E-Commerce Credit Risk Assessment Based on Fuzzy Neural Network

In this paper, we propose a cooperative strategy-based self-organization mechanism to reconstruct the network. The mechanism includes a comprehensive evaluation algorithm and structure adjustment mechanism. The self-organization mechanism can be carried out simultaneously with the parameter optimization process. By calculating the similarity and independent contribution of normative neurons, the effectiveness of fuzzy rules can be jointly evaluated, and effective structural changes can be realized. Moreover, this mechanism should not set the threshold in advance in practical application. In order to optimize the parameters of SC-IR2FNN, we developed a parameter optimization mechanism based on an interaction strategy. The parameter optimization mechanism based on a joint strategy, namely multilayer optimization engine, can split SC-IR2FNN parameters into nonlinear and linear parameters for joint optimization. The nonlinear parameters are optimized by an advanced two-level algorithm, and the linear parameters are updated with the minimum biological multiplication. Two parameter optimization algorithms optimize nonlinear and linear parameters, reduce the computational complexity of SC-IR2FNN, and improve the learning rate. Using the principal component factor analysis method, seven representative common factors are selected to replace the original variables, which include the profitability factor of the financing enterprise, the solvency factor of the financing enterprise, the profitability factor of the core enterprise, the operation guarantee factor, and the growth ability of the financing enterprise. Factors, supply chain online degree factors, financing enterprise quality, and cooperation factors, can well measure the credit risk of online supply chains. The logistic model shows that the profitability factor of the financing company, the debt repayment factor of the financing company, and the profitability of the core company are three factors that have a significant impact on the credit risk of online supply chain finance. Based on the improved credit calculation model, we developed an online clue risk calculation. This method is based on site conditions and can evaluate credit risk. From the test results, the improved credit scoring system is the result of facing speculative and circular credit fraud and implies that the traders of risk commentators are in a leading position in each electronic device. The results show that risk analysis is effective in any case.

PQROM: To optimize software defined network QoS-aware routing with proximal policy optimization

Currently, Quality-of-Service (QoS)-aware routing is one of the crucial challenges in Software Defined Network (SDN). The QoS performances, e.g. latency, packet loss ratio and throughput, must be optimized to improve the performance of network. Traditional static routing algorithms based on Open Shortest Path First (OSPF) could not adapt to traffic fluctuation, which may cause severe network congestion and service degradation. Central intelligence of SDN controller and recent breakthroughs of Deep Reinforcement Learning (DRL) pose a promising solution to tackle this challenge. Thus, we propose an on-policy DRL mechanism, namely the PPO-based (Proximal Policy Optimization) QoS-aware Routing Optimization Mechanism (PQROM), to achieve a general and re-customizable routing optimization. PQROM can dynamically update the routing calculation by adjusting the reward function according to different optimization objectives, and it is independent of any specific network pattern. Additionally, as a black-box one-step optimization, PQROM is qualified for both continuous and discrete action space with high-dimensional input and output. The OMNeT ++ simulation experiment results show that PQROM not only has good convergence, but also has better stability compared with OSPF, less training time and simpler hyper-parameters adjustment than Deep Deterministic Policy Gradient (DDPG) and less hardware consumption than Asynchronous Advantage Actor-Critic (A3C).

Active syndromic surveillance of COVID-19 in Israel

Syndromic surveillance systems monitor disease indicators to detect emergence of diseases and track their progression. Here, we report on a rapidly deployed active syndromic surveillance system for tracking COVID-19 in Israel. The system was a novel combination of active and passive components: Ads were shown to people searching for COVID-19 symptoms on the Google search engine. Those who clicked on the ads were referred to a chat bot which helped them decide whether they needed urgent medical care. Through its conversion optimization mechanism, the ad system was guided to focus on those people who required such care. Over 6 months, the ads were shown approximately 214,000 times and clicked on 12,000 times, and 722 people were informed they needed urgent care. Click rates on ads and the fraction of people deemed to require urgent care were correlated with the hospitalization rate ($$R^2=0.54$$ R 2 = 0.54 and $$R^2=0.50$$ R 2 = 0.50 , respectively) with a lead time of 9 days. Males and younger people were more likely to use the system, and younger people were more likely to be determined to require urgent care (slope: $$- \,0.009$$ - 0.009 , $$P=0.01$$ P = 0.01 ). Thus, the system can assist in predicting case numbers and hospital load at a significant lead time and, simultaneously, help people determine if they need medical care.

Effect of Gas-Liquid Contact Intensification on Heat and Mass Transfer in Deflector and Rod Bank Desulfurization Spray Tower

The deflector and the rod bank are commonly used to optimize flue gas distribution in the original spray tower (OST) of a wet flue gas desulfurization system (WFGD). In this paper, the internal optimization mechanism of the deflector desulfurization spray tower (DST) and the rod bank desulfurization spray tower (RBST) are studied. Based on the Euler–Lagrange method, the standard k-ε turbulence model, an SO2 absorption model and a porous media model, the numerical simulation of the desulfurization spray tower is carried out with the verification of the model rationality. The results show that there are gas-liquid contact intensification effects in DST and RBST. Compared with OST, gas-liquid contact intensification enhances the heat and mass transfer effects of DST and RBST. The temperature difference between inlet and outlet of flue gas increased by 3.3 K and the desulfurization efficiency of DST increased by 1.8%; the pressure drop decreased by 37 Pa. In RBST, the temperature difference between the flue gas inlet and outlet increased by 5.3 K and the desulfurization efficiency increased by 3.6%; the pressure drop increased by 33 Pa.

Impact of the “Low-Carbon City Pilot” Policy on Energy Intensity Based on the Empirical Evidence of Chinese Cities

Reducing energy intensity is conducive to the sustainable use of non-renewable fossil energy, and is also one of the main strategies to deal with climate change and environmental degradation. The effect of national macro-level factors on energy intensity has been basically confirmed, but the effect of regional low-carbon policy remains to be investigated. Based on this, our analysis exploits China’s “low-carbon city pilot” policy as a quasi-natural experiment and conducts the difference-in-difference resign. We collect the panel data of 271 cities in China from 2006 to 2016. The empirical results show that: first, the low-carbon city pilot policy can effectively reduce the energy intensity. Second, there exist heterogeneous effects on energy intensity among different cities, and the inhibition effects in eastern cities, high economic development cites, and non-old industrial-base cities are more significant. Third, the policy mainly affects regional energy intensity through technological innovation rather than industrial structure optimization mechanism.