Abstract: A data storage system having data storage devices (DSDs) housed in rows in an enclosure further includes a series of funnel structures within which a respective row of DSDs is positioned, where the funnel structures are configured successively wider from front to back to direct airflow through the respective row to a successively wider central exhaust channel. The system may further include an upper wall structure with a deflector portion configured to direct airflow from above down to a back section of the DSDs, side channels extending beyond the deflector portion toward the back to direct airflow down to successive rows of DSDs beyond the deflector portion, and a central channel extending from the deflector portion toward the front and over a cutout portion of a ceiling structure and configured to receive exhaust airflow from a front section of the DSDs via the cutout portion.

Abstract: A technique for recovering power from data center waste heat involves an organic Rankine cycle which includes pumping an organic working fluid through a low-temperature preheater chamber configured to exchange relatively low-temperature waste heat from low-temperature data storage devices to the organic working fluid flowing through the preheater chamber, pumping the working fluid through a high-temperature evaporator thermally coupled with the preheater chamber and configured to exchange relatively high-temperature waste heat from high-temperature CPUs to the working fluid flowing through the evaporator, and pumping the working fluid vapor from the evaporator to an expander for generating power via expansion of the working fluid. The preheater and evaporator may be directly incorporated with the enclosure box housing the various heat-generating components.

Abstract: A digital video camera architecture for updating an object identification and tracking model deployed with the camera is disclosed. The invention comprises optics, a processor, a memory, and an artificial intelligence logic which may further comprise artificial neural networks. The architecture identifies objects according to a first confidence threshold of the model and identifies candidate objects according to the first confidence threshold and a second confidence threshold. The model may track the motion of the candidate objects within a visual field, separate the candidate objects into false positive candidate objects and false negative candidate objects according to their tracked motions, and present at least a portion of the false positive candidate objects and false negative candidate objects for further annotation.

Abstract: A removable disk clamp assembly for mounting disk media on a motor-driven spindle of a magnetic read-write device includes a disk clamp and a mechanism for generating a predetermined force to press the disk media to a flange of the spindle such that the predetermined force can be repeatedly overcome by an applied counterforce to remove the disk clamp from engagement with a hub of the spindle. Such a mechanism may include a spring-loaded removable disk clamp assembly or a magnetic removable disk clamp assembly, and whereby a vacuum-driven chuck may be employed for disk and clamp handling purposes, all of which are suitable for implementation and use in a read-write device configured for use in an archival data storage system library such as in a cleanroom storage system.

Abstract: Systems, methods, and data storage devices using a video group classifier based on an object tracker are described. A group classifier may be trained using machine learning to classify image objects from a video frame and assign a classifier identifier. An object tracker and the group classifier may be used to determine correspondence between tracker identifiers and classifier identifiers for assigning group identifiers. The object tracker may then be used to determine image objects, assign tracker identifiers, and track the movement of those image objects through a video data stream to associate tracker identifiers with the video frames. The tracker identifier may be used to assign a group identifier to each video frame based the correspondence between the tracker identifier and the classifier identifier.

Abstract: Systems, methods, and data storage devices for image grouping in an end user device using trained machine learning group classifiers are described. The end user device may include an image group classifier configured to classify new image data objects using an image classification algorithm and set of machine learning parameters previously trained for a specific image group. The end user device may determine embeddings that quantify features of the target image object and use those embeddings and the image group classifier to selectively associate group identifiers with each new image data object received or generated by the end user device. Calibration, including selection and training, of the image group classifiers and ranking of classified images are also described.

Abstract: Systems, methods, and data storage devices for image grouping in an end user device using trained machine learning group classifiers are described. The end user device may include an image group classifier configured to classify new image data objects using an image classification algorithm and set of machine learning parameters previously trained for a specific image group. The end user device may determine embeddings that quantify features of the target image object and use those embeddings and the image group classifier to selectively associate group identifiers with each new image data object received or generated by the end user device. Calibration, including selection and training, of the image group classifiers and ranking of classified images are also described.

Abstract: A digital video camera architecture for updating an object identification and tracking model deployed with the camera is disclosed. The invention comprises optics, a processor, a memory, and an artificial intelligence logic which may further comprise artificial neural networks. The architecture may identify objects according to a confidence threshold of a model. The confidence threshold may be monitored over time, and the model may be updated if the confidence threshold drops below an acceptable level. The data for retraining is ideally generated substantially internal to the camera. A filter is generated to process the entire field data set stored on the camera to create a field data subset also stored on the camera. The field data subset may be run through the model to generate cases that may be used in further monitoring, training, and updating of the model.

Abstract: Systems and methods for audio privacy in network video surveillance systems are described. A video camera may include an image sensor and a microphone to generate a video stream. Responsive to detecting a human speaking condition in the video stream, the audio data may be selectively modified to mask a human voice component of the audio data for storing and/or displaying the surveillance video stream.

Abstract: A disk retention system includes a spindle motor assembly with a spindle motor and an electromagnet retainer coupled and rotatable therewith, and a disk media assembly including a disk medium and a ferromagnetic material coupled therewith, whereby the disk is retained on the spindle motor by an adjustable attractive magnetic force between the ferromagnetic material of the disk assembly and the electromagnet retainer of the motor assembly. The motor assembly may further include a pair of stationary electrically-conductive liquid or liquid metal slip rings and a pair of rotatable electrical contacts each electrically coupled with a respective slip ring and with the electromagnet retainer, where the slip rings may utilize a Gallium-Indium-Tin alloy.

Abstract: A data storage device including, in one implementation, a non-volatile memory device having a memory block including a number of memory dies, and a controller coupled to the non-volatile memory device. The controller is configured to monitor a temperature of the data storage device and determine whether the monitored temperature exceeds a first temperature threshold. The controller is also configured to perform a default thermal throttling operation based on the monitored temperature exceeding the first temperature threshold, determine whether the monitored temperature exceeds a second temperature threshold, and perform a customized thermal throttling operation based on the monitored temperature exceeding the second temperature threshold.

Abstract: Systems and methods for site-based estimation of storage requirements, such as for surveillance video cameras, are described. Product information, a data retention policy, and an intended recording mode about a camera of a surveillance system may be received through a user interface of a user device. A baseline storage value is determined based on the received product information and the data retention policy. A storage requirement may be calculated based on the baseline data storage value and a determined recording co-efficient value based on a sample scene at the camera location. Scene descriptors may be generated based on the sample scene to retrieve the recording co-efficient value from a lookup table.

Abstract: A surveillance system includes at least one image or video capture device and a controller configured to determine a change in location for the at least one image or video capture device from a first location to a second location. First image or video data is received from the at least one image or video capture device at the second location, and in response to the location change, a preconfigured neural network is obtained or weights for a neural network are obtained based at least in part on the received first image or video data. Second image or video data is received from the at least one image or video capture device at the second location and an inference operation is performed on the second image or video data by processing the second image or video data using the obtained weights or the obtained preconfigured neural network.

Abstract: In one embodiment, a sensor device includes a sensor configured to obtain sensor data and a communication interface configured to communicate with a set of secondary sensor devices. The set of secondary sensor devices comprise a set of secondary sensors and a set of secondary processing devices. The set of secondary sensors obtain additional sensor data. The set of secondary processing devices process the additional sensor data based on a set of secondary machine learning models, and generate activation data based on the additional sensor data. The sensor device also includes a processing device. The processing device is also configured to receive the activation data from the set of secondary sensor devices and cause the sensor to obtain first sensor data based on the activation data. The processing device is further configured to generate one or more inferences based on the first sensor data and a machine learning model.

Abstract: Systems and methods for site-based estimation of storage requirements, such as for surveillance video cameras, are described. Product information, a data retention policy, and an intended recording mode about a camera of a surveillance system may be received through a user interface of a user device. A baseline storage value is determined based on the received product information and the data retention policy. A storage requirement may be calculated based on the baseline data storage value and a determined recording co-efficient value based on a sample scene at the camera location. Scene descriptors may be generated based on the sample scene to retrieve the recording co-efficient value from a lookup table.

Abstract: Systems and methods for site-based calibration of object detection rules, such as for surveillance video cameras, are described. Video data from a video image sensor may be processed using an object detector to determine object data for a detected object. The object data may be post-processed using a post-processing rule set to determine whether the detected object violates the post-processing rule set. Event notifications to a video surveillance application may be prevented responsive to the object data violating the post-processing rule set.

Abstract: A removable disk clamp assembly for mounting disk media on a motor-driven spindle of a magnetic read-write device includes a disk clamp and a mechanism for generating a predetermined force to press the disk media to a flange of the spindle such that the predetermined force can be repeatedly overcome by an applied counterforce to remove the disk clamp from engagement with a hub of the spindle. Such a mechanism may include a spring-loaded removable disk clamp assembly or a magnetic removable disk clamp assembly, and whereby a vacuum-driven chuck may be employed for disk and clamp handling purposes, all of which are suitable for implementation and use in a read-write device configured for use in an archival data storage system library such as in a cleanroom storage system.

Abstract: A magnetic read-write device includes a disk spindle on which disk media are rotatably mounted, an enclosure in which the spindle is housed, an opening/closing mechanism such as a cover configured for opening to provide access to the spindle and for closing to contain particles that may be generated during operation of the device, and a seal configured for sealing the enclosure when the opening/closing mechanism is closed. The device may further include a pre-loaded hinge coupling the cover with the enclosure, and a loading mechanism such as a spring coupled with the hinge and configured for biasing the cover to a closed position and for applying a sealing force to the seal at an interface of the cover and the enclosure. This type of device may be implemented for use in an archival data storage system library such as in a cleanroom storage system.

Abstract: Systems and methods for processing surveillance video streams using image classification and object detection are described. Video data from a video image sensor may be processed using an image classifier to determine whether an object type is present in a video frame. If the object type is present, the video frame and/or subsequent video frames may be processed using an object detector to provide additional object data, such as position information, for use in other video surveillance processes. In some examples, an event message may be generated and sent to a video surveillance application in response to selective object detection.

Abstract: Systems and methods for site-based calibration of object detection values, such as for surveillance video cameras, are described. Video data from a video image sensor may be processed using an object detector to determine object data and a confidence score for a detected object. The object data and confidence score may be post-processed to apply calibration values based on the camera location to one or more parameters used for determining detection events. Event notifications may be sent for detection events. The calibration values may be determined from a calibration period where a verification object detector is used to verify the object detections and failure analysis is applied to determine calibration values for the camera location.