Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
4,993
result(s) for
"Sumathi, S."
Sort by:
Recurrent and Deep Learning Neural Network Models for DDoS Attack Detection
Distributed denial of service (DDoS) attack is a subclass of denial of service attack that performs severe attack in a cloud computing environment. It makes a malicious attempt to disturb the usual services of any network or server by using botnets. Hence, an efficient intrusion detection system (IDS) is essential to detect this attack. Some limitations in the existing IDS models for DDoS attack detection are delayed convergence, local stagnation issues, and local and global optimal trapping issues. These limitations are met by the recurrent neural network (RNN) and deep learning- (DL-) based proposed models that can utilize the previous states of the hidden neuron. The proposed research has used a long short-term memory (LSTM) recurrent neural network and autoencoder- and decoder-based deep learning strategy with gradient descent learning rule. The network parameters like weight vectors and bias coefficient are tuned optimally by employing the proposed a hybrid Harris Hawks optimization (HHO) and particle swarm optimization (PSO) algorithm. The proposed hybrid optimization algorithm selects the essential attributes, and the results obtained confirmed that the proposed LSTM and deep learning model outperformed all other models developed in the literature.
Journal Article
Agaricus Bisporus Mediated Synthesis of Cobalt Ferrite, Copper Ferrite and Zinc Ferrite Nanoparticles for Hyperthermia Treatment and Drug Delivery
A bio approach (mediated by
Agaricus bisporus)
was attempted in the present study to synthesize ferrite nanoparticles MFe
2
O
4
(M = Zn, Cu and Co]. The synthesized ferrites nanoparticles were characterized in terms of variations in the crystallinity, dimension and sizes using standard techniques (XRD, FTIR, SEM-EDAX, Zeta potential and DLS). VSM analysis showed noticeable differences in the magnetic saturation values: zinc ferrite (12.5 emu/g); cobalt ferrite (27.5 emu/g) and copper ferrite (21.5 emu/g).
In- vitro
cytotoxic effect of the synthesised ferrite nanoparticles resulted in effective inhibition of colon cell line growth (SW620). The ferrite nanoparticles were also evaluated for their drug-release behaviour using doxorubicin (DOX). The results indicated that the maximum DOX delivery was 98.74% using zinc ferrite, 97.34% using cobalt ferrite and 99.52% using copper ferrite within 6 h using 10 mg of nanoparticles. From the hyperthermia results, a SAR of 337 W/g was noted using 10 mg of copper ferrite nanoparticles at an applied frequency of 335 kHz and magnetic field strength of 235 A/m.
Journal Article
Multi-Functional Biological Effects of Palladium Nanoparticles Synthesized Using Agaricus bisporus
The present study deals with the biosynthesis of palladium nanoparticles (PdNPs) using
Agaricus bisporus
and exploring its potential biological applications. The synthesized PdNPs were characterized by UV–visible, FTIR and XRD techniques. Microscopic analyses revealed the triangular (SEM and AFM) and spherical (TEM) morphologies of the nanoparticles with nanosize dimension ranging from 13 to 18 nm. The surface charge of the PdNPs were identified with the help of zeta potential and found to be negatively charged (− 24.3 mV). The PdNPs exhibited good antioxidant effect against DPPH free radicals with maximum radical scavenging activity of 77% using 50 μg/ml. FTIR spectra of the final DPPH solution depicted sharp intense signals at 1018 cm
−1
(polysaccharides) and 3342 cm
−1
(phenolic acids) evidencing the role of these bio functional groups in neutralizing the free radicals. Antibacterial assay revealed that PdNPs exhibited enhanced growth inhibition effect against gram positive bacteria (
S. auerus
;
S. pyrogens
;
B. subtilis
) than gram negative bacterial pathogens (
E. aerogenes
;
K. pneumoniae
;
P. vulgaris
). Anti-inflammatory activity performed with RBC cells showing 87% of activity for biosynthesized PdNPs. MTT assay demonstrated that PdNPs exhibited excellent cytotoxic effect against PK13 cell lines. Maximum growth inhibition of 79% was observed for the maximum dose (50 µg/ml) with IC50 value of 26.1 µg/ml.
Journal Article
Automata Based Hybrid PSO–GWO Algorithm for Secured Energy Efficient Optimal Routing in Wireless Sensor Network
The main objective in wireless sensor networks is to exploit efficiently the sensor nodes and to prolong the lifetime of the network. The discussion of energy is a significant concern to extend the lifetime of the network. Moreover, a nature inspired hybrid optimization approach called hybrid Particle Swarm Optimization–Grey Wolf Optimizer (PSO–GWO) is used in this work to efficiently utilize the energy and to transmit the data securely in an augmented path. A Learning Dynamic Deterministic Finite Automata (LD
2
FA) has been innovated and initiated to learn the dynamic role of the environment. LD
2
FA is mainly used to provide the learned and accepted string to hybrid PSO–GGWO so that the routes are optimized. Hybrid PSO–GWO is used to choose the optimal next node for each path to obtain the optimal route. The simulation results are obtained in MATLAB for 100–700 sensor nodes in a region of 500 × 500 m
2
which demonstrate that the proposed LD
2
FA based Hybrid PSO–GWO algorithm obtains better results when compared with existing algorithms. It is observed that LD
2
FA based Hybrid PSO–GWO has an increase of 18% and 48% betterment in lifetime of the network than PSO and GLBCA, nearly 57% and 75% increase in network lifetime when compared with GA and LDC respectively. It also shows an improvement of 24% increase compared to cluster-based IDS, nearly a rise of 90% throughput when compared with lightweight IDS. The consumption of energy is reduced by 13% and 15% than PSO and GA and an increase of 15% utilization of energy than LDC. Therefore, LD
2
FA based Hybrid PSO–GWO is been considered to efficiently utilize energy in an optimal route.
Journal Article
Weather-driven groundnut price forecasting and profitability assessment of cropping patterns in Tamil Nadu using boosting algorithms
This research explores the integration of weather-based forecasting and profitability analysis to optimize groundnut-based cropping patterns in Tamil Nadu. Groundnut, a crucial oilseed crop, is significantly influenced by weather variability, which impacts its price and profitability. The study leverages advanced boosting algorithms, including Light Gradient Boost, XGBoost, HistGradientBoosting, and CatBoost, to forecast groundnut prices using a multivariate approach that incorporates weather parameters like Minimum and Maximum Temperature, Relative Humidity and Rainfall. Weather parameters were discretized using
-means clustering. Crop prices were decomposed using Seasonal-Trend decomposition based on LOESS and each component was forecasted separately. HistGradientBoosting consistently outperforms other models, achieving the lowest multivariate Mean Absolute Error (MAE) across most crops and districts, underscoring its capability to handle complex, high-dimensional data effectively. The results reveal a substantial improvement in forecasting accuracy with multivariate models compared to univariate ones, establishing the importance of integrating weather features. Groundnut-related cropping patterns were analyzed for profitability using forecasted prices, with patterns involving high-value crops, such as onion in Namakkal, achieving the highest benefit-cost ratio (BCR) of 2.18. Patterns involving black gram also consistently outperformed green gram in economic efficiency. The findings emphasize the need for region-specific, weather-informed cropping strategies to maximize returns for farmers while mitigating risks.
Journal Article
Synthesis, characterization, optical and photocatalytic activity of yttrium and copper co-doped zinc ferrite under visible light
In this study, yttrium doped zinc ferrite (ZnFe
2−
x
Y
x
O
4
x
= 0.01–0.1) and yttrium and copper co-doped zinc ferrite (Cu
y
Zn
1−
y
Fe
2−
x
Y
x
O
4
x
= 0.1 and
y
= 0.5) were synthesized by solution combustion method. The synthesized nanoparticles were authenticated by various techniques such as X-ray diffraction (XRD), Fourier transform infrared spectroscopy (FTIR), scanning electron microscopy–energy dispersive X-ray analysis (SEM-EDAX) and UV–visible spectroscopy. The photocatalytic activity of synthesized nanoparticles was studied by performing the degradation of methylene blue (MB) under visible light. 95% of MB was degraded in 180 min using yttrium-doped zinc ferrite. 89% of MB was degraded in 30 min using copper and yttrium co-doped zinc ferrite under visible light using 10 mg of the catalyst and 50 µl of hydrogen peroxide. Photocatalytic degradation of colorless pollutant bisphenol A also carried out using the doped zinc ferrite.
Journal Article
PSO based power allocation in multiuser hybrid beamforming mmWave NOMA
Non-Orthogonal Multiple Access (NOMA) is one of the blooming technologies in 5G and beyond wireless networks to support a massive number of users with a huge data rate. In this work, we investigate a multiuser hybrid beamforming millimeter wave (mmWave) downlink NOMA system. Wideband mmWave line of sight (LOS) channel and non-line of sight (NLOS) channels are considered in this study. The first step of the multiuser power allocation problem is user clustering, where users are clustered based on their channel correlation and difference. Subsequently, low complex analog beamforming design and zero forcing digital beamforming design are employed. Finally, we formulate users’ power allocation problem with the objectives of spectral efficiency maximization / energy efficiency maximization based on the constraints of users’ quality of service requirements (QoS) and total available power. Existing research solves the non-convex problem by assuming equal power to all the clusters. Then the problem is decomposed into sub-problems and independently solved for each cluster, which increases the complexity. But, we propose a particle swarm optimization (PSO) based single step low complex algorithm, which achieves a faster convergence rate and grants consistent results. Moreover, the simulation results show that our proposed approach outperforms existing sub-optimal method and the conventional zero forcing time division multiple access scheme (ZF-TDMA).
Journal Article
Structural, magnetic, electrical and catalytic activity of copper and bismuth co-substituted cobalt ferrite nanoparticles
Cobalt ferrite, copper and bismuth co-substituted cobalt ferrite nanoparticles are prepared by solution combustion method. The synthesized compounds are authenticated by powder X-ray diffraction, Fourier transform infrared spectroscopy, Scanning electron microscopy-Energy dispersive X-ray analyser and Vibrating sample magnetometer. Particle size, lattice parameter, saturation magnetization and coercivity as a function of bismuth and copper substitution in cobalt ferrite nano particles are studied. Lattice parameter and dielectric constant are increased due to the substitution of bismuth in cobalt ferrite. Catalytic activity of the synthesized compounds are tested for the reduction of 4-nitrophenol (4-NP) to 4-aminophenol (4-AP). The conversion of nitrophenol to amino phenol is achieved in seconds using the substituted cobalt ferrite compounds.
Journal Article