“Angle sensitivity” aggravates the difficulty in radarbased omnidirectional human motion recognition. This issue is addressed in earlier work by using omnidirectional radar data for training. However, this practice requires labor-intensive radar measurements and a time-consuming annotation process. Tackling this issue, this paper first introduces the active learning technique for the radar-based omnidirectional recognition problem, and we present a hybrid-uncertainty active learning method, which significantly reduces the annotation expenses required to train an omnidirectional motion classifier. In the context of the complex motions and varying angles, we propose a pixel-wise similarity assessment methodology in addition to semantic-based sampling. This approach is proven to alleviate the issue of “Imbalanced Sampling” in active learning significantly by rebalancing the selected samples across categories. Furthermore, a hybrid-uncertainty dimension is introduced to quantify the uncertainty of the unlabeled samples from both pixel and semantic levels. The dimension is evaluated through three perspectives, including the consistency factor, difficulty factor and pixel-wise similarity. The experimental results exhibit that our algorithm achieves a recognition accuracy of 76.06% using only 40% of labeled data, which is a mere decrease of only 0.15% compared to the accuracy achieved with 100% labeled data. Our approach surpasses six state-of-the-art active learning methods in solving the omnidirectional problem, and ablation studies confirm the efficacy of each component presented in our model.
1 March 2021 in Journal of Physics: Conference Series
In recent years, due to the influence of policies such as environmental protection and reduction of harmful gas emissions, clean energy such as lithium batteries, hydrogen-oxygen fuel cells, and waste heat power generation technologies are being applied on ships. As the application level of new energy continues to expand, its safety issues have attracted more and more attention from society. The system collects the air pressure, temperature, humidity, flame heat radiation, and smoke information inside the ship’s power battery box, and uses the STM32 processor to determine whether the ship’s power battery has a fire hazard. This system can effectively avoid the thermal runaway of the power battery, detect the thermal runaway at an early stage and actively respond to reduce losses, and protect the life and property safety of passengers on board.
The consistent speckle noise in SAR images easily interferes with the semantic information of the target. Additionally, the limited quantity of supervisory information available in one-shot learning leads to poor performance. To address the aforementioned issues, we creatively propose an SAR target recognition model based on one-shot learning. This model incorporates a background noise removal technique to eliminate the interference caused by consistent speckle noise in the image. Then, a global and local complementary strategy is employed to utilize the data’s inherent a priori information as a supplement to the supervisory information. The experimental results show that our approach achieves a recognition performance of 70.867% under the three-way one-shot condition, which attains a minimum improvement of 7.467% compared to five state-of-the-art one-shot learning methods. The ablation studies demonstrate the efficacy of each design introduced in our model.
Hydrogen fuel cell and photovoltaic panel are ideal energy devices. If they are to be used in ships, it is necessary to select and simulate the relevant parameters, and calculate and match the power output. In this paper, aiming at the aspects of power matching, parameter selection and design synthesis of hydrogen light ship, which are less studied in China and relatively weak in related technology, taking safety and real ship realizability as the premise of system design, the theoretical value calculation and model establishment are carried out, the feasibility of design is determined by theoretical calculation, and the Simulink is constructed according to the output characteristics of the actual module Finally, through simulation analysis, the output characteristic curve meets the requirements of the actual ship. On this basis, a set of marine hydrogen photodynamic system is designed according to the engineering standards, in order to make some technical breakthroughs in the four aspects of marine use, integration, safety and efficiency.
This project designs an intelligent banking management system.The essence of intelligent management system is an intelligent information management system based on computer technology, communication technology, sensing technology, automatic control technology and video technology.It integrates the information and communication of the entrance to the bank building, the bank staff and the security department into one network, and introduces the database of dangerous goods and dangerous people.This system is the precise processing center of K210 and other rough processing modules, which will be connected with the police command center. The network will become an important security guarantee means to prevent the bank from being invaded illegally, and effectively protect the personal and property safety of customers. At the same time, in addition to the function of risk control, the system can also import the customer database, realize the customer can enjoy the exclusive service at the door, effectively improve the customer experience.