The emergence of Edge Computing has led to an increasingly intricate and widespread issue of network infiltration in Edge Computing devices. Therefore, it is crucial to explore intelligent, automated, and resilient methods for network intrusion detection. Graph neural network-based techniques for network intrusion detection have been proposed by many scholars recently. However, the graph construction methods of these approaches cannot fully adapt to real network intrusion datasets, leading to problems such as overfitting and insufficient graph information mining. Furthermore, the methods employed in the model training phase are relatively limited, failing to consider the characteristic presence of grouping within networks. These shortcomings result in a lack of high accuracy in intrusion detection systems, especially in multi-class classification scenarios. This research suggests a graph neural network technique based on behavior similarity employing a graph attention network (BS-GAT) to handle the aforementioned problem. To address overfitting and inadequate graph information mining, a behavioral similarity-based graph creation method is first presented through an analysis of real datasets. Subsequently, the inclusion of edge behavioral relationship weights into the GAT leverages the relationship between data flow and graph structural information, enhancing the performance of the trained model. In the final stage, experiments were executed using the most recent datasets to assess the effectiveness of the proposed behavior similarity-based graph attention network in network intrusion detection. The findings indicate that the proposed approach is highly effective and significantly outperforms existing solutions. In binary classification, recall, precision, f1-score, and accuracy all exceed 99%. For multi-class performance, the recognition accuracy exceeds 93%, the weighted recall surpasses 91%, and the weighted f1-score exceeds 92%, showing a substantial improvement in multi-class recognition effectiveness.
The impact of manufacturing transfer in Jiangsu province, China, on the spatial-temporal variations of SO2 emissions is investigated using estimated sector-specific SO2 emissions, and emissions in the different transfer-in and transfer-out regions were quantified during 2000–2011. Our results show that SO2 emissions had undergone three phases: an increase in the period of 2000–2005, a rapid decline in 2005–2008 and a slow decline in 2008–2011. Emissions from the south dominated the total emissions in the province. Cleaner production generally contributed to the reduced emissions, but rather, at the industrial scale. Pollution abatement was occasional and industrial structure was negligible in some years. The three phases also coincided with the three periods of the manufacturing transfer: transferred to the south from outside the province during 2000–2005, to the central from the south within the province during 2005–2008 and to the north from the south or partly from the inner central within the province during 2008–2011. With the manufacturing transfer, SO2 emission magnitudes and distributions were also changed. In the south, −12.36 and −5.62 Mt of SO2 emissions were transferred out during 2005–2008 and 2008–2011, respectively. Forty-three-point-four percent and 56.4% of the SO2 emissions in the south were transferred to the central and north during 2005–2008, respectively. The north region received 77.7% and 22.1% of SO2 emissions from the south and the central region during 2008–2011, respectively. The paper reveals that structure adjustments should be executed in a timely manner in the manufacturing transfer-in process so that the transfer-in regions can benefit from the economic boom without bearing a deteriorated environment.