Abstract: Certain aspects provide techniques and apparatuses for efficiently processing inputs in a neural network using multiple receptive field sizes. An example method includes partitioning a first input into a first set of channels and a second set of channels. At a first layer of a neural network, the first set of channels and the second set of channels are convolved into a first output having a smaller dimensionality a dimensionality of the first input. The first set of channels and the first output are concatenated into a second input. The second input is convolved into a second output via a second layer of the neural network, wherein the second output merges a first receptive field generated by the first layer with a larger second receptive field generated by the second layer. One or more actions are taken based on at least one of the first output and the second output.

Abstract: The present invention relates to a deep learning neural network based security system and a control method therefor and, more particularly, to a deep learning neural network based security system comprising: at least one WiFi node; and a deep learning module for detecting an object from a WiFi signal received from the WiFi node, wherein the deep learning module identifies information on the object when the object is detected.

Abstract: The present invention relates to a deep learning neural network based security system and a control method therefor and, more particularly, to a deep learning neural network based security system comprising: at least one WiFi node; and a deep learning module for detecting an object from a WiFi signal received from the WiFi node, wherein the deep learning module identifies information on the object when the object is detected.

Abstract: A method includes transmitting first wireless signals towards a conveyor belt having multiple layers of material. The first wireless signals penetrate one or more layers in the conveyor belt. The method also includes receiving second wireless signals that have interacted with the conveyor belt. The method further includes identifying a condition of the conveyor belt using the second wireless signals and outputting an indicator identifying the condition of the conveyor belt. Identifying the condition of the conveyor belt could include identifying a thickness of at least one of the layers in the conveyor belt. This could be done by identifying pulses in the second wireless signals and using time of flight calculations.

Abstract: A method includes transmitting first wireless signals towards a conveyor belt having multiple layers of material. The first wireless signals penetrate one or more layers in the conveyor belt. The method also includes receiving second wireless signals that have interacted with the conveyor belt. The method further includes identifying a condition of the conveyor belt using the second wireless signals and outputting an indicator identifying the condition of the conveyor belt. Identifying the condition of the conveyor belt could include identifying a thickness of at least one of the layers in the conveyor belt. This could be done by identifying pulses in the second wireless signals and using time of flight calculations.

Abstract: A method includes transmitting wireless signals toward material in a tank. The method also includes receiving first return wireless signals reflected off a surface of the material and identifying a level of the material in the tank using the first return wireless signals. The method further includes receiving second return wireless signals reflected off a bottom of the tank and determining whether the material has been adulterated using the level of the material in the tank and the second return wireless signals. Determining whether the material has been adulterated could include determining a dielectric constant of the material, determining a density of the material using the dielectric constant of the material, and comparing the determined density of the material against a specified density. Determining the dielectric constant of the material could include using a time between peaks associated with the first and second return wireless signals.

Abstract: A computer implemented method of communicating includes receiving systematic group codes representative of one or more messages. A Tanner graph is used to decode such systematic group codes. A method of forming a communication decoder includes obtaining a dual code for a systematic group code, obtaining a Tanner graph from the dual code, and reducing vertex complexity of the Tanner graph to provide a decoding Tanner graph for the communication decoder.

Abstract: A receiver includes a channel providing information received from wireless communications, including information from a selected user. A minimum mean square error combiner is coupled to the channel for receiving samples in a symbol duration and minimizes mean square error in such samples. The combiner has coefficients derived from a training sequence. Information of the selected user is extracted from a mixture consisting of information from unintended users, interference and noise.

Abstract: A method and system are used for constructing a minimal BCJR trellis for a block group code. A parity check matrix of a block group code is obtained, as is a generator matrix of the block group code. A root vertex is determined at a first time. Syndromes of the parity check matrix are determined at further times to determine distinct vertices at such further times until a null vector is encountered to obtain a minimal BCJR trellis for the block group code for storing or use in decoding received codes.

Abstract: A method and system constructs a minimal trellis for decoding a block group code. A generator matrix of the code is obtained and converted into a row-reduced echelon matrix form. Vertices are determined from the row-reduced echelon matrix form at a first time. Further vertices at later times are also determined to obtain a minimal trellis for the block group code C for storing or use in decoding received codes.