Abstract: A method, computer system, and a computer program product for adaptively selecting an acoustic feature extractor in an Artificial Intelligence system is provided. The present invention may include acquiring a frame of an acoustic signal. The present invention may include checking a status of a flag to be used to indicate a proper acoustic feature extractor to be selected. The present invention may include processing the frame of the acoustic signal by the selected acoustic feature extractor indicated by the checked status. The present invention may include determining, based on data generated in the processing of the frame of the acoustic signal, an actual status of the frame of the acoustic signal. The present invention may include updating the status of the flag according to the actual status.

Abstract: A method, system, and computer product for anomaly detection in a sensor network. The method comprises: receiving measurements from a plurality of sensors in the sensor network. The method further comprises performing a graph Fourier transform on the measurements to obtain a spectrum. The graph Fourier transform is defined by a graph structure generated from the plurality of sensors. The method further comprises generating an anomaly alert in response to high frequency components of the spectrum exceeding a first threshold.

Abstract: Intelligent snapshot tiering facilitates efficient management of snapshots and efficient restore of snapshots. For intelligent snapshot tiering, a storage appliance can limit cross-tier migration to invalidated data blocks of a snapshot instead of an entire snapshot. Based on a policy, a storage appliance can identify a snapshot to be migrated to another storage tier and then determine which data blocks are invalidated by an immediately succeeding snapshot. This would limit network bandwidth consumption to the invalidated data blocks and maintain the valid data blocks at the faster access storage tier since the more recent snapshots are more likely to be restored.

Abstract: Intelligent snapshot tiering facilitates efficient management of snapshots and efficient restore of snapshots. For intelligent snapshot tiering, a storage appliance can limit cross-tier migration to invalidated data blocks of a snapshot instead of an entire snapshot. Based on a policy, a storage appliance can identify a snapshot to be migrated to another storage tier and then determine which data blocks are invalidated by an immediately succeeding snapshot. This would limit network bandwidth consumption to the invalidated data blocks and maintain the valid data blocks at the faster access storage tier since the more recent snapshots are more likely to be restored.

Abstract: A computer implemented method, computer system and computer program product are provided for acoustic event detection in polyphonic acoustic data, according to the method, polyphonic acoustic data is inputted by one or more processing units into a trained neural network trained by labeled monophonic acoustic data, a first output from a hidden layer of the trained neural network is obtained by one or more processing units, and at least one acoustic classification of the polyphonic acoustic data is determined by one or more processing units based on the first output and a feature dictionary learnt from the trained neural network.

Abstract: A storage appliance can be designed to facilitate efficient restore of multiple backed up files in a system that allows files to share data blocks. A data management application or storage OS names data blocks and communicates those names to the storage appliance when backing up to or through the storage appliance. The storage appliance can leverage the data block names when restoring a group of files by restoring at data block granularity instead of file granularity. Restoring at the granularity of the data blocks by their names allows the storage appliance to avoid repeatedly sending a same data block to the restore requestor (e.g., a storage OS or data management application) while still instructing the restore requestor how to reconstruct the corresponding file(s) with mappings between valid data ranges and the named data blocks.

Abstract: Facilitation of determination of detailed location of a source signal is provided. In one embodiment, a device comprises a memory that stores computer executable components; and a processor that executes computer executable components stored in the memory. The computer executable components can comprise: a low-resolution computation logic component that implements a coarse algorithm and determines an approximate direction of arrival (DOA) of a source signal of an input signal, wherein the coarse algorithm uses both a coarse spatial grid and input data received from the input signal to determine the approximate DOA; and an error estimation logic component that estimates an estimation error of the coarse algorithm, and wherein the error estimation logic component uses the estimation error and the approximate DOA to determine a spatial interval range.

Abstract: A method, system, and computer program product for graph-based searching for one or more data streams is disclosed. A computer-implemented method comprises extracting a plurality of tuples from one or more data streams. The method further comprises generating a graph for the plurality of tuples in which a node represents a tuple of the plurality of tuples and an edge represents a correlation between the node and another node, and the edge is generated based at least partly on one or more predetermined queries for the one or more data streams. The method further comprises traversing the graph based on the one or more predetermined queries. Accordingly, embodiments of the present disclosure can improve the search speed by use of the graph-based searching for one or more data streams.

Abstract: Embodiments of the present disclosure relate to a new approach used for adaptively selecting an acoustic feature extractor used in an Artificial Intelligence system. The method comprises: acquiring a frame of acoustic signal; checking a status of a flag to be used to indicate a proper acoustic feature extractor to be selected, the first status of the flag indicates a low-cost feature extractor associated with quasi-stationary acoustic signal, the second status of the flag indicates a high-cost feature extractor associated with non-stationary acoustic signal; processing the frame of acoustic signal by the selected acoustic feature extractor indicated by the checked status; determining, based on data generated in the processing of the frame of acoustic signal, an actual status of the frame of acoustic signal; and updating the status of the flag according to the actual status.

Abstract: An apparatus is described. The apparatus includes an electro-mechanical interface having angled signal interconnects, wherein, the angling of the signal interconnects is to reduce noise coupling between the angled signal interconnects.

Abstract: Electrical interconnects having a non-linear conductive pathway, and related apparatuses and methods, are disclosed herein. In some embodiments, an electrical interconnect may include a non-linear conductive pathway electrically coupling top and bottom conductive portions. In some embodiments, an electrical interconnect may include a non-linear conductive pathway that propagates an electrical signal generating electromagnetic fields with an electrical field orthogonal to the direction of electromagnetic-wave propagation. In some embodiments, an electrical interconnect may include a non-linear conductive pathway portion and a linear conductive pathway portion. Also disclosed are connectors including an electrical interconnect having a non-linear conductive pathway.

Abstract: A technique provides memory efficient caching of metadata managed by a volume layer of a storage input/output stack executing on one or more nodes of a cluster. Efficient caching of the metadata in a memory of a node may be realized through the use of a caching data structure, i.e., a page cache, configured to store a key-value pair, wherein the key is an extent key and the value is a metadata page containing the index entries. The page cache illustratively includes two data structures configured to maintain the properties of Least Recently Used (LRU) and Least Frequently Used (LFU) for the cache. The first data structure is a hash table that stores a dense tree metadata page (value) indexed by the extent key. The second data structure is a recycle queue that controls the metadata page stored in the hash table based on spatial and temporal locality of the page.

Abstract: One or more techniques and/or computing devices are provided for cross-platform replication. For example, a replication relationship may be established between a first storage endpoint and a second storage endpoint, where at least one of the storage endpoints, such as the first storage endpoint, lacks or has incompatible functionality to perform and manage replication because the storage endpoints have different storage platforms that store data differently, use different control operations and interfaces, etc. Accordingly, replication destination workflow, replication source workflow, and/or a proxy representing the first storage endpoint may be implemented at the second storage endpoint comprising the replication functionality.

Abstract: One or more techniques and/or computing devices are provided for cross-platform replication. For example, a replication relationship may be established between a first storage endpoint and a second storage endpoint, where at least one of the storage endpoints, such as the first storage endpoint, lacks or has incompatible functionality to perform and manage replication because the storage endpoints have different storage platforms that store data differently, use different control operations and interfaces, etc. Accordingly, replication destination workflow, replication source workflow, and/or a proxy representing the first storage endpoint may be implemented at the second storage endpoint comprising the replication functionality.

Abstract: With a forever incremental snapshot configuration and a typical caching policy (e.g., least recently used), a storage appliance may evict stable data blocks of an older snapshot, perhaps unchanged data blocks of the snapshot baseline. If stable data blocks have been evicted, restore of a recent snapshot will suffer the time penalty of downloading the stable blocks for restoring the recent snapshot. Creating synthetic baseline snapshots and refreshing eviction data of stable data blocks can avoid eviction of stable data blocks and reduce the risk of violating a recovery time objective.

Abstract: A storage appliance arranges snapshot data and snapshot metadata into different structures, and arranges the snapshot metadata to facilitate efficient snapshot manipulation, which may be for snapshot management or snapshot restore. The storage appliance receives snapshots according to a forever incremental configuration and arranges snapshot metadata into different types of records. The storage appliance stores these records in key-value stores maintained for each defined data collection (e.g., volume). The storage appliance arranges the snapshot metadata into records for inode information, records for directory information, and records that map source descriptors of data blocks to snapshot file descriptors. The storage appliance uses a locally generated snapshot identifier as a key prefix for the records to conform to a sort constrain of the key-value store, which allows the efficiency of the key-value store to be leveraged.

Abstract: A consistency group is used as a basic unit of data management of storage containers served by a storage input/output (I/O) stack executing on one or more nodes of a cluster. The storage container may be a LUN embodied as parent volume (active volume), a snapshot (represented as an independent volume embodied as read-only copy of the active volume), and a clone (represented as another independent volume embodied as a read-write copy (clone) of the active volume). A consistency group (CG) is a set (i.e., collection) of objects, e.g., LUNs or other CGs (nested CG), which may be managed and operated upon collectively by an administrative command via a Storage Area Network administration layer (SAL) of the storage I/O stack.

Abstract: A N-way merge technique efficiently updates metadata in accordance with a N-way merge operation managed by a volume layer of a storage input/output (I/O) stack executing on one or more nodes of a cluster. The metadata is embodied as mappings from logical block addresses (LBAs) of a logical unit (LUN) accessible by a host to durable extent keys, and is organized as a multi-level dense tree. The mappings are organized such that a higher level of the dense tree contains more recent mappings than a next lower level, i.e., the level immediately below. The N-way merge operation is an efficient (i.e., optimized) way of updating the volume metadata mappings of the dense tree by merging the mapping content of all three levels in a single iteration, as opposed to merging the content of the first level with the content of the second level in a first iteration of a two-way merge operation and then merging the results of the first iteration with the content of the third level in a second iteration of the operation.

Abstract: A system can maintain multiple queues for deduplication requests of different priorities. The system can also designate priority of storage units. The scheduling priority of a deduplication request is based on the priority of the storage unit indicated in the deduplication request and a trigger for the deduplication request.

Abstract: A N-way merge technique efficiently updates metadata in accordance with a N-way merge operation managed by a volume layer of a storage input/output (I/O) stack executing on one or more nodes of a cluster. The metadata is embodied as mappings from logical block addresses (LBAs) of a logical unit (LUN) accessible by a host to durable extent keys, and is organized as a multi-level dense tree. The mappings are organized such that a higher level of the dense tree contains more recent mappings than a next lower level, i.e., the level immediately below. The N-way merge operation is an efficient (i.e., optimized) way of updating the volume metadata mappings of the dense tree by merging the mapping content of all three levels in a single iteration, as opposed to merging the content of the first level with the content of the second level in a first iteration of a two-way merge operation and then merging the results of the first iteration with the content of the third level in a second iteration of the operation.