Abstract: The invention relates to a method for determining a water current velocity profile in a water column by registration of a deviation between a first position and a second position of an underwater vehicle travelling in the water column. A batch of underwater vehicles is deployed from a surface vessel into the water. The vehicle(s) steers to the first position, which for the first batch is a predefined estimated position (PEP). The vehicle is by first means recording the second position, which is the actual position (AP). The difference ?P between the predefined estimated position PEP and the actual position is registered and based on the difference a deviation data set is calculated. An updated current profile or stack of horizontal water current velocities UV is determined.

Abstract: Constructing an estimated orientation of the vehicle from a previous position and a previous orientation of the vehicle, then correcting this estimated orientation to obtain a first corrected orientation containing a corrected yaw angle of the vehicle, obtaining a measurement of the yaw angle of the vehicle, then replacing, in the first corrected orientation, the corrected yaw angle with the measured yaw angle, to obtain a second corrected orientation, then delivering the corrected second orientation by way of orientation determined for the vehicle and using, in the next execution of the constructing step, the corrected second orientation by way of previous orientation.

Abstract: Techniques are described herein for detecting and/or enrolling (or commissioning) new “hot commands” that are useable to cause an automated assistant to perform responsive action(s) without having to be first explicitly invoked. In various implementations, an automated assistant may be transitioned from a limited listening state into a full speech recognition state in response to a trigger event. While in the full speech recognition state, the automated assistant may receive and perform speech recognition processing on a spoken command from a user to generate a textual command. The textual command may be determined to satisfy a frequency threshold in a corpus of textual commands Consequently, data indicative of the textual command may be enrolled as a hot command. Subsequent utterance of another textual command that is semantically consistent with the textual command may trigger performance of a responsive action by the automated assistant, without requiring explicit invocation.

Abstract: Implementations can reduce the time required to obtain responses from an automated assistant through proactive caching, locally at a client device, of proactive assistant cache entries—and through on-device utilization of the proactive assistant cache entries. Different proactive cache entries can be provided to different client devices, and various implementations relate to technique(s) utilized in determining which proactive cache entries to provide to which client devices. In some of those implementations, in determining which proactive cache entries to provide (proactively or in response to a request) to a given client device, a remote system selects, from a superset of candidate proactive cache entries, a subset of the cache entries for providing to the given client device.

Abstract: A method for tracking non-homogeneous products on a shelf comprises monitoring weight measurement data points corresponding to the weight of the shelf and the products arranged thereupon, determining a set of weight-event parameters of a weight event, such as product identification and an action taken with respect to the product, and at least one of recording information about the results and displaying information about the results. A system for tracking non-homogeneous products on a shelf comprises processors for carrying out stored program instructions for carrying out the steps of the method.

Abstract: Provided are a semantic classification method and apparatus, a neural network training method and apparatus and a storage medium.

Abstract: In order to provide a method for predicting process deviations in an industrial-method plant, for example a painting plant, by means of which process deviations are predictable simply and reliably, it is proposed according to the invention that the method should comprise the following: automatic generation of a prediction model; prediction of process deviations during operation of the industrial-method plant, using the prediction model.

Abstract: Apparatuses, systems, methods, and computer program products for corn leaf disease detection are described. An apparatus may include an image sensor, an electronic display screen, a processor, and/or a memory storing computer program code executable by the processor to perform operations. An operation may include receiving an image of a corn leaf taken by an image sensor. An operation may include processing an image of a corn leaf using multiple machine learning models, each of the multiple machine learning models determining one or more likelihoods that the corn leaf has a plurality of diseases. An operation may include determining whether a corn leaf has any of a plurality of diseases based on one or more likelihoods. An operation may include displaying, in response to determining that a corn leaf has one or more of a plurality of diseases, the one or more of the plurality of diseases to a user on an electronic display screen.

Abstract: Systems and method for operating and monitoring refrigerators are described. Temperature cycles within the compartment are characterized using statistical, frequency and pattern analysis techniques to derive a steady-state characteristic of temperature within the compartment. A thermal sensor inside the conditioned area is monitored and temperature data sets can be analyzed to determine performance in comparison to a baseline, and energy consumption. Analysis of continuous temperature readings taken from individual or groups of freezers identifies patterns of variations in temperature cycles from which feedback on efficiency can be inferred. Electrical load can be determined by measuring or estimating current usage and identifying periods of time when compressors are active in the refrigerator.

Abstract: The present disclosure describes multi-parameter dynamic sampling methods and systems. An example method includes: configuring two sampling rates for each parameter in a set of sampling parameters; selecting one of the sampling rates for each parameters to sample it; calculating a load for each parameter at the selected sampling rate, sorting the parameters according to the loads, and determining high-loaded parameters according to a sorting result; and determining whether each parameter has data loss, and if at least one of the sampling parameters has data loss, performing down-sampling on the high-loaded sampling parameters within a range of the configured at least two sampling rates.

Abstract: Method and system are provided for efficiently populating a phase diagram for modeling of multiple substances. The method may include defining an n-way phase diagram with data points each being an n-tuple describing the n substance inputs, wherein the n-way phase diagram is defined at a user-configured resolution. The method may select an initial subset of data points and calculate their contribution to the phase diagram. The method may then generate a Bayesian model based on the initial subset of calculated data points and predicting the resultant phase and an associated uncertainty of all the uncalculated data points in the defined phase diagram. The method may select a sample subset of the data points using maximum entropy sampling and calculating a resultant phase for each of the selected data points, and incorporate the calculated phases into the Bayesian model.

Abstract: A method for invoking a user-intended Internet of Things (IoT) device amongst a number of IoT devices is disclosed. The method includes extracting by the number of IoT devices, a number of voice parameters from a voice wakeup command for waking up the device. The method includes sharing by the number of IoT devices, the number of voice parameters amongst the number of IoT devices. The method includes comparing the number of voice parameters with a number of pre-stored voice parameters in the number of IoT devices. The method includes determining, a user-intended IoT device amongst the number of IoT devices based on the voice wakeup command and at least one of a similarity between the plurality of pre-stored voice parameters and the plurality of voice parameters and a previously invoked IoT device associated with a previous voice wakeup command. The method includes invoking the user-intended IoT device selected amongst the number of IoT devices.

Abstract: The invention relates to a method for controlling preparative liquid chromatography, comprising the following steps, at least a part of said steps being implemented by a computer comprising a processor and a display screen coupled to said processor: (a) selecting an analytical liquid chromatography method from among thin layer chromatography (TLC) and high performance liquid chromatography (HPLC), (b) inputting analytical liquid chromatography data obtained by the method selected at step (a) for a product to be purified, (c) accessing a table of separating tools available to the user to implement said preparative liquid chromatography, (d) from said analytical liquid chromatography data and table of available separating tools, selecting an optimal separating tool from said table and computing preparative liquid chromatography operating conditions for said selected separating tool.

Abstract: A method and a system for fault diagnosis with small samples of power equipment based on virtual and real twin spaces are disclosed, which belong to the field of fault diagnosis of power equipment. The method includes: test samples containing different locations, types and severity levels of fault of power equipment are acquired to form a real physical space; a virtual mirror space is acquired by simulation according to a simulation model of the equipment to be diagnosed; the training set in the real physical space is spatially integrated with the sample set in the virtual mirror space to obtain a training sample set in the twin spaces; the training sample set in the twin spaces serves as the supplement to the training set in the real physical space, and the fault type and fault location serve as diagnostic labels to be input to the deep neural network for training.

Abstract: A wireless motion detection system is provided which uses a sharp band-stop and low-pass filters to reject unwanted low and high frequency components of a signal in the CSI. A gap in the frequency domain is caused by taking the absolute value of the signal when using the absolute value of channel matrix H? for motion detection. A sharp band-stop (notch) filter is used to reject any unwanted signals that have significant components in this gap. A low-pass filter is used to reject all unwanted signal after the motion highest frequency.

Abstract: The current document is directed to a methods and systems that use observational data collected by various devices and sensors to generate electronic-data representations of human conversations. The implementations of these methods and systems, disclosed in the current document, provide a highly extensible and generic platform for converting observational data into affect-annotated-timeline outputs that provide both a textual transcription of a conversation and a parallel set of affect annotations to the conversation. The affect-annotated-timeline outputs may be useful to researchers and developers, but also serve as inputs to any of a wide variety of downstream analytical processes and analysis systems that are, in turn, incorporated into many different types of special-purpose analysis and control systems.

Abstract: Systems and methods dynamically extracting n-grams for automated vocabulary updates. Text is received. An n-gram extracted from the text is matched to a canonical n-gram from a vocabulary to identify a tag for the text. An n-gram weight is computed for the n-gram extracted from the text. The n-gram weight may be computed by adjusting a term frequency of the n-gram. A relevancy score is computed for the tag using the n-gram weight and using an n-gram frequency of the canonical n-gram. The relevancy score is computed by dividing the n-gram weight by a value proportional to the n-gram frequency of the canonical n-gram. The relevancy score of the n-gram is presented.

Abstract: A tire system includes a tire-side device and a vehicle-body-side system. The tire-side device may be attached to a tire included in a vehicle. The vehicle-body-side system may be attached to a body of the vehicle. The tire-side device may output a detection signal corresponding to each of a plurality of types of detection targets. The tire-side device may perform processing of the detection signal and generate the data related to the detection target. The tire-side device may perform bidirectional communication with the vehicle-body-side system and transmit the data to the vehicle-body-side system. The vehicle-body-side system may perform bidirectional communication with the tire-side device and receive the data. The vehicle-body-side system may acquire the detection result for the detection target based on the data.

Abstract: In a sensor system for an actuator, in particular a lifting column, a force sensor is configured to detect a total force acting on an actuator part. An acceleration sensor is configured to detect an acceleration of the actuator part. Accordingly, the sensor system has a processing device, which is configured to control a drive of the actuator for moving the actuator part on a basis of the detected total force and the detected acceleration.

Abstract: An audio-visual automated speech recognition model for transcribing speech from audio-visual data includes an encoder frontend and a decoder. The encoder includes an attention mechanism configured to receive an audio track of the audio-visual data and a video portion of the audio-visual data. The video portion of the audio-visual data includes a plurality of video face tracks each associated with a face of a respective person. For each video face track of the plurality of video face tracks, the attention mechanism is configured to determine a confidence score indicating a likelihood that the face of the respective person associated with the video face track includes a speaking face of the audio track. The decoder is configured to process the audio track and the video face track of the plurality of video face tracks associated with the highest confidence score to determine a speech recognition result of the audio track.