Abstract: This invention proposes a method of crowd abnormal behavior detection from video using artificial intelligence, includes three steps: step 1: Data-preprocessing; step 2: Feature extraction and abnormal prediction using a three-dimensional convolution neural network (3D CNN), step 3: Post-processing and synthesizing information to issue warning.

Abstract: A method for multi-object tracking from video. The method includes the following steps: (1) Capturing frames from the streaming source and preprocess the data; (2) Extract video features with three choices: a 3D-CNN backbone followed by a Transformer Encoder, a Video Transformer Encoder, a 2D-CNN Encoder with a stack of frames as input followed by a Transformer Encoder; (3) Multi-object tracking using a new end-to-end multi-task deep learning model named JDAT (Joint Detection Association Transformer), then post-processing and updating tracking state with Temporal Aggregation Module (TAM). The deep learning models in step 2 and step 3 are trained simultaneously end-to-end with a loss function that is accumulated over multiple timesteps (Collective Average Loss—CAL). Also, the model can be pretrained with weakly labeled image dataset in a self-supervised learning manner first, then finetuned on supervised video datasets with full tracking labels.

Abstract: The present invention provides a method of masked face recognition from images by artificial intelligence technology including four steps: step 1: generating the images of face wearing a mask; step 2: training a deep learning model for face detection while wearing a mask; step 3: training the deep learning model for face feature extraction while wearing a mask; step 4: building a full pipeline of masked face recognition from images using the trained models from step 2, step 3, and some post-processing algorithms. The method aims to improve the accuracy of identity verification in the context of wearing masks has become popular and compulsory in life.

Abstract: A method may include obtaining, by a computer processor, a request to initiate a cementing procedure. The method may further include determining, by the computer processor, an automated sequence for the cementing procedure. The method may further include transmitting, by the computer processor and based on the automated sequence, a cementing management command that triggers the cementing procedure for cementing equipment in a cementing system. The method may further include obtaining, by the computer processor, sensor data regarding the cementing equipment. The method may further include determining, by the computer processor and in response to the sensor data, whether to perform a next procedure in the automated sequence.

Abstract: The present invention provides a noise modeling method to improve the speech recognition quality to help the recognition system perform better in real-life environments. With this method, we not only add noise to the training audio signal to simulate different environments, but we also add noise labels to the speech transcripts. Since then, the recognition model will perform better in different environments and increase the accuracy of the recognition model.

Abstract: A method may include obtaining, by a computer processor, a request to initiate a cementing procedure. The method may further include determining, by the computer processor, an automated sequence for the cementing procedure. The method may further include transmitting, by the computer processor and based on the automated sequence, a cementing management command that triggers the cementing procedure for cementing equipment in a cementing system. The method may further include obtaining, by the computer processor, sensor data regarding the cementing equipment. The method may further include determining, by the computer processor and in response to the sensor data, whether to perform a next procedure in the automated sequence.

Abstract: Methods and apparatus for controlling a characteristic of a cement slurry at a cementing unit, including regulating a characteristic of the cement slurry employing a closed loop feedback arrangement in the cementing unit, and adjusting a gain of the closed loop feedback arrangement in response to sampling an error of the characteristic.

Abstract: The present invention provides a method for speech separation and recognition. The present invention overcomes the disadvantages of the existing techniques by providing automatic speech recognition and separation that helps managers see what their service agents and customers are saying. From there, quickly and objectively knowing the wishes and concerns of customers as well as whether their service agents can give accurate and correct advice. In addition, the system is constantly updated based on the semi-supervised training mechanism, which means that the system can self-learn from actual data during operation, thereby helping to improve the system's accuracy.

Abstract: The present invention provides a method of facial expression recognition including 3 steps: step 1: collecting facial expression data, which contributes to solve the problem of lacking data, disparate and bias data, that cause the overfitting problem when training the deep learning model; step 2: designing a new deep learning network that able to focus on special regions of the face to extract and learn the important features of facial expressions by intergating ensemble attention modules into basic deep network architecture like ResNet; step 3: training the ensemble attention deep learning model in step 2 on the collected dataset in step 1, using the combination of two loss functions including ArcFace and Softmax to reduce the overfitting problem.

Abstract: Disclosed are various embodiments for managing network address allocations using prefix allocation trees. In one embodiment, a request is received to allocate a network address block. The request specifying a prefix size for the network address block. A particular network address block having the prefix size that is allocatable is determined based at least in part on a prefix allocation tree representing the available and allocated network address space. The prefix allocation tree is updated to indicate that the particular network address block is allocated. An identification of the particular network address block is returned in response to the request to allocate the network address block.

Abstract: Systems and methods for monitoring system health of a well cementing operation are disclosed. A well cementing system includes several fluid pathways and holding/mixing containers. A series of sensors monitors the status of the fluid pathways and the holding/mixing containers. There are redundancies in the fluid pathways, and a preferred order in which the fluid pathways are used. Under normal conditions the fluid for the cementing operation is moved from place to place via the most desired pathway. If the sensors detect a fault, the next-most desired fluid pathway is used. If there are no available fluid pathways, an alarm is issued.

Abstract: Systems and methods for monitoring system health of a well cementing operation are disclosed. A well cementing system includes several fluid pathways and holding/mixing containers. A series of sensors monitors the status of the fluid pathways and the holding/mixing containers. There are redundancies in the fluid pathways, and a preferred order in which the fluid pathways are used. Under normal conditions the fluid for the cementing operation is moved from place to place via the most desired pathway. If the sensors detect a fault, the next-most desired fluid pathway is used. If there are no available fluid pathways, an alarm is issued.

Abstract: A method may include obtaining, by a computer processor, a request to initiate a cementing procedure. The method may further include determining, by the computer processor, an automated sequence for the cementing procedure. The method may further include transmitting, by the computer processor and based on the automated sequence, a cementing management command that triggers the cementing procedure for cementing equipment in a cementing system. The method may further include obtaining, by the computer processor, sensor data regarding the cementing equipment. The method may further include determining, by the computer processor and in response to the sensor data, whether to perform a next procedure in the automated sequence.

Abstract: Methods and apparatus for controlling a characteristic of a cement slurry at a cementing unit, including regulating a characteristic of the cement slurry employing a closed loop feedback arrangement in the cementing unit, and adjusting a gain of the closed loop feedback arrangement in response to sampling an error of the characteristic.

Abstract: An earth-boring tool includes a blade located on a body of the earth-boring tool with a pocket formed in an exposed outer surface of the blade. A formation-engaging structure is affixed within the pocket. The formation-engaging structure includes a distal end, a proximal end and a tapered sidewall therebetween. The distal end of the formation-engaging structure includes a formation-engaging surface. The tapered sidewall engages a tapered inner surface of the pocket. The tapered sidewall of the formation-engaging structure and the tapered inner surface of the pocket are each sized and configured to provide an interference fit between the formation-engaging structure and the pocket of the blade. In additional embodiments, instead of retention by interference fit, the formation-engaging structure is retained to the blade by a threaded fastener threaded within a tapped bore extending through the blade. The threaded fastener is received within a receiving formation of the formation-engaging structure.

Abstract: An earth-boring tool includes a blade located on a body of the earth-boring tool with a pocket formed in an exposed outer surface of the blade. A formation-engaging structure is affixed within the pocket. The formation-engaging structure includes a distal end, a proximal end and a tapered sidewall therebetween. The distal end of the formation-engaging structure includes a formation-engaging surface. The tapered sidewall engages a tapered inner surface of the pocket. The tapered sidewall of the formation-engaging structure and the tapered inner surface of the pocket are each sized and configured to provide an interference fit between the formation-engaging structure and the pocket of the blade. In additional embodiments, instead of retention by interference fit, the formation-engaging structure is retained to the blade by a threaded fastener threaded within a tapped bore extending through the blade. The threaded fastener is received within a receiving formation of the formation-engaging structure.

Abstract: A master tracking device, including a first transceiver for a local area network (LAN) configured to acquire a tag information from a plurality of radio frequency identification (RFID) tags; a global positioning system (GPS) receiver configured to acquire a location information; a microcontroller; a time base; and a second transceiver for a wide area network (WAN) configured to transmit a time stamp and the acquired information to a server. In other aspects, a method of tracking asserts using a master tracking device and a non-transitory computer readable medium are provided.

Abstract: An earth-boring tool includes a blade located on a body of the earth-boring tool with a pocket formed in an exposed outer surface of the blade. A formation-engaging structure is affixed within the pocket. The formation-engaging structure includes a distal end, a proximal end and a tapered sidewall therebetween. The distal end of the formation-engaging structure includes a formation-engaging surface. The tapered sidewall engages a tapered inner surface of the pocket. The tapered sidewall of the formation-engaging structure and the tapered inner surface of the pocket are each sized and configured to provide an interference fit between the formation-engaging structure and the pocket of the blade. In additional embodiments, instead of retention by interference fit, the formation-engaging structure is retained to the blade by a threaded fastener threaded within a tapped bore extending through the blade. The threaded fastener is received within a receiving formation of the formation-engaging structure.

Abstract: A master tracking device, including a first transceiver for a local area network (LAN) configured to acquire a tag information from a plurality of radio frequency identification (RFID) tags; a global positioning system (GPS) receiver configured to acquire a location information; a microcontroller; a time base; and a second transceiver for a wide area network (WAN) configured to transmit a time stamp and the acquired information to a server. In other aspects, a method of tracking asserts using a master tracking device and a non-transitory computer readable medium are provided.

Abstract: An elastomeric seal ring is located between each bearing pin and each cone of an earth-boring bit. An auxiliary ring or band is imbedded within an annular recess formed in the inner diameter of the seal ring. A portion of the inner diameter of the seal ring as well as the auxiliary ring are in dynamic contact with the bearing pin. The auxiliary ring has a geometric feature that enhances radial flexibility but prevents it from sealing. The geometric feature may be a transverse cut, notches in either the inner or outer diameters, or holes extending between the sides of the auxiliary ring. The auxiliary ring has lubricating properties.