skip to main content

Title: Validation of Temporal Scoring Metrics for Automatic Seizure Detection
There has been a lack of standardization of the evaluation of sequential decoding systems in the bioengineering community. Assessment of the accuracy of a candidate system’s segmentations and measurement of a false alarm rate are examples of two performance metrics that are very critical to the operational acceptance of a technology. However, measurement of such quantities in a consistent manner require many scoring software implementation details to be resolved. Results can be highly sensitive to these implementation details. In this paper, we revisit and evaluate a set of metrics introduced in our open source scoring software for sequential decoding of multichannel signals. This software was used to rank sixteen automatic seizure detection systems recently developed for the 2020 Neureka® Epilepsy Challenge. The systems produced by the participants provided us with a broad range of design variations that allowed assessment of the consistency of the proposed metrics. We present a comprehensive assessment of four of these new metrics and validate our findings with our previous studies. We also validate a proposed new metric, time-aligned event scoring, that focuses on the segmentation behavior of an algorithm. We demonstrate how we can gain insight into the performance of a system using these metrics.
Authors:
; ; ; ; ;
Editors:
Obeid, Iyad; Selesnick, Ivan; Picone, Joseph
Award ID(s):
1827565
Publication Date:
NSF-PAR ID:
10199681
Journal Name:
Proceedings of the IEEE Signal Processing in Medicine and Biology Symposium (SPMB)
Volume:
1
Issue:
1
Page Range or eLocation-ID:
1-5
ISSN:
2473-716X
Sponsoring Org:
National Science Foundation
More Like this
  1. ABSTRACT We present MeqSilhouette v2.0 (MeqSv2), a fully polarimetric, time-and frequency-resolved synthetic data generation software for simulating millimetre (mm) wavelength very long baseline interferometry (VLBI) observations with heterogeneous arrays. Synthetic data are a critical component in understanding real observations, testing calibration and imaging algorithms, and predicting performance metrics of existing or proposed sites. MeqSv2 applies physics-based instrumental and atmospheric signal corruptions constrained by empirically derived site and station parameters to the data. The new version is capable of applying instrumental polarization effects and various other spectrally resolved effects using the Radio Interferometry Measurement Equation (RIME) formalism and produces synthetic data compatiblemore »with calibration pipelines designed to process real data. We demonstrate the various corruption capabilities of MeqSv2 using different arrays, with a focus on the effect of complex bandpass gains on closure quantities for the EHT at 230 GHz. We validate the frequency-dependent polarization leakage implementation by performing polarization self-calibration of synthetic EHT data using PolSolve. We also note the potential applications for cm-wavelength VLBI array analysis and design and future directions.« less
  2. Obeid, Iyad ; Selesnick, Ivan ; Picone, Joseph (Ed.)
    The evaluation of machine learning algorithms in biomedical fields for ap-plications involving sequential data lacks both rigor and standardization. Common quantitative scalar evaluation metrics such as sensitivity and specificity can often be misleading and not accurately integrate application requirements. Evaluation metrics must ultimately reflect the needs of users yet be sufficiently sensitive to guide algorithm development. For example, feedback from critical care clinicians who use automated event detection software in clinical applications has been overwhelmingly emphatic that a low false alarm rate, typically measured in units of the number of errors per 24 hours, is the single most important criterionmore »for user acceptance. Though using a single metric is not often as insightful as examining performance over a range of operating conditions, there is, nevertheless, a need for a sin-gle scalar figure of merit. In this chapter, we discuss the deficiencies of existing metrics for a seizure detection task and propose several new metrics that offer a more balanced view of performance. We demonstrate these metrics on a seizure detection task based on the TUH EEG Seizure Corpus. We introduce two promising metrics: (1) a measure based on a concept borrowed from the spoken term detection literature, Actual Term-Weighted Value, and (2) a new metric, Time-Aligned Event Scoring (TAES), that accounts for the temporal align-ment of the hypothesis to the reference annotation. We demonstrate that state of the art technology based on deep learning, though impressive in its performance, still needs significant improvement before it will meet very strict user acceptance guidelines.« less
  3. Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)
    The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3]more »as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should produce identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues.« less
  4. Abstract

    This paper describes outcomes of the 2019 Cryo-EM Model Challenge. The goals were to (1) assess the quality of models that can be produced from cryogenic electron microscopy (cryo-EM) maps using current modeling software, (2) evaluate reproducibility of modeling results from different software developers and users and (3) compare performance of current metrics used for model evaluation, particularly Fit-to-Map metrics, with focus on near-atomic resolution. Our findings demonstrate the relatively high accuracy and reproducibility of cryo-EM models derived by 13 participating teams from four benchmark maps, including three forming a resolution series (1.8 to 3.1 Å). The results permit specificmore »recommendations to be made about validating near-atomic cryo-EM structures both in the context of individual experiments and structure data archives such as the Protein Data Bank. We recommend the adoption of multiple scoring parameters to provide full and objective annotation and assessment of the model, reflective of the observed cryo-EM map density.

    « less
  5. Controller design and their software implementations are usually done in isolated design spaces using respective COTS design tools. However, this separation of concerns can lead to long debugging and integration phases. This is because assumptions made about the implementation platform during the design phase—e.g., related to timing—might not hold in practice, thereby leading to unacceptable control performance. In order to address this, several control/architecture co-design techniques have been proposed in the literature. However, their adoption in practice has been hampered by the lack of design flows using commercial tools. To the best of our knowledge, this is the first articlemore »that implements such a co-design method using commercially available design tools in an automotive setting, with the aim of minimally disrupting existing design flows practiced in the industry. The goal of such co-design is to jointly determine controller and platform parameters in order to avoid any design-implementation gap , thereby minimizing implementation time testing and debugging. Our setting involves distributed implementations of control algorithms on automotive electronic control units ( ECUs ) communicating via a FlexRay bus. The co-design and the associated toolchain Co-Flex jointly determines controller and FlexRay parameters (that impact signal delays) in order to optimize specified design metrics. Co-Flex seamlessly integrates the modeling and analysis of control systems in MATLAB/Simulink with platform modeling and configuration in SIMTOOLS/SIMTARGET that is used for configuring FlexRay bus parameters. It automates the generation of multiple Pareto-optimal design options with respect to the quality of control and the resource usage, that an engineer can choose from. In this article, we outline a step-by-step software development process based on Co-Flex tools for distributed control applications. While our exposition is automotive specific, this design flow can easily be extended to other domains.« less