Abstract: A system includes a processor and a memory storing software code and a machine learning (ML) model. The software code is executed to receive contextual data samples each including raw data and a descriptive label, for each contextual data sample: search a database for a data pattern matching the raw data, determine, when the data pattern is detected, whether the data pattern is correlated with an anomalous event, and generate, when the correlation is determined, training data including a label identifying the anomalous event, and the raw data, the data pattern, or both, to provide one of multiple training data samples, wherein the training data samples describe anomalous events corresponding respectively to the raw data, the data pattern, or both. The software code is further executed to train the ML model, using the training data samples, to provide a trained predictive ML model configured to predict the anomalous events.

Abstract: Improved inspection techniques are described herein for checking for the presence of and identifying surface defects on a honeycomb body. The improved inspection utilizes measurement of travel of an outer surface of the honeycomb body to collect images of the outer surface. The images are combined into a composite image showing the outer surface of the honeycomb body. The composite image is analyzed to identify surface defects.

Abstract: A chemical mechanical planarization (CMP) tool includes a platen and a polishing pad attached to the platen, where a first surface of the polishing pad facing away from the platen includes a first polishing zone and a second polishing zone, where the first polishing zone is a circular region at a center of the first surface of the polishing pad, and the second polishing zone is an annular region around the first polishing zone, where the first polishing zone and the second polishing zone have different surface properties.

Abstract: A chemical mechanical planarization (CMP) tool includes a platen and a polishing pad attached to the platen, where a first surface of the polishing pad facing away from the platen includes a first polishing zone and a second polishing zone, where the first polishing zone is a circular region at a center of the first surface of the polishing pad, and the second polishing zone is an annular region around the first polishing zone, where the first polishing zone and the second polishing zone have different surface properties.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: Improved inspection techniques are described herein for checking for the presence of and identifying surface defects on a honeycomb body. The improved inspection utilizes measurement of travel of an outer surface of the honeycomb body to collect images of the outer surface. The images are combined into a composite image showing the outer surface of the honeycomb body. The composite image is analyzed to identify surface defects.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: A chemical mechanical planarization (CMP) tool includes a platen and a polishing pad attached to the platen, where a first surface of the polishing pad facing away from the platen includes a first polishing zone and a second polishing zone, where the first polishing zone is a circular region at a center of the first surface of the polishing pad, and the second polishing zone is an annular region around the first polishing zone, where the first polishing zone and the second polishing zone have different surface properties.

Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.

Abstract: A method of detecting and analyzing abnormalities, like lung nodules, in thoracic computer tomography (CT) images uses digital image processing techniques and adaptive computing methods. The techniques include an automatic detection process to detect candidate abnormalities, an image matching process to match CT slices from two different CT scans, and a measurement process that determines parameters of the candidate abnormalities. Final results and processed CT images are displayed on a user interface.

Abstract: An insertion socket for flat cable includes a socket main body defining a plurality of terminal cavities therein, a cover pivotally connected to a top of the socket main body, and a plurality of terminals separately received in the terminal cavities. Each of the terminals has a rear end projected from a rear side of the socket main body to provide a connecting pin, and a front barb portion that is formed at a lower side with a plurality of backward extended barbs. When the cover is pivotally turned downward to close the socket main body, it contacts with and applies a pressure on the barb portions of the terminals to cause the barbs on the barb portions to contact with and press against a flat cable inserted into the insertion socket. And, a reactive force acted by the terminals on the closed cover does not result in a lifted cover.