Deep learning has become a research hotspot in the field of network intrusion detection. In order to further improve the detection accuracy and performance, we proposed an intrusion detection model based on improved deep belief network (DBN). Traditional neural network training methods, like Back Propagation (BP), start to train a model with preset parameters such as the randomly initialized weights and thresholds, which may bring some issues, e.g., attracting the model to the local optimal solutions, or requiring a long training period. We use the Kernel-based Extreme Learning Machine (KELM) with the supervised learning ability to replace the BP algorithm in DBN in a bid to ameliorate the situation. Considering the problem of poor classification performance usually caused by randomly initializing kernel parameters with KELM, an enhanced grey wolf optimizer (EGWO) is designed to optimize the parameters of KELM. In order to improve the search ability and optimization ability of the traditional grey wolf optimizer algorithm, a novel optimization strategy combining the inner and outer hunting is introduced. Experiments on KDDCup99, NSL-KDD, UNSW-NB15 and CICIDS2017 datasets show that the proposed DBN-EGWO-KELM algorithm has greater advantages in terms of its accuracy, precision, true positive rate, false positive rate and other evaluation indices compared with BP, RBF, SVM, KELM, LIBSVM, CNN, DBN-KELM and other intrusion detection models, and can effectively meet the requirements of intrusion detection of complex networks.INDEX TERMS Intrusion detection, deep belief network, kernel-based extreme learning machine, grey wolf optimizer.

No abstract

It is of great significance to popularize and apply nanotechnology in forest plantations for the high-quality development of such areas. Camphor trees have good ecological and environmental benefits and are economic, which makes them worthy of widespread popularization and promotion. In this paper, we successfully synthesized bulk and rod-like TiO2 powder and used it to study the influence of camphor seed germination and seedling growth. The germination rate, germination potential, germination index activity index of camphorwood seed during germination were measured by TiO2 solution with different morphology. Meanwhile, the fresh weight, root length and seedling height of seedlings, as well as the activities of CAT, SOD and POD and MDA content in the seedlings were measured in detail. The difference in the promoting effect between bulk and rod TiO2 powder was compared. The possible reasons are also explained. The results showed that bulk and rod-like TiO2 solution improved the activities of SOD, POD and CAT, and increased the resilience of camphor seedlings. Moreover, the rod-like TiO2 solution has a stronger osmotic effect on seed, and has a better effect on promoting seed germination and seedling growth. The study on the influence of nano-TiO2 concentration also further showed that the treatment of nano-TiO2 solution with appropriate concentration could effectively promote seed germination and seedling growth, and enhance its adoptability to adversity; but excessive concentration will bring some side effects, which was not conducive to seed germination and seedling growth. In general, the results of this study provide a theoretical basis and technical guidance for the practical application of nanotechnology in camphor seedling and afforestation production.

No abstract

The ability to effectively detect N-nitrosamine compounds by liquid chromatography–tandem mass spectrometry presents a challenge due to the problems of high detection limits and difficulty in simultaneous N-nitrosamine compound detection. In order to overcome these limitations, this study reduced the detection limit of N-nitrosamine compounds by applying n-hexane pre-treatment to remove non-polar impurities before the conventional process of column extraction. In addition, ammonium acetate was used as the mobile phase to enhance the retention of nitrosamine target substances on the chromatographic column, with formic acid added to the mobile phase to improve the ionization level of N-nitrosodiphenylamine, to achieve the simultaneous detection of multiple N-nitrosamine compounds. Applying these modifications to the established detection method allowed the rapid and accurate detection of N-nitrosamine in water within 12 min. The linear relationship, detection limit, quantification limit and sample spiked recovery rate of nine types of nitrosamine compound were investigated, showing that the correlation coefficient ranged from 0.9985–0.9999, while the detection limits of the instrument and the method were 0.280–0.928 µg·L−1 and 1.12–3.71 ng·L−1, respectively. The spiked sample recovery rate ranged from 64.2–83.0%, with a standard deviation of 2.07–8.52%, meeting the requirements for trace analysis. The method was applied to the detection of N-nitrosamine compounds in nine groundwater samples in Wuhan, China, and showed that the concentrations of N-nitrosodimethylamine and NDEA were relatively high, highlighting the need to monitor water bodies with very low levels of pollutants and identify those requiring treatment.