GB2615174A

GB2615174A - Goalkeeper sensor system and method

Info

Publication number: GB2615174A
Application number: GB2217696.0A
Authority: GB
Inventors: James Clark Anthony; Scott Roslund Brendan; Edmund Button David
Original assignee: Goalkeeper Com Ltd
Current assignee: Goalkeeper Com Ltd
Priority date: 2022-01-28
Filing date: 2022-01-28
Publication date: 2023-08-02
Also published as: GB202217696D0

Abstract

A method comprises receiving by a processor goalkeeper movement data from a 9 axis Inertial measurement unit (IMU) in a goalkeeper glove, inserting the data in a machine learning library and generating a machine learning model and comparing the data to the model to classify the movement as a prediction. The IMU is preferably in a chamber in a goalkeeper glove aligned with the ring finger metacarpal. The IMU may include a gyroscope, accelerometer and magnetometer. The data may be used to display a 3d animation of the movement.

Description

Goalkeeper Sensor System and Method

BACKGROUND

[0001] It is believed by many that goalkeeper is the most difficult position in football or soccer.

It is the goalkeeper's job or role to prevent or stop the opposing team from scoring by stopping the ball from moving over a goal line into a goal. Goalkeeper typically requires a unique skill set and, in many instances, each time a goalkeeper touches a ball, it can be a very high pressure situation. Unlike other players on the field or pitch, the goalkeeper has the ability to use their hands as long as it is in a permitted location of the field or pitch, e.g., the penalty area. The penalty area comprises an eighteen-yard box of the pitch that is located around a goal. To prevent the other team from scoring, the goalkeeper moves their body into the path of the ball and can catch the ball using their hands, punch the ball using one or more hands, or redirect the ball away from the goal using their hands or another part of their body (e.g., feet, legs, chest, head). After making a save, the goalkeeper can either throw or roll the ball to their teammates or may use their feet to pass the ball to their teammates.

[0002] The goalkeeper typically trains separately from the rest of their teammates and works on many different skills that players other than goalkeepers do not practice. Unlike other players that focus on cardio-related skills, the goalkeeper may practice quick and explosive movements such as dives, leaps, and lunges to prevent a ball from entering the goal.

100031 Data analytics has been applied to many different fields including sports such as baseball, football or soccer, basketball, hockey, and American football, among others. However, much of the analytics and analysis in football or soccer has focused on players other than goalkeepers such as the field players. As a result, it has been very difficult to analyze a goalkeeper's performance during matches and during practice.

[0004] It is with these issues in mind, among others, that various aspects of the disclosure were conceived.

SUMMARY

100051 The present disclosure is directed to a goalkeeper sensor system and method. The system may include one or more goalkeeper gloves each having one or more goalkeeper sensors. As an example, the goalkeeper sensor may be placed or held in a cradle or a pouch in the goalkeeper glove that protects the goalkeeper sensor and may limit noisy data obtained by the goalkeeper sensor. The goalkeeper sensor may be located on a back side of the goalkeeper glove.

During activity, the goalkeeper sensor may obtain data that may be collected in realtime such as goalkeeper movement. The data may be provided to a machine learning library to generate a machine learning model to compare and classify goalkeeper movement and predict particular actions or movements performed during athletic activity such as football matches and practice sessions. The goalkeeper may view information such as statistics associated with the activity as well as view three-dimensional movement information associated with the activity as obtained by the goalkeeper sensor.

[0006] In one example, a device may include a nine-axis inertial measurement unit (IMU) and a goalkeeper glove having a hollow section to receive a hand and configured to receive the nine-axis IMU in a receiving chamber in the hollow section between a first side of the goalkeeper glove in communication with a palmar side of the hand and a second side of the goalkeeper glove in communication with a dorsal side of the hand, the receiving chamber on the dorsal side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove.

[0007] In another example, a method may include receiving, by at least one processor, data associated with a goalkeeper movement obtained by a nine-axis inertial measurement unit (IMU) in a goalkeeper glove, inserting, by the at least one processor, the data in a machine learning library, generating, by the at least one processor, a machine learning model using the data in the machine learning library, and comparing, by the at least one processor, the data with the machine learning model to classify the goalkeeper movement as a prediction.

[0008] These and other aspects, features, and benefits of the present disclosure will become apparent from the following detailed written description of the preferred embodiments and aspects taken in conjunction with the following drawings, although variations and modifications thereto may be effected without departing from the spirit and scope of the novel concepts of the disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings illustrate embodiments and/or aspects of the disclosure and, together with the written description, serve to explain the principles of the disclosure. Wherever possible, the same reference numbers are used throughout the drawings to refer to the same or like elements of an embodiment, and wherein: [0010] Figure 1 is a block diagram of a goalkeeper sensor system according to an example of

the instant disclosure.

100111 Figure 2 is an image of a goalkeeper glove associated with the goalkeeper sensor system according to an example of the instant disclosure.

[0012] Figure 3 is another image of the goalkeeper glove associated with the goalkeeper sensor system according to an example of the instant disclosure.

[0013] Figure 4 is another image of the goalkeeper glove associated with the goalkeeper sensor system according to an example of the instant disclosure.

[0014] Figure 5 is a diagram of the goalkeeper glove and a position of a sensor according to

an example of the instant disclosure.

[0015] Figure 6 is a database schema diagram associated with the goalkeeper sensor system

according to an example of the instant disclosure.

[0016] Figure 7 is a diagram showing machine learning techniques associated with the goalkeeper sensor system according to an example of the instant disclosure.

[0017] Figure 8 shows a diagram associated with a movement prediction performed by the goalkeeper sensor system using a machine learning model according to an example of the instant disclosure.

[0018] Figure 9 shows a block diagram of the sewer computing device having a goalkeeper sensor application according to an example of the instant disclosure.

[0019] Figure 10 is a flowchart of performing a movement prediction by the goalkeeper sensor system according to an example of the instant disclosure.

[0020] Figure 1 I shows example data obtained by a goalkeeper sensor of the goalkeeper sensor system according to an example of the instant disclosure.

[0021] Figure 12 is a three-dimensional visual representation of data obtained by the goalkeeper sensor system according to an example of the instant disclosure.

[0022] Figure 13 shows an example of a system for implementing certain aspects of the present technology.

DETAILED DESCRIPTION

[0023] The present invention is more fully described below with reference to the accompanying figures. The following description is exemplary in that several embodiments are described (e.g, by use of the terms "preferably," "for example," or "in one embodiment"); however, such should not be viewed as limiting or as setting forth the only embodiments of the present invention, as the invention encompasses other embodiments not specifically recited in this description, including alternatives, modifications, and equivalents within the spirit and scope of the invention. Further, the use of the terms "invention," "present invention," "embodiment," and similar terms throughout the description are used broadly and not intended to mean that the invention requires, or is limited to, any particular aspect being described or that such description is the only manner in which the invention may be made or used. Additionally the invention may be described in the context of specific applications; however, the invention may be used in a variety of applications not specifically described.

[0024] The embodiment(s) described, and references in the specification to one embodiment", "an embodiment", "an example embodiment", etc., indicate that the embodiment(s) described may include a particular feature, structure, or characteristic. Such phrases are not necessarily referring to the same embodiment. When a particular feature, structure, or characteristic is described in connection with an embodiment, persons skilled in the art may effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0025] In the several figures, like reference numerals may be used for like elements having like functions even in different drawings. The embodiments described, and their detailed construction and elements, are merely provided to assist in a comprehensive understanding of the invention. Thus, it is apparent that the present invention can be carried out in a variety of ways, and does not require any of the specific features described herein. Also, well-known functions or constructions are not described in detail since they would obscure the invention with unnecessary detail. Any signal arrows in the drawings/figures should be considered only as exemplary, and not limiting, unless otherwise specifically noted. Further, the description is not to be taken in a limiting sense, but is made merely for the purpose of illustrating the general principles of the invention, since the scope of the invention is best defined by the appended claims.

[0026] It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. Purely as a non-limiting example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items. As used herein, the singular forms "a", "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be noted that, in some alternative implementations, the functions and/or acts noted may occur out of the order as represented in at least one of the several figures. Purely as a non-limiting example, two figures shown in succession may in fact be executed substantially concurrently or may sometimes be executed in the reverse order, depending upon the functionality and/or acts described or depicted.

[0027] It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may in fact be executed substantially concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.

[0028] Conditional language, such as, among others, "can," "could," "might," or may," unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments include, while other embodiments do not include, certain features, elements and/or steps. Thus, such conditional language is not generally intended to imply that features, elements and/or steps are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without user input or prompting, whether these features, elements and/or steps are included or are to be performed in any particular embodiment.

[0029] Aspects of a goalkeeper sensor system and method includes a device such as one or more goalkeeper gloves that include a nine-axis inertial measurement unit (1MU) or goalkeeper sensor that communicates with a server computing device having a goalkeeper sensor application. The server computing device may have or communicate with a database that includes a machine learning library that may be used generate a machine learning model to train the goalkeeper sensor application and predict a goalkeeper action or movement using the goalkeeper sensor application.

[0030] The goalkeeper glove may securely protect the goalkeeper sensor in a pouch or a cradle that may be made of a fabric or material and may be located on a backside or backhand of the glove. This may allow the goalkeeper sensor to be mounted securely as well as limit an amount of noisy data obtained by the goalkeeper sensor. The goalkeeper sensor may be securely attached or affixed within the goalkeeper glove using an elastic or stretchy material that may provide a force on the goalkeeper sensor to hold the goalkeeper sensor in place.

[0031] As another example, the goalkeeper sensor may be held in place using a high friction rubberized surface within the goalkeeper glove. As another example, the goalkeeper sensor may be held in place using one or more layers of material. As another example, the goalkeeper sensor may be held in place in a secure and accessible pouch within an interior of the goalkeeper glove to securely house the goalkeeper sensor. The secure and accessible pouch may be water resistant and may be opened and closed using a hook and loop fastener and/or a zipper or another type of closure device.

[0032] The goalkeeper sensor may be located in a particular area on the goalkeeper glove to limit or prevent injury to the goalkeeper such as a back of the glove where the goalkeeper's hand may be least likely to be injured due to forces associated with athletic activity including forces due to contact with a ball, the ground, and/or other players or athletes. The goalkeeper sensor may be protected by padding and structure associated with the glove to prevent injury to the goalkeeper. The padding, structure, and fabric may help to dissipate and dampen forces between the hand of the goalkeeper and the goalkeeper sensor. In addition, the goalkeeper sensor may have a particular shape such as curvature and/or contouring that may limit forces to the hand of the goalkeeper. In addition, by locating the goalkeeper sensor on a back of the glove, data resolution associated with force absorbed by the goalkeeper's hands may be obtained. In one example, the goalkeeper sensor may be centralized onto a lower section of a ring finger metacarpal on each backhand of the goalkeeper.

[0033] The goalkeeper sensor may be placed into the cradle or pouch with a side entry system that may allow input of the goalkeeper sensor into an opening near a pinky finger of a hand. The opening may be externally facing. In another example, the goalkeeper sensor may be placed into the cradle or pouch with a lower entry system from a proximal side closest to a wrist of the goalkeeper. The opening may be internally facing or externally facing. In addition, the goalkeeper sensor may have a slight concave contact surface to further secure the goalkeeper sensor in the cradle or pouch against a back of a hand of the goalkeeper.

[0034] In an example, the goalkeeper sensor may communicate with a computing device such as a server computing device over a network. The network may be associated with near-field communication (NFC) or another type of network or communication protocols.

[0035] Although the sensor is described as a goalkeeper sensor, it may be used in other athletics or sports including other sports that may have gloves such as baseball, American football, and others. In another example, the sensor may be located elsewhere such as clothing including a jersey, shorts, socks, pants, another piece of clothing, or a helmet worn by the athlete. As an example, the sensor may be used to determine and display statistics related to athlete movements and to leverage information to assist athletes in improving their performance. The sensor discussed herein may include one or more sensors or devices including one or more accelerometers, one or more gyroscopes, and one or more magnetometers or compasses. The sensor may be used to track movement of the goalkeeper (e.g., acceleration, magnetic orientation, and angular velocity in three dimensions) over short periods of time to determine changes in position in orientation of one or more hands of the goalkeeper. The sensor may include one or more three-axis accelerometers, one or more three-axis gyroscopes, and one or more magnetometers, among other sensors.

[0036] In one example, a device may include a nine-axis inertial measurement unit (WU) and a goalkeeper glove having a hollow section to receive a hand and is configured to receive the nine-axis IMU in a receiving chamber in the hollow section between a first side of the goalkeeper glove in communication with a palmar side of the hand and a second side of the goalkeeper glove in communication with a dorsal side of the hand, the receiving chamber on the dorsal side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove.

[0037] The system may include one or more goalkeeper gloves each having one or more goalkeeper sensors. As an example, the goalkeeper sensor may be placed or held in a cradle or a pouch in the goalkeeper glove that protects the goalkeeper sensor and may limit noisy data obtained by the goalkeeper sensor. The goalkeeper sensor may be located on a back side of the goalkeeper glove. During activity, the goalkeeper sensor may obtain data that may be collected in realtime such as goalkeeper movement. The data may be provided to a machine learning or artificial intelligence library to generate a machine learning/artificial intelligence model to compare and classify goalkeeper movement and predict particular actions or movements performed during athletic activity such as football matches and practice sessions among others. The goalkeeper may view information such as statistics associated with the activity as well as view three-dimensional movement information associated with the activity as obtained by the goalkeeper sensor.

[0038] As an example, the goalkeeper sensor may communicate with another computing device to transfer the data obtained during the athletic activity. The data may be transferred using near-field communication (NFC), Bluetooth, or using another method or protocol. The computing device may be a server computing device that may store the data in a database, data lake, or a data warehouse, among others. A client computing device may request information associated with the data collected by the goalkeeper sensor and may view the information using a graphical user interface (GUI) that may display the information using a dashboard.

[0039] As an example, the goalkeeper may wear a first glove on a first hand. The first glove may have a first goalkeeper sensor. The goalkeeper may wear a second glove on a second hand. The second glove may have a second goalkeeper sensor. Each goalkeeper sensor may obtain data while the goalkeeper is performing athletic activity and transfer the data to an application executed by a computing device such as a client computing device. The client computing device may be a mobile computing device. The mobile computing device may process the data and/or may transmit the data to a server computing device. The server computing device and/or the client computing device may have a goalkeeper sensor application that may filter the data and perform machine learning (ML) or use artificial intelligence (Al) to make determinations based on the data.

[0040] The machine learning or artificial intelligence may be used to generate a ML or Al model associated with goalkeeping or another athletic activity. The machine learning model may perform movement identification on movements and actions in the data. The movements and actions may be used to provide statistics and analytics associated with goalkeeping. This may be used to analyze goalkeeping performance. The goalkeeper and/or other users such as a goalkeeping coach, head coach, or assistant coach, or other coach may view the statistics and analytics using either a mobile application executed by the client computing device or using a web browser that may display a user interface.

[0041] As an example, the dashboard or user interface may include a summary of statistics and one or more session workload statistics There may be information associated with a total workload, a dive load, and an impact load. There may be information associated with a hand load including total force absorbed by a right hand and a total force absorbed by a left hand, a heavy touch count, and a max force. The hand load information may be used to generate a force line plot that may show right hand versus left hand impact force throughout a session. In addition, there may be save type information including a catch count percentage, parry count percentage, punch count percentage, multi-touch handling and a count percentage, a contour catch count percentage success rate, a basket catch count percentage success rate, a low catch count percentage success rate, and a multi-touch handling count percentage success rate.

[0042] The dashboard or user interface may further include a save type line plot that may be a timeline based view of a session that may have different user interface elements or symbols to show an action type over a course of a session. This may also include periods of time in action with no ball contact. The save type line plot may include information associated with a dive left high count, percentage, and success rate, a dive left mid count, percentage, and success rate, a dive left low count, percentage, and success rate, and a sprawl/shape left count, percentage, and success rate. The save type line plot may include a high tip count, percentage, and success rate, a multi-touch count, percentage, and success rate, a punch/redirect count, percentage, and success rate, and a messy contact low count, percentage, and success rate. The save type line plot may include a high contour count, percentage, and success rate, a contour count, percentage, and success rate, a basket count, percentage, and success rate, and a clean catch low count, percentage, and success rate. The save type line plot may include a dive right high count, percentage, and success rate, a dive right mid count, percentage, and success rate, a dive right low count, percentage, and success rate, and a sprawl/shape right count, percentage, and success rate.

[0043] The dashboard or user interface may include vector based data including one or more action sequences. The action sequences may be based on vectors of a specific sequence of movements including arm swing/stationary, high set position, low set position, and mixed right/left starting position. In addition, the action sequences may be based on vectors associated with save attack angle (SAA) or curve, save hand speed and acceleration curve, hand speed at contact, hand movement through save sequence, and distance covered. The dashboard or user interface may include a sample sequence visualizer that may include a sequence X & Y axis on a goal frame as well as a sequence Y & Z axis.

[0044] The dashboard or user interface may include distribution statistics including throwing as well as a throw count and maximum throw speed. The dashboard or user interface may include information associated with volleys/punts as well as style information associated with volleys/punts and counts for each. A user may select each throw and may view a throw session X, Y axis, a hand speed, back swing, release point, and follow through information. In addition, a user may select a session associated with a volley or punt and may view volley session hand position X, Y axis, a hand position, and other details.

[0045] The dashboard or user interface may include crossing/high ball statistics information.

There may be information associated with crossings including a catch count and success rate, punch information such as a one-handed punch count and success rate and a two-handed punch count and success rate, and multi-touch count and success rate. A user may select each instance associated with the crossings/high balls and may view crossing session hand position X, Y axis information, hand position pre, during, and post, engagement type including a catch, one-handed punch, and a two-handed punch, palm position, engagement height, and velocity generated from arm swing. In addition, a user may view crossing session hand position Y, Z axis information, hand position pre, during, post, engagement type including a catch, one-handed punch, and a two-handed punch, palm position, and velocity generated from arm swing.

[0046] In particular, the dashboard or user interface may have a unique user interface element or symbol for each hand position. A save attack angle may indicate a movement path that a goalkeeper's hands may take toward a ball including a negative angle. A save hand speed may be shown using a line having a variable color and may include an acceleration curve. Contact with a ball may be shown using a unique user interface element or symbol. The dashboard or user interface may show one or more arrows that may indicate a right hand vector and a left hand vector to indicate right/left hand involvement in a save. Distance covered may be step-based, in-air, or an on-ground slide. A save type may be derived from a mixture of the data.

[0047] Figure 1 is a block diagram of a goalkeeper sensor system 100 according to an example of the instant disclosure. As shown in Figure 1, the system 100 may include at least one goalkeeper glove or device 102 and at least one sewer computing device 104. The at least one server computing device 104 may be in communication with at least one database 112. As shown in Figure 1, the goalkeeper glove 102 may have one or more goalkeeper sensors 106 that may be one or more nine-axis inertial measurement units (EMUS). The nine-axis WU may include one or more accelerometers, one or more gyroscopes, and one or more magnetometers.

[0048] In one example, the goalkeeper glove 102 may have a hollow section to receive a hand and may be configured to receive the nine-axis IMU or goalkeeper sensor in a receiving chamber in the hollow section between a first side of the goalkeeper glove in communication with a palmar side of the hand and a second side of the goalkeeper glove in communication with a dorsal side of the hand, the receiving chamber on the dorsal side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove 102.

[0049] The goalkeeper sensor 106 and the server computing device 104 may have a goalkeeper sensor application 108 that may be a component of an application and/or service executable by the at least one client computing device and/or the server computing device I 04. For example, the goalkeeper sensor application 108 may be a single unit of deployable executable code or a plurality l0 of units of deployable executable code. According to one aspect, the goalkeeper sensor application 108 may include one component that may be a web application, a native application, and/or a mobile application (e.g., an app) downloaded from a digital distribution application platform that allows users to browse and download applications developed with mobile software development kits (SDKs) including the App Store and GOOGLE PLAY®, among others.

[0050] The goalkeeper sensor system 100 also may include a relational database management system (RDBMS), e.g., MySQL, or another type of database management system such as a NoSQL database system that stores and communicates data from at least one database 112. The data stored in the at least one database 112 may be associated with goalkeeper movement including goalkeeper actions or movements associated with a plurality of athletes.

[0051] The database 112 may be a data warehouse and may include a machine learning or artificial intelligence library that includes a vast amount of data associated with one or more goalkeepers obtained by the goalkeeper sensor 106.

[0052] The at least one goalkeeper sensor 106 and the at least one server computing device 104 may be configured to receive data from and/or transmit data through a communication network 110. Although the server computing device 104 is shown as a single computing device, it is contemplated each computing device may include multiple computing devices or multiple virtual machines, or multiple containers, for example, in a cloud computing configuration.

[0053] The communication network I 10 can be the Internet, an intranet, or another wired or wireless communication network. For example, the communication network may include a Mobile Communications (GSM) network, a code division multiple access (CDMA) network, 3' Generation Partnership Project (GPP) network, an Internet Protocol (IP) network, a wireless application protocol (WAP) network, a WiFi network, a near-field communication (NFC) network, a Bluetooth network, a near field communication (NFC) network, a satellite communications network, or an IEEE 802.11 standards network, as well as various communications thereof. Other conventional and/or later developed wired and wireless networks may also be used.

[0054] The goalkeeper sensor 106 may include at least one processor to process data and memory to store data. The processor processes communications, builds communications, retrieves data from memory, and stores data to memory. The processor and the memory are hardware. The memory may include volatile and/or non-volatile memory, e.g., a computer-readable storage medium such as a cache, random access memory (RANI), read only memory (ROM), flash memory, or other memory to store data and/or computer-readable executable instructions. In addition, the goalkeeper sensor 106 further includes at least one communications interface to transmit and receive communications, messages, and/or signals. The goalkeeper sensor 106 may also include a Global Positioning System (GPS) hardware device for determining a particular location and an input device such as one or more hardware buttons, among other components.

[0055] The goalkeeper sensor 106 may communicate with a client computing device that could be a programmable logic controller, a programmable controller, a laptop computer, a smartphone, a personal digital assistant, a tablet computer, a standard personal computer, or another processing device. The client computing device may include a display, such as a computer monitor, for displaying data and/or graphical user interfaces.

[0056] The client computing device may include at least one processor to process data and memory to store data. The processor processes communications, builds communications, retrieves data from memory, and stores data to memory. The processor and the memory are hardware. The memory may include volatile and/or non-volatile memory, e.g., a computer-readable storage medium such as a cache, random access memory (RAM), read only memory (ROM), flash memory, or other memory to store data and/or computer-readable executable instructions. In addition, the client computing device further includes at least one communications interface to transmit and receive communications, messages, and/or signals.

[0057] The client computing device may have input devices such as one or more cameras or imaging devices, a keyboard or a pointing device (e.g., a mouse, trackball, pen, or touch screen) to enter data into or interact with graphical and/or other types of user interfaces. The client computing device may also include a Global Positioning System (GPS) hardware device for determining a particular location as well as one or more imaging devices such as cameras. In an exemplary embodiment, the display and the input device may be incorporated together as a touch screen of the smartphone or tablet computer.

[0058] The server computing device 104 may include at least one processor to process data and memory to store data. The processor processes communications, builds communications, retrieves data from memory, and stores data to memory. The processor and the memory are hardware. The memory may include volatile and/or non-volatile memory, e.g., a computer-readable storage medium such as a cache, random access memory (RAM), read only memory (ROM), flash memory, or other memory to store data and/or computer-readable executable instructions. In addition, the server computing device 104 further includes at least one communications interface to transmit and receive communications, messages, and/or signals.

[0059] As an example, the goalkeeper sensor 106 and the server computing device 104 communicate data in packets, messages, or other communications using a common protocol, e.g., Hypertext Transfer Protocol (HTTP) and/or Hypertext Transfer Protocol Secure (HTTPS). The one or more computing devices may communicate based on representational state transfer (REST) and/or Simple Object Access Protocol (SOAP). As an example, a first computer (e.g., the goalkeeper sensor 106 or client computing device) may send a request message that is a REST and/or a SOAP request formatted using Javascript Object Notation (JSON) and/or Extensible Markup Language (XML,). In response to the request message, a second computer (e.g., the server computing device 104) may transmit a REST and/or SOAP response formatted using JSON and/or XML. In some examples, the goalkeeper sensor 106 may communicate with the client computing device and the client computing device may communicate with the server computing device 104.

[0060] Figure 2 shows a side view of the goalkeeper glove 102 according to an example of the instant disclosure. As shown in Figure 2, there is a receiving chamber 202 in a hollow section of the goalkeeper glove to receive a hand. The receiving chamber may be in the hollow section between a first side of the goalkeeper glove 102 in communication with a palmar side of the hand and a second side of the goalkeeper glove 102 in communication with a dorsal side of the hand, the receiving chamber on the dorsal or backside side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove.

[0061] Figure 3 shows another view of the goalkeeper glove 102 according to an example of the instant disclosure. As shown in Figure 3, the receiving chamber 202 may be located on a backhand of the goalkeeper glove, or the dorsal side of the hand. As shown in Figure 3, the receiving chamber may have one or more openings that may be used including a side entry or access opening and a low entry or wrist entry access opening.

[0062] Figure 4 shows another view of the goalkeeper glove 102 according to an example of the instant disclosure. As shown in Figure 4, there is a punch zone 402 of the goalkeeper glove 102. This punch zone 402 may typically be used by the goalkeeper to punch away the ball. The goalkeeper may use one or two hands to punch away the ball and typically uses the punch zone 402 on each glove. The goalkeeper sensor 106 may be located in a number of locations on the backhand of the goalkeeper glove. However, it is ideal to locate the goalkeeper sensor 106 in the particular location 404 shown in Figure 4 to isolate the goalkeeper sensor 106 from noise that may not be associated with goalkeeper movements and actions. In addition, by placing the goalkeeper sensor 106 in the particular location 404, it keeps it away from the punch zone 402 of the goalkeeper glove 102.

[0063] Figure 5 shows a diagram of the goalkeeper glove 102 and a position of the goalkeeper sensor 106 according to an example of the instant disclosure. As shown in Figure 5, the goalkeeper sensor 106 may be located in a middle portion of the goalkeeper glove 106, or alternatively, toward an exterior of the hand to isolate the goalkeeper sensor 106 from noise that may not be associated with goalkeeper movements and actions.

[0064] Figure 6 shows a database schema diagram of the database 112 associated with the goalkeeper sensor system according to an example of the instant disclosure. As shown in Figure 6, the database 112 may have one or more tables including a table associated with each entity and its attributes. In particular, Figure 6 shows entities including frame data obtained by the goalkeeper sensor 106. As an example, the FrameData may include a framelD that may be a unique identifier, gX, gY, gZ, dpsX, dpsY, dpsZ, tX, tY, tZ, timestamp, and a channel identifier. Movement may include a movementID that may be a unique identifier, a sessionID, a startFrameM, and a stopFrameID. Conditions may include a weatherlD that may be a unique identifier, humidity, temperature, windSpeed, and windDirection. Session may include a sessionID that may be a unique identifier, a date, an athleteID, movementrns, weatherTD, configurationID, and a sportName (e.g., football or soccer). Athlete may include an athletelD that may be a unique identifier, an athleteName, a height, and an armSpan.

[0065] Figure 7 shows a diagram showing machine learning techniques associated with the goalkeeper sensor system 100 according to an example of the instant disclosure. As shown in Figure 7, the goalkeeper sensor system 100 may receive training machine learning data such as instances of data over a period of time that may represent one or more goalkeeper moves. Inputs to the machine learning model 708 may include the data as well as a support vector machine (SVM) that may include one or more data segments or periods of time that include collections of data including one or more packets of data that may correspond to labeled movements such as an "up move" 702, a "bottom right move" 704, and a "bottom left move" 706. The SVM may learn from the input and may be used to predict future movements based on input data. As an example, the machine learning model 708 may learn from the input and labels associated with each movement 710.

[0066] Figure 8 shows a diagram associated with a movement prediction performed by the goalkeeper sensor system 100 according to an example of the instant disclosure. As shown in Figure 8, input data may include data associated with an up move 702 that may be sent to the machine learning model 708. The server computing device 104 may use the machine learning model 708 to predict that this corresponds with a movement prediction one 802. The input data may include data associated with a bottom right move 704. The server computing device 104 may use the machine learning model 708 to predict that this corresponds with a movement prediction two 804. The input data may include data associated with a bottom left move 706. The server computing device 104 may use the machine learning model 708 to predict that this corresponds with a movement prediction three 806.

[0067] Figure 9 shows a block diagram of the server computing device 104 of the goalkeeper sensor system 100 according to an example of the instant disclosure. The server computing device 104 includes computer readable media (CRM) 904 in memory on which the goalkeeper sensor application 108 is stored. The computer readable media 904 may include volatile media, nonvolatile media, removable media, non-removable media, and/or another available medium that can be accessed by the processor 902. By way of example and not limitation, the computer readable media 904 comprises computer storage media and communication media. Computer storage media includes non-transitory storage memory, volatile media, nonvolatile media, removable media, and/or non-removable media implemented in a method or technology for storage of information, such as computer/machine-readable/executable instructions, data structures, program modules, or other data. Communication media may embody computer/machinereadable/executable instructions, data structures, program modules, or other data and include an information delivery media or system, both of which are hardware.

[0068] The goalkeeper sensor application 108 may include a data receiver module 906. The data receiver module 906 may receive data associated with one or more sessions from the goalkeeper sensor 106 and store the data in the database 112. The data may include data as shown, for example, in Figure 6 including frame data, movement data, conditions data, session data, configuration data, channel data, athlete data, and sport data. As an example, the data may include athlete information, a configuration identifier, environment conditions, and a session identifier, among others.

[0069] As an example, the data receiver module 906 may receive data from the gyroscope, accelerometer, and magnetometer readings from the goalkeeper sensor 106. There may be a set sampling frequency of 200 Hz that may be used for the gyroscope and the accelerometer and there may be a set sampling frequency of 25Hz for the magnetometer. After the data is collected, it may be processed to determine and calculate quaternions or rotations in three-dimensional space. The data may be processed using sensor fusion to combine the data from each of the readings. The processing may find a balance between the gyroscope or accelerometer with the magnetometer to provide an accurate angular vector. In addition, the processing may use filtering algorithms such as the Kalman filter. The Kalman filter may take a previous vector and a current vector to predict a next vector in the sequence. It can then use the predicted vector to estimate error and check if the error is within an error range. Once vectors have been determined, they may be animated. The animation may plot points for a projected space of the vector. Then, quivers for each of the x, y, and z vectors may be plotted and the animation may represent the sensor moving through three-dimensional space along the x, y, and z axis.

[0070] The goalkeeper sensor application 108 may include a machine learning library module 908. As an example, data in the database 112 may be inserted into the machine learning library by the machine learning library module 908. The machine learning library module 908 may receive training machine learning data such as one or more instances of data over time that may represent one or more goalkeeper moves. For instance, the data may be frame data from one or more frames and may include three-dimensional data from the nine-axis IMU including X, Y, and Z data In addition, the data may include a label that identifies an action or movement that may be provided by a user or from another source such as "contour catch" or another label. The machine learning library module 908 may remove outlier data or information from the data.

[0071] The machine learning library model module 910 may generate or build the model by receiving the data as well as the label and then compare received data with the data in the library to make more accurate determinations and predictions based on the data in the library. When the data is added to the library and provided with a prediction, the prediction may be a label that is added to the data and inserted into the machine learning library. As an example, the machine learning model module 910 may generate the model using one or more of supervised learning, unsupervised learning, and reinforcement learning. The machine learning model module 910 may continue to build upon and refine the model as the model continues to learn from the data.

[0072] The goalkeeper sensor application 108 may include an action/movement prediction module 912 that may predict or classify data associated with an action or movement associated with an athlete as a particular movement or action. As an example, the data associated with a particular moment in time may be determined to be a movement prediction one 802 such as a one-handed punch or a low dive to the left. The data may include frame data such as three-dimensional data from the nine-axis IMU including X axis, Y axis, and Z axis data from each of the one or more accelerometers, one or more magnetometers, and one or more gyroscopes.

[0073] The goalkeeper sensor application 108 may include a user interface module 914. The user interface module 914 receives requests or other communications from the client computing device 102 and transmits a representation of requested information, user interface elements, and other data and communications to the client computing device for display on the display. As an example, the user interface module 914 generates a native and/or web-based graphical user interface (GUI) that accepts input and provides output by generating content that is transmitted via the communications network 110 and viewed by a user of the client computing device. The user interface module 914 may provide realtime automatically and dynamically refreshed information to the user of the client computing device using Java, Javascript, AJAX (Asynchronous Javascript and XML), ASP.NET, Microsoft.NET, and/or node.js, among others. The user interface module 914 may send data to other modules of the goalkeeper sensor application 108 of the server computing device 104, and retrieve data from other modules of the goalkeeper sensor application 108 of the server computing device 104 asynchronously without interfering with the display and behavior of the client computing device.

[0074] Figure 10 illustrates an example method 1000 of performing a movement prediction by the goalkeeper sensor system 100 according to an example of the instant disclosure. Although the example method 1000 depicts a particular sequence of operations, the sequence may be altered without departing from the scope of the present disclosure. For example, some of the operations depicted may be performed in parallel or in a different sequence that does not materially affect the function of the method 1000. In other examples, different components of an example device or system that implements the method 1000 may perform functions at substantially the same time or in a specific sequence.

[0075] According to some examples, the method 1000 may include receiving, by at least one processor, data associated with a goalkeeper movement obtained by a nine-axis measurement unit (IMU) or the goalkeeper sensor 106 in the goalkeeper glove 102 at block 1010. This may include receiving the data from one or more goalkeeper gloves 102. The goalkeeper glove 102 may have a hollow section to receive a hand and is configured to receive the nine-axis MU in a receiving chamber in the hollow section between a first side of the goalkeeper glove in communication with a palmar side of the hand and a second side of the goalkeeper glove in communication with a dorsal side of the hand, the receiving chamber on the dorsal side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove 102.

[0076] As an example, the goalkeeper glove 102 may include a fastener configured to open and close the receiving chamber. The fastener can be one of a zipper and a hook and loop fastener, among others. In some examples, the fastener is located on an exterior of a pinky finger metacarpal section of the goalkeeper glove 102 and between the first side of the goalkeeper glove 102 and the second side of the goalkeeper glove. The fastener is located on a wrist section of the goalkeeper glove 102 on the second side of the goalkeeper glove.

[0077] As an example, the goalkeeper glove may include a near-field communication (NEC) device to transmit data received by the nine-axis IMU to a computing device such as the server computing device 104 or another computing device, in an example, the nine-axis IMU is configured to be removable from the receiving chamber. The receiving chamber may have one of a pouch and a cradle to receive the nine-axis EMU. The receiving chamber may have a flexible material to receive the nine-axis IMU. As an example, the nine-axis IMU can have a rechargeable battery or another power source.

[0078] As an example, the receiving chamber may have a concave contact surface that is in communication with the nine-axis IMU on a first end of the concave contact surface and on a second end of the concave contact surface.

[0079] The collection of the data may include collecting the data at a set sampling frequency of 200 Hz for a gyroscope and an accelerometer of the nine-axis IMU and 25 Hz for a magnetometer of the nine-axis MU.

[0080] Next, according to some examples, the method 1000 may include inserting, by the at least one processor, the data in a machine learning library at block 1020. The data may include a plurality of frames associated with one or more athletes such as data obtained from goalkeeper sensors 106 and/or from another source. The data may include labels such as a type or goalkeeper movement or athlete movement for the data.

[0081] Next, according to some examples, the method 1000 may include generating, by the at least one processor, a machine learning model using the data in the machine learning library at block 1030.

[0082] Next, according to some examples, the method 1000 may include comparing, by the at least one processor, the data with the machine learning model to classify the goalkeeper movement as a prediction of a particular movement or action at block 1040.

[0083] Next, according to some examples, the method 1000 may include determining, by the at least one processor, a force of a ball striking the goalkeeper glove 102 and an attack angle using the machine learning model at block 1050.

[0084] Next, according to some examples, the method 1000 may include displaying, by the at least one processor, a representation of the data obtained from the nine-axis 1MU in a three-dimensional model representing a specific movement based on the prediction at block 1060. As an example, this may include generating an animation in three-dimensional space over a period of time based on the data and displaying the animation on a display such as a display of the client computing device.

[0085] According to some examples, the method 1000 may include determining one of a quaternion and a rotation in three-dimensional space represented in the data using the machine learning model.

[0086] According to some examples, the method 1000 may include determining an angular vector represented in the data using the machine learning model.

[0087] According to some examples, the method 1000 may include classifying the goalkeeper movement as a contour catch or a different type of catch using the machine learning model.

[0088] According to some examples, the method 1000 may include further storing in the database 112 the data, athlete information associated with the data, a configuration identifier, a session identifier, and environmental conditions.

[0089] Figure 11 shows example data 1100 obtained by the goalkeeper sensor 106 of the goalkeeper sensor system 100 that may be stored in the database 112. As shown in Figure 11, the data may include a packet number, a gyroscope reading for the X axis in angular velocity in degrees/second, a gyroscope reading for the Y axis in in angular velocity in degrees/second, a gyroscope reading for the Z axis in angular velocity in degrees/second, an accelerometer reading for the X axis (g) that shows a rate of change of the velocity of the goalkeeper, an accelerometer reading for the Y axis (g) that shows a rate of change of the velocity of the goalkeeper, an accelerometer reading for the Z axis (g) that shows a rate of change of the velocity of the goalkeeper, a magnetometer reading for the X axis (G), a magnetometer reading for the Y axis (G), and a magnetometer reading for the Z axis (G).

[0090] Figure I 2 shows a three-dimensional visual representation of data 1200 obtained by the goalkeeper sensor system 100 according to an example of the instant disclosure. As shown in Figure 12, once vectors have been determined, they may be animated. The animation may plot points for a projected space of the vector. Then, quivers for each of the x, y, and z vectors may be plotted and the animation may represent the goalkeeper sensor 106 moving through three-dimensional space along the x, y, and z axis.

[0091] Additionally, the client computing device may display statistics and analytics in a visual representation of the data. The movements and actions may be used to provide statistics and analytics associated with goalkeeping. This may be used to analyze goalkeeping performance. The goalkeeper and/or other users such as a goalkeeping coach, head coach, or assistant coach, or other coach may view the statistics and analytics using either a mobile application executed by the client computing device or using a web browser that may display a user interface.

[0092] As an example, the dashboard or user interface may include a summary of statistics and one or more session workload statistics There may be information associated with a total workload, a dive load, and an impact load. There may be information associated with a hand load including total force absorbed by a right hand and a total force absorbed by a left hand, a heavy touch count, and a max force. The hand load information may be used to generate a force line plot that may show right hand versus left hand impact force throughout a session. in addition, there may be save type information including a catch count percentage, parry count percentage, punch count percentage, multi-touch handling and a count percentage, a contour catch count percentage success rate, a basket catch count percentage success rate, a low catch count percentage success rate, and a multi-touch handling count percentage success rate.

[0093] The dashboard or user interface may further include a save type line plot that may be a timeline based view of a session that may have different user interface elements or symbols to show an action type over a course of a session. This may also include periods of time in action with no ball contact. The save type line plot may include information associated with a dive left high count, percentage, and success rate, a dive left mid count, percentage, and success rate, a dive left low count, percentage, and success rate, and a sprawl/shape left count, percentage, and success rate. The save type line plot may include a high tip count, percentage, and success rate, a multi-touch count, percentage, and success rate, a punch/redirect count, percentage, and success rate, and a messy contact low count, percentage, and success rate. The save type line plot may include a high contour count, percentage, and success rate, a contour count, percentage, and success rate, a basket count, percentage, and success rate, and a clean catch low count, percentage, and success rate. The save type line plot may include a dive right high count, percentage, and success rate, a dive right mid count, percentage, and success rate, a dive right low count, percentage, and success rate, and a sprawl/shape right count, percentage, and success rate.

[0094] The dashboard or user interface may include vector based data including one or more action sequences. The action sequences may be based on vectors of a specific sequence of movements including arm swing/stationary, high set position, low set position, and mixed right/left starting position. In addition, the action sequences may be based on vectors associated with save attack angle (SAA) or curve, save hand speed and acceleration curve, hand speed at contact, hand movement through save sequence, and distance covered. The dashboard or user interface may include a sample sequence visualizer that may include a sequence X & Y axis on a goal frame as well as a sequence Y & Z axis.

[0095] The dashboard or user interface may include distribution statistics including throwing as well as a throw count and maximum throw speed. The dashboard or user interface may include information associated with volleys/punts as well as style information associated with volleys/punts and counts for each. A user may select each throw and may view a throw session X, Y axis, a hand speed, back swing, release point, and follow through information. In addition, a user may select a session associated with a volley or punt and may view volley session hand position X, Y axis, a hand position, and other details.

[0096] The dashboard or user interface may include crossing/high ball statistics information.

[0097] In particular, the dashboard or user interface may have a unique user interface element or symbol for each hand position. A save attack angle may indicate a movement path that a goalkeeper's hands may take toward a ball including a negative angle. A save hand speed may be shown using a line having a variable color and may include an acceleration curve. Contact with a ball may be shown using a unique user interface element or symbol. The dashboard or user interface may show one or more arrows that may indicate a right hand vector and a left hand vector to indicate right/left hand involvement in a save. Distance covered may be step-based, in-air, or an on-ground slide. A save type may be derived from a mixture of the data.

[0098] Figure 13 shows an example of computing system 1300, which can be for example any computing device making up the computing device such as a computing device associated with the goalkeeping sensor 106, the client computing device, the server computing device 104, or any component thereof in which the components of the system are in communication with each other using connection 1305. Connection 1305 can be a physical connection via a bus, or a direct connection into processor 1310, such as in a chipset architecture. Connection 1305 can also be a virtual connection, networked connection, or logical connection.

[0099] In some embodiments, computing system 1300 is a distributed system in which the functions described in this disclosure can be distributed within a datacenter, multiple data centers, a peer network, etc. In some embodiments, one or more of the described system components represents many such components each performing some or all of the function for which the component is described. In some embodiments, the components can be physical or virtual devices. 1001001 Example system 1300 includes at least one processing unit (CPU or processor) 1310 and connection 1305 that couples various system components including system memory 1315, such as read-only memory (ROM) 1320 and random access memory (RAM) 1325 to processor 1310. Computing system 1300 can include a cache of high-speed memory 1312 connected directly with, in close proximity to, or integrated as part of processor 1310.

1001011 Processor 1310 can include any general purpose processor and a hardware service or software service, such as services 1332, 1334, and 1336 stored in storage device 1330, configured to control processor 1310 as well as a special-purpose processor where software instructions are incorporated into the actual processor design. Processor 1310 may essentially be a completely self-contained computing system, containing multiple cores or processors, a bus, memory controller, cache, etc. A multi-core processor may be symmetric or asymmetric.

1001021 To enable user interaction, computing system 1300 includes an input device 1345, which can represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphical input, keyboard, mouse, motion input, speech, etc. Computing system 1300 can also include output device 1335, which can be one or more of a number of output mechanisms known to those of skill in the art. In some instances, multimodal systems can enable a user to provide multiple types of input/output to communicate with computing system 1300. Computing system 1300 can include communications interface 1340, which can generally govern and manage the user input and system output. There is no restriction on operating on any particular hardware arrangement, and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.

1001031 Storage device 1330 can be a non-volatile memory device and can be a hard disk or other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, solid state memory devices, digital versatile disks, cartridges, random access memories (RAMs), read-only memory (ROM), and/or some combination of these devices.

1001041 The storage device 1330 can include software services, servers, services, etc., that when the code that defines such software is executed by the processor 1310, it causes the system to perform a function. In some embodiments, a hardware service that performs a particular function can include the software component stored in a computer-readable medium in connection with the necessary hardware components, such as processor 1310, connection 1305, output device 1335, etc., to carry out the function.

1001051 For clarity of explanation, in some instances, the present technology may be presented as including individual functional blocks including functional blocks comprising devices, device components, steps or routines in a method embodied in software, or combinations of hardware and software.

1001061 Any of the steps, operations, functions, or processes described herein may be performed or implemented by a combination of hardware and software services or services, alone or in combination with other devices. In some embodiments, a service can be software that resides in memory of a client device and/or one or more servers of a content management system and perform one or more functions when a processor executes the software associated with the service. In some embodiments, a service is a program or a collection of programs that carry out a specific function. In some embodiments, a service can be considered a server. The memory can be a non-transitory computer-readable medium.

100107] In some embodiments, the computer-readable storage devices, mediums, and memories can include a cable or wireless signal containing a bit stream and the like. However, when mentioned, non-transitory computer-readable storage media expressly exclude media such as energy, carrier signals, electromagnetic waves, and signals per se.

1001081 Methods according to the above-described examples can be implemented using computer-executable instructions that are stored or otherwise available from computer-readable media. Such instructions can comprise, for example, instructions and data which cause or otherwise configure a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Portions of computer resources used can be accessible over a network. The executable computer instructions may be, for example, binaries, intermediate format instructions such as assembly language, firmware, or source code. Examples of computer-readable media that may be used to store instructions, information used, and/or information created during methods according to described examples include magnetic or optical disks, solid-state memory devices, flash memory, USB devices provided with non-volatile memory, networked storage devices, and so on.

1001091 Devices implementing methods according to these disclosures can comprise hardware, firmware and/or software, and can take any of a variety of form factors. Typical examples of such form factors include servers, laptops, smartphones, small form factor personal computers, personal digital assistants, and so on. The functionality described herein also can be embodied in peripherals or add-in cards. Such functionality can also be implemented on a circuit board among different chips or different processes executing in a single device, by way of further example.

1001101 The instructions, media for conveying such instructions, computing resources for executing them, and other structures for supporting such computing resources are means for providing the functions described in these disclosures.

1001111 Illustrative examples of the disclosure include: 1001121 Aspect 1: A device comprising: a nine-axis inertial measurement unit (IMU) and a goalkeeper glove having a hollow section to receive a hand and configured to receive the nine-axis BTU in a receiving chamber in the hollow section between a first side of the goalkeeper glove in communication with a palmar side of the hand and a second side of the goalkeeper glove in communication with a dorsal side of the hand, the receiving chamber on the dorsal side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove.

1001131 Aspect 2: The device of Aspect 1, the receiving chamber further comprising a fastener configured to open and close the receiving chamber.

1001141 Aspect 3: The device of Aspects 1 and 2, wherein the fastener comprises one of a zipper and a hook and loop fastener.

1001151 Aspect 4: The device of Aspects 1 to 3, wherein the fastener is located on an exterior of a pinky finger metacarpal section of the goalkeeper glove and between the first side of the goalkeeper glove and the second side of the goalkeeper glove.

1001161 Aspect 5: The device of Aspects Ito 4, wherein the fastener is located on a wrist section of the goalkeeper glove on the second side of the goalkeeper glove.

100117] Aspect 6: The device of Aspects I to 5, further comprising a near-field communication (NFC) device to transmit data received by the nine-axis IMU to a computing device.

100118] Aspect 7: The device of Aspects I to 6, wherein the nine-axis IMU is configured to be removable from the receiving chamber.

1001191 Aspect 8: The device of Aspects 1 to 7, wherein the receiving chamber comprises one of a pouch and a cradle to receive the nine-axis IMU.

1001201 Aspect 9: The device of Aspects 1 to 8, wherein the receiving chamber comprises a flexible material to receive the nine-axis IMU.

100121] Aspect 10: The device of Aspects 1 to 9, the nine-axis [MU further comprising a rechargeable battery.

1001221 Aspect 11: The device of Aspects 1 to 10, wherein the receiving chamber comprises a concave contact surface that is in communication with the nine-axis INTIJ on a first end of the concave contact surface and on a second end of the concave contact surface.

1001231 Aspect 12: A method comprising receiving, by at least one processor, data associated with a goalkeeper movement obtained by a nine-axis inertial measurement unit (INIU) in a goalkeeper glove, inserting, by the at least one processor, the data in a machine learning library, generating, by the at least one processor, a machine learning model using the data in the machine learning library, and comparing, by the at least one processor, the data with the machine learning model to classify the goalkeeper movement as a prediction.

1001241 Aspect 13: The method of Aspect 12, wherein the goalkeeper glove comprises a hollow section to receive a hand and is configured to receive the nine-axis ll\TU in a receiving chamber in the hollow section between a first side of the goalkeeper glove in communication with a palmar side of the hand and a second side of the goalkeeper glove in communication with a dorsal side of the hand, the receiving chamber on the dorsal side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove.

1001251 Aspect 14: The method of Aspects 12 and 13, further comprising collecting the data at a set sampling frequency of 200 Hz for a gyroscope and an accelerometer of the nine-axis WU and 25 Hz for a magnetometer of the nine-axis MU.

1001261 Aspect IS: The method of Aspects 12 to 14, further comprising determining one of a quaternion and a rotation in three-dimensional space represented in the data using the machine learning model.

1001271 Aspect 16: The method of Aspects 12 to IS, further comprising determining an angular vector represented in the data using the machine learning model.

1001281 Aspect 17: The method of Aspects 12 to 16, further comprising generating an animation in three-dimensional space over a period of time based on the data and displaying the animation on a display.

1001291 Aspect 18: The method of Aspects 12 to 17, further comprising determining a force of a ball striking the goalkeeper glove and an attack angle using the machine learning model 1001301 Aspect 19: The method of Aspects 12 to 18, further comprising classifying the goalkeeper movement as a contour catch using the machine learning model.

1001311 Aspect 20: The method of Aspects 12 to 19, further comprising displaying a representation of the data obtained from the nine-axis IMU in a three-dimensional model representing a specific movement based on the prediction.

1001321 Aspect 21: The method of Aspects 12 to 20, further comprising storing in a database the data, athlete information associated with the data, a configuration identifier, a session identifier, and environment& conditions.

Claims

CLAIMSWhat is claimed is: 1. A method, comprising: receiving, by at least one processor, data associated with a goalkeeper movement obtained by a nine-axis inertial measurement unit (EMU) in a goalkeeper glove; inserting, by the at least one processor, the data in a machine learning library; generating, by the at least one processor, a machine learning model using the data in the machine learning library; and comparing, by the at least one processor, the data with the machine learning model to classify the goalkeeper movement as a prediction.
2. The method of claim I, wherein the goalkeeper glove comprises a hollow section to receive a hand and is configured to receive the nine-axis IMU in a receiving chamber in the hollow section between a first side of the goalkeeper glove in communication with a palmar side of the hand and a second side of the goalkeeper glove in communication with a dorsal side of the hand, the receiving chamber on the dorsal side of the hand and aligned with a ring finger metacarpal section of the goalkeeper glove.
3. The method of claim 1 or claim 2, further comprising collecting the data at a set sampling frequency of 200 Hz for a gyroscope and an accelerometer of the nine-axis IMU and 25 Hz for a magnetometer of the nine-axis IMU.
4. The method of claim 1, 2 or 3, further comprising determining one of a quaternion and a rotation in three-dimensional space represented in the data using the machine learning model.
5. The method of any one of claims 1 to 4, further comprising determining an angular vector represented in the data using the machine learning model
6. The method of any one of the preceding claims, further comprising generating an animation in three-dimensional space over a period of time based on the data and displaying the animation on a display.
7. The method of any one of the preceding claims, further comprising determining a force of a ball striking the goalkeeper glove and an attack angle using the machine learning model.
8. The method of any one of the preceding claims, further comprising classifying the goalkeeper movement as a contour catch using the machine learning model.
9. The method of any one of the preceding claims, further comprising displaying a representation of the data obtained from the nine-axis 1MU in a three-dimensional model representing a specific movement based on the prediction.
10. The method of any one of the preceding claims, further comprising storing in a database the data athlete information associated with the data, a configuration identifier, a session identifier, and environmental conditions