84 results about "Activity classification" patented technology

Activities, actions and events during user performance of physical activity may be detected using various algorithms and templates. Templates may include an arrangement of one or more states that may identify particular event types and timing between events. Templates may be specific to a particular type of activity (e.g., types of sports, drills, events, etc.), user, terrain, time of day and the like.

The invention relates to a system and method that can detect botnets by classifying the communication activities for each client according to destination or based on similarity between the groups of collected traffic. According to certain aspects of the invention, the communication activities for each client can be classified to model network activity by differentiating the protocols of the collected network traffic based on destination and patterning the subgroups for the respective protocols. Those servers that are estimated to be C&C servers can be classified into download and upload, spam servers and command control servers, within a botnet group detected by modeling network activity, i.e. analyzing network-based activity patterns. Also, botnet groups can be detected by way of a group information management function, for generating an activity pattern-based group matrix based on group data, and a mutual similarity analysis, performed on groups suspected to be botnets from the group information.

A system and method for processing motion-related sensor data for health application examines motion-related signal from a motion sensor located on a subject on a frame-by-frame basis to detect physical activities performed by the subject. For each frame, a detected activity is classified into a category of activities and performance parameters of the detected activity are estimated.

An activity classification device is disclosed. The activity classification device comprises one or more motion sensors and a memory configured to receive signals from the one or more motion sensors. The device further includes a processor in communication with the memory. Finally, the device includes a classification algorithm executed by the processor, the classification algorithm for identifying activities that a user is engaged in. The memory may also record a user's activity log, calorie count and an RF module, which transmits the recorded data to a host either upon request or continuously.

Apparatus and method for refining subject activity classification for the recognition of daily activities of a subject, and a system for recognizing daily activities using the same. The refining apparatus improves the correctness of subject activity classification using daily activities of a subject, activation time information of sensors mounted on objects associated with the daily activities of the subject, and the suitability of a continuous activity pattern in relation to the daily activities. This improves the correctness of subject activity classification that becomes basic information in daily activity analysis.

In a user-activity identification technique, a user's actions are monitored while the user is using a computer. While these user actions are associated with user activities, the user activities are initially unspecified, so the tracked user actions constitute unsupervised data. Then, the tracked user actions are aggregated into subsets (for example, using clustering analysis), and user-activity classifications for the subsets (such as activity labels) are provided by the user, so the subsets constitute supervised data. Subsequently, when additional user actions (which are associated with one or more initially unspecified current user activities) are tracked, they can be associated with one or more of the classified subsets. For example, information about the additional user actions can be mapped in real time (or near real time) to one or more of the subsets using a supervised learning technique. In this way, the one or more current user activities can be identified.

A method implemented in a system which comprises a lightweight personal wearable monitoring device, supplied by a battery, comprising an accelerometer, a processing unit, a display, a remote server, said method comprising the steps: / a / collecting, from a plurality of individuals caused to practice various physical activities from a set of predefined activities, acceleration data from sensing devices placed on each of said individuals, / b / defining N small data-size specific metrics, computed from acceleration signals, which allow to define a global activity classifier, / c / acquiring, at a first monitoring device worn by a first user, acceleration signals from the accelerometer of the first monitoring device, / d / calculating, at the first monitoring device, over each lapsed time unit T1, specific metrics values from the sensed signals, to form a series of specific metrics values, / e / send them to the processing unit, / f / allocate an activity type for each time unit together with corresponding specific metrics values of the received series, to form a time chart of activity types presumably performed by the first user over a second period T2, / g / display the time chart of activity types presumably performed by the first user on the display and allow the first user to confirm or correct partly the type of activity performed over the second period, and allow correction by the first user.

A system and method for providing multi-floor activity classification for a mobile device within a multi-floor environment includes an activity recognition module receiving inertial readings and pressure readings from the mobile device. The activity recognition module classifies activities for the mobile device from the inertial readings and the pressure readings.

The invention provides a method of analysing a sporting activity comprising receiving location data associated to a first player; receiving location data associated to a game object; receiving location data associated to a second player; determining a relative location of the first player in (5) relation to the game object location and the second player location, at least partly from the received location data associated to the first player, the game object and / or the second player; comparing the determined relative location of the first player with a set of reference relative locations of the first player; and determining a match between the determined relative location of the first player and at least one reference relative location of the first player. Other aspects of the (10) invention provide a classification system.

Aspects of the present disclosure provide techniques for displaying reduced data sets based on pre-classification of a larger data set. Embodiments include receiving a plurality of activity records describing a plurality of activities associated with the user. Embodiments further include grouping the plurality of activities into one or more pre-classified data sets based on the plurality of activity records. Embodiments further include providing the user with a summary of a pre-classified data set of the one or more pre-classified data sets via a user interface. Embodiments further include providing the user, via the user interface, with a user interface element that allows the user to categorize all activities in the pre-classified data set together based on the summary. Embodiments further include receiving input from the user via the user interface, the input assigning a category to all activities in the pre-classified data set together based on the summary.

The invention relates to a human body tumble identification method based on WIFI CSI dynamic subcarrier selection in a WiFi interference environment, and belongs to the technical field of wireless communication. The method comprises the following steps: firstly, analyzing CSI interference intensity and a CSI active ratio, constructing a WiFi interference characteristic mapping matrix, and calculating each channel interference index by using the matrix to realize interference discrimination; and then, through a dynamic subcarrier selection algorithm CSI-DSSA based on an interference index, selecting a subcarrier combination with the weakest cross correlation in the interference data to carry out interference processing, and analyzing time domain feature information of multiple data streamsin uninterfered data aggregated by a multi-link data fusion method CSI-MLDF; and finally, extracting a time domain characteristic value and constructing an SVM multi-activity classification model in aWiFi interference environment to obtain a tumble activity identification result. According to the invention, the human body tumble activity identification accuracy in the WiFi interference environment can be effectively improved.

A method and system to control an interaction of a plurality of participants in a workflow process. The method classifies the plurality of activities as (1) first activity of the workflow process, (2) first activity of a participant in an on-going workflow process, and (3) interaction activity. A set of access control policies is generated for each type of activity. The policies include workflow initialization policy, participation policy and interaction policies. The policies determine if a requesting participant is permitted to interact with a responding participant. In addition, the system includes a policy enforcement point for receiving a request from a requesting participant, wherein the request is for activating an activity of a responding participant. The policy enforcement point forwards the request to a policy decision point where the request is evaluated based on the set of access control policies.

A device worn by a human performing a method using accelerometer data to classify human activities is disclosed. The method uses memory and computation efficiently. A stream of samples is divided into a sequence of sampling periods; each sample has an acceleration value for each axis (e.g., a 3-D accelerometer). Standard deviation of the values for each axis during each sampling period are calculated. A running sum of each axis' values can be maintained sample-by-sample. Each value is sorted into a bin of a histogram, by quantifying a deviance from a respective mean in standard deviations. A standard deviation produced from samples of a previous period can be used. The histogram is compared with histograms associated with particular activities and a classification output can be produced. Classification outputs from multiple sampling periods can be used for voting. A threshold amount of activity can be required to begin activity classification.

A system and method for predictive categorization of risk of at least one project related activity is provided. The system and method provide categorization of the project related activity into one of a plurality of predetermined risk categories. Further, the risk category of the project related activity is predicted in at least one stage of the project life cycle. The method comprises collecting inputs pertaining to the project related activity being categorized and a predetermined set of details for categorizing the project related activity. The method further comprises categorizing the project related activity by applying discriminant analysis. The application of discriminant analysis comprises constructing a set of functions based on the predetermined set of details. Thereafter, the constructed set of functions are applied on the details collected pertaining to the project related activity, wherein the functions are applied for predicting the risk category of the project related activity.

System and methods are provided for predicting occupancy of a parking area. A request is received for data relating to occupancy of the parking area. One or more entities within a first predefined distance of the first parking area are identified. Activity classification codes for each of the one or more entities are identified. A predicted occupancy for the parking area is calculated as a function of the activity classification codes. The predicted occupancy for the parking area is transmitted.

The relates to a user activity type judgment method based on smart device data, comprising the following steps of obtaining the smart device data of a user; carrying out data cleaning to obtain moving tracks of the user and obtaining trip links of the user through travel identification; extracting activity start time and activity duration time and obtaining land usage corresponding to staying sections according to points of interest in the staying sections; analyzing the smart device data of trips of the user within a few days and judging a position of a user home and / or a workplace, thereby obtaining two activity types: being at home and being at work; and for other types of activities except being at home and being at work, inputting activity features into an activity classifier, thereby obtaining corresponding activity types. According to the method, the activity types of the user can be analyzed according to the smart device data of the user, a time threshold or a space threshold involved in an analysis process is calibrated according to traditional user trip survey data, and the method has usability, accuracy and timeliness.

A kit, and method of using the kit, for use by persons having brain function deficit, and by persons helping the affected person, to plan, organize, and manage the tasks of daily life to promote the independence of the affected person's lifestyle. A daily planner book is used in combination with a color-coded system of adhesive stickers, writing instruments, and note papers to classify the affected person's activities into one ore more designated categories of life tasks. By assigning life tasks to discrete categories and implementing a system of color-coded reminders, the affected person with the assistance of a friend organizes, plans, and executes his daily activities in an orderly manner, with emphasis on accepting the person's affected condition, supporting the affected person, and fostering conduct (such as adequate rest) to optimize potential recovery. Mnemonic components are supplied with the kit to assist the affected person in remembering tasks of high importance needing immediate attention. Educational books, workbooks, and videotapes of digital video disks provide instruction and support to the users of the kit.

Components, methods, and apparatuses are provided that may be used to determining activity likelihood function values for the activity classification for two or more past epochs based, at least in part, on signals from one or more sensors of a mobile device. For example, a method may comprise, for each of a plurality of activity classifications, determining activity likelihood function values for each of the plurality of activity classifications for two or more past epochs. The activity likelihood function values are based, at least in part, on signals from one or more sensors of a mobile device. The method may also include combining the activity likelihood function values to determine a likelihood function for an activity classification at a present epoch. The method may also include inferring a present activity of a user co-located with the mobile device to be one of the activity classifications based, at least in part, on the determined likelihood functions for the activity classifications at the present epoch.

A method of identifying the activity of a camera used for capturing an image or video, such activity not being related to the activity of subjects of the scene being captured includes determining a steadiness signal related to movement of the camera while capturing an image or video, wherein the steadiness signal identifies the motion of the camera in at least two dimensions as a function of time; and using a processor for determining a camera activity classification for the camera based on an analysis of the steadiness signal, wherein the camera activity classification includes categories of the camera being stationary, the camera being located in a moving vehicle, the camera being held by hand, or the camera being held by a jogging or walking user.

The invention relates to an automatic economic activities classification device in organizing institution bar codes. The device comprises the following modules: (1) a classification rule maintenance module which mainly comprises the operation steps of establishing a storage class characteristic word set, an industry category system and an industry system, forming a digital standard classification system and performing category management, dictionary management and subject and normal form management; (2) a small text classification module comprising the operation steps of testing training corpus and comparing and analyzing to obtain a small text reference model; (3) a word list establishment module comprising the operation steps of abstracting the basic relation information in a narrower range, relation properties and relation association by analyzing the relation between words, and establishing and describing the relation between words by virtue of an assembly mode; and (4) an intelligent retrieval module comprising the operation steps of performing semantics decomposition on inquired statements, analyzing various kinds of fuzzy input, mapping the prepared classification module, analyzing the possible multiple classification modes and user behaviors and finally obtaining the possibility of each category so as to be recommended to the user.

The embodiment of the invention discloses a service prediction method and system and a computer storage medium. The method comprises the steps of training to obtain a place classification model through training, and determining a place set of terminal users; training to obtain an activity classification model and determining an activity set of the terminal user; training based on the activity set,the place set and the historical detailed list data to obtain a business prediction model; when the real-time detailed list data and the real-time terminal state data corresponding to the terminal user at the current moment are obtained, determining the activity of the next moment based on the real-time terminal state data and the activity classification model, and determining the place of the next moment based on the real-time detailed list data and the place classification model; and obtaining the business type of the next moment based on the real-time detailed list data, the activity of the next moment, the place of the next moment and the business prediction model.

Device-based activity classification using predictive feature analysis is described, including receiving a signal from a sensor coupled to a device, the sensor being configured to sense the signal over a time period, evaluating the signal to generate data, the data being further evaluated to select a classifier, invoking the classifier, the classifier being configured to evaluate a predictive feature, the predictive feature invoking an application configured to determine a state using a feature interpreter, and processing the data using the application and the feature interpreter to generate information associated with a biological state, the information being configured to display on an interface associated with the device.

Various examples are described for using a movement sensor to detecting an activity of an infant. In an example, an activity classification system includes a sensor configured to measure the activity of an infant and an external monitor. The monitor receives, from a sensor, a time series of data comprising an inertial measurement for each a time period. The monitor determines, from the time series and by using a predictive model, an activity from a list of identified activities. Examples of identified activities are deep sleep, light sleep, sitting, awake, nursing, or bottle feeding.

A system and method for processing motion-related sensor data for health application examines motion-related signal from a motion sensor located on a subject on a frame-by-frame basis to detect physical activities performed by the subject. For each frame, a detected activity is classified into a category of activities and performance parameters of the detected activity are estimated.

The embodiment of the invention provides an activity identification method and device. The method comprises the steps that radio frequency identification RFID signals from each type of activity of multiple types of predefined activities are acquired; multiple activity characteristics are extracted from the RFID signals for each type of activity; and learning of the multiple activity characteristics is performed so that an associated activity dictionary is constructed for each type of activity, and the constructed activity dictionary is enabled to classify an activity to be identified into one of the multiple types of predefined activities. The dictionary learning and training process for each type of activity is performed in a way of being independent of other activities so that the activity identification method and device are enabled to have flexibility and expandability.

The invention discloses an unsupervised personalized human activity recognition method based on multi-sensor data alignment, and the method comprises the steps: 1) carrying out the preprocessing of activity data, collected by a plurality of wearable sensors, of a training user and a new user, and respectively constructing a source domain data set and a target domain data set; 2) optimizing a humanactivity recognition model by utilizing the labeled samples in the source domain data set, so a good activity classification effect is realized on training user data; 3) selecting samples from the source domain data set and the target domain data set, adding domain labels, and using an adversarial learning strategy to alternately maximize / minimize domain discrimination loss so as to align distribution of multi-sensor data of the training user and the new user in the feature space; 4) inputting the preprocessed new user data into the activity identification model with determined parameters toobtain an activity identification result. The method can improve the activity identification accuracy of the new user.