Abstract
Hindawi International Transactions on Electrical Energy Systems Volume 2022, Article ID 8190398, 11 pages https://doi.org/10.1155/2022/8190398 Research Article Parameter Testing and System of Skiing Aerial Skills under the Background of Artificial Intelligence Dan Wang School of Physical Education, Hulunbuir College, Hulunbuir 021008, Inner Mongolia Autonomous Region, China Correspondence should be addressed to Dan Wang; wangd@hlbec.edu.cn Received 1 July 2022; Revised 3 August 2022; Accepted 13 August 2022; Published 15 September 2022 Academic Editor: Raghavan Dhanasekaran Copyright © 2022 Dan Wang. &is is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Skiing aerial skills are a perfect combination of gymnastics tossing technology and skiing technology. It pursues technology and aesthetics in the process of completing the action, and is a sporting event with strong skills and high viewing. However, the training of ski aerial skills is more difficult, and there is no qualified training mode, which may be detrimental to the long-term development of the overall strength of ski aerial skills. &erefore, based on the shortcomings of the current stage, this paper proposed a ski aerial skill movement detection system. &e system mainly assists the MTi sensor to obtain the sports shape parameters of the skier’s sports information and then analyzes the obtained data to find out the approximate data of each parameter when the skiing succeeds and fails, as well as the relationship between acceleration and speed. &e experimental results showed that the maximum resultant acceleration and resultant velocity are obtained at the lowest point of the landslide. At a certain stage of the air, the resultant acceleration is always around 10m/s due to gravity. &e shoulder joint angle of the skier at the ° ° ° moment of introduction is about 163.2 for success and about 167.6 for failure. &e inclination of the trunk is about 30.4 when the action is successful at the moment of landing, while the inclination of the trunk is about 38.4 when the action fails, and the angle of ° ° the hip joint in the successful and failed actions is about 138.5 and 153.8 , respectively. In order to better study the parametric test and analysis 1. Introduction system for ski aerial skills, some researchers have studied With the rapid development of competitive sports, many from a single aspect, among which Kim has studied the modern sciences and technologies are combined with sports aerodynamic and kinematic aspects related to ski jumping, for sports scientific research and training and play an in- by using various measurement sensors to obtain and analyze creasingly important role in improving the performance of the information of the entire platform [1]. Sands studied the athletes. At present, the main method of scientific training at possible hazards of trampoline by analyzing various pa- home and abroad is to use modern information acquisition rameters of trampoline’s aerial action and then applied it to technology to obtain human body motion information skiing [2]. Dhruv studied mathematical optimization methods to find optimal interactions between articulating parameters, which are used to guide training after com- prehensive analysis. Due to the complexity of human motion body parts [3]. Jaam identified appropriate aerial motor and the necessity of training real-time diagnosis, it is re- skills by studying normative values of motor skills tests for quired that the device for acquiring human motion infor- children aged 4–12 [4]. But, none of them found a suitable mation has high accuracy and real-time performance. Skiing algorithm to validate their research. aerial skills are a high-skill, high-difficulty, and high-risk Based on the development of artificial intelligence, sport. Any technical flaws may lead to the failure of sports scholars have developed some artificial intelligence algo- movements or even injuries to athletes. &e signal extraction rithms in order to find the optimal algorithm to test the and data processing research of the ski aerial skill test system parameters of skiing aerial skills. Among them, Youssef has is very important to the digital research of the standard studied artificial intelligence algorithms in the modeling, movements of the athletes in each technical link. selection and model, control, fault diagnosis, and output 2 International Transactions on Electrical Energy Systems estimation. &e important role of artificial intelligence al- conditions in the snow field, but also overcome the incon- gorithms in photovoltaic systems was proved by a com- venience caused by the weight of clothing and snow gear [5]. At the same time, the project is a sport with a high error rate, prehensive comparison with traditional methods [5]. Wang proposed a region growing image processing method to and athletes have a high possibility of sports injuries. study the seeds of region growing [6]. Ekici proposed a Moreover, the motion morphological parameters of human multizone optimization method to support decision-making motion information are mainly composed of dynamics, ki- across tall buildings. Proposed approaches include para- nematics, and EMG information, as shown in Figure 2. metric modeling and simulation of tall buildings and ma- Aiming at the characteristics of skiing aerial skills, chine learning and optimization as an artificial intelligence combined with the knowledge of sports biomechanics, ad- approach [7]. Hassabis examined the role of artificial in- vanced sensing technology, information acquisition, and telligence in neuroscience [8]. Makridakis examined the ergonomics, a contact method for acquiring key parameters impact of the AI revolution on companies and employment such as acceleration, velocity, angular velocity, and angle was [9]. But, they did not apply the algorithm to skiing. proposed and a prototype test system for skiing aerial skills was constructed. &e system displays all the data in the form Based on the existing technology, this paper developed a system for detecting the action parameters of ski aerial skills of two-dimensional curves while acquiring the kinematic and proposed a contact detection method to obtain the parameters of the skiers in real time. A large number of kinematic information of the athlete’s entire action process, experiments have proved that not only can the system obtain so as to realize the real-time analysis of the athlete’s action. real-time and accurate data information of athletes, but also &e innovation of this paper is that this paper used the MTi this data information can reflect some key posture features sensor to detect the movement parameters of five skiers in in the movement process, thus verifying the reliability and real time and used multiple drones to shoot at the same time. practicability of the system [11, 12]. By comparing and analyzing the sports data and states of Aiming at the technical characteristics of ski aerial skills and the shortcomings of the current motion video analysis athletes at various time nodes, the standardization of skiing actions can be further analyzed. system, this paper designed a test system based on attitude sensors. &e system consists of four modules, and the four modules communicate through wireless signals. &e kine- 2. Ski Aerial Skills under the Background of matic parameters such as acceleration and angular velocity Artificial Intelligence of athletes during exercise can be obtained in real time, and data information such as speed, angle, and angular accel- 2.1. Artificial Intelligence. Artificial intelligence (AI) can be eration of athletes can be obtained through certain algo- explained in two ways. On the one hand, AI originates from rithms. &ese four modules are shown in Figure 3. the continuous progress and development of human beings. &e signal acquisition module in Figure 3 is worn on the On the other hand, it is a computer imitating certain human waist of the athlete during the test, which can collect and behaviors [10]. Artificial intelligence is the study of how to store the data information of human body movement in real use computers to simulate certain human thought processes time and transmit the data information to the PC receiving and intelligent behaviors. &ere are many application fields module through wireless signals. &e remote control module of artificial intelligence, mainly in agriculture, communi- controls the signal acquisition module through wireless cation, medical care, social security, transportation, service signals, so as to minimize the inconvenience caused by the industry, financial industry, big data processing, and so on, athlete’s operation of the signal acquisition module. When as shown in Figure 1. receiving the synchronization signal sent by the receiving module of the PC, the camera will record the time point, so 2.2. Ski Aerial Skills Motion Detection System. &e skiing as to realize the synchronization of collecting data and aerial skill movement consists of four parts: assisting, taking shooting video. &e PC receiver module is connected with off, flipping in the air, and landing. It requires “stable, dif- the host computer, and this module communicates the PC with the other three modules through wireless signals [13]. ficult, accurate, and beautiful” in the completion of the ac- tion. &e so-called “stability” refers to the stability when When the host computer sends and receives the command, the PC receiver module starts to receive data. landing, which is one of the keys to winning the athlete; the so-called “difficult” means that the movements are techni- &e signal acquisition module is the core part, which can collect and store data information. &e structure of this cally complex and highly skilled; the so-called “beauty” means that it does not only look at the result but not the module is shown in Figure 4. &e MTi sensor and wireless process in some projects, but also depend on both the result module are connected to the microprocessor through serial and the whole process, and it pays attention to the beauty and port 1 and serial port 2, respectively. &e memory transmits artistry of the athletes’ movements. For those who watch the data with the microprocessor through the SPI interface. game, ski aerial skills sports have a great viewing experience. Since the microprocessor integrates the AD converter, the However, for athletes, it is necessary to have good coordi- power detection module can directly input the analog signal into the microprocessor [14]. nation, balance, sense of direction, good air feel, and strong explosive qualities. In the process of exercising, athletes have &e data information measured by the placement po- sition of the module should best reflect the movement to not only overcome and adapt to the difficulties brought by the climate, wind direction, snow quality, and other natural posture of the athlete, and the waist should be the center of International Transactions on Electrical Energy Systems 3 medical Agriculture transportation artificial intelligence service industry social security financial industry Figure 1: Artificial intelligence application areas. Human Movement Information Kinesiology Information Kinetic information EMG information Spatial time spatiotemporal Inertial energy muscle skeletal properties characteristic characteristics feature properties properties features Figure 2: Composition diagram of human motion information. PC receiver module host computer wireless wireless wireless Sync signal module wireless Remote control module Signal acquisition module Figure 3: Ski aerial skills test system. mass and the center of the human body. Obviously, the should be the part with the smallest range of motion of the motion information here can best reflect the motion posture human body. Moreover, the module is designed in the form of the human body. To accurately obtain the posture in- of a belt, which is tied to the waist of the athlete during formation of the movement, it must be ensured that the exercise and is very convenient to wear, and the belt part is selected position is more conducive to the fixation of the made of elastic material, which can be properly scaled [15]. module and will not fall off the athlete. &roughout the Since the module is to be worn on the body, the in- whole process of freestyle skiing, the waist of the athlete terference of the instrument to the athlete’s movements 4 International Transactions on Electrical Energy Systems power module Storage SPI interface I/O port Signal indicator Serial port 1 microprocessor MTi sensor Serial port 2 Power detection module wireless module Figure 4: Block diagram of the signal acquisition module. should be minimized, and the athlete should not be injured. measurement system that is a miniature, integrated MEMS &erefore, the module is designed to be small in size and inertial measurement sensor. MTi sensors have the advan- tages of small size, light weight, high precision, convenient light in weight. At the same time, the shell of the module is made of plastic with not too much hardness, which not only operation, and easy development, so they are widely used in robotics, aerospace, automotive, marine industries, and reduces the weight and ensures the safety of athletes, but also takes into account the aesthetics of the module. other fields [18,19]. &e block diagram of the synchronization signal ac- &e physical properties and positioning performance quisition module and the PC receiver module is shown in parameters of the MTi sensor are shown in Table 1, and the Figure 5. main performance parameters are shown in Table 2. It can be seen from Figure 5 that, in the synchronization &e coordinate system that defines the sensor itself is the signal acquisition module, when the synchronization signal S (Sensor) coordinate system, also known as the carrier sent by the PC receiving module is received, the signal coordinate system, and its coordinate system is aligned with indicator light will flash, and the camera will record this time the housing of the MTi sensor. &e reference coordinate system based on geomagnetism is the G (geomagnetism) point. &ereby, the synchronization of the collected data and the captured video is realized. &e camera is an auxiliary coordinate system, also known as the inertial reference coordinate system. &e G coordinate system is a right- analysis tool, which can assist the coaches to analyze the data information, so as to guide the athletes in a targeted manner. handed Cartesian coordinate system, which is defined as &e PC receiver module mainly realizes the following follows. &e positive direction of the X-axis points to the functions: data stored in the signal acquisition module is geomagnetic north pole; the Y-axis is determined according received; synchronization signals to the synchronization to the definition of the right-handed coordinate system; the signal module are sent; the signal acquisition module is positive direction of the Z-axis points vertically upward. debugged; data through the host computer software is Since the data (acceleration and angular velocity) measured processed and visualized [16, 17]. by the MTi sensor are all defined in the S coordinate system, &e remote control module can realize the control of the in order to analyze the movement of skiing aerial skills, some data need to be transformed into the G coordinate system. signal acquisition module. At the same time, the stop of the signal acquisition is completed by the timing of the internal &e direction cosine matrix output mode is adopted in microprocessor of the module, thereby minimizing the this system. &e direction cosine matrix is also called the inconvenience caused by the athlete’s operation of the signal transformation matrix method. It consists of nine param- acquisition module. &e structural block diagram of the eters in total, which is a method of representing the attitude remote control module is shown in Figure 6. rotation matrix by the direction cosine of the vector. &e direction cosine matrix represents the relationship between two coordinate systems rotating around a fixed point, and its 2.3. MTi Sensor. &e sensor in this system adopts MTi variation law can be described by the differential formula of sensor. It is a gyroscope-enhanced heading and attitude the direction cosine matrix. &e transformation matrix is International Transactions on Electrical Energy Systems 5 power module power module I/O port Serial port 1 Signal indicator Power detection module Power detection module PC side Serial port 2 Serial port 2 wireless module wireless module (a) (b) Figure 5: Structure block diagram of synchronization signal acquisition module and PC receiver module. Power detection module power module start up button I/O port I/O port Signal indicator 1 I/O port I/O port microprocessor Serial port 2 reset button Signal indicator 2 wireless module Figure 6: Block diagram of remote control module structure. shown in formula (1), which represents the transformation dimensional acceleration vector in the G coordinate system. matrix from the sensor coordinate system to the inertial For the angular velocity, there is no need for coordinate reference frame coordinate system. transformation. a b c R R R 11 12 13 ⎡ ⎢ ⎤ ⎥ ⎡ ⎢ ⎤ ⎥ ⎢ ⎥ ⎢ ⎥ (2) ⎢ ⎥ ⎢ ⎥ A � R A . ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ T G SG S ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ ⎢ ⎥ R � ⎢ d e f ⎥ � ⎢ R R R ⎥ � R . (1) ⎢ ⎥ ⎢ ⎥ GS ⎢ ⎥ ⎢ 14 15 16 ⎥ ⎢ ⎥ ⎢ ⎥ SG ⎣ ⎦ ⎣ ⎦ Since the acceleration signal output by the MTi sensor g h i R R R 17 18 19 contains a certain trend term, and the acceleration output by In order to facilitate the description and analysis of the the sensor contains a gravitational acceleration g, these are athlete’s movements, it is necessary to transform the ac- uniformly defined as the DC component of the signal. &e celeration into the G coordinate system. &e transformation DC component needs to be removed when calculating the method is shown in formula (2). Among them, A is the speed by integration. A common practice is to approximate three-dimensional acceleration or angular velocity vector in the mathematical expectation of the signal in place of the DC the S coordinate system, and A is the corresponding three- component. G 6 International Transactions on Electrical Energy Systems Table 1: MTi sensor physical properties and positioning performance parameters. Weight Volume Operating voltage Power consumption Operating temperature 50g 58∗58∗23mm 5V 350mW -15∼50 C Dynamic range Angular velocity resolution Static accuracy (roll) Static accuracy (heading) Dynamic accuracy 3D all angles 0.05deg <0.4deg <0.8deg 2 degRNS Table 2: MTi sensor performance parameters. project Angular velocity Acceleration Geomagnetic field Dimension &ree-dimensional &ree-dimensional &ree-dimensional Full range ±1250deg/s ±20g/s ±800mGauss Linearity 0.1% of FS 0.1% of FS 0.2% of FS Zero point stability 5deg/s 0.02m/s 0.5m Gauss Noise density 0.1deg/s√Hz 0.1m/s√Hz 0.5m Gauss Axis calibration error 0.1deg 0.1deg 0.1deg Width 40Hz 30Hz 10Hz N &e Kalman filter mainly includes the process of pre- x � x . (3) diction and update. Kalman filter is an algorithm that utilizes i�1 the linear system state formula to optimally estimate the state of the system by inputting and outputting observation In the formula, x (i � 1, . . . , N) is the acceleration signal data of the system. According to the model of Kalman filter, collected by the sensor. &erefore, the signal formula after assuming that the current state of the system is a, removing the DC component is x(a|a − 1) � Ax(a − 1|a − 1) + Bu(a). (9) x � x − x. (4) i i Among them, x(a|a − 1) refers to the result of predicting However, the method cannot completely remove the DC the current state through the previous state; x(a − 1|a − 1) component in most cases. a(t) is the acceleration signal with refers to the optimal result of the previous state; u(a) is the the DC component removed in the time domain, and A(ω) current control amount. If P represents covariance, the is obtained by Fourier transform. According to the prop- covariance formula is as follows: erties of Fourier transform, if a(t) ⟶ A(ω)q, as shown in (10) P(a|a − 1) � AP(a − 1|a − 1)A + Q. formula (5), the left end is the acceleration integral formula and ω is the frequency. Among them, P(a|a − 1) corresponds to the covariance of x(a|a − 1), P(a − 1|a − 1) corresponds to the covariance a(t)dt↔ A(ω). (5) iω −∞ of x(a − 1|a − 1), and Q refers to the covariance matrix. According to the predicted value x(a|a − 1) and the By integrating the accelerations in the three directions by current measured value Z(a), the optimal estimated value the method, the corresponding speed v (i), v (i), v (i) can x y z x(a|a) of the current state can be obtained. Among them, be obtained. Among them, i is the label of the signal se- KG(a) is the Kalman gain in the a state: quence, and the combined speed is as follows: ������������������ � P(a|a − 1)H 2 2 2 KG(a) � , (6) v(i) � v (i) + v (i) + v (i) . x y z HP(a|a − 1)H + R (11) Although the angular velocity output by the MTi sensor x(a|a) � x(a|a − 1) + KG(a)(Z(a) − Hx(a|a − 1)). is in the S coordinate system, it is not necessary to perform coordinate transformation on the angular velocity. &ere- After obtaining the optimal estimated value in the fore, the angular acceleration can be obtained by directly current state, the covariance transformation matrix P(a|a) differentiating the angular velocity. &en, trapezoidal inte- of the current state x(a|a) is updated. gration is used to find the angle with the following formula: P(a|a) � (1 − KG(a)H)P(a|a − 1). (12) θ(i) � θ(i − 1) + × [y(i − 1) + y(i)], (7) 2 × Fs When dealing with nonlinear relationships, an extended Kalman filter is required. &e basic idea is to linearize the a(i) � Fs∗ [y(i) − y(i − 1)], (8) nonlinear system and then perform Kalman filtering. As- suming the state vector x ∈ R of the process, its state where y(i) is the angular velocity and i � 1,2, ..., N and N formula is expressed as follows: are the signal sequence lengths. Fs is the sampling frequency. &e angles and angular accelerations in other directions can x � f x , u ,ω . (13) a a−1 a−1 a−1 be obtained by formulas (7) and (8). International Transactions on Electrical Energy Systems 7 ° ° &en the observed variable z ∈ R is expressed as is between 25 and 27 ; the slope of the uphill area is between ° ° ° 65 and 70 ; the slope of the landing area is between 35 and z � h x , v . (14) a a a ° 38 , and the athlete will land on the landing area after completing the aerial movements. Among them, ω , v represents the process excitation a a &e movement of ski aerial skills consists of four stages: noise and observation noise, respectively, and f and h are assist, take-off, flying, and landing. &e take-off stage refers nonlinear functions. In practical applications, ω , v at a a to the moment when the athlete starts to prepare for the different times has its own value, which can be assumed to be jump, after entering the upper wave area until the moment 0 when used, and then formulas (13) and (14) can be before the tail of the double board completely leaves the expressed as follows: platform. &e aerial stage refers to the moment when the x � f x , u ,0 , athlete’s double tails completely leave the platform to the a a−1 a−1 (15) moment before the snowboard hits the ground. A total of 5 z � h x ,0 . a a skiers were invited this time, and their basic information is Among them, x refers to the posterior estimate in a shown in Table 3. stochastic process. &e basic operation process of the ex- tended Kalman filter is basically the same as that of the 3.2. Field Experiment and Data. In order to better illustrate discrete Kalman filter. the accuracy and practicability of the system, 5 skiers were However, the obtained motion signals always contain accompanied to the experimental ski resort for field ex- some noise signals. In order to reduce the interference of the periments. Data collection was carried out on these 5 ski noise signals and better analyze the movements of the aerials. At the same time, the cameras in the system were athletes, it is necessary to remove the noise in the signals, so shot synchronously for auxiliary analysis. Aerial skills are as to restore the real movement information of the athletes. scored based on the athlete’s movement in the air and According to the characteristics of these signals, wavelet landing smoothness. It is known from the principles of decomposition and reconstruction denoising method are human kinematics that the completion of the flipping action used in this paper to denoise all motion signals of athletes. in the air is related to the speed of the flight, and the stability &e signal contaminated by noise is of the landing is closely related to the attitude when landing. x(k) � s(k) + n(k). (16) &e parameter testing and analysis system for skiing aerial skills can obtain the acceleration and angular velocity in- In the formula, x(k) is the signal with noise, s(k) is the formation of the whole movement process and obtain the real signal, n(k) is the noise, and k is the number of sampling relevant parameter information such as velocity and angle points. &en the decomposition formula is through the numerical integration and differential operation j j−1 c � h c , of the acceleration and angular velocity signals. n−2k k n Figure 8 shows the three-dimensional acceleration pa- (17) j−1 rameters in the G coordinate system during the process from d � g c . n−2k n the starting point to the landing point. &e picture distin- guishes three curves and compares the trend of acceleration In the formula, k � 1,2, ..., N and N are discrete sam- in three directions. j j pling points; c is the scale coefficient; d is the detail co- &rough analysis, it is known that the combined ac- k k efficient. &e purpose of denoising can be achieved by celeration obtained by the athlete at the lowest point of the decomposing the signal containing noise into different landslide reaches the maximum value, as shown at point a in frequency bands at a certain scale, retaining the frequency Figure 8(d). At the same time, after the athlete is in the air, band where the useful signal is located, and performing the athlete is only affected by one gravitational acceleration. wavelet reconstruction. Inverse wavelet transform is per- &erefore, the resultant velocity in the figure is about 10m/ formed to obtain the estimate of the original signal, and the s , which is consistent with the athlete receiving only a reconstruction formula is vertical downward gravitational acceleration. Since the j−1 j j athlete is subjected to a very large force at the moment of c � h c + g d . n−2k n−2k k n n (18) landing, the acceleration of the athlete will have a sudden n n change at this time. Pointb is the landing point of the athlete. Between 6s and 7s, the combined acceleration of the athlete is always around 10m/s , so the interval is the athlete’s 3. Experiment of Parameter Testing and vacating stage, which is consistent with the time of the video System for Ski Aerial Skills shot. However, (a), (b), and (c) in Figure 8 are the three- dimensional accelerations in the G coordinate system, 3.1. Ski Aerial Skills Track Model. &rough on-the-spot in- spection, the field situation of ski aerial skills is shown in respectively. Figure 9 shows the velocities in the X, Y, and Z-axis Figure 7. &e freestyle skiing aerial skill field includes the following five areas: the gliding area, the level area, the uphill directions of the athlete’s G coordinate system, which are obtained from the accelerations in Figure 8, respectively. It area, the air area, and the landing area. &e downhill area is the starting point of the athlete’s competition, and the slope can be seen from Figure 9 that, before the introduction, the 8 International Transactions on Electrical Energy Systems landslide Glide zone horizontal zone vacant area fall area Uphill area Figure 7: Ski aerial skills field model. Table 3: Basic information for skiers. Athlete Height (cm) Weight (kg) Age 1 172 75 26 2 175 73 27 3 171 68 26 4 178 70 28 5 174 69 25 25 30 20 20 15 10 10 0 5 -10 0 -20 -5 -30 -10 -40 03 1 254768 9 10 03 1 254768 9 10 Time (s) Time (s) (a) (b) 30 80 10 (m/s ) -10 -10 -20 -20 03 1 254768 9 10 03 1 254768 9 10 Time (s) Time (s) (c) (d) Figure 8: Acceleration of ski movements. (a) X-axis acceleration. (b) Y-axis acceleration. (c) Z-axis acceleration. (d) Resultant acceleration. speed trend in the X and Y directions is increasing. In this speed. &ere is a sudden change in the Z-axis acceleration stage, the Z-axis speed reaches point a; that is, when the when landing; that is, point b is the landing point. athlete reaches the lowest point of the landslide, only the Z- In addition, this experiment also analyzed multiple data axis direction is affected by gravity when in the air. parameters of the skier’s movements, mainly the intro- &erefore, the speed of X and Y axes remains basically duction of the skier and the standard degree of landing unchanged, while the speed of Z-axis decreases at a constant movements. &e experimental data are shown in Figure 10. Az (m/s ) Ax (m/s ) A (m/s ) Ay (m/s ) International Transactions on Electrical Energy Systems 9 10 10 8 8 6 6 4 4 2 2 0 0 -2 -10 -4 -20 03 1 254768 9 10 03 1 254768 9 10 Time (s) Time (s) (a) (b) -5 -10 -15 -20 -25 03 1 254768 9 10 Time (s) (c) Figure 9: Speed of skiing action. 200 180 0 0 Parameter Parameter success success fail fail (a) (b) Figure 10: Various movements of the skier’s introduction and landing. (a) Parameters at launch. (b) Parameters at landing. From Figure 10(a), it can be seen that, in the absence of vertical speed of the center of gravity and the slow assist external interference, all the sports indicators of the five speed are the key factors that cause the failure of the action. skiers have significant differences in the results at the mo- Because the length of the assist distance is proportional to ment of introduction. At the moment of introduction, the the assist speed, the speed of the assist speed affects the speed shoulder joint angle succeeded at about 163.2 and failed at of the athlete’s center of gravity, and the speed of the center about 167.6 . For the influence factors of the instant index of of gravity is affected by the horizontal speed of the center of the skier on the action result, it can be analyzed that the gravity and the vertical speed of the center of gravity. Ax (m/s) Angle hip angle ankle angle Az (m/s) torso inclination shoulder angle knee angle Ay (m/s) Angle hip angle ankle angle torso inclination shoulder angle knee angle 10 International Transactions on Electrical Energy Systems From Figure 10(b), it can be seen that the trunk incli- References nation angle of the skier was about 30.4 when the landing [1] H. Kim, L. Kim, and C. Lee, “Biomechanical research trends action was successful, and the trunk inclination angle was for ski jump analysis,” 2e Korean Journal of Physical Edu- about 38.4 when the action failed. One of the reasons for the cation, vol. 56, no. 3, pp. 613–626, 2017. failure of the movement is that the athlete’s torso inclination [2] W. A. Sands, B. Kelly, G. Bogdanis, L. Barker, and is too large when the athlete lands, and the upper body leans G. Penitente, “Comparison of bungee-aided and free- ° ° back. &e hip angles were around 138.5 and 153.8 in the bouncing accelerations on trampoline,” Science of Gymnastics successful and failed movements, respectively. Journal, vol. 1, no. 3, pp. 279–288, 2019. [3] G. Dhruv, J. Jody, and A. Lawrence, “Analysis of simulated annealing based optimization of human movement for per- 3.3. Recommendations. According to the kinematic char- formance enhancement,” ISBS Proceedings Archive, vol. 35, acteristics of the landing stage, training methods are found no. 1, p. 17, 2017. to improve sports performance, the landing posture from [4] J. Hoeboer, G. Ongena, M. Krijger-HombergenKrijger- take-off, flying, and aerial movements are adjusted, the speed Hombergen, E. Stolk, and S. Savelsberghde Vries, “&e of the center of gravity in the three-dimensional direction is Athletic Skills Track: age- and gender-related normative values of a motor skills test for 4- to 12-year-old children,” maintained, the changing angle of each joint is adjusted, and Journal of Science and Medicine in Sport, vol. 21, no. 9, landing stability is improved. &e young athletes of skiing pp. 975–979, 2018. aerial skills strengthen the targeted training of the hip and [5] A. Youssef, M. El-Telbany, and A. Zekry, “&e role of artificial knee joints, improve the joint angle control, and help im- intelligence in photo-voltaic systems design and control: a prove the landing stability during the landing stage. In the review,” Renewable and Sustainable Energy Reviews, vol. 78, training of skiers, unstable landing caused by excessive pp. 72–79, 2017. lateral drift is avoided. [6] F. Wang, Y. Z. Li, L. P. Li, and D. R. Kong, “Research on FAE cloud image processing method based on background sub- traction and region growing,” International Journal of Pattern 4. Conclusion Recognition and Artificial Intelligence, vol. 32, no. 07, p. 1854019, 2018. Aiming at the characteristics of ski aerial skills, this paper [7] B. Ekici, Z. T. Kazanasmaz, M. Turrin, M. F. Ta¸getiren, s and developed a set of snow aerial skills detection system that can I. S. Sariyildiz, “Multi-zone optimisation of high-rise buildings obtain the movement parameters of skiers during the using artificial intelligence for sustainable metropolises. Part movement process. &is paper divided the movement stages 1: background, methodology, setup, and machine learning according to the characteristics of the freestyle skiing aerial results,” Solar Energy, vol. 224, no. 2, pp. 373–389, 2021. skills movement process, and verified the reliability and [8] D. Hassabis, D. Kumaran, C. Summerfield, and M. Botvinick, “Neuroscience-inspired artificial intelligence,” Neuron, practicability of the detection system through field experi- vol. 95, no. 2, pp. 245–258, 2017. ments. However, there are still some problems in the in- [9] S. Makridakis, “&e forthcoming artificial intelligence (AI) formation acquisition system used in this paper to detect revolution: its impact on society and firms,” Futures, vol. 90, motion parameters, and the types of sensors in the system pp. 46–60, 2017. should be optimized. For example, in the motion with high [10] R. Liu, B. Yang, E. Zio, and X. Chen, “Artificial intelligence for speed parameter requirements, it is necessary to select a fault diagnosis of rotating machinery: a review,” Mechanical speed sensor that directly measures the speed to avoid the Systems and Signal Processing, vol. 108, pp. 33–47, 2018. error in the process of calculating the speed by the accel- [11] L. Caviglione, M. Gaggero, J. F. Lalande, W. Mazurczyk, and eration integral. &e number of sensors was increased, the M. Urbanski, “Seeing the unseen: revealing mobile malware sensors in multiple positions on the athlete’s body were hidden communications via energy consumption and artifi- configured, and multipoint motion parameters were ob- cial intelligence,” IEEE Transactions on Information Forensics and Security, vol. 11, no. 4, pp. 799–810, 2016. tained. Moreover, the system will provide a data basis for [12] M. S. Chehadeh and I. Boiko, “Design of rules for in-flight coaches to guide athletes in training. With the development, non-parametric tuning of PID controllers for unmanned a complete database of elite athletes may be established in the aerial vehicles,” Journal of the Franklin Institute, vol. 356, future to provide the necessary data basis for the compar- no. 1, pp. 474–491, 2019. ative analysis of athletes’ training. [13] L. M. D. Santos, G. Ferraz, M. T. Andrade, L. S. Santana, and G. Rossi, “Analysis of flight parameters and georeferencing of images with different control points obtained by RPA,” Data Availability Agronomy Research, vol. 17, no. 5, pp. 2054–2063, 2019. [14] H. Lee, F. M. Troschel, S. Tajmir, and S. Fuchs Mario Fin- &e data that support the findings of this study are available telmann Do, “Pixel-level deep segmentation: artificial intel- from the corresponding author upon reasonable request. ligence quantifies muscle on computed tomography for body morphometric analysis,” Journal of Digital Imaging, vol. 30, Conflicts of Interest no. 4, pp. 487–498, 2017. [15] A. Hermann, N. Bauer, V. Senner, S. Fischer, S. Lindner, and &e author declares that there are no conflicts of interest S. Seitz, “Ski underwear for real time measuring of knee with respect to the research, authorship, and/or publication flexion during skiing,” Technische Textilien, vol. 60, no. 5, of this article. pp. E289–E291, 2017. International Transactions on Electrical Energy Systems 11 [16] A. K. Adzhiev, N. V. Kondratyeva, and M. Y. Bekkiev, “Engineering-hydrometeorological researches for the object “Mountain-Skiing infrastructure of the resort “arkhyz” - avalanche risk evaluation,” Materials Science Forum, vol. 931, no. 2, pp. 1092–1097, 2018. [17] R. Chatila, K. Firth-Butterflied, J. C. Havens, and K. Karachalios, “&e IEEE global initiative for ethical con- siderations in artificial intelligence and autonomous systems [standards],” IEEE Robotics and Automation Magazine, vol. 24, no. 1, p. 110, 2017. [18] F. Mavliev, V. Demidov, A. Nazarenko, N. Davletova, and A. Nabatov, “Particularities of microcirculation of athletes training for endurance, and its factors,” Science And Sport: Current Trends, vol. 7, no. 3, pp. 100–107, 2019. [19] S. Price and P. A. Flach, “Computational support for academic peer review,” Communications of the ACM, vol. 60, no. 3, pp. 70–79, 2017.
Journal
International Transactions on Electrical Energy Systems
– Hindawi Publishing Corporation
Published: Sep 15, 2022