An official website of the United States government
Background Stress affects learning during training, and virtual reality (VR) based training systems that manipulate stress can improve retention and retrieval performance for firefighters. Brain imaging using functional Near Infrared Spectroscopy (fNIRS) can facilitate development of VR-based adaptive training systems that can continuously assess the trainee’s states of learning and cognition. Objective The aim of this study was to model the neural dynamics associated with learning and retrieval under stress in a VR-based emergency response training exercise. Methods Forty firefighters underwent an emergency shutdown training in VR and were randomly assigned to either a control or a stress group. The stress group experienced stressors including smoke, fire, and explosions during the familiarization and training phase. Both groups underwent a stress memory retrieval and no-stress memory retrieval condition. Participant’s performance scores, fNIRS-based neural activity, and functional connectivity between the prefrontal cortex (PFC) and motor regions were obtained for the training and retrieval phases. Results The performance scores indicate that the rate of learning was slower in the stress group compared to the control group, but both groups performed similarly during each retrieval condition. Compared to the control group, the stress group exhibited suppressed PFC activation. However, they showed stronger connectivity within the PFC regions during the training and between PFC and motor regions during the retrieval phases. Discussion While stress impaired performance during training, adoption of stress-adaptive neural strategies (i.e., stronger brain connectivity) were associated with comparable performance between the stress and the control groups during the retrieval phase.
more »
« less
Brain Activity-Based Metrics for Assessing Learning States in VR under Stress among Firefighters: An Explorative Machine Learning Approach in Neuroergonomics
The nature of firefighters’ duties requires them to work for long periods under unfavorable conditions. To perform their jobs effectively, they are required to endure long hours of extensive, stressful training. Creating such training environments is very expensive and it is difficult to guarantee trainees’ safety. In this study, firefighters are trained in a virtual environment that includes virtual perturbations such as fires, alarms, and smoke. The objective of this paper is to use machine learning methods to discern encoding and retrieval states in firefighters during a visuospatial episodic memory task and explore which regions of the brain provide suitable signals to solve this classification problem. Our results show that the Random Forest algorithm could be used to distinguish between information encoding and retrieval using features extracted from fNIRS data. Our algorithm achieved an F-1 score of 0.844 and an accuracy of 79.10% if the training and testing data are obtained at similar environmental conditions. However, the algorithm’s performance dropped to an F-1 score of 0.723 and accuracy of 60.61% when evaluated on data collected under different environmental conditions than the training data. We also found that if the training and evaluation data were recorded under the same environmental conditions, the RPM, LDLPFC, RDLPFC were the most relevant brain regions under non-stressful, stressful, and a mix of stressful and non-stressful conditions, respectively.
more »
« less
- Award ID(s):
- 2033592
- PAR ID:
- 10291684
- Date Published:
- Journal Name:
- Brain Sciences
- Volume:
- 11
- Issue:
- 7
- ISSN:
- 2076-3425
- Page Range / eLocation ID:
- 885
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Brain-inspired HyperDimensional (HD) computing emulates cognitive tasks by computing with long binary vectors–aka hypervectors–as opposed to computing with numbers. However, we observed that in order to provide acceptable classification accuracy on practical applications, HD algorithms need to be trained and tested on non-binary hypervectors. In this paper, we propose SearcHD, a fully binarized HD computing algorithm with a fully binary training. SearcHD maps every data points to a high-dimensional space with binary elements. Instead of training an HD model with non-binary elements, SearcHD implements a full binary training method which generates multiple binary hypervectors for each class. We also use the analog characteristic of non-volatile memories (NVMs) to perform all encoding, training, and inference computations in memory. We evaluate the efficiency and accuracy of SearcHD on a wide range of classification applications. Our evaluation shows that SearcHD can provide on average 31.1× higher energy efficiency and 12.8× faster training as compared to the state-of-the-art HD computing algorithms.more » « less
-
Abstract Satellite precipitation retrieval is inherently an underdetermined inverse problem where additional physical constraints could substantially enhance accuracy. While previous studies have explored static (pixel‐based/spatial‐context‐based) environmental variables at discrete satellite observation times, their temporal dynamic information remains underutilized. Building on our earlier finding that retrieval errors depend on storm progression (event stage), we propose a new, physically interpretable mechanism for improving retrievals, namely, leveraging environmental variables' temporal dynamics as proxies for event stages. Using IMERG satellite product and GV‐MRMS as ground‐truth over CONUS (2018–2020), we first demonstrate robust coevolution patterns of environmental variables and satellite errors throughout events, and show that these variables' temporal gradients reliably infer event stages. We then demonstrate that incorporating these variables and their gradients into a machine‐learning post‐processing framework improves retrieval accuracy. This work inspires and guides more thorough utilization of spatiotemporal atmospheric fields encoding rich physical information within advanced machine‐learning frameworks for further algorithm improvement.more » « less
-
The need for manual and detailed annotations limits the applicability of supervised deep learning algorithms in medical image analyses, specifically in the field of pathology. Semi-supervised learning (SSL) provides an effective way for leveraging unlabeled data to relieve the heavy reliance on the amount of labeled samples when training a model. Although SSL has shown good performance, the performance of recent state-of-the-art SSL methods on pathology images is still under study. The problem for selecting the most optimal data to label for SSL is not fully explored. To tackle this challenge, we propose a semi-supervised active learning framework with a region-based selection criterion. This framework iteratively selects regions for an-notation query to quickly expand the diversity and volume of the labeled set. We evaluate our framework on a grey-matter/white-matter segmentation problem using gigapixel pathology images from autopsied human brain tissues. With only 0.1% regions labeled, our proposed algorithm can reach a competitive IoU score compared to fully-supervised learning and outperform the current state-of-the-art SSL by more than 10% of IoU score and DICE coefficient.more » « less
-
Federated learning (FL) involves training a model over massive distributed devices, while keeping the training data localized and private. This form of collaborative learning exposes new tradeoffs among model convergence speed, model accuracy, balance across clients, and communication cost, with new challenges including: (1) straggler problem—where clients lag due to data or (computing and network) resource heterogeneity, and (2) communication bottleneck—where a large number of clients communicate their local updates to a central server and bottleneck the server. Many existing FL methods focus on optimizing along only one single dimension of the tradeoff space. Existing solutions use asynchronous model updating or tiering-based, synchronous mechanisms to tackle the straggler problem. However, asynchronous methods can easily create a communication bottleneck, while tiering may introduce biases that favor faster tiers with shorter response latencies. To address these issues, we present FedAT, a novel Federated learning system with Asynchronous Tiers under Non-i.i.d. training data. FedAT synergistically combines synchronous, intra-tier training and asynchronous, cross-tier training. By bridging the synchronous and asynchronous training through tiering, FedAT minimizes the straggler effect with improved convergence speed and test accuracy. FedAT uses a straggler-aware, weighted aggregation heuristic to steer and balance the training across clients for further accuracy improvement. FedAT compresses uplink and downlink communications using an efficient, polyline-encoding-based compression algorithm, which minimizes the communication cost. Results show that FedAT improves the prediction performance by up to 21.09% and reduces the communication cost by up to 8.5×, compared to state-of-the-art FL methods.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/brainsci11070885
