Multi-Step Attack Detection Based on Pre-Trained Hidden Markov Models.

Currently, hidden Markov-based multi-step attack detection models are mainly trained using the unsupervised Baum-Welch algorithm. The Baum-Welch algorithm is sensitive to the initial values of model parameters. However, its training uses random or average parameter initialization methods, which frequently results in the model training into a local optimum, thus, making the model unable to fit the alert logs well and thereby reducing the detection effectiveness of the model. To solve this issue, we propose a pre-training method for multi-step attack detection models based on the high semantic similarity of alerts in the same attack phase. The method first clusters the alerts based on their semantic information and pre-classifies the attack phase to which each alert belongs. Then, the distance of the alert vector to each attack stage is converted into the probability of generating alerts in each attack stage, replacing the initial value of Baum-Welch. The effectiveness of the proposed method is evaluated using the DARPA 2000 dataset, DEFCON21 CTF dataset, and ISCXIDS 2012 dataset. The experimental results show that the hidden Markov multi-step attack detection method based on pre-training of the proposed model parameters had higher detection accuracy than the Baum-Welch-based, K-means-based, and transfer learning differential evolution-based hidden Markov multi-step attack detection methods.

Prediction Model for Infectious Disease Health Literacy Based on Synthetic Minority Oversampling Technique Algorithm.

Objective: Improving health literacy in infectious diseases is a direct manifestation of the solid advance in disease control and prevention. Our study is aimed at exploring applying synthetic minority oversampling technique (SMOTE) in the prediction assessment of whether residents and business employees have infectious disease health literacy. Methods: The Chinese resident infectious disease health literacy evaluation scale was used to investigate the associated variables. The screened variables were input variables and the presence or absence of infectious diseases health literacy as outcome variables. Logistic regression, random forest, and support vector machine (SVM) models were built in the data sets before and after treatment by the SMOTE algorithm, respectively, and the performance of the models was evaluated by receiver operating characteristic curves (ROC). Results: Logistic regression, random forest, and SVM achieved accuracies of 0.828, 0.612, and 0.654 before SMOTE algorithm processing, and the areas under the ROC curves (AUCs) of the three models were 0.754, 0.817, and 0.759, respectively. The accuracies were 0.938, 0.911, and 0.894 after SMOTE algorithm processing, and the AUCs of the three models were 0.913, 0.925, and 0.910, respectively. Conclusions: The random forest model based on the SMOTE has high application value in assessing whether residents versus enterprise employees have infectious disease health literacy.

Several carbon-coated Ga2O3 anodes: efficient coating of reduced graphene oxide enhanced the electrochemical performance of lithium ion batteries.

Gallium oxide as a novel electrode material has attracted attention because of its high stability and conductivity. In addition, Ga2O3 will be converted to Ga during the charge and discharge process, and the self-healing behavior of Ga can improve the cycling stability. In this paper, we synthesized Ga2O3 nanoparticles with a size of about 4 nm via a facile sol-gel method. Meanwhile, we employed three types of carbon materials (reduced graphene oxide, mesoporous carbon nanofiber arrays, and carbon nanotubes) to avoid the aggregation of Ga2O3 nanoparticles and improve the conductivity of Ga2O3 during the discharge/charge process as well. Among the three samples, the deactivating defective sites and special carbon matrix of reduced graphene oxide can provide more attachment points for Ga ions, so the Ga2O3 nanoparticles can be more closely and uniformly distributed on rGO. Benefitting from the perfect combination of reduced graphene oxide sheets and Ga2O3 nanoparticles, a stable capacity of the Ga2O3/rGO electrode can be maintained at 411 mA h g-1 at a current density of 1000 mA g-1 after 600 cycles. We believe that this work provides a novel and efficient way to improve the electrochemical stability of Li-ion batteries.

A novel Zr-MOF-based and polyaniline-coated UIO-67@Se@PANI composite cathode for lithium-selenium batteries.

In this work, we synthesized a novel UIO-67@Se@PANI composite cathode material for Li-Se battery applications. Zr-MOFs (metal organic frameworks) were used as a support and a PANI (polyaniline) layer was employed as the coating. UIO-67@Se@PANI was expected to be one of the candidates for Li-Se batteries, with a high specific capacity of 248.3 mA h g-1 at 1C (1C = 675 mA g-1) after 100 cycles. In particular, stable capacities of 203.1 and 167.6 mA h g-1 were received after 100 cycles at high rates of 2C and 5C, respectively. To explain such a good electrochemistry performance of the composite cathode material, multiple characterization methods were carried out. And that can be attributed to the sandwich-like structure of the UIO-67@Se@PANI composite and the fact that UIO-67 can provide unsaturated sites to tether the selenium effectively and the PANI layer can improve the electronic conductivity of the whole electrode significantly.

One-step synthesis of MOF-derived Ga/Ga2O3@C dodecahedra as an anode material for high-performance lithium-ion batteries.

A Ga/Ga2O3@C dodecahedron composite with a high specific capacity of about 542 mA h g-1 after 200 cycles at the current density of 1000 mA g-1 was synthesized by one-step hydrogen reduction. This hierarchical homogeneous structure combined the Ga, Ga2O3 and carbon frameworks (from Ga-MOF) to exhibit excellent electrochemical performance.

Bi2S3/C nanorods as efficient anode materials for lithium-ion batteries.

Bi2S3 is a promising negative electrode material for lithium storage owing to its high theoretical capacity. Nevertheless, the capacity of Bi2S3 decays very rapidly upon Li cycling. Here, Bi2S3 and Bi2S3/C were successfully synthesized by a novel route. Sulfur powder as a kind of sulfur source reacted with a metal organic framework based on bismuth and trimesinic acid-Bi(BTC)(DMF)·DMF·(CH3OH)2 (denoted as Bi-BTC). Trimesic acid further acted as a new type of carbon source to synthesize the Bi2S3/C composite. The particle sizes of the composite were smaller than those of pure Bi2S3, showing the suppression of Bi2S3 aggregation. Charge-discharge performance and cyclability for both the Bi2S3 and Bi2S3/C composites in lithium-ion batteries were measured. Specifically, the specific capacities of Bi2S3/C and Bi2S3 reached 765 and 603 mA h g-1, respectively, at 100 mA g-1 after 100 cycles. Because of its high capacity and excellent cycle life, Bi2S3/C is a promising energy storage material.