According to an aspect of the present invention there is provided a method of detecting and categorising an event occurring on a sports field, the method comprising: obtaining a series of ball and player position data measurements; determining a rotation rate of the ball device over the time period from data received from the ball device; determining the player is likely in possession of the ball based on a plurality of possession tests comprising: comparing a current position of the ball device and the player device to identify a relative distance between the ball device and the player device and calculating if the relative distance is lower than a reference value; comparing an obtained velocity of the ball device and the player device, respectively, to identify a relative velocity of the ball device with respect to the player device and calculating if the relative velocity is lower than a reference value; and, calculating if the rotation rate of the ball device is lower than a reference value; subsequently identifying a change in possession event based on the tests; categorising the event; and, outputting a notification of the event and its associated categorisation.

A motion recognition method for a computer to execute a process includes acquiring skeleton information in time series based on positional information of each of a plurality of joints that includes a certain joint of a subject who makes a motion; estimating a region where the certain joint is positioned among a plurality of regions obtained by dividing a region of an object used for the motion based on the positional information; recognizing the motion of the subject by using the skeleton information and the estimated region; and outputting the recognized motion of the subject.

A muscle-strengthening passive and active motion device includes: a joint supporter supporting a body part that is bendable or stretchable with a joint region; a driver driving the joint supporter by being combined to the joint supporter; and a controller controlling the driver, wherein the controller is capable of accelerating or decelerating a driving speed of the joint supporter.

A system, method, and computer-readable media collect and analyze the physical performance of an individual and structure and generate an athletic protocol. Athletic assessment devices perform an athletic assessment of an individual, including kinetic, neurological, musculoskeletal and aerobic capacity. Athletic data is collected and stored in a digital data storage medium of a computer system having a display, and a central processing unit (CPU) operable with programming executes one or more analytical algorithms to assess injury risk levels of said individual based on said athletic data. Data mining algorithms using artificial intelligence are used to execute predictive modeling and analytics. The resultant athletic protocol includes information to correct imbalances to treat and/or prevent injuries, corrective exercises, performance training exercises, and protocols to maximize physical performance.

An evaluation method for a computer to execute a process includes, acquiring a plurality of pieces of skeleton information in time series based on position information of joints of an object that executes a plurality of motions; specifying a transition period between a first motion and a second motion that follows the first motion, which are included in the plurality of motions based on the plurality of pieces of skeleton information; determining whether the transition period is related to a certain combination of motions by inputting skeleton information among the plurality of pieces of skeleton information that corresponds to the transition period into an evaluation model trained to evaluate a transition period between motions based on a plurality of pieces of skeleton information in time series; and outputting an evaluation result of the transition period by the evaluation model.

Systems and methods are provided for generating and provisioning personalized news feeds for athletes. One embodiment is a system that receives metrics for exercise activities performed by athletes. The system generates records of the exercise activities of the athletes based on the metrics, determines a type of exercise for each record, classifies the records based on corresponding types of exercise, and compiles a fitness history, for each athlete, comprising records of exercise activities performed by the athlete. For each of the athletes, the system generates a digital news feed for the athlete, identifies categories of engagement for the athlete based on types of exercise indicated in the fitness history of the athlete, selects articles from a repository, personalizes the digital news feed for the athlete by populating the digital news feed with the selected articles, and transmits the digital news feed to a user device.

A recommendation system may store user data, fitness class data, and expert rules data. The user data may correspond to health or fitness information about a user. The fitness class data may correspond to information about a fitness class. The expert rules data may correspond to an action for accomplishing a health objective. The recommendation system may be configured to determine health objective data based on the user data. The health objective data may be determined directly or inferentially. The health objective data may be matched with the expert rules data. The expert rules data may be matched with the fitness class data. The fitness class data may correspond to an aspect of the fitness class that aligns with the health objective of the user. Recommendation data may be generated that corresponds to a recommendation of the fitness class for the user.

A sensor event detection and tagging system that analyzes data from multiple sensors to detect an event and to automatically select or generate tags for the event. Sensors may include for example a motion capture sensor and one or more additional sensors that measure values such as temperature, humidity, wind or elevation. Tags and event detection may be performed by a microprocessor associated with or integrated with the sensors, or by a computer that receives data from the microprocessor. Tags may represent for example activity types, players, performance levels, or scoring results. The system may analyze social media postings to confirm or augment event tags. Users may filter and analyze saved events based on the assigned tags. The system may create highlight and fail reels filtered by metrics and by tags.

A mechanical braking system which can provide a brake to a self-powered treadmill, or a dual mode treadmill that can operate in both self-powered and motor-powered modes, that will rapidly halt the motion of the belt or rollers in the event of a power disconnect such as from the removal of a safety key.

A sensor event detection system including a motion capture element and another sensor. The sensor captures values associated with an orientation, position, velocity and acceleration and recognizes an event within the data to determine event data. Uses other values associated with a temperature, humidity, wind and elevation, i.e., environmental and physiological sensors and correlates the data or event data with the other values to determine a type of event or true event or a false positive event, or a type of equipment the motion capture element is coupled with, or a type of activity indicated by the data or event data and transmits the data or event data associated with the event.