3763 results about "Feature set" patented technology

A system and method for detecting malware by modeling the behavior of malware and comparing a suspect executable with the model. The system and method extracts feature elements from malware-infected applications, groups the feature elements into feature sets, and develops rules describing a malicious probability relationship between the feature elements. Using malware-free and malware-infected applications as training data, the system and method heuristically trains the rules and creates a probability model for identifying malware. To detect malware, the system and method scans the suspect executable for feature sets and applies the results to the probability model to determine the probability that the suspect executable is malware-infected.

A system and method for detecting malware on a limited access mobile platform in a mobile network. The system and method uses one or more feature sets that describe various non-executable portions of malware-infected and malware-free applications, and compares a application on the limited access mobile platform to the features sets. A match of the features in a suspect application to one of the feature sets provides an indication as to whether the suspect application is malware-infected or malware-free.

Systems and methods are disclosed herein to allow a service provider supporting applications running on a client device to remotely disable the applications, features of the applications, or sessions of the applications running on the client device. The service providers may initiate the disable action automatically upon the detection of certain events on or through the client device without requiring user input. The disable action is specific for the client device. In one embodiment, the service provider collects information associated with the application and with the remote client device that runs the application to conduct one or more transactions with the service provider. The service provider determines from the collected information a feature set of the application to disable on the client device. The service provider disabling remotely the feature set of the application on the client device without affecting any other client devices that run the application.

The invention provides systems and methods for detection, grading, scoring and tele-screening of cancerous lesions. A complete scheme for automated quantitative analysis and assessment of human and animal tissue images of several types of cancers is presented. Various aspects of the invention are directed to the detection, grading, prediction and staging of prostate cancer on serial sections/slides of prostate core images, or biopsy images. Accordingly, the invention includes a variety of sub-systems, which could be used separately or in conjunction to automatically grade cancerous regions. Each system utilizes a different approach with a different feature set. For instance, in the quantitative analysis, textural-based and morphology-based features may be extracted at image- and (or) object-levels from regions of interest. Additionally, the invention provides sub-systems and methods for accurate detection and mapping of disease in whole slide digitized images by extracting new features through integration of one or more of the above-mentioned classification systems. The invention also addresses the modeling, qualitative analysis and assessment of 3-D histopathology images which assist pathologists in visualization, evaluation and diagnosis of diseased tissue. Moreover, the invention includes systems and methods for the development of a tele-screening system in which the proposed computer-aided diagnosis (CAD) systems. In some embodiments, novel methods for image analysis (including edge detection, color mapping characterization and others) are provided for use prior to feature extraction in the proposed CAD systems.

A method and apparatus for forecasting and controlling neurological abnormalities in humans such as seizures or other brain disturbances. The system is based on a multi-level control strategy. Using as inputs one or more types of physiological measures such as brain electrical, chemical or magnetic activity, heart rate, pupil dilation, eye movement, temperature, chemical concentration of certain substances, a feature set is selected off-line from a pre-programmed feature library contained in a high level controller within a supervisory control architecture. This high level controller stores the feature library within a notebook or external PC. The supervisory control also contains a knowledge base that is continuously updated at discrete steps with the feedback information coming from an implantable device where the selected feature set (feature vector) is implemented. This high level controller also establishes the initial system settings (off-line) and subsequent settings (on-line) or tunings through an outer control loop by an intelligent procedure that incorporates knowledge as it arises. The subsequent adaptive settings for the system are determined in conjunction with a low-level controller that resides within the implantable device. The device has the capabilities of forecasting brain disturbances, controlling the disturbances, or both. Forecasting is achieved by indicating the probability of an oncoming seizure within one or more time frames, which is accomplished through an inner-loop control law and a feedback necessary to prevent or control the neurological event by either electrical, chemical, cognitive, sensory, and/or magnetic stimulation.

A 1D-CNN-based ((one-dimensional convolutional neural network)-based) distributed optical fiber sensing signal feature learning and classification method is provided, which solves a problem that an existing distributed optical fiber sensing system has poor adaptive ability to a complex and changing environment and consumes time and effort due to adoption of manually extracted distinguishable event features, The method includes steps of: segmenting time sequences of distributed optical fiber sensing acoustic and vibration signals acquired at all spatial points, and building a typical event signal dataset; constructing a 1D-CNN model, conducting iterative update training of the network through typical event signals in a training dataset to obtain optimal network parameters, and learning and extracting 1D-CNN distinguishable features of different types of events through an optimal network to obtain typical event signal feature sets; and after training different types of classifiers through the typical event signal feature sets, screening out an optimal classifier.

A system and method for performing a VM migration which manages a cluster of machines in a pool for live migration to the same feature set or behavior. In certain embodiments, machines within the pool can be configured to emulate a certain feature set to enable a VM migration amongst the similar pools. The emulation can be by either masking reporting of a feature set or enabling/disabling a feature set. The handling of emulation registers within the hardware occurs at a firmware level rather than an operating system or hypervisor level.

A method, apparatus and computer program product are provided for visually searching feature sets that are organized in a grid-like manner. As such, a feature set associated with a location-based grid area may be received. The location-based grid area may also be associated with the location of a device. After receiving query image features, a visual search may be performed by comparing the query image features with the feature set. The search results are then returned. By conducting the visual search within a feature set that is selected based upon the location of the device, the efficiency of the search can be enhanced and the search may potentially be performed by the device, such as a mobile device, itself.

A run-time feature set of a process or a thread is generated and compared to at least one processor feature set. Each processor feature set represents zero or more optional hardware features supported by one or more processors, whereas the run-time feature set represents zero or more optional hardware features the process or thread relies upon. The comparison of the feature sets determines whether a particular process or thread may run on a particular processor, even in a heterogeneous processor environment. A system task dispatcher assigns the process or thread to execute on one or more processors indicated by the comparison as being compatible with the process or thread. When a new feature is added to the process or thread, the run-time feature set is updated and again compared to at least one processor feature set. The system task dispatcher reassigns the process or thread if necessary.

An exemplary method includes a remote control emulation system directing a mobile device to display an emulation graphical user interface (“GUI”) on a display screen of the mobile device and directing the mobile device to emulate one or more user input devices by selectively positioning one or more interactive graphical depictions of one or more feature sets associated with the one or more user input devices within the emulation GUI. Corresponding methods and systems are also disclosed.

A method of extracting features characterising objects consists in discriminating an object from a context, the discriminating step comprising, determining the context consisting of at least two objects, choosing a topic object from the context, deriving feature sets of the topic object and the other objects in the context, judging whether there is at least one distinctive feature set in the feature sets, deriving a new feature set if there is not a distinctive feature set amongst the feature sets, and registering one of the distinctive feature sets as an outcome; and restarting the discriminating step when there exists an object which is not discriminated from the other objects. This method represents a selectionist approach to the characterisation of objects, driven by a discrimination task. There is also an apparatus putting this method into practice and a system for autonomous development of a common vocabulary by a plurality of agents incorporating the method and/or apparatus.

The invention relates to a method and apparatus for generating noise-attenuated feature vectors for use in recognizing speech, more particularly to a system and method providing a feature set for speech recognition that is robust to adverse noise conditions. This is done by receiving, through an input, a set of signal frames, at least some containing speech sounds, and then classifying the frames in the set of signal frames into classification groups on the basis of their energy levels. Each classification group is characterized by a mean energy value. In a specific example of implementation, the invention makes use of channel energy values to condition the frames in the set of signal frames. The frames in the set of signal frames are attenuated or noise reduced by altering the energy of the frames on the basis of the frames containing non-speech sounds. In a specific example of implementation, the invention compresses the energy of the frames in the set of signal frames such that the energy lies within a range. The invention also allows separate energy ranges to be defined for each channel.

The invention discloses a hybrid machine learning credit scoring model building method. The method comprises the steps of 1, determining client risk classification standards based on a loan client historical data set; 2, based on the loan client historical data set, obtaining a loan client data feature set through feature extraction; 3, selecting at least two model algorithms from an alternative model library, building corresponding models based on the selected algorithms, performing model performance check on the built models by adopting a K-fold cross check method, performing standard check on the models about to pass the model performance check based on model check standards, obtaining evaluation index statistical quantity values, and selecting a model type used by final modeling according to the evaluation index statistical quantity values returned by the standard check of the models; and 4, based on the algorithm corresponding to the selected model type, building a credit scoring model. The technical effect of efficiently and accurately finishing user credit evaluation through the built hybrid machine learning credit scoring model is achieved.

A method, system, and apparatus for informing a plurality of operating systems, each assigned to a separate partition within a logically partitioned data processing system, of which functions, provided by a hypervisor for creating and enforcing separation of the logical partitions, are available for use by the operating systems is provided. In a preferred embodiment, the hypervisor includes a plurality of function sets. Each function set includes a list of functions that may be called by any one of the operating systems to perform tasks for the operating systems while maintaining separation between each of the logical partitions. The hypervisor informs each of the plurality of operating systems of an enabled function set. Functions identified within the enabled function set are enabled for use by each of the plurality of operating systems and functions not identified within the enabled function set are disabled for use by each of the plurality of operating systems.

The invention provides a universal machine learning data analysis platform. The universal machine learning data analysis platform comprises an interface module, a data storage module, a preprocessing module, a feature extraction module, a feature conversion module, an algorithm module and a selection optimization module, wherein the feature extraction module extracts feature parameters from to-be-analyzed data according to the feature parameters set by a user; the feature conversion module is used for converting features set by the user to be in a representation form required by the user; the algorithm module comprises a plurality of algorithm models for the user to select and build, and the user builds at least one group of models; the selection optimization module selects out an optimal model and an optimal parameter from the built models and then stores the optimal model; and data generated by the modules is stored in the data storage module. According to the platform, the user can freely combine and use the modules and the algorithm models, and also can build a complex model and quickly and iteratively develop a novel analytic model, so that the working efficiency is greatly improved.

The embodiment of the invention provides a multi-target tracking method and system based on depth features. The method comprises the following steps: obtaining detection frame positions correspondingto targets detected in a current frame image and the depth features of the targets; based on the position of the detection frame corresponding to each target in the previous frame of image, obtainingthe prediction position of each target in the current frame by using a Kalman filter; according to the detection frame position corresponding to each target, the prediction position of each target inthe current frame, the depth feature of each target and the depth feature set of each tracker, performing cascade matching on the detection frame corresponding to each target and the tracker by usinga Hungarian algorithm; And calculating an IOU distance matrix between the detection frame on the non-cascade matching and the tracker to be matched, and performing IOU matching between the detection frame and the tracker by using a Hungarian algorithm based on the IOU distance matrix to obtain a final matching set. According to the embodiment of the invention, the target tracking effect under theshielding condition can be effectively improved, and the number of times of ID switching is reduced.

A translator, system, and method of translation is provided for translating a source file in a source format to a target file in a target format. A feature identifier determines a feature set of the source file, and a feature writer writes the feature set into the target file in the target format. Optionally, the feature identifier may include a front-end lookup table to map code fragments of the source file to a list of features. The feature writer may include a back-end lookup table to map the feature set to code fragments of the target file format.

Systems and methods for threat detection in a network are provided. The system obtains recoils for entities that access a network. The records include attributes associated with the entities. The system identifies features for each of the entities based on the attributes. The system generates a feature set for each of the entities. The feature set is generated from the features identified based on the attributes of each of the entities. The system forms clusters of entities based on the feature set for each of the entities. The system classifies each of the clusters with a threat severity score calculated based on scores associated with entities forming each of the clusters. The system determines to generate an alert for an entity in a cluster response to the threat severity score of the cluster being greater than a threshold.

This invention provides a system and method for capturing, detecting and extracting features of an ID, such as a 1D barcode, that employs an efficient processing system based upon a CPU-controlled vision system on a chip (VSoC) architecture, which illustratively provides a linear array processor (LAP) constructed with a single instruction multiple data (SIMD) architecture in which each pixel of the rows of the pixel array are directed to individual processors in a similarly wide array. The pixel data are processed in a front end (FE) process that performs rough finding and tracking of regions of interest (ROIs) that potentially contain ID-like features. The ROI-finding process occurs in two parts so as to optimize the efficiency of the LAP in neighborhood operations—a row-processing step that occurs during image pixel readout from the pixel array and an image-processing step that occurs typically after readout occurs. The relative motion of the ID-containing ROI with respect to the pixel array is tracked and predicted. An optional back end (BE) process employs the predicted ROI to perform feature-extraction after image capture. The feature extraction derives candidate ID features that are verified by a verification step that confirms the ID, creates a refined ROI, angle of orientation and feature set. These are transmitted to a decoding processor or other device.