Abstract: A data protection system implements a Naïve Bayes classifier-based server health resiliency process that greatly helps the amount of time needed to resolve any health-based issue in the server. The Naive Bayes is an example of a simple classifier that classifies based on probabilities of problematic or potential failure causing events. This helps empower vendor applications to intelligently identify automatically resolve these flaws without the need for vendor personnel on the customer environment. Such a process uses historical cases and trains machine learning models in such a way that troubleshooting, log analysis and recommendations will be done proactively to identify root causes of issue and identify and apply available and appropriate fixes and workarounds.

Abstract: A container prioritization process helps schedule backups of containerized data based on defined attributes and historical data. Containers are classified using a KNN-based classifier based on attributes. A tagger component assigns a priority tag to each container. Containers are backed up by a backup server through a schedule based on the priority tags of the containers. New containers are automatically classified and tagged within the prioritization schedule using the KNN-based classifier.

Abstract: A data protection system uses machine learning to detect the cyber-attacks on a data protection system in advance to notify the user of possible attacks and also instigate any counter attacks to the best possible extent. The system trains a support vector machine model (SVM) to recognize a malware, or other type of attack before it comes into action against the system. This model learns the parameters of hazardous files or code to prepare the best model of attributes of such files to help block the malware proactively. It uses several independent variables as features to gain more accuracy to the threat detection. Some of the parameters include: rate of data change (Drastic/High/Low), attack vulnerability history, resource usage history, performance metrics, application hit ratio, and the like.

Abstract: Embodiments of a device and method are disclosed. In an embodiment, a method for network security involves determining whether a device connected to a network port of a switch of a network is a native device or a non-native device for the network and in response to determining whether the device is the native device or the non-native device for the network, performing native device authentication or non-native device authentication.

Abstract: An access control device monitors devices on a local area network and transmits alerts to a premises operator upon detection of any failures based on monitored operational data. The access control device transmits alerts to relevant device maintenance vendors regarding failures. Vendor alerts may be automatic or may be instigated by the premises operator. The vendor may be provided temporary remote access to one or more devices on the premises LAN for troubleshooting, remote repair, or configuration purposes without port forwarding by a network access device. Access rights may be time limited or cease upon completion of a maintenance activity by the vendor, and may be retracted at any time by the premises operator. The access control device limits network access of the vendor to only permitted devices; no other devices on the network are visible to or accessible by the vendor.

Abstract: Spacers, structural support systems that includes the spacers, and method of coupling components therewith are provided. The spacers may include a body having oppositely disposed ends, cylindrical sidewalls extending therebetween, and radially outward extending flanges at the ends. Inner surfaces of the sidewalls define a longitudinal bore with openings at each of the ends. The bore is configured to receive a shank of a fastener such that the body is secured between a head of the fastener and a structure to which the fastener is secured. The spacer is formed from a super-elastic shape memory alloy that allows for recoverable deformation without failing when at or above a transformation temperature thereof. The sidewalls have an initial shape prior to undergoing deformation, undergo the recoverable deformation when a load thereon exceeds a first threshold, and recover back to the initial shape once the load drops below a second threshold.

Abstract: A vulnerability tagging process helps prioritize backups of datasets in a network by monitoring events that affect containers in the network. The monitored events are processed by an AI-based event analyzer to characterize each event in terms of a potential for destruction or damage to the data by each event. A vulnerability measure is calculated as the product of the number of occurrences of each event based on the severity associated with each event. Once the events are analyzed and the vulnerability scores are calculated, the scores are tagged on each workload. The vulnerability tags can then be utilized by the backup server to modify protection policies and/or prioritize backup schedules for the container workloads.

Abstract: A method for training a neural network system to predict the behavior of a set of interacting agents.

Abstract: Questions play a central role in assessment of a candidate's expertise during an interview or examination. However, generating such questions from input text documents manually needs specialized expertise and experience. Further, techniques that are available for automated question generation require input sentence as well as an answer phrase in that sentence to generate question. This in-turn requires large training datasets consisting tuples of input sentence answer-phrase and the corresponding question. Additionally, training datasets are available are for general purpose text, but not for technical text. Present application provides systems and methods for generating technical questions from technical documents. The system extracts meta information and linguistic information of text data present in technical documents. The system then identifies relationships that exist in provided text data. The system further creates one or more graphs based on the identified relationships.

Abstract: This disclosure describes a card-scan system that can update a card-scan machine learning model to improve card-character predictions for character-bearing cards by using an active-learning technique that learns from card-scan representations indicating corrections by users to predicted card characters. In particular, the disclosed systems can use a client device to capture and analyze a set of card images of a character-bearing card to predict card characters using a card-scan machine learning model. The disclosed systems can further receive card-scan gradients representing one or more corrections to incorrectly predicted card characters. Based on the card-scan gradients, the disclosed systems can generate active-learning metrics and retrain or update the card-scan machine learning model based on such active-learning metrics.

Abstract: Disclosed are aspects of network function placement in virtual graphics processing unit (vGPU)-enabled environments. In one example a network function request is associated with a network function. A scheduler selects a vGPU-enabled GPU to handle the network function request. The vGPU-enabled GPU is selected in consideration of a network function memory requirement or a network function IO requirement. The network function request is processed using an instance of the network function within a virtual machine that is executed using the selected vGPU-enabled GPU.

Abstract: Embodiments of a device and method are disclosed. In an embodiment, a method for network security involves determining whether a device connected to a network port of a switch of a network is a native device or a non-native device for the network and in response to determining whether the device is the native device or the non-native device for the network, performing native device authentication or non-native device authentication.

Abstract: Techniques related to calibration of wide-baseline outside-in multi camera systems are discussed. Such techniques include receiving video sequences and intrinsic parameters corresponding to each of the cameras in the system, generating first extrinsic parameters for the cameras using tracked features and the intrinsic parameters and second extrinsic parameters using location parameters corresponding to motion control systems coupled to the cameras, and combining the first and second extrinsic parameters to provide real-time calibration of extrinsic parameters for the cameras.

Abstract: Embodiments of a device and method are disclosed. In an embodiment, a method for network device authentication involves using Remote Procedure Call (RPC) proxies of network devices of a network at a customer site, accessing identity certificates from Trusted Platform Modules (TPMs) of the network devices, and using the RPC proxies, sequentially establishing Transport Layer Security (TLS) connections between the network devices to perform mutual authentication between the network devices based on the identity certificates.

Abstract: A bearing assembly includes an inner race to receive a rotating component having an axis of rotation, and at least one bearing element coupled to the inner race. The at least one bearing element is to rotate with the inner race along the axis of rotation. The bearing assembly includes an outer race coupled to the at least one bearing element, and a bearing housing coupled to the outer race and to be coupled to a static structure. The bearing housing includes a first frangible portion to release upon receipt of a moment load greater than a moment threshold and a second frangible portion to release upon receipt of a radial load greater than a radial threshold.

Abstract: Examples disclosed herein involve a computing system configured to (i) obtain (a) a first set of sensor data captured by a first sensor system of a first vehicle that indicates the first vehicle's movement and location with a first degree of accuracy and (b) a second set of sensor data captured by a second sensor system of a second vehicle that indicates the second vehicle's movement and location with a second degree of accuracy that differs from the first degree of accuracy, (ii) based on the first set of sensor data, derive a first trajectory for the first vehicle that is defined in terms of a source-agnostic coordinate frame, (iii) based on the second set of sensor data, derive a second trajectory for the second vehicle that is defined in terms of the source-agnostic coordinate frame, and (iv) store the first and second trajectories in a database of source-agnostic trajectories.

Abstract: A method of virtually inspecting a quality of a product in a production environment includes receiving production information associated with the product, wherein the information is indicative of an operation performed on the product in relation to a first process of the production environment. The method further includes: determining a label for the product using a first classifier model based on the received information associated with the product; comparing the determined label against inspection data associated with an inspection of the product; and storing the production information and the inspection data associated with the product in an extension buffer, based on the comparison of the determined label and the inspection data, for retraining the first classifier model. The above method allows for storing new fault category information that is then dynamically used to retrain the model. Accordingly, this allows for retraining of classifier models without human intervention.

Abstract: This disclosure describes a card-scan system that can update a card-scan machine learning model to improve card-character predictions for payment cards, driver licenses, or other character-bearing cards by using an active-learning technique that learns from card-scan representations indicating corrections by users to predicted card characters. In particular, the disclosed systems can use a client device to capture and analyze a set of card images of a character-bearing card to predict card characters using a card-scan machine learning model. The disclosed systems can further receive card-scan gradients representing one or more corrections to incorrectly predicted card characters. Based on the card-scan gradients, the disclosed systems can generate active-learning metrics and retrain or update the card-scan machine learning model based on such active-learning metrics.

Abstract: Disclosed herein are methods, systems, and programming for evaluating a medical workflow. For example, one or more images depicting a medical environment and a medical workflow performed in the medical environment may be received. Contextual information associated with the medical workflow may be determined, and a stage of the medical workflow may be identified, based on the one or more images. A subsequent stage of the medical workflow may be determined based on the identified stage, and first medical content associated with the contextual information and second medical content associated with the subsequent stage may be presented to one or more medical staff located within the medical environment.

Abstract: Conventional Question and Answer (QA) datasets are created for generating factoid questions only and the present disclosure generates longform technical QA dataset from textbooks. Initially, the system receives a technical textbook document and extracts a plurality of contexts. Further, a first plurality of questions are generated based on the plurality of contexts. A plurality of answerable questions are generated further based on the plurality of contexts using an unsupervised template-based matching technique. Further, a combined plurality of questions are generated by combining the first plurality of questions and the plurality of answerable questions. Further, an answer for the combined plurality of questions are generated using an autoregressive language model and a mapping score is computed. Further, a plurality of optimal answers are selected based on the corresponding mapping score.