Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence最新文献

{"title":"An Effective Software Vulnerability Detection Method Based On Devised Deep-Learning Model To Fix The Vague Separation","authors":"Yuankun Liu, Yu Wang","doi":"10.1145/3598438.3598452","DOIUrl":"https://doi.org/10.1145/3598438.3598452","url":null,"abstract":"SVD(Software Vulnerability Detection) methods based on automated deep learning is critical in software safety, they are designable and promising. Several function-level deep-learning SVD methods achieve an accuracy of up to 0.97 on open-source C/C++ datasets. However, as vulnerable samples have a low proportion in existing open-source datasets, these methods suffer from high false negative rate, they fail to identify cross-domain software vulnerabilities for neglecting the imbalance and vague separation of existing datasets. This paper proposes a novel framework based on the SeqGAN and TextCNN to fix the vague separation of aggregated 7 open-source C/C++ datasets, therefore improving the performance of SVD. As a result, SeqGAN&TextCNN scores 0.9385 of F1 score, compared with merely adopting the TextCNN, the method achieves an increase of 119% in recall and 31.31% in precision, and from the separations plotted by t-SNE, SeqGAN effectively improves the separation of original datasets. SeqGAN&TextCNN detects more vulnerable samples with low false negative rate, the method’ s F1 score is 79.58% higher than that of leveraging the VulDeePecker on 7 open-source C/C++ datasets.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121646031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on the Construction of E-learning Information Ecosystem Based on Explanatory Structural Model","authors":"L. Ye, Min Chen, Jiaxin Cui","doi":"10.1145/3598438.3598442","DOIUrl":"https://doi.org/10.1145/3598438.3598442","url":null,"abstract":"The online learning information ecosystem gives full play to the advantages of electronic education, makes full use of educational resources, and maximizes the value of educational resources. In this paper, from the four dimensions of educators, educators, online teaching content and online teaching environment, this paper establishes 20 influencing factors for the stable operation of university network education information ecosystem. And by using the interpretive structural model method, the relationship between any two influencing factors is determined, the adjacency matrix is constructed, the reachability matrix is calculated by Python software, and then the reachability matrix is decomposed to form the interpretive structural model framework of influencing factors for the stable operation of university network education information ecosystem. On this basis, the influencing factors are defined as three levels. They are surface layer, middle layer and deep layer, and the interpretive structural model level is analyzed in turn. Finally, it puts forward countermeasures and suggestions to promote the stable operation of university network education information ecosystem, and provides guidance for the sustainable and stable development of university network education information ecosystem.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127727862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on Citizenization of the New Generation of Migrant Workers from the Perspective of Employment Policy Based on Grounded theory and DEA model","authors":"Y. Li, Gong Chen","doi":"10.1145/3598438.3598439","DOIUrl":"https://doi.org/10.1145/3598438.3598439","url":null,"abstract":"Due to the continuous deepening impact of the COVID-19 pandemic on the global economy and the exacerbation of the \"triple overlapping\" situation in China, there has been a significant increase in employment pressure and dynamic changes in a considerable number of migrant workers. This has brought about new situations and problems for the economic and social development of urban and rural areas. The urbanization of rural migrant workers is a systematic project involving multiple sectors and departments such as development and reform, finance, education, housing, human resources, and culture. It requires systematic research and coordinated promotion.This study provides a basic overview of the employment policies for the new generation of migrant workers in China in \"three stages\" and analyzes the main challenges and reasons faced by these workers in terms of employment policies. By summarizing and organizing the employment policies released at the national level in China since 2008, using the grounded theory and data envelopment analysis model, input and output indicators for employment policies and the urbanization of the new generation of migrant workers are deduced and summarized. The data envelopment analysis model is used as an evaluation tool for the efficiency of employment policies in promoting the urbanization of migrant workers. The results show that the employment policies currently implemented in China have played an important role in improving the urbanization of migrant workers, and the degree of urbanization is increasing year by year. The direction of policy formulation and implementation is completely correct, so policy investment should be further increased along the current direction, and policy items should be refined and enriched to further promote the speed and quality of the urbanization of migrant workers.Specifically, the years 2009, 2010, and 2011 were the main periods of analysis. Considering the historical background and employment policies at that time, the economic growth was slow during the post-financial crisis era, and the overall economic environment was depressed. Although the government proposed proactive employment policies in 2008, the actual implementation of these policies lacked clear instructions on how to guarantee the welfare, safety, and other protections for migrant workers in non-standard employment regulated by the market. Therefore, the employment policies in this stage were still in the exploration phase. The overall efficiency showed improvement in 2010 and 2011, mainly driven by market conditions, but the interaction between policy resource input and market factors was relatively weak. Analyzing the efficiency input and output adjustments of employment policies in years where data envelopment analysis was ineffective, it was found that the number of employed and income levels of the new generation of migrant workers reached an optimal state in 2011, aligning with the level of socio-economic develo","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"62 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126075721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ResNet Small Target Detection Algorithm Based on Deep Separable Sonvolution","authors":"Ye Yuan","doi":"10.1145/3598438.3598453","DOIUrl":"https://doi.org/10.1145/3598438.3598453","url":null,"abstract":"Abstract: Because of the poor effect of traditional small target detection, by analyzing the characteristics of small targets, taking RESNET of deep separable convolution as the feature extraction network, a small target detection algorithm based on RESNET of deep separable convolution is proposed. In order to ensure that the network has good adaptability and strong small target feature extraction ability, the algorithm adopts the topology of the multi convolution kernel. The convolution form of the network is improved by packet convolution to reduce the number of network parameters and computation, and the improved channel shuffling is used to enhance the exchange of feature information between different packets and splice the output features. Finally, combined with the residual connection form, a deep separable packet convolution RESNET network (mower) with multiple convolution cores is formed. The experimental results of the DOTA data set show that the Top1 error rate and top5 error rate of the RESNET network based on deep separable convolution are 30.68% and 8.75%, respectively, which is 3.34% and 1.56% lower than that of traditional RESNET network. The complexity of the model is also reduced, which has obvious advantages over other network models.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133268410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}