Underwater target recognition is an important supporting technology for the development of marine resources, which is mainly limited by the purity of feature extraction and the universality of recognition schemes. The low-frequency analysis and recording (LOFAR) spectrum is one of the key features of the underwater target, which can be used for feature extraction. However, the complex underwater environment noise and the extremely low signal-to-noise ratio of the target signal lead to breakpoints in the LOFAR spectrum, which seriously hinders the underwater target recognition. To overcome this issue and to further improve the recognition performance, we adopted a deep-learning approach for underwater target recognition, and a novel LOFAR spectrum enhancement (LSE)-based underwater target-recognition scheme was proposed, which consists of preprocessing, offline training, and online testing. In preprocessing, we specifically design a LOFAR spectrum enhancement based on multi-step decision algorithm to recover the breakpoints in LOFAR spectrum. In offline training, the enhanced LOFAR spectrum is adopted as the input of convolutional neural network (CNN) and a LOFAR-based CNN (LOFAR-CNN) for online recognition is developed. Taking advantage of the powerful capability of CNN in feature extraction, the recognition accuracy can be further improved by the proposed LOFAR-CNN. Finally, extensive simulation results demonstrate that the LOFAR-CNN network can achieve a recognition accuracy of 95.22%, which outperforms the state-of-the-art methods.

No abstract

No abstract

Research and development of virtual reality somatosensory game based on Unity3D and exercise bike is conducted in this manuscript. The novelty of the paper is focused on: (1) The game design method is used to realize a game design method based on the exercise bike platform, which is versatile and can be applied to other simulation interactive systems. And try to solve the rigid exercise of sports games, make the exercises vivid and interesting, give full play to the entertainment characteristics of electronic games, and let participants get a virtual and real experience. (2) In program development, using game engine as development tool improves the reuse of code, reduces the difficulty of development and shortens the development cycle. The key technologies of network communication, collision detection and artificial intelligence are studied and applied in fitness bicycle somatosensory game. The performance of the proposed model is validated through the experimental analysis. In the future, the applications will be tested.