Abstract: The present disclosure presents distributed attack detection systems and related methods. One such method comprises executing, by a client computing device, a convolutional neural network model that is configured to detect a network attack on the client computing device; receiving an HTTP request; extracting a uniform resource locator contained within the HTTP request; inputting the uniform resource locator in the convolutional neural network model; receiving an output from the convolutional neural network model that classifies the uniform resource locator as being directed to a network attack on the client computing device; and transmitting, by the client computing device, embeddings of a hidden layer of the convolutional neural network model to one or more computer servers that are hosting a recurrent neural network model for detecting a distributed network attack across a plurality of client computing devices.

Abstract: Evaluating the engagement and attentiveness of persons in a group by preparing a streaming video of the group, extracting faces of the persons in the group, aligning the extracted faces, assigning an identity to each of the faces, recognizing the emotional state of each face by a temporal emotion recognition module, and estimating the attentiveness of each person based on the recognized emotional state of each face of each person. The estimated attentiveness may also include recognizing the gaze of each person.

Abstract: A system and method are provided for accurately recognizing actions and estimating action intensity. To enable the system to deal with the uncertainty and varied nature inherent in action recognition and intensity indexing, the system is a hybrid system that combines the concept of fuzzy logic and deep recurrent neural networks. The methodology is an attentive neuro-fuzzy system designed to recognize qualitative differences in human actions and to self-adapt to different intensities. The model of the system and method utilizes recurrent neural networks to detect actions from spatio-temporal patterns of human poses, in tandem with an adaptive fuzzy inference system to learn the various human motions used to perform actions with different intensities and then estimate the action's intensity. The integrated model can successfully learn the unique way a specific action with a certain intensity is performed and can estimate the intensity of the respective action.

Abstract: Disclosed are systems and methods to encrypt an image for secure image transmission and parallel decryption using resources from a networked environment. Upon reception of encrypted data from the mobile user, the data can be decrypted by transforming the data, decrypting the transformed data, and inversing the transformation. The decrypted data can be sent for storage in a cloud storage.

Abstract: Disclosed are systems and methods for optimally provisioning tasks to machine instances. The machine instances can correspond to cloud providers and can be part of a multi-cloud. The machine instances can each have various resources available. The task can be received from a user including a job profile. A ranking can be determined for the machine instances. Based on the ranking, the task can be provisioned to one or more of the machine instances.

Abstract: Evaluating the engagement and attentiveness of persons in a group by preparing a streaming video of the group, extracting faces of the persons in the group, aligning the extracted faces, assigning an identity to each of the faces, recognizing the emotional state of each face by a temporal emotion recognition module, and estimating the attentiveness of each person based on the recognized emotional state of each face of each person. The estimated attentiveness may also include recognizing the gaze of each person.

Abstract: The present disclosure relates to a cascade thresholding system to find an optimal threshold for binarization of a gray scale image. The cascade system can perform different levels of quantization on an input image. The cascade system can process each quantized image across multiple threshold levels. SSIM scores can be calculated for the quantized images to determine a best image for binarization. A best binary image can be generated.

Abstract: Disclosed are systems and methods for optimally provisioning tasks to machine instances. The machine instances can correspond to cloud providers and can be part of a multi-cloud. The machine instances can each have various resources available. The task can be received from a user including a job profile. A ranking can be determined for the machine instances. Based on the ranking, the task can be provisioned to one or more of the machine instances.

Abstract: A system and method is disclosed for the adaptive and dynamic adjustment of the characteristics of a cache on a basis that is specific the operation of each logical unit. A storage controller may include a cache. The cache is subdivided so that a portion of the cache is associated with each logical unit that is coupled to the storage controller. A cache management utility monitors the data access commands transmitted to each logical unit of the storage array. The size of the portion of the cache dedicated to each logical unit may be adjusted on the basis of the data access commands directed to the logical unit. The size of the read cache subportion and the size of the write cache subportion of a cache portion associated with a single logical unit may be adjusted on the basis of the read and write commands directed to the logical unit.

Abstract: Systems and methods for providing access to shared storage, for example, using multiple information handling system nodes configured as server nodes. Each server node is given ownership of different portions of data on the shared storage so that each portion of data is allowed to have only one owner at any given time. Data ownership information may be globally stored and used by the multiple server nodes to determine ownership and control access to a requested portion of data.

Abstract: A method of managing node resets in a cluster is provided. Status information from a node cluster including a plurality of nodes may be received. A determination of whether a time delay associated with a first node of the cluster is greater than a node reset time may be made based at least on the received status information. The node reset time may comprise a time after which a node reset is automatically triggered. If the time delay associated with the first node is greater than the node reset time, the node reset time may be dynamically adjusted such that a node reset of the first node is not automatically triggered.

Abstract: A system and method is disclosed for the management of virtual machines in the nodes of a cluster network. An active virtual machine and a standby virtual machine are provided. In operation, a delta file is periodically created in the active node. The delta files include an indication of the changes between the virtual machine as measured at the present and at a preceding point in time. The delta files are transmitted to a standby virtual machine, where the files are applied to the standby virtual machine to synchronize the content of the active virtual machine and the standby virtual machine.

Abstract: A system and method is disclosed for the adaptive and dynamic adjustment of the characteristics of a cache on a basis that is specific the operation of each logical unit. A storage controller may include a cache. The cache is subdivided so that a portion of the cache is associated with each logical unit that is coupled to the storage controller. A cache management utility monitors the data access commands transmitted to each logical unit of the storage array. The size of the portion of the cache dedicated to each logical unit may be adjusted on the basis of the data access commands directed to the logical unit. The size of the read cache subportion and the size of the write cache subportion of a cache portion associated with a single logical unit may be adjusted on the basis of the read and write commands directed to the logical unit.

Abstract: A method of enforcing active-active cluster input/output fencing through out-of-band management network for hung cluster nodes is disclosed. In accordance with one embodiment of the present disclosure, a method of resetting a cluster node in a shared storage system includes identifying the cluster node from a plurality of cluster nodes based on the cluster node failing to respond to a cluster service application. The method further includes propagating a reset signal to the cluster node using an out-of-band channel to perform a hardware reset of the cluster node.

Abstract: A system and method for the implementation of an adaptive cache policy in a storage controller is disclosed in which a cache optimization utility monitors data access commands generated by one or more of the software applications of a server node. On the basis of one or more characteristics of the data access commands, the cache optimization utility can adjust the cache policy of the storage controller. In the case of a database application, the cache policy of the storage controller can be adjusted so that a first cache policy is applied with respect to data access commands directed to the data files of the database and a second cache policy is applied with respect to data access commands directed to transaction log files of the database.

Abstract: Built-to-order products, such as information handling systems, are packaged-to-order based on user preferences for reduced packaging waste. The user is presented packaging options at an order for one or more information handling systems and selects desired options, such as excluding recovery media, application media and user manuals. For instance, a corporate user ordering plural information handling systems has the user manual included in only one package, excludes recovery CDs and elects to have a recovery image with applications electronically available over the Internet, such as with the entry of license keys. Selected options are saved as a packaging policy associated with the user for use with subsequent orders by the user.

Abstract: Systems and methods for providing access to shared storage, for example, using multiple information handling system nodes configured as server nodes. Each server node is given ownership of different portions of data on the shared storage so that each portion of data is allowed to have only one owner at any given time. Data ownership information may be globally stored and used by the multiple server nodes to determine ownership and control access to a requested portion of data.

Abstract: An architecture and method of operation of a server cluster is disclosed in which a virtual standby node is established for each active node of the server cluster. The virtual nodes are each housed in singly physical server. The standby cluster also includes a monitoring module for monitoring the operational status of each virtual machine of the standby node. A cloning and seeding agent is included in the standby node for creating copies of virtual machines and managing the promotion of virtual machines to an operational state.

Abstract: A system and method is disclosed for managing the serving of read and write commands in a computer cluster system having redundant storage. A plurality of database servers is included in the computer cluster network to serve read and write commands from the database clients of the network. One of the database servers is configured to handle both read commands and write commands. The remainder of the database servers are configured to handle only read commands. The database of the computer system includes a redundant storage subsystem that involves the use of mirrored disks associated with each of the database servers.

Abstract: A method, system and software for allocating information handling system resources in response to cluster fail-over events are disclosed. In operation, the method provides for the calculation of a performance ratio between a failing node and a fail-over node and the transformation of an application calendar schedule from the failing node into a new application calendar schedule for the fail-over node. Before implementing the new application calendar schedule for the failing-over application on the fail-over node, the method verifies that the fail-over node includes sufficient resources to process its existing calendar schedule as well as the new application calendar schedule for the failing-over application. A resource negotiation algorithm may be applied to one or more of the calendar schedules to prevent application starvation in the event the fail-over node does not include sufficient resources to process the failing-over application calendar schedule as well as its existing application calendar schedules.