Malicious Synchrophasor Detection Based on Highly Imbalanced Historical Operational Data

By maliciously manipulating the synchrophasors produced by phasor measurement units in power systems,cyber attackers can mislead the control center into taking wrong actions.From the viewpoint of machine learning,normal and malicious synchrophasors may exhibit different spatial distribution characteristics when mapped into a latent space.Hence,a malicious synchrophasor detector can be acquired by training a classification model with instances derived from historical operational synchrophasor data.However,malicious synchrophasors occur infrequently in practice.It is likely to incur a great deal of effort and may even introduce inevitable experience errors when extracting and labeling a sufficient number of malicious synchrophasors from historical operational data for training.For most existing detectors,if they are directly trained with highly imbalanced datasets,their performances may severely deteriorate.In this paper,a novel type of malicious synchrophasor detector is developed based on a combinatorial use of data rebalancing,Bagging-based ensemble learning,and the widely recognized eXtreme Gradient Boosting(XGBoost)classifier.Experiments show that although fewer malicious instances are provided,the proposed detector is still capable of detecting malicious synchrophasors.

Fibrinolytic Evaluation of Compounds Isolated from a Marine Fungus Stachybotrys Iongispora FG216

As a part of our continuing work to discover bioactive leading molecules from marine microorganism, ethyl acetate fraction of organic extract of the train Stachybotrys longispora FG216 showed fibrinolytic activity in our primary screen. The bioassay-guided purification of the active fractions resulted in isolation of a new isoindolone, FGFC2 （1） （FGFC2, Fungi fibrinolytic compound 2）, together with two known compounds, LL-Zl272β （2） and ergosterol （3）. The structure of compound 1 was elucidated by the spectral analysis of 1D （^1H, ^13C） NMR, 2D （COSY, HSQC, and HMBC） and ESI-MS. Three compounds were evaluated for fibrinolytic activities in vitro. Compared to FGFC1 （EC50=47 μmol/L） as a reference drug, compound 1 and ergosterol （3） showed moderate fibrinolytic activities in vitro with EC50 values of 108.16 and 156.30 μmol/L, respectively. LL-Z127213 （2） had no fibrinolytic activity.

Identification and Fibrinolytic Evaluation of an Isoindolone Derivative Isolated from a Rare Marine Fungus Stachybotrys Iongispora FG216

An isoindolone derivative, Fungi fibrinolytic compound （R）-2,5-bis（（2R,3R）-2-（（E）-4,8-dimethylnona-3,7-dien- 1-y1）-3,5-dihydroxy-2-methy--7-oxo-3,4,7,9-tetrahydr pyrano[2,3-e]isoindol-8（2H）-yl）pentanoic acid （FGFC1, Fungi fibrinolytic compound 1）, was isolated from a rare marine microorganism strain Stachybotrys longispora FG216. The structure of FGFC1 was elucidated by 1H NMR, 13C NMR, IR, and MS data; moreover, it was also evaluated for fibrinolytic activity in vitro and in vivo. The results showed that 0.1--0.4 mmol/L of FGFC1 could stimulate generation of plasmin activity （increased by 2.05--11.44 folds） by measuring Glu-plasminogen and Lys-plasminogen activation in vitro. The experiment of fluorescein isothiocyanate （FITC）-fibrinogen degradation indicated that the effect of FGFCI on fibrinolytic activity was mediated by plasminogen and scuPA. In addition, FGFC 1 （10 mg/kg） could dissolve most of pulmonary thrombus of Wistar rat in vivo. It is possible that FGFC 1 is a potential thrombolytic agent in the future.