An Intelligent Agent-Based Detection System for DDoS Attacks Using Automatic Feature Extraction and Selection.

Distributed Denial of Service (DDoS) attacks, advanced persistent threats, and malware actively compromise the availability and security of Internet services. Thus, this paper proposes an intelligent agent system for detecting DDoS attacks using automatic feature extraction and selection. We used dataset CICDDoS2019, a custom-generated dataset, in our experiment, and the system achieved a 99.7% improvement over state-of-the-art machine learning-based DDoS attack detection techniques. We also designed an agent-based mechanism that combines machine learning techniques and sequential feature selection in this system. The system learning phase selected the best features and reconstructed the DDoS detector agent when the system dynamically detected DDoS attack traffic. By utilizing the most recent CICDDoS2019 custom-generated dataset and automatic feature extraction and selection, our proposed method meets the current, most advanced detection accuracy while delivering faster processing than the current standard.

CAVVPM: Challenge-Based Authentication and Verification of Vehicle Platooning at Motorway.

As a result of vehicle platooning, advantages including decreased traffic congestion and improved fuel economy are expected. Vehicles in a platoon move in a single line, closely spaced, and at a constant speed. Vehicle-to-vehicle communications and sensor data help keep the platoon formation in place, and the CACC system is responsible for maintaining it. In reality, V2V transmissions are essential for reducing platooning distances while still ensuring their safety and security. It is far more difficult to confirm the veracity of a V2V message's content than it is to verify its integrity and source authentication. Only platoon members can send and receive V2V communications by implementing a practical access control mechanism. The goal is to link a prospective platoon member's digital identification to their actual location inside the unit. A physical challenge-response interaction is used in the CAVVPM process to verify that a prospective platoon member respects the rules. The applicant is asked to perform a series of random longitudinal movements, thus, the protocol's name. Remote attackers cannot join the platoon or send bogus CACC communications because CAVVPM blocks them. CAVVPM is more resistant to pre-recording assaults than previous work, and it can validate that the candidate is precisely behind the verifier in the same lane compared to previous studies.

Melatonin and 14-hydroxyed brassinosteroid combined promote kiwifruit seedling growth by improving soil microbial distribution, enzyme activity and nutrients uptake.

Kiwifruit, a nutrient-dense fruit, has become increasingly popular with consumers in recent decades. However, kiwifruit trees are prone to stunted growth after a few years of planting, called early tree decline. In this study, melatonin (MT), pollen polysaccharide (SF), 14-hydroxyed brassinosteroid (14-HBR) were applied alone or in combination to investigate their influence on plant growth, nutrition absorption and rhizosphere bacterial abundance in kiwifruit seedlings. The results revealed that MT, SF and 14-HBR alone treatments significantly increased leaf chlorophyll content, photosynthetic capacity and activities of dismutase and catalase compared with the control. Among them, MT treatment significantly increased the dry root biomass by 35.7%, while MT+14-HBR treatment significant enhanced the dry shoot biomass by 36.9%. Furthermore, both MT and MT+14-HBR treatments markedly improved the activities of invertase, urease, protease and phosphatase in soil, as well as the abundance of Proteobacteria and Acidobacteria in rhizosphere microorganisms based on 16S rDNA sequencing. In addition, MT treatment improved the content of available K and organic matter in soil, and increased the uptake of P, K and Fe by seedlings. In summary, 14-HBR and MT combined had the best effect on promoting rhizosphere bacterial distribution, nutrient absorption and plant growth. These findings may provide valuable guidance for solving growth weakness problem in kiwifruit cultivation.

Enhanced Adaptability to Limited Water Supply Regulated by Diethyl Aminoethyl Hexanoate (DA-6) Associated With Lipidomic Reprogramming in Two White Clover Genotypes.

Membrane lipid reprogramming is one of the most important adaptive strategies in plant species under unfavorable environmental circumstances. Therefore, the present experiment was conducted to elucidate the effect of diethyl aminoethyl hexanoate (DA-6), a novel synthetic plant growth regulator, on oxidative damage, photosynthetic performance, changes in lipidomic profile, and unsaturation index of lipids in two white clover (Trifolium repens) cultivars (drought-sensitive "Ladino" and drought-resistant "Riverdel") under PEG-6000-induced water-deficit stress. Results revealed that water-deficit stress significantly enhanced oxidative damage and decreased photosynthetic functions in both cultivars. However, the damage was less in Riverdel. In addition, water-deficit stress significantly decreased the relative content of monogalactocyl-diacylglycerols (MGDG), sulfoquinovosyl-diacylglycerols (SQDG), phosphatidic acisd (PA), phosphatidyl-ethanolamines (PE), phosphatidyl-glycerols (PG), phosphatidyl-serines (PS), ceramides (Cer), hexosylmonoceramides (Hex1Cer), sphingomyelins (SM), and sphingosines (Sph) in both cultivars, but a more pronounced decline was observed in Ladino. Exogenous application of DA-6 significantly increased the relative content of digalactocyl-diacylglycerols (DGDG), monogalactocyl-diacylglycerolsabstra (MGDG), sulfoquinovosyl-diacylglycerols (SQDG), phosphatidic acids (PA), phosphatidyl-ethanolamines (PE), phosphatidyl-glycerols (PG), phosphatidyl-inositols (PI), phosphatidyl-serines (PS), ceramides (Cer), hexosylmonoceramides (Hex1Cer), neutral glycosphingolipids (CerG2GNAc1), and sphingosines (Sph) in the two cultivars under water-deficit stress. DA-6-treated Riverdel exhibited a significantly higher DGDG:MGDG ratio and relative content of sphingomyelins (SM) than untreated plants in response to water deficiency. Furthermore, the DA-6-pretreated plants increased the unsaturation index of phosphatidic acids (PA) and phosphatidylinositols (PI) in Ladino, ceramides (Cer) and hexosylmonoceramides (Hex1Cer) in Riverdel, and sulfoquinovosyl-diacylglycerols (SQDG) in both cultivars under water stress. These results suggested that DA-6 regulated drought resistance in white clover could be associated with increased lipid content and reprogramming, higher DGDG:MGDG ratio, and improved unsaturation index of lipids, contributing to enhanced membrane stability, integrity, fluidity, and downstream signaling transduction.

Role of Hybrid Deep Neural Networks (HDNNs), Computed Tomography, and Chest X-rays for the Detection of COVID-19.

COVID-19 syndrome has extensively escalated worldwide with the induction of the year 2020 and has resulted in the illness of millions of people. COVID-19 patients bear an elevated risk once the symptoms deteriorate. Hence, early recognition of diseased patients can facilitate early intervention and avoid disease succession. This article intends to develop a hybrid deep neural networks (HDNNs), using computed tomography (CT) and X-ray imaging, to predict the risk of the onset of disease in patients suffering from COVID-19. To be precise, the subjects were classified into 3 categories namely normal, Pneumonia, and COVID-19. Initially, the CT and chest X-ray images, denoted as 'hybrid images' (with resolution 1080 × 1080) were collected from different sources, including GitHub, COVID-19 radiography database, Kaggle, COVID-19 image data collection, and Actual Med COVID-19 Chest X-ray Dataset, which are open source and publicly available data repositories. The 80% hybrid images were used to train the hybrid deep neural network model and the remaining 20% were used for the testing purpose. The capability and prediction accuracy of the HDNNs were calculated using the confusion matrix. The hybrid deep neural network showed a 99% classification accuracy on the test set data.