Abstract: A mechanism is described for facilitating portable, reusable, and shareable Internet of Things-based services and resources according to one embodiment. A method of embodiments, as described herein, includes wherein receiving a recipe request for selecting a recipe relating to Internet of Things (IoT) services, where selecting includes at least one of searching the recipe and modifying the recipe. The method may further include selecting the recipe, where the recipe includes a set of resource requirements and business logic. The method may further include modifying the set of resource requirements, where the modified set of resource requirements is associated with the business logic to modify the recipe, and deploying the modified recipe at one or more computing devices, where the modified recipe to facilitate management for one or more IoT devices at one or more locations.

Abstract: An embodiment includes at least one computer readable storage medium comprising instructions that when executed enable a system to: receive (a)(i) first radio signal location data for a first object from a radio sensor; and (a)(ii) first visual signal location data for the first object from a camera sensor; perform feature extraction on (b)(i) the first radio signal location data to determine first extracted radio signal features; and (b)(ii) the first visual signal location data to determine first extracted visual signal features; solve a first association problem between the first extracted radio signal features and the first extracted visual signal features to determine first fused location data; and store the first fused location data in the at least one computer readable storage medium. Other embodiments are described herein.

Abstract: Techniques related to implementing distributed neural networks for data analytics are discussed. Such techniques may include generating sensor data at a device including a sensor, implementing one or more lower level convolutional neural network layers at the device, optionally implementing one or more additional lower level convolutional neural network layers at another device such as a gateway, and generating a neural network output label at a computing resource such as a cloud computing resource based on optionally implementing one or more additional lower level convolutional neural network layers and at least implementing a fully connected portion of the neural network.

Abstract: Classification techniques are disclosed that take into account the “cost” of each type of classification error for minimizing total cost of errors. In one example embodiment, a pre-trained cost-sensitive auto-encoder can be used in combination with a training (fine-tuning) stage for cost-sensitive deep learning. Thus, cost information is effectively combined with deep learning by modifying the objective function in the pre-training phase. By minimizing the modified objective function, the auto-encoder not only tries to capture underlying pattern, it further “learns” the cost information and “stores” it in the structure. By later fine-tuning at the training stage, the classification system yields improved performance (lower cost) than a typical classification system that does not take cost information into account during pre-training.

Abstract: In one embodiment, a method includes: presenting, in a user interface of an authoring tool, a plurality of levels of abstraction for a network having a plurality of devices; receiving information from a user regarding a subset of the plurality of devices to be provisioned with one or more security keys and an access control policy; automatically provisioning a key schedule for the subset of the plurality of devices in the network based on the user input and a topological context of the network; and automatically provisioning the access control policy for the subset of the plurality of devices in the network based on the user input and the topological context of the network.

Abstract: An adaptive video end-to-end network is described that uses local abstraction. One example includes an image sensor to generate a sequence of images, a processor coupled to the image sensor to analyze the sequence of images to detect an event, to select images related to the event and to generate metadata regarding the event, and a communications interface coupled to the processor to send the metadata information through a network connection to a central node.

Abstract: This disclosure describes systems, methods, and computer-readable media related to employing particle filter methods to estimate the location of a mobile device. The data may include wireless data measurement associated with the mobile device and one or more access points and inertial data associated with the mobile device. Radio fingerprinting data associated with the one or more access points may be retrieved. A respective location for the wireless data measurements may be determined based on the radio fingerprinting data and inertial data. A respective weight may be calculated for the respective location for each of the plurality of particles. A respective confidence level may be maintained for the respective location for each of the plurality of particles. A current location may be identified based on the respective location for each of the plurality of particles and the respective weight associated with the respective location for each of the particles.

Abstract: Disclosed herein are techniques to update a wireless fingerprint location database. According to such techniques, an update server updates a location database based on trajectories of a number of computing devices. The trajectories corresponding to sensor data collected by the computing devices, the sensor data including at least indication of RSSIs and inertial measurements. The RSSIs corresponding to wireless APs within an interior of a structure and represented in the location database.

Abstract: This document discloses one or more systems, apparatuses, methods, etc. for detecting precise indoor location of a portable wireless device based on a WiFi simultaneous localization and mapping (SLAM) algorithm that implements spatial and temporal coherence. In an implementation, a SLAM algorithm includes WiFi similarities and inertial navigational system (INS) measurements data as location estimates (i.e., references) for the spatial and temporal coherences implementations to constitute the WiFi SLAM algorithm.

Abstract: This disclosure describes systems, methods, and computer-readable media related to employing particle filter methods to estimate the location of a mobile device. The data may include wireless data measurement associated with the mobile device and one or more access points and inertial data associated with the mobile device. Radio fingerprinting data associated with the one or more access points may be retrieved. A respective location for the wireless data measurements may be determined based on the radio fingerprinting data and inertial data. A respective weight may be calculated for the respective location for each of the plurality of particles. A respective confidence level may be maintained for the respective location for each of the plurality of particles. A current location may be identified based on the respective location for each of the plurality of particles and the respective weight associated with the respective location for each of the particles.

Abstract: This document discloses one or more systems, apparatuses, methods, etc. for detecting precise indoor location of a portable wireless device based on a WiFi simultaneous localization and mapping (SLAM) algorithm that implements spatial and temporal coherence. In an implementation, a SLAM algorithm includes WiFi similarities and inertial navigational system (INS) measurements data as location estimates (i.e., references) for the spatial and temporal coherences implementations to constitute the WiFi SLAM algorithm.