Abstract: Provided are computer-implemented technologies of authenticating documents. The technologies use a set of photo images (or videos), taken under a certain illumination condition and from a set of distinct tilting angles, on one or more security/ID features of one or more documents of a document genre whose authenticity is ascertained, to train an Artificial Intelligence (AI) machine learning program to build a learned model. The learned model, through the said training, attains a set of angular responses of the document genre under the illumination condition which encode a set of descriptive information about each of the one or more security/ID features of the document genre under the illumination condition. The learned model, then, is applied to authenticate, one by one, a number of target documents of the document genre whose authenticity is unknown and to be determined.

Abstract: A tailgating detection system and method includes a single monocular camera, an embedded computer system for determining a tailgating event based on images captured by the camera, the determining of the tailgating event including detecting and tracking wheels of front and tailgating vehicle candidates and determining respective speeds relative to a speed of a vehicle that the camera is mounted and using frame rate of the camera, a location determining device for determining the location where the tailgating event occurred, and a communication unit for transmitting a notification of the tailgating event including the location where the tailgating event occurred.

Abstract: An Arabic information extraction apparatus includes one or more processors configured to: receive a query comprising a long query or a short query; extract, using one or more language models, a named entity and a keyword from the query to generate extracted information; classify, using one or more classification models, the query to generate a classified query; convert the classified query and the extracted information into a dense vector representation; and determine and output a similarity match between the dense vector representation and a document vector representation of a knowledge base comprising an Islamic law document.

Abstract: A system, apparatus and method of embedded ego vehicle speed estimation apparatus, including a car-mounted monocular camera for capturing a sequence of video frames of an outdoor scene from a moving car, where the outdoor scene includes a road, as a camera channel, and processing circuitry. The processing circuitry is configured with a single-shot network and a 3D convolutional neural network (3D-CNN), the single-shot network segments features of the road in the video frame sequence and generates a masked-attention map for the segmented road features, a concatenation circuit concatenates the masked-attention map as an additional channel to the camera channel to generate a masked-attention input, and the 3D-CNN network receives the masked-attention input and generates an estimated speed of the ego vehicle based on displacement of the segmented road features in the video sequences.

Abstract: A stackable, non-contact device for operating elevator buttons is described. The non-contact device includes a servo mechanism with a dual-arm configured to press either of two elevator buttons. Two proximity sensors are configured to register the approach of a finger touch of either proximity sensor, which commands the servo mechanism to press the corresponding elevator button. The stackable, non-contact device includes a microcontroller configured to receive near field communications from a mobile application, which includes commands for pressing a specific elevator button.

Abstract: Methods, systems, and computer readable media to automatically generate source code for simple object application protocol (SOAP) web services are described. The method can include selecting a type of web service and a web service. The method can also include selecting one or more inputs or one or more outputs corresponding to the type of the selected web service. The method can further include defining one or more conditions for the one or more outputs. The method can also include automatically generating a source code file for the web service based on one or more of the type of web service, the one or more inputs, the one or more outputs, or the one or more conditions, and deploying the source code file to a server. The method can further include generating a document that lists one or more specifications of the web service.

Abstract: An apparatus for generating an inspection schedule includes one or more processors configured to: receive one or more schedule requests comprising inspector features, establishment features, and penalty features; generate inspector information for an inspector model based on the inspector features; generate establishment information, comprising a probability of imposing a penalty on an establishment of the establishment features, for an establishment model based on the establishment features and the penalty features; and generate, for an inspector of the inspector features using a violation model, the inspection schedule based on the inspector information and the establishment information.

Abstract: An Edge encapsulated method and system for real-time detection of a double parking vehicle blocking parked vehicles by capturing images using a mounted monocular camera then processing using two Semi-Supervised Object Detection (sSOD) stages, that is trained with partly labeled and mostly unlabeled data to optimize the model parameters for the detection problem, gathered by capturing video from moving vehicle passing through multiple different vehicle types and parking systems with unconfined location.

Abstract: A method, system, and computer readable medium are described to capture, detect, and recognize faces using machine learning and a single-stage face detector. A method to determine live faces from spoof 2D and spoof 3D images using a liveness score as well as a method to classify faces using machine learning deep convolutional neural networks is also described.

Abstract: Disclosed is a method and apparatus for identifying similar record elements to a query, the method including receiving a query, determining an index for the query, generating candidate records from a reference list to match the query based on the index and applying any one or any combination of a q-gram filter, a length filter, and a shared character count (SCC) filter, determining similarity scores of each of the candidate records identifying records from among the candidate records having a similarity score greater than or equal to a threshold, selecting data records similar to the query based on sorting the selected records according to respective similarity scores, and outputting one or more of the selected data records.

Abstract: Methods, systems, and computer readable media to automatically generate source code for simple object application protocol (SOAP) web services are described. The method can include selecting a type of web service and a web service. The method can also include selecting one or more inputs or one or more outputs corresponding to the type of the selected web service. The method can further include defining one or more conditions for the one or more outputs. The method can also include automatically generating a source code file for the web service based on one or more of the type of web service, the one or more inputs, the one or more outputs, or the one or more conditions, and deploying the source code file to a server. The method can further include generating a document that lists one or more specifications of the web service.

Abstract: A grafting device including a rootstock holding unit and a scion holding unit both provided in a main body and relatively movable in a predetermined direction, at least one of the rootstock holding unit and the scion holding unit includes: a hand module including: a grip portion configured to be openable and closable for gripping a stem of a plant; reciprocating portions an operating rod and a slide plate provided between the grip portion and the main body and capable of reciprocating; a motion converting portion configured to convert reciprocation of the reciprocating portion into an opening/closing motion of the grip portion; and a biasing means configured to bias the reciprocating portion in any one direction of the reciprocating movement; and a drive means provided in the main body and configured to drive the reciprocating portion in a direction opposite to a biasing direction by the biasing means.

Abstract: A multi-dynamic data retrieval and data disbursement method that is carried out with circuitry such as a computer platform that includes a configurable platform with an eligibility engine having a rules-based processing engine for bulk and parallel processing of an extract-transform-load (ETL) data load flow, a workflow engine, and a prioritization engine, and is connected to internal and external data sources via the configurable platform. The method includes authenticating data according to authenticity parameters and generating an assessment of the data based on processing rules to identify task programs and measure ETL data load flow against a predetermined performance threshold. A plurality of granularity levels of data via ETL processing corresponding to the processing rules is generated in response to the rules-based processing engine then a data disbursement of results is output.

Abstract: A seedling growing system includes: a cargo transport container provided with heat insulating treatment; a movement robot for moving on a path in the cargo transport container; seedling growing tray racks including a multi-shelf germination rack for holding, until germination, a seedling growing tray on which seeds are sown, a multi-shelf seedling growing rack for holding a seedling growing tray on which seedlings have germinated, and a multi-shelf shipment rack for holding a seedling growing tray for shipping grown seedlings; and an arm or table provided to the movement robot and capable of transferring each seedling growing tray between the movement robot and each of the multi-shelf germination rack, multi-shelf seedling growing rack, and the multi-shelf shipment rack.

Abstract: A long base sheet is a thin paper like toilet paper, made of water-decomposable paper, and is supplied from a base sheet supply section. A water-soluble adhesive is applied to a surface of the sheet at a predetermined interval in an adhesive applying section. Multiple seeds are placed on the surface of the sheet, and then the sheet is put up to non-adhering remove seeds. Thereafter, in a base sheet transportation/seed pressing section, the sheet is pressed by a pair of rollers and softer than the seed, producing a seeded paper. In the seeded paper, concave portions are on the long base sheet, and have a plane shape approximately equal to a shape of the target seed and depth of one tenth to equal to a height of the target seed, and the target seed adheres to an inside area of each of the concave portions by the water-soluble adhesive.

Abstract: A description of a machine learning (ML) model is received, with the ML model including multiple features such as an unlikely combination feature, which corresponds to a first attribute to be located in an invoice and a second attribute to be located the invoice concurrently with the first attribute. Training data is received, including (i) invoice data with multiple invoices, each including the first attribute and the second attribute, and respective values of the first attribute and the second attribute, and (ii) validity data including indications of which of the invoices are valid and which of the invoices are invalid. The ML model is trained using the training data using the ML model. The training includes applying the values of the attributes to the unlikely combination feature. The ML model is applied to an invoice to be validated to determine a probability that the invoice is invalid.

Abstract: A multi-dynamic data retrieval and data disbursement method that is carried out with circuitry such as a computer platform that includes a configurable platform with an eligibility engine having a rules-based processing engine for bulk and parallel processing of an extract-transform-load (ETL) data load flow, a workflow engine, and a prioritization engine, and is connected to internal and external data sources via the configurable platform. The method includes authenticating data according to authenticity parameters and generating an assessment of the data based on processing rules to identify task programs and measure ETL data load flow against a predetermined performance threshold. A plurality of granularity levels of data via ETL processing corresponding to the processing rules is generated in response to the rules-based processing engine then a data disbursement of results is output.

Abstract: A device includes circuitry configured to provide a configurable platform including a rules-based processing engine, access and manipulate a plurality of configurable databases, retrieve first data from one of the configurable databases, register the first data for task programs, authenticate the first data according to authenticity parameters, process the first data against processing rules, identify and configure each task program when the assessment of the first data satisfies predetermined criteria, measure the ETL data load flow against a predetermined performance threshold, route the ETL data load flow to a database processing engine, and output a data disbursement of results when the first data is authenticated and the predetermined performance threshold has been satisfied by the rules-based processing engine. In one aspect, such implementation can increase data search and retrieval times as well as outputting a more thorough and accurate count of eligible end-user services.