Abstract: Devices and methods for detecting an analyte in a gas involve the use of plasmonic excitation of a nanostructured sensing element that is tuned to absorb at a narrow bandwidth specific for light absorbed by the analyte. The sensing element can be used as a capacitive or inductive element in a circuit.

Abstract: A communication error diagnosis apparatus for a vehicle, a system including the same and a method thereof may provide a communication error diagnosis apparatus including: a processor configured to transmit a request message including diagnostic identifiers for diagnosing a plurality of controllers that perform vehicle functions and sequence identifiers of the controllers to the controllers depending on a sequence to receive response messages, and configured to analyze vehicle communication errors based on the response messages received from the controllers; and a storage configured to store data and algorithms driven by the processor.

Abstract: A method for controlling a state of a first tube, said first tube being intended to be integrated in an extraction structure, a first server managing a digital descriptor of the first tube, said digital descriptor having a first set of data stored on at least a first memory, said first set of data comprising at least: one identification number of the first tube and; a completion status and a planification status, the method includes generating a first request to a first server from a computer located near the first tube acquiring the identification number in order to generate an inventory status of the first tube, acquiring a first value of a completion status of the first tube, acquiring a second value of a planification status of the first tube, and generating at least one alert when the first or the second value is equal to a predefined state value.

Abstract: The invention relates to devices for the culture of cellular aggregates A comprising a three-dimensional network of interconnected vessels of a biocompatible liquid- and gas-permeable photo polymerised material, wherein the three-dimensional network is connected to a plurality of inlets and a plurality of outlets for the delivery of liquids, and overlayed with a secondary hydrogel network wherein the cellular aggregates are embedded. Herein defined vessels within the three-dimensional network are blocked, thereby defining at least one spatially segregated network within and structurally in contact with the three-dimensional network, wherein the at least one spatially segregated network is connected to a separate inlet and a separate outlet, allowing the supply of a liquid to a subregion within the three-dimensional network.

Abstract: Aspects of the subject technology relate to systems, methods, and computer-readable media for corrosion analysis using magnetic flux leakage measurements. The present technology can magnetic flux leakage data obtained by a magnetic flux leakage tool placed in a pipe within a wellbore and convert the magnetic flux leakage data into image data. Further, the present technology can provide the image data to a machine learning model. The machine learning model is configured to identify one or more physical parameters associated with corrosion present on the pipe.

Abstract: A system for analysis of a fluid sample has a carrier with a channel. A plug with a sensor can be inserted into a socket arranged on the carrier in such a way that the sensor is in contact with an interior volume of the channel. The sensor can be an optical sensor, in particular based on fluorescence. Optical fibres may be connected to the plug. A camera (8) may be provided to record an image of the plug. The carrier may in particular be a microfluidic chip and the channel a microfluidic channel.

Abstract: The present disclosure provides a method of manufacturing a bonding structural test block with defects. The method of manufacturing the bonding structural test block with defects includes: providing a first plate and a second plate; applying an adhesive on an upper surface of the first plate to form an adhesive layer; heating and curing at least partial region of the adhesive layer for the first time; placing the second plate on the adhesive layer; and heating and curing the adhesive layer for the second time to form a boding structural test block. According to the present disclosure, the at least partial region of the adhesive layer is heated and cured for the first time and chemical reaction occurs, so that the at least partial region forms a defect, and controllable manufacturing of the defect is realized. The test block with the defect is subjected to mechanical detection to simulate the actual defective product.

Abstract: A vial supply system is provided with: a sampler configured to supply a vial to a predetermined supply destination by a transport arm; a management device communicatively connected to the sampler, the management device being configured to manage a supply operation of the vial by the sampler; and a display device provided so as to be able to communicate with the management device. When a teaching mode for performing teaching for setting a position of a transport arm at the time when a transport arm of the sampler transports the vial to and from the supply destination is started, the management device is configured to cause the display device to display an operation to be performed by a user in the teaching.

Abstract: A sensor includes a sensing element configured to generate a sensing element output signal indicative of a sensed parameter and a signal path responsive to the sensing element output signal and having at least one of an adjustable gain or an adjustable offset, wherein the signal path is configured to generate a sensor output signal indicative of the sensed parameter. A supply voltage detector is configured to generate a supply voltage signal indicative of which of a plurality of voltage ranges a supply voltage of the sensor falls within and at least one of the adjustable gain or the adjustable offset is adjustable in response to the supply voltage signal.

Abstract: A device for calibrating a laser level includes a base platform, a target, and an image recognition device. The base platform is configured to support the laser level that is to be mounted on the base platform at a first position. The target is arranged at a second position of the base platform and configured to receive a laser. The image recognition device is configured to obtain images of lasers projected on the target before and after the laser level rotates a first angle, determine, based on an image recognition result of the images, positions of the lasers emitted by the laser level to determine a deviation distance, and determine whether the laser level needs to be calibrated based on the deviation distance. The deviation distance is determined by position data of the first position and the second position, and the first angle.

Abstract: The present invention provides a method for inspecting a material to be inspected using ultrasound waves, the method including the following step 201 to step 301, in which step 201 is performed in a condition where: the surface temperature of a material under inspection—atmospheric temperature>2° C., and inspection using ultrasound waves in step 301 satisfies: a refractive attenuation rate?1.5%. Step 201: blowing a fluid from a blowing port onto the material to be inspected. Step 301: inspecting the material to be inspected using the ultrasound waves after step 201 or at the same time as the step 201.

Abstract: Disclosed is a medical robot system including medical robots placed at different locations and a data analysis apparatus. Each of the medical robots includes a controller that transmits data on a state of operation of the medical robot to the data analysis apparatus. The data analysis apparatus includes a data analysis unit that generates a reference for determining whether or not the medical robots are normal, based on the data transmitted from the medical robots. The data analysis unit monitors the data transmitted from each of the medical robots in operation based on the reference.

Abstract: A surgical system is disclosed that includes an end effector, a firing member, a motor, a position sensor, a timer, and a control system. The end effector comprises a staple cartridge comprising a plurality of staples. The staples are deployable from the staple cartridge based on the firing member moving toward a distal position. The motor is configured to drive the firing member between the proximal position and the distal position. The position sensor is configured to measure a positon of the firing member. The timer is configured to measure elapsed time. The control system is configured to control the motor by comparing actual displacement of the firing member over a time interval to anticipated displacement of the firing member over the time interval.

Abstract: An apparatus includes a processor to: present prompts guiding selection of first subset terms for estimation of variants of an experiment design based on a model thereof, and second subset terms for estimation using Bayesian modification; monitor for selections of term; in response to each change in the first subset terms, determine whether all first subset terms can be estimated based on the model; in response to the first subset including too many terms, present an indication of too many terms being selected for estimation based on the model; in response to the first subset including fewer terms than can be estimated based on the model, present an indication that more terms could be selected for estimation based on the model; and for each variant of the experiment design, estimate each first subset term based on the model, and estimate each second subset term using Bayesian modification.

Abstract: A projection apparatus includes a projection system, a distance measuring sensor that is used to adjust the focal point of the projection system and outputs infrared light in the frontward direction, and an enclosure that houses the projection system and the distance measuring sensor. An exit port of the projection system is disposed at a position which is shifted from the distance measuring sensor in a second direction opposite the first direction. The enclosure has a detection opening via which the infrared light exits. The distance measuring sensor has a detection range over which distance detection is allowed and a non-detection range over which no distance detection is allowed and which is shifted from the detection range toward the distance measurement sensor, and the distance measuring sensor is disposed at a distance from the detection opening, the distance including the non-detection range of the distance measuring sensor.

Abstract: An in-vehicle life detection system and detection method thereof are provided. The system includes a processor, an electromagnetic wave detection module, and a warning module. The method includes following steps: vehicle condition identifying step, life form detecting step, and warning step. Upon receiving an engine off signal and a driver absence signal, the processor emits a detection activation signal, activating the electromagnetic wave detection module to emit an electromagnetic wave for detecting a life form. When the life form is detected, the warning module sends a warning signal, indicating that the life form is left in the vehicle when the vehicle is in the engine off status with the doors closed. Thus, the tragedy of a life form remaining inside the vehicle incapable of calling for help is avoided.

Abstract: Non-limiting examples of the present disclosure describe a non-destructive evaluation (NDE) application/service that is configured for NDE of a wooden specimen. The NDE application/service provides a user-friendly graphical user interface that enables inspectors to manage each phase of NDE of a wooden specimen through one or more computing devices. An exemplary NDE application/service is configured to analyze captured acoustic signal data (e.g., ultrasonic signal data) and transform that captured signal data into feature information that is used to more accurately assess the structural integrity of a wooden specimen. For instance, execution of a programmed NDE application/service employs a trained artificial intelligence (AI) classifier that evaluates waveform propagation (e.g., TOF and energy attenuation) through a wooden specimen to classify a condition and a quality the wooden specimen.

Abstract: A wafer drying method that detects molecular contaminants in a drying gas as a feedback parameter for a multiple wafer drying process is disclosed. For example, the method includes dispensing, in a wafer drying module, a drying gas over a batch of wafers. Further, the method includes collecting the drying gas from an exhaust of the wafer drying module and determining the concentration of contaminants in the drying gas. The method also includes re-dispensing the drying gas over the batch of wafers if the concentration of contaminants is greater than a baseline value and transferring the batch of wafers out of the wafer drying module if the concentration is equal to or less than the baseline value.

Abstract: A method for testing a pressure-medium-operated electronic brake system of a vehicle having a valve and sensor device including a control pressure inlet, a control pressure outlet, a plurality of valves selected from electrically activated inlet valves, outlet valves, redundancy valves, and pressure valves, an actual pressure sensor for measuring an actual control pressure, a setpoint pressure sensor for measuring a setpoint control pressure, and an electronic control unit, which has a signal-conducting connection to the electrically activated valves and pressure sensors, for receiving pressure signals and actuating the electrically activated valves, includes testing the setpoint pressure sensor while the control unit is in a passive operating mode, passing the setpoint control pressure directly through to the control pressure outlet, measuring the actual pressure at the control pressure outlet using a sensor, and transmitting the measured value to the control unit for plausibility checking against the setpoi

Abstract: The selection support system selects components constituting a machine tool including a drive system having a motor and a motor drive device configured to drive and control the machine tool, and a housing part configured to house at least a part of the drive system. The selection support system includes an information reception unit configured to receive operation information on operation of the machine tool, machine information on a configuration of the machine tool, and housing part information on the housing part, and a calculation unit. The calculation unit has a temperature estimation unit configured to estimate a temperature of an inside of the housing part, on the basis of the operation information, the machine information, and the housing part information received by the information reception unit.

Abstract: A condition warning system for an apparatus such as a pot and pan washing machine, a control system and control methods for a pot and pan washing machine are provided. The condition warning system includes a control system that monitors operational, safety or compliance parameters of an apparatus, and a light that illuminates a location below (or above) an operator's direct line of sight, and which is outside of the operator's direct line of sight. The control system and control methods include a punitive wash action lockout, an extended wash cycle time, and a deep clean wash cycle.

Abstract: An apparatus for monitoring an ambient environment of a wind turbine is described. The apparatus comprises a cooling system comprising first and second heat exchangers, and a fluid circuit arranged to enable coolant to flow between the first and second heat exchangers. The apparatus further comprises a processor configured to: monitor one or more operational parameters of the cooling system; determine an efficiency of the cooling system based on the monitored one or more operational parameters; and calculate a liquid water content of the ambient environment based on the measured efficiency of the cooling system.

Abstract: A hand-actuatable plier tool for processing cables has a plier head for handling or processing a workpiece such as a cable, two plier handles that can be pivoted relative to one another between an open position and a closed position, an electronic monitoring unit detachably arranged on a first of the plier handles and with which at least the number of handling or processing procedures can be counted and stored. The monitoring unit has an electronic circuit and a signal transmitter emitting actuation signals to the electronic circuit when the plier tool is actuated. The signal transmitter has an energy harvesting module for supplying energy to the monitoring unit and an actuation mechanism activating the signal transmitter.

Abstract: A camera is provided that has an image sensor having a plurality of pixel elements for recording image data of an object stream moved in a direction of movement relative to the camera and having objects of a height, and a control and evaluation unit that is configured to determine the height of a respective object with reference to the image data. The image sensor here is an event-based image sensor and the control and evaluation unit is configured to detect a measurement series of points in time at which pixel elements adjacent in the direction of movement consecutively register an event to determine a speed of an object image of the object on the image sensor from said measurement series and from this the height.

Abstract: The present disclosure provides a method and a device for autonomous driving control, a vehicle, a storage medium and an electronic device. The method includes: obtaining first actual position data of a first vehicle body; obtaining relative position data between a second vehicle body and the first vehicle body; determining second actual position data of the second vehicle body according to the first actual position data and the relative position data, so that the vehicle performs autonomous driving control according to the first and second actual position data. The method can obtain the relative position between two vehicle bodies connected in the non-rigid manner and the real-time positions of the two vehicle bodies under different driving conditions in real time during the driving, can accurately depict the dynamic characteristics of two vehicle bodies, so that the vehicle performs autonomous driving control according to the first and second actual position data.

Abstract: A method of generating training spectra for training of a neural network includes generating a plurality of theoretically generated initial spectra from an optical model, sending the plurality of theoretically generated initial spectra to a feedforward neural network to generate a plurality of modified theoretically generated spectra, sending an output of the feedforward neural network and empirically collected spectra to a discriminatory convolutional neural network, determining that the discriminatory convolutional neural network does not discriminate between the modified theoretically generated spectra and empirically collected spectra, and thereafter, generating a plurality of training spectra from the feedforward neural network.

Abstract: A loading unit detection system includes an elongate member, a loading unit, a magnet, and a GMR IC. The elongate member defines a receiver. The loading unit includes a connector that is configured to be received within the receiver to releasably couple the loading unit to the elongate member. The magnet is supported on the connector and is configured to translate relative to the elongate member as the connector is received within the receiver. The GMR IC is embedded within the elongate member and is configured to output a differential voltage in response to a magnetic field produced by the magnet of the loading unit. The differential voltage is indicative of the position of the loading unit within the receiver of the elongate member.

Abstract: A test device and a calibration method thereof are disclosed. The test device for calibrating a test equipment, which is used to test a waterproof level of an electronic apparatus, comprises: two plates, which are pressed against each other with pressure, wherein minor gap between the two plates are used as water leakage path.

Abstract: A sensor arrangement and a method of operating a sensor arrangement are disclosed. In an embodiment, a sensor arrangement includes a pressure sensor realized as a capacitive pressure sensor, a capacitance-to-digital converter, a test circuit and a switching circuit coupling the capacitance-to-digital converter and the test circuit to the pressure sensor.

Abstract: Embodiments relate to a method including obtaining m measured values for each field sensor by measuring with respect to a first sensor group including first type of field sensors and a second sensor group including different second type of field sensors, which are attached to the rigid body, at m time steps; and calibrating a sensor frame of the first type of field sensor and a sensor frame of the second type of field sensor by using a correlation between the first type of field sensor and the second type of field sensor based on measured values of at least some of the m time steps, wherein the multiple field sensors include different field sensors of a magnetic field sensor, an acceleration sensor, and a force sensor, and a system therefor.

Abstract: A motorized surgical instrument is disclosed. The surgical instrument includes a displacement member, a motor coupled to the displacement member, a control circuit coupled to the motor, a position sensor coupled to the control circuit, and a timer circuit coupled to the control circuit. The control circuit is configured to receive, from the position sensor, a position of the displacement member in a current zone defined by a set displacement interval, measure time at a set position of the displacement interval, wherein the measured time is defined as the time taken by the displacement member to traverse the displacement interval, and set a command velocity of the displacement member for a subsequent zone based on the measured time in the current predefined zone.

Abstract: According to an embodiment of the present invention there is provided an apparatus for controlling a sub-system of a wind turbine. The apparatus comprises a cooling system comprising first and second heat exchangers, and a fluid circuit arranged to enable a coolant to flow between the first and second heat exchangers; and a processor. The processor is configured to: monitor one or more operational parameters of the cooling system; determine an icing risk based on the one or more operational parameters; and generate a control signal for output to the wind turbine sub-system in dependence on the determined icing risk.

Abstract: In the event of an abnormality occurring in a temperature sensor that is used to detect the temperature of a battery, an electrically driven vehicle sets a drivable time by using a reference temperature of the battery and gives permission for emergency drive until a driving time of the electrically driven vehicle reaches the drivable time. When the reference temperature is used for the first time since the occurrence of the abnormality in the temperature sensor, a temperature detected before the occurrence of the abnormality in the temperature sensor is used as the reference temperature. When the reference temperature is used for the second or subsequent time since the occurrence of the abnormality in the temperature sensor, a temperature obtained by applying a resistance value based on an inter-terminal voltage of the battery and an electric current flowing in the battery, to a correlation between battery resistance and battery temperature is used as the reference temperature.

Abstract: A maintenance support system includes a numerical controller that controls the drive of an operating mechanism of an industrial machine and a server that is a support device capable of communicating with the numerical controller, and the maintenance support system supports maintenance of the industrial machine. The numerical controller includes a first information generating unit that acquires, from among data related to a state of operation of the operating mechanism, data related to the state of operation of the operating mechanism when an anomaly is found in an operation of the operating mechanism, and generates first information including the data acquired. The server includes a second information generating unit that generates second information to be proposed to the numerical controller for the maintenance on the basis of the content of the first information.

Abstract: A method of controlling a robot system includes measuring, capturing, and calculating. A measuring device attached to the robot measures a position and an orientation of a marker with respect to the robot. An imaging device captures an image of the marker and a workpiece. A control device calculates a relative positional relationship between the workpiece and the robot in accordance with a result obtained by the measuring device and with the image captured by the imaging device.

Abstract: A micro-electromechanical system (MEMS) transducer assembly includes a transducer including a condenser microphone, an integrated circuit electrically connected to the transducer to receive an output voltage from the transducer, wherein the integrated circuit comprises a test signal generator configured to induce a test acoustic response in the transducer, and an evaluation circuit configured to compare the test acoustic response to a baseline acoustic response to identify a fault in the transducer.

Abstract: A method of determining the location of the first object (10) may include receiving signals at a second object (20) from a plurality of measurement points (11) on the first object (10), estimating locations of the plurality of measurement points (11) on the first object (10), determining an estimate of a location of the first object (10), determining a first measurement of an orientation of the first object (10) based on the estimating of the locations of the plurality of measurement points (11) on the first object (10), and determining a second measurement of the orientation of the first object (10) based on measurements by an orientation sensor (12) on the first object (10). The method may include estimating an error of the estimate of the location of the first object (10) based on a difference between the first and second orientation measurements and adjusting a movement of the second object (20) based on the estimated error.

Abstract: An inspection device includes a chuck top that holds a wafer, a probe card disposed to face the wafer held by the chuck top and having a plurality of contact probes on a surface facing the wafer, a pogo frame that holds the probe card, a bellows that surrounds the probe card and the contact probes and forms a sealed space when the wafer is close to or in contact with the contact probes, a gas exhaust path configured to depressurize the pressure in the sealed space, and a mechanical stopper that is provided between the pogo frame and the chuck top and restricts the vertical inclination of the chuck top when a predetermined contact is made between the wafer and the contact probes.

Abstract: A monitoring system for an industrial operation having one or more machines, the monitoring system operates to obtain operational information comprising performance operating parameters and uses the operational information to create an operational baseline and reference thresholds and monitors real-time operational data to determine if an operating parameter exceeds a reference threshold.

Abstract: A method of controlling a wind turbine is described. The method comprises calculating a current wear rate for each of the main bearing of a turbine rotor and the blade bearings of rotor blades mounted on the turbine rotor, and calculating a blade pitch adjustment of the rotor blades to achieved a desired ratio between main bearing wear and blade bearing wear in dependence on the calculated current wear rates of the main bearing and the blade bearings.

Abstract: A fully-automated handheld pressure calibrator, comprising a housing, and gas circuit and electrical circuit components installed in the housing. The gas circuit components comprise a pressure source capable of supplying a pressurized gas. The gas circuit and electrical circuit components are integrated and installed in the housing in a modular manner, and the shape of the housing is suitable to be held in a hand. The pressure calibrator of the present invention enables all kinds of functions including pressure generation, pressure control, pressure instrument connection, and recording, result calculation, and report output of a pressure calibration process, and is suitable for on-site an on-line calibration of a pressure instrument.

Abstract: An abnormality monitoring apparatus for a wind farm includes: a parameter obtaining part configured to obtain a power generation parameter related to power generation of the wind turbine power generating apparatus and a strain parameter measured by a sensor mounted to a wind turbine blade of the wind turbine power generating apparatus; a member candidate extraction part configured to extract at least two of the wind turbine power generating apparatuses in which a correlation between the power generation parameters of the at least two wind turbine power generating apparatuses is not smaller than a first predetermined value, and a correlation between the strain parameters of the at least two wind turbine power generating apparatuses is not smaller than a second predetermined value; a monitoring group setting part configured to set at least two of the wind turbine power generating apparatuses; and a group monitoring part configured to perform abnormality monitoring.

Abstract: A motorized surgical instrument is disclosed. The surgical instrument includes a displacement member, an energy source, a motor, a control circuit, and a position sensor. The control circuit is configured to initiate firing the displacement member at a predetermined electrical load on the energy source, wherein the predetermined electrical load is applied to the motor to actuate the displacement member, monitor the position of the displacement member via the position sensor, continually sample a voltage of the energy source during a first interval of travel of the displacement member, compare the sampled voltage to a threshold voltage, and continue firing the displacement at the first velocity when the sampled voltage is greater than or equal to the threshold voltage or adjust the first velocity when the sampled voltage is less than the threshold voltage. Techniques for handling motor stall conditions and transitions between velocities also are disclosed.

Abstract: A method for modeling an environment with a risk of nuclear contamination comprising steps of: acquiring, using a detector (10) and through a 3-dimensional displacement of the detector in the environment, information related to the topography of the environment and radiological measurement data of the environment, and then via a computer processing unit (20), associating the radiological measurement data with location data in the environment, the location data having been deduced from path data of the detector, incrementially creating, using the information and via the computer processing unit: at least one matrix in which topographic data of the environment and the radiological data associated with the location data are compiled, and a 3-dimensional mapping representing the environment in which the topographic data and the radiological data are jointly represented.

Abstract: The present disclosure is directed to methods and systems for calibration, calibration verification, and sensitivity checks for a detector. The methods and systems include calibrating a detector by releasing at least one calibrant from at least one calibrant chamber in flow communication with the detector. The systems and methods further include verifying the calibration by releasing at least one verification substance from at least one verification chamber in flow communication with the detector. The systems and methods further include checking a sensitivity of the detector by releasing at least one sensitivity substance from at least one sensitivity chamber in flow communication with the detector.

Abstract: A method for operating a control unit of a motor vehicle including a function unit and a monitoring unit which have a communication connection to one another. In a first check, the function unit is checked for errors, an error of the function unit being inferred if an error counter reaches a threshold value, and the monitoring unit and the function unit exchange first data with one another. In the event of a correct exchange of the first data, a positive change of the error counter is carried out. Otherwise, a negative change of the error counter is carried out. In a second check, the monitoring unit and the function unit exchange second data with one another. In the event of an incorrect exchange of the second data, a negative change of the error counter and a negative change of the threshold value are carried out.

Abstract: A calibration method for a bonder. Characteristics of a force actuator of the bonder are measured and stored in such a way that the force actuator can be controlled optimally during production operation of the bonder on the basis of the measured data. Further, a device for fully automatic or partially automatic bonding force calibration.

Abstract: A three-dimensional coordinate measuring device of the present invention achieves high operability and relaxes limitations on the size of a measurement object. A table which places a measurement object thereon is translatable and/or rotatable around a predetermined axis. A position and an attitude of a probe that is capable of designating a measurement position of a measurement object are identified. A displacement resistance mechanism that generates, when an external force is applied to the table in a displacement direction of the table, a certain resistance force against the external force is provided. A table displacement identifying unit that identifies a displacement amount of the table from an original position is provided. Relative position coordinates of a position designated by the probe are obtained on the basis of the position and the attitude of the probe and the displacement amount of the table.

Abstract: One embodiment provides an apparatus. The apparatus includes a sensor module. The sensor module includes a sensor; and a sensor controller. The sensor controller is to enumerate the sensor to a sensor processing unit in response to being powered on. The enumerating includes communicating enumeration data to the sensor processing unit. The enumeration data includes one or more of a sensor name, a sensor manufacturer name, a sensor serial number, a hardware version, a firmware version, and/or one or more sensor characteristics. The sensor controller is further to monitor operation of the sensor and to provide sensor lifecycle information to the sensor processing unit over the lifecycle of the sensor.

Abstract: Systems and methods for machine learning, models, and related explainability and interpretability are provided. A computing device determines a contribution of a feature to a predicted value. A feature computation dataset is defined based on a selected next selection vector. A prediction value is computed for each observation vector included in the feature computation dataset using a trained predictive model. An expected value is computed for the selected next selection vector based on the prediction values. The feature computation dataset is at least a partial copy of a training dataset with each variable value replaced in each observation vector included in the feature computation dataset based on the selected next selection vector. Each replaced variable value is replaced with a value included in a predefined query for a respective variable. A Shapley estimate value is computed for each variable.