Abstract: A method and a system for monitoring abnormal state of swines based on edge computing are provided, including a data acquisition and processing module, an edge computing gateway, a cloud server and a client, where the data acquisition and processing module includes a microphone array, a digital signal processing module, a power amplification module, a power supply module and a communication module; the microphone array is used to acquire and store audio data collected in the pigsty; after being processed by the data processing module, the audio data is transmitted to the edge computing gateway through the communication module; the edge computing gateway identifies and locates the abnormal sound in the pigsty, and sends the result to the cloud server; the cloud server stores the data, establishes an early warning model of the swine abnormal state, and sends the early warning information to mobile phone or computer client.

Abstract: A scheduling method for a model inference request is provided. The implementation includes: determining, based on a model inference request to be scheduled, at least one first data item to be encoded; determining a cache hit rate corresponding to each model instance based on a first data index and the at least one first data item, where the first data index includes: a plurality of second data items determined by performing deduplication processing based on a plurality of historical data items cached by the plurality of model instances; and a data identifier corresponding to each second data item, which includes a plurality of sub-identifiers, each sub-identifier indicating whether the model instance corresponding to the sub-identifier caches the second data item; determining a target model instance based on the cache hit rate corresponding to each model instance; and scheduling the model inference request to the target model instance to perform inference.

Abstract: Methods, systems, and computer program products for traffic flow forecasting: obtain a graph representing a traffic network; obtain historical time-series traffic data associated with historical traffic conditions at a number of historical time steps in the traffic network; process, with each spatial-temporal graph sandwich transformer of at least one spatial-temporal graph sandwich transformer, the graph and the historical time-series traffic data to generate a sandwich transformer output, wherein each spatial-temporal graph sandwich transformer includes a top temporal transformer, a spatial transformer that receives, as an input, an output of the top temporal transformer and the graph, and a bottom temporal transformer that receives, as an input, an output of the spatial transformer; and generate, based on the sandwich transformer output from each spatial-temporal graph sandwich transformer, predicted time-series traffic data associated with predicted traffic conditions at a number of next time steps in the

Abstract: A display module and a display device are provided. The display module includes a display panel, a support layer, a support structure, and an adhesive structure. The display panel includes a display portion, a bending portion, and a binding portion. The bending portion connects the display portion to the binding portion and makes the binding portion bend to a non-light-emitting side of the display panel. The support layer includes a first support section on a side of the display portion close to the binding portion and a second support section on a side of the binding portion close to the display portion. The support structure and the adhesive structure are located between the first support section and the second support section, and the support layer covers the adhesive structure. Along a second direction, the adhesive structure is located on a side of the support structure close to the bending portion.

Abstract: Provided are methods for generating a multitask machine learning model based on time series data, that may include receiving input time series data associated with an input time series of data points, calculating a pairwise distance between the input time series and a plurality of time series templates, providing the pairwise distance as a first input to a building block of a residual neural network, where the residual neural network has a plurality of multi-dimensional convolutional layers; generating a first output of the first building block of the residual neural network based on the first input, generating a final output of the residual neural network based on the first output, and generating a first output of a multitask machine learning model using a first output layer and a second output of the multitask machine learning model using a second output layer. Systems and computer program products are also disclosed.

Abstract: A display module includes a display panel, a flexible circuit board, a conductive cloth, and a compensation structure. The display panel includes a first binding area disposed on a non-light-exiting surface. The flexible circuit board includes a first portion bound to the first binding area of the display panel. The conductive cloth is located on one side of the flexible circuit board away from the display panel, and covering at least a portion of the first binding area. The compensation structure is in contact with at least a portion of a side surface, and the conductive cloth covers the compensation structure. The conductive cloth includes a main body portion and an extension portion that is located on both sides of the main body portion along the second direction and connected to the main body portion.

Abstract: A system comprising: a liquid ring pump; a separator coupled to an exhaust outlet of the liquid ring pump; a valve module, the valve module being coupled to the separator via a first drainage line and coupled to the liquid ring pump via a second drainage line, the valve module comprising a first valve arranged along the first drainage line and a second valve arranged along the second drainage line; and a controller configured to control the valves.

Abstract: The present application discloses a solar cell and a photovoltaic module, and relates to the field of photovoltaic technologies. As an example, a solar cell includes a semiconductor substrate, a first doped semiconductor portion, a first anti-reflection layer, and a second anti-reflection layer. The semiconductor substrate has a first surface having a first region and a second region that do not overlap. The first doped semiconductor portion is arranged on the first region. The first anti-reflection layer is arranged on a surface of the first doped semiconductor portion. The second anti-reflection layer is arranged on the second region. A difference between a surface reflectivity of a side of the first anti-reflection layer facing away from the semiconductor substrate and a surface reflectivity of a side of the second anti-reflection layer facing away from the semiconductor substrate is greater than or equal to 0.5% and less than or equal to 40%.

Abstract: Systems, methods, and computer program products for multi-head posterior based pre-trained model evaluation are provided. The system includes at least one processor configured to: generate an embedding dataset based on a pre-trained model, the embedding dataset including a plurality of embeddings representing a plurality of entities; cluster each entity of the plurality of entities based on a feature dataset, resulting in a plurality of clusters; and generate a metric for the pre-trained model based on a posterior probability of each entity of the plurality of entities and the plurality of clusters.

Abstract: A method performed by a first network device comprises reaching a synchronization state with a first communication device based on alignment information of a first interface of the first network device. The alignment information of the first interface includes at least one of a line rate order for line rate iteration, an iteration time interval and an iteration start time. The method further comprises determining whether a second network device has reached the synchronization state with a second communication device at a same line rate as the first interface, wherein the second network device includes a second interface, and the second network device tries to reach the synchronization state with the second communication device based on the same alignment information as the first interface of the first network device. The method further comprises locking the same line rate at the first interface of the first network device.

Abstract: Provided are methods that include receiving interaction data associated with a plurality of interactions, the interaction data including interaction records that include a plurality of fields including a static field and a dynamic field, generating a static interaction embedding representation based on static field data associated with the static field and a first transformer model, generating a plurality of dynamic interaction embedding representations based on dynamic field data associated with the dynamic field of a sequence of interaction records and a second transformer model, generating a first intermediate input and a plurality of second intermediate inputs, generating a static sequence embedding representation and dynamic sequence embedding representations based on a third transformer model, and generating at least one prediction based on inputting the static sequence embedding representation and the plurality of dynamic sequence embedding representations to a machine learning model.

Abstract: The disclosure provides an energy-saving control system and method for a boiler in a thermal power plant. The system includes: a prediction module, used for predicting current boiler operating efficiency; an optimization module, used for optimizing boiler input parameters based on a particle swarm algorithm, determining an optimal operating condition parameter combination, and setting adjustment steps of the optimal operating condition parameter combination; an emission detection module, used for obtaining NOx emission data of the boiler in thermal power plant and calculating a NOx emission fluctuation degree according to the NOx emission data; a parameter correction module, used for setting emission weight according to the fluctuation degree and setting a correction value of the optimal operating condition parameter combination according to the emission weight; a regulating and controlling module, used for regulating and controlling the boiler of the thermal power plant.

Abstract: Methods, systems, and computer program products are provided for content-based time series retrieval. An example system includes at least one processor configured to: obtain, from at least one database, a plurality of known time series; for each known time series of the plurality of known time series: compute a pairwise distance matrix between that known time series and each learned template of a plurality of learned templates to generate a plurality of pairwise distance matrices; stack the plurality of pairwise distance matrices together to generate a tensor; and process, with the residual network, the tensor, wherein the residual network receives, as input, the tensor, and provides, as output, a feature vector for that known time series; and provide the feature vector for each known time series of the plurality of known time series.

Abstract: A system comprising: a liquid ring pump; a separator coupled to an exhaust outlet of the liquid ring pump; a valve module, the valve module being coupled to the separator via a first drainage line and coupled to the liquid ring pump via a second drainage line, the valve module comprising a first valve arranged along the first drainage line and a second valve arranged along the second drainage line; and a controller configured to control the valves.

Abstract: A method and a system for monitoring abnormal state of swines based on edge computing are provided, including a data acquisition and processing module, an edge computing gateway, a cloud server and a client, where the data acquisition and processing module includes a microphone array, a digital signal processing module, a power amplification module, a power supply module and a communication module; the microphone array is used to acquire and store audio data collected in the pigsty; after being processed by the data processing module, the audio data is transmitted to the edge computing gateway through the communication module; the edge computing gateway identifies and locates the abnormal sound in the pigsty, and sends the result to the cloud server; the cloud server stores the data, establishes an early warning model of the swine abnormal state, and sends the early warning information to mobile phone or computer client.

Abstract: A display module includes a display panel, a flexible circuit board, a conductive cloth, and a compensation structure. The display panel includes a first binding area disposed on a non-light-exiting surface. The flexible circuit board includes a first portion bound to the first binding area of the display panel. The conductive cloth is located on one side of the flexible circuit board away from the display panel, and covering at least a portion of the first binding area. The compensation structure is in contact with at least a portion of a side surface, and the conductive cloth covers the compensation structure. The conductive cloth includes a main body portion and an extension portion that is located on both sides of the main body portion along the second direction and connected to the main body portion.

Abstract: A separated table lamp, comprising: a base, a first electrical connection portion being arranged on the base, and an electronic control module electrically connected to the first electrical connection portion being arranged inside the base; a lamp head comprising a light source assembly; and a foldable bracket, one end of the foldable bracket being rotatably connected to the lamp head, and the other end of the foldable bracket being detachably connected to the base. The foldable bracket is internally provided with a cable channel for a cable to pass through, a second electrical connection portion is arranged on the end of the foldable bracket connected to the base, one end of the cable is electrically connected to the light source assembly, and the other end of the cable is electrically connected to the second electrical connection portion.

Abstract: A control system comprising: a liquid ring pump; a motor configured to drive the liquid ring pump; and a controller configured to: determine an electrical current within the motor; determine a speed of the motor; calculate a value of a function, the function being a function of the determined electrical current within the motor and the determined speed of the motor; and output one or more control signals based on the calculated value of the function.

Abstract: Methods, systems, and computer program products are provided for embedding learning to provide uniformity and orthogonality of embeddings. A method may include receiving a dataset that includes a plurality of data points including a first plurality of data points having a first classification and a second plurality of data points having a second classification, generating a first normalized class mean vector of the first plurality of data instances having the first classification, generating a second normalized class mean vector of the second plurality of data instances having the second classification, performing a class rectification operation on the first plurality of data instances having the first classification and the second plurality of data instances having a second classification, and generating embeddings of the dataset based on original embedding space projections of the dataset.

Abstract: A control system comprising: a suction line; an exhaust line; an operating liquid line; a liquid ring pump coupled to the suction, exhaust, and operating liquid lines; a regulating device configured to control flow of operating liquid into the liquid ring pump; a pressure sensor configured to measure a pressure of an input fluid to the liquid ring pump via the suction line; a first temperature sensor configured to measure temperature of an exhaust fluid output by the liquid ring pump via the exhaust line; a second temperature sensor configured to measure temperature of an operating liquid received by the liquid ring pump via the operating liquid line; and a controller configured to: using the sensor measurements control the one or more regulating devices.