Abstract: A method includes obtaining a test image captured by a camera of a mobile device, the image including a test component; processing the test image using a machine learning model, wherein the machine learning model has been trained by obtaining a 3D model file representing a 3D model of a training component, generating a plurality of images of the training component based on the 3D model file, the plurality of images differing from one another in at least one of orientation, background, or texture, determining locations of the training component, and training the machine learning model using the plurality of images and the locations of the training component, wherein the machine learning model is trained to detect the training component in photographs captured by mobile devices; and presenting one or more candidate identities of the test component based on an output of the machine learning model.

Abstract: A method includes capturing an image using a camera of a mobile device; processing the image using one or more machine learning models, wherein the one or more machine learning models have been trained to identify a face of first packaging in the image, and determine whether the first packaging in the image satisfies one or more capture conditions; providing feedback for image capture based on a first output of the one or more machine learning models relating to the one or more capture conditions; and in response to output of the one or more machine learning models indicating that the one or more capture conditions are satisfied, and in response to the output of the one or more machine learning models indicating that the face of the first packaging is present in the image, sending the image for authentication of the first packaging.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for generating synthetic images, include: obtaining a captured image of a symbol that encodes data; producing a synthetic image from the captured image using a trained machine learning model, wherein the trained machine learning model has been trained using first images and second images of examples of symbols, wherein the second images have a second image quality that is different than a first image quality of first images, and wherein parameters of the machine learning model have been adjusted responsive to image features to tradeoff content loss versus style loss using measurements of information content correlation between third images produced during training and each of the first images and the second images, the measurements being from a comparison metric; and providing the synthetic image for use by a program configured to identify information in images of symbols.

Abstract: Data characterizing a fuel storage facility can be received from one or more of a plurality of sensors disposed in the fuel storage facility. A fuel leak prediction for the fuel storage facility can be determined by a server, based on the received data, and further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility. The fuel leak prediction can be provided by the server. Related apparatus, systems, methods, techniques, and articles are also described.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for generating synthetic images, include: obtaining a captured image of a symbol that encodes data; producing a synthetic image from the captured image using a trained machine learning model, wherein the trained machine learning model has been trained using first images and second images of examples of symbols, wherein the second images have a second image quality that is different than a first image quality of first images, and wherein parameters of the machine learning model have been adjusted responsive to image features to tradeoff content loss versus style loss using measurements of information content correlation between third images produced during training and each of the first images and the second images, the measurements being from a comparison metric; and providing the synthetic image for use by a program configured to identify information in images of symbols.

Abstract: Among other things, the techniques described herein include a method for receiving a plurality of images of one or more containers while the one or more containers are being emptied, the plurality of images comprising a training set of images and a validation set of images; labeling each image of the plurality of images as including either an overfilled container or a not-overfilled container; processing each image of the plurality of images to reduce bias of a machine learning model; training, and based on the labeling, the machine learning model using the plurality of images; and optimizing the machine learning model by performing learning against the validation set, the optimized machine learning model being used to generate a prediction for a new image of a container, the prediction indicating whether the container in the new image was overfilled prior to the new container being emptied.

Abstract: A process includes obtaining a target thermal load profile and a target location; determining weather conditions associated with the target location; simulating regulation of the target thermal load profile by different temperature regulation systems having different corresponding sets of components, subject to the weather conditions, to obtain energy consumption data for each of the different temperature regulation systems; and providing at least one of the different temperature regulation systems based on the energy consumption data, to cause use of the at least one of the different temperature regulation systems having the corresponding set of components.

Abstract: Methods, devices, apparatus, systems and computer-readable storage media for assessing damages on vehicles are provided. In one aspect, a computer-implemented method includes: determining present damage data of at least one section of a vehicle based on an image of the at least one section of the vehicle using at least one machine learning model, comparing the present damage data of the at least one section of the vehicle to historical damage data of the at least one section of the vehicle to generate a comparison result, and determining whether there is a fraud event based on the comparison result. The present damage data includes information of a plurality of hail damage areas on the at least one section of the vehicle.

Abstract: Among other things, the techniques described herein include a method for receiving a plurality of images of one or more containers while the one or more containers are being emptied, the plurality of images comprising a training set of images and a validation set of images; labeling each image of the plurality of images as including either an overfilled container or a not-overfilled container; processing each image of the plurality of images to reduce bias of a machine learning model; training, and based on the labeling, the machine learning model using the plurality of images; and optimizing the machine learning model by performing learning against the validation set, the optimized machine learning model being used to generate a prediction for a new image of a container, the prediction indicating whether the container in the new image was overfilled prior to the new container being emptied.

Abstract: Methods, devices, apparatus, systems and computer-readable storage media for assessing damages on vehicles are provided. In one aspect, a method includes: accessing an image of a vehicle showing shapes each indicating at least one damage area on the vehicle; providing the image as input to a first model to identify the shapes in the image and obtaining shape data describing a position of each shape identified in the image; providing the image as input to a second model to identify one or more panels of the vehicle and obtaining panel data describing a position of each panel identified in the image; automatically correlating the one or more shapes and the one or more panels based on the shape data and the panel data to determine a number of shapes present on each panel; and generating a damage assessment report describing the number of shapes present on each panel.

Abstract: Among other things, systems and techniques are described for a predictive model for determining overall equipment effectiveness (OEE) in industrial equipment. Data including spectral features is obtained. A probability of survival is determined by fitting at least one degradation function to degradation data associated with the industrial equipment. An overall equipment effectiveness metric is predicted as a product of predicted planned production time, predicted performance, and predicted quality output by trained machine learning models.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer for an industrial machine-learning operation model monitoring system, that include the actions of receiving monitoring data for an industrial machine-learning operations model, determining, from the monitoring data, to retrain the industrial machine-learning operations model, where the determining includes computing drift parameters, each of the drift parameters being indicative of a type of observable drift of the industrial machine-learning operations model, where the drift parameters include (i) a usage drift, (ii) a performance drift, (iii) a data drift, and (iv) a prediction drift, and where each drift parameter includes a respective retraining criteria, and confirming, from the drift parameters, the respective retraining criteria is met by at least one of the drift parameters, and triggering, in response to the determining to retrain the industrial machine-learning operations model, an update of the industrial machine-learn

Abstract: Among other things, techniques are described for an after-market service process digitization. Service data is obtained that is associated with at least one asset and comprises at least historical warranty data and current IoT data. Predictive analysis to generate an asset survival prediction is performed based on current data associated with a first asset and the service data. Troubleshooting data associated with the first asset from at least one knowledge data source is received. A warranty coverage metric is determined based on the asset survival prediction and the troubleshooting data, wherein the warranty coverage metric is calculated in real time according to the asset survival prediction and the troubleshooting data. The warranty coverage metric is transformed at a device into human-readable form.

Abstract: Among other things, systems and techniques are described for predictive maintenance of industrial equipment. Sensor data is obtained, e.g., using sensor hubs that are configured to capture sensor data associated with one or more operating conditions of the industrial equipment. The sensor data is input to a trained machine learning model. The trained machine learning model includes a physics based feature extraction model and a deep learning based automatic feature extraction model. Operating conditions associated with operation of the industrial equipment are predicted using the trained machine learning models.

Abstract: Data characterizing a fuel storage facility can be received from one or more of a plurality of sensors disposed in the fuel storage facility. A fuel leak prediction for the fuel storage facility can be determined by a server, based on the received data, and further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility. The fuel leak prediction can be provided by the server. Related apparatus, systems, methods, techniques, and articles are also described.

Abstract: In one aspect, fuel inventory data characterizing a level of fuel stored at a fuel storage facility can be received from a sensor in operable communication with the fuel storage facility. Flow meter data characterizing an amount of fuel dispensed from the fuel storage facility by a fuel dispenser nozzle can be received from a flow meter in fluid communication with the fuel dispenser nozzle and the fuel storage facility. Fuel transaction data characterizing the dispensing of fuel by the fuel dispenser nozzle and the dispensing of the fuel by one or more additional fuel dispenser nozzles in fluid communication with the fuel storage facility can be received. An estimate of meter drift characterizing a change in calibration of the flow meter can be determined based on the fuel inventory data, the flow meter data, and the fuel transaction data. The estimate of meter drift can be provided.

Abstract: Data characterizing a fuel storage facility can be received from one or more of a plurality of sensors disposed in the fuel storage facility. A fuel leak prediction for the fuel storage facility can be determined by a server, based on the received data, and further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility. The fuel leak prediction can be provided by the server. Related apparatus, systems, methods, techniques, and articles are also described.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for an end-to-end wireless sensor hub include: configuring a sensor hubs in an order using a sequence established by 5 a time of addition to a network. The sensor hubs is grouped into one or more groups. Sensor data captured by the one or more groups is obtained according to a current group number, wherein the sensor data is obtained from each group of the one or more groups according to a predetermined schedule.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for generating synthetic images, include: obtaining a captured image of a symbol that encodes data; producing a synthetic image from the captured image using a trained machine learning model, wherein the trained machine learning model has been trained using first images and second images of examples of symbols, wherein the second images have a second image quality that is different than a first image quality of first images, and wherein parameters of the machine learning model have been adjusted responsive to image features to tradeoff content loss versus style loss using measurements of information content correlation between third images produced during training and each of the first images and the second images, the measurements being from a comparison metric; and providing the synthetic image for use by a program configured to identify information in images of symbols.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for glare mitigation techniques include: obtaining images containing a representation of a mark, the images comprising multiple poses of the mark and generating a single image from the images that contain a representation of the mark with reduced glare when compared to the images comprising multiple poses of the mark. The single image is provided for processing of the representation of the mark to identify information associated with the mark.