Hybrid CNN-SVM Based Seed Purity Identification and Classification System

Suganthi, M,Sathiaseelan, J.G.R. International Journal of Computer ScienceNetwork S 2022 International journal of computer science and netw Vol.22 No.10

Manual seed classification challenges can be overcome using a reliable and autonomous seed purity identification and classification technique. It is a highly practical and commercially important requirement of the agricultural industry. Researchers can create a new data mining method with improved accuracy using current machine learning and artificial intelligence approaches. Seed classification can help with quality making, seed quality controller, and impurity identification. Seeds have traditionally been classified based on characteristics such as colour, shape, and texture. Generally, this is done by experts by visually examining each model, which is a very time-consuming and tedious task. This approach is simple to automate, making seed sorting far more efficient than manually inspecting them. Computer vision technologies based on machine learning (ML), symmetry, and, more specifically, convolutional neural networks (CNNs) have been widely used in related fields, resulting in greater labour efficiency in many cases. To sort a sample of 3000 seeds, KNN, SVM, CNN and CNN-SVM hybrid classification algorithms were used. A model that uses advanced deep learning techniques to categorise some well-known seeds is included in the proposed hybrid system. In most cases, the CNN-SVM model outperformed the comparable SVM and CNN models, demonstrating the effectiveness of utilising CNN-SVM to evaluate data. The findings of this research revealed that CNN-SVM could be used to analyse data with promising results. Future study should look into more seed kinds to expand the use of CNN-SVMs in data processing.

Effect of Aflatoxin on Feed Conversion Ratio in Broilers: A Meta-analysis

Suganthi, R. Umaya,Suresh, K.P.,Parvatham, R. Asian Australasian Association of Animal Productio 2011 Animal Bioscience Vol.24 No.12

Aflatoxins are natural contaminants of poultry feeds and feed ingredients and cause liver damage, immunosuppression, reduction in performance and mortality in broilers. A number of studies have been carried out to study the effects of aflatoxin on feed conversion ratio in broilers. The results on feed conversion ratio of 10 research articles in broilers fed with aflatoxin from first day of age to six weeks of age were compiled and were subjected to meta-analysis. Chi-square test and $Tau^2$ (heterogeneity co-efficient) were applied to test for significance of heterogeneity of studies. To integrate results, fixed effect model by Inverse Variance method (IV method) was used when heterogeneity was insignificant and otherwise random effect model by DerSimonian and Laird Method (DL method) was used. The results of meta-analysis showed that the adverse effect of aflatoxin on feed conversion ratio at the end of first week was negligible, second week was medium and third to six weeks was very large.

Dynamic performance improvement of PMSM drive using fuzzy‑based adaptive control strategy for EV applications

S. Suganthi,R. Karpagam 전력전자학회 2023 JOURNAL OF POWER ELECTRONICS Vol.23 No.3

The permanent magnet synchronous motor (PMSM) is the heart of the electric drive system in electric vehicle technology. The effects of load variation and motor parameter changes are the important key challenges, which deteriorate the dynamicperformances of interior PMSM (IPMSM) drives. To overcome these issues, this study suggests the development of anefficient new control drive system by integrating the Model Reference Adaptive Control (MRAC) with a fuzzy logic controller (FLC) using a finite-element model optimized motor model. The proposed cascaded system comprises two loops: a main outer loop that runs MRAC to mitigate the effects of load variation, and a secondary inner loop with FLC for resilient performance against parametric fluctuations of the IPMSM drive system. The proposed controller uses the hybrid space vector pulse width modulation technique to regulate the switching components of the inverter. It also reduces total harmonic distortion (THD) and torque ripple during the startup of the motor. The overall examination of the PMSM drive system is accomplished by co-simulation using MATLAB and Simcenter MAGNET software. The simulated results demonstrate the superiority of the proposed fuzzy adaptive controller in terms of higher maximum torque and improved speed tracking accuracy. A prototype of the proposed PMSM is developed and validated by experiment, which shows the robustness of the proposed methodology against load and speed fluctuations by reducing THD and torque ripples.

Stackelberg Game between Multi-Leader and Multi-Follower for Detecting Black Hole and Warm Hole Attacks In WSN

S.Suganthi,D.Usha International Journal of Computer ScienceNetwork S 2023 International journal of computer science and netw Vol.23 No.8

Objective: • To detect black hole and warm hole attacks in wireless sensor networks. • To give a solution for energy depletion and security breach in wireless sensor networks. • To address the security problem using strategic decision support system. Methods: The proposed stackelberg game is used to make the spirited relations between multi leaders and multi followers. In this game, all cluster heads are acts as leaders, whereas agent nodes are acts as followers. The game is initially modeled as Quadratic Programming and also use backtracking search optimization algorithm for getting threshold value to determine the optimal strategies of both defender and attacker. Findings: To find optimal payoffs of multi leaders and multi followers are based on their utility functions. The attacks are easily detected based on some defined rules and optimum results of the game. Finally, the simulations are executed in matlab and the impacts of detection of black hole and warm hole attacks are also presented in this paper. Novelty: The novelty of this study is to considering the stackelberg game with backtracking search optimization algorithm (BSOA). BSOA is based on iterative process which tries to minimize the objective function. Thus we obtain the better optimization results than the earlier approaches.

An Advanced Efficient Secured Blind Authentication and Verification Crypto Protocol

S. Princy Suganthi Bai,S. Selvakani Kandeeban 보안공학연구지원센터 2011 International Journal of Future Generation Communi Vol.4 No.3

An Efficient Cluster Based Service Discovery Model for Mobile Ad hoc Network

( Buvana M ),( Suganthi M ) 한국인터넷정보학회 2015 KSII Transactions on Internet and Information Syst Vol.9 No.2

1. Introduction 2. Related Work 3. Cluster Based Service Discovery Model 4. Cross Layer Integration with MAC layer for energy efficient 5. Implementation 6. Analysis 7. Experimental Results 8. Conclusion 9. References

Intraovarian Synthesis and Tissue Distribution of Hexameric Storage Protein-1 in the Ovary of Red Hairy Caterpillar, Amsacta albistriga

Chandrasekar, R.,Manohar, Suganthi L.,Krishnan, M. Korean Society of Applied Entomology 2007 Journal of Asia-Pacific Entomology Vol.10 No.3

In insects, the source of storage protein-1 (SP1) in ovaries has been the subject of controversy for several decades, and both extraovarian and intraovarian synthesized proteins have been implicated. Ovarian SP1 is presumed to contribute towards the chorion formation. The amino acid analysis of SP-1 of A. albistriga revealed that it consists of relatively high methionine content (10.9%) and is female-specific. The paper deals with the intraovarian synthesis and tissue distribution of SP1 in the pupal ovaries of A. albistriga. Northern hybridization analysis clearly demonstrates that the SP1 gene was expressed in the developing follicles, the maximum accumulation of its transcript at vitellogenic stage (day 4-8) during the mid pupal periods. Further, the result of EM studies regarding the localization of this protein in follicular epithelial cells is confirmed by immunogold labeling tracer techniques. A possible role for ovarian SP1 in A. albistriga and its relationship with SP1 synthesis by the fat body is discussed.

A Desirable Strategy for Resource Allocation using Virtual Machine in Cloud

B. Abinaya.,J. Suganthi,R. G. Suresh Kumar,T. Nalini 보안공학연구지원센터 2016 International Journal of Grid and Distributed Comp Vol.9 No.5

Cloud computing is a facsimile of legalizing ubiquitous, expedient, on-demand network access to a shared pool of configurable computing resources that can be rapidly furnished and released with negligible management effort. It relies on sharing computing resources rather than having local servers or personal devices to handle applications. The resource allocation, still lack on sustaining tools that enable developers to compare different resource allocation strategies in cloud computing. In this paper we initiate the concept of “skewness” to measure the bumpy utilization of a server. By minimizing skewness, we can improve the overall utilization of servers in the face of multidimensional resource constraints. Here we use skewness metric to combine VMs with different resource characteristics suitably so that the capacities of servers are well utilized.

Fabrication of heterostructured vanadium modified g-C3N4/TiO2 hybrid photocatalyst for improved photocatalytic performance under visible light exposure and antibacterial activities

Shanmugam Vignesh,Sanjeevamuthu Suganthi,Jeyaperumal Kalyana Sundar,Vairamuthu Raj 한국공업화학회 2019 Journal of Industrial and Engineering Chemistry Vol.76 No.-

Improving visible-light active photocatalytic performance of the heterostructured g-C3N4-V-TiO2 (g-C3N4-Vanadium-TiO2) hybrid catalyst has been synthesized via facile calcination and ultrasonicdispersion facilitated hydrothermal techniques were considered. The phase composition, morphology,surface area, chemical structure as well as optical properties were systematically characterized. HR-TEMimages were exposed good crystallinity of g-C3N4-10% V-TiO2 nanocomposite (size~35–40 nm) with VTiO2porous discrete on g-C3N4 nanosheets. Too occurred in high pore volume and large surface area(91.5 m2 g 1) of g-C3N4-10% V-TiO2 hybrid catalyst compared than pristine g-C3N4. The 10% g-C3N4-V-TiO2photocatalyst shows substantial photocatalytic activity, 5.7 and 4.8 times higher that pristine g-C3N4nanosheets and TiO2 under visible light with the degradation efficiency over 99.5% for 60 min. Besides,the recycling test specified that the g-C3N4-10% V-TiO2 photocatalyst had admirable stability up to 5sequential cycles. The trapping assessments which authorize that OH radicals and h+ plays an activerole in the degradation process and the separation of photoinduced charges transversely theheterostructure boundary reserved electron-hole recombination they were good agree with PL studies. Moreover, g-C3N4-10% V-TiO2 composite catalyst show high catalytic antibacterial activity againstEscherichia coli (G ) and the Staphylococcus aureus (G+) bacteria.

Free convective flow over a vertical plate in a doubly stratified medium with electrophoresis, heat source/sink and chemical reaction effects

Periyanagounder Ganesan,Renugopal Kanniappan Suganthi 한국화학공학회 2013 Korean Journal of Chemical Engineering Vol.30 No.4

We analyzed the problem of unsteady, incompressible free convective doubly stratified flow past a semiinfinite vertical plate with the influence of electrophoresis, heat source/sink and chemical reaction. The partial differential equations governing the flow are solved by employing an implicit finite difference scheme of Crank-Nicolson type. The effect of heat generation and absorption in stratified and unstratified flow are examined and hence the influence of stratification on velocity, temperature and concentration are investigated and presented graphically. Further, the impact of the electrophoresis on particle concentration in the presence of generative and destructive reaction is analyzed. As well, the effects of the physical parameters on local and average values of skin friction, Nusselt number and Sherwood number are also investigated and illustrated graphically. The particular solutions of the present results are compared with the existing solution in literature and are found to be in good agreement.