Nowadays, we see more and more cyber-attacks on major Internet sites and enterprise networks. Intrusion Detection System (IDS) is a critical component of such infrastructure defense mechanism. IDS monitors and analyzes networks' activities for potential intrusions and security attacks. Machinelearning (ML) models have been well accepted for signaturebased IDSs due to their learnability and flexibility. However, the performance of existing IDSs does not seem to be satisfactory due to the rapid evolution of sophisticated cyber threats in recent decades. Moreover, the volumes of data to be analyzed are beyond the ability of commonly used computer software and hardware tools. They are not only large in scale but fast in/out in terms of velocity. In big data IDS, the one must find an efficient way to reduce the size of data dimensions and volumes. In this paper, we propose novel feature selection methods, namely, RF-FSR (RandomForest-Forward Selection Ranking) and RF-BER (RandomForest-Backward Elimination Ranking). The features selected by the proposed methods were tested and compared with three of the most well-known feature sets in the IDS literature. The experimental results showed that the selected features by the proposed methods effectively improved their detection rate and false-positive rate, achieving 99.8% and 0.001% on well-known KDD-99 dataset, respectively.
GaN is an attractive wide bandgap semiconductor for power applications, owing to its superior electrical properties, such as high critical electric field and saturation drift velocity. Recent advancements in developing native GaN substrates has drawn attention toward exploring vertical GaN power diodes with high breakdown voltages (V BR). In practice, effective edge terminations techniques, such as junction termination extension (JTE) structures, play a crucial role in realizing high-voltage devices. Though certain challenges in fabricating GaN diodes, such as difficulty in forming p-type region, makes it difficult to realize edge termination, hence impeding the development and adoption of such devices. This paper aims to address these challenges by presenting the design and methodology of forming multi-zone, counterdoped JTE structures in vertical GaN diodes, which attains close to theoretical breakdown voltage for a wide range of tolerance in implant dose variation. Extensive device simulations using experimental data and including the effects of surface charges and implant profiles, are performed to present realistic results. The results suggest that >80% of ideal V BR is achievable for a wide range of doping concentration (2.4 × 10 17 cm −3) with a maximum V BR reaching 96% of the ideal value. This paper serves as the first step toward leveraging the current challenges in the fabrication of GaN diodes, by proposing optimum design techniques for realizing vertical GaN diodes with high breakdown voltages. INDEX TERMS GaN, vertical diodes, breakdown voltage, junction edge termination (JTE), counter-doping, partial compensation, multi-zone JTEs (MZJTEs).
Owing to its superior material and electrical properties such as wide bandgap and high breakdown electric field, 4H-silicon carbide (4H-SiC) has shown promise in high power, high temperature, and radiation...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.