Abstract: In example embodiments, techniques are provided for classifying elements of infrastructure models using a convolutional graph neural network (GNN). Graph-structured data structures are generated from infrastructure models, in which nodes represent elements and edges represent contextual relationships among elements (e.g., based on proximity, functionality, parent-child relationships, etc.). During training, the GNN learns embeddings from the nodes and edges of the graph-structured data structures, the embeddings capturing contextual clues that distinguish between elements that may share similar geometry (e.g., cross section, volume, surface area, etc.), yet serve different purposes.

Abstract: In example embodiments, techniques are provided for labeling elements of an infrastructure model with classes. The techniques may be implemented by a labeling tool that uses an ML model to create element selections and provides a cycle review mode to speed review within such selections. The labeling tool may further provide for two file loading and a number of visualization schemes to speed comparison of label files and prediction files.

Abstract: 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).

Abstract: 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.

Abstract: In example embodiments, a software service may employ a neural network to learn a non-linear mapping that transforms element features into embeddings. The neural network may be trained to distribute the embeddings in multi-dimensional embedding space, such that distance between the embeddings is meaningful to the class or category classification, or property prediction, task at hand. The neural network may be trained using weakly supervised machine learning, using weakly labeled infrastructure models. Embeddings for groups may be used to determine prototypes. Elements of an infrastructure model may be classified into classes or categories, or their properties predicted, as the case may be, by finding a nearest prototype.

Abstract: 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).

Abstract: 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.

Abstract: A cylindrical cutting head for a wood workpiece, comprising an even number of main grooves disposed on helices running on a length of a surface thereof, wherein each main groove comprises cutting inserts; each cutting insert comprising a knife removably locked in position in relation to the main groove by a clamp. A cutting insert for a cylindrical cutting head for a wood workpiece, comprising a knife and a clamp, wherein the knife is removably positioned and locked in position in relation to the cylindrical cutting head by a clamp.

Abstract: 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.

Abstract: 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.

Abstract: A system and method for stacking two bulk bags one on top of the other on a pallet, the method comprising controlling a pallet feeder into providing a pallet; filling a first bag with a first amount of product on the pallet and sealing the first bag; filling a second bag with a second amount of product, and depositing the second bag filled with the second amount of product on top of the first bag on the pallet; and straightening the bags on the pallet; wherein these steps of controlling, filling the first and second bags, and straightening are controlled by a programmable controller, the programmable controller selecting the first amount to be fed to the first bag supported by the pallet and, selecting the second amount to be fed to the second bag.

Abstract: A method and a system for classifying a plurality of random length boards of random grade, using a conveyer provided with reading units to read both the length and the grade of each board at a first end of said conveyer; a processor, receiving length and grade data from the reading units; calculating combinations of board lengths and grades and selecting a preferred combination of boards from the combinations; and a distribution section, located at a second end of the conveyer, and operated by the processor according to the preferred combination; the processor being fed with a large number of identified boards, from which to calculate the combinations of board lengths and grades, before they reach the distribution section.

Abstract: A floor planks production method, for producing wood flooring from raw lumbers, by surfacing top and lower faces of the lumbers to a final thickness of the lumbers; optimizing the lumbers along a length thereof to determine lengths of best faces; and profiling edges of the optimized lumbers. The system comprises a surfacing unit processing both top and lower faces of each lumber to final dimensions; an optimizing unit receiving lumbers from the surfacing unit; and a profiling unit processing edges of each length of best faces positioned by the optimizing unit.

Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.

Abstract: A floor planks production method, for producing wood flooring from raw lumbers, by surfacing top and lower faces of the lumbers to a final thickness of the lumbers; optimizing the lumbers along a length thereof to determine lengths of best faces; and profiling edges of the optimized lumbers. The system comprises a surfacing unit processing both top and lower faces of each lumber to final dimensions; an optimizing unit receiving lumbers from the surfacing unit; and a profiling unit processing edges of each length of best faces positioned by the optimizing unit.

Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.

Abstract: A method and a system for classifying a plurality of random length boards of random grade, using a conveyer provided with reading units to read both the length and the grade of each board at a first end of said conveyer; a processor, receiving length and grade data from the reading units; calculating combinations of board lengths and grades and selecting a preferred combination of boards from the combinations; and a distribution section, located at a second end of the conveyer, and operated by the processor according to the preferred combination; the processor being fed with a large number of identified boards, from which to calculate the combinations of board lengths and grades, before they reach the distribution section.

Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.

Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.

Abstract: A presser roll for surface planers is described herein. The presser roll comprises a longitudinal shaft, a radially deformable generally cylindrical sleeve mounted on said longitudinal shaft for rotation in unison therewith and a biasing assembly mounted between the shaft and the sleeve for outwardly biasing the sleeve.