Abstract: Provided is a method for calculating an evaluation score of clustering quality, based on the number of clusters into which a plurality of data is clustered. The calculating the evaluation score includes: calculating a degree of internal compactness that is a sum of values, each being defined by normalizing a first index value by a first value that is based on a number of data within each cluster, the first index value indicating a degree of dispersion of data within each cluster; calculating a degree of external separation defined by normalizing a sum of a second index value for each cluster by a second value that is based on the number of clusters, the second index value indicating an index of a distance between the clusters; and calculating the evaluation score according to a predetermined formula having, as variables, the degree of internal compactness and the degree of external separation.

Abstract: A radio node may transmit a signal using a transmit power. Then, the radio node may adjust the transmit power within a range of values. The adjustment may include reducing the transmit power when a spatial received signal strength indication (RSSI) metric of the radio node is greater than a first threshold value and a coverage criterion is met. Note that the spatial RSSI metric of the radio node may correspond to a set of temporal RSSI metrics of the radio node received from neighboring radio nodes. Moreover, the coverage criterion may be that less than a portion of RSSI measurements of the radio node associated with electronic devices, which are communicatively attached with the radio node, is less than a second threshold value. Alternatively, the adjustment may include increasing the transmit power when the spatial RSSI metric is less than the first threshold value.

Abstract: In various examples, systems and methods are disclosed that preserve rich spatial information from an input resolution of a machine learning model to regress on lines in an input image. The machine learning model may be trained to predict, in deployment, distances for each pixel of the input image at an input resolution to a line pixel determined to correspond to a line in the input image. The machine learning model may further be trained to predict angles and label classes of the line. An embedding algorithm may be used to train the machine learning model to predict clusters of line pixels that each correspond to a respective line in the input image. In deployment, the predictions of the machine learning model may be used as an aid for understanding the surrounding environment—e.g., for updating a world model—in a variety of autonomous machine applications.

Abstract: Methods, systems, and apparatus for controlling smart devices are described. In one aspect a method includes capturing, by a camera on a user device, a plurality of successive images for display in an application environment of an application executing on the user device, performing an object recognition process on the images, the object recognition process including determining that a plurality of images, each depicting a particular object, are required to perform object recognition on the particular object, and in response to the determination, generating a user interface element that indicates a camera operation to be performed, the camera option capturing two or more images, determining that a user, in response to the user interface element, has caused the indicated camera operation to be performed to capture the two or more images, and in response, determining whether a particular object is positively identified from the plurality of images.

Abstract: Disclosed herein are methods and systems that apply a multi-layer Hidden Markov Model (HMM) for intrusion detection. The methods and systems employ a dimension reduction technique to extract only important features from network packet data and apply a decomposition algorithm to lower levels of data to construct lower level HMMs (representing partial solutions), which lower level HMMs are then combined to form a final, global solution. The multi-layer approach can be expanded beyond the exemplary case of 2 layers in order to capture multi-phase attacks over longer spans of time. A pyramid of HMMs can resolve disparate digital events and signatures across protocols and platforms to actionable information where lower layers identify discrete events (such as network scan) and higher layers identify new states which are the result of multi-phase events of the lower layers.

Abstract: A method according to an aspect of the present disclosure includes combining pieces of first feature data and pieces of second feature data. Each of the pieces of first feature data is associated with first identification information related to a corresponding one or more of first constituents included in a first group and indicates a feature of the corresponding one or more of the first constituents. Each of the pieces of the second feature data corresponds to one of clusters in the second group. The second feature data includes statistic data associated with second identification information related to two or more of the second constituents included in a corresponding cluster. The statistic data has a statistic indicating a feature of two or more of the second constituents included in the corresponding cluster. The combining is performed based on the first identification information and the second identification information.

Abstract: Provided are an object detection system and an object detection method. An object detection system may include a feature map extraction module configured to receive an image for object detection and extract a feature map having multiple resolutions for the image; a bounding box detection module configured to classify a bounding box by applying a first group of convolutional layers to the feature map, and predict the bounding box by applying a second group of convolutional layers to the feature map; and a mask generation module configured to generate a mask for the shape of the object in the bounding box using the feature map.

Abstract: This disclosure relates to method and system for detecting and tracking at least one object in a rotational environment. The method includes receiving a set of first features based on first data and a set of second features based on second data, detecting at least one object based on the set of first features using a Convolutional Neural Network (CNN) based predictive model, determining a set of first parameters for the at least one object, detecting the at least one object based on the set of second features using the CNN based predictive model, determining a set of second parameters for the at least one object, and tracking the at least one object based on the set of first parameters and the set of second parameters. It should be noted that the first data and the second data sequentially belong to an input dataset that includes images or video frames.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to collect a plurality of data sets, each data set from a respective sensor in a plurality of sensors, and each data set including a range, an azimuth angle, and a range rate for a detection point of the respective one of the sensors on an object to determine, for each detection point, a radial component of a ground speed of the detection point based on the data set associated with the detection point and a speed of a vehicle, and to generate a plurality of clusters, each cluster including selected detection points within a distance threshold from each other and having respective radial components of ground speeds that are (1) above a first threshold and (2) within a second threshold of each other.

Abstract: Aspects of the disclosed technology provide ways to detect the object of ultrasound scanning and to automatically, load system settings and image preferences necessary to generate high quality output images. In some aspects, an ultrasound system can be configured to perform steps including receiving a selection of a first transducer, identifying a body structure or organ based on a signal received in response to an activation of the first transducer, retrieving a first set of image parameters corresponding with the body structure, and configuring the first transducer based on the first set of image parameters. Methods and machine-readable media are also provided.

Abstract: In another aspect, a system for machine learning using a distributed framework, includes a computing device communicatively connected to a plurality of remote devices, the computing device designed and configured to select at least a remote device of a plurality of remote devices, determine a confidence level of the at least a remote device, and assign at least a machine-learning task to the at least a remote device, wherein assigning further comprises assigning at least a secure data storage task to the at least a remote device and assigning at least a model-generation task to the at least a remote device.

Abstract: A method and an apparatus optimizes scan data obtained by sensors on vehicle, and corrects trajectory for a vehicle/robot based on the optimized scan data.

Abstract: A method and apparatus are provided that analyzing sequence-to-sequence data, such as sequence-to-sequence speech data or sequence-to-sequence machine translation data for example, by minimum Bayes risk (MBR) training a sequence-to-sequence model and within introduction of applications of softmax smoothing to an N-best generation of the MBR training of the sequence-to-sequence model.

Abstract: A control apparatus configured to allow a communication device supporting a first frequency setting to enter a system providing a communications facility based on a second frequency setting, wherein the first frequency setting provides only a partial support for communications in the system is disclosed. The control apparatus may be co-operative with a second control apparatus. The second control apparatus is configured to determine based on frequency setting information received from the system if it is possible to transmit to the system based on the first frequency setting supported by the communication device.

Abstract: A system and method for locating radio-frequency identification tags within a predetermined area. The method can incorporate sub-threshold superposition response mapping techniques, alone, or in combination with other methods for locating radio-frequency identification tags such as but not limited to time differential on arrival (TDOA), frequency domain phase difference on arrival (FD-PDOA), and radio signal strength indication (RSSI). The system can include a plurality of antennas dispersed in a predefined area; one or more radio-frequency identification tags; a radio-frequency transceiver in communication with said antennas; a phase modulator coupled to the radio-frequency transceiver; and a system controller in communication with said transceiver and said phase modulator. Calibration techniques can be employed to map constructive interference zones for improved accuracy.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for finding lost objects. In some implementations, a request for a location of an item is obtained. Current video data from one or more cameras is obtained. It is determined that the item is not shown in the current video data. Sensor data corresponding to historical video data is obtained. Events that likely occurred with the item and corresponding likelihoods for each of the events are determined. A likely location for the item is determined based on the likelihoods determined for the events. An indication of the likely location of the item is provided.

Abstract: In one embodiment, an apparatus comprises a storage device and a processor. The storage device may store a plurality of compressed images comprising one or more compressed master images and one or more compressed slave images.

Abstract: An information processing method in which an object of interest is classified using node group information defining a node group having modeled a scheme of classification as a tree structure and having grouped nodes possessing a same parent node, comprises: setting depth information for determining whether to perform classification for a particular node group when sequentially traversing node groups from the parent node using the node group information to classify the object of interest; and classifying the object of interest by sequentially traversing node groups from the parent node using the node group information, and providing a classification result, wherein classifying the object of interest varies a depth up to which node groups are sequentially traversed from the parent node to classify the object of interest, in accordance with setting of the depth information.

Abstract: Systems and methods for video object segmentation are described. Embodiments of systems and methods may receive a referral expression and a video comprising a plurality of image frames, generate a first image mask based on the referral expression and a first image frame of the plurality of image frames, generate a second image mask based on the referral expression, the first image frame, the first image mask, and a second image frame of the plurality of image frames, and generate annotation information for the video including the first image mask overlaid on the first image frame and the second image mask overlaid on the second image frame.

Abstract: Herein is a probabilistic indexing technique for searching semi-structured text documents in columnar storage formats such as Parquet, using columnar input/output (I/O) avoidance, and needing minimal storage overhead. In an embodiment, a computer associates columns with text strings that occur in semi-structured documents. Text words that occur in the text strings are detected. Respectively for each text word, a bitmap, of a plurality of bitmaps, that contains a respective bit for each column is generated. Based on at least one of the bitmaps, some of the columns or some of the semi-structured documents are accessed.