SEARCH · Engineering Papers

Results for “benchmarks”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,531 records · Page 85

All sources NASA NTRS DOE OSTI

DOE OSTI2023

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of ‹ instrument, verb, target › combination delivers more comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. Here, the challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and the assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. Here, a total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms from the competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

Benchmark CO 2 separation achieved by highly fluorinated nanoporous molecular sieve membranes from nonporous precursor via in situ cross-linking

Molecular sieve membranes with rigid micropores and CO 2 -philic functionalities within the architectures are promising candidates in CO 2 separation. However, the development of ctieve approaches for their fabrication still remains a significant challenge. In this study, an in situ cross-linking strategy is developed for the preparation of nanoporous fluorinated moleffecular sieve membranes using commercially available dense and non-porous polystyrene (M PS ) as a precursor template. Based on the dehydrative Friedel-Crafts reactions with highly fluorinated benzylic alcohols, M PS membranes are cross-linked in situ upon exposure to Brønsted acid (CF 3 SO 3 H), affording fluorinated microporous polymeric membranes with surface areas up to 523 m 2 g –1 and the presence of micropores centered at 1.1–1.3 nm as well as ultra-micropores (~0.6 nm). The obtained modified membranes exhibit good ideal CO 2 permeability of 797 barrer and CO 2 /N 2 selectivity of 28.5. In addition, high fluorine content (up to 28.5 wt%) and good thermal stability made the cross-linked membranes promising candidates to produce fluorinated carbon molecular sieve membranes with improved textural properties, exhibiting surface areas up to 1020 m 2 g –1 and ultra-micropores of ~0.4 nm. These membranes achieve superior CO 2 /N 2 separation performances exceeding the Robeson upper bound limit (2008).

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

Edge-cloud computing performance benchmarking for IoT based machinery vibration monitoring

Advances in low cost and reliable sensing, connectivity (Internet of Things), computational power, and advanced analytics, are leading to a new wave of innovation in machinery status sensing and condition monitoring. Significant research efforts are directed towards cloud computing architectures. However, given the latency, bandwidth, cost, security, and privacy concerns, further supported by the ever-increasing capabilities of edge computing devices, there is a need to consider both edge and cloud computing together to make informed decisions based upon context and performance. In this work, we present an edge-cloud performance evaluation for IoT based machinery vibration monitoring, to foster deployment for the contexts considered.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators

Software simulators play a critical role in the development of new algorithms and system architectures in any field of engineering. Neuromorphic computing, which has shown potential in building brain-inspired energy-efficient hardware, suffers a slow-down in the development cycle due to a lack of flexible and easy-to-use simulators of either neuromorphic hardware itself or of spiking neural networks (SNNs), the type of neural network computation executed on most neuromorphic systems. While there are several openly available neuromorphic or SNN simulation packages developed by a variety of research groups, they have mostly targeted computational neuroscience simulations, and only a few have targeted small-scale machine learning tasks with SNNs. Evaluations or comparisons of these simulators have often targeted computational neuroscience-style workloads. In this work, we seek to evaluate the performance of several publicly available SNN simulators with respect to non-computational neuroscience workloads, in terms of speed, flexibility, and scalability. We evaluate the performance of the NEST, Brian2, Brian2GeNN, BindsNET and Nengo packages under a common front-end neuromorphic framework. Our evaluation tasks include a variety of different network architectures and workload types to mimic the computation common in different algorithms, including feed-forward network inference, genetic algorithms, and reservoir computing. We also study the scalability of each of these simulators when running on different computing hardware, from single core CPU workstations to multi-node supercomputers. Our results show that the BindsNET simulator has the best speed and scalability for most of the SNN workloads (sparse, dense, and layered SNN architectures) on a single core CPU. However, when comparing the simulators leveraging the GPU capabilities, Brian2GeNN outperforms the others for these workloads in terms of scalability. NEST performs the best for small sparse networks and is also the most flexible simulator in terms of reconfiguration capability NEST shows a speedup of at least 2x compared to the other packages when running evolutionary algorithms for SNNs. The multi-node and multi-thread capabilities of NEST show at least 2x speedup compared to the rest of the simulators (single core CPU or GPU based simulators) for large and sparse networks. We conclude our work by providing a set of recommendations on the suitability of employing these simulators for different tasks and scales of operations. We also present the characteristics for a future generic ideal SNN simulator for different neuromorphic computing workloads.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2015

Analytical benchmarks for precision particle tracking in electric and magnetic rings

Not Available

Metodiev, E. M.↗

DOE OSTI2018

Using the JCC-71 neutron coincidence collar as a benchmark for detector characterization with PTR-32 list mode data acquisition

Augmenting or interchanging current international safeguards shift registerbased data acquisition systems with list mode data acquisition systems gives nondestructive assay (NDA) systems greater versatility. Neutron list mode data analysis offers comparable analytical results to the more widely used shift register analysis in nuclear material quantification applications and offers several diagnostic tools that are specifically beneficial to in-laboratory characterization and calibration measurements. These benefits include identification of non-ideal behavior, optimization of operational parameters from a single measurement, and an improved understanding of the physics-based behavior of NDA systems for a more precise system representation and more confident assay results. In this work the advantages of using list mode data acquisition for detector characterization are demonstrated experimentally. Two commercial-off-the-shelf International Atomic Energy Agency-supported technologies are used for a typical detector characterization procedure and their performance is compared. Specifically, a 3 He-based Canberra Industries JCC-71 Neutron Coincidence Collar is characterized using the Hungarian Institute of Isotopes’ Pulse Train Recorder-32 (PTR-32) list mode data acquisition system, and the results are compared to those obtained using the standard Canberra Industries JSR-15 model shift register. The quantitative results from the two systems are in agreement, which demonstrates that the PTR-32 is a technically viable alternative to conventional shift register electronics for this task. A suitable procedure for full instrument characterization is described, and the added benefits of list mode for characterization and data collection are discussed. Furthermore, this is an important step toward establishing a procedure for the routine use of list mode data acquisition and analysis for neutron NDA system characterization in safeguards field applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2015