Affected by the Internet, computer, information technology, etc., building a smart city has become a key task of socialist construction work. The smart city has always regarded green and low-carbon development as one of the goals, and the carbon emissions of the auto parts industry cannot be ignored, so we should carry out energy conservation and emission reduction. With the rapid development of the domestic auto parts industry, the number of car ownership has increased dramatically, producing more and more CO2 and waste. Facing the pressure of resources, energy, and environment, the effective and circular operation of the auto parts supply chain under the low-carbon transformation is not only a great challenge, but also a development opportunity. Under the background of carbon emission, this paper establishes a decision-making optimization model of the low-carbon supply chain of auto parts based on carbon emission responsibility sharing and resource sharing. This paper analyzes the optimal decision-making behavior and interaction of suppliers, producers, physical retailers, online retailers, demand markets, and recyclers in the auto parts industry, constructs the economic and environmental objective functions of low-carbon supply chain management, applies variational inequality to analyze the optimal conditions of the whole low-carbon supply chain system, and finally carries out simulation calculation. The research shows that the upstream and downstream auto parts enterprises based on low-carbon competition and cooperation can effectively manage the carbon footprint of the whole supply chain through the sharing of responsibilities and resources among enterprises, so as to reduce the overall carbon emissions of the supply chain system.

The carbon footprint of the cold chain logistics system refers to the greenhouse gas emissions directly or indirectly caused in each link of the cold chain logistics activities. Because cold chain logistics is the main carbon emitter in the field of logistics, research on how to reduce carbon emissions in the field of cold chain logistics plays an important role in energy conservation and emission reduction. Based on the in-depth analysis of the carbon footprint of cold chain logistics, this paper introduces the distance coefficient and freshness parameters into the optimization model innovatively and uses the life cycle assessment method and input-output method to determine the calculation range of the carbon footprint of fresh products of each link in the cold chain logistics. The system calculates the carbon emissions generated by the production and operation activities of each place of origin, distribution center, retailer, and waste disposal during the circulation of fresh products. This paper establishes a carbon footprint optimization model to discuss how to balance carbon constraints and minimized costs. Through the analysis of the simulation results, from the perspective of the government and enterprises, corresponding countermeasures are put forward to more effectively achieve the goal of energy conservation and emission reduction and guide the cold chain logistics industry to sustainable development.

The concept of “green supply chain” puts forward new requirements for the recycling management of waste products. The waste electronic products are taken as the research object, and a two-stage closed-loop supply chain composed of a manufacturer, a retailer, and consumers is considered in this paper. By constructing a Stackelberg game model, the pricing strategy and profit distribution of the supply chain under different decision modes considering asymmetric powers are studied. Finally, Python is used for simulation. The results show that the gross profit of supply chain under decentralized decision is always lower than that under centralized decision-making, and asymmetric power has an impact on the pricing decision-making of forward supply chain and reverse supply chain; compared with transfer cost, wholesale price has a greater impact on coordination effect.

Chest X-ray has become one of the most common ways in diagnostic radiology exams, and this technology assists expert radiologists with finding the patients at potential risk of cardiopathy and lung diseases. However, it is still a challenge for expert radiologists to assess thousands of cases in a short period so that deep learning methods are introduced to tackle this problem. Since the diseases have correlations with each other and have hierarchical features, the traditional classification scheme could not achieve a good performance. In order to extract the correlation features among the diseases, some GCN-based models are introduced to combine the features extracted from the images to make prediction. This scheme can work well with the high quality of image features, so backbone with high computation cost plays a vital role in this scheme. However, a fast prediction in diagnostic radiology is also needed especially in case of emergency or region with low computation facilities, so we proposed an efficient convolutional neural network with GCN, which is named SGGCN, to meet the need of efficient computation and considerable accuracy. SGGCN used SGNet-101 as backbone, which is built by ShuffleGhost Block (Huang et al., 2021) to extract features with a low computation cost. In order to make sufficient usage of the information in GCN, a new GCN architecture is designed to combine information from different layers together in GCNM module so that we can utilize various hierarchical features and meanwhile make the GCN scheme faster. The experiment on CheXPert datasets illustrated that SGGCN achieves a considerable performance. Compared with GCN and ResNet-101 (He et al., 2015) backbone (test AUC 0.8080, parameters 4.7M and FLOPs 16.0B), the SGGCN achieves 0.7831 (−3.08%) test AUC with parameters 1.2M (−73.73%) and FLOPs 3.1B (−80.82%), where GCN with MobileNet (Sandler and Howard, 2018) backbone achieves 0.7531 (−6.79%) test AUC with parameters 0.5M (−88.46%) and FLOPs 0.66B (−95.88%).