Abstract: A computer-implemented method and a distributed computer system (100) for privacy-preserving distributed training of a global neural network model on distributed datasets (DS1 to DSn). The system has a plurality of data providers (DP1 to DPn) being communicatively coupled. Each data provider has a respective local training dataset (DS1 to DSn) and a vector of output labels (OL1 to OLn) for training the global model. Further, it has a portion of a cryptographic distributed secret key (SK1 to SKn) and a corresponding collective cryptographic public key (CPK) of a multiparty fully homomorphic encryption scheme, with the weights of the global model being encrypted with the collective public key. Each data provider (DP1) computes and aggregates, for each layer of the global model, encrypted local gradients (LG1) using the respective local training dataset (DS1) and output labels (OL1), with forward pass and backpropagation using stochastic gradient descent.

Abstract: A computer-implemented method and a distributed computer system (100) for privacy-preserving distributed training of a global model on distributed datasets (DS1 to DSn). The system has a plurality of data providers (DP1 to DPn) being communicatively coupled. Each data provider has a respective local model (LM1 to LMn) and a respective local training dataset (DS1 to DSn) for training the local model using an iterative training algorithm (IA). Further it has a portion of a cryptographic distributed secret key (SK1 to SKn) and a corresponding collective cryptographic public key (CPK) of a multiparty fully homomorphic encryption scheme, with the local and global model being encrypted with the collective public key. Each data provider (DP1) trains its local model (LM1) using the respective local training dataset (DS1) by executing gradient descent updates of its local model (LM1), and combining (1340) the updated local model (LM1?) with the current global model (GM) into a current local model (LM1c).

Abstract: Various aspects of this disclosure provide systems and methods for managing vehicle on-board diagnostic (OBD) data in a network of moving things. As non-limiting examples, various aspects of this disclosure provide systems and methods for interfacing with vehicle OBD systems, acquiring OBD data, communicating OBD data, and/or processing OBD data in a network of moving things, for example including OBD data of autonomous vehicles and other vehicles.

Abstract: Communication network architectures, systems and methods for supporting a network of mobile nodes. As a non-limiting example, various aspects of this disclosure provide communication network architectures, systems, and methods for providing context-aware and/or profile-based security in a dynamically configurable communication network comprising a complex array of both static and moving communication nodes (e.g., the Internet of moving things).

Abstract: A method of generating an output image having an output resolution of N pixels×N pixels, each pixel in the output image having a respective color value for each of a plurality of color channels, the method comprising: obtaining a low-resolution version of the output image; and upscaling the low-resolution version of the output image to generate the output image having the output resolution by repeatedly performing the following operations: obtaining a current version of the output image having a current K×K resolution; and processing the current version of the output image using a set of convolutional neural networks that are specific to the current resolution to generate an updated version of the output image having a 2K×2K resolution.

Abstract: A request from a mobile access point that is installed on a vehicle may be received via network interface circuitry of one or more computing devices. Processing circuitry of the one or more computing devices may determine characteristics of a captive portal to present in response to the request based on current location of the vehicle and mobile access point. A captive portal with the determined characteristics is then provided by the processing circuitry, via the network interface circuitry, in response to the request.

Abstract: Communication network architectures, systems and methods for supporting a network of mobile nodes. As a non-limiting example, various aspects of this disclosure provide communication network architectures, systems, and methods for providing context-aware and/or profile-based security in a dynamically configurable communication network comprising a complex array of both static and moving communication nodes (e.g., the Internet of moving things).

Abstract: Various aspects of this disclosure provide systems and methods for managing vehicle on-board diagnostic (OBD) data in a network of moving things. As non-limiting examples, various aspects of this disclosure provide systems and methods for interfacing with vehicle OBD systems, acquiring OBD data, communicating OBD data, and/or processing OBD data in a network of moving things, for example including OBD data of autonomous vehicles and other vehicles.

Abstract: A request from a mobile access point that is installed on a vehicle may be received via network interface circuitry of one or more computing devices. Processing circuitry of the one or more computing devices may determine characteristics of a captive portal to present in response to the request based on current location of the vehicle and mobile access point. A captive portal with the determined characteristics is then provided by the processing circuitry, via the network interface circuitry, in response to the request.

Abstract: A request from a mobile access point that is installed on a vehicle may be received via network interface circuitry of one or more computing devices. Processing circuitry of the one or more computing devices may determine characteristics of a captive portal to present in response to the request based on current location of the vehicle and mobile access point. A captive portal with the determined characteristics is then provided by the processing circuitry, via the network interface circuitry, in response to the request.

Abstract: A request from a mobile access point that is installed on a vehicle may be received via network interface circuitry of one or more computing devices. Processing circuitry of the one or more computing devices may determine characteristics of a captive portal to present in response to the request based on current location of the vehicle and mobile access point. A captive portal with the determined characteristics is then provided by the processing circuitry, via the network interface circuitry, in response to the request.

Abstract: A request from a mobile access point that is installed on a vehicle may be received via network interface circuitry of one or more computing devices. Processing circuitry of the one or more computing devices may determine characteristics of a captive portal to present in response to the request based on current location of the vehicle and mobile access point. A captive portal with the determined characteristics is then provided by the processing circuitry, via the network interface circuitry, in response to the request.

Abstract: The invention refers to a new keyboard based in a polymeric, copolymeric or composite film (11) with piezo- and pyroelectric properties capable of receiving a tactile signal and giving a respond in the form of an electrical signal. The system described in this invention includes one or more keys (10), being each one of them made by a piezoelectric film (11) with electric conductive contacts, transparent or not, above and below the piezoelectric film and with the inferior layer of grounded electrodes (13).

Abstract: The invention refers to a new keyboard based in a polymeric, copolymeric or composite film (11) with piezo- and pyroelectric properties capable of receiving a tactile signal and giving a respond in the form of an electrical signal. The system described in this invention includes one or more keys (10), being each one of them made by a piezoelectric film (11) with electric conductive contacts, transparent or not, above and below the piezoelectric film and with the inferior layer of grounded electrodes (13).

Abstract: The invention reports a new film of the beta phase of polyvinylidene fluoride (PVDF) and its processing for the elimination of porosity, using a compression force along the thickness direction of the sample at a high temperature. The join action of the compression force and the temperature eliminates the porosity of the PVDF beta phase, improving its mechanical (Young's modulus, yielding and breaking stress, yielding and breaking strain), electrical (dielectric constant, electric rupture) and electromechanical properties (electromechanical coupling, piezoelectric coefficients) and, therefore, the use of the material in technological applications.

Abstract: An apparatus and method for drying reconstituted tobacco sheets includes positioning a steam box below an endless conveyor belt. A slurry is cast onto the conveyor belt and conveyed over a steam box before entry into a drying apparatus. The steam box functions to pre-treat the slurry so as to increase the rate by which the slurry may be dried. The steam box includes the use of a perforated plate which encloses an upper portion of the steam box and which functions to uniformly distribute steam to the underside of the conveyor belt.