Abstract: Embodiments of the invention are directed to a computer system including a memory communicatively coupled to a processor system. The processor system is operable to perform processor system operations that include using a first machine learning (ML) algorithm to convert to-be-classified-data (TBC-data) from a TBC-data format to a second data format; and extract features from the TBC-data in the second data format. A second ML algorithm is used to perform a task that includes determining, based at least in part on the features of the TBC-data in the second data format, that the TBC-data having the second data format is an outlier.

Abstract: According to a present invention embodiment, a system identifies a plurality of configurations for machine learning models. Each configuration indicates a machine learning model and a corresponding technique to determine parameters for the machine learning model. The plurality of configurations are evaluated by training the machine learning model of the plurality of configurations according to the parameters determined by the corresponding technique. Performance of the machine learning models of the plurality of configurations is monitored, and resources used for evaluating at least one configuration are adjusted based on the performance of the machine learning model for the at least one configuration relative to the performance of the machine learning models of others of the plurality of configurations. Embodiments of the present invention further include a method and computer program product for training machine learning models in substantially the same manner described above.

Abstract: An endless track assembly configured to mount to a rotating wheel drive of a vehicle. The endless track assembly has a rotatable drive sprocket for driving an endless track about a frame and idler wheels. Guide rollers mounted to the frame support and rotate with the drive sprocket and limit the movement of the drive sprocket relative to the frame.

Abstract: The present disclosure is directed to a rotor blade having a passive airflow modifying assembly to create an airflow feature along the blade, based on the instant pressure gradient around the blade during operation. The present disclosure also is directed to a rotor blade that passively channels airflow through the passive airflow modifying assembly to create an air feature that decreases the aerodynamic load, at times when the aerodynamic load experienced by the blade is bearing on the rotatable hub, and one the passively channels airflow through the passive airflow modifying assembly to create an air feature that increases the aerodynamic load, at times when the aerodynamic load is not bearing on the rotatable hub, and one that passively operates to not create an air feature, at times when the requisite pressure gradient is not met and/or when the load conditions are not an issue.

Abstract: A compact wearable modular multifunctional inhalation and detection device. The device includes a housing with at least one port; a removable cartridge module adapted to seat within the housing, the cartridge module including a removable cylindrical cartridge adapted to seat within a cartridge housing. The cartridge includes a source of inhalant, a port and a heating element for heating the inhalant. A permanent magnet and/or an electromagnet is mounted within the cartridge housing to secure the cartridge to the cartridge housing via the adapter ring whereby the cartridge is pneumatically coupled to an inlet chamber in the mouthpiece housing. Multiple sensors are coupled to the air switch and provide data to an onboard processor. The processor executes software to provide a useful output data regarding inhalation activity. In an alternative embodiment, the device housing is adapted to retain a cartridge with a sensor adapted to detect and address airborne pathogens.

Abstract: The invention is a method for determining whether an input image is sufficiently sharp, comprising the steps of providing a blur score threshold value, inputting the input image to an image processing system, generating, by the image processing system, a two-dimensional frequency spectrum of the input image, generating a one-dimensional frequency spectrum from the two-dimensional frequency spectrum, fitting a straight line on the one-dimensional frequency spectrum, and determining a blur score value based on a residual of the fitting, and considering the input image as sufficiently sharp based on a comparison of the blur score value with the blur score threshold value. The invention further relates to a data processing system, a computer program product and a computer readable medium carrying out the above method.

Abstract: To automate time series forecasting machine learning pipeline generation, a data allocation size of time series data may be determined based on one or more characteristics of a time series data set. The time series data may be allocated for use by candidate machine learning pipelines based on the data allocation size. Features for the time series data may be determined and cached by the candidate machine learning pipelines. Predictions of each of the candidate machine learning pipelines using at least the one or more features may be evaluated. A ranked list of machine learning pipelines may be automatically generated from the candidate machine learning pipelines for time series forecasting based upon evaluating predictions of each of the one or more candidate machine learning pipelines.

Abstract: Computer hardware and/or software that performs the following operations: (i) assessing a performance of a plurality of unsupervised machine learning pipelines against a plurality of data sets; (ii) associating the performance with meta-features corresponding to respective pipeline/data set combinations; (iii) training a supervised meta-learning model using the associated performance and meta-features as training data; and (iv) utilizing the trained model to identify one or more pipelines for processing an input data set.

Abstract: An embodiment of the invention may include a method, computer program product, and system for creating a data analysis tool. The method may include a computing device that generates an AI pipeline based on an input dataset, wherein the AI pipeline is generated using an Automated Machine Learning program. The method may include converting the AI pipeline to a non-native format of the Automated Machine Learning program. This may enable the AI pipeline to be used outside of the Automated Machine Learning program, thereby increasing the usefulness of the created program by not tying it to the Automated Machine Learning program. Additionally, this may increase the efficiency of running the AI pipeline by eliminating unnecessary computations performed by the Automated Machine Learning program.

Abstract: Systems and methods are disclosed for monitoring models for bias. In one implementation, a system for automatically assessing a deployed model for selection of a cohort may include a processing device programmed to: apply the deployed model to data representing a first plurality of individuals, the data including at least one characteristic of the first plurality of individuals; based on the application, select a subset of the first plurality of individuals as a cohort; receive data representing a second plurality of individuals labeled as within the cohort, the data including the at least one characteristic of the second plurality of individuals; compare the selected subset and the second plurality of individuals along the at least one characteristic; and determine whether the comparison results in a difference between the selected subset and the second plurality of individuals greater than a threshold.

Abstract: A gas turbine engine includes: a compressor section including a compressor mean radius; a combustor section fluidly coupled downstream of the compressor section and include a combustor mean radius; and a turbine section fluidly coupled downstream of the combustor section and a turbine mid-span radius. The combustor mean radius is greater than each of the compressor mean radius and the turbine mid-span radius.

Abstract: Predefined pipelines may be created with predefined meta-features. Time series data may be segmented using lookback window parameters. Meta-features may be determined for windowed data. Those of the predefined pipelines having a maximum amount of matching predefined meta-features may be determined. Those of the lookback window parameters that result in the windowed data having the meta-features most similar to the meta-features of one or more of the plurality of predefined pipelines may be identified.

Abstract: Computer hardware and/or software that performs the following operations: (i) assessing a performance of a plurality of unsupervised machine learning pipelines against a plurality of data sets; (ii) associating the performance with meta-features corresponding to respective pipeline/data set combinations; (iii) training a supervised meta-learning model using the associated performance and meta-features as training data; and (iv) utilizing the trained model to identify one or more pipelines for processing an input data set.

Abstract: A microelectromechanical system (MEMS) coil assembly is presented herein. In some embodiments, the MEMS coil assembly includes a foldable substrate and a plurality of coil segments. Each coil segment includes a portion of the substrate, two conductors arranged on the portion of the substrate. The substrate can be folded to stack the coil segments on top of each other and to electrically connect first and second conductors of adjacent coil segments. In some other embodiments, the MEMS coil assembly includes a plurality of coil layers stacked onto each other. Each coil layer includes a substrate and a conductor to form a coil. The conductors of adjacent coil layers are connected through a via. The MEMS coil assembly can be arranged between a pair of magnets. An input signal can be applied to the MEMS coil assembly to cause the MEMS coil assembly to move orthogonally relative to the magnets.

Abstract: Systems and methods are disclosed for monitoring models for bias. In one implementation, a system for automatically assessing a deployed model for selection of a cohort may include a processing device programmed to: apply the deployed model to data representing a first plurality of individuals, the data including at least one characteristic of the first plurality of individuals; based on the application, select a subset of the first plurality of individuals as a cohort; receive data representing a second plurality of individuals labeled as within the cohort, the data including the at least one characteristic of the second plurality of individuals; compare the selected subset and the second plurality of individuals along the at least one characteristic; and determine whether the comparison results in a difference between the selected subset and the second plurality of individuals greater than a threshold.

Abstract: There is described a cutting element (106) for a hair cutting device (100). The cutting element (106) comprises a tactile wear indicator (140) that defines a skin-contact surface of the cutting element (106). The tactile wear indicator (140) comprises a wearable outer layer (148) of coating material having a dry lubricant additive (150).

Abstract: According to an aspect, there is provided a method of manufacturing a hair trimmer attachment for a hair trimmer, the hair trimmer attachment comprising a fixed blade comprising: a skin contacting part forming a surface of the hair trimmer attachment to be placed against the skin of a user, in use of the hair trimmer, and an angled part, the angled part being angled relative to the skin contacting part, wherein a plurality of hair openings are spaced apart along a bend between the skin contacting part and the angled part, portions of the fixed blade between the hair openings forming guard teeth of the fixed blade, the method comprising: providing a sheet of material for forming the fixed blade; deforming the sheet of material over a fixed blade support of the hair trimmer attachment to create the bend between the skin contacting part and the angled part of the fixed blade, the bend being curved or angled about an axis extending in a first direction; and forming a compound curved and/or angled portion on the g

Abstract: A method, system, and computer program product for a metalearner for automated machine learning are provided. The method receives a labeled data set. A set of data subsets is generated from the labeled data set. A set of unsupervised machine learning pipelines is generated. A training set is generated from the set of data subsets and the set of unsupervised machine learning pipelines. The method trains a metalearner for unsupervised tasks based on the training set.

Abstract: A compact modular multifunctional inhalation device including a housing having an inlet port and an outlet port; a removable cartridge module adapted to seat within the housing, the cartridge including: a tray within the cartridge for holding a solid inhalant, a heating element mounted within the cartridge above and through the tray for heating the inhalant; and a removable modular electronic circuit adapted to seat within the housing to provide electrical current to the heating element. The heating element is a coil mounted within a chamber in thermal proximity to the solid inhalant. A quartz rod is mounted within the coil. A plunger is mounted within the cartridge to translate therein and compact the solid inhalant. In an alternative embodiment, dual channels and outlet ports are mounted in communication with an inlet port. In another embodiment, the cartridge is a split chamber cartridge with a split plunger mounted therein.

Abstract: Techniques regarding one or more automated machine learning processes that analyze time series data are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a time series analysis component that selects a machine learning pipeline for meta transfer learning on time series data by sequentially allocating subsets of training data from the time series data amongst a plurality of machine learning pipeline candidates.