Search

This study addresses the growing threat of network attacks by exploring their types and analyzing the challenges associated with their precise detection. To mitigate these threats, we propose a novel cyber security approach that integrates Genetic Algorithm (GA) and neural network architecture. The GA is employed for the selection and optimization of attributes that represent DDoS and malware attack features. These optimized features are then fed into a neural network for training and classification. The effectiveness of the proposed approach was evaluated through precision, recall, and F-measure analyses, demonstrating superior detection capabilities for DDoS and malware attacks compared to existing methods. Furthermore, we introduce a hybrid approach that combines Swarm Intelligence (SI) and nature-inspired techniques. The GA is utilized to select features and reduce the dataset size, followed by the application of Discrete Wavelet Transform (DWT) with Artificial Bee Colony (ABC) to further filter irrelevant features. The results show that this hybrid approach significantly enhances the accuracy and efficiency of network attack detection in wide area networks. [ABSTRACT FROM AUTHOR]

In recent years, video surveillance has become an integral part of computer vision research, addressing a variety of challenges in security, memory management and content extraction from video sequences. This paper introduces the Robust Object Detection using Fire Hawks Optimizer with Deep Learning (ROD-FHODL) technique, a novel approach designed specifically for video surveillance applications. Combining object detection and classification the proposed technique employs a two-step procedure. Utilizing the power of the Mask Region-based Convolutional Neural Network (Mask-RCNN) for object detection, we optimize its hyperparameters using the Fire Hawks Optimizer (FHO) algorithm to improve its efficacy. Our experimental results on the UCSD dataset demonstrate the significant impact of the proposed work. It achieves an extraordinary RUNNT of 1.34 s on the pedestrian-1 dataset, significantly outperforming existing models. In addition, the proposed system surpasses in accuracy, with a pedestrian-1 accuracy rate of 97.45% and Area Under the Curve (AUC) values of 98.92%. Comparative analysis demonstrates the superiority of the proposed system in True Positive Rate (TPR) versus False Positive Rate (FPR) across thresholds. In conclusion, the proposed system represents a significant advancement in video surveillance, offering advances in speed, precision and robustness that hold promise for enhancing security, traffic management and public space monitoring in smart city infrastructure and other applications. [ABSTRACT FROM AUTHOR]

The agricultural industry faces significant challenges in improving efficiency and productivity, particularly in monitoring crop health and environmental conditions. Traditional methods are often labor-intensive, timeconsuming, and lack real-time data, leading to suboptimal decision-making. Recent advancements in Internet of Things (IoT) and Artificial Intelligence (AI) technologies offer promising solutions. Long Range (LoRa) communication, a type of low-power wide-area network (LPWAN), enables long-distance data transmission with minimal power consumption, making it ideal for rural and expansive agricultural areas. When combined with deep learning, which can analyze large volumes of data to generate predictive insights, these technologies have the potential to revolutionize agricultural practices by providing farmers with timely and accurate information to optimize crop management and resource utilization. This study introduces an intelligent mote for agricultural applications, leveraging Long Range (LoRa) communication and deep learning techniques to improve precision farming. Traditional agricultural monitoring methods are labor-intensive and lack real-time insights. To address this, the mote is equipped with sensors to monitor temperature, humidity, soil moisture, and light intensity, transmitting real-time data over long distances with minimal power consumption using LoRaWAN. The collected data is processed by deep learning models to predict crop yield and identify potential issues. Field tests demonstrated a 15% improvement in yield prediction accuracy and a 20% reduction in water usage compared to traditional methods. These results highlight the effectiveness of integrating LoRa and deep learning in enhancing agricultural resource management and productivity. [ABSTRACT FROM AUTHOR]

In this paper, cost-effective methods are used to synthesize NiFe2O4 nanoparticles-MoS2 nanosheets with double PEGylation (NIMPI). The preparation strategies were chosen to improve the characteristics and biocompatibility of nickel ferrite and dichalcogenide nanomaterials with polyethylene oxide polymer (PEG) at a low cost. Powder XRD, TEM, and XPS methods were used for structural and morphological research. This nanocomposite was synthesized to investigate the bio-efficacy of anticancer, antioxidant, and antibacterial properties. NIMPI was tested for antiproliferation efficacy in HepG-2 hepatocellular carcinoma (liver cancer) and MCF-7 adenocarcinoma (breast cancer) cell lines. Both HepG-2 along MCF-7 cell lines indicated high cytotoxic potential. SOD and H2O2 antioxidant assays were used to determine toxicity end-points. The strategy for attaining in vitro effectiveness and the key to understanding the unique interaction between PEGylation and ferrite nanoparticles encased in 2D MoS2 nanosheets are demonstrated in this study that gives a strong indication to assist the growth of antimicrobial, antioxidant, and cytotoxicity properties for major biomedical compatibility. [ABSTRACT FROM AUTHOR]

The hot corrosion behaviours of 5-mm-thick plates of dissimilar AISI 904L and Inconel 625 weldments produced by continuous current gas tungsten arc welding process using Ni-Cr-Mo-enriched filler wires (ERNiCrMo-4 and ERNiCrCoMo-1) were investigated. Optical microscopy was used to examine the microstructure of these weldments. The corrosion performance of the weldments and base metals was determined in the mixture of K2SO4 + 60% NaCl molten salt (MS) and air oxidation conditions at 700°C for 50 cycles. The thermogravimetric plots derived the corrosion kinetics of the weldments. The microstructure and the elemental analysis of the scales formed on the corroded samples were evaluated by scanning electron microscopy and energy-dispersive spectroscopy. The phases developed on the oxide layers during the corrosion were analysed using X-ray diffraction. The fusion zones of ERNiCrCoMo-1 weldment and AISI 904L base metal were vulnerable to degradation in the MS environment, causing severe cracks and spallation compared to ERNiCrCoMo-1 weldment. [ABSTRACT FROM AUTHOR]

Biofilms are multi-species bacterial communities with complex structures that create antibiotic resistance, cause life-threatening infections, thereby considerable economic loss; needed new approaches. Medicinal plants are focused as new alternatives for their therapeutic and antimicrobial effects. Our present study, Azadirachta indica, Moringa oleifera, Murraya koenigii, and Psidium guajava extracts were investigated against MRSA. The preliminary antimicrobial study showed pet. ether extract of A. indica and ethanolic extract of P. guajava showed a MIC value of 125 μg/mL and MBC value of 500 μg/mL. These extracts showed biofilm inhibition in the range of 60.0–83.9 % and did not possess any hemolytic activity to the human erythrocytes. The plant species investigated in this study had different degrees of antibiofilm activity against MRSA. However, we suggest that A. indica and P. guajava are promising candidates and further investigation is needed to isolate the antimicrobial compounds for the management of MRSA and its mechanism of activity.

This paper reports the influence of process parameters on the size and distribution of in situ titanium diboride (TiB2) particles within the aluminium (Al) matrix. TiB2 particles were formed as a result of the in situ reaction of potassium hexafluorotitanate (K2TiF6) and potassium tetra fluoroborate (KBF4) with molten Al. Two process parameters, namely, the addition time (AT) and holding time (HT) of precursor salts, were considered. The Al/TiB2 composites were produced by allowing the in situ reaction to occur at various ATs (10, 20, and 30 min) and HTs (20, 30, and 40 min). Results showed that the formation of TiB2 was confirmed by XRD analysis. The microstructure, TiB2 particle size, hardness, yield strength (YS), and ultimate tensile strength (UTS) were strongly affected by the said process parameters. The variations in hardness and UTS were highly consistent with those found in the microstructure of the composites. Compared with the Al parent material, the increase in the average hardness and UTS of the composite were 51% and 44%, respectively. This improvement was achieved for the composite sample fabricated with 20 min of AT and 30 min of HT. At this condition, the composite displayed near-uniform particle distribution.