In this paper, we propose a new detection method for network anomaly detection, a key problem in the field of cyber security, which combines deep learning feature extraction and DBSCAN clustering algorithm. First, in ...
详细信息
ISBN:
(纸本)9798400716959
In this paper, we propose a new detection method for network anomaly detection, a key problem in the field of cyber security, which combines deep learning feature extraction and DBSCAN clustering algorithm. First, in terms of data processing and feature learning, we employ deep learning models CNN and RNN to automatically extract useful features from complex network traffic data. These advanced features can represent network behavior more accurately and provide richer information for subsequent clustering and anomaly detection. Then, using the DBSCAN algorithm, we can not only effectively identify normal behavioral patterns, but also accurately detect anomalies and potential threats. In the experimental part, by evaluating on the publicly available KDD Cup 99 dataset, the method in this paper demonstrates its superiority in key metrics such as accuracy and recall.
Previous studies on feature extraction techniques frequently depended on converting data straight from high-dimensional regions into low-dimensional subspaces. However, these approaches often struggled to preserve the...
详细信息
Through the exploration of the principle of behavioral decision-making method, we propose an intelligent decision-making framework and design a personalized driving strategy generation model. Combined with big data dr...
详细信息
With the rapid development of information technology today, data is emerging at an unprecedented speed and scale, with diverse forms of existence and extremely wide sources. Especially in the medical field, the comple...
详细信息
In this study, the accuracy of pine wood nematode detection was significantly improved by combining a UAV-mounted multispectral imaging system with machinelearning algorithms, particularly the deep learning models SS...
详细信息
ISBN:
(纸本)9798350386660;9798350386677
In this study, the accuracy of pine wood nematode detection was significantly improved by combining a UAV-mounted multispectral imaging system with machinelearning algorithms, particularly the deep learning models SSD and YOLO v5. The study employed image preprocessing techniques, such as orthorectification and atmospheric correction, to ensure the accuracy and consistency of the data. On this basis, subtle differences in the health status of pine trees were revealed by analysing the spectral features extracted from the multispectral images. Traditional algorithms such as random forest and support vector machine, as well as deep learning models were used for classification and recognition, in which SSD and YOLO v5 demonstrated high accuracy in processing complex image data, reaching 0.92 and 0.93, respectively. This achievement not only improves the detection efficiency of pine wilt disease, but also provides a new technological pathway for forestry health management, which has an early diagnosis and treatment of the disease. important significance for early disease diagnosis and treatment.
This paper mainly introduces some machinelearning methods used in the field of datamining. The method of datamining is discussed by taking market segmentation algorithm as an example. This paper presents an improve...
详细信息
Financial frauds are on the rise globally, causing significant financial losses. This issue has far-reaching consequences, impacting the investment industry, government, and corporate sectors alike. Manual verificatio...
详细信息
Graphs, which encode pairwise relations between entities, are a kind of universal data structure for a lot of real-world data, including social networks, transportation networks, and chemical molecules. Many important...
详细信息
ISBN:
(纸本)9781450394079
Graphs, which encode pairwise relations between entities, are a kind of universal data structure for a lot of real-world data, including social networks, transportation networks, and chemical molecules. Many important applications on these data can be treated as computational tasks on graphs. Recently, machinelearning techniques are widely developed and utilized to effectively tame graphs for discovering actionable patterns and harnessing them for advancing various graph-related computational tasks. Huge success has been achieved and numerous real-world applications have benefited from it. However, since in today's world, we are generating and gathering data in a much faster and more diverse way, real-world graphs are becoming increasingly large-scale and complex. More dedicated efforts are needed to propose more advanced machinelearning techniques and properly deploy them for real-world applications in a scalable way. Thus, we organize The 3rdinternational Workshop on machinelearning on Graphs (MLoG)(1), held in conjunction with the 16th ACM conference on Web Search and datamining (WSDM), which provides a venue to gather academia researchers and industry researchers/practitioners to present the recent progress on machinelearning on graphs.
The widespread use of datamining is a direct result of the practice's first success in more public arenas like marketing, e-commerce, and retail. Discoveries in healthcare are among them. data is abundant in heal...
详细信息
Cluster analysis is an unsupervised machinelearning job of grouping objects based on some similarity measure. Among clustering algorithms, DBSCAN (Density Based Spatial Clustering of Application with Noise) contribut...
详细信息
暂无评论