Suchergebnisse

AbstractAccording to the principle of total entropy change of dissipative structure, the carbon trading market is defined as a nonlinear complex system that follows the law of entropy increase in this paper. Based on the potential function of sudden change theory, this paper studies the risk point and scale of the carbon trading market. The results show that (1) the theory of dissipative structure and catastrophe theory can be used as the theoretical basis of carbon financial market risk research, and its core technology can be used to measure and predict risks. (2) The risk mutation point measurement model based on the total entropy change principle and potential function technology effectively detected 16 major risk mutation points in the financial crisis, the European debt crisis, and the European new energy efficiency plan. The empirical test shows that the model has a good ability to capture abrupt changes and prediction accuracy. The fitting effect is very good. (3) The risk index value of the risk abrupt point can be calculated effectively by the risk scale measurement technique based on information entropy and the potential function surface equation. Furthermore, we judge the degree and grade of risk. From 2008 to 2021, amongst the 16 risk mutation points in the EU carbon trading market, there are three extremely high risk mutation points, seven high-risk mutation points, two medium-risk mutation points, two low-risk mutation points, and two very low risk mutation points. High risk or above grade accounted for 62.5%. Empirical analysis supports this conclusion.

Ship detection plays a significant role in military and civil fields. Although some state-of-the-art detection methods, based on convolutional neural networks (CNN) have certain advantages, they still cannot solve the challenge well, including the large size of images, complex scene structure, a large amount of false alarm interference, and inshore ships. This paper proposes a ship detection method from optical remote sensing images, based on visual attention enhanced network. To effectively reduce false alarm in non-ship area and improve the detection efficiency from remote sensing images, we developed a light-weight local candidate scene network([Formula: see text] CSN) to extract the local candidate scenes with ships. Then, for the selected local candidate scenes, we propose a ship detection method, based on the visual attention DSOD(VA-DSOD). Here, to enhance the detection performance and positioning accuracy of inshore ships, we both extract semantic features, based on DSOD and embed a visual attention enhanced network in DSOD to extract the visual features. We test the detection method on a large number of typical remote sensing datasets, which consist of Google Earth images and GaoFen-2 images. We regard the state-of-the-art method [sliding window DSOD (SW+DSOD)] as a baseline, which achieves the average precision (AP) of 82.33%. The AP of the proposed method increases by 7.53%. The detection and location performance of our proposed method outperforms the baseline in complex remote sensing scenes.