Abstract: Systems and techniques for scene classification and prediction is provided herein. A first series of image frames of an environment from a moving vehicle may be captured. Traffic participants within the environment may be identified and masked based on a first convolutional neural network (CNN). Temporal classification may be performed to generate a series of image frames associated with temporal predictions based on a scene classification model based on CNNs and a long short-term memory (LSTM) network. Additionally, scene classification may occur based on global average pooling. Feature vectors may be generated based on different series of image frames and a fusion feature vector may be obtained by performing data fusion based on a first feature vector, a second feature vector, a third feature vector, etc. In this way, a behavior predictor may generate a predicted driver behavior based on the fusion feature.

Abstract: According to one aspect, scene classification may be provided. An image capture device may capture a series of image frames of an environment from a moving vehicle. A temporal classifier may classify image frames with temporal predictions and generate a series of image frames associated with respective temporal predictions based on a scene classification model. The temporal classifier may perform classification of image frames based on a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a fully connected layer. The scene classifier may classify image frames based on a CNN, global average pooling, and a fully connected layer and generate an associated scene prediction based on the scene classification model and respective temporal predictions. A controller of a vehicle may activate or deactivate vehicle sensors or vehicle systems of the vehicle based on the scene prediction.

Abstract: Driver behavior recognition or driver behavior prediction are described herein. A first image sequence including image frames associated with a forward-facing image capture device of a vehicle and a corresponding vehicle data signal sequence may be received. A second image sequence including image frames associated with a rear or driver facing image capture device of the vehicle may be received. Feature vectors may be generated for respective sequences using neural networks, such as a convolutional neural network (CNN), a depth CNN, a recurrent neural network (RNN), a fully connected layer, a long short term memory (LSTM) layer, etc. A fusion feature may be generated by performing data fusion on any combination of the feature vectors. A predicted driver behavior may be generated based on the LSTM layer and n image frames on an image sequence and include x number of prediction frames.

Abstract: Various communication systems may benefit from appropriate handling of secure data. More specifically, certain packet-based communication systems may benefit from a mechanism to support coordinated packet delivery of one or more encrypted sessions. A method can include identifying metadata for an application flow, wherein the application flow is encrypted. The method can also include publishing the metadata in a core network, wherein the metadata is unencrypted when published.

Abstract: Driver behavior recognition may be provided using a processor and a memory. The memory may receive an image sequence and a corresponding vehicle data signal sequence. The processor may generate or process features for each frame of the respective sequences. The processor may generate a first feature vector based on the image sequence and a first neural network. The processor may generate a second feature vector based on a fully connected layer and the vehicle data signal sequence. The processor may generate a fusion feature by performing data fusion based on the first feature vector and the second feature vector. The processor may process the fusion feature using a long short term memory layer and store the processed fusion feature as a recognized driver behavior associated with each corresponding frame. The processor may, according to other aspects, generate the fusion feature based on a third feature vector.

Abstract: According to one aspect of the invention there is provided an apparatus including at least one processor configured to detect a failure with a first cellular network base station; and establish an out of band communication channel with the first cellular network base station via a second cellular network base station being adjacent to the first cellular network base station to enable remote maintenance of the first cellular network base via the established out of band communication channel.

Abstract: A system, computer-readable medium, and method for improving semantic mapping and traffic participant detection for an autonomous vehicle are provided. The methods and systems may include obtain a two-dimensional image, obtain a three-dimensional point cloud comprising a plurality of points, perform semantic segmentation on the image to map objects with a discrete pixel color, and overlaying the semantic segmentation on the image to generate a updated image, generate superpixel clusters from the semantic segmentation to group like pixels together, project the point cloud onto the updated image comprising the superpixel clusters, and remove points determined to be noise/errors from the point cloud based on determining noisy points within each superpixel cluster.

Abstract: Information is determined affecting data presentation of part of a data stream to a user application on a UE, and may be EC information and/or QoE information caused at least by the data presentation. The information is sent from the UE toward a content server from which the data stream is received by the UE. At radio network element(s), radio timer information corresponding to data transmission of part of the data stream from a base station to a UE is determined and sent (e.g., possibly with the energy consumption information and/or QoE information) to other radio network elements and/or to the content server. The content server can adjust streaming strategy of the data stream based on the information received, and the radio network element(s) can perform power aware scheduling and/or radio timer adjustments based on received EC information and/or the QoE information.

Abstract: Determination of the position of devices may be useful in various communication systems. For example, wireless communication systems that support emergency services may benefit from being able to make a vertical position determination of user equipment and/or network elements within a building or in other indoor environments, such as caves. A method can be implemented by a processor of a base station. The method can include receiving from at least one user equipment, at least one report based on at least a signal strength of a wireless connection between the at least one user equipment and the base station. The method can also include determining a vertical position of the base station, from the at least one report.

Abstract: Data in a storage system is deduplicated after receiving from at least one writing entity requests for a plurality of write operations for a corresponding plurality of data blocks in a storage object. The received blocks are buffered and sorted in order and a sequence of clumps is created from the buffered blocks, where each clump comprises a grouping of at least one of the sorted, buffered blocks. A boundary is determined between at least one pair of clumps based at least in part on the content of at least one of the buffered blocks, and it is then determined whether at least one of the clumps is a duplicate of a previously stored clump.

Abstract: Managing contact transfer requests in a contact center with a processor of the contact center receiving a request to transfer a contact to a destination within the contact center. Next, the processor determines in real time, one or more first characteristics related to a source of the request and one or more second characteristics related to the destination of the request. Ultimately, based on the one or more first characteristics and the one or more second characteristics, the processor performs one of: a) transferring the contact to the destination, or b) preventing transfer of the contact to the destination.

Abstract: A method and system for grouping and compressing system logs are described herein. A generation module residing and executing on a computer system may be configured to generate system logs containing system data important for support purposes describing the computer system, and system log metadata for describing the system logs. A grouping module residing and executing on a computer system may be configured to group system logs based on the system log metadata. Each group of system logs may comprise two or more system logs having the same or similar system log metadata. A data container is produced for each group of system logs and the data container is compressed. System logs having the same or similar system log metadata are more likely to have similar data, thus resulting in a higher degree of compression when grouped and compressed together.

Abstract: The present disclosure generally relates to methods and systems for identifying objects from a 3D point cloud and a 2D image. The method may include determining a first set of 3D proposals using Euclidean clustering on the 3D point cloud and determining a second set of 3D proposals from the 3D point cloud based on a 3D convolutional neural network. The method may include pooling the first and second sets of 3D proposals to determine a set of 3D candidates. The method may include projecting the first set of 3D proposals onto the 2D image and determining a first set of 2D proposals using 2D convolutional neural network. The method may include pooling the projected first set of 3D proposals and the first set of 2D proposals to determine a set of 2D candidates then pooling the set of 3D candidates and the set of 2D candidates.

Abstract: Data in a storage system is deduplicated after receiving from at least one writing entity requests for a plurality of write operations for a corresponding plurality of data blocks in a storage object. The received blocks are buffered and sorted in order and a sequence of clumps is created from the buffered blocks, where each clump comprises a grouping of at least one of the sorted, buffered blocks. A boundary is determined between at least one pair of clumps based at least in part on the content of at least one of the buffered blocks, and it is then determined whether at least one of the clumps is a duplicate of a previously stored clump.

Abstract: Downhole plugs having single anchoring mechanisms and methods thereof are disclosed. The plug comprises of inner mandrel with proximal portion and distal portion, outer assembly and one or more retaining members. The outer assembly comprises of support element, elastomeric element for sealing the gap between the plug and casing, anchoring mechanism at the distal portion for anchoring the plug to the casing and nose element. The elastomeric element is retained in a compressed state at the downhole end by the anchoring mechanism and at the up hole end by the retaining members. In some embodiments, the retaining members are snap rings that are pushed down from step portions at the proximal portion when the plug is mobilized to a set position thereby retaining the elastomeric element. In some embodiments, the retaining members are ratcheted open rings that ratchet over the proximal portion thus retaining the elastomeric element.

Abstract: Various systems and devices may benefit from cooperative resources management. For example, third and fourth generation wireless networks may benefit from a mechanism and apparatus to perform cooperative resource management, for example, for video downloads. Various methods are possible. For example, a method can include regulating fill and drain phases for a downloading session, to meet just in time delivery. The regulating can be performed by a user equipment based on parameters provided by a network. Another method can include providing parameters to a user equipment and instructing the user equipment with respect to regulating fill and drain phases for a downloading session, to meet just in time delivery, based on the parameters. A further method can include performing a mutual handshake between an application and a radio network regarding just in time delivery of a download.

Abstract: Various communication systems may benefit from appropriate handling of secure data. More specifically, certain packet-based communication systems may benefit from a mechanism to support coordinated packet delivery of one or more encrypted sessions. A method can include identifying metadata for an application flow, wherein the application flow is encrypted. The method can also include publishing the metadata in a core network, wherein the metadata is unencrypted when published.

Abstract: Performing semantic segmentation of an image can include processing the image using a plurality of convolutional layers to generate one or more feature maps, providing at least one of the one or more feature maps to multiple segmentation branches, and generating segmentations of the image based on the multiple segmentation branches, including providing feedback to, or generating feedback from, at least one of the multiple segmentation branches in performing segmentation in another of the segmentation branches.

Abstract: Various communication systems may benefit from network assisted automatic clustering. For example, wireless communication systems may benefit from such clustering that enables victim to victim communication after the network becomes unavailable, for example due to a disaster. A method can include forming, by an element of a network, a cluster group for a plurality of user equipment in a location. The method can also include communicating, by the element, information comprising a cluster group identifier to a user equipment of the plurality of the user equipment. The cluster group can be configured to operate only when the network fails to operate.

Abstract: Small cell provisioning and validation may be performed, for small cells, in a small cell cluster, based on wireless cellular network connections (i.e., without requiring the use of a backhaul connection). In some implementations, the small cells may communicate with one another using direct Device-to-Device (D2D) communications. The D2D communications may be used to further enhance the network connectivity (i.e., to the cellular network and the OAM server) and to transmit test traffic during performance of the validation functions.