The fusion steps were incorporated into the network structure, and the data were validated by the multi-static DCNN. Then, it was trained on each receiving node and the results were fused by binary voting. Firstly, a single static DCNN was proposed based on voting. The directional diversity provided by polymorphic radar was applied to improve the classification accuracy. (2018) proposed two deep convolutional neural networks (DCNNs) based on multi-static radar micro-Doppler signals for human recognition and gait classification. In combination with the basketball movement rules and the relevant theories of psychology and physiology, analysis and investigation have been conducted for the fake actions of basketball players to obtain qualitative and quantitative results ( Du et al., 2020).Ĭhen et al. The artificial intelligence algorithm based on human–computer interaction is adopted to recognise the actions of basketball players in the game. Therefore, the reasonable application of fake action can specifically reflect the psychology of athletes in sports. What’s more, it can conceal their own movement intention, realise their own real purpose of sports, and gain the advantage of time and space on the court ( Qi et al., 2019). Fake action refers to how athletes use the illusion of their own movement techniques to confuse the vision and feeling of the opposing players so that the opposing athletes make wrong judgments or lose their own body balance. In the process of ball holding, players can effectively promote the chances of breaking through the defence by taking advantage of their own speed and reasonable use of fake actions ( Zhou et al., 2016). The basketball player with the ball applies footstep movement and dribbling skills to break through and quickly pass the defence of the opposing player. Therefore, the proposed optimised C3D can recognise effectively human actions, and the results of this study can provide a reference for the investigation of the image recognition of human action in sports. Besides, the time complexity is reduced by 33%. The optimised convolutional three-dimensional network (C3D) HAR model designed in this study has a recognition accuracy of 80% with an image loss of 5.6. Experimental results show that the combination of grayscale and red-green-blue (RGB) images can reduce the image loss and effectively improve the recognition accuracy of the model. Then, the psychology of athletes is also analysed through the collected videos, so as to predict the next response action of the athletes.
Secondly, the psychology of basketball players displaying fake actions during the offensive and defensive process is investigated by combining with related sports psychological theories. First, a HAR model is established based on the convolutional neural network (CNN) to classify the current action state by analysing the action information of a task in the collected videos.
#Speedgoat kernel transfer matlab 2018b Pc
Thus if IP adress of target PC is configured to 192.168.6.6 in Step 5, then host PC can be set for example to static IP adress of 192.168.6.5.In order to analyse the sports psychology of athletes and to identify the psychology of athletes in their movements, a human action recognition (HAR) algorithm has been designed in this study. The ethernet device of the PC must be configured with static IP adress in the same network as configured for the target PC.
Setup ethernet device and network settings in "Host-to-Target communication" dropdown list.In the target window, select properties of the Target PC session.In Matlab, open Simulink Real-Time Explorer using the matlab command "slrtexplr".Create bootable USB with FreeDOS Lite image using the Rufus tool from.The target PC must also have a supported ethernet device, see the device list in Simulink Real-Time Explorer discussed in Step 5.
You need BIOS firmware or UEFI firmware with BIOS legacy support (to be enabled in boot settings screen). Thus motherboards with UEFI only firmware will not work. Answer for Simulink Real-Time version up to 2020a.