Search for: All records

This study focuses on developing and examining the effectiveness of Transfer Learning (TL) for structural health monitoring (SHM) systems that transfer knowledge about damage states from one structure (i.e., the source domain) to another structure (i.e., the target domain). Transfer Learning (TL) is an efficient method for knowledge transfer and mapping from source to target domains. In addition, Proper Orthogonal Modes (POMs), which help classify behavior and health, provide a promising tool for damage identification in structural systems. Previous investigations show that damage intensity and location are highly correlated with POM variations for structures under unknown loads. To train damage identification algorithms based on POMs and ML, one generally needs to use multiple simulations to generate damage scenarios. The developed process is applied to a simply supported truss span in a multi-span railway bridge. TL is first used to obtain relationships between POMs for two modeled bridges: one being a source model (i.e., labeled) and the other being the target modeled bridge (i.e., unlabeled). This technique is then implemented to develop POMs for a damaged, unknown target using TL that links source and target POMs. It is shown that the trained knowledge from one bridge was effectively generalized to other, somewhat similar, bridges in the population. 

According to the market research firm Tractica, the global artificial intelligence software market is forecast to grow to 126 billion by 2025. Additionally, the Gartner group predicts that during the same time as much as 80% of the routine work ,  which represents the bulk of human hours spent in today's project management (PM) activities, can be eliminated because of collaboration between humans and smart machines. Today's PM practices rely heavily on human input. However, that is not the optimum use of the human project manager's intuitive, innovative, and creative abilities. Many aspects of a project manager's work could be managed by machines that utilize AI/ML approaches to address nonroutine and predictive tasks. This paper describes IT project management (ITPM) processes and associated tasks and identifies the AI/ML approaches that can support them. 

Homomorphic encryption (HE) is the ultimate tool for performing secure computations even in untrusted environments. Application of HE for deep learning (DL) inference is an active area of research, given the fact that DL models are often deployed in untrusted environments (e.g., third-party servers) yet inferring on private data. However, existing HE libraries [somewhat (SWHE), leveled (LHE) or fully homomorphic (FHE)] suffer from extensive computational and memory overhead. Few performance optimized high-speed homomorphic libraries are either suffering from certain approximation issues leading to decryption errors or proven to be insecure according to recent published attacks. In this article, we propose architectural tricks to achieve performance speedup for encrypted DL inference developed with exact HE schemes without any approximation or decryption error in homomorphic computations. The main idea is to apply quantization and suitable data packing in the form of bitslicing to reduce the costly noise handling operation, Bootstrapping while achieving a functionally correct and highly parallel DL pipeline with a moderate memory footprint. Experimental evaluation on the MNIST dataset shows a significant ( 37× ) speedup over the nonbitsliced versions of the same architecture. Low memory bandwidths (700 MB) of our design pipelines further highlight their promise toward scaling over larger gamut of Edge-AI analytics use cases. 

Abstract This paper presents a multi-sensor data collection and data fusion procedure for nondestructive evaluation/testing (NDE/NDT) of a concrete bridge deck. Three NDE technologies, vertical electrical impedance (VEI), ground-penetrating radar (GPR), and high-definition imaging (HDI) for surface crack detection, were deployed on the bridge deck. A neural network autoencoder was trained to quantify the relationship between VEI and GPR results using the data collected at common positions. This relationship was then used for fusion of VEI and GPR data to increase the reliability and spatial resolution of the NDE measurements and to generate a data-fused condition map that showed novel characteristics. Threshold values for VEI and GPR tests were obtained and used to determine the color scale in the fused map. Surface cracks identified from HDI show reasonable agreement with the deterioration areas on the data-fused condition map. Chloride concentration measurements on sound and deteriorated areas of the deck were consistent with the NDE results. 

The C+ score for US bridges on the 2017 infrastructure report card underscores the need for improved data-driven methods to understand bridge performance. There is a lot of interest and prior work in using inspection records to determine bridge health scores. However, aggregating, cleaning, and analyzing bridge inspection records from all states and all past years is a challenging task, limiting the access and reproducibility of findings. This research introduces a new score computed using inspection records from the National Bridge Inventory (NBI) data set. Differences between the time series of condition ratings for a bridge and a time series of average national condition ratings by age are used to develop a health score for that bridge. This baseline difference score complements NBI condition ratings in further understanding a bridge’s performance over time. Moreover, the role of bridge attributes and environmental factors can be analyzed using the score. Such analysis shows that bridge material type has the highest association with the baseline difference score, followed by snowfall and maintenance. This research also makes a methodological contribution by outlining a data-driven approach to repeatable and scalable analysis of the NBI data set.