed US imaging + deep learning approach for net joint moment prediction. With the same CNN structure, compared to the prediction performance by using sEMG spectrum imaging, US imaging significantly reduced the normalized prediction root mean square error by 37.55% ( $ p $ < .001) and increased the prediction coefficient of determination by 20.13% ( $ p $ < .001). The findings show that the US imaging + deep learning approach personalizes the assessment of human joint voluntary effort, which can be incorporated with assistive or rehabilitative devices to improve clinical performance based on the assist-as-needed control strategy.
more »
« less
A Stochastic Approach to Handle Non-Determinism in Deep Learning-Based Design Rule Violation Predictions
Deep learning is a promising approach to early DRV (Design Rule Violation) prediction. However, non-deterministic parallel routing hampers model training and degrades prediction accuracy. In this work, we propose a stochastic approach, called LGC-Net, to solve this problem. In this approach, we develop new techniques of Gaussian random field layer and focal likelihood loss function to seamlessly integrate Log Gaussian Cox process with deep learning. This approach provides not only statistical regression results but also classification ones with different thresholds without retraining. Experimental results with noisy training data on industrial designs demonstrate that LGC-Net achieves significantly better accuracy of DRV density prediction than prior arts.
more »
« less
- Award ID(s):
- 2106725
- PAR ID:
- 10464458
- Date Published:
- Journal Name:
- IEEE/ACM International Conference on Computer-Aided Design
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Deep learning holds a great promise of revolutionizing healthcare and medicine. Unfortunately, various inference attack models demonstrated that deep learning puts sensitive patient information at risk. The high capacity of deep neural networks is the main reason behind the privacy loss. In particular, patient information in the training data can be unintentionally memorized by a deep network. Adversarial parties can extract that information given the ability to access or query the network. In this paper, we propose a novel privacy-preserving mechanism for training deep neural networks. Our approach adds decaying Gaussian noise to the gradients at every training iteration. This is in contrast to the mainstream approach adopted by Google's TensorFlow Privacy, which employs the same noise scale in each step of the whole training process. Compared to existing methods, our proposed approach provides an explicit closed-form mathematical expression to approximately estimate the privacy loss. It is easy to compute and can be useful when the users would like to decide proper training time, noise scale, and sampling ratio during the planning phase. We provide extensive experimental results using one real-world medical dataset (chest radiographs from the CheXpert dataset) to validate the effectiveness of the proposed approach. The proposed differential privacy based deep learning model achieves significantly higher classification accuracy over the existing methods with the same privacy budget.more » « less
-
The Finite-Difference Time-Domain (FDTD) method is a numerical modeling technique used by researchers as one of the most accurate methods to simulate the propagation of an electromagnetic wave through an object over time. Due to the nature of the method, FDTD can be computationally expensive when used in complex setting such as light propagation in highly heterogenous object such as the imaging process of tissues. In this paper, we explore a Deep Learning (DL) model that predicts the evolution of an electromagnetic field in a heterogeneous medium. In particular, modeling for propagation of a Gaussian beam in skin tissue layers. This is relevant for the characterization of microscopy imaging of tissues. Our proposed model named FDTD-net, is based on the U-net architecture, seems to perform the prediction of the electric field (EF) with good accuracy and faster when compared to the FDTD method. A dataset of different geometries was created to simulate the propagation of the electric field. The propagation of the electric field was initially generated using the traditional FDTD method. This data set was used for training and testing of the FDTD-net. The experiments show that the FDTD-net learns the physics related to the propagation of the source in the heterogeneous objects, and it can capture changes in the field due to changes in the object morphology. As a result, we present a DL model that can compute a propagated electric field in less time than the traditional method.more » « less
-
null (Ed.)Due to Wildfire's huge destructive impacts on agriculture and food production, wildlife habitat, climate, human life and ecosystem, timely discovery of fires enable swift response to fires before they go out of control, in order to minimize the resulting damage and impacts. One of the emerging technologies for fire monitoring is deploying Unmanned Aerial Vehicles, due to their high flexibility and maneuverability, less human risk, and on-demand high quality imaging capabilities. In order to realize a real-time system for fire detection and expansion analysis, fast and high-accuracy image-processing algorithms are required. Several studies have shown that deep learning methods can provide the most accurate response, however the training time can be prohibitively long, especially when using online learning for constant refinement of the developed model. Another challenge is the lack of large datasets for training a deep learning algorithm. In this respect, we propose to use a pretrained mobileNetV2 architecture to implement transfer learning, which requires a smaller dataset and reduces the computational complexity while not compromising the accuracy. In addition, we conduct an effective data augmentation pipeline to simulate some extreme scenarios, which could promise the robustness of our approach. The testing results illustrate that our method maintains a high identification accuracy in different situations - original dataset (99.7%), adding Gaussian blurred (95.3%), and additive Gaussian noise (99.3%).more » « less
-
Abstract Nucleic acid-binding proteins (NABPs), including DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs), play important roles in essential biological processes. To facilitate functional annotation and accurate prediction of different types of NABPs, many machine learning-based computational approaches have been developed. However, the datasets used for training and testing as well as the prediction scopes in these studies have limited their applications. In this paper, we developed new strategies to overcome these limitations by generating more accurate and robust datasets and developing deep learning-based methods including both hierarchical and multi-class approaches to predict the types of NABPs for any given protein. The deep learning models employ two layers of convolutional neural network and one layer of long short-term memory. Our approaches outperform existing DBP and RBP predictors with a balanced prediction between DBPs and RBPs, and are more practically useful in identifying novel NABPs. The multi-class approach greatly improves the prediction accuracy of DBPs and RBPs, especially for the DBPs with ~12% improvement. Moreover, we explored the prediction accuracy of single-stranded DNA binding proteins and their effect on the overall prediction accuracy of NABP predictions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
