Bentley Systems, Inc.

Coractive High-Tech, Inc.

Marc-André Lapointe

Karl-Alexandre Jahjah

Kaustubh Page

Hugo Bergeron

Marc-André Gardner

Simon Savary

Serge Doucet

Evan Rausch-Larouche

Lucas Flett

Andrew Smith

Jean-Noel Maran

In example embodiments, techniques are provided for using machine learning to predict railroad track geometry exceedances to enable proactive maintenance. A machine learning model of a rail operational analytics application may be trained to directly output a probability of future railroad track geometry exceedances for each portion of track of a railroad. Training may be performed using all available railroad track data, and the task of selecting which data is relevant to predicting probability of railroad track geometry exceedances may be devolved to the machine learning model. Further, assumptions about the specific railroad and data characteristics may be avoided, providing the machine learning model flexibility, and allowing for dynamic changes in the problem formulation.

Techniques for predicting railroad track geometry exceedances

In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model). In a second set of embodiments, unsupervised machine learning is used to detect abnormal associations in data describing elements (e.g., geometric data and textual data) that indicate misclassifications. Identified misclassifications are displayed to a user for review and correction.

Automatic identification of misclassified elements of an infrastructure model

In example embodiments, techniques are provided to automatically classify individual elements of an infrastructure model by training one or more machine learning algorithms on classified infrastructure models, producing a classification model that maps features to classification labels, and utilizing the classification model to classify the individual elements of the infrastructure model. The resulting classified elements may then be readily subject to analytics, for example, enabling the display of dashboards for monitoring project performance and the impact of design changes. Such techniques enable classification of elements of new infrastructure models or in updates to existing infrastructure models.

Classifying individual elements of an infrastructure model

The present relates to a spatially modulated cladding mode stripper and to an optical fiber comprising a spatially modulated cladding mode stripper. The spatially modulated cladding mode stripper comprises a series of alternating high cladding light extracting regions and low cladding light extracting regions located along a portion of a cladding to modulate extracting of cladding light therefrom.

Spatially modulated cladding mode stripper and optical fiber therewith

Growing community of inventors

CA

Marc-André Lapointe