As a continuous antenna, the leaky coaxial cable (LCX) is widely used in wireless communication of closed or semi-closed areas such as the subway, mine, tunnel, etc. Usually, LCX networks are required in coal mines. Its channel characteristics are of great significance to mobile communication and mine safety. This paper presents an effective channel modeling and optimization method that combines the state transition and the particle swarm optimization (PSO) algorithms for the LCX network. First, a channel model can be established with a few parameters based on the state transition method, which can describe the complex transfer function of the LCX network; then, taking the transfer characteristics of the LCX network as the optimization objective, which should be consistent with the measured results. And the established objective function is optimized and designed with the PSO algorithm. Finally, the proposed method is validated by comparing the measured results and the model-based simulations on two test LCX networks. The experimental results show that the absolute error between the proposed model and the measurement model is less than that of other models at any frequency point. The proposed model can accurately obtain all responses between point-to-point channels at one time. It will help to accurately obtain the performance of different LCX networks and help to detect and locate faults in future studies.
While end-to-end models have shown great success on the Automatic Speech Recognition task, performance degrades severely when target sentences are long-form. The previous proposed methods, (partial) overlapping inference are shown to be effective on long-form decoding. For both methods, word error rate (WER) decreases monotonically when over-lapping percentage decreases. Setting aside computational cost, the setup with 50% overlapping during inference can achieve the best performance. However, a lower overlapping percentage has an advantage of fast inference speed. In this paper, we first conduct comprehensive experiments comparing overlapping inference and partial overlapping inference with various configurations. We then propose Voice-Activity-Detection Overlapping Inference to provide a trade-off between WER and computation cost. Results show that the pro-posed method can achieve a 20% relative computation cost reduction on Librispeech and Microsoft Speech Language Translation long-form corpus while maintaining the WER performance when comparing to the best performing over-lapping inference algorithm. We also propose Soft-Match to compensate for similar words misaligned problem.
When integrating evolutionary algorithms into the process of the design of modular robots, the "reality gap" problem leads to the difference between simulation and reality. A modular robot transplantation method based on the improved inverse distance weighting method proxy model is presented. Based on the plane moving task, the portability of the modular robot consisting of EMERGE modules of different shapes and types was experimentally studied. The information of other real robots can be predicted according to the limited evolutionary data of real robots. It is no need to do all the evaluation experiments on a physical robot. The number and complexity of experiments are reduced. the experiment efficiency is improved. This method can effectively reduce the performance difference between the results of simulation and the real robot caused by the "reality gap" problem, and the portability of modular robots improves greatly.