An official website of the United States government
With recent advances in Deep Learning (DL) models, the healthcare domain has seen an increased adoption of neural networks for clinical diagnosis, monitoring, and prediction. Deep Learning models have been developed for various tasks using 1D (one-dimensional) time-series signals. Time-series healthcare data, typically collected through sensors, have specific structures and characteristics such as frequency and amplitude. The nature of these features, including varying sampling rates that depend on the instruments used for sensing, poses challenges in handling them. Electrocardiograms (ECG), a class of 1D time-series signals representing the electrical activity of the heart, have been used to develop heart condition classification decision support systems. The sampling rate of these signals, influenced by different ECG instruments as well as their calibrations, can greatly impact the learning functions of deep learning models and subsequently, their decision outcomes. This hinders the development and deployment of generalized, DL-based ECG classifiers that can work with data from a variety of ECG instruments, particularly when the sampling rate of the training data remains unknown to users. Moreover, DL models are not designed to recognize the sampling rate of the testing data on which they are being deployed, further complicating their effective application across diverse clinical settings. In this study, we investigated the effect of different sampling rates of time-series ECG signals on DL-based ECG classifiers. To the best of our knowledge, this is the first work to understand how varying sampling rates affect the performance of DL-based models for classifying 1D time-series ECG signals. Through our comprehensive experiments, we showed that accuracy can drop by as much as 20% when the training and testing sampling rates are different. We provide visual explanations to understand the differences in learned model features through activation maps when the sampling rates for training and testing data are different. We also investigated potential strategies to address the challenges posed by different sampling rates: (i) transfer learning, (ii) resampling, and (iii) training a DL model using ECG data at different sampling rates.
more »
« less
Toward Sampling for Deep Learning Model Diagnosis
Deep learning (DL) models have achieved paradigm-changing performance in many fields with high dimensional data, such as images, audio, and text. However, the black-box nature of deep neural networks is not only a barrier to adoption in applications such as medical diagnosis, where interpretability is essential, but it also impedes diagnosis of under performing models. The task of diagnosing or explaining DL models requires the computation of additional artifacts, such as activation values and gradients. These artifacts are large in volume, and their computation, storage, and querying raise significant data management challenges. In this paper, we develop a novel data sampling technique that produces approximate but accurate results for these model debugging queries. Our sampling technique utilizes the lower dimension representation learned by the DL model and focuses on model decision boundaries for the data in this lower dimensional space.
more »
« less
- PAR ID:
- 10184821
- Date Published:
- Journal Name:
- 2020 IEEE 36th International Conference on Data Engineering (ICDE)
- Page Range / eLocation ID:
- 1910 to 1913
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Deep learning (DL) is a popular technique for building models from large quantities of data such as pictures, videos, messages generated from edges devices at rapid pace all over the world. It is often infeasible to migrate large quantities of data from the edges to centralized data center(s) over WANs for training due to privacy, cost, and performance reasons. At the same time, training large DL models on edge devices is infeasible due to their limited resources. An attractive alternative for DL training distributed data is to use micro-clouds---small-scale clouds deployed near edge devices in multiple locations. However, micro-clouds present the challenges of both computation and network resource heterogeneity as well as dynamism. In this paper, we introduce DLion, a new and generic decentralized distributed DL system designed to address the key challenges in micro-cloud environments, in order to reduce overall training time and improve model accuracy. We present three key techniques in DLion: (1) Weighted dynamic batching to maximize data parallelism for dealing with heterogeneous and dynamic compute capacity, (2) Per-link prioritized gradient exchange to reduce communication overhead for model updates based on available network capacity, and (3) Direct knowledge transfer to improve model accuracy by merging the best performing model parameters. We build a prototype of DLion on top of TensorFlow and show that DLion achieves up to 4.2X speedup in an Amazon GPU cluster, and up to 2X speed up and 26% higher model accuracy in a CPU cluster over four state-of-the-art distributed DL systems.more » « less
-
Deep learning (DL) has attracted interest in healthcare for disease diagnosis systems in medical imaging analysis (MedIA) and is especially applicable in Big Data environments like federated learning (FL) and edge computing. However, there is little research into mitigating the vulnerabilities and robustness of such systems against adversarial attacks, which can force DL models to misclassify, leading to concerns about diagnosis accuracy. This paper aims to evaluate the robustness and scalability of DL models for MedIA applications against adversarial attacks while ensuring their applicability in FL settings with Big Data. We fine-tune three state-of-the-art transfer learning models, DenseNet121, MobileNet-V2, and ResNet50, on several MedIA datasets of varying sizes and show that they are effective at disease diagnosis. We then apply the Fast Gradient Sign Method (FGSM) to attack the models and utilize adversarial training (AT) and knowledge distillation to defend them. We provide a performance comparison of the original transfer learning models and the defended models on the clean and perturbed data. The experimental results show that the defensive techniques can improve the robustness of the models to the FGSM attack and be scaled for Big Data as well as utilized for edge computing environments.more » « less
-
Deep learning (DL) is of great interest in psychiatry due its potential yet largely untapped ability to utilize multidimensional datasets (such as fMRI data) to predict clinical outcomes. Typical DL methods, however, have strong assumptions, such as large datasets and underlying model opaqueness, that are suitable for natural image prediction problems but not medical imaging. Here we describe three relatively novel DL approaches that may help accelerate its incorporation into mainstream psychiatry research and ultimately bring it into the clinic as a prognostic tool. We first introduce two methods that can reduce the amount of training data required to develop accurate models. These may prove invaluable for fMRI-based DL given the time and monetary expense required to acquire neuroimaging data. These methods are (1) transfer learning − the ability of deep learners to incorporate knowledge learned from one data source (e.g., fMRI data from one site) and apply it toward learning from a second data source (e.g., data from another site), and (2) data augmentation (via Mixup) − a self-supervised learning technique in which “virtual” instances are created. We then discuss explainable artificial intelligence (XAI), i.e., tools that reveal what features (and in what combinations) deep learners use to make decisions. XAI can be used to solve the “black box” criticism common in DL and reveal mechanisms that ultimately produce clinical outcomes. We expect these techniques to greatly enhance the applicability of DL in psychiatric research and help reveal novel mechanisms and potential pathways for therapeutic intervention in mental illness.more » « less
-
Deep learning (DL) is growing in popularity for many data analytics applications, including among enterprises. Large business-critical datasets in such settings typically reside in RDBMSs or other data systems. The DB community has long aimed to bring machine learning (ML) to DBMS-resident data. Given past lessons from in-DBMS ML and recent advances in scalable DL systems, DBMS and cloud vendors are increasingly interested in adding more DL support for DB-resident data. Recently, a new parallel DL model selection execution approach called Model Hopper Parallelism (MOP) was proposed. In this paper, we characterize the particular suitability of MOP for DL on data systems, but to bring MOP-based DL to DB-resident data, we show that there is no single "best" approach, and an interesting tradeoff space of approaches exists. We explain four canonical approaches and build prototypes upon Greenplum Database, compare them analytically on multiple criteria (e.g., runtime efficiency and ease of governance) and compare them empirically with large-scale DL workloads. Our experiments and analyses show that it is non-trivial to meet all practical desiderata well and there is a Pareto frontier; for instance, some approaches are 3x-6x faster but fare worse on governance and portability. Our results and insights can help DBMS and cloud vendors design better DL support for DB users. All of our source code, data, and other artifacts are available at https://github.com/makemebitter/cerebro-ds.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ICDE48307.2020.00201
