Modern communication and computing technology is the basic support of the industrial intelligent systems (IIS). As a key component of IIS, the smart port is essential to be offered low‐complexity and high‐reliability communication service, especially for driverless engineering vehicles. However, it is combined and nonconvex to find the optimal association between vehicles and the road side units (RSUs). Besides, due to the mobility of vehicles and the severe path loss of mmWave links, beam switching and reassociation between vehicles and RSUs are required frequently, which brings a great challenge to the communication for the IIS. A low complexity closed‐loop strategy based on distributed cooperation for mmWave communication in IIS is proposed in this study, in which user association and beam tracking with the assistance of beam pools is proposed. Many‐to‐many user association is established based on distributed multiagent reinforcement learning, where the vehicle can independently select the set of serving RSUs based on the local observation without information exchange with others, reducing the signaling overhead and computational complexity while improving system throughput. Furthermore, multipoint‐cooperation soft switching of beams based on beam tracking improves the reliability of mmWave communication with the smaller training cost. Extensive analysis and simulation results demonstrate that the proposed solution significantly reduces the complexity of the mmWave communication while improving the throughput and stability in IIS.
In order to analyze the sound production mechanism and the acoustic characteristics of Haliotis discus hannai during feeding, this paper proposes a multi-source information fusion approach combining passive acoustics with videos. In the experiments, abalones with a shell length of 60 ± 2.7 mm were divided into two groups: Group A was fed with fresh macro algae Gracilaria lemaneiformis as food once each day; Group B was placed on a small amount of sand as impurities at the bottom of the tank. As control groups, Group C did not have abalone or food and Group D did not have abalones but food was added. The eating acoustic signals of abalone were mainly concentrated in the frequency range between 9.49 kHz and 44.36 kHz, wherein the peak frequency is 37.86 ± 2.55 kHz, with the maximum energy -66.43 ± 5.17 dBm/Hz. Each pulse sequence is with a duration of 119.12 ± 70.51 ms and consists of several sub-pulses. Nearly 70% of the pulse sequences consist of 1~2 sub-pulses and the duration of the pulse containing one sub-pulse is 42.62 ± 19.72 ms. The eating rate was kept at 0.61 ± 0.04 times/min at the beginning and was decreased significantly to 0.48 ± 0.08 times/min after 60 mins. Note that the characteristic analysis of abalone acoustic signals during feeding are first reported in this manuscript to the best of our knowledge, and this paper also demonstrates that the sound of abalone is produced by scraping and grinding food with radula. Because the eating rate decreases with the reduction in the abalone’s level of hunger, the results may be used as an acoustic indicator of feeding strategy for the abalone aquaculture industry.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.