Microsoft Technology Licensing, LLC

Core Wireless Licensing S.a.r.l.

Alexandre De Baynast

Joseph R Cavallaro

Arsalan Ahmad

Marjan Karkooti

Andreas Steinmetzler

Predrag Radosavljevic

Alain Franck Gefflaut

Olga Ivanova

Eldar Akchurin

Alain Gefflaut

Alexander Armin Spengler

Thomas Minka

Smita Ojha

Venkat Narayanan

Vitaly V Filimonov

Zhou Wang

Yi Wang

Dmitry Starostin

William Dunlap

Panagiotis Periorellis

Aleksandr Klimov

Satnam Singh

Markus Cozowicz

Thomas Santen

Ulrich Pinsdorf

Philipp Kranen

Examining time series sequences representing performance counters from executing programs can provide significant clues about potential malfunctions, busy periods in terms of traffic on networks, intensive processing cycles and so on. An unsupervised anomaly detector can detect anomalies for any time series. A combination of known techniques from statistics, signal processing and machine learning can be used to identify outliers on unsupervised data, and to capture anomalies like edge detection, spike detection, and pattern error anomalies. Boolean and probabilistic results concerning whether an anomaly was detected can be provided.

Unsupervised anomaly detection for arbitrary time series

Anomalies detection in error signals of a cloud based service is provided. An application such as an analysis application identifies a machine learning algorithm that matches error signals of components of a cloud based service. A periodic pattern from the error signals is removed with the machine learning algorithm to filter the periodic pattern from an error count in the error signals. The error signals are processed with the machine learning algorithm to detect one or more anomalies with the components. The machine learning algorithm is updated while processing new data to detect new patterns.

Detection of anomalies in error signals of cloud based service

The invention relates to low density parity check decoding. A method for decoding an encoded data block is described. Encoded data block comprising data sub-blocks are stored. Decoding is performed in a pipelined manner using an irregular, block-structured parity check matrix, where at least two data sub-block matrices of the parity check matrix are read from and written in each of a plurality of clock cycles. The reading and writing of the data sub-blocks is evenly distributed between at least two area of a memory. The decoding is performed with shift values which eliminate cycles at or below a predetermined threshold length. An apparatus, computer program product and device are also described.

Method, apparatus, computer program product and device providing semi-parallel low density parity check decoding using a block structured parity check matrix

A stream processing execution engine evaluates development-time performance characteristic estimates in combination with run-time parameters to schedule execution of stream processing software components in a stack of a stream processing application that satisfy a defined performance criterion in a heterogeneous hardware device. A stream processing application includes a stack of interdependent stream processing software components. A stream processing execution engine evaluates one or more performance characteristics of multiple computational resources in the heterogeneous hardware device. Each performance characteristic is associated with performance of a computational resource in executing a computational-resource-dependent instance of a stream processing software component. The stream processing execution engine schedules within the run-time environment a computational resource on which to execute a computational-resource-dependent instance of one of the stream processing software components. The computational-resource-dependent instance is targeted for execution on the computational resource that satisfies a performance policy attributed to the stream processing software component.

Stream processing on heterogeneous hardware devices

A framework capable of providing transparent handling of network traffic in close proximity networks such as home networks is provided. A single virtual network interface is exposed to users/applications on connected devices. A virtual network interface manager determines available physical network interfaces and switches to a different physical network interface or a different configuration on the same physical network interface in a transparent manner to the communicating application(s). This enables the framework to optimize network communications for the communicating applications, devices, and users based on predefined criteria, application requirements such as different data throughput, or changing environment conditions such as interference. Network communication operations are also simplified for users since they are no longer required to have the necessary knowledge for configuring physical network interfaces manually in response to changing conditions.

Framework for optimizing and simplifying network communication in close proximity networks

Growing community of inventors

Aachen, Germany

Alexandre De Baynast