Search

Intrusion detection systems play an important role in numerous industrial applications, such as network security and abnormal event detection. They effectively protect our critical computer systems or networks against the network attackers. Anomaly detection is an effective detection method, which can find patterns that do not meet a desired behavior. Mainstream anomaly detection system (ADS) typically depend on data mining techniques. That is, they recognize abnormal patterns and exceptions from a set of network data. Nevertheless, supervised or semi-supervised data mining techniques rely on data label information. This setup may be infeasible in real-world applications, especially when the network data is large-scale. To solve these problems, we propose a novel unsupervised and manifold-based feature selection algorithm, associated with a graph density search mechanism for detecting abnormal network behaviors. First, toward a succinct set of features to describe each network pattern, we realize that these pattern can be optimally described on manifold. Thus, a Laplacian score feature selection is developed to discover a set of descriptive features for each pattern, wherein the patterns’ locality relationships are well preserved. Second, based on the refined features, a graph clustering method for network anomaly detection is proposed, by incorporating the patterns’ distance and density properties simultaneously. Comprehensive experimental results show that our method can achieve higher detection accuracy as well as a significant efficiency improvement.

Objective To investigate the clinical significance of long non-coding RNA LINC01617 in esophageal cancer and explore the effect of LINC01617 on the proliferation and metastasis of esophageal cancer cells. Methods Real time fluorescence PCR was used to detect the expression of LINC01617 in 142 cases of esophageal cancer and adjacent tissues. The relationship between the expression level of LINC01617 and the survival rate of esophageal cancer patients was analyzed. The function of LINC01617 was detected in esophageal cancer cell lines. The tumor growth ability test was carried out in the nude mice. Results We found that LINC01617 was overexpressed in esophageal cancer, and its expression was associated with poor prognosis of esophageal cancer. In vitro experiments confirmed that knockout of LINC01617 significantly inhibited the proliferation, migration and invasion of esophageal cancer cells. Moreover, knockout of LNC01617 can inhibit the growth of esophageal cancer in nude mice. The Akt pathway may be involved in the regulation of cell activity in esophageal cancer. Conclusions LINC01617 may be involved in the occurrence and development of esophageal cancer, suggesting that LINC01617 can be used as a biomarker and potential therapeutic target for esophageal cancer.

Intrusion detection systems play an important role in numerous industrial applications, such as network security and abnormal event detection. They effectively protect our critical computer systems or networks against the network attackers. Anomaly detection is an effective detection method, which can find patterns that do not meet a desired behavior. Mainstream anomaly detection system (ADS) typically depend on data mining techniques. That is, they recognize abnormal patterns and exceptions from a set of network data. Nevertheless, supervised or semi-supervised data mining techniques rely on data label information. This setup may be infeasible in real-world applications, especially when the network data is large-scale. To solve these problems, we propose a novel unsupervised and manifold-based feature selection algorithm, associated with a graph density search mechanism for detecting abnormal network behaviors. First, toward a succinct set of features to describe each network pattern, we realize that these pattern can be optimally described on manifold. Thus, a Laplacian score feature selection is developed to discover a set of descriptive features for each pattern, wherein the patterns’ locality relationships are well preserved. Second, based on the refined features, a graph clustering method for network anomaly detection is proposed, by incorporating the patterns’ distance and density properties simultaneously. Comprehensive experimental results show that our method can achieve higher detection accuracy as well as a significant efficiency improvement.