Abstract: Exemplary embodiments may employ contrastive learning to identify anomalies in unlabeled data, such as tabular financial-related data. The contrastive learning may be performed by a neural network model. The exemplary embodiments may employ a hybrid approach that includes both a supervised component and an unsupervised approach. This enables the use of both supervised and unsupervised techniques to enjoy the expertise of the supervised technique while benefiting from an unsupervised technique. There is not the problem of the computational challenge of calculating probabilities for all locations as found in some conventional approaches.

Abstract: The present disclosure relates to systems and methods for image generation. The methods may include obtaining projection data generated by a scanner; generating, based on a first weighting function, a first image by back-projecting the projection data, the first image having a first region corresponding to a first part of the object; generating, based on a second weighting function, a second image by back-projecting the projection data, the second image having a second region corresponding to the first part of the object, the second region of the second image presenting a better CT number uniformity than the first region of the first image; and generating a third image based on the first image and the second image.

Abstract: The present disclosure relates to systems and methods for image generation. The methods may include obtaining projection data generated by a scanner; generating, based on a first weighting function, a first image by back-projecting the projection data, the first image having a first region corresponding to a first part of the object; generating, based on a second weighting function, a second image by back-projecting the projection data, the second image having a second region corresponding to the first part of the object, the second region of the second image presenting a better CT number uniformity than the first region of the first image; and generating a third image based on the first image and the second image.

Abstract: A display substrate, a method of manufacturing the display substrate, a display panel, and a display device are provided. The display panel includes: an array substrate and an opposite substrate disposed opposite to each other; a liquid crystal layer between the array substrate and the opposite substrate; a first support component on a side of the array substrate facing the liquid crystal layer; and a second support component on a side of the opposite substrate facing the liquid crystal layer. An end portion of a side of the first support component facing away from the array substrate is contacted with an end portion of a side of the second support component facing away from the opposite substrate, and a contact surface has a concave-convex structure.

Abstract: A multi-coordinate system calibration and equipment alignment method includes: determining a first mapping relationship between a first image pixel coordinate system of an intermediate carrier substrate carrying stage and a world coordinate system; determining a second mapping relationship between a second image pixel coordinate system of a backplane carrying stage and the world coordinate system; determining galvanometer start point coordinates in the world coordinate system; obtaining first template calibration coordinates in the world coordinate system by using the first mapping relationship and the galvanometer start point coordinates; obtaining second template calibration coordinates in the world coordinate system by using the second mapping relationship and the galvanometer start point coordinates; aligning the intermediate carrier substrate based on actual coordinates of the intermediate carrier substrate carrying stage and the first template calibration coordinates; and aligning the backplane based on

Abstract: A display substrate, a method of manufacturing the display substrate, a display panel, and a display device are provided. The display panel includes: an array substrate and an opposite substrate disposed opposite to each other; a liquid crystal layer between the array substrate and the opposite substrate; a first support component on a side of the array substrate facing the liquid crystal layer; and a second support component on a side of the opposite substrate facing the liquid crystal layer. An end portion of a side of the first support component facing away from the array substrate is contacted with an end portion of a side of the second support component facing away from the opposite substrate, and a contact surface has a concave-convex structure.

Abstract: The present disclosure relates to systems and methods for image generation. The methods may include obtaining projection data generated by a scanner; generating, based on a first weighting function, a first image by back-projecting the projection data, the first image having a first region corresponding to a first part of the object; generating, based on a second weighting function, a second image by back-projecting the projection data, the second image having a second region corresponding to the first part of the object, the second region of the second image presenting a better CT number uniformity than the first region of the first image; and generating a third image based on the first image and the second image.

Abstract: The present disclosure relates to systems and methods for image generation. The methods may include obtaining projection data generated by a scanner; generating, based on a first weighting function, a first image by back-projecting the projection data, the first image having a first region corresponding to a first part of the object; generating, based on a second weighting function, a second image by back-projecting the projection data, the second image having a second region corresponding to the first part of the object, the second region of the second image presenting a better CT number uniformity than the first region of the first image; and generating a third image based on the first image and the second image.

Abstract: The present disclosure describes techniques to forecast financial data using deep learning. These techniques are operative to transform time series data in a financial context into a machine learning model configured to predict future financial data. The machine learning model may implement a deep learning structure to account for a sequence-sequence prediction where a movement/distribution of the time series data is non-linear. The machine learning model may incorporate features related to one or more external factors affecting the future financial data. Other embodiments are described and claimed.

Abstract: A method and a system for rail transit communication. The method includes: selecting a second target FSO transceiver from the FSO transceivers that are currently located within a signal coverage of a target FSO base station, in response to detecting that a first target free-space-optics (FSO) transceiver moves out of the signal coverage of the target FSO base station when data communication between the target FSO base station and the target user terminal is performed via the first target FSO transceiver, where the target FSO base station is one of the FSO base stations located on the rail; and maintaining the data communication between the target FSO base station and the target user terminal, by using the second target FSO transceiver. Handover among the base stations is reduced for user equipment, data communication rate is increased, and communication experience of passengers can be improved.

Abstract: A system and method for CT image reconstruction are provided. The method may include: obtaining raw data set related to an object; generating a first image set based on the raw data set, wherein the first image set includes a first full quality image and a first max field of view image; generating one or more reference images based on the first max field of view image; generating a first bone information image based on the one or more reference images; generating a second image set based on the raw data set, wherein the second image set includes a second full quality image; generating a second bone information image based on the one or more reference images; correcting hardening beam artifact of the second full quality image based on the second bone information image to generate a hardening beam artifact corrected image.

Abstract: The present disclosure describes techniques to forecast financial data using deep learning. These techniques are operative to transform time series data in a financial context into a machine learning model configured to predict future financial data. The machine learning model may implement a deep learning structure to account for a sequence-sequence prediction where a movement/distribution of the time series data is non-linear. The machine learning model may incorporate features related to one or more external factors affecting the future financial data. Other embodiments are described and claimed.

Abstract: Techniques to use deep learning to forecast future orders for a financial service provider to execute by a future date. These techniques leverage a variety of features to predict an appropriate number of orders to execute, for example, on a next trading day. Some features correspond to market indices including their reconstitution schedule while others may correspond to historical orders by the financial service provider. By segregating the features and filtering individual features, these techniques are able to eliminate some noise and focus on a particular feature for insight into the future orders. Other embodiments are described and claimed.

Abstract: The present disclosure relates to systems and methods for image generation. The methods may include obtaining projection data generated by a scanner; generating, based on a first weighting function, a first image by back-projecting the projection data, the first image having a first region corresponding to a first part of the object; generating, based on a second weighting function, a second image by back-projecting the projection data, the second image having a second region corresponding to the first part of the object, the second region of the second image presenting a better CT number uniformity than the first region of the first image; and generating a third image based on the first image and the second image.

Abstract: The present disclosure relates to systems and methods for image generation. The methods may include obtaining projection data generated by a scanner; generating, based on a first weighting function, a first image by back-projecting the projection data, the first image having a first region corresponding to a first part of the object; generating, based on a second weighting function, a second image by back-projecting the projection data, the second image having a second region corresponding to the first part of the object, the second region of the second image presenting a better CT number uniformity than the first region of the first image; and generating a third image based on the first image and the second image.

Abstract: A system and method for CT image reconstruction are provided. The method may include: obtaining raw data set related to an object; generating a first image set based on the raw data set, wherein the first image set includes a first full quality image and a first max field of view image; generating one or more reference images based on the first max field of view image; generating a first bone information image based on the one or more reference images; generating a second image set based on the raw data set, wherein the second image set includes a second full quality image; generating a second bone information image based on the one or more reference images; correcting hardening beam artifact of the second full quality image based on the second bone information image to generate a hardening beam artifact corrected image.

Abstract: The present disclosure relates to systems and methods for image generation. The methods may include obtaining projection data generated by a scanner; generating, based on a first weighting function, a first image by back-projecting the projection data, the first image having a first region corresponding to a first part of the object; generating, based on a second weighting function, a second image by back-projecting the projection data, the second image having a second region corresponding to the first part of the object, the second region of the second image presenting a better CT number uniformity than the first region of the first image; and generating a third image based on the first image and the second image.