Network Intrusion Detection System (NIDS) is a key security device in modern networks to detect malicious activities. However, the problem of imbalanced class associated with intrusion detection ...dataset limits the classifier’s performance for minority classes. To improve the detection rate of minority classes while ensuring efficiency, we propose a novel class imbalance processing technology for large-scale dataset, referred to as SGM, which combines Synthetic Minority Over-Sampling Technique (SMOTE) and under-sampling for clustering based on Gaussian Mixture Model (GMM). We then design a flow-based intrusion detection model, SGM-CNN, which integrates imbalanced class processing with convolutional neural network, and investigate the impact of different numbers of convolution kernels and different learning rates on model performance. The advantages of the proposed model are verified using the UNSW-NB15 and CICIDS2017 datasets. The experimental results show that i) for binary classification and multiclass classification on the UNSW-NB15 dataset, SGM-CNN achieves a detection rate of 99.74% and 96.54%, respectively; ii) for 15-class classification on the CICIDS2017 dataset, it achieves a detection rate of 99.85%. We compare five imbalanced processing methods and two classification algorithms, and conclude that SGM-CNN provides an effective solution to imbalanced intrusion detection and outperforms the state-of-the-art intrusion detection methods.
Self-lubricating polymer composite coatings, with tailorable tribological and mechanical properties, have been widely employed on mechanical parts to reduce friction and wear, which saves energy and ...improves the overall performance for applications such as aerospace satellite parts, shafts, gears, and bushings. The addition of functional fillers can overcome the limitations of single-polymer coatings and extend the service life of the coatings by providing a combination of low friction, high wear resistance, high load bearing, high temperature resistance, and high adhesion. This paper compares the heat resistance, and the tribological and mechanical properties of common polymer matrices, as well as the categories of functional fillers that improve the coating performance. Applicable scopes, process parameters, advantages, and limitations of the preparation methods of polymer coatings are discussed in detail. The tribological properties of the composite coatings with different matrices and fillers are compared, and the lubrication mechanisms are analyzed. Fillers reduce friction by promoting the formation of transfer films or liquid shear films. Improvement of the mechanical properties of the composite coatings with fillers of different morphologies is described in terms of strengthening and toughening mechanisms, including a stress transfer mechanism, shear yielding, crack bridging, and interfacial debonding. The test and enhancement methods for the adhesion properties between the coating and substrate are discussed. The coating adhesion can be enhanced through mechanical treatment, chemical treatment, and energy treatment of the substrate. Finally, we propose the design strategies for high-performance polymer composite coating systems adapted to specific operating conditions, and the limitations of current polymer composite coating research are identified.
Label flipping attack is a poisoning attack that flips the labels of training samples to reduce the classification performance of the model. Robustness is used to measure the applicability of machine ...learning algorithms to adversarial attack. Naive Bayes (NB) algorithm is a anti-noise and robust machine learning technique. It shows good robustness when dealing with issues such as document classification and spam filtering. Here we propose two novel label flipping attacks to evaluate the robustness of NB under label noise. For the three datasets of Spambase, TREC 2006c and TREC 2007 in the spam classification domain, our attack goal is to increase the false negative rate of NB under the influence of label noise without affecting normal mail classification. Our evaluation shows that at a noise level of 20%, the false negative rate of Spambase and TREC 2006c has increased by about 20%, and the test error of the TREC 2007 dataset has increased to nearly 30%. We compared the classification accuracy of five classic machine learning algorithms (random forest(RF), support vector machine(SVM), decision tree(DT), logistic regression(LR), and NB) and two deep learning models(AlexNet, LeNet) under the proposed label flipping attacks. The experimental results show that two label noises are suitable for various classification models and effectively reduce the accuracy of the models.
Luminescent probes have wide applications in biological system analysis and environmental science. Here, one novel luminescent dinuclear europium compound with a crown ether analogous ligand was ...synthesized through a solvent–thermal reaction. Through transformation, upon the addition of Al3+ ions to the N,N′-dimethyl formamide solution of the europium compound, the luminescent intensity of the characteristic emission of Eu3+ decreased, and a new emission peak appeared at 346 nm and increased rapidly. The luminescent investigation indicated that it could act as a highly sensitive and selective luminescent probe for Al3+ ions. Moreover, mass spectrometry and single-crystal X-ray diffraction confirmed the formation of a new more stable trinuclear aluminium compound during the sensing process.
In this study, we demonstrate the structural evolution of a two-dimensional (2D) supramolecular assembly system, which is steered by the thermally activated deprotonation of the primary organic ...building blocks on a Ag(111) surface. Scanning tunneling microscopy revealed that a variety of structures, featuring distinct structural, chiral, and intermolecular bonding characters, emerged with the gradual thermal treatments. According to our structural analysis, in combination with density function theory calculations, the structural evolution can be attributed to the successive deprotonation of the organic building blocks due to the inductive effect. Our finding offers a facile strategy towards controlling the supramolecular assembly pathways and provides a comprehensive understanding of the 2D crystal engineering on surfaces.
Land-cover mapping is important for urban planning and management, and current land-cover mapping products are unable to meet the needs of cities due to frequent land surface changes. In this study, ...based on the L2HNet network, we generate a high-resolution land-cover mapping product for Wuhan and its surrounding areas. In this paper, we adopt a simplified L2HNet by removing the CAS and the L2H loss module to shorten the cycle time of entire mapping process. The mapping process used ESA LandCover (2021) as LR labels and Google Maps as high-resolution remote sensing images. In the course of the experiment, we also calculate the four indicators MIoU, Oa, FWIoU, and Kappa, evaluate the accuracy of our product in predicting fine feature structure using a point-based test method, and compare it with six mainstream land-cover mapping products. The product achieves a 1m-resolution land-cover product in study areas while maintaining an over 75.21% MIoU. Oa, FWIoU and Kappa all maintain values above 85.00%, showing excellent prediction results. In quantitative analysis, compared to ESA LandCover(2021), the L2HNet product has a significant improvement in mapping accuracy for build-up and permanent water, including an exciting 21.08% improvement in permanent water accuracy and an amazing improvement in build-up. The comparison with mainstream products also shows the credibility and practicality of the product. The end result of this research fills a gap in Wuhan and its surrounding areas' 1m-resolution land-cover mapping product. While significantly improving the product's resolution, L2HNet makes time- and labor-saving periodic mapping a reality.
Graphene is a superior active material in energy storages due to its exceptional properties, such as high specific area, high electrical conductivity, and excellent chemical stability. Currently, the ...large-scale preparation of graphene powder constitutes a research hotspot. Usually, the as-prepared graphene powders was used directly leading to poor dispersion which greatly affects the electrode's properties. Thus, one crucial application problem which needs to be solved urgently is how to obtain ultrahigh concentration and stable dispersion of single-layer graphene. Therefore, in this work, we prepared successfully a single-layer reduced graphene oxide (RGO) powder by expansion-oxidation-expansion process. The RGO paste was obtained through high-speed ball-milling technology, offering ultrahigh concentration (27 mg/mL) and high stability. Meanwhile, the above-mentioned paste be combined with LiFePO4 (LFP) towards obtaining cathode materials for Li-ion batteries. LFP@RGO demonstrated an excellent discharge capacity of 168.3 mA h g−1 at 0.1 C, and maintained 99.9% of capacity after 100 cycles at 0.5 C. Herein, we demonstrated an effective way to prepare the ultrahigh concentration, and stable dispersion of single-layer graphene paste in the field of energy storage and conversion.
Display omitted
The label flipping attack is a special poisoning attack in the adversarial environment. The research designed a novel label noise processing framework, the core of which is the semi-supervised ...learning label correction algorithm based on AdaBoost (AdaSSL). It can effectively improve the label quality of training data and improve the classification performance of the model. Based on five real UCI datasets, this study chose six classic machine learning algorithms (NB, LR, SVM, DT, KNN and MLP) as the base classifiers to classify them. With a noise level of 0
∼
20%, we evaluated the classification effect of these classifiers on UCI datasets based on the entropy label flipping attack and the AdaSSL defense algorithm. The experimental results show that the AdaSSL algorithm can effectively improve the robustness of the classifier against label flipping attack. Compared with the most advanced semi-supervised defense algorithm in the literature, the algorithm does not need to use additional datasets. At a noise ratio of 10%, the AdaSSL algorithm is significantly better than state-of-the-art label noise defense technology.
Luminescent probes have wide applications in biological system analysis and environmental science. Here, one novel luminescent dinuclear europium compound with a crown ether analogous ligand was ...synthesized through a solvent-thermal reaction. Through transformation, upon the addition of Alsup.3+ ions to the N,N′-dimethyl formamide solution of the europium compound, the luminescent intensity of the characteristic emission of Eusup.3+ decreased, and a new emission peak appeared at 346 nm and increased rapidly. The luminescent investigation indicated that it could act as a highly sensitive and selective luminescent probe for Alsup.3+ ions. Moreover, mass spectrometry and single-crystal X-ray diffraction confirmed the formation of a new more stable trinuclear aluminium compound during the sensing process.
We have achieved an on‐surface synthesis of giant conjugated macrocycles having a diameter of ≈7 nm and consisting of up to 30 subunits. The synthesis started with a debrominative coupling of the ...molecular precursors on a hot Ag(111) surface, leading to the formation of arched oligomeric chains and macrocycles. These products were revealed by scanning tunneling microscopy in combination with density functional theory to be covalent oligomers. These intermediates also display C–Ag organometallic bonds between parallel molecular subunits due to site‐selective debromination and the asymmetric molecular conformation. Subsequent cyclodehydrogenation at higher temperatures steered the final conjugation of the macrocycles. Our findings provide a novel design strategy toward π‐conjugated macrocycles and open up new opportunities for the precise synthesis of organic nanostructures.
Giant conjugated macrocycles with a diameter of roughly 7 nm consisting of up to 30 subunits were synthesized on a Ag(111) surface in a two‐step reaction. Site‐selective debromination initiated the synthesis, resulting in arched covalent oligomers and macrocycles, which were assisted by C–Ag organometallic bonds between parallel molecular subunits. The subsequent cyclodehydrogenation steered the final conjugation of the macrocycles.