Search NASA⌕ Search

SEARCH · Search NASA

Results for “Intelligent Systems”

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.

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

At least 109 records · Page 6

Device Feasibility Analysis of Multi-level FeFETs for Neuromorphic Computing

As an emerging non-volatile memory device technology, Ferroelectric Field-Effect Transistors (FeFETs) can enable low-power, adaptive intelligent system design. However, device dimension and operating voltage dependent reliability issues of scaled FeFETs can ultimately lead to degraded performance in solving machine learning tasks. In this article, detailed experimental characterization of FeFET devices of different dimensions have been carried out to explicitly evaluate the non-ideal behavior in device conductance programming properties like number of programming states, cycle-to-cycle (C2C) variations, device-to-device (D2D) variations, and state retention. A hardware-aware software simulation approach has been adopted to capture the adversarial effects of the non-idealities on recognition accuracy through algorithm-level performance assessment by including them in NeuroSim, a popular neural network hardware simulator, to execute a neural network model considering all other hardware constraints. With the added non-idealities, significant accuracy degradation has been observed compared to the ideal scenarios where D2D variations play the most critical role. Thereafter, feasibility of a variation-aware training method has been evaluated to tackle the accuracy drop.

42 ENGINEERING↗

Accelerating Traction Motor Optimization Design with AI Surrogate Models

The advancement of artificial intelligence systems enables the use of data-driven physics-based surrogate models to explore design spaces rapidly and deeply for engineering projects. This work presents a surrogate model workflow that accelerates electric traction motor design optimization by replacing finite element analysis (FEA) with an artificial neural network (ANN) and using this model in a genetic algorithm for design optimization. A baseline interior permanent-magnet motor is parameterized and sampled to generate FEA-labeled training data, after which a feed-forward ANN predicts key outputs (e.g., loss components and weight). The validated surrogate enables genetic-algorithm optimization and deep search over the design space without new FEA runs, producing Pareto-optimal trade-offs between weight and losses and set of optimized designs for rapid downselection of manufacturable motor designs.

Ribeiro, Pedro [ORNL] (ORCID:0009000921026641)↗

167-PFlops Deep Learning for Electron Microscopy: From Learning Physics to Atomic Manipulation

An artificial intelligence system called MENNDL, which used 25,200 Nvidia Volta GPUs on Oak Ridge National Laboratory’s Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity toward nanofabricating materials automatically. Finally, MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.

97 MATHEMATICS AND COMPUTING↗

A Recursive Multiscale Correlation-Averaging Algorithm for an Automated Distributed Road Condition Monitoring System

A signal processing approach is proposed to jointly filter and fuse spatially indexed measurements captured from many vehicles. It is assumed that these measurements are influenced by both sensor noise and measurement indexing uncertainties. Measurements from low-cost vehicle-mounted sensors (e.g., accelerometers and Global Positioning System (GPS) receivers) are properly combined to produce higher quality road roughness data for cost-effective road surface condition monitoring. The proposed algorithms are recursively implemented and thus require only moderate computational power and memory space. These algorithms are important for future road management systems, which will use on-road vehicles as a distributed network of sensing probes gathering spatially indexed measurements for condition monitoring, in addition to other applications, such as environmental sensing and/or traffic monitoring. Our method and the related signal processing algorithms have been successfully tested using field data.

47 OTHER INSTRUMENTATION↗

Skin-like low-noise elastomeric organic photodiodes

Stretchable optoelectronics made of elastomeric semiconductors could enable the integration of intelligent systems with soft materials, such as those of the biological world. Organic semiconductors and photodiodes have been engineered to be elastomeric; however, for photodetector applications, it remains a challenge to identify an elastomeric bulk heterojunction (e-BHJ) photoactive layer that combines a low Young’s modulus and a high strain at break that yields organic photodiodes with low electronic noise values and high photodetector performance. Here, a blend of an elastomer, a donor-like polymer, and an acceptor-like molecule yields a skin-like e-BHJ with a Young’s modulus of a few megapascals, comparable to values of human tissues, and a high strain at break of 189%. Elastomeric organic photodiodes based on e-BHJ photoactive layers maintain low electronic noise current values in the tens of femtoamperes range and noise equivalent power values in the tens of picowatts range under at least 60% strain.

42 ENGINEERING↗

BOSC 2025, the 26th Bioinformatics Open Source Conference

The 26th annual Bioinformatics Open Source Conference (BOSC 2025, open-bio.org/events/bosc-2025) brought its community-driven focus on open-source bioinformatics and open science to the 2025 conference on Intelligent Systems for Molecular Biology and the European Conference on Computational Biology (ISMB/ECCB 2025). Since its launch in 2000, BOSC has been the premier annual meeting covering open-source bioinformatics and open science. Framed by two keynote addresses and a thought-provoking panel discussion, the two-day conference included sessions dedicated to open data, analytic tools and pipelines, workflow platforms, knowledge representation, and the application of AI/ML. The first keynote talk was delivered by Christine Orengo: “Working together to develop, promote and protect our data resources: Lessons learnt developing CATH and TED.” A joint session with the Bio-Ontologies and Knowledge Representation (BOKR) track the second day of BOSC started with a keynote talk by Chris Mungall entitled “Open Knowledge Bases in the Age of Generative AI”. A closing panel on Data Sustainability, moderated by Mónica Muñoz Torres, featured panelists Scott Edmunds, Varsha Khodiyar, Tony Burdett, Nicky Mulder, and Chris Mungall. This year, the CollaborationFest collaborative work event that typically precedes or follows ISMB was incorporated as part of the main conference and organized by BOSC with help from the Function and 3D-SIG tracks.

bioinformatics↗

BOSC 2019, the 20th annual Bioinformatics Open Source Conference

The Bioinformatics Open Source Conference is a volunteer-organized meeting that covers open source software development and open science in bioinformatics. Launched in 2000, BOSC has been held every year since. BOSC 2019, the 20th annual BOSC, took place as one of the Communities of Special Interest (COSIs) at the Intelligent Systems for Molecular Biology meeting (ISMB/ECCB 2019). The two-day meeting included a total of 46 talks and 55 posters, as well as eight Birds of a Feather interest groups. The keynote speaker was University of Cape Town professor Dr. Nicola Mulder, who spoke on “Building infrastructure for responsible open science in Africa”. Immediately after BOSC 2019, about 50 people participated in the two-day CollaborationFest (CoFest for short), an open and free community-driven event at which participants work together to contribute to bioinformatics software, documentation, training materials, and use cases.

97 MATHEMATICS AND COMPUTING↗

The 2015 Bioinformatics Open Source Conference (BOSC 2015)

The Bioinformatics Open Source Conference (BOSC) is organized by the Open Bioinformatics Foundation (OBF), a nonprofit group dedicated to promoting the practice and philosophy of open source software development and open science within the biological research community. Since its inception in 2000, BOSC has provided bioinformatics developers with a forum for communicating the results of their latest efforts to the wider research community. BOSC offers a focused environment for developers and users to interact and share ideas about standards; software development practices; practical techniques for solving bioinformatics problems; and approaches that promote open science and sharing of data, results, and software. BOSC is run as a two-day special interest group (SIG) before the annual Intelligent Systems in Molecular Biology (ISMB) conference. BOSC 2015 took place in Dublin, Ireland, and was attended by over 125 people, about half of whom were first-time attendees. Session topics included “Data Science;” “Standards and Interoperability;” “Open Science and Reproducibility;” “Translational Bioinformatics;” “Visualization;” and “Bioinformatics Open Source Project Updates”. In addition to two keynote talks and dozens of shorter talks chosen from submitted abstracts, BOSC 2015 included a panel, titled “Open Source, Open Door: Increasing Diversity in the Bioinformatics Open Source Community,” that provided an opportunity for open discussion about ways to increase the diversity of participants in BOSC in particular, and in open source bioinformatics in general. The complete program of BOSC 2015 is available online at http://www.open-bio.org/wiki/BOSC_2015_Schedule.

59 BASIC BIOLOGICAL SCIENCES↗

NeuroSymbolic Approaches as a Vector for Assured Artificial Intelligence

The deployment of artificial intelligence systems in critical applications requires higher levels of assurance for safety, security, and interpretability. While neurosymbolic (NESY) approaches combining neural networks with symbolic reasoning offer potential advantages for assured AI, existing differentiable neurosymbolic frameworks face significant limitations including computational overhead and performance constraints. This report investigates the ISED (InferSampleEstimateDescend) framework as an alternative approach that enables neurosymbolic learning without requiring endtoend differentiability. We evaluate ISED’s utility for geointelligence applications by comparing neurosymbolic models against standard neural networks on aircraft classification tasks using the RarePlanes and MTARSI imagery datasets. Our results demonstrate that while ISEDbased models achieve slightly lower accuracy (89.7% vs 92.1% on RarePlanes; 91.1% vs 92.5% on MTARSI), they provide critical explainability capabilities that enable tracing incorrect predictions back to specific attribute misclassifications. We also present an automated pipeline that generates both attributeclass mappings and neurosymbolic model architectures from natural language descriptions, significantly reducing the manual effort required for NESY model deployment. These findings suggest that ISED offers a promising direction for developing assured AI systems where interpretability and reasoning transparency are prioritized alongside performance.

97 MATHEMATICS AND COMPUTING↗

Seeing is Believing: Autonomous Microscopy and the Data Revolution in Materials Science [Slides]

Machine intelligence has the potential to revolutionize materials science, enabling autonomous synthesis, self-driving characterization, and accelerated modeling. However, despite the promise, successful implementation of these methods in day-to-day research remains a challenge. This talk will delve into the reasons behind this, exploring how truly intelligent experiments are hindered by opaque experiment control, a lack of domain-specific models, and human-centric design. Through a focus on the characterization of next-generation microelectronics and energy storage materials, I will share insights from both successful and failed attempts to implement machine intelligence. We will then explore the next steps necessary to unlock the full potential of machine intelligence in materials science, creating a future where intelligent systems work seamlessly alongside researchers to drive innovation and discovery.

36 MATERIALS SCIENCE↗

TIME-RESOLVED EMISSION FROM BRIGHT HOT PIXELS OF AN ACTIVE REGION OBSERVED IN THE EUV BAND WITH SDO/AIA AND MULTI-STRANDED LOOP MODELING

Evidence of small amounts of very hot plasma has been found in active regions and might be an indication of impulsive heating released at spatial scales smaller than the cross-section of a single loop. We investigate the heating and substructure of coronal loops in the core of one such active region by analyzing the light curves in the smallest resolution elements of solar observations in two EUV channels (94 and 335 Å) from the Atmospheric Imaging Assembly on board the Solar Dynamics Observatory. We model the evolution of a bundle of strands heated by a storm of nanoflares by means of a hydrodynamic 0D loop model (EBTEL). The light curves obtained from a random combination of those of single strands are compared to the observed light curves either in a single pixel or in a row of pixels, simultaneously in the two channels, and using two independent methods: an artificial intelligent system (Probabilistic Neural Network) and a simple cross-correlation technique. We explore the space of the parameters to constrain the distribution of the heat pulses, their duration, their spatial size, and, as a feedback on the data, their signatures on the light curves. From both methods the best agreement is obtained for a relatively large population of events (1000) with a short duration (less than 1 minute) and a relatively shallow distribution (power law with index 1.5) in a limited energy range (1.5 decades). The feedback on the data indicates that bumps in the light curves, especially in the 94 Å channel, are signatures of a heating excess that occurred a few minutes before.

79 ASTRONOMY AND ASTROPHYSICS↗

Meeting Report: Metagenomics, Metadata and MetaAnalysis (M3) at ISMB 2010

This report summarizes the proceedings of the first day of the Metagenomics, Metadata and MetaAnalysis (M3) workshop held at the Intelligent Systems for Molecular Biology 2010 conference. The second day, which was dedicated to the inaugural meeting of the BioSharing initiative is presented in a separate report. The Genomic Standards Consortium (GSC) hosted the first day of this Special Interest Group (SIG) at ISMB to continue exploring the bottlenecks and emerging solutions for obtaining biological insights through large-scale comparative analysis of metagenomic datasets. The M3 SIG included invited and selected talks and a panel discussion at the end of the day involving the plenary speakers. Further information about the GSC and its range of activities can be found at http://gensc.org. Information about the newly established BioSharing effort can be found at http://biosharing.org/.

59 BASIC BIOLOGICAL SCIENCES↗

Meeting Report: BioSharing at ISMB 2010

This report summarizes the proceedings of the one day BioSharing meeting held at the Intelligent Systems for Molecular Biology (ISMB) 2010 conference in Boston, MA, USA This inaugural BioSharing event was hosted by the Genomic Standards Consortium as part of its M3 & BioSharing special interest group (SIG) workshop. The BioSharing event included invited talks from a range of community leaders and a panel discussion at the end of the day. The panel session led to the formal agreement among community leaders to join together to promote cross-community knowledge exchange and collaborations. A key focus of the newly formed Biosharing community will be linking up resources to promote real-world data sharing (virtuous cycle of data) and supporting compliance with data policies through the creation of a one-stop-portal of information. Further information about the newly established BioSharing effort can be found at http://biosharing.org.

59 BASIC BIOLOGICAL SCIENCES↗

Optimizing Batch Crystallization with Model-based Design of Experiments

Adaptive and self-optimizing intelligent systems such as digital twins are increasingly important in science and engineering. Digital twins utilize mathematical models to provide added precision to decision-making. However, physics-informed models are challenging to build, calibrate, and validate with existing data science methods. Model-based design of experiments (MBDoE) is a popular framework for optimizing data collection to maximize parameter precision in mathematical models and digital twins. In this work, we apply MBDoE, facilitated by the open-source package Pyomo.DoE, to train and validate mathematical models for batch crystallization. We quantitatively examined the estimability of the model parameters for experiments with different cooling rates. This analysis provides a quantitative explanation for the heuristic of using multiple experiments at different cooling rates.

Lynch, Hailey↗

ISMB Conference Proceedings

This special issue comprises the papers accepted for presentation at the 19th Annual International Conference on Intelligent Systems for Molecular Biology, joint with the 10th European Conference on Computational Biology, an official conference of the International Society for Computational Biology (ISCB; http://www.iscb.org). ISMB/ECCB 2011 (http://www.iscb.org/ismb2011/) will take place in Vienna, Austria, from July 17 through July 19, 2011; preceded during July 14–16 by eight 1- or 2- day Special Interest Group (SIG) meetings, three satellite meetings and nine half-day tutorials; and followed by two additional satellite meetings. The 48 papers in this volume were selected from 258 submitted papers. Submitted papers were assigned to 13 areas. Area Chairs led each topic area by selecting their area's program committee and overseeing the reviewing process. Many Area Chairs were new compared to 2010, and two completely new areas were added in 2011, ‘Data Visualization’ and ‘Mass Spectrometry and Proteomics’. Six papers for which Area Chairs were in conflict were reviewed under a ‘Conflicts Management’ section headed by the Proceedings Chairs; one such paper was accepted in ‘Bioimaging’. Areas, co-chairs and acceptance information are listed in Table 1. Compared to prior years, five mature topic areas had steady submissions, ‘Evolution and Comparative Genomics’, ‘Gene Regulation and Transcriptomics’, ‘Protein Structure and Function’, ‘Sequence Analysis’, ‘Text Mining’. Two areas newer to ISMB were underrepresented this year, ‘Bioimaging’ and ‘Disease Models and Epidemiology’. One area doubled, ‘Applied Bioinformatics’, renamed from last year's ‘Other Bioinformatics Applications’; and one tripled, ‘Protein Interactions and Molecular Networks’. Across the areas, 326 members of the bioinformatics community provided reviews. Most papers received three reviews and several received four or more. There was significant discussion of the merits of the papers first between referees and the Area Chairs, and then between Area Chairs and the proceedings chairs. Initial decisions to accept papers were made during a comprehensive conference call with the Area Chairs, and several papers underwent a further evaluation by additional Area Chairs before acceptance decisions were finalized. We appreciate that in several cases reviewers' opinions might have changed with additional input or further clarifications from the authors; because the ISMB/ECCB 2011 timeline did not allow for a second round of reviews, however, only papers where referees suggested minor revisions could be accepted. For several papers where referee comments might have been unclear to the authors, Area Chairs added additional comments and explanations. In total, 48 papers were conditionally accepted, pending revision. After acceptance notices were sent, the authors had 2 weeks to modify their papers according to the suggestions made by the reviewers and to respond to the reviewers' comments. Modified papers and authors' responses were reexamined during the next week to ensure each paper was modified appropriately in response to the reviewers' comments. We were pleased that all 48 conditionally accepted papers were finally accepted for the conference. The final acceptance rate was 19%, similar to the rates of 20% and 19% in the two prior years. Collectively, the 48 accepted papers had 185 authors from 18 countries across 6 continents, with 82 authors from North America, 54 from Europe, 25 from Asia (excluding Israel), 10 from Israel, 9 from Australia, 4 from South America and 1 author from Africa. We thank the area chairs and reviewers for their hard work and dedication to maintaining a professional review process. We thank all authors of submitted papers and authors of accepted papers for their diligences in responding to reviewer comments within 2 weeks. We thank Steven Leard's team for extensive technical support with the EasyChair submission and reviewing system; Mona Singh and Joel S. Bader for sharing their experience from last year; the team at Oxford University Press for typesetting the papers; Conference Chairs Burkhard Rost, Michal Linial, Peter Schuster and Kurt Zatloukal, as well as the ISMB/ECCB 2011 Steering Committee, for their valuable input; and Steven Leard for helping us oversee the process.

60 APPLIED LIFE SCIENCES↗

Big Data, Big Solutions

Data—lots of data—generated in seconds and piling up on the internet, streaming and stored in countless databases. Big data is important for commerce, society and our nation’s security. Yet the volume, velocity, variety and veracity of data is simply too great for any single analyst to make sense of alone. It requires advanced, data-intensive computing. Simply put, data-intensive computing is the use of sophisticated computers to sort through mounds of information and present analysts with solutions in the form of graphics, scenarios, formulas, new hypotheses and more. This scientific capability is foundational to PNNL’s energy, environment and security missions. Senior Scientist and Division Director Bill Pike and his team are developing analytic tools that are used to solve important national challenges, including cyber systems defense, power grid control systems, intelligence analysis, climate change and scientific exploration.

97 MATHEMATICS AND COMPUTING↗

167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation

An artificial intelligence system called MENNDL, which used 25,200 NVIDIA Volta GPUs on Oak Ridge National Laboratory's Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity towards nanofabricating materials automatically. MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.

Patton, Robert↗

Noise-Based Selection of Robust Inherited Model for Accurate Continual Learning

There is a growing demand for an intelligent system to continually learn knowledge from a data stream. Continual learning requires both the preservation of previous knowledge (i.e., avoiding catastrophic forgetting) and the acquisition of new knowledge. Different from previous works that focus only on model adaptation (e.g., regularization, network expansion, memory rehearsal, etc.), we propose a novel training scheme named acquisitive learning (AL), which emphasizes both the knowledge inheritance and knowledge acquisition. AL starts from an elaborately selected model with pre-trained knowledge (the inherited model) and then adapts it to new data using segmented training. The selection is achieved by injecting random noise to various inherited models for better model robustness, which promises higher accuracy in further knowledge acquisition. The approach is validated by the visualization of the loss landscape and quantitative roughness measurement. The combination of the selective inherited model and knowledge acquisition reduces catastrophic forgetting by 10X on the CIFAR-100 dataset.

Du, Xiaocong↗