Microsoft Technology Licensing, LLC

Vaishnavi Nattar Ranganathan

Jonathan Bernard Lester

Paramvir Bahl

Ranveer Chandra

Jingxian Wang

Peeyush Kumar

Michael McNab Bassani

Vishal Jain

Nissanka Arachchige Bodhi Priyantha

Sidhant Gupta

Mike Nakahara

Vikram Subramaniam Iyer

Jeremy Randall Reynolds

Upinder Kaur

Hui Qing Li

Lillian Jane Ratliff

Harsh Sandesh Desai

A computing system including a processor configured to receive training data including, for each of a plurality of training timesteps, training forecast states associated with respective training-phase agents included in a training supply chain graph. The processor may train a reinforcement learning simulation of the training supply chain graph using the training data via policy gradient reinforcement learning. At each training timestep, the training forecast states may be shared between the training-phase agents during training. The processor may receive runtime forecast states associated with respective runtime agents included in a runtime supply chain graph. For a runtime agent, at the trained reinforcement learning simulation, the processor may generate a respective runtime action output associated with a corresponding runtime forecast state of the runtime agent based at least in part on the runtime forecast states. The processor may output the runtime action output.

Reinforcement learning simulation of supply chain graph

Examples are disclosed that relate to improving security of radio frequency (RF) backscattered communication. In one example, a RF device includes a primary RF signal receiver, a secondary signal receiver, a signal mixer, and a transmitter. The primary RF signal receiver is configured to receive a RF carrier signal sent from a base station. The secondary signal receiver is configured to receive a masking signal from the base station. The signal mixer is configured to generate a response signal based at least on the RF carrier signal and generate a mixed signal by mixing the response signal and the masking signal. The transmitter is configured to broadcast the mixed signal, via backscattering, as a masked backscattered signal.

Signal masking for secure backscattered communication

The devices and methods leverage harmonics to resolve, separate, and identify devices. The devices and methods use the harmonic patterns associated with a frequency modulating (FM) signal to discern and extract information from the FM signal using correlation learning in a crowded spectrum space where the nodes are transmitting simultaneously on multiple channels. The methods and devices leverage harmonics to resolve, separate, and/or identify wireless communication devices.

Harmonic-enhanced identification (ID) and device resolution for frequency modulating communication

A traceability system for a bulk commodity supply chain is provided. The system includes a tracking device, a location determination subsystem, and at least one computing device having at least one processor. The location determination subsystem is configured to determine positional information of the tracking device while placed in a bulk commodity traveling along the bulk commodity supply chain. The processor receives the positional information from the location subsystem, extracts positional values from the positional information, and processes the positional values to identify motion primitives. A modeling tool is applied to the identified motion primitives to produce a positional path of the tracking device, which is output, for example, via a user interface. The positional path represents travel of the bulk commodity along the supply chain.

Traceability system for bulk commodity supply chain

A wearable radio frequency receiver device is provided, which includes a receiver antenna configured to receive an interrogation signal from a transmitter. The receiver device further includes a sensor coupled to the receiver antenna and configured to receive a physiological input from a user wearing the device and generate a sensor signal based on the physiological input, and a modulator configured to perform direct modulation on the received interrogation signal based on the sensor signal to encode the physiological input in the directly modulated interrogation signal. The receiver antenna may be configured to reflect at least a portion of the directly modulated interrogation signal as backscatter radiation. A transceiver including a transceiver antenna may be provided to receive the directly modulated interrogation signal, and the modulation receiver may be configured to process the directly modulated interrogation signal and output a decoded physiological input.

Direct frequency modulating radio-frequency sensors

Growing community of inventors

Woodinville, WA, United States of America

Vaishnavi Nattar Ranganathan